Re: Linux 4.14.34

[Greg KH]

diff --git a/Makefile b/Makefile
index 00dd6af8eab4..a6906dfb112e 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 4
 PATCHLEVEL = 14
-SUBLEVEL = 33
+SUBLEVEL = 34
 EXTRAVERSION =
 NAME = Petit Gorille
 
diff --git a/arch/arm/boot/dts/ls1021a.dtsi b/arch/arm/boot/dts/ls1021a.dtsi
index 9319e1f0f1d8..379b4a03cfe2 100644
--- a/arch/arm/boot/dts/ls1021a.dtsi
+++ b/arch/arm/boot/dts/ls1021a.dtsi
@@ -155,7 +155,7 @@
 		};
 
 		esdhc: esdhc@1560000 {
-			compatible = "fsl,esdhc";
+			compatible = "fsl,ls1021a-esdhc", "fsl,esdhc";
 			reg = <0x0 0x1560000 0x0 0x10000>;
 			interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>;
 			clock-frequency = <0>;
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index 12fd81af1d1c..93dbf4889eb6 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -24,7 +24,7 @@ obj-$(CONFIG_CRYPTO_CRC32_ARM64_CE) += crc32-ce.o
 crc32-ce-y:= crc32-ce-core.o crc32-ce-glue.o
 
 obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o
-CFLAGS_aes-ce-cipher.o += -march=armv8-a+crypto
+aes-ce-cipher-y := aes-ce-core.o aes-ce-glue.o
 
 obj-$(CONFIG_CRYPTO_AES_ARM64_CE_CCM) += aes-ce-ccm.o
 aes-ce-ccm-y := aes-ce-ccm-glue.o aes-ce-ccm-core.o
diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher.c
deleted file mode 100644
index 6a75cd75ed11..000000000000
--- a/arch/arm64/crypto/aes-ce-cipher.c
+++ /dev/null
@@ -1,281 +0,0 @@
-/*
- * aes-ce-cipher.c - core AES cipher using ARMv8 Crypto Extensions
- *
- * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@xxxxxxxxxx>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <asm/neon.h>
-#include <asm/simd.h>
-#include <asm/unaligned.h>
-#include <crypto/aes.h>
-#include <linux/cpufeature.h>
-#include <linux/crypto.h>
-#include <linux/module.h>
-
-#include "aes-ce-setkey.h"
-
-MODULE_DESCRIPTION("Synchronous AES cipher using ARMv8 Crypto Extensions");
-MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@xxxxxxxxxx>");
-MODULE_LICENSE("GPL v2");
-
-asmlinkage void __aes_arm64_encrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
-asmlinkage void __aes_arm64_decrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
-
-struct aes_block {
-	u8 b[AES_BLOCK_SIZE];
-};
-
-static int num_rounds(struct crypto_aes_ctx *ctx)
-{
-	/*
-	 * # of rounds specified by AES:
-	 * 128 bit key		10 rounds
-	 * 192 bit key		12 rounds
-	 * 256 bit key		14 rounds
-	 * => n byte key	=> 6 + (n/4) rounds
-	 */
-	return 6 + ctx->key_length / 4;
-}
-
-static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
-{
-	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct aes_block *out = (struct aes_block *)dst;
-	struct aes_block const *in = (struct aes_block *)src;
-	void *dummy0;
-	int dummy1;
-
-	if (!may_use_simd()) {
-		__aes_arm64_encrypt(ctx->key_enc, dst, src, num_rounds(ctx));
-		return;
-	}
-
-	kernel_neon_begin();
-
-	__asm__("	ld1	{v0.16b}, %[in]			;"
-		"	ld1	{v1.4s}, [%[key]], #16		;"
-		"	cmp	%w[rounds], #10			;"
-		"	bmi	0f				;"
-		"	bne	3f				;"
-		"	mov	v3.16b, v1.16b			;"
-		"	b	2f				;"
-		"0:	mov	v2.16b, v1.16b			;"
-		"	ld1	{v3.4s}, [%[key]], #16		;"
-		"1:	aese	v0.16b, v2.16b			;"
-		"	aesmc	v0.16b, v0.16b			;"
-		"2:	ld1	{v1.4s}, [%[key]], #16		;"
-		"	aese	v0.16b, v3.16b			;"
-		"	aesmc	v0.16b, v0.16b			;"
-		"3:	ld1	{v2.4s}, [%[key]], #16		;"
-		"	subs	%w[rounds], %w[rounds], #3	;"
-		"	aese	v0.16b, v1.16b			;"
-		"	aesmc	v0.16b, v0.16b			;"
-		"	ld1	{v3.4s}, [%[key]], #16		;"
-		"	bpl	1b				;"
-		"	aese	v0.16b, v2.16b			;"
-		"	eor	v0.16b, v0.16b, v3.16b		;"
-		"	st1	{v0.16b}, %[out]		;"
-
-	:	[out]		"=Q"(*out),
-		[key]		"=r"(dummy0),
-		[rounds]	"=r"(dummy1)
-	:	[in]		"Q"(*in),
-				"1"(ctx->key_enc),
-				"2"(num_rounds(ctx) - 2)
-	:	"cc");
-
-	kernel_neon_end();
-}
-
-static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
-{
-	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct aes_block *out = (struct aes_block *)dst;
-	struct aes_block const *in = (struct aes_block *)src;
-	void *dummy0;
-	int dummy1;
-
-	if (!may_use_simd()) {
-		__aes_arm64_decrypt(ctx->key_dec, dst, src, num_rounds(ctx));
-		return;
-	}
-
-	kernel_neon_begin();
-
-	__asm__("	ld1	{v0.16b}, %[in]			;"
-		"	ld1	{v1.4s}, [%[key]], #16		;"
-		"	cmp	%w[rounds], #10			;"
-		"	bmi	0f				;"
-		"	bne	3f				;"
-		"	mov	v3.16b, v1.16b			;"
-		"	b	2f				;"
-		"0:	mov	v2.16b, v1.16b			;"
-		"	ld1	{v3.4s}, [%[key]], #16		;"
-		"1:	aesd	v0.16b, v2.16b			;"
-		"	aesimc	v0.16b, v0.16b			;"
-		"2:	ld1	{v1.4s}, [%[key]], #16		;"
-		"	aesd	v0.16b, v3.16b			;"
-		"	aesimc	v0.16b, v0.16b			;"
-		"3:	ld1	{v2.4s}, [%[key]], #16		;"
-		"	subs	%w[rounds], %w[rounds], #3	;"
-		"	aesd	v0.16b, v1.16b			;"
-		"	aesimc	v0.16b, v0.16b			;"
-		"	ld1	{v3.4s}, [%[key]], #16		;"
-		"	bpl	1b				;"
-		"	aesd	v0.16b, v2.16b			;"
-		"	eor	v0.16b, v0.16b, v3.16b		;"
-		"	st1	{v0.16b}, %[out]		;"
-
-	:	[out]		"=Q"(*out),
-		[key]		"=r"(dummy0),
-		[rounds]	"=r"(dummy1)
-	:	[in]		"Q"(*in),
-				"1"(ctx->key_dec),
-				"2"(num_rounds(ctx) - 2)
-	:	"cc");
-
-	kernel_neon_end();
-}
-
-/*
- * aes_sub() - use the aese instruction to perform the AES sbox substitution
- *             on each byte in 'input'
- */
-static u32 aes_sub(u32 input)
-{
-	u32 ret;
-
-	__asm__("dup	v1.4s, %w[in]		;"
-		"movi	v0.16b, #0		;"
-		"aese	v0.16b, v1.16b		;"
-		"umov	%w[out], v0.4s[0]	;"
-
-	:	[out]	"=r"(ret)
-	:	[in]	"r"(input)
-	:		"v0","v1");
-
-	return ret;
-}
-
-int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
-		     unsigned int key_len)
-{
-	/*
-	 * The AES key schedule round constants
-	 */
-	static u8 const rcon[] = {
-		0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36,
-	};
-
-	u32 kwords = key_len / sizeof(u32);
-	struct aes_block *key_enc, *key_dec;
-	int i, j;
-
-	if (key_len != AES_KEYSIZE_128 &&
-	    key_len != AES_KEYSIZE_192 &&
-	    key_len != AES_KEYSIZE_256)
-		return -EINVAL;
-
-	ctx->key_length = key_len;
-	for (i = 0; i < kwords; i++)
-		ctx->key_enc[i] = get_unaligned_le32(in_key + i * sizeof(u32));
-
-	kernel_neon_begin();
-	for (i = 0; i < sizeof(rcon); i++) {
-		u32 *rki = ctx->key_enc + (i * kwords);
-		u32 *rko = rki + kwords;
-
-		rko[0] = ror32(aes_sub(rki[kwords - 1]), 8) ^ rcon[i] ^ rki[0];
-		rko[1] = rko[0] ^ rki[1];
-		rko[2] = rko[1] ^ rki[2];
-		rko[3] = rko[2] ^ rki[3];
-
-		if (key_len == AES_KEYSIZE_192) {
-			if (i >= 7)
-				break;
-			rko[4] = rko[3] ^ rki[4];
-			rko[5] = rko[4] ^ rki[5];
-		} else if (key_len == AES_KEYSIZE_256) {
-			if (i >= 6)
-				break;
-			rko[4] = aes_sub(rko[3]) ^ rki[4];
-			rko[5] = rko[4] ^ rki[5];
-			rko[6] = rko[5] ^ rki[6];
-			rko[7] = rko[6] ^ rki[7];
-		}
-	}
-
-	/*
-	 * Generate the decryption keys for the Equivalent Inverse Cipher.
-	 * This involves reversing the order of the round keys, and applying
-	 * the Inverse Mix Columns transformation on all but the first and
-	 * the last one.
-	 */
-	key_enc = (struct aes_block *)ctx->key_enc;
-	key_dec = (struct aes_block *)ctx->key_dec;
-	j = num_rounds(ctx);
-
-	key_dec[0] = key_enc[j];
-	for (i = 1, j--; j > 0; i++, j--)
-		__asm__("ld1	{v0.4s}, %[in]		;"
-			"aesimc	v1.16b, v0.16b		;"
-			"st1	{v1.4s}, %[out]	;"
-
-		:	[out]	"=Q"(key_dec[i])
-		:	[in]	"Q"(key_enc[j])
-		:		"v0","v1");
-	key_dec[i] = key_enc[0];
-
-	kernel_neon_end();
-	return 0;
-}
-EXPORT_SYMBOL(ce_aes_expandkey);
-
-int ce_aes_setkey(struct crypto_tfm *tfm, const u8 *in_key,
-		  unsigned int key_len)
-{
-	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
-	int ret;
-
-	ret = ce_aes_expandkey(ctx, in_key, key_len);
-	if (!ret)
-		return 0;
-
-	tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-	return -EINVAL;
-}
-EXPORT_SYMBOL(ce_aes_setkey);
-
-static struct crypto_alg aes_alg = {
-	.cra_name		= "aes",
-	.cra_driver_name	= "aes-ce",
-	.cra_priority		= 250,
-	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
-	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
-	.cra_module		= THIS_MODULE,
-	.cra_cipher = {
-		.cia_min_keysize	= AES_MIN_KEY_SIZE,
-		.cia_max_keysize	= AES_MAX_KEY_SIZE,
-		.cia_setkey		= ce_aes_setkey,
-		.cia_encrypt		= aes_cipher_encrypt,
-		.cia_decrypt		= aes_cipher_decrypt
-	}
-};
-
-static int __init aes_mod_init(void)
-{
-	return crypto_register_alg(&aes_alg);
-}
-
-static void __exit aes_mod_exit(void)
-{
-	crypto_unregister_alg(&aes_alg);
-}
-
-module_cpu_feature_match(AES, aes_mod_init);
-module_exit(aes_mod_exit);
diff --git a/arch/arm64/crypto/aes-ce-core.S b/arch/arm64/crypto/aes-ce-core.S
new file mode 100644
index 000000000000..8efdfdade393
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-core.S
@@ -0,0 +1,87 @@
+/*
+ * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@xxxxxxxxxx>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.arch		armv8-a+crypto
+
+ENTRY(__aes_ce_encrypt)
+	sub		w3, w3, #2
+	ld1		{v0.16b}, [x2]
+	ld1		{v1.4s}, [x0], #16
+	cmp		w3, #10
+	bmi		0f
+	bne		3f
+	mov		v3.16b, v1.16b
+	b		2f
+0:	mov		v2.16b, v1.16b
+	ld1		{v3.4s}, [x0], #16
+1:	aese		v0.16b, v2.16b
+	aesmc		v0.16b, v0.16b
+2:	ld1		{v1.4s}, [x0], #16
+	aese		v0.16b, v3.16b
+	aesmc		v0.16b, v0.16b
+3:	ld1		{v2.4s}, [x0], #16
+	subs		w3, w3, #3
+	aese		v0.16b, v1.16b
+	aesmc		v0.16b, v0.16b
+	ld1		{v3.4s}, [x0], #16
+	bpl		1b
+	aese		v0.16b, v2.16b
+	eor		v0.16b, v0.16b, v3.16b
+	st1		{v0.16b}, [x1]
+	ret
+ENDPROC(__aes_ce_encrypt)
+
+ENTRY(__aes_ce_decrypt)
+	sub		w3, w3, #2
+	ld1		{v0.16b}, [x2]
+	ld1		{v1.4s}, [x0], #16
+	cmp		w3, #10
+	bmi		0f
+	bne		3f
+	mov		v3.16b, v1.16b
+	b		2f
+0:	mov		v2.16b, v1.16b
+	ld1		{v3.4s}, [x0], #16
+1:	aesd		v0.16b, v2.16b
+	aesimc		v0.16b, v0.16b
+2:	ld1		{v1.4s}, [x0], #16
+	aesd		v0.16b, v3.16b
+	aesimc		v0.16b, v0.16b
+3:	ld1		{v2.4s}, [x0], #16
+	subs		w3, w3, #3
+	aesd		v0.16b, v1.16b
+	aesimc		v0.16b, v0.16b
+	ld1		{v3.4s}, [x0], #16
+	bpl		1b
+	aesd		v0.16b, v2.16b
+	eor		v0.16b, v0.16b, v3.16b
+	st1		{v0.16b}, [x1]
+	ret
+ENDPROC(__aes_ce_decrypt)
+
+/*
+ * __aes_ce_sub() - use the aese instruction to perform the AES sbox
+ *                  substitution on each byte in 'input'
+ */
+ENTRY(__aes_ce_sub)
+	dup		v1.4s, w0
+	movi		v0.16b, #0
+	aese		v0.16b, v1.16b
+	umov		w0, v0.s[0]
+	ret
+ENDPROC(__aes_ce_sub)
+
+ENTRY(__aes_ce_invert)
+	ld1		{v0.4s}, [x1]
+	aesimc		v1.16b, v0.16b
+	st1		{v1.4s}, [x0]
+	ret
+ENDPROC(__aes_ce_invert)
diff --git a/arch/arm64/crypto/aes-ce-glue.c b/arch/arm64/crypto/aes-ce-glue.c
new file mode 100644
index 000000000000..e6b3227bbf57
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-glue.c
@@ -0,0 +1,190 @@
+/*
+ * aes-ce-cipher.c - core AES cipher using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@xxxxxxxxxx>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/aes.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+#include "aes-ce-setkey.h"
+
+MODULE_DESCRIPTION("Synchronous AES cipher using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@xxxxxxxxxx>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage void __aes_arm64_encrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+asmlinkage void __aes_arm64_decrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+
+struct aes_block {
+	u8 b[AES_BLOCK_SIZE];
+};
+
+asmlinkage void __aes_ce_encrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+asmlinkage void __aes_ce_decrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+
+asmlinkage u32 __aes_ce_sub(u32 l);
+asmlinkage void __aes_ce_invert(struct aes_block *out,
+				const struct aes_block *in);
+
+static int num_rounds(struct crypto_aes_ctx *ctx)
+{
+	/*
+	 * # of rounds specified by AES:
+	 * 128 bit key		10 rounds
+	 * 192 bit key		12 rounds
+	 * 256 bit key		14 rounds
+	 * => n byte key	=> 6 + (n/4) rounds
+	 */
+	return 6 + ctx->key_length / 4;
+}
+
+static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!may_use_simd()) {
+		__aes_arm64_encrypt(ctx->key_enc, dst, src, num_rounds(ctx));
+		return;
+	}
+
+	kernel_neon_begin();
+	__aes_ce_encrypt(ctx->key_enc, dst, src, num_rounds(ctx));
+	kernel_neon_end();
+}
+
+static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!may_use_simd()) {
+		__aes_arm64_decrypt(ctx->key_dec, dst, src, num_rounds(ctx));
+		return;
+	}
+
+	kernel_neon_begin();
+	__aes_ce_decrypt(ctx->key_dec, dst, src, num_rounds(ctx));
+	kernel_neon_end();
+}
+
+int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
+		     unsigned int key_len)
+{
+	/*
+	 * The AES key schedule round constants
+	 */
+	static u8 const rcon[] = {
+		0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36,
+	};
+
+	u32 kwords = key_len / sizeof(u32);
+	struct aes_block *key_enc, *key_dec;
+	int i, j;
+
+	if (key_len != AES_KEYSIZE_128 &&
+	    key_len != AES_KEYSIZE_192 &&
+	    key_len != AES_KEYSIZE_256)
+		return -EINVAL;
+
+	ctx->key_length = key_len;
+	for (i = 0; i < kwords; i++)
+		ctx->key_enc[i] = get_unaligned_le32(in_key + i * sizeof(u32));
+
+	kernel_neon_begin();
+	for (i = 0; i < sizeof(rcon); i++) {
+		u32 *rki = ctx->key_enc + (i * kwords);
+		u32 *rko = rki + kwords;
+
+		rko[0] = ror32(__aes_ce_sub(rki[kwords - 1]), 8) ^ rcon[i] ^ rki[0];
+		rko[1] = rko[0] ^ rki[1];
+		rko[2] = rko[1] ^ rki[2];
+		rko[3] = rko[2] ^ rki[3];
+
+		if (key_len == AES_KEYSIZE_192) {
+			if (i >= 7)
+				break;
+			rko[4] = rko[3] ^ rki[4];
+			rko[5] = rko[4] ^ rki[5];
+		} else if (key_len == AES_KEYSIZE_256) {
+			if (i >= 6)
+				break;
+			rko[4] = __aes_ce_sub(rko[3]) ^ rki[4];
+			rko[5] = rko[4] ^ rki[5];
+			rko[6] = rko[5] ^ rki[6];
+			rko[7] = rko[6] ^ rki[7];
+		}
+	}
+
+	/*
+	 * Generate the decryption keys for the Equivalent Inverse Cipher.
+	 * This involves reversing the order of the round keys, and applying
+	 * the Inverse Mix Columns transformation on all but the first and
+	 * the last one.
+	 */
+	key_enc = (struct aes_block *)ctx->key_enc;
+	key_dec = (struct aes_block *)ctx->key_dec;
+	j = num_rounds(ctx);
+
+	key_dec[0] = key_enc[j];
+	for (i = 1, j--; j > 0; i++, j--)
+		__aes_ce_invert(key_dec + i, key_enc + j);
+	key_dec[i] = key_enc[0];
+
+	kernel_neon_end();
+	return 0;
+}
+EXPORT_SYMBOL(ce_aes_expandkey);
+
+int ce_aes_setkey(struct crypto_tfm *tfm, const u8 *in_key,
+		  unsigned int key_len)
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	int ret;
+
+	ret = ce_aes_expandkey(ctx, in_key, key_len);
+	if (!ret)
+		return 0;
+
+	tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+	return -EINVAL;
+}
+EXPORT_SYMBOL(ce_aes_setkey);
+
+static struct crypto_alg aes_alg = {
+	.cra_name		= "aes",
+	.cra_driver_name	= "aes-ce",
+	.cra_priority		= 250,
+	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_module		= THIS_MODULE,
+	.cra_cipher = {
+		.cia_min_keysize	= AES_MIN_KEY_SIZE,
+		.cia_max_keysize	= AES_MAX_KEY_SIZE,
+		.cia_setkey		= ce_aes_setkey,
+		.cia_encrypt		= aes_cipher_encrypt,
+		.cia_decrypt		= aes_cipher_decrypt
+	}
+};
+
+static int __init aes_mod_init(void)
+{
+	return crypto_register_alg(&aes_alg);
+}
+
+static void __exit aes_mod_exit(void)
+{
+	crypto_unregister_alg(&aes_alg);
+}
+
+module_cpu_feature_match(AES, aes_mod_init);
+module_exit(aes_mod_exit);
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 55520cec8b27..6cf0e4cb7b97 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -37,7 +37,13 @@ struct cpu_signature {
 
 struct device;
 
-enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND };
+enum ucode_state {
+	UCODE_OK	= 0,
+	UCODE_NEW,
+	UCODE_UPDATED,
+	UCODE_NFOUND,
+	UCODE_ERROR,
+};
 
 struct microcode_ops {
 	enum ucode_state (*request_microcode_user) (int cpu,
@@ -54,7 +60,7 @@ struct microcode_ops {
 	 * are being called.
 	 * See also the "Synchronization" section in microcode_core.c.
 	 */
-	int (*apply_microcode) (int cpu);
+	enum ucode_state (*apply_microcode) (int cpu);
 	int (*collect_cpu_info) (int cpu, struct cpu_signature *csig);
 };
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 15fc074bd628..3222c7746cb1 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -968,4 +968,5 @@ bool xen_set_default_idle(void);
 
 void stop_this_cpu(void *dummy);
 void df_debug(struct pt_regs *regs, long error_code);
+void microcode_check(void);
 #endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index f5d92bc3b884..2c4d5ece7456 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -30,6 +30,7 @@
 #include <asm/dma.h>
 #include <asm/amd_nb.h>
 #include <asm/x86_init.h>
+#include <linux/crash_dump.h>
 
 /*
  * Using 512M as goal, in case kexec will load kernel_big
@@ -56,6 +57,33 @@ int fallback_aper_force __initdata;
 
 int fix_aperture __initdata = 1;
 
+#ifdef CONFIG_PROC_VMCORE
+/*
+ * If the first kernel maps the aperture over e820 RAM, the kdump kernel will
+ * use the same range because it will remain configured in the northbridge.
+ * Trying to dump this area via /proc/vmcore may crash the machine, so exclude
+ * it from vmcore.
+ */
+static unsigned long aperture_pfn_start, aperture_page_count;
+
+static int gart_oldmem_pfn_is_ram(unsigned long pfn)
+{
+	return likely((pfn < aperture_pfn_start) ||
+		      (pfn >= aperture_pfn_start + aperture_page_count));
+}
+
+static void exclude_from_vmcore(u64 aper_base, u32 aper_order)
+{
+	aperture_pfn_start = aper_base >> PAGE_SHIFT;
+	aperture_page_count = (32 * 1024 * 1024) << aper_order >> PAGE_SHIFT;
+	WARN_ON(register_oldmem_pfn_is_ram(&gart_oldmem_pfn_is_ram));
+}
+#else
+static void exclude_from_vmcore(u64 aper_base, u32 aper_order)
+{
+}
+#endif
+
 /* This code runs before the PCI subsystem is initialized, so just
    access the northbridge directly. */
 
@@ -435,8 +463,16 @@ int __init gart_iommu_hole_init(void)
 
 out:
 	if (!fix && !fallback_aper_force) {
-		if (last_aper_base)
+		if (last_aper_base) {
+			/*
+			 * If this is the kdump kernel, the first kernel
+			 * may have allocated the range over its e820 RAM
+			 * and fixed up the northbridge
+			 */
+			exclude_from_vmcore(last_aper_base, last_aper_order);
+
 			return 1;
+		}
 		return 0;
 	}
 
@@ -473,6 +509,14 @@ int __init gart_iommu_hole_init(void)
 		return 0;
 	}
 
+	/*
+	 * If this is the kdump kernel _and_ the first kernel did not
+	 * configure the aperture in the northbridge, this range may
+	 * overlap with the first kernel's memory. We can't access the
+	 * range through vmcore even though it should be part of the dump.
+	 */
+	exclude_from_vmcore(aper_alloc, aper_order);
+
 	/* Fix up the north bridges */
 	for (i = 0; i < amd_nb_bus_dev_ranges[i].dev_limit; i++) {
 		int bus, dev_base, dev_limit;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 651b7afed4da..cf6380200dc2 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1724,3 +1724,33 @@ static int __init init_cpu_syscore(void)
 	return 0;
 }
 core_initcall(init_cpu_syscore);
+
+/*
+ * The microcode loader calls this upon late microcode load to recheck features,
+ * only when microcode has been updated. Caller holds microcode_mutex and CPU
+ * hotplug lock.
+ */
+void microcode_check(void)
+{
+	struct cpuinfo_x86 info;
+
+	perf_check_microcode();
+
+	/* Reload CPUID max function as it might've changed. */
+	info.cpuid_level = cpuid_eax(0);
+
+	/*
+	 * Copy all capability leafs to pick up the synthetic ones so that
+	 * memcmp() below doesn't fail on that. The ones coming from CPUID will
+	 * get overwritten in get_cpu_cap().
+	 */
+	memcpy(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability));
+
+	get_cpu_cap(&info);
+
+	if (!memcmp(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability)))
+		return;
+
+	pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n");
+	pr_warn("x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update.\n");
+}
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 330b8462d426..48179928ff38 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -339,7 +339,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
 		return -EINVAL;
 
 	ret = load_microcode_amd(true, x86_family(cpuid_1_eax), desc.data, desc.size);
-	if (ret != UCODE_OK)
+	if (ret > UCODE_UPDATED)
 		return -EINVAL;
 
 	return 0;
@@ -498,7 +498,7 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size,
 	return patch_size;
 }
 
-static int apply_microcode_amd(int cpu)
+static enum ucode_state apply_microcode_amd(int cpu)
 {
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct microcode_amd *mc_amd;
@@ -512,7 +512,7 @@ static int apply_microcode_amd(int cpu)
 
 	p = find_patch(cpu);
 	if (!p)
-		return 0;
+		return UCODE_NFOUND;
 
 	mc_amd  = p->data;
 	uci->mc = p->data;
@@ -523,13 +523,13 @@ static int apply_microcode_amd(int cpu)
 	if (rev >= mc_amd->hdr.patch_id) {
 		c->microcode = rev;
 		uci->cpu_sig.rev = rev;
-		return 0;
+		return UCODE_OK;
 	}
 
 	if (__apply_microcode_amd(mc_amd)) {
 		pr_err("CPU%d: update failed for patch_level=0x%08x\n",
 			cpu, mc_amd->hdr.patch_id);
-		return -1;
+		return UCODE_ERROR;
 	}
 	pr_info("CPU%d: new patch_level=0x%08x\n", cpu,
 		mc_amd->hdr.patch_id);
@@ -537,7 +537,7 @@ static int apply_microcode_amd(int cpu)
 	uci->cpu_sig.rev = mc_amd->hdr.patch_id;
 	c->microcode = mc_amd->hdr.patch_id;
 
-	return 0;
+	return UCODE_UPDATED;
 }
 
 static int install_equiv_cpu_table(const u8 *buf)
@@ -683,27 +683,35 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
 static enum ucode_state
 load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
 {
+	struct ucode_patch *p;
 	enum ucode_state ret;
 
 	/* free old equiv table */
 	free_equiv_cpu_table();
 
 	ret = __load_microcode_amd(family, data, size);
-
-	if (ret != UCODE_OK)
+	if (ret != UCODE_OK) {
 		cleanup();
+		return ret;
+	}
 
-#ifdef CONFIG_X86_32
-	/* save BSP's matching patch for early load */
-	if (save) {
-		struct ucode_patch *p = find_patch(0);
-		if (p) {
-			memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
-			memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data),
-							       PATCH_MAX_SIZE));
-		}
+	p = find_patch(0);
+	if (!p) {
+		return ret;
+	} else {
+		if (boot_cpu_data.microcode == p->patch_id)
+			return ret;
+
+		ret = UCODE_NEW;
 	}
-#endif
+
+	/* save BSP's matching patch for early load */
+	if (!save)
+		return ret;
+
+	memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
+	memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), PATCH_MAX_SIZE));
+
 	return ret;
 }
 
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index e4fc595cd6ea..021c90464cc2 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -22,13 +22,16 @@
 #define pr_fmt(fmt) "microcode: " fmt
 
 #include <linux/platform_device.h>
+#include <linux/stop_machine.h>
 #include <linux/syscore_ops.h>
 #include <linux/miscdevice.h>
 #include <linux/capability.h>
 #include <linux/firmware.h>
 #include <linux/kernel.h>
+#include <linux/delay.h>
 #include <linux/mutex.h>
 #include <linux/cpu.h>
+#include <linux/nmi.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
 
@@ -64,6 +67,11 @@ LIST_HEAD(microcode_cache);
  */
 static DEFINE_MUTEX(microcode_mutex);
 
+/*
+ * Serialize late loading so that CPUs get updated one-by-one.
+ */
+static DEFINE_SPINLOCK(update_lock);
+
 struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
 
 struct cpu_info_ctx {
@@ -373,26 +381,23 @@ static int collect_cpu_info(int cpu)
 	return ret;
 }
 
-struct apply_microcode_ctx {
-	int err;
-};
-
 static void apply_microcode_local(void *arg)
 {
-	struct apply_microcode_ctx *ctx = arg;
+	enum ucode_state *err = arg;
 
-	ctx->err = microcode_ops->apply_microcode(smp_processor_id());
+	*err = microcode_ops->apply_microcode(smp_processor_id());
 }
 
 static int apply_microcode_on_target(int cpu)
 {
-	struct apply_microcode_ctx ctx = { .err = 0 };
+	enum ucode_state err;
 	int ret;
 
-	ret = smp_call_function_single(cpu, apply_microcode_local, &ctx, 1);
-	if (!ret)
-		ret = ctx.err;
-
+	ret = smp_call_function_single(cpu, apply_microcode_local, &err, 1);
+	if (!ret) {
+		if (err == UCODE_ERROR)
+			ret = 1;
+	}
 	return ret;
 }
 
@@ -489,31 +494,124 @@ static void __exit microcode_dev_exit(void)
 /* fake device for request_firmware */
 static struct platform_device	*microcode_pdev;
 
-static int reload_for_cpu(int cpu)
+/*
+ * Late loading dance. Why the heavy-handed stomp_machine effort?
+ *
+ * - HT siblings must be idle and not execute other code while the other sibling
+ *   is loading microcode in order to avoid any negative interactions caused by
+ *   the loading.
+ *
+ * - In addition, microcode update on the cores must be serialized until this
+ *   requirement can be relaxed in the future. Right now, this is conservative
+ *   and good.
+ */
+#define SPINUNIT 100 /* 100 nsec */
+
+static int check_online_cpus(void)
 {
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	enum ucode_state ustate;
-	int err = 0;
+	if (num_online_cpus() == num_present_cpus())
+		return 0;
 
-	if (!uci->valid)
-		return err;
+	pr_err("Not all CPUs online, aborting microcode update.\n");
 
-	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev, true);
-	if (ustate == UCODE_OK)
-		apply_microcode_on_target(cpu);
-	else
-		if (ustate == UCODE_ERROR)
-			err = -EINVAL;
-	return err;
+	return -EINVAL;
+}
+
+static atomic_t late_cpus_in;
+static atomic_t late_cpus_out;
+
+static int __wait_for_cpus(atomic_t *t, long long timeout)
+{
+	int all_cpus = num_online_cpus();
+
+	atomic_inc(t);
+
+	while (atomic_read(t) < all_cpus) {
+		if (timeout < SPINUNIT) {
+			pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n",
+				all_cpus - atomic_read(t));
+			return 1;
+		}
+
+		ndelay(SPINUNIT);
+		timeout -= SPINUNIT;
+
+		touch_nmi_watchdog();
+	}
+	return 0;
+}
+
+/*
+ * Returns:
+ * < 0 - on error
+ *   0 - no update done
+ *   1 - microcode was updated
+ */
+static int __reload_late(void *info)
+{
+	int cpu = smp_processor_id();
+	enum ucode_state err;
+	int ret = 0;
+
+	/*
+	 * Wait for all CPUs to arrive. A load will not be attempted unless all
+	 * CPUs show up.
+	 * */
+	if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC))
+		return -1;
+
+	spin_lock(&update_lock);
+	apply_microcode_local(&err);
+	spin_unlock(&update_lock);
+
+	if (err > UCODE_NFOUND) {
+		pr_warn("Error reloading microcode on CPU %d\n", cpu);
+		return -1;
+	/* siblings return UCODE_OK because their engine got updated already */
+	} else if (err == UCODE_UPDATED || err == UCODE_OK) {
+		ret = 1;
+	} else {
+		return ret;
+	}
+
+	/*
+	 * Increase the wait timeout to a safe value here since we're
+	 * serializing the microcode update and that could take a while on a
+	 * large number of CPUs. And that is fine as the *actual* timeout will
+	 * be determined by the last CPU finished updating and thus cut short.
+	 */
+	if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC * num_online_cpus()))
+		panic("Timeout during microcode update!\n");
+
+	return ret;
+}
+
+/*
+ * Reload microcode late on all CPUs. Wait for a sec until they
+ * all gather together.
+ */
+static int microcode_reload_late(void)
+{
+	int ret;
+
+	atomic_set(&late_cpus_in,  0);
+	atomic_set(&late_cpus_out, 0);
+
+	ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask);
+	if (ret > 0)
+		microcode_check();
+
+	return ret;
 }
 
 static ssize_t reload_store(struct device *dev,
 			    struct device_attribute *attr,
 			    const char *buf, size_t size)
 {
+	enum ucode_state tmp_ret = UCODE_OK;
+	int bsp = boot_cpu_data.cpu_index;
 	unsigned long val;
-	int cpu;
-	ssize_t ret = 0, tmp_ret;
+	ssize_t ret = 0;
 
 	ret = kstrtoul(buf, 0, &val);
 	if (ret)
@@ -522,23 +620,24 @@ static ssize_t reload_store(struct device *dev,
 	if (val != 1)
 		return size;
 
+	tmp_ret = microcode_ops->request_microcode_fw(bsp, &microcode_pdev->dev, true);
+	if (tmp_ret != UCODE_NEW)
+		return size;
+
 	get_online_cpus();
-	mutex_lock(&microcode_mutex);
-	for_each_online_cpu(cpu) {
-		tmp_ret = reload_for_cpu(cpu);
-		if (tmp_ret != 0)
-			pr_warn("Error reloading microcode on CPU %d\n", cpu);
 
-		/* save retval of the first encountered reload error */
-		if (!ret)
-			ret = tmp_ret;
-	}
-	if (!ret)
-		perf_check_microcode();
+	ret = check_online_cpus();
+	if (ret)
+		goto put;
+
+	mutex_lock(&microcode_mutex);
+	ret = microcode_reload_late();
 	mutex_unlock(&microcode_mutex);
+
+put:
 	put_online_cpus();
 
-	if (!ret)
+	if (ret >= 0)
 		ret = size;
 
 	return ret;
@@ -606,10 +705,8 @@ static enum ucode_state microcode_init_cpu(int cpu, bool refresh_fw)
 	if (system_state != SYSTEM_RUNNING)
 		return UCODE_NFOUND;
 
-	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev,
-						     refresh_fw);
-
-	if (ustate == UCODE_OK) {
+	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev, refresh_fw);
+	if (ustate == UCODE_NEW) {
 		pr_debug("CPU%d updated upon init\n", cpu);
 		apply_microcode_on_target(cpu);
 	}
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index a15db2b4e0d6..32b8e5724f96 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -589,6 +589,23 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
 	if (!mc)
 		return 0;
 
+	/*
+	 * Save us the MSR write below - which is a particular expensive
+	 * operation - when the other hyperthread has updated the microcode
+	 * already.
+	 */
+	rev = intel_get_microcode_revision();
+	if (rev >= mc->hdr.rev) {
+		uci->cpu_sig.rev = rev;
+		return UCODE_OK;
+	}
+
+	/*
+	 * Writeback and invalidate caches before updating microcode to avoid
+	 * internal issues depending on what the microcode is updating.
+	 */
+	native_wbinvd();
+
 	/* write microcode via MSR 0x79 */
 	native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
 
@@ -772,27 +789,44 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
 	return 0;
 }
 
-static int apply_microcode_intel(int cpu)
+static enum ucode_state apply_microcode_intel(int cpu)
 {
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct microcode_intel *mc;
-	struct ucode_cpu_info *uci;
-	struct cpuinfo_x86 *c;
 	static int prev_rev;
 	u32 rev;
 
 	/* We should bind the task to the CPU */
 	if (WARN_ON(raw_smp_processor_id() != cpu))
-		return -1;
+		return UCODE_ERROR;
 
-	uci = ucode_cpu_info + cpu;
-	mc = uci->mc;
+	/* Look for a newer patch in our cache: */
+	mc = find_patch(uci);
 	if (!mc) {
-		/* Look for a newer patch in our cache: */
-		mc = find_patch(uci);
+		mc = uci->mc;
 		if (!mc)
-			return 0;
+			return UCODE_NFOUND;
 	}
 
+	/*
+	 * Save us the MSR write below - which is a particular expensive
+	 * operation - when the other hyperthread has updated the microcode
+	 * already.
+	 */
+	rev = intel_get_microcode_revision();
+	if (rev >= mc->hdr.rev) {
+		uci->cpu_sig.rev = rev;
+		c->microcode = rev;
+		return UCODE_OK;
+	}
+
+	/*
+	 * Writeback and invalidate caches before updating microcode to avoid
+	 * internal issues depending on what the microcode is updating.
+	 */
+	native_wbinvd();
+
 	/* write microcode via MSR 0x79 */
 	wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
 
@@ -801,7 +835,7 @@ static int apply_microcode_intel(int cpu)
 	if (rev != mc->hdr.rev) {
 		pr_err("CPU%d update to revision 0x%x failed\n",
 		       cpu, mc->hdr.rev);
-		return -1;
+		return UCODE_ERROR;
 	}
 
 	if (rev != prev_rev) {
@@ -813,12 +847,10 @@ static int apply_microcode_intel(int cpu)
 		prev_rev = rev;
 	}
 
-	c = &cpu_data(cpu);
-
 	uci->cpu_sig.rev = rev;
 	c->microcode = rev;
 
-	return 0;
+	return UCODE_UPDATED;
 }
 
 static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
@@ -830,6 +862,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 	unsigned int leftover = size;
 	unsigned int curr_mc_size = 0, new_mc_size = 0;
 	unsigned int csig, cpf;
+	enum ucode_state ret = UCODE_OK;
 
 	while (leftover) {
 		struct microcode_header_intel mc_header;
@@ -871,6 +904,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 			new_mc  = mc;
 			new_mc_size = mc_size;
 			mc = NULL;	/* trigger new vmalloc */
+			ret = UCODE_NEW;
 		}
 
 		ucode_ptr += mc_size;
@@ -900,7 +934,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 	pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
 		 cpu, new_rev, uci->cpu_sig.rev);
 
-	return UCODE_OK;
+	return ret;
 }
 
 static int get_ucode_fw(void *to, const void *from, size_t n)
diff --git a/arch/x86/xen/mmu_hvm.c b/arch/x86/xen/mmu_hvm.c
index 2cfcfe4f6b2a..dd2ad82eee80 100644
--- a/arch/x86/xen/mmu_hvm.c
+++ b/arch/x86/xen/mmu_hvm.c
@@ -75,6 +75,6 @@ void __init xen_hvm_init_mmu_ops(void)
 	if (is_pagetable_dying_supported())
 		pv_mmu_ops.exit_mmap = xen_hvm_exit_mmap;
 #ifdef CONFIG_PROC_VMCORE
-	register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram);
+	WARN_ON(register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram));
 #endif
 }
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index ceefb9a706d6..5d53e504acae 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -749,10 +749,11 @@ static void bfq_pd_offline(struct blkg_policy_data *pd)
 	unsigned long flags;
 	int i;
 
+	spin_lock_irqsave(&bfqd->lock, flags);
+
 	if (!entity) /* root group */
-		return;
+		goto put_async_queues;
 
-	spin_lock_irqsave(&bfqd->lock, flags);
 	/*
 	 * Empty all service_trees belonging to this group before
 	 * deactivating the group itself.
@@ -783,6 +784,8 @@ static void bfq_pd_offline(struct blkg_policy_data *pd)
 	}
 
 	__bfq_deactivate_entity(entity, false);
+
+put_async_queues:
 	bfq_put_async_queues(bfqd, bfqg);
 
 	spin_unlock_irqrestore(&bfqd->lock, flags);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index f1fb126a3be5..6f899669cbdd 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1928,7 +1928,8 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 {
 	blk_mq_debugfs_unregister_hctx(hctx);
 
-	blk_mq_tag_idle(hctx);
+	if (blk_mq_hw_queue_mapped(hctx))
+		blk_mq_tag_idle(hctx);
 
 	if (set->ops->exit_request)
 		set->ops->exit_request(set, hctx->fq->flush_rq, hctx_idx);
@@ -2314,6 +2315,9 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 	struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx;
 
 	blk_mq_sysfs_unregister(q);
+
+	/* protect against switching io scheduler  */
+	mutex_lock(&q->sysfs_lock);
 	for (i = 0; i < set->nr_hw_queues; i++) {
 		int node;
 
@@ -2358,6 +2362,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 		}
 	}
 	q->nr_hw_queues = i;
+	mutex_unlock(&q->sysfs_lock);
 	blk_mq_sysfs_register(q);
 }
 
@@ -2528,9 +2533,27 @@ static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
 
 static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 {
-	if (set->ops->map_queues)
+	if (set->ops->map_queues) {
+		int cpu;
+		/*
+		 * transport .map_queues is usually done in the following
+		 * way:
+		 *
+		 * for (queue = 0; queue < set->nr_hw_queues; queue++) {
+		 * 	mask = get_cpu_mask(queue)
+		 * 	for_each_cpu(cpu, mask)
+		 * 		set->mq_map[cpu] = queue;
+		 * }
+		 *
+		 * When we need to remap, the table has to be cleared for
+		 * killing stale mapping since one CPU may not be mapped
+		 * to any hw queue.
+		 */
+		for_each_possible_cpu(cpu)
+			set->mq_map[cpu] = 0;
+
 		return set->ops->map_queues(set);
-	else
+	} else
 		return blk_mq_map_queues(set);
 }
 
diff --git a/crypto/Makefile b/crypto/Makefile
index da190be60ce2..adaf2c63baeb 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -98,6 +98,7 @@ obj-$(CONFIG_CRYPTO_TWOFISH_COMMON) += twofish_common.o
 obj-$(CONFIG_CRYPTO_SERPENT) += serpent_generic.o
 CFLAGS_serpent_generic.o := $(call cc-option,-fsched-pressure)  # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79149
 obj-$(CONFIG_CRYPTO_AES) += aes_generic.o
+CFLAGS_aes_generic.o := $(call cc-ifversion, -ge, 0701, -Os) # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83356
 obj-$(CONFIG_CRYPTO_AES_TI) += aes_ti.o
 obj-$(CONFIG_CRYPTO_CAMELLIA) += camellia_generic.o
 obj-$(CONFIG_CRYPTO_CAST_COMMON) += cast_common.o
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 0972ec0e2eb8..f53ccc680238 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -80,8 +80,8 @@ MODULE_PARM_DESC(report_key_events,
 static bool device_id_scheme = false;
 module_param(device_id_scheme, bool, 0444);
 
-static bool only_lcd = false;
-module_param(only_lcd, bool, 0444);
+static int only_lcd = -1;
+module_param(only_lcd, int, 0444);
 
 static int register_count;
 static DEFINE_MUTEX(register_count_mutex);
@@ -2136,6 +2136,16 @@ int acpi_video_register(void)
 		goto leave;
 	}
 
+	/*
+	 * We're seeing a lot of bogus backlight interfaces on newer machines
+	 * without a LCD such as desktops, servers and HDMI sticks. Checking
+	 * the lcd flag fixes this, so enable this on any machines which are
+	 * win8 ready (where we also prefer the native backlight driver, so
+	 * normally the acpi_video code should not register there anyways).
+	 */
+	if (only_lcd == -1)
+		only_lcd = acpi_osi_is_win8();
+
 	dmi_check_system(video_dmi_table);
 
 	ret = acpi_bus_register_driver(&acpi_video_bus);
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index df842465634a..6adcda057b36 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1516,7 +1516,7 @@ static int acpi_ec_setup(struct acpi_ec *ec, bool handle_events)
 	}
 
 	acpi_handle_info(ec->handle,
-			 "GPE=0x%lx, EC_CMD/EC_SC=0x%lx, EC_DATA=0x%lx\n",
+			 "GPE=0x%x, EC_CMD/EC_SC=0x%lx, EC_DATA=0x%lx\n",
 			 ec->gpe, ec->command_addr, ec->data_addr);
 	return ret;
 }
diff --git a/drivers/acpi/ec_sys.c b/drivers/acpi/ec_sys.c
index 6c7dd7af789e..dd70d6c2bca0 100644
--- a/drivers/acpi/ec_sys.c
+++ b/drivers/acpi/ec_sys.c
@@ -128,7 +128,7 @@ static int acpi_ec_add_debugfs(struct acpi_ec *ec, unsigned int ec_device_count)
 		return -ENOMEM;
 	}
 
-	if (!debugfs_create_x32("gpe", 0444, dev_dir, (u32 *)&first_ec->gpe))
+	if (!debugfs_create_x32("gpe", 0444, dev_dir, &first_ec->gpe))
 		goto error;
 	if (!debugfs_create_bool("use_global_lock", 0444, dev_dir,
 				 &first_ec->global_lock))
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index ede83d38beed..2cd2ae152ab7 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -159,7 +159,7 @@ static inline void acpi_early_processor_osc(void) {}
    -------------------------------------------------------------------------- */
 struct acpi_ec {
 	acpi_handle handle;
-	unsigned long gpe;
+	u32 gpe;
 	unsigned long command_addr;
 	unsigned long data_addr;
 	bool global_lock;
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index b2c0306f97ed..e9dff868c028 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -277,6 +277,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0489, 0xe09f), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x0489, 0xe0a2), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x04ca, 0x3011), .driver_info = BTUSB_QCA_ROME },
+	{ USB_DEVICE(0x04ca, 0x3015), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x04ca, 0x3016), .driver_info = BTUSB_QCA_ROME },
 
 	/* Broadcom BCM2035 */
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index 5294442505cb..0f1dc35e7078 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -328,7 +328,7 @@ unsigned long tpm_calc_ordinal_duration(struct tpm_chip *chip,
 }
 EXPORT_SYMBOL_GPL(tpm_calc_ordinal_duration);
 
-static bool tpm_validate_command(struct tpm_chip *chip,
+static int tpm_validate_command(struct tpm_chip *chip,
 				 struct tpm_space *space,
 				 const u8 *cmd,
 				 size_t len)
@@ -340,10 +340,10 @@ static bool tpm_validate_command(struct tpm_chip *chip,
 	unsigned int nr_handles;
 
 	if (len < TPM_HEADER_SIZE)
-		return false;
+		return -EINVAL;
 
 	if (!space)
-		return true;
+		return 0;
 
 	if (chip->flags & TPM_CHIP_FLAG_TPM2 && chip->nr_commands) {
 		cc = be32_to_cpu(header->ordinal);
@@ -352,7 +352,7 @@ static bool tpm_validate_command(struct tpm_chip *chip,
 		if (i < 0) {
 			dev_dbg(&chip->dev, "0x%04X is an invalid command\n",
 				cc);
-			return false;
+			return -EOPNOTSUPP;
 		}
 
 		attrs = chip->cc_attrs_tbl[i];
@@ -362,11 +362,11 @@ static bool tpm_validate_command(struct tpm_chip *chip,
 			goto err_len;
 	}
 
-	return true;
+	return 0;
 err_len:
 	dev_dbg(&chip->dev,
 		"%s: insufficient command length %zu", __func__, len);
-	return false;
+	return -EINVAL;
 }
 
 /**
@@ -391,8 +391,20 @@ ssize_t tpm_transmit(struct tpm_chip *chip, struct tpm_space *space,
 	unsigned long stop;
 	bool need_locality;
 
-	if (!tpm_validate_command(chip, space, buf, bufsiz))
-		return -EINVAL;
+	rc = tpm_validate_command(chip, space, buf, bufsiz);
+	if (rc == -EINVAL)
+		return rc;
+	/*
+	 * If the command is not implemented by the TPM, synthesize a
+	 * response with a TPM2_RC_COMMAND_CODE return for user-space.
+	 */
+	if (rc == -EOPNOTSUPP) {
+		header->length = cpu_to_be32(sizeof(*header));
+		header->tag = cpu_to_be16(TPM2_ST_NO_SESSIONS);
+		header->return_code = cpu_to_be32(TPM2_RC_COMMAND_CODE |
+						  TSS2_RESMGR_TPM_RC_LAYER);
+		return bufsiz;
+	}
 
 	if (bufsiz > TPM_BUFSIZE)
 		bufsiz = TPM_BUFSIZE;
diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index 2d5466a72e40..0b5b499f726a 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -93,12 +93,17 @@ enum tpm2_structures {
 	TPM2_ST_SESSIONS	= 0x8002,
 };
 
+/* Indicates from what layer of the software stack the error comes from */
+#define TSS2_RC_LAYER_SHIFT	 16
+#define TSS2_RESMGR_TPM_RC_LAYER (11 << TSS2_RC_LAYER_SHIFT)
+
 enum tpm2_return_codes {
 	TPM2_RC_SUCCESS		= 0x0000,
 	TPM2_RC_HASH		= 0x0083, /* RC_FMT1 */
 	TPM2_RC_HANDLE		= 0x008B,
 	TPM2_RC_INITIALIZE	= 0x0100, /* RC_VER1 */
 	TPM2_RC_DISABLED	= 0x0120,
+	TPM2_RC_COMMAND_CODE    = 0x0143,
 	TPM2_RC_TESTING		= 0x090A, /* RC_WARN */
 	TPM2_RC_REFERENCE_H0	= 0x0910,
 };
diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c
index 4ed516cb7276..b49942b9fe50 100644
--- a/drivers/clk/clk-divider.c
+++ b/drivers/clk/clk-divider.c
@@ -118,12 +118,11 @@ static unsigned int _get_val(const struct clk_div_table *table,
 unsigned long divider_recalc_rate(struct clk_hw *hw, unsigned long parent_rate,
 				  unsigned int val,
 				  const struct clk_div_table *table,
-				  unsigned long flags)
+				  unsigned long flags, unsigned long width)
 {
-	struct clk_divider *divider = to_clk_divider(hw);
 	unsigned int div;
 
-	div = _get_div(table, val, flags, divider->width);
+	div = _get_div(table, val, flags, width);
 	if (!div) {
 		WARN(!(flags & CLK_DIVIDER_ALLOW_ZERO),
 			"%s: Zero divisor and CLK_DIVIDER_ALLOW_ZERO not set\n",
@@ -145,7 +144,7 @@ static unsigned long clk_divider_recalc_rate(struct clk_hw *hw,
 	val &= div_mask(divider->width);
 
 	return divider_recalc_rate(hw, parent_rate, val, divider->table,
-				   divider->flags);
+				   divider->flags, divider->width);
 }
 
 static bool _is_valid_table_div(const struct clk_div_table *table,
diff --git a/drivers/clk/hisilicon/clkdivider-hi6220.c b/drivers/clk/hisilicon/clkdivider-hi6220.c
index a1c1f684ad58..9f46cf9dcc65 100644
--- a/drivers/clk/hisilicon/clkdivider-hi6220.c
+++ b/drivers/clk/hisilicon/clkdivider-hi6220.c
@@ -56,7 +56,7 @@ static unsigned long hi6220_clkdiv_recalc_rate(struct clk_hw *hw,
 	val &= div_mask(dclk->width);
 
 	return divider_recalc_rate(hw, parent_rate, val, dclk->table,
-				   CLK_DIVIDER_ROUND_CLOSEST);
+				   CLK_DIVIDER_ROUND_CLOSEST, dclk->width);
 }
 
 static long hi6220_clkdiv_round_rate(struct clk_hw *hw, unsigned long rate,
diff --git a/drivers/clk/meson/clk-mpll.c b/drivers/clk/meson/clk-mpll.c
index 44a5a535ca63..5144360e2c80 100644
--- a/drivers/clk/meson/clk-mpll.c
+++ b/drivers/clk/meson/clk-mpll.c
@@ -98,7 +98,7 @@ static void params_from_rate(unsigned long requested_rate,
 		*sdm = SDM_DEN - 1;
 	} else {
 		*n2 = div;
-		*sdm = DIV_ROUND_UP(rem * SDM_DEN, requested_rate);
+		*sdm = DIV_ROUND_UP_ULL((u64)rem * SDM_DEN, requested_rate);
 	}
 }
 
diff --git a/drivers/clk/nxp/clk-lpc32xx.c b/drivers/clk/nxp/clk-lpc32xx.c
index 7b359afd620e..a6438f50e6db 100644
--- a/drivers/clk/nxp/clk-lpc32xx.c
+++ b/drivers/clk/nxp/clk-lpc32xx.c
@@ -956,7 +956,7 @@ static unsigned long clk_divider_recalc_rate(struct clk_hw *hw,
 	val &= div_mask(divider->width);
 
 	return divider_recalc_rate(hw, parent_rate, val, divider->table,
-				   divider->flags);
+				   divider->flags, divider->width);
 }
 
 static long clk_divider_round_rate(struct clk_hw *hw, unsigned long rate,
diff --git a/drivers/clk/qcom/clk-regmap-divider.c b/drivers/clk/qcom/clk-regmap-divider.c
index 53484912301e..928fcc16ee27 100644
--- a/drivers/clk/qcom/clk-regmap-divider.c
+++ b/drivers/clk/qcom/clk-regmap-divider.c
@@ -59,7 +59,7 @@ static unsigned long div_recalc_rate(struct clk_hw *hw,
 	div &= BIT(divider->width) - 1;
 
 	return divider_recalc_rate(hw, parent_rate, div, NULL,
-				   CLK_DIVIDER_ROUND_CLOSEST);
+				   CLK_DIVIDER_ROUND_CLOSEST, divider->width);
 }
 
 const struct clk_ops clk_regmap_div_ops = {
diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-a83t.c b/drivers/clk/sunxi-ng/ccu-sun8i-a83t.c
index f8203115a6bc..c10160d7a556 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-a83t.c
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-a83t.c
@@ -493,8 +493,8 @@ static SUNXI_CCU_MUX_WITH_GATE(tcon0_clk, "tcon0", tcon0_parents,
 				 0x118, 24, 3, BIT(31), CLK_SET_RATE_PARENT);
 
 static const char * const tcon1_parents[] = { "pll-video1" };
-static SUNXI_CCU_MUX_WITH_GATE(tcon1_clk, "tcon1", tcon1_parents,
-				 0x11c, 24, 3, BIT(31), CLK_SET_RATE_PARENT);
+static SUNXI_CCU_M_WITH_MUX_GATE(tcon1_clk, "tcon1", tcon1_parents,
+				 0x11c, 0, 4, 24, 2, BIT(31), CLK_SET_RATE_PARENT);
 
 static SUNXI_CCU_GATE(csi_misc_clk, "csi-misc", "osc24M", 0x130, BIT(16), 0);
 
diff --git a/drivers/clk/sunxi-ng/ccu_div.c b/drivers/clk/sunxi-ng/ccu_div.c
index baa3cf96507b..302a18efd39f 100644
--- a/drivers/clk/sunxi-ng/ccu_div.c
+++ b/drivers/clk/sunxi-ng/ccu_div.c
@@ -71,7 +71,7 @@ static unsigned long ccu_div_recalc_rate(struct clk_hw *hw,
 						  parent_rate);
 
 	val = divider_recalc_rate(hw, parent_rate, val, cd->div.table,
-				  cd->div.flags);
+				  cd->div.flags, cd->div.width);
 
 	if (cd->common.features & CCU_FEATURE_FIXED_POSTDIV)
 		val /= cd->fixed_post_div;
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 7e1e5bbcf430..6b3a63545619 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -41,11 +41,9 @@
 #define POWERNV_MAX_PSTATES	256
 #define PMSR_PSAFE_ENABLE	(1UL << 30)
 #define PMSR_SPR_EM_DISABLE	(1UL << 31)
-#define PMSR_MAX(x)		((x >> 32) & 0xFF)
+#define MAX_PSTATE_SHIFT	32
 #define LPSTATE_SHIFT		48
 #define GPSTATE_SHIFT		56
-#define GET_LPSTATE(x)		(((x) >> LPSTATE_SHIFT) & 0xFF)
-#define GET_GPSTATE(x)		(((x) >> GPSTATE_SHIFT) & 0xFF)
 
 #define MAX_RAMP_DOWN_TIME				5120
 /*
@@ -93,6 +91,7 @@ struct global_pstate_info {
 };
 
 static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1];
+u32 pstate_sign_prefix;
 static bool rebooting, throttled, occ_reset;
 
 static const char * const throttle_reason[] = {
@@ -147,6 +146,20 @@ static struct powernv_pstate_info {
 	bool wof_enabled;
 } powernv_pstate_info;
 
+static inline int extract_pstate(u64 pmsr_val, unsigned int shift)
+{
+	int ret = ((pmsr_val >> shift) & 0xFF);
+
+	if (!ret)
+		return ret;
+
+	return (pstate_sign_prefix | ret);
+}
+
+#define extract_local_pstate(x) extract_pstate(x, LPSTATE_SHIFT)
+#define extract_global_pstate(x) extract_pstate(x, GPSTATE_SHIFT)
+#define extract_max_pstate(x)  extract_pstate(x, MAX_PSTATE_SHIFT)
+
 /* Use following macros for conversions between pstate_id and index */
 static inline int idx_to_pstate(unsigned int i)
 {
@@ -277,6 +290,9 @@ static int init_powernv_pstates(void)
 
 	powernv_pstate_info.nr_pstates = nr_pstates;
 	pr_debug("NR PStates %d\n", nr_pstates);
+
+	pstate_sign_prefix = pstate_min & ~0xFF;
+
 	for (i = 0; i < nr_pstates; i++) {
 		u32 id = be32_to_cpu(pstate_ids[i]);
 		u32 freq = be32_to_cpu(pstate_freqs[i]);
@@ -437,17 +453,10 @@ struct powernv_smp_call_data {
 static void powernv_read_cpu_freq(void *arg)
 {
 	unsigned long pmspr_val;
-	s8 local_pstate_id;
 	struct powernv_smp_call_data *freq_data = arg;
 
 	pmspr_val = get_pmspr(SPRN_PMSR);
-
-	/*
-	 * The local pstate id corresponds bits 48..55 in the PMSR.
-	 * Note: Watch out for the sign!
-	 */
-	local_pstate_id = (pmspr_val >> 48) & 0xFF;
-	freq_data->pstate_id = local_pstate_id;
+	freq_data->pstate_id = extract_local_pstate(pmspr_val);
 	freq_data->freq = pstate_id_to_freq(freq_data->pstate_id);
 
 	pr_debug("cpu %d pmsr %016lX pstate_id %d frequency %d kHz\n",
@@ -521,7 +530,7 @@ static void powernv_cpufreq_throttle_check(void *data)
 	chip = this_cpu_read(chip_info);
 
 	/* Check for Pmax Capping */
-	pmsr_pmax = (s8)PMSR_MAX(pmsr);
+	pmsr_pmax = extract_max_pstate(pmsr);
 	pmsr_pmax_idx = pstate_to_idx(pmsr_pmax);
 	if (pmsr_pmax_idx != powernv_pstate_info.max) {
 		if (chip->throttled)
@@ -644,8 +653,8 @@ void gpstate_timer_handler(unsigned long data)
 	 * value. Hence, read from PMCR to get correct data.
 	 */
 	val = get_pmspr(SPRN_PMCR);
-	freq_data.gpstate_id = (s8)GET_GPSTATE(val);
-	freq_data.pstate_id = (s8)GET_LPSTATE(val);
+	freq_data.gpstate_id = extract_global_pstate(val);
+	freq_data.pstate_id = extract_local_pstate(val);
 	if (freq_data.gpstate_id  == freq_data.pstate_id) {
 		reset_gpstates(policy);
 		spin_unlock(&gpstates->gpstate_lock);
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 202476fbbc4c..8a411514a7c5 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -935,7 +935,8 @@ static ssize_t governor_store(struct device *dev, struct device_attribute *attr,
 	if (df->governor == governor) {
 		ret = 0;
 		goto out;
-	} else if (df->governor->immutable || governor->immutable) {
+	} else if ((df->governor && df->governor->immutable) ||
+					governor->immutable) {
 		ret = -EINVAL;
 		goto out;
 	}
diff --git a/drivers/edac/mv64x60_edac.c b/drivers/edac/mv64x60_edac.c
index ec5d695bbb72..3c68bb525d5d 100644
--- a/drivers/edac/mv64x60_edac.c
+++ b/drivers/edac/mv64x60_edac.c
@@ -758,7 +758,7 @@ static int mv64x60_mc_err_probe(struct platform_device *pdev)
 		/* Non-ECC RAM? */
 		printk(KERN_WARNING "%s: No ECC DIMMs discovered\n", __func__);
 		res = -ENODEV;
-		goto err2;
+		goto err;
 	}
 
 	edac_dbg(3, "init mci\n");
diff --git a/drivers/gpio/gpio-thunderx.c b/drivers/gpio/gpio-thunderx.c
index 57efb251f9c4..10523ce00c38 100644
--- a/drivers/gpio/gpio-thunderx.c
+++ b/drivers/gpio/gpio-thunderx.c
@@ -566,8 +566,10 @@ static int thunderx_gpio_probe(struct pci_dev *pdev,
 	txgpio->irqd = irq_domain_create_hierarchy(irq_get_irq_data(txgpio->msix_entries[0].vector)->domain,
 						   0, 0, of_node_to_fwnode(dev->of_node),
 						   &thunderx_gpio_irqd_ops, txgpio);
-	if (!txgpio->irqd)
+	if (!txgpio->irqd) {
+		err = -ENOMEM;
 		goto out;
+	}
 
 	/* Push on irq_data and the domain for each line. */
 	for (i = 0; i < ngpio; i++) {
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index bdd68ff197dc..b4c8b25453a6 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -3340,7 +3340,8 @@ struct gpio_desc *__must_check gpiod_get_index(struct device *dev,
 		return desc;
 	}
 
-	status = gpiod_request(desc, con_id);
+	/* If a connection label was passed use that, else use the device name as label */
+	status = gpiod_request(desc, con_id ? con_id : dev_name(dev));
 	if (status < 0)
 		return ERR_PTR(status);
 
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_14nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_14nm.c
index fe15aa64086f..71fe60e5f01f 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_14nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_14nm.c
@@ -698,7 +698,7 @@ static unsigned long dsi_pll_14nm_postdiv_recalc_rate(struct clk_hw *hw,
 	val &= div_mask(width);
 
 	return divider_recalc_rate(hw, parent_rate, val, NULL,
-				   postdiv->flags);
+				   postdiv->flags, width);
 }
 
 static long dsi_pll_14nm_postdiv_round_rate(struct clk_hw *hw,
diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c
index 62e38fa8cda2..e362a932fe8c 100644
--- a/drivers/hwmon/ina2xx.c
+++ b/drivers/hwmon/ina2xx.c
@@ -95,18 +95,20 @@ enum ina2xx_ids { ina219, ina226 };
 
 struct ina2xx_config {
 	u16 config_default;
-	int calibration_factor;
+	int calibration_value;
 	int registers;
 	int shunt_div;
 	int bus_voltage_shift;
 	int bus_voltage_lsb;	/* uV */
-	int power_lsb;		/* uW */
+	int power_lsb_factor;
 };
 
 struct ina2xx_data {
 	const struct ina2xx_config *config;
 
 	long rshunt;
+	long current_lsb_uA;
+	long power_lsb_uW;
 	struct mutex config_lock;
 	struct regmap *regmap;
 
@@ -116,21 +118,21 @@ struct ina2xx_data {
 static const struct ina2xx_config ina2xx_config[] = {
 	[ina219] = {
 		.config_default = INA219_CONFIG_DEFAULT,
-		.calibration_factor = 40960000,
+		.calibration_value = 4096,
 		.registers = INA219_REGISTERS,
 		.shunt_div = 100,
 		.bus_voltage_shift = 3,
 		.bus_voltage_lsb = 4000,
-		.power_lsb = 20000,
+		.power_lsb_factor = 20,
 	},
 	[ina226] = {
 		.config_default = INA226_CONFIG_DEFAULT,
-		.calibration_factor = 5120000,
+		.calibration_value = 2048,
 		.registers = INA226_REGISTERS,
 		.shunt_div = 400,
 		.bus_voltage_shift = 0,
 		.bus_voltage_lsb = 1250,
-		.power_lsb = 25000,
+		.power_lsb_factor = 25,
 	},
 };
 
@@ -169,12 +171,16 @@ static u16 ina226_interval_to_reg(int interval)
 	return INA226_SHIFT_AVG(avg_bits);
 }
 
+/*
+ * Calibration register is set to the best value, which eliminates
+ * truncation errors on calculating current register in hardware.
+ * According to datasheet (eq. 3) the best values are 2048 for
+ * ina226 and 4096 for ina219. They are hardcoded as calibration_value.
+ */
 static int ina2xx_calibrate(struct ina2xx_data *data)
 {
-	u16 val = DIV_ROUND_CLOSEST(data->config->calibration_factor,
-				    data->rshunt);
-
-	return regmap_write(data->regmap, INA2XX_CALIBRATION, val);
+	return regmap_write(data->regmap, INA2XX_CALIBRATION,
+			    data->config->calibration_value);
 }
 
 /*
@@ -187,10 +193,6 @@ static int ina2xx_init(struct ina2xx_data *data)
 	if (ret < 0)
 		return ret;
 
-	/*
-	 * Set current LSB to 1mA, shunt is in uOhms
-	 * (equation 13 in datasheet).
-	 */
 	return ina2xx_calibrate(data);
 }
 
@@ -268,15 +270,15 @@ static int ina2xx_get_value(struct ina2xx_data *data, u8 reg,
 		val = DIV_ROUND_CLOSEST(val, 1000);
 		break;
 	case INA2XX_POWER:
-		val = regval * data->config->power_lsb;
+		val = regval * data->power_lsb_uW;
 		break;
 	case INA2XX_CURRENT:
-		/* signed register, LSB=1mA (selected), in mA */
-		val = (s16)regval;
+		/* signed register, result in mA */
+		val = regval * data->current_lsb_uA;
+		val = DIV_ROUND_CLOSEST(val, 1000);
 		break;
 	case INA2XX_CALIBRATION:
-		val = DIV_ROUND_CLOSEST(data->config->calibration_factor,
-					regval);
+		val = regval;
 		break;
 	default:
 		/* programmer goofed */
@@ -304,9 +306,32 @@ static ssize_t ina2xx_show_value(struct device *dev,
 			ina2xx_get_value(data, attr->index, regval));
 }
 
-static ssize_t ina2xx_set_shunt(struct device *dev,
-				struct device_attribute *da,
-				const char *buf, size_t count)
+/*
+ * In order to keep calibration register value fixed, the product
+ * of current_lsb and shunt_resistor should also be fixed and equal
+ * to shunt_voltage_lsb = 1 / shunt_div multiplied by 10^9 in order
+ * to keep the scale.
+ */
+static int ina2xx_set_shunt(struct ina2xx_data *data, long val)
+{
+	unsigned int dividend = DIV_ROUND_CLOSEST(1000000000,
+						  data->config->shunt_div);
+	if (val <= 0 || val > dividend)
+		return -EINVAL;
+
+	mutex_lock(&data->config_lock);
+	data->rshunt = val;
+	data->current_lsb_uA = DIV_ROUND_CLOSEST(dividend, val);
+	data->power_lsb_uW = data->config->power_lsb_factor *
+			     data->current_lsb_uA;
+	mutex_unlock(&data->config_lock);
+
+	return 0;
+}
+
+static ssize_t ina2xx_store_shunt(struct device *dev,
+				  struct device_attribute *da,
+				  const char *buf, size_t count)
 {
 	unsigned long val;
 	int status;
@@ -316,18 +341,9 @@ static ssize_t ina2xx_set_shunt(struct device *dev,
 	if (status < 0)
 		return status;
 
-	if (val == 0 ||
-	    /* Values greater than the calibration factor make no sense. */
-	    val > data->config->calibration_factor)
-		return -EINVAL;
-
-	mutex_lock(&data->config_lock);
-	data->rshunt = val;
-	status = ina2xx_calibrate(data);
-	mutex_unlock(&data->config_lock);
+	status = ina2xx_set_shunt(data, val);
 	if (status < 0)
 		return status;
-
 	return count;
 }
 
@@ -387,7 +403,7 @@ static SENSOR_DEVICE_ATTR(power1_input, S_IRUGO, ina2xx_show_value, NULL,
 
 /* shunt resistance */
 static SENSOR_DEVICE_ATTR(shunt_resistor, S_IRUGO | S_IWUSR,
-			  ina2xx_show_value, ina2xx_set_shunt,
+			  ina2xx_show_value, ina2xx_store_shunt,
 			  INA2XX_CALIBRATION);
 
 /* update interval (ina226 only) */
@@ -448,10 +464,7 @@ static int ina2xx_probe(struct i2c_client *client,
 			val = INA2XX_RSHUNT_DEFAULT;
 	}
 
-	if (val <= 0 || val > data->config->calibration_factor)
-		return -ENODEV;
-
-	data->rshunt = val;
+	ina2xx_set_shunt(data, val);
 
 	ina2xx_regmap_config.max_register = data->config->registers;
 
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 6cae00ecc905..25de7cc9f49f 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -4453,6 +4453,7 @@ static int cma_get_id_stats(struct sk_buff *skb, struct netlink_callback *cb)
 			id_stats->qp_type	= id->qp_type;
 
 			i_id++;
+			nlmsg_end(skb, nlh);
 		}
 
 		cb->args[1] = 0;
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 722235bed075..d6fa38f8604f 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -914,13 +914,14 @@ static ssize_t ucma_query_path(struct ucma_context *ctx,
 
 		resp->path_data[i].flags = IB_PATH_GMP | IB_PATH_PRIMARY |
 					   IB_PATH_BIDIRECTIONAL;
-		if (rec->rec_type == SA_PATH_REC_TYPE_IB) {
-			ib_sa_pack_path(rec, &resp->path_data[i].path_rec);
-		} else {
+		if (rec->rec_type == SA_PATH_REC_TYPE_OPA) {
 			struct sa_path_rec ib;
 
 			sa_convert_path_opa_to_ib(&ib, rec);
 			ib_sa_pack_path(&ib, &resp->path_data[i].path_rec);
+
+		} else {
+			ib_sa_pack_path(rec, &resp->path_data[i].path_rec);
 		}
 	}
 
diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c
index d6a1a308c6a0..b7f1ce5333cb 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_cm.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c
@@ -125,7 +125,8 @@ static u8 i40iw_derive_hw_ird_setting(u16 cm_ird)
  * @conn_ird: connection IRD
  * @conn_ord: connection ORD
  */
-static void i40iw_record_ird_ord(struct i40iw_cm_node *cm_node, u16 conn_ird, u16 conn_ord)
+static void i40iw_record_ird_ord(struct i40iw_cm_node *cm_node, u32 conn_ird,
+				 u32 conn_ord)
 {
 	if (conn_ird > I40IW_MAX_IRD_SIZE)
 		conn_ird = I40IW_MAX_IRD_SIZE;
@@ -3841,7 +3842,7 @@ int i40iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	}
 
 	cm_node->apbvt_set = true;
-	i40iw_record_ird_ord(cm_node, (u16)conn_param->ird, (u16)conn_param->ord);
+	i40iw_record_ird_ord(cm_node, conn_param->ird, conn_param->ord);
 	if (cm_node->send_rdma0_op == SEND_RDMA_READ_ZERO &&
 	    !cm_node->ord_size)
 		cm_node->ord_size = 1;
diff --git a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
index d86f3e670804..472ef4d6e858 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
@@ -3875,8 +3875,10 @@ enum i40iw_status_code i40iw_config_fpm_values(struct i40iw_sc_dev *dev, u32 qp_
 		hmc_info->hmc_obj[I40IW_HMC_IW_APBVT_ENTRY].cnt = 1;
 		hmc_info->hmc_obj[I40IW_HMC_IW_MR].cnt = mrwanted;
 
-		hmc_info->hmc_obj[I40IW_HMC_IW_XF].cnt = I40IW_MAX_WQ_ENTRIES * qpwanted;
-		hmc_info->hmc_obj[I40IW_HMC_IW_Q1].cnt = 4 * I40IW_MAX_IRD_SIZE * qpwanted;
+		hmc_info->hmc_obj[I40IW_HMC_IW_XF].cnt =
+			roundup_pow_of_two(I40IW_MAX_WQ_ENTRIES * qpwanted);
+		hmc_info->hmc_obj[I40IW_HMC_IW_Q1].cnt =
+			roundup_pow_of_two(2 * I40IW_MAX_IRD_SIZE * qpwanted);
 		hmc_info->hmc_obj[I40IW_HMC_IW_XFFL].cnt =
 			hmc_info->hmc_obj[I40IW_HMC_IW_XF].cnt / hmc_fpm_misc->xf_block_size;
 		hmc_info->hmc_obj[I40IW_HMC_IW_Q1FL].cnt =
diff --git a/drivers/infiniband/hw/i40iw/i40iw_d.h b/drivers/infiniband/hw/i40iw/i40iw_d.h
index 24eabcad5e40..019ad3b939f9 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_d.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_d.h
@@ -93,6 +93,7 @@
 #define RDMA_OPCODE_MASK        0x0f
 #define RDMA_READ_REQ_OPCODE    1
 #define Q2_BAD_FRAME_OFFSET     72
+#define Q2_FPSN_OFFSET          64
 #define CQE_MAJOR_DRV           0x8000
 
 #define I40IW_TERM_SENT 0x01
diff --git a/drivers/infiniband/hw/i40iw/i40iw_puda.c b/drivers/infiniband/hw/i40iw/i40iw_puda.c
index 59f70676f0e0..14d38d733cb4 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_puda.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_puda.c
@@ -1376,7 +1376,7 @@ static void i40iw_ieq_handle_exception(struct i40iw_puda_rsrc *ieq,
 	u32 *hw_host_ctx = (u32 *)qp->hw_host_ctx;
 	u32 rcv_wnd = hw_host_ctx[23];
 	/* first partial seq # in q2 */
-	u32 fps = qp->q2_buf[16];
+	u32 fps = *(u32 *)(qp->q2_buf + Q2_FPSN_OFFSET);
 	struct list_head *rxlist = &pfpdu->rxlist;
 	struct list_head *plist;
 
diff --git a/drivers/infiniband/sw/rdmavt/cq.c b/drivers/infiniband/sw/rdmavt/cq.c
index 97d71e49c092..88fa4d44ab5f 100644
--- a/drivers/infiniband/sw/rdmavt/cq.c
+++ b/drivers/infiniband/sw/rdmavt/cq.c
@@ -198,7 +198,7 @@ struct ib_cq *rvt_create_cq(struct ib_device *ibdev,
 		return ERR_PTR(-EINVAL);
 
 	/* Allocate the completion queue structure. */
-	cq = kzalloc(sizeof(*cq), GFP_KERNEL);
+	cq = kzalloc_node(sizeof(*cq), GFP_KERNEL, rdi->dparms.node);
 	if (!cq)
 		return ERR_PTR(-ENOMEM);
 
@@ -214,7 +214,9 @@ struct ib_cq *rvt_create_cq(struct ib_device *ibdev,
 		sz += sizeof(struct ib_uverbs_wc) * (entries + 1);
 	else
 		sz += sizeof(struct ib_wc) * (entries + 1);
-	wc = vmalloc_user(sz);
+	wc = udata ?
+		vmalloc_user(sz) :
+		vzalloc_node(sz, rdi->dparms.node);
 	if (!wc) {
 		ret = ERR_PTR(-ENOMEM);
 		goto bail_cq;
@@ -369,7 +371,9 @@ int rvt_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata)
 		sz += sizeof(struct ib_uverbs_wc) * (cqe + 1);
 	else
 		sz += sizeof(struct ib_wc) * (cqe + 1);
-	wc = vmalloc_user(sz);
+	wc = udata ?
+		vmalloc_user(sz) :
+		vzalloc_node(sz, rdi->dparms.node);
 	if (!wc)
 		return -ENOMEM;
 
diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c
index b3bbad7d2282..5dafafad6351 100644
--- a/drivers/input/touchscreen/goodix.c
+++ b/drivers/input/touchscreen/goodix.c
@@ -808,8 +808,10 @@ static int __maybe_unused goodix_suspend(struct device *dev)
 	int error;
 
 	/* We need gpio pins to suspend/resume */
-	if (!ts->gpiod_int || !ts->gpiod_rst)
+	if (!ts->gpiod_int || !ts->gpiod_rst) {
+		disable_irq(client->irq);
 		return 0;
+	}
 
 	wait_for_completion(&ts->firmware_loading_complete);
 
@@ -849,8 +851,10 @@ static int __maybe_unused goodix_resume(struct device *dev)
 	struct goodix_ts_data *ts = i2c_get_clientdata(client);
 	int error;
 
-	if (!ts->gpiod_int || !ts->gpiod_rst)
+	if (!ts->gpiod_int || !ts->gpiod_rst) {
+		enable_irq(client->irq);
 		return 0;
+	}
 
 	/*
 	 * Exit sleep mode by outputting HIGH level to INT pin
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index ae9ff72e83ee..848fcdf6a112 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -1297,6 +1297,10 @@ gic_acpi_parse_madt_gicc(struct acpi_subtable_header *header,
 	u32 size = reg == GIC_PIDR2_ARCH_GICv4 ? SZ_64K * 4 : SZ_64K * 2;
 	void __iomem *redist_base;
 
+	/* GICC entry which has !ACPI_MADT_ENABLED is not unusable so skip */
+	if (!(gicc->flags & ACPI_MADT_ENABLED))
+		return 0;
+
 	redist_base = ioremap(gicc->gicr_base_address, size);
 	if (!redist_base)
 		return -ENOMEM;
@@ -1346,6 +1350,13 @@ static int __init gic_acpi_match_gicc(struct acpi_subtable_header *header,
 	if ((gicc->flags & ACPI_MADT_ENABLED) && gicc->gicr_base_address)
 		return 0;
 
+	/*
+	 * It's perfectly valid firmware can pass disabled GICC entry, driver
+	 * should not treat as errors, skip the entry instead of probe fail.
+	 */
+	if (!(gicc->flags & ACPI_MADT_ENABLED))
+		return 0;
+
 	return -ENODEV;
 }
 
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 934b1fce4ce1..f0dc8e2aee65 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -515,15 +515,21 @@ struct open_bucket {
 
 /*
  * We keep multiple buckets open for writes, and try to segregate different
- * write streams for better cache utilization: first we look for a bucket where
- * the last write to it was sequential with the current write, and failing that
- * we look for a bucket that was last used by the same task.
+ * write streams for better cache utilization: first we try to segregate flash
+ * only volume write streams from cached devices, secondly we look for a bucket
+ * where the last write to it was sequential with the current write, and
+ * failing that we look for a bucket that was last used by the same task.
  *
  * The ideas is if you've got multiple tasks pulling data into the cache at the
  * same time, you'll get better cache utilization if you try to segregate their
  * data and preserve locality.
  *
- * For example, say you've starting Firefox at the same time you're copying a
+ * For example, dirty sectors of flash only volume is not reclaimable, if their
+ * dirty sectors mixed with dirty sectors of cached device, such buckets will
+ * be marked as dirty and won't be reclaimed, though the dirty data of cached
+ * device have been written back to backend device.
+ *
+ * And say you've starting Firefox at the same time you're copying a
  * bunch of files. Firefox will likely end up being fairly hot and stay in the
  * cache awhile, but the data you copied might not be; if you wrote all that
  * data to the same buckets it'd get invalidated at the same time.
@@ -540,7 +546,10 @@ static struct open_bucket *pick_data_bucket(struct cache_set *c,
 	struct open_bucket *ret, *ret_task = NULL;
 
 	list_for_each_entry_reverse(ret, &c->data_buckets, list)
-		if (!bkey_cmp(&ret->key, search))
+		if (UUID_FLASH_ONLY(&c->uuids[KEY_INODE(&ret->key)]) !=
+		    UUID_FLASH_ONLY(&c->uuids[KEY_INODE(search)]))
+			continue;
+		else if (!bkey_cmp(&ret->key, search))
 			goto found;
 		else if (ret->last_write_point == write_point)
 			ret_task = ret;
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index e9fbf2bcd122..f34ad8720756 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -568,6 +568,7 @@ static void cache_lookup(struct closure *cl)
 {
 	struct search *s = container_of(cl, struct search, iop.cl);
 	struct bio *bio = &s->bio.bio;
+	struct cached_dev *dc;
 	int ret;
 
 	bch_btree_op_init(&s->op, -1);
@@ -580,6 +581,27 @@ static void cache_lookup(struct closure *cl)
 		return;
 	}
 
+	/*
+	 * We might meet err when searching the btree, If that happens, we will
+	 * get negative ret, in this scenario we should not recover data from
+	 * backing device (when cache device is dirty) because we don't know
+	 * whether bkeys the read request covered are all clean.
+	 *
+	 * And after that happened, s->iop.status is still its initial value
+	 * before we submit s->bio.bio
+	 */
+	if (ret < 0) {
+		BUG_ON(ret == -EINTR);
+		if (s->d && s->d->c &&
+				!UUID_FLASH_ONLY(&s->d->c->uuids[s->d->id])) {
+			dc = container_of(s->d, struct cached_dev, disk);
+			if (dc && atomic_read(&dc->has_dirty))
+				s->recoverable = false;
+		}
+		if (!s->iop.status)
+			s->iop.status = BLK_STS_IOERR;
+	}
+
 	closure_return(cl);
 }
 
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 9417170f180a..5d0430777dda 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -893,6 +893,12 @@ static void cached_dev_detach_finish(struct work_struct *w)
 
 	mutex_lock(&bch_register_lock);
 
+	cancel_delayed_work_sync(&dc->writeback_rate_update);
+	if (!IS_ERR_OR_NULL(dc->writeback_thread)) {
+		kthread_stop(dc->writeback_thread);
+		dc->writeback_thread = NULL;
+	}
+
 	memset(&dc->sb.set_uuid, 0, 16);
 	SET_BDEV_STATE(&dc->sb, BDEV_STATE_NONE);
 
diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index cb115ba6a1d2..6d9adcaa26ba 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -332,6 +332,10 @@ static int __vb2_queue_alloc(struct vb2_queue *q, enum vb2_memory memory,
 	struct vb2_buffer *vb;
 	int ret;
 
+	/* Ensure that q->num_buffers+num_buffers is below VB2_MAX_FRAME */
+	num_buffers = min_t(unsigned int, num_buffers,
+			    VB2_MAX_FRAME - q->num_buffers);
+
 	for (buffer = 0; buffer < num_buffers; ++buffer) {
 		/* Allocate videobuf buffer structures */
 		vb = kzalloc(q->buf_struct_size, GFP_KERNEL);
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 070f5da06fd2..5bedf4b7f0f7 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -806,6 +806,8 @@ static int intel_mrfld_mmc_probe_slot(struct sdhci_pci_slot *slot)
 		slot->host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
 		break;
 	case INTEL_MRFLD_SDIO:
+		/* Advertise 2.0v for compatibility with the SDIO card's OCR */
+		slot->host->ocr_mask = MMC_VDD_20_21 | MMC_VDD_165_195;
 		slot->host->mmc->caps |= MMC_CAP_NONREMOVABLE |
 					 MMC_CAP_POWER_OFF_CARD;
 		break;
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 90cc1977b792..d35deb79965d 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1470,6 +1470,13 @@ void sdhci_set_power_noreg(struct sdhci_host *host, unsigned char mode,
 	if (mode != MMC_POWER_OFF) {
 		switch (1 << vdd) {
 		case MMC_VDD_165_195:
+		/*
+		 * Without a regulator, SDHCI does not support 2.0v
+		 * so we only get here if the driver deliberately
+		 * added the 2.0v range to ocr_avail. Map it to 1.8v
+		 * for the purpose of turning on the power.
+		 */
+		case MMC_VDD_20_21:
 			pwr = SDHCI_POWER_180;
 			break;
 		case MMC_VDD_29_30:
diff --git a/drivers/mtd/tests/oobtest.c b/drivers/mtd/tests/oobtest.c
index 1cb3f7758fb6..766b2c385682 100644
--- a/drivers/mtd/tests/oobtest.c
+++ b/drivers/mtd/tests/oobtest.c
@@ -193,6 +193,9 @@ static int verify_eraseblock(int ebnum)
 		ops.datbuf    = NULL;
 		ops.oobbuf    = readbuf;
 		err = mtd_read_oob(mtd, addr, &ops);
+		if (mtd_is_bitflip(err))
+			err = 0;
+
 		if (err || ops.oobretlen != use_len) {
 			pr_err("error: readoob failed at %#llx\n",
 			       (long long)addr);
@@ -227,6 +230,9 @@ static int verify_eraseblock(int ebnum)
 			ops.datbuf    = NULL;
 			ops.oobbuf    = readbuf;
 			err = mtd_read_oob(mtd, addr, &ops);
+			if (mtd_is_bitflip(err))
+				err = 0;
+
 			if (err || ops.oobretlen != mtd->oobavail) {
 				pr_err("error: readoob failed at %#llx\n",
 						(long long)addr);
@@ -286,6 +292,9 @@ static int verify_eraseblock_in_one_go(int ebnum)
 
 	/* read entire block's OOB at one go */
 	err = mtd_read_oob(mtd, addr, &ops);
+	if (mtd_is_bitflip(err))
+		err = 0;
+
 	if (err || ops.oobretlen != len) {
 		pr_err("error: readoob failed at %#llx\n",
 		       (long long)addr);
@@ -527,6 +536,9 @@ static int __init mtd_oobtest_init(void)
 	pr_info("attempting to start read past end of OOB\n");
 	pr_info("an error is expected...\n");
 	err = mtd_read_oob(mtd, addr0, &ops);
+	if (mtd_is_bitflip(err))
+		err = 0;
+
 	if (err) {
 		pr_info("error occurred as expected\n");
 		err = 0;
@@ -571,6 +583,9 @@ static int __init mtd_oobtest_init(void)
 		pr_info("attempting to read past end of device\n");
 		pr_info("an error is expected...\n");
 		err = mtd_read_oob(mtd, mtd->size - mtd->writesize, &ops);
+		if (mtd_is_bitflip(err))
+			err = 0;
+
 		if (err) {
 			pr_info("error occurred as expected\n");
 			err = 0;
@@ -615,6 +630,9 @@ static int __init mtd_oobtest_init(void)
 		pr_info("attempting to read past end of device\n");
 		pr_info("an error is expected...\n");
 		err = mtd_read_oob(mtd, mtd->size - mtd->writesize, &ops);
+		if (mtd_is_bitflip(err))
+			err = 0;
+
 		if (err) {
 			pr_info("error occurred as expected\n");
 			err = 0;
@@ -684,6 +702,9 @@ static int __init mtd_oobtest_init(void)
 		ops.datbuf    = NULL;
 		ops.oobbuf    = readbuf;
 		err = mtd_read_oob(mtd, addr, &ops);
+		if (mtd_is_bitflip(err))
+			err = 0;
+
 		if (err)
 			goto out;
 		if (memcmpshow(addr, readbuf, writebuf,
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b2db581131b2..82f28ffccddf 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1524,39 +1524,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 			goto err_close;
 	}
 
-	/* If the mode uses primary, then the following is handled by
-	 * bond_change_active_slave().
-	 */
-	if (!bond_uses_primary(bond)) {
-		/* set promiscuity level to new slave */
-		if (bond_dev->flags & IFF_PROMISC) {
-			res = dev_set_promiscuity(slave_dev, 1);
-			if (res)
-				goto err_close;
-		}
-
-		/* set allmulti level to new slave */
-		if (bond_dev->flags & IFF_ALLMULTI) {
-			res = dev_set_allmulti(slave_dev, 1);
-			if (res)
-				goto err_close;
-		}
-
-		netif_addr_lock_bh(bond_dev);
-
-		dev_mc_sync_multiple(slave_dev, bond_dev);
-		dev_uc_sync_multiple(slave_dev, bond_dev);
-
-		netif_addr_unlock_bh(bond_dev);
-	}
-
-	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
-		/* add lacpdu mc addr to mc list */
-		u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR;
-
-		dev_mc_add(slave_dev, lacpdu_multicast);
-	}
-
 	res = vlan_vids_add_by_dev(slave_dev, bond_dev);
 	if (res) {
 		netdev_err(bond_dev, "Couldn't add bond vlan ids to %s\n",
@@ -1721,6 +1688,40 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		goto err_upper_unlink;
 	}
 
+	/* If the mode uses primary, then the following is handled by
+	 * bond_change_active_slave().
+	 */
+	if (!bond_uses_primary(bond)) {
+		/* set promiscuity level to new slave */
+		if (bond_dev->flags & IFF_PROMISC) {
+			res = dev_set_promiscuity(slave_dev, 1);
+			if (res)
+				goto err_sysfs_del;
+		}
+
+		/* set allmulti level to new slave */
+		if (bond_dev->flags & IFF_ALLMULTI) {
+			res = dev_set_allmulti(slave_dev, 1);
+			if (res) {
+				if (bond_dev->flags & IFF_PROMISC)
+					dev_set_promiscuity(slave_dev, -1);
+				goto err_sysfs_del;
+			}
+		}
+
+		netif_addr_lock_bh(bond_dev);
+		dev_mc_sync_multiple(slave_dev, bond_dev);
+		dev_uc_sync_multiple(slave_dev, bond_dev);
+		netif_addr_unlock_bh(bond_dev);
+
+		if (BOND_MODE(bond) == BOND_MODE_8023AD) {
+			/* add lacpdu mc addr to mc list */
+			u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR;
+
+			dev_mc_add(slave_dev, lacpdu_multicast);
+		}
+	}
+
 	bond->slave_cnt++;
 	bond_compute_features(bond);
 	bond_set_carrier(bond);
@@ -1744,6 +1745,9 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	return 0;
 
 /* Undo stages on error */
+err_sysfs_del:
+	bond_sysfs_slave_del(new_slave);
+
 err_upper_unlink:
 	bond_upper_dev_unlink(bond, new_slave);
 
@@ -1751,9 +1755,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	netdev_rx_handler_unregister(slave_dev);
 
 err_detach:
-	if (!bond_uses_primary(bond))
-		bond_hw_addr_flush(bond_dev, slave_dev);
-
 	vlan_vids_del_by_dev(slave_dev, bond_dev);
 	if (rcu_access_pointer(bond->primary_slave) == new_slave)
 		RCU_INIT_POINTER(bond->primary_slave, NULL);
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
index 05498e7f2840..6246003f9922 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
@@ -2619,8 +2619,8 @@ void t4vf_sge_stop(struct adapter *adapter)
 int t4vf_sge_init(struct adapter *adapter)
 {
 	struct sge_params *sge_params = &adapter->params.sge;
-	u32 fl0 = sge_params->sge_fl_buffer_size[0];
-	u32 fl1 = sge_params->sge_fl_buffer_size[1];
+	u32 fl_small_pg = sge_params->sge_fl_buffer_size[0];
+	u32 fl_large_pg = sge_params->sge_fl_buffer_size[1];
 	struct sge *s = &adapter->sge;
 
 	/*
@@ -2628,9 +2628,20 @@ int t4vf_sge_init(struct adapter *adapter)
 	 * the Physical Function Driver.  Ideally we should be able to deal
 	 * with _any_ configuration.  Practice is different ...
 	 */
-	if (fl0 != PAGE_SIZE || (fl1 != 0 && fl1 <= fl0)) {
+
+	/* We only bother using the Large Page logic if the Large Page Buffer
+	 * is larger than our Page Size Buffer.
+	 */
+	if (fl_large_pg <= fl_small_pg)
+		fl_large_pg = 0;
+
+	/* The Page Size Buffer must be exactly equal to our Page Size and the
+	 * Large Page Size Buffer should be 0 (per above) or a power of 2.
+	 */
+	if (fl_small_pg != PAGE_SIZE ||
+	    (fl_large_pg & (fl_large_pg - 1)) != 0) {
 		dev_err(adapter->pdev_dev, "bad SGE FL buffer sizes [%d, %d]\n",
-			fl0, fl1);
+			fl_small_pg, fl_large_pg);
 		return -EINVAL;
 	}
 	if ((sge_params->sge_control & RXPKTCPLMODE_F) !=
@@ -2642,8 +2653,8 @@ int t4vf_sge_init(struct adapter *adapter)
 	/*
 	 * Now translate the adapter parameters into our internal forms.
 	 */
-	if (fl1)
-		s->fl_pg_order = ilog2(fl1) - PAGE_SHIFT;
+	if (fl_large_pg)
+		s->fl_pg_order = ilog2(fl_large_pg) - PAGE_SHIFT;
 	s->stat_len = ((sge_params->sge_control & EGRSTATUSPAGESIZE_F)
 			? 128 : 64);
 	s->pktshift = PKTSHIFT_G(sge_params->sge_control);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index a0ef97e7f3c9..ff7a70ffafc6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2092,6 +2092,10 @@ static int hclge_get_autoneg(struct hnae3_handle *handle)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
+	struct phy_device *phydev = hdev->hw.mac.phydev;
+
+	if (phydev)
+		return phydev->autoneg;
 
 	hclge_query_autoneg_result(hdev);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
index 186772493711..d1e4dcec5db2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
@@ -1060,6 +1060,8 @@ hns3_nic_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats)
 	u64 rx_bytes = 0;
 	u64 tx_pkts = 0;
 	u64 rx_pkts = 0;
+	u64 tx_drop = 0;
+	u64 rx_drop = 0;
 
 	for (idx = 0; idx < queue_num; idx++) {
 		/* fetch the tx stats */
@@ -1068,6 +1070,8 @@ hns3_nic_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats)
 			start = u64_stats_fetch_begin_irq(&ring->syncp);
 			tx_bytes += ring->stats.tx_bytes;
 			tx_pkts += ring->stats.tx_pkts;
+			tx_drop += ring->stats.tx_busy;
+			tx_drop += ring->stats.sw_err_cnt;
 		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
 
 		/* fetch the rx stats */
@@ -1076,6 +1080,9 @@ hns3_nic_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats)
 			start = u64_stats_fetch_begin_irq(&ring->syncp);
 			rx_bytes += ring->stats.rx_bytes;
 			rx_pkts += ring->stats.rx_pkts;
+			rx_drop += ring->stats.non_vld_descs;
+			rx_drop += ring->stats.err_pkt_len;
+			rx_drop += ring->stats.l2_err;
 		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
 	}
 
@@ -1091,8 +1098,8 @@ hns3_nic_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats)
 	stats->rx_missed_errors = netdev->stats.rx_missed_errors;
 
 	stats->tx_errors = netdev->stats.tx_errors;
-	stats->rx_dropped = netdev->stats.rx_dropped;
-	stats->tx_dropped = netdev->stats.tx_dropped;
+	stats->rx_dropped = rx_drop + netdev->stats.rx_dropped;
+	stats->tx_dropped = tx_drop + netdev->stats.tx_dropped;
 	stats->collisions = netdev->stats.collisions;
 	stats->rx_over_errors = netdev->stats.rx_over_errors;
 	stats->rx_frame_errors = netdev->stats.rx_frame_errors;
@@ -1306,6 +1313,8 @@ static int hns3_nic_change_mtu(struct net_device *netdev, int new_mtu)
 		return ret;
 	}
 
+	netdev->mtu = new_mtu;
+
 	/* if the netdev was running earlier, bring it up again */
 	if (if_running && hns3_nic_net_open(netdev))
 		ret = -EINVAL;
@@ -2687,8 +2696,12 @@ static int hns3_uninit_all_ring(struct hns3_nic_priv *priv)
 			h->ae_algo->ops->reset_queue(h, i);
 
 		hns3_fini_ring(priv->ring_data[i].ring);
+		devm_kfree(priv->dev, priv->ring_data[i].ring);
 		hns3_fini_ring(priv->ring_data[i + h->kinfo.num_tqps].ring);
+		devm_kfree(priv->dev,
+			   priv->ring_data[i + h->kinfo.num_tqps].ring);
 	}
+	devm_kfree(priv->dev, priv->ring_data);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c
index e590d96e434a..a64a5a413d4d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c
@@ -22,7 +22,8 @@ struct hns3_stats {
 #define HNS3_TQP_STAT(_string, _member)	{			\
 	.stats_string = _string,				\
 	.stats_size = FIELD_SIZEOF(struct ring_stats, _member),	\
-	.stats_offset = offsetof(struct hns3_enet_ring, stats),	\
+	.stats_offset = offsetof(struct hns3_enet_ring, stats) +\
+			offsetof(struct ring_stats, _member),   \
 }								\
 
 static const struct hns3_stats hns3_txq_stats[] = {
@@ -189,13 +190,13 @@ static u64 *hns3_get_stats_tqps(struct hnae3_handle *handle, u64 *data)
 	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 	struct hns3_enet_ring *ring;
 	u8 *stat;
-	u32 i;
+	int i, j;
 
 	/* get stats for Tx */
 	for (i = 0; i < kinfo->num_tqps; i++) {
 		ring = nic_priv->ring_data[i].ring;
-		for (i = 0; i < HNS3_TXQ_STATS_COUNT; i++) {
-			stat = (u8 *)ring + hns3_txq_stats[i].stats_offset;
+		for (j = 0; j < HNS3_TXQ_STATS_COUNT; j++) {
+			stat = (u8 *)ring + hns3_txq_stats[j].stats_offset;
 			*data++ = *(u64 *)stat;
 		}
 	}
@@ -203,8 +204,8 @@ static u64 *hns3_get_stats_tqps(struct hnae3_handle *handle, u64 *data)
 	/* get stats for Rx */
 	for (i = 0; i < kinfo->num_tqps; i++) {
 		ring = nic_priv->ring_data[i + kinfo->num_tqps].ring;
-		for (i = 0; i < HNS3_RXQ_STATS_COUNT; i++) {
-			stat = (u8 *)ring + hns3_rxq_stats[i].stats_offset;
+		for (j = 0; j < HNS3_RXQ_STATS_COUNT; j++) {
+			stat = (u8 *)ring + hns3_rxq_stats[j].stats_offset;
 			*data++ = *(u64 *)stat;
 		}
 	}
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 3b0db01ead1f..3ae02b0620bc 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2209,6 +2209,12 @@ static irqreturn_t ibmvnic_interrupt_rx(int irq, void *instance)
 	struct ibmvnic_sub_crq_queue *scrq = instance;
 	struct ibmvnic_adapter *adapter = scrq->adapter;
 
+	/* When booting a kdump kernel we can hit pending interrupts
+	 * prior to completing driver initialization.
+	 */
+	if (unlikely(adapter->state != VNIC_OPEN))
+		return IRQ_NONE;
+
 	adapter->rx_stats_buffers[scrq->scrq_num].interrupts++;
 
 	if (napi_schedule_prep(&adapter->napi[scrq->scrq_num])) {
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 1ccad6f30ebf..4eb6ff60e8fc 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -1775,7 +1775,11 @@ static void i40evf_disable_vf(struct i40evf_adapter *adapter)
 
 	adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED;
 
-	if (netif_running(adapter->netdev)) {
+	/* We don't use netif_running() because it may be true prior to
+	 * ndo_open() returning, so we can't assume it means all our open
+	 * tasks have finished, since we're not holding the rtnl_lock here.
+	 */
+	if (adapter->state == __I40EVF_RUNNING) {
 		set_bit(__I40E_VSI_DOWN, adapter->vsi.state);
 		netif_carrier_off(adapter->netdev);
 		netif_tx_disable(adapter->netdev);
@@ -1833,6 +1837,7 @@ static void i40evf_reset_task(struct work_struct *work)
 	struct i40evf_mac_filter *f;
 	u32 reg_val;
 	int i = 0, err;
+	bool running;
 
 	while (test_and_set_bit(__I40EVF_IN_CLIENT_TASK,
 				&adapter->crit_section))
@@ -1892,7 +1897,13 @@ static void i40evf_reset_task(struct work_struct *work)
 	}
 
 continue_reset:
-	if (netif_running(netdev)) {
+	/* We don't use netif_running() because it may be true prior to
+	 * ndo_open() returning, so we can't assume it means all our open
+	 * tasks have finished, since we're not holding the rtnl_lock here.
+	 */
+	running = (adapter->state == __I40EVF_RUNNING);
+
+	if (running) {
 		netif_carrier_off(netdev);
 		netif_tx_stop_all_queues(netdev);
 		adapter->link_up = false;
@@ -1936,7 +1947,10 @@ static void i40evf_reset_task(struct work_struct *work)
 
 	mod_timer(&adapter->watchdog_timer, jiffies + 2);
 
-	if (netif_running(adapter->netdev)) {
+	/* We were running when the reset started, so we need to restore some
+	 * state here.
+	 */
+	if (running) {
 		/* allocate transmit descriptors */
 		err = i40evf_setup_all_tx_resources(adapter);
 		if (err)
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 1145cde2274a..b12e3a4f9439 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -5087,7 +5087,7 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	INIT_WORK(&hw->restart_work, sky2_restart);
 
 	pci_set_drvdata(pdev, hw);
-	pdev->d3_delay = 150;
+	pdev->d3_delay = 200;
 
 	return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
index 5f41dc92aa68..752a72499b4f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
@@ -156,57 +156,63 @@ static int mlx4_en_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num)
 static u8 mlx4_en_dcbnl_set_all(struct net_device *netdev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	struct mlx4_en_port_profile *prof = priv->prof;
 	struct mlx4_en_dev *mdev = priv->mdev;
+	u8 tx_pause, tx_ppp, rx_pause, rx_ppp;
 
 	if (!(priv->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
 		return 1;
 
 	if (priv->cee_config.pfc_state) {
 		int tc;
+		rx_ppp = prof->rx_ppp;
+		tx_ppp = prof->tx_ppp;
 
-		priv->prof->rx_pause = 0;
-		priv->prof->tx_pause = 0;
 		for (tc = 0; tc < CEE_DCBX_MAX_PRIO; tc++) {
 			u8 tc_mask = 1 << tc;
 
 			switch (priv->cee_config.dcb_pfc[tc]) {
 			case pfc_disabled:
-				priv->prof->tx_ppp &= ~tc_mask;
-				priv->prof->rx_ppp &= ~tc_mask;
+				tx_ppp &= ~tc_mask;
+				rx_ppp &= ~tc_mask;
 				break;
 			case pfc_enabled_full:
-				priv->prof->tx_ppp |= tc_mask;
-				priv->prof->rx_ppp |= tc_mask;
+				tx_ppp |= tc_mask;
+				rx_ppp |= tc_mask;
 				break;
 			case pfc_enabled_tx:
-				priv->prof->tx_ppp |= tc_mask;
-				priv->prof->rx_ppp &= ~tc_mask;
+				tx_ppp |= tc_mask;
+				rx_ppp &= ~tc_mask;
 				break;
 			case pfc_enabled_rx:
-				priv->prof->tx_ppp &= ~tc_mask;
-				priv->prof->rx_ppp |= tc_mask;
+				tx_ppp &= ~tc_mask;
+				rx_ppp |= tc_mask;
 				break;
 			default:
 				break;
 			}
 		}
-		en_dbg(DRV, priv, "Set pfc on\n");
+		rx_pause = !!(rx_ppp || tx_ppp) ? 0 : prof->rx_pause;
+		tx_pause = !!(rx_ppp || tx_ppp) ? 0 : prof->tx_pause;
 	} else {
-		priv->prof->rx_pause = 1;
-		priv->prof->tx_pause = 1;
-		en_dbg(DRV, priv, "Set pfc off\n");
+		rx_ppp = 0;
+		tx_ppp = 0;
+		rx_pause = prof->rx_pause;
+		tx_pause = prof->tx_pause;
 	}
 
 	if (mlx4_SET_PORT_general(mdev->dev, priv->port,
 				  priv->rx_skb_size + ETH_FCS_LEN,
-				  priv->prof->tx_pause,
-				  priv->prof->tx_ppp,
-				  priv->prof->rx_pause,
-				  priv->prof->rx_ppp)) {
+				  tx_pause, tx_ppp, rx_pause, rx_ppp)) {
 		en_err(priv, "Failed setting pause params\n");
 		return 1;
 	}
 
+	prof->tx_ppp = tx_ppp;
+	prof->rx_ppp = rx_ppp;
+	prof->tx_pause = tx_pause;
+	prof->rx_pause = rx_pause;
+
 	return 0;
 }
 
@@ -310,6 +316,7 @@ static int mlx4_en_ets_validate(struct mlx4_en_priv *priv, struct ieee_ets *ets)
 		}
 
 		switch (ets->tc_tsa[i]) {
+		case IEEE_8021QAZ_TSA_VENDOR:
 		case IEEE_8021QAZ_TSA_STRICT:
 			break;
 		case IEEE_8021QAZ_TSA_ETS:
@@ -347,6 +354,10 @@ static int mlx4_en_config_port_scheduler(struct mlx4_en_priv *priv,
 	/* higher TC means higher priority => lower pg */
 	for (i = IEEE_8021QAZ_MAX_TCS - 1; i >= 0; i--) {
 		switch (ets->tc_tsa[i]) {
+		case IEEE_8021QAZ_TSA_VENDOR:
+			pg[i] = MLX4_EN_TC_VENDOR;
+			tc_tx_bw[i] = MLX4_EN_BW_MAX;
+			break;
 		case IEEE_8021QAZ_TSA_STRICT:
 			pg[i] = num_strict++;
 			tc_tx_bw[i] = MLX4_EN_BW_MAX;
@@ -403,6 +414,7 @@ static int mlx4_en_dcbnl_ieee_setpfc(struct net_device *dev,
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_port_profile *prof = priv->prof;
 	struct mlx4_en_dev *mdev = priv->mdev;
+	u32 tx_pause, tx_ppp, rx_pause, rx_ppp;
 	int err;
 
 	en_dbg(DRV, priv, "cap: 0x%x en: 0x%x mbc: 0x%x delay: %d\n",
@@ -411,23 +423,26 @@ static int mlx4_en_dcbnl_ieee_setpfc(struct net_device *dev,
 			pfc->mbc,
 			pfc->delay);
 
-	prof->rx_pause = !pfc->pfc_en;
-	prof->tx_pause = !pfc->pfc_en;
-	prof->rx_ppp = pfc->pfc_en;
-	prof->tx_ppp = pfc->pfc_en;
+	rx_pause = prof->rx_pause && !pfc->pfc_en;
+	tx_pause = prof->tx_pause && !pfc->pfc_en;
+	rx_ppp = pfc->pfc_en;
+	tx_ppp = pfc->pfc_en;
 
 	err = mlx4_SET_PORT_general(mdev->dev, priv->port,
 				    priv->rx_skb_size + ETH_FCS_LEN,
-				    prof->tx_pause,
-				    prof->tx_ppp,
-				    prof->rx_pause,
-				    prof->rx_ppp);
-	if (err)
+				    tx_pause, tx_ppp, rx_pause, rx_ppp);
+	if (err) {
 		en_err(priv, "Failed setting pause params\n");
-	else
-		mlx4_en_update_pfc_stats_bitmap(mdev->dev, &priv->stats_bitmap,
-						prof->rx_ppp, prof->rx_pause,
-						prof->tx_ppp, prof->tx_pause);
+		return err;
+	}
+
+	mlx4_en_update_pfc_stats_bitmap(mdev->dev, &priv->stats_bitmap,
+					rx_ppp, rx_pause, tx_ppp, tx_pause);
+
+	prof->tx_ppp = tx_ppp;
+	prof->rx_ppp = rx_ppp;
+	prof->rx_pause = rx_pause;
+	prof->tx_pause = tx_pause;
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 3d4e4a5d00d1..67f74fcb265e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1046,27 +1046,32 @@ static int mlx4_en_set_pauseparam(struct net_device *dev,
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
+	u8 tx_pause, tx_ppp, rx_pause, rx_ppp;
 	int err;
 
 	if (pause->autoneg)
 		return -EINVAL;
 
-	priv->prof->tx_pause = pause->tx_pause != 0;
-	priv->prof->rx_pause = pause->rx_pause != 0;
+	tx_pause = !!(pause->tx_pause);
+	rx_pause = !!(pause->rx_pause);
+	rx_ppp = priv->prof->rx_ppp && !(tx_pause || rx_pause);
+	tx_ppp = priv->prof->tx_ppp && !(tx_pause || rx_pause);
+
 	err = mlx4_SET_PORT_general(mdev->dev, priv->port,
 				    priv->rx_skb_size + ETH_FCS_LEN,
-				    priv->prof->tx_pause,
-				    priv->prof->tx_ppp,
-				    priv->prof->rx_pause,
-				    priv->prof->rx_ppp);
-	if (err)
-		en_err(priv, "Failed setting pause params\n");
-	else
-		mlx4_en_update_pfc_stats_bitmap(mdev->dev, &priv->stats_bitmap,
-						priv->prof->rx_ppp,
-						priv->prof->rx_pause,
-						priv->prof->tx_ppp,
-						priv->prof->tx_pause);
+				    tx_pause, tx_ppp, rx_pause, rx_ppp);
+	if (err) {
+		en_err(priv, "Failed setting pause params, err = %d\n", err);
+		return err;
+	}
+
+	mlx4_en_update_pfc_stats_bitmap(mdev->dev, &priv->stats_bitmap,
+					rx_ppp, rx_pause, tx_ppp, tx_pause);
+
+	priv->prof->tx_pause = tx_pause;
+	priv->prof->rx_pause = rx_pause;
+	priv->prof->tx_ppp = tx_ppp;
+	priv->prof->rx_ppp = rx_ppp;
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index 686e18de9a97..6b2f7122b3ab 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -163,9 +163,9 @@ static void mlx4_en_get_profile(struct mlx4_en_dev *mdev)
 		params->udp_rss = 0;
 	}
 	for (i = 1; i <= MLX4_MAX_PORTS; i++) {
-		params->prof[i].rx_pause = 1;
+		params->prof[i].rx_pause = !(pfcrx || pfctx);
 		params->prof[i].rx_ppp = pfcrx;
-		params->prof[i].tx_pause = 1;
+		params->prof[i].tx_pause = !(pfcrx || pfctx);
 		params->prof[i].tx_ppp = pfctx;
 		params->prof[i].tx_ring_size = MLX4_EN_DEF_TX_RING_SIZE;
 		params->prof[i].rx_ring_size = MLX4_EN_DEF_RX_RING_SIZE;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 9c218f1cfc6c..c097eef41a9c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -3335,6 +3335,13 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	priv->msg_enable = MLX4_EN_MSG_LEVEL;
 #ifdef CONFIG_MLX4_EN_DCB
 	if (!mlx4_is_slave(priv->mdev->dev)) {
+		u8 prio;
+
+		for (prio = 0; prio < IEEE_8021QAZ_MAX_TCS; ++prio) {
+			priv->ets.prio_tc[prio] = prio;
+			priv->ets.tc_tsa[prio]  = IEEE_8021QAZ_TSA_VENDOR;
+		}
+
 		priv->dcbx_cap = DCB_CAP_DCBX_VER_CEE | DCB_CAP_DCBX_HOST |
 			DCB_CAP_DCBX_VER_IEEE;
 		priv->flags |= MLX4_EN_DCB_ENABLED;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index fdb3ad0cbe54..2c1a5ff6acfa 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -476,6 +476,7 @@ struct mlx4_en_frag_info {
 #define MLX4_EN_BW_MIN 1
 #define MLX4_EN_BW_MAX 100 /* Utilize 100% of the line */
 
+#define MLX4_EN_TC_VENDOR 0
 #define MLX4_EN_TC_ETS 7
 
 enum dcb_pfc_type {
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index fabb53379727..a069fcc823c3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -5089,6 +5089,7 @@ static void rem_slave_fs_rule(struct mlx4_dev *dev, int slave)
 						 &tracker->res_tree[RES_FS_RULE]);
 					list_del(&fs_rule->com.list);
 					spin_unlock_irq(mlx4_tlock(dev));
+					kfree(fs_rule->mirr_mbox);
 					kfree(fs_rule);
 					state = 0;
 					break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a863572882b2..225b2ad3e15f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2718,6 +2718,9 @@ int mlx5e_open(struct net_device *netdev)
 		mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_UP);
 	mutex_unlock(&priv->state_lock);
 
+	if (mlx5e_vxlan_allowed(priv->mdev))
+		udp_tunnel_get_rx_info(netdev);
+
 	return err;
 }
 
@@ -4276,13 +4279,6 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	if (netdev->reg_state != NETREG_REGISTERED)
 		return;
 
-	/* Device already registered: sync netdev system state */
-	if (mlx5e_vxlan_allowed(mdev)) {
-		rtnl_lock();
-		udp_tunnel_get_rx_info(netdev);
-		rtnl_unlock();
-	}
-
 	queue_work(priv->wq, &priv->set_rx_mode_work);
 
 	rtnl_lock();
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 45e03c427faf..5ffd1db4e797 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -43,6 +43,11 @@
 #include "en_tc.h"
 #include "fs_core.h"
 
+#define MLX5E_REP_PARAMS_LOG_SQ_SIZE \
+	max(0x6, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)
+#define MLX5E_REP_PARAMS_LOG_RQ_SIZE \
+	max(0x6, MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE)
+
 static const char mlx5e_rep_driver_name[] = "mlx5e_rep";
 
 static void mlx5e_rep_get_drvinfo(struct net_device *dev,
@@ -230,7 +235,7 @@ void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv)
 static void mlx5e_rep_neigh_update_init_interval(struct mlx5e_rep_priv *rpriv)
 {
 #if IS_ENABLED(CONFIG_IPV6)
-	unsigned long ipv6_interval = NEIGH_VAR(&ipv6_stub->nd_tbl->parms,
+	unsigned long ipv6_interval = NEIGH_VAR(&nd_tbl.parms,
 						DELAY_PROBE_TIME);
 #else
 	unsigned long ipv6_interval = ~0UL;
@@ -366,7 +371,7 @@ static int mlx5e_rep_netevent_event(struct notifier_block *nb,
 	case NETEVENT_NEIGH_UPDATE:
 		n = ptr;
 #if IS_ENABLED(CONFIG_IPV6)
-		if (n->tbl != ipv6_stub->nd_tbl && n->tbl != &arp_tbl)
+		if (n->tbl != &nd_tbl && n->tbl != &arp_tbl)
 #else
 		if (n->tbl != &arp_tbl)
 #endif
@@ -414,7 +419,7 @@ static int mlx5e_rep_netevent_event(struct notifier_block *nb,
 		 * done per device delay prob time parameter.
 		 */
 #if IS_ENABLED(CONFIG_IPV6)
-		if (!p->dev || (p->tbl != ipv6_stub->nd_tbl && p->tbl != &arp_tbl))
+		if (!p->dev || (p->tbl != &nd_tbl && p->tbl != &arp_tbl))
 #else
 		if (!p->dev || p->tbl != &arp_tbl)
 #endif
@@ -610,7 +615,6 @@ static int mlx5e_rep_open(struct net_device *dev)
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	int err;
 
 	mutex_lock(&priv->state_lock);
@@ -618,8 +622,9 @@ static int mlx5e_rep_open(struct net_device *dev)
 	if (err)
 		goto unlock;
 
-	if (!mlx5_eswitch_set_vport_state(esw, rep->vport,
-					  MLX5_ESW_VPORT_ADMIN_STATE_UP))
+	if (!mlx5_modify_vport_admin_state(priv->mdev,
+			MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
+			rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_UP))
 		netif_carrier_on(dev);
 
 unlock:
@@ -632,11 +637,12 @@ static int mlx5e_rep_close(struct net_device *dev)
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	int ret;
 
 	mutex_lock(&priv->state_lock);
-	(void)mlx5_eswitch_set_vport_state(esw, rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN);
+	mlx5_modify_vport_admin_state(priv->mdev,
+			MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
+			rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN);
 	ret = mlx5e_close_locked(dev);
 	mutex_unlock(&priv->state_lock);
 	return ret;
@@ -797,9 +803,9 @@ static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
 					 MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
 					 MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
 
-	params->log_sq_size = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
+	params->log_sq_size = MLX5E_REP_PARAMS_LOG_SQ_SIZE;
 	params->rq_wq_type  = MLX5_WQ_TYPE_LINKED_LIST;
-	params->log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
+	params->log_rq_size = MLX5E_REP_PARAMS_LOG_RQ_SIZE;
 
 	params->rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
 	mlx5e_set_rx_cq_mode_params(params, cq_period_mode);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 9ba1f72060aa..42bab73a9f40 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -484,7 +484,7 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
 		tbl = &arp_tbl;
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (m_neigh->family == AF_INET6)
-		tbl = ipv6_stub->nd_tbl;
+		tbl = &nd_tbl;
 #endif
 	else
 		return;
@@ -2091,19 +2091,19 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv,
 	if (err != -EAGAIN)
 		flow->flags |= MLX5E_TC_FLOW_OFFLOADED;
 
+	if (!(flow->flags & MLX5E_TC_FLOW_ESWITCH) ||
+	    !(flow->esw_attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP))
+		kvfree(parse_attr);
+
 	err = rhashtable_insert_fast(&tc->ht, &flow->node,
 				     tc->ht_params);
-	if (err)
-		goto err_del_rule;
+	if (err) {
+		mlx5e_tc_del_flow(priv, flow);
+		kfree(flow);
+	}
 
-	if (flow->flags & MLX5E_TC_FLOW_ESWITCH &&
-	    !(flow->esw_attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP))
-		kvfree(parse_attr);
 	return err;
 
-err_del_rule:
-	mlx5e_tc_del_flow(priv, flow);
-
 err_free:
 	kvfree(parse_attr);
 	kfree(flow);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index a1296a62497d..71153c0f1605 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -36,6 +36,9 @@
 #include <linux/mlx5/vport.h>
 #include "mlx5_core.h"
 
+/* Mutex to hold while enabling or disabling RoCE */
+static DEFINE_MUTEX(mlx5_roce_en_lock);
+
 static int _mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod,
 				   u16 vport, u32 *out, int outlen)
 {
@@ -998,17 +1001,35 @@ static int mlx5_nic_vport_update_roce_state(struct mlx5_core_dev *mdev,
 
 int mlx5_nic_vport_enable_roce(struct mlx5_core_dev *mdev)
 {
-	if (atomic_inc_return(&mdev->roce.roce_en) != 1)
-		return 0;
-	return mlx5_nic_vport_update_roce_state(mdev, MLX5_VPORT_ROCE_ENABLED);
+	int err = 0;
+
+	mutex_lock(&mlx5_roce_en_lock);
+	if (!mdev->roce.roce_en)
+		err = mlx5_nic_vport_update_roce_state(mdev, MLX5_VPORT_ROCE_ENABLED);
+
+	if (!err)
+		mdev->roce.roce_en++;
+	mutex_unlock(&mlx5_roce_en_lock);
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_nic_vport_enable_roce);
 
 int mlx5_nic_vport_disable_roce(struct mlx5_core_dev *mdev)
 {
-	if (atomic_dec_return(&mdev->roce.roce_en) != 0)
-		return 0;
-	return mlx5_nic_vport_update_roce_state(mdev, MLX5_VPORT_ROCE_DISABLED);
+	int err = 0;
+
+	mutex_lock(&mlx5_roce_en_lock);
+	if (mdev->roce.roce_en) {
+		mdev->roce.roce_en--;
+		if (mdev->roce.roce_en == 0)
+			err = mlx5_nic_vport_update_roce_state(mdev, MLX5_VPORT_ROCE_DISABLED);
+
+		if (err)
+			mdev->roce.roce_en++;
+	}
+	mutex_unlock(&mlx5_roce_en_lock);
+	return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_nic_vport_disable_roce);
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
index 37364555c42b..f88ff3f4b661 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
@@ -68,10 +68,11 @@
 /* CPP address to retrieve the data from */
 #define NSP_BUFFER		0x10
 #define   NSP_BUFFER_CPP	GENMASK_ULL(63, 40)
-#define   NSP_BUFFER_PCIE	GENMASK_ULL(39, 38)
-#define   NSP_BUFFER_ADDRESS	GENMASK_ULL(37, 0)
+#define   NSP_BUFFER_ADDRESS	GENMASK_ULL(39, 0)
 
 #define NSP_DFLT_BUFFER		0x18
+#define   NSP_DFLT_BUFFER_CPP	GENMASK_ULL(63, 40)
+#define   NSP_DFLT_BUFFER_ADDRESS	GENMASK_ULL(39, 0)
 
 #define NSP_DFLT_BUFFER_CONFIG	0x20
 #define   NSP_DFLT_BUFFER_SIZE_MB	GENMASK_ULL(7, 0)
@@ -412,8 +413,8 @@ static int nfp_nsp_command_buf(struct nfp_nsp *nsp, u16 code, u32 option,
 	if (err < 0)
 		return err;
 
-	cpp_id = FIELD_GET(NSP_BUFFER_CPP, reg) << 8;
-	cpp_buf = FIELD_GET(NSP_BUFFER_ADDRESS, reg);
+	cpp_id = FIELD_GET(NSP_DFLT_BUFFER_CPP, reg) << 8;
+	cpp_buf = FIELD_GET(NSP_DFLT_BUFFER_ADDRESS, reg);
 
 	if (in_buf && in_size) {
 		err = nfp_cpp_write(cpp, cpp_id, cpp_buf, in_buf, in_size);
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 619a1b7281a0..db553d4e8d22 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -8466,12 +8466,12 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_out_msi_5;
 	}
 
+	pci_set_drvdata(pdev, dev);
+
 	rc = register_netdev(dev);
 	if (rc < 0)
 		goto err_out_cnt_6;
 
-	pci_set_drvdata(pdev, dev);
-
 	netif_info(tp, probe, dev, "%s at 0x%p, %pM, XID %08x IRQ %d\n",
 		   rtl_chip_infos[chipset].name, ioaddr, dev->dev_addr,
 		   (u32)(RTL_R32(TxConfig) & 0x9cf0f8ff), pdev->irq);
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 6dde9a0cfe76..9b70a3af678e 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -464,7 +464,6 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	po->chan.mtu = dst_mtu(&rt->dst);
 	if (!po->chan.mtu)
 		po->chan.mtu = PPP_MRU;
-	ip_rt_put(rt);
 	po->chan.mtu -= PPTP_HEADER_OVERHEAD;
 
 	po->chan.hdrlen = 2 + sizeof(struct pptp_gre_header);
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 23cd41c82210..2a366554c503 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1197,11 +1197,6 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
 		goto err_dev_open;
 	}
 
-	netif_addr_lock_bh(dev);
-	dev_uc_sync_multiple(port_dev, dev);
-	dev_mc_sync_multiple(port_dev, dev);
-	netif_addr_unlock_bh(dev);
-
 	err = vlan_vids_add_by_dev(port_dev, dev);
 	if (err) {
 		netdev_err(dev, "Failed to add vlan ids to device %s\n",
@@ -1241,6 +1236,11 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
 		goto err_option_port_add;
 	}
 
+	netif_addr_lock_bh(dev);
+	dev_uc_sync_multiple(port_dev, dev);
+	dev_mc_sync_multiple(port_dev, dev);
+	netif_addr_unlock_bh(dev);
+
 	port->index = -1;
 	list_add_tail_rcu(&port->list, &team->port_list);
 	team_port_enable(team, port);
@@ -1265,8 +1265,6 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
 	vlan_vids_del_by_dev(port_dev, dev);
 
 err_vids_add:
-	dev_uc_unsync(port_dev, dev);
-	dev_mc_unsync(port_dev, dev);
 	dev_close(port_dev);
 
 err_dev_open:
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index a8dd1c7a08cb..89d82c4ee8df 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -2863,8 +2863,7 @@ static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf)
 	if (ret < 0) {
 		netdev_warn(dev->net,
 			    "lan78xx_setup_irq_domain() failed : %d", ret);
-		kfree(pdata);
-		return ret;
+		goto out1;
 	}
 
 	dev->net->hard_header_len += TX_OVERHEAD;
@@ -2872,14 +2871,32 @@ static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf)
 
 	/* Init all registers */
 	ret = lan78xx_reset(dev);
+	if (ret) {
+		netdev_warn(dev->net, "Registers INIT FAILED....");
+		goto out2;
+	}
 
 	ret = lan78xx_mdio_init(dev);
+	if (ret) {
+		netdev_warn(dev->net, "MDIO INIT FAILED.....");
+		goto out2;
+	}
 
 	dev->net->flags |= IFF_MULTICAST;
 
 	pdata->wol = WAKE_MAGIC;
 
 	return ret;
+
+out2:
+	lan78xx_remove_irq_domain(dev);
+
+out1:
+	netdev_warn(dev->net, "Bind routine FAILED");
+	cancel_work_sync(&pdata->set_multicast);
+	cancel_work_sync(&pdata->set_vlan);
+	kfree(pdata);
+	return ret;
 }
 
 static void lan78xx_unbind(struct lan78xx_net *dev, struct usb_interface *intf)
@@ -2891,6 +2908,8 @@ static void lan78xx_unbind(struct lan78xx_net *dev, struct usb_interface *intf)
 	lan78xx_remove_mdio(dev);
 
 	if (pdata) {
+		cancel_work_sync(&pdata->set_multicast);
+		cancel_work_sync(&pdata->set_vlan);
 		netif_dbg(dev, ifdown, dev->net, "free pdata");
 		kfree(pdata);
 		pdata = NULL;
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 67ecf2425b88..5c6a8ef54aec 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -579,12 +579,13 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 	if (!IS_ERR(neigh)) {
 		sock_confirm_neigh(skb, neigh);
 		ret = neigh_output(neigh, skb);
+		rcu_read_unlock_bh();
+		return ret;
 	}
 
 	rcu_read_unlock_bh();
 err:
-	if (unlikely(ret < 0))
-		vrf_tx_error(skb->dev, skb);
+	vrf_tx_error(skb->dev, skb);
 	return ret;
 }
 
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
index ecc96312a370..6fe0c6abe0d6 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
@@ -142,15 +142,25 @@ void rt2x00mac_tx(struct ieee80211_hw *hw,
 	if (!rt2x00dev->ops->hw->set_rts_threshold &&
 	    (tx_info->control.rates[0].flags & (IEEE80211_TX_RC_USE_RTS_CTS |
 						IEEE80211_TX_RC_USE_CTS_PROTECT))) {
-		if (rt2x00queue_available(queue) <= 1)
-			goto exit_fail;
+		if (rt2x00queue_available(queue) <= 1) {
+			/*
+			 * Recheck for full queue under lock to avoid race
+			 * conditions with rt2x00lib_txdone().
+			 */
+			spin_lock(&queue->tx_lock);
+			if (rt2x00queue_threshold(queue))
+				rt2x00queue_pause_queue(queue);
+			spin_unlock(&queue->tx_lock);
+
+			goto exit_free_skb;
+		}
 
 		if (rt2x00mac_tx_rts_cts(rt2x00dev, queue, skb))
-			goto exit_fail;
+			goto exit_free_skb;
 	}
 
 	if (unlikely(rt2x00queue_write_tx_frame(queue, skb, control->sta, false)))
-		goto exit_fail;
+		goto exit_free_skb;
 
 	/*
 	 * Pausing queue has to be serialized with rt2x00lib_txdone(). Note
@@ -164,10 +174,6 @@ void rt2x00mac_tx(struct ieee80211_hw *hw,
 
 	return;
 
- exit_fail:
-	spin_lock(&queue->tx_lock);
-	rt2x00queue_pause_queue(queue);
-	spin_unlock(&queue->tx_lock);
  exit_free_skb:
 	ieee80211_free_txskb(hw, skb);
 }
diff --git a/drivers/net/wireless/ti/wl1251/main.c b/drivers/net/wireless/ti/wl1251/main.c
index 6d02c660b4ab..037defd10b91 100644
--- a/drivers/net/wireless/ti/wl1251/main.c
+++ b/drivers/net/wireless/ti/wl1251/main.c
@@ -1200,8 +1200,7 @@ static void wl1251_op_bss_info_changed(struct ieee80211_hw *hw,
 		WARN_ON(wl->bss_type != BSS_TYPE_STA_BSS);
 
 		enable = bss_conf->arp_addr_cnt == 1 && bss_conf->assoc;
-		wl1251_acx_arp_ip_filter(wl, enable, addr);
-
+		ret = wl1251_acx_arp_ip_filter(wl, enable, addr);
 		if (ret < 0)
 			goto out_sleep;
 	}
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index 7b75d9de55ab..c0080f6ab2f5 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -204,6 +204,10 @@ struct fcloop_lport {
 	struct completion unreg_done;
 };
 
+struct fcloop_lport_priv {
+	struct fcloop_lport *lport;
+};
+
 struct fcloop_rport {
 	struct nvme_fc_remote_port *remoteport;
 	struct nvmet_fc_target_port *targetport;
@@ -370,6 +374,7 @@ fcloop_tgt_fcprqst_done_work(struct work_struct *work)
 
 	spin_lock(&tfcp_req->reqlock);
 	fcpreq = tfcp_req->fcpreq;
+	tfcp_req->fcpreq = NULL;
 	spin_unlock(&tfcp_req->reqlock);
 
 	if (tport->remoteport && fcpreq) {
@@ -611,11 +616,7 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport,
 
 	if (!tfcp_req)
 		/* abort has already been called */
-		return;
-
-	if (rport->targetport)
-		nvmet_fc_rcv_fcp_abort(rport->targetport,
-					&tfcp_req->tgt_fcp_req);
+		goto finish;
 
 	/* break initiator/target relationship for io */
 	spin_lock(&tfcp_req->reqlock);
@@ -623,6 +624,11 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport,
 	tfcp_req->fcpreq = NULL;
 	spin_unlock(&tfcp_req->reqlock);
 
+	if (rport->targetport)
+		nvmet_fc_rcv_fcp_abort(rport->targetport,
+					&tfcp_req->tgt_fcp_req);
+
+finish:
 	/* post the aborted io completion */
 	fcpreq->status = -ECANCELED;
 	schedule_work(&inireq->iniwork);
@@ -657,7 +663,8 @@ fcloop_nport_get(struct fcloop_nport *nport)
 static void
 fcloop_localport_delete(struct nvme_fc_local_port *localport)
 {
-	struct fcloop_lport *lport = localport->private;
+	struct fcloop_lport_priv *lport_priv = localport->private;
+	struct fcloop_lport *lport = lport_priv->lport;
 
 	/* release any threads waiting for the unreg to complete */
 	complete(&lport->unreg_done);
@@ -697,7 +704,7 @@ static struct nvme_fc_port_template fctemplate = {
 	.max_dif_sgl_segments	= FCLOOP_SGL_SEGS,
 	.dma_boundary		= FCLOOP_DMABOUND_4G,
 	/* sizes of additional private data for data structures */
-	.local_priv_sz		= sizeof(struct fcloop_lport),
+	.local_priv_sz		= sizeof(struct fcloop_lport_priv),
 	.remote_priv_sz		= sizeof(struct fcloop_rport),
 	.lsrqst_priv_sz		= sizeof(struct fcloop_lsreq),
 	.fcprqst_priv_sz	= sizeof(struct fcloop_ini_fcpreq),
@@ -728,11 +735,17 @@ fcloop_create_local_port(struct device *dev, struct device_attribute *attr,
 	struct fcloop_ctrl_options *opts;
 	struct nvme_fc_local_port *localport;
 	struct fcloop_lport *lport;
-	int ret;
+	struct fcloop_lport_priv *lport_priv;
+	unsigned long flags;
+	int ret = -ENOMEM;
+
+	lport = kzalloc(sizeof(*lport), GFP_KERNEL);
+	if (!lport)
+		return -ENOMEM;
 
 	opts = kzalloc(sizeof(*opts), GFP_KERNEL);
 	if (!opts)
-		return -ENOMEM;
+		goto out_free_lport;
 
 	ret = fcloop_parse_options(opts, buf);
 	if (ret)
@@ -752,23 +765,25 @@ fcloop_create_local_port(struct device *dev, struct device_attribute *attr,
 
 	ret = nvme_fc_register_localport(&pinfo, &fctemplate, NULL, &localport);
 	if (!ret) {
-		unsigned long flags;
-
 		/* success */
-		lport = localport->private;
+		lport_priv = localport->private;
+		lport_priv->lport = lport;
+
 		lport->localport = localport;
 		INIT_LIST_HEAD(&lport->lport_list);
 
 		spin_lock_irqsave(&fcloop_lock, flags);
 		list_add_tail(&lport->lport_list, &fcloop_lports);
 		spin_unlock_irqrestore(&fcloop_lock, flags);
-
-		/* mark all of the input buffer consumed */
-		ret = count;
 	}
 
 out_free_opts:
 	kfree(opts);
+out_free_lport:
+	/* free only if we're going to fail */
+	if (ret)
+		kfree(lport);
+
 	return ret ? ret : count;
 }
 
@@ -790,6 +805,8 @@ __wait_localport_unreg(struct fcloop_lport *lport)
 
 	wait_for_completion(&lport->unreg_done);
 
+	kfree(lport);
+
 	return ret;
 }
 
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 0f3a02495aeb..beeb7cbb5015 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -46,6 +46,9 @@
 #define BYT_TRIG_POS		BIT(25)
 #define BYT_TRIG_LVL		BIT(24)
 #define BYT_DEBOUNCE_EN		BIT(20)
+#define BYT_GLITCH_FILTER_EN	BIT(19)
+#define BYT_GLITCH_F_SLOW_CLK	BIT(17)
+#define BYT_GLITCH_F_FAST_CLK	BIT(16)
 #define BYT_PULL_STR_SHIFT	9
 #define BYT_PULL_STR_MASK	(3 << BYT_PULL_STR_SHIFT)
 #define BYT_PULL_STR_2K		(0 << BYT_PULL_STR_SHIFT)
@@ -1579,6 +1582,9 @@ static int byt_irq_type(struct irq_data *d, unsigned int type)
 	 */
 	value &= ~(BYT_DIRECT_IRQ_EN | BYT_TRIG_POS | BYT_TRIG_NEG |
 		   BYT_TRIG_LVL);
+	/* Enable glitch filtering */
+	value |= BYT_GLITCH_FILTER_EN | BYT_GLITCH_F_SLOW_CLK |
+		 BYT_GLITCH_F_FAST_CLK;
 
 	writel(value, reg);
 
diff --git a/drivers/power/supply/axp288_charger.c b/drivers/power/supply/axp288_charger.c
index d51ebd1da65e..9dc7590e07cb 100644
--- a/drivers/power/supply/axp288_charger.c
+++ b/drivers/power/supply/axp288_charger.c
@@ -785,6 +785,14 @@ static int charger_init_hw_regs(struct axp288_chrg_info *info)
 	return 0;
 }
 
+static void axp288_charger_cancel_work(void *data)
+{
+	struct axp288_chrg_info *info = data;
+
+	cancel_work_sync(&info->otg.work);
+	cancel_work_sync(&info->cable.work);
+}
+
 static int axp288_charger_probe(struct platform_device *pdev)
 {
 	int ret, i, pirq;
@@ -836,6 +844,11 @@ static int axp288_charger_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	/* Cancel our work on cleanup, register this before the notifiers */
+	ret = devm_add_action(dev, axp288_charger_cancel_work, info);
+	if (ret)
+		return ret;
+
 	/* Register for extcon notification */
 	INIT_WORK(&info->cable.work, axp288_charger_extcon_evt_worker);
 	info->cable.nb[0].notifier_call = axp288_charger_handle_cable0_evt;
diff --git a/drivers/rtc/rtc-ac100.c b/drivers/rtc/rtc-ac100.c
index 0e358d4b6738..8ff9dc3fe5bf 100644
--- a/drivers/rtc/rtc-ac100.c
+++ b/drivers/rtc/rtc-ac100.c
@@ -137,13 +137,15 @@ static unsigned long ac100_clkout_recalc_rate(struct clk_hw *hw,
 		div = (reg >> AC100_CLKOUT_PRE_DIV_SHIFT) &
 			((1 << AC100_CLKOUT_PRE_DIV_WIDTH) - 1);
 		prate = divider_recalc_rate(hw, prate, div,
-					    ac100_clkout_prediv, 0);
+					    ac100_clkout_prediv, 0,
+					    AC100_CLKOUT_PRE_DIV_WIDTH);
 	}
 
 	div = (reg >> AC100_CLKOUT_DIV_SHIFT) &
 		(BIT(AC100_CLKOUT_DIV_WIDTH) - 1);
 	return divider_recalc_rate(hw, prate, div, NULL,
-				   CLK_DIVIDER_POWER_OF_TWO);
+				   CLK_DIVIDER_POWER_OF_TWO,
+				   AC100_CLKOUT_DIV_WIDTH);
 }
 
 static long ac100_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index f8dc1601efd5..bddbe2da5283 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -1696,6 +1696,15 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc)
 		 */
 		switch (session->state) {
 		case ISCSI_STATE_FAILED:
+			/*
+			 * cmds should fail during shutdown, if the session
+			 * state is bad, allowing completion to happen
+			 */
+			if (unlikely(system_state != SYSTEM_RUNNING)) {
+				reason = FAILURE_SESSION_FAILED;
+				sc->result = DID_NO_CONNECT << 16;
+				break;
+			}
 		case ISCSI_STATE_IN_RECOVERY:
 			reason = FAILURE_SESSION_IN_RECOVERY;
 			sc->result = DID_IMM_RETRY << 16;
@@ -1980,6 +1989,19 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
 	}
 
 	if (session->state != ISCSI_STATE_LOGGED_IN) {
+		/*
+		 * During shutdown, if session is prematurely disconnected,
+		 * recovery won't happen and there will be hung cmds. Not
+		 * handling cmds would trigger EH, also bad in this case.
+		 * Instead, handle cmd, allow completion to happen and let
+		 * upper layer to deal with the result.
+		 */
+		if (unlikely(system_state != SYSTEM_RUNNING)) {
+			sc->result = DID_NO_CONNECT << 16;
+			ISCSI_DBG_EH(session, "sc on shutdown, handled\n");
+			rc = BLK_EH_HANDLED;
+			goto done;
+		}
 		/*
 		 * We are probably in the middle of iscsi recovery so let
 		 * that complete and handle the error.
@@ -2084,7 +2106,7 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
 		task->last_timeout = jiffies;
 	spin_unlock(&session->frwd_lock);
 	ISCSI_DBG_EH(session, "return %s\n", rc == BLK_EH_RESET_TIMER ?
-		     "timer reset" : "nh");
+		     "timer reset" : "shutdown or nh");
 	return rc;
 }
 EXPORT_SYMBOL_GPL(iscsi_eh_cmd_timed_out);
diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c
index 324d8d8c62de..e2ea389fbec3 100644
--- a/drivers/scsi/libsas/sas_expander.c
+++ b/drivers/scsi/libsas/sas_expander.c
@@ -293,6 +293,7 @@ static void sas_set_ex_phy(struct domain_device *dev, int phy_id, void *rsp)
 	phy->phy->minimum_linkrate = dr->pmin_linkrate;
 	phy->phy->maximum_linkrate = dr->pmax_linkrate;
 	phy->phy->negotiated_linkrate = phy->linkrate;
+	phy->phy->enabled = (phy->linkrate != SAS_PHY_DISABLED);
 
  skip:
 	if (new_phy)
@@ -686,7 +687,7 @@ int sas_smp_get_phy_events(struct sas_phy *phy)
 	res = smp_execute_task(dev, req, RPEL_REQ_SIZE,
 			            resp, RPEL_RESP_SIZE);
 
-	if (!res)
+	if (res)
 		goto out;
 
 	phy->invalid_dword_count = scsi_to_u32(&resp[12]);
@@ -695,6 +696,7 @@ int sas_smp_get_phy_events(struct sas_phy *phy)
 	phy->phy_reset_problem_count = scsi_to_u32(&resp[24]);
 
  out:
+	kfree(req);
 	kfree(resp);
 	return res;
 
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index e518dadc8161..4beb4dd2bee8 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -6605,7 +6605,6 @@ static void megasas_detach_one(struct pci_dev *pdev)
 	u32 pd_seq_map_sz;
 
 	instance = pci_get_drvdata(pdev);
-	instance->unload = 1;
 	host = instance->host;
 	fusion = instance->ctrl_context;
 
@@ -6616,6 +6615,7 @@ static void megasas_detach_one(struct pci_dev *pdev)
 	if (instance->fw_crash_state != UNAVAILABLE)
 		megasas_free_host_crash_buffer(instance);
 	scsi_remove_host(instance->host);
+	instance->unload = 1;
 
 	if (megasas_wait_for_adapter_operational(instance))
 		goto skip_firing_dcmds;
diff --git a/drivers/scsi/megaraid/megaraid_sas_fp.c b/drivers/scsi/megaraid/megaraid_sas_fp.c
index ecc699a65bac..08945142b9f8 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fp.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fp.c
@@ -168,7 +168,7 @@ static struct MR_LD_SPAN *MR_LdSpanPtrGet(u32 ld, u32 span,
 /*
  * This function will Populate Driver Map using firmware raid map
  */
-void MR_PopulateDrvRaidMap(struct megasas_instance *instance)
+static int MR_PopulateDrvRaidMap(struct megasas_instance *instance)
 {
 	struct fusion_context *fusion = instance->ctrl_context;
 	struct MR_FW_RAID_MAP_ALL     *fw_map_old    = NULL;
@@ -259,7 +259,7 @@ void MR_PopulateDrvRaidMap(struct megasas_instance *instance)
 		ld_count = (u16)le16_to_cpu(fw_map_ext->ldCount);
 		if (ld_count > MAX_LOGICAL_DRIVES_EXT) {
 			dev_dbg(&instance->pdev->dev, "megaraid_sas: LD count exposed in RAID map in not valid\n");
-			return;
+			return 1;
 		}
 
 		pDrvRaidMap->ldCount = (__le16)cpu_to_le16(ld_count);
@@ -285,6 +285,12 @@ void MR_PopulateDrvRaidMap(struct megasas_instance *instance)
 			fusion->ld_map[(instance->map_id & 1)];
 		pFwRaidMap = &fw_map_old->raidMap;
 		ld_count = (u16)le32_to_cpu(pFwRaidMap->ldCount);
+		if (ld_count > MAX_LOGICAL_DRIVES) {
+			dev_dbg(&instance->pdev->dev,
+				"LD count exposed in RAID map in not valid\n");
+			return 1;
+		}
+
 		pDrvRaidMap->totalSize = pFwRaidMap->totalSize;
 		pDrvRaidMap->ldCount = (__le16)cpu_to_le16(ld_count);
 		pDrvRaidMap->fpPdIoTimeoutSec = pFwRaidMap->fpPdIoTimeoutSec;
@@ -300,6 +306,8 @@ void MR_PopulateDrvRaidMap(struct megasas_instance *instance)
 			sizeof(struct MR_DEV_HANDLE_INFO) *
 			MAX_RAIDMAP_PHYSICAL_DEVICES);
 	}
+
+	return 0;
 }
 
 /*
@@ -317,8 +325,8 @@ u8 MR_ValidateMapInfo(struct megasas_instance *instance)
 	u16 ld;
 	u32 expected_size;
 
-
-	MR_PopulateDrvRaidMap(instance);
+	if (MR_PopulateDrvRaidMap(instance))
+		return 0;
 
 	fusion = instance->ctrl_context;
 	drv_map = fusion->ld_drv_map[(instance->map_id & 1)];
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index beb4bf8fe9b0..139219c994e9 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -4106,19 +4106,6 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 		return 0;
 	}
 
-	/*
-	 * Bug work around for firmware SATL handling.  The loop
-	 * is based on atomic operations and ensures consistency
-	 * since we're lockless at this point
-	 */
-	do {
-		if (test_bit(0, &sas_device_priv_data->ata_command_pending)) {
-			scmd->result = SAM_STAT_BUSY;
-			scmd->scsi_done(scmd);
-			return 0;
-		}
-	} while (_scsih_set_satl_pending(scmd, true));
-
 	sas_target_priv_data = sas_device_priv_data->sas_target;
 
 	/* invalid device handle */
@@ -4144,6 +4131,19 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 	    sas_device_priv_data->block)
 		return SCSI_MLQUEUE_DEVICE_BUSY;
 
+	/*
+	 * Bug work around for firmware SATL handling.  The loop
+	 * is based on atomic operations and ensures consistency
+	 * since we're lockless at this point
+	 */
+	do {
+		if (test_bit(0, &sas_device_priv_data->ata_command_pending)) {
+			scmd->result = SAM_STAT_BUSY;
+			scmd->scsi_done(scmd);
+			return 0;
+		}
+	} while (_scsih_set_satl_pending(scmd, true));
+
 	if (scmd->sc_data_direction == DMA_FROM_DEVICE)
 		mpi_control = MPI2_SCSIIO_CONTROL_READ;
 	else if (scmd->sc_data_direction == DMA_TO_DEVICE)
@@ -4170,6 +4170,7 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 	if (!smid) {
 		pr_err(MPT3SAS_FMT "%s: failed obtaining a smid\n",
 		    ioc->name, __func__);
+		_scsih_set_satl_pending(scmd, false);
 		goto out;
 	}
 	mpi_request = mpt3sas_base_get_msg_frame(ioc, smid);
@@ -4200,6 +4201,7 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 	if (mpi_request->DataLength) {
 		if (ioc->build_sg_scmd(ioc, scmd, smid)) {
 			mpt3sas_base_free_smid(ioc, smid);
+			_scsih_set_satl_pending(scmd, false);
 			goto out;
 		}
 	} else
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index 092a5fc85b9a..2770fbd4ce49 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -797,11 +797,21 @@ static int sh_msiof_dma_once(struct sh_msiof_spi_priv *p, const void *tx,
 		goto stop_dma;
 	}
 
-	/* wait for tx fifo to be emptied / rx fifo to be filled */
+	/* wait for tx/rx DMA completion */
 	ret = sh_msiof_wait_for_completion(p);
 	if (ret)
 		goto stop_reset;
 
+	if (!rx) {
+		reinit_completion(&p->done);
+		sh_msiof_write(p, IER, IER_TEOFE);
+
+		/* wait for tx fifo to be emptied */
+		ret = sh_msiof_wait_for_completion(p);
+		if (ret)
+			goto stop_reset;
+	}
+
 	/* clear status bits */
 	sh_msiof_reset_str(p);
 
diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
index 2da051c0d251..a4bb93b440a5 100644
--- a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
+++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
@@ -528,19 +528,20 @@ EXPORT_SYMBOL(cfs_cpt_spread_node);
 int
 cfs_cpt_current(struct cfs_cpt_table *cptab, int remap)
 {
-	int cpu = smp_processor_id();
-	int cpt = cptab->ctb_cpu2cpt[cpu];
+	int cpu;
+	int cpt;
 
-	if (cpt < 0) {
-		if (!remap)
-			return cpt;
+	preempt_disable();
+	cpu = smp_processor_id();
+	cpt = cptab->ctb_cpu2cpt[cpu];
 
+	if (cpt < 0 && remap) {
 		/* don't return negative value for safety of upper layer,
 		 * instead we shadow the unknown cpu to a valid partition ID
 		 */
 		cpt = cpu % cptab->ctb_nparts;
 	}
-
+	preempt_enable();
 	return cpt;
 }
 EXPORT_SYMBOL(cfs_cpt_current);
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 942d094269fb..c4a5fb6f038f 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -796,6 +796,13 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
 		int ret;
 		DEFINE_WAIT(__wait);
 
+		/*
+		 * Don't leave commands partially setup because the unmap
+		 * thread might need the blocks to make forward progress.
+		 */
+		tcmu_cmd_free_data(tcmu_cmd, tcmu_cmd->dbi_cur);
+		tcmu_cmd_reset_dbi_cur(tcmu_cmd);
+
 		prepare_to_wait(&udev->wait_cmdr, &__wait, TASK_INTERRUPTIBLE);
 
 		pr_debug("sleeping for ring space\n");
diff --git a/drivers/thermal/int340x_thermal/int3400_thermal.c b/drivers/thermal/int340x_thermal/int3400_thermal.c
index 8ee38f55c7f3..43b90fd577e4 100644
--- a/drivers/thermal/int340x_thermal/int3400_thermal.c
+++ b/drivers/thermal/int340x_thermal/int3400_thermal.c
@@ -319,17 +319,21 @@ static int int3400_thermal_probe(struct platform_device *pdev)
 
 	result = sysfs_create_group(&pdev->dev.kobj, &uuid_attribute_group);
 	if (result)
-		goto free_zone;
+		goto free_rel_misc;
 
 	result = acpi_install_notify_handler(
 			priv->adev->handle, ACPI_DEVICE_NOTIFY, int3400_notify,
 			(void *)priv);
 	if (result)
-		goto free_zone;
+		goto free_sysfs;
 
 	return 0;
 
-free_zone:
+free_sysfs:
+	sysfs_remove_group(&pdev->dev.kobj, &uuid_attribute_group);
+free_rel_misc:
+	if (!priv->rel_misc_dev_res)
+		acpi_thermal_rel_misc_device_remove(priv->adev->handle);
 	thermal_zone_device_unregister(priv->thermal);
 free_art_trt:
 	kfree(priv->trts);
diff --git a/drivers/thermal/power_allocator.c b/drivers/thermal/power_allocator.c
index b4d3116cfdaf..3055f9a12a17 100644
--- a/drivers/thermal/power_allocator.c
+++ b/drivers/thermal/power_allocator.c
@@ -523,6 +523,7 @@ static void allow_maximum_power(struct thermal_zone_device *tz)
 	struct thermal_instance *instance;
 	struct power_allocator_params *params = tz->governor_data;
 
+	mutex_lock(&tz->lock);
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
 		if ((instance->trip != params->trip_max_desired_temperature) ||
 		    (!cdev_is_power_actor(instance->cdev)))
@@ -534,6 +535,7 @@ static void allow_maximum_power(struct thermal_zone_device *tz)
 		mutex_unlock(&instance->cdev->lock);
 		thermal_cdev_update(instance->cdev);
 	}
+	mutex_unlock(&tz->lock);
 }
 
 /**
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index 0a3c9665e015..7253e8d2c6d9 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -1463,6 +1463,10 @@ static void gsm_dlci_open(struct gsm_dlci *dlci)
  *	in which case an opening port goes back to closed and a closing port
  *	is simply put into closed state (any further frames from the other
  *	end will get a DM response)
+ *
+ *	Some control dlci can stay in ADM mode with other dlci working just
+ *	fine. In that case we can just keep the control dlci open after the
+ *	DLCI_OPENING retries time out.
  */
 
 static void gsm_dlci_t1(unsigned long data)
@@ -1476,8 +1480,15 @@ static void gsm_dlci_t1(unsigned long data)
 		if (dlci->retries) {
 			gsm_command(dlci->gsm, dlci->addr, SABM|PF);
 			mod_timer(&dlci->t1, jiffies + gsm->t1 * HZ / 100);
-		} else
+		} else if (!dlci->addr && gsm->control == (DM | PF)) {
+			if (debug & 8)
+				pr_info("DLCI %d opening in ADM mode.\n",
+					dlci->addr);
+			gsm_dlci_open(dlci);
+		} else {
 			gsm_dlci_close(dlci);
+		}
+
 		break;
 	case DLCI_CLOSING:
 		dlci->retries--;
@@ -1495,8 +1506,8 @@ static void gsm_dlci_t1(unsigned long data)
  *	@dlci: DLCI to open
  *
  *	Commence opening a DLCI from the Linux side. We issue SABM messages
- *	to the modem which should then reply with a UA, at which point we
- *	will move into open state. Opening is done asynchronously with retry
+ *	to the modem which should then reply with a UA or ADM, at which point
+ *	we will move into open state. Opening is done asynchronously with retry
  *	running off timers and the responses.
  */
 
diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c
index 48d5327d38d4..fe5cdda80b2c 100644
--- a/drivers/uio/uio_hv_generic.c
+++ b/drivers/uio/uio_hv_generic.c
@@ -124,6 +124,13 @@ hv_uio_probe(struct hv_device *dev,
 	if (ret)
 		goto fail;
 
+	/* Communicating with host has to be via shared memory not hypercall */
+	if (!dev->channel->offermsg.monitor_allocated) {
+		dev_err(&dev->device, "vmbus channel requires hypercall\n");
+		ret = -ENOTSUPP;
+		goto fail_close;
+	}
+
 	dev->channel->inbound.ring_buffer->interrupt_mask = 1;
 	set_channel_read_mode(dev->channel, HV_CALL_DIRECT);
 
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 082891dffd9d..b0d606b2d06c 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -622,7 +622,7 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 
 	if (!len && vq->busyloop_timeout) {
 		/* Both tx vq and rx socket were polled here */
-		mutex_lock(&vq->mutex);
+		mutex_lock_nested(&vq->mutex, 1);
 		vhost_disable_notify(&net->dev, vq);
 
 		preempt_disable();
@@ -755,7 +755,7 @@ static void handle_rx(struct vhost_net *net)
 	struct iov_iter fixup;
 	__virtio16 num_buffers;
 
-	mutex_lock(&vq->mutex);
+	mutex_lock_nested(&vq->mutex, 0);
 	sock = vq->private_data;
 	if (!sock)
 		goto out;
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index a827c1a684a9..c692e0b13242 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -213,8 +213,7 @@ int vhost_poll_start(struct vhost_poll *poll, struct file *file)
 	if (mask)
 		vhost_poll_wakeup(&poll->wait, 0, 0, (void *)mask);
 	if (mask & POLLERR) {
-		if (poll->wqh)
-			remove_wait_queue(poll->wqh, &poll->wait);
+		vhost_poll_stop(poll);
 		ret = -EINVAL;
 	}
 
@@ -1253,14 +1252,12 @@ static int vq_log_access_ok(struct vhost_virtqueue *vq,
 /* Caller should have vq mutex and device mutex */
 int vhost_vq_access_ok(struct vhost_virtqueue *vq)
 {
-	if (vq->iotlb) {
-		/* When device IOTLB was used, the access validation
-		 * will be validated during prefetching.
-		 */
-		return 1;
-	}
-	return vq_access_ok(vq, vq->num, vq->desc, vq->avail, vq->used) &&
-		vq_log_access_ok(vq, vq->log_base);
+	int ret = vq_log_access_ok(vq, vq->log_base);
+
+	if (ret || vq->iotlb)
+		return ret;
+
+	return vq_access_ok(vq, vq->num, vq->desc, vq->avail, vq->used);
 }
 EXPORT_SYMBOL_GPL(vhost_vq_access_ok);
 
diff --git a/drivers/video/backlight/corgi_lcd.c b/drivers/video/backlight/corgi_lcd.c
index d7c239ea3d09..f5574060f9c8 100644
--- a/drivers/video/backlight/corgi_lcd.c
+++ b/drivers/video/backlight/corgi_lcd.c
@@ -177,7 +177,7 @@ static int corgi_ssp_lcdtg_send(struct corgi_lcd *lcd, int adrs, uint8_t data)
 	struct spi_message msg;
 	struct spi_transfer xfer = {
 		.len		= 1,
-		.cs_change	= 1,
+		.cs_change	= 0,
 		.tx_buf		= lcd->buf,
 	};
 
diff --git a/drivers/video/backlight/tdo24m.c b/drivers/video/backlight/tdo24m.c
index eab1f842f9c0..e4bd63e9db6b 100644
--- a/drivers/video/backlight/tdo24m.c
+++ b/drivers/video/backlight/tdo24m.c
@@ -369,7 +369,7 @@ static int tdo24m_probe(struct spi_device *spi)
 
 	spi_message_init(m);
 
-	x->cs_change = 1;
+	x->cs_change = 0;
 	x->tx_buf = &lcd->buf[0];
 	spi_message_add_tail(x, m);
 
diff --git a/drivers/video/backlight/tosa_lcd.c b/drivers/video/backlight/tosa_lcd.c
index 6a41ea92737a..4dc5ee8debeb 100644
--- a/drivers/video/backlight/tosa_lcd.c
+++ b/drivers/video/backlight/tosa_lcd.c
@@ -49,7 +49,7 @@ static int tosa_tg_send(struct spi_device *spi, int adrs, uint8_t data)
 	struct spi_message msg;
 	struct spi_transfer xfer = {
 		.len		= 1,
-		.cs_change	= 1,
+		.cs_change	= 0,
 		.tx_buf		= buf,
 	};
 
diff --git a/drivers/video/fbdev/vfb.c b/drivers/video/fbdev/vfb.c
index da653a080394..54127905bfe7 100644
--- a/drivers/video/fbdev/vfb.c
+++ b/drivers/video/fbdev/vfb.c
@@ -239,8 +239,23 @@ static int vfb_check_var(struct fb_var_screeninfo *var,
  */
 static int vfb_set_par(struct fb_info *info)
 {
+	switch (info->var.bits_per_pixel) {
+	case 1:
+		info->fix.visual = FB_VISUAL_MONO01;
+		break;
+	case 8:
+		info->fix.visual = FB_VISUAL_PSEUDOCOLOR;
+		break;
+	case 16:
+	case 24:
+	case 32:
+		info->fix.visual = FB_VISUAL_TRUECOLOR;
+		break;
+	}
+
 	info->fix.line_length = get_line_length(info->var.xres_virtual,
 						info->var.bits_per_pixel);
+
 	return 0;
 }
 
@@ -450,6 +465,8 @@ static int vfb_probe(struct platform_device *dev)
 		goto err2;
 	platform_set_drvdata(dev, info);
 
+	vfb_set_par(info);
+
 	fb_info(info, "Virtual frame buffer device, using %ldK of video memory\n",
 		videomemorysize >> 10);
 	return 0;
diff --git a/drivers/watchdog/dw_wdt.c b/drivers/watchdog/dw_wdt.c
index 36be987ff9ef..c2f4ff516230 100644
--- a/drivers/watchdog/dw_wdt.c
+++ b/drivers/watchdog/dw_wdt.c
@@ -127,14 +127,27 @@ static int dw_wdt_start(struct watchdog_device *wdd)
 
 	dw_wdt_set_timeout(wdd, wdd->timeout);
 
-	set_bit(WDOG_HW_RUNNING, &wdd->status);
-
 	writel(WDOG_CONTROL_REG_WDT_EN_MASK,
 	       dw_wdt->regs + WDOG_CONTROL_REG_OFFSET);
 
 	return 0;
 }
 
+static int dw_wdt_stop(struct watchdog_device *wdd)
+{
+	struct dw_wdt *dw_wdt = to_dw_wdt(wdd);
+
+	if (!dw_wdt->rst) {
+		set_bit(WDOG_HW_RUNNING, &wdd->status);
+		return 0;
+	}
+
+	reset_control_assert(dw_wdt->rst);
+	reset_control_deassert(dw_wdt->rst);
+
+	return 0;
+}
+
 static int dw_wdt_restart(struct watchdog_device *wdd,
 			  unsigned long action, void *data)
 {
@@ -173,6 +186,7 @@ static const struct watchdog_info dw_wdt_ident = {
 static const struct watchdog_ops dw_wdt_ops = {
 	.owner		= THIS_MODULE,
 	.start		= dw_wdt_start,
+	.stop		= dw_wdt_stop,
 	.ping		= dw_wdt_ping,
 	.set_timeout	= dw_wdt_set_timeout,
 	.get_timeleft	= dw_wdt_get_timeleft,
diff --git a/fs/dcache.c b/fs/dcache.c
index a1417787e269..c28b9c91b5cb 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -468,9 +468,11 @@ static void dentry_lru_add(struct dentry *dentry)
  * d_drop() is used mainly for stuff that wants to invalidate a dentry for some
  * reason (NFS timeouts or autofs deletes).
  *
- * __d_drop requires dentry->d_lock.
+ * __d_drop requires dentry->d_lock
+ * ___d_drop doesn't mark dentry as "unhashed"
+ *   (dentry->d_hash.pprev will be LIST_POISON2, not NULL).
  */
-void __d_drop(struct dentry *dentry)
+static void ___d_drop(struct dentry *dentry)
 {
 	if (!d_unhashed(dentry)) {
 		struct hlist_bl_head *b;
@@ -486,12 +488,17 @@ void __d_drop(struct dentry *dentry)
 
 		hlist_bl_lock(b);
 		__hlist_bl_del(&dentry->d_hash);
-		dentry->d_hash.pprev = NULL;
 		hlist_bl_unlock(b);
 		/* After this call, in-progress rcu-walk path lookup will fail. */
 		write_seqcount_invalidate(&dentry->d_seq);
 	}
 }
+
+void __d_drop(struct dentry *dentry)
+{
+	___d_drop(dentry);
+	dentry->d_hash.pprev = NULL;
+}
 EXPORT_SYMBOL(__d_drop);
 
 void d_drop(struct dentry *dentry)
@@ -2386,7 +2393,7 @@ EXPORT_SYMBOL(d_delete);
 static void __d_rehash(struct dentry *entry)
 {
 	struct hlist_bl_head *b = d_hash(entry->d_name.hash);
-	BUG_ON(!d_unhashed(entry));
+
 	hlist_bl_lock(b);
 	hlist_bl_add_head_rcu(&entry->d_hash, b);
 	hlist_bl_unlock(b);
@@ -2821,9 +2828,9 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
 	write_seqcount_begin_nested(&target->d_seq, DENTRY_D_LOCK_NESTED);
 
 	/* unhash both */
-	/* __d_drop does write_seqcount_barrier, but they're OK to nest. */
-	__d_drop(dentry);
-	__d_drop(target);
+	/* ___d_drop does write_seqcount_barrier, but they're OK to nest. */
+	___d_drop(dentry);
+	___d_drop(target);
 
 	/* Switch the names.. */
 	if (exchange)
@@ -2835,6 +2842,8 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
 	__d_rehash(dentry);
 	if (exchange)
 		__d_rehash(target);
+	else
+		target->d_hash.pprev = NULL;
 
 	/* ... and switch them in the tree */
 	if (IS_ROOT(dentry)) {
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 5100ec1b5d55..86eb33f67618 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -412,7 +412,7 @@ extern const struct clk_ops clk_divider_ro_ops;
 
 unsigned long divider_recalc_rate(struct clk_hw *hw, unsigned long parent_rate,
 		unsigned int val, const struct clk_div_table *table,
-		unsigned long flags);
+		unsigned long flags, unsigned long width);
 long divider_round_rate_parent(struct clk_hw *hw, struct clk_hw *parent,
 			       unsigned long rate, unsigned long *prate,
 			       const struct clk_div_table *table,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index bfb4a9d962a5..f2f9e957bf1b 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -794,7 +794,7 @@ struct mlx5_core_dev {
 	struct mlx5e_resources  mlx5e_res;
 	struct {
 		struct mlx5_rsvd_gids	reserved_gids;
-		atomic_t                roce_en;
+		u32			roce_en;
 	} roce;
 #ifdef CONFIG_MLX5_FPGA
 	struct mlx5_fpga_device *fpga;
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index f7e83f6d2e64..236452ebbd9e 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -29,6 +29,7 @@
 #include <linux/net_tstamp.h>
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
+#include <linux/phy.h>
 #include <net/arp.h>
 #include <net/switchdev.h>
 
@@ -665,8 +666,11 @@ static int vlan_ethtool_get_ts_info(struct net_device *dev,
 {
 	const struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	const struct ethtool_ops *ops = vlan->real_dev->ethtool_ops;
+	struct phy_device *phydev = vlan->real_dev->phydev;
 
-	if (ops->get_ts_info) {
+	if (phydev && phydev->drv && phydev->drv->ts_info) {
+		 return phydev->drv->ts_info(phydev, info);
+	} else if (ops->get_ts_info) {
 		return ops->get_ts_info(vlan->real_dev, info);
 	} else {
 		info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
diff --git a/net/core/dev.c b/net/core/dev.c
index 387af3415385..4be2a4047640 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1025,7 +1025,7 @@ bool dev_valid_name(const char *name)
 {
 	if (*name == '\0')
 		return false;
-	if (strlen(name) >= IFNAMSIZ)
+	if (strnlen(name, IFNAMSIZ) == IFNAMSIZ)
 		return false;
 	if (!strcmp(name, ".") || !strcmp(name, ".."))
 		return false;
@@ -2696,7 +2696,7 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 		if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr))))
 			return 0;
 
-		eth = (struct ethhdr *)skb_mac_header(skb);
+		eth = (struct ethhdr *)skb->data;
 		type = eth->h_proto;
 	}
 
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index a1d1f50e0e19..7d9cf26f4bb1 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -437,7 +437,7 @@ static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev)
 	/*unsigned long now; */
 	struct net *net = dev_net(dev);
 
-	rt = ip_route_output(net, sip, tip, 0, 0);
+	rt = ip_route_output(net, sip, tip, 0, l3mdev_master_ifindex_rcu(dev));
 	if (IS_ERR(rt))
 		return 1;
 	if (rt->dst.dev != dev) {
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 1ee6c0d8dde4..f39955913d3f 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1755,18 +1755,20 @@ void fib_select_multipath(struct fib_result *res, int hash)
 	bool first = false;
 
 	for_nexthops(fi) {
+		if (net->ipv4.sysctl_fib_multipath_use_neigh) {
+			if (!fib_good_nh(nh))
+				continue;
+			if (!first) {
+				res->nh_sel = nhsel;
+				first = true;
+			}
+		}
+
 		if (hash > atomic_read(&nh->nh_upper_bound))
 			continue;
 
-		if (!net->ipv4.sysctl_fib_multipath_use_neigh ||
-		    fib_good_nh(nh)) {
-			res->nh_sel = nhsel;
-			return;
-		}
-		if (!first) {
-			res->nh_sel = nhsel;
-			first = true;
-		}
+		res->nh_sel = nhsel;
+		return;
 	} endfor_nexthops(fi);
 }
 #endif
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 4e90082b23a6..13f7bbc0168d 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -253,13 +253,14 @@ static struct net_device *__ip_tunnel_create(struct net *net,
 	struct net_device *dev;
 	char name[IFNAMSIZ];
 
-	if (parms->name[0])
+	err = -E2BIG;
+	if (parms->name[0]) {
+		if (!dev_valid_name(parms->name))
+			goto failed;
 		strlcpy(name, parms->name, IFNAMSIZ);
-	else {
-		if (strlen(ops->kind) > (IFNAMSIZ - 3)) {
-			err = -E2BIG;
+	} else {
+		if (strlen(ops->kind) > (IFNAMSIZ - 3))
 			goto failed;
-		}
 		strlcpy(name, ops->kind, IFNAMSIZ);
 		strncat(name, "%d", 2);
 	}
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index e8ab306794d8..4228f3b2f347 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -319,11 +319,13 @@ static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net,
 	if (t || !create)
 		return t;
 
-	if (parms->name[0])
+	if (parms->name[0]) {
+		if (!dev_valid_name(parms->name))
+			return NULL;
 		strlcpy(name, parms->name, IFNAMSIZ);
-	else
+	} else {
 		strcpy(name, "ip6gre%d");
-
+	}
 	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN,
 			   ip6gre_tunnel_setup);
 	if (!dev)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 3763dc01e374..ffbb81609016 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -138,6 +138,14 @@ static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 		return ret;
 	}
 
+#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
+	/* Policy lookup after SNAT yielded a new policy */
+	if (skb_dst(skb)->xfrm) {
+		IPCB(skb)->flags |= IPSKB_REROUTED;
+		return dst_output(net, sk, skb);
+	}
+#endif
+
 	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
 	    dst_allfrag(skb_dst(skb)) ||
 	    (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
@@ -367,6 +375,11 @@ static int ip6_forward_proxy_check(struct sk_buff *skb)
 static inline int ip6_forward_finish(struct net *net, struct sock *sk,
 				     struct sk_buff *skb)
 {
+	struct dst_entry *dst = skb_dst(skb);
+
+	__IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
+	__IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
+
 	return dst_output(net, sk, skb);
 }
 
@@ -560,8 +573,6 @@ int ip6_forward(struct sk_buff *skb)
 
 	hdr->hop_limit--;
 
-	__IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
-	__IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
 	return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD,
 		       net, NULL, skb, skb->dev, dst->dev,
 		       ip6_forward_finish);
@@ -1237,7 +1248,7 @@ static int __ip6_append_data(struct sock *sk,
 			     const struct sockcm_cookie *sockc)
 {
 	struct sk_buff *skb, *skb_prev = NULL;
-	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
+	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu;
 	int exthdrlen = 0;
 	int dst_exthdrlen = 0;
 	int hh_len;
@@ -1273,6 +1284,12 @@ static int __ip6_append_data(struct sock *sk,
 		      sizeof(struct frag_hdr) : 0) +
 		     rt->rt6i_nfheader_len;
 
+	/* as per RFC 7112 section 5, the entire IPv6 Header Chain must fit
+	 * the first fragment
+	 */
+	if (headersize + transhdrlen > mtu)
+		goto emsgsize;
+
 	if (cork->length + length > mtu - headersize && ipc6->dontfrag &&
 	    (sk->sk_protocol == IPPROTO_UDP ||
 	     sk->sk_protocol == IPPROTO_RAW)) {
@@ -1288,9 +1305,8 @@ static int __ip6_append_data(struct sock *sk,
 
 	if (cork->length + length > maxnonfragsize - headersize) {
 emsgsize:
-		ipv6_local_error(sk, EMSGSIZE, fl6,
-				 mtu - headersize +
-				 sizeof(struct ipv6hdr));
+		pmtu = max_t(int, mtu - headersize + sizeof(struct ipv6hdr), 0);
+		ipv6_local_error(sk, EMSGSIZE, fl6, pmtu);
 		return -EMSGSIZE;
 	}
 
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 1161fd5630c1..7e11f6a811f5 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -297,13 +297,16 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
 	struct net_device *dev;
 	struct ip6_tnl *t;
 	char name[IFNAMSIZ];
-	int err = -ENOMEM;
+	int err = -E2BIG;
 
-	if (p->name[0])
+	if (p->name[0]) {
+		if (!dev_valid_name(p->name))
+			goto failed;
 		strlcpy(name, p->name, IFNAMSIZ);
-	else
+	} else {
 		sprintf(name, "ip6tnl%%d");
-
+	}
+	err = -ENOMEM;
 	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN,
 			   ip6_tnl_dev_setup);
 	if (!dev)
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index bcdc2d557de1..7c0f647b5195 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -212,10 +212,13 @@ static struct ip6_tnl *vti6_tnl_create(struct net *net, struct __ip6_tnl_parm *p
 	char name[IFNAMSIZ];
 	int err;
 
-	if (p->name[0])
+	if (p->name[0]) {
+		if (!dev_valid_name(p->name))
+			goto failed;
 		strlcpy(name, p->name, IFNAMSIZ);
-	else
+	} else {
 		sprintf(name, "ip6_vti%%d");
+	}
 
 	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, vti6_dev_setup);
 	if (!dev)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a4a865c8a23c..0126d9bfa670 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -871,6 +871,9 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 	struct fib6_node *fn;
 	struct rt6_info *rt;
 
+	if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF)
+		flags &= ~RT6_LOOKUP_F_IFACE;
+
 	read_lock_bh(&table->tb6_lock);
 	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 restart:
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 7a78dcfda68a..f343e6f0fc95 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -16,6 +16,7 @@
 #include <linux/net.h>
 #include <linux/module.h>
 #include <net/ip.h>
+#include <net/ip_tunnels.h>
 #include <net/lwtunnel.h>
 #include <net/netevent.h>
 #include <net/netns/generic.h>
@@ -211,11 +212,6 @@ static int seg6_do_srh(struct sk_buff *skb)
 
 	tinfo = seg6_encap_lwtunnel(dst->lwtstate);
 
-	if (likely(!skb->encapsulation)) {
-		skb_reset_inner_headers(skb);
-		skb->encapsulation = 1;
-	}
-
 	switch (tinfo->mode) {
 	case SEG6_IPTUN_MODE_INLINE:
 		if (skb->protocol != htons(ETH_P_IPV6))
@@ -224,10 +220,12 @@ static int seg6_do_srh(struct sk_buff *skb)
 		err = seg6_do_srh_inline(skb, tinfo->srh);
 		if (err)
 			return err;
-
-		skb_reset_inner_headers(skb);
 		break;
 	case SEG6_IPTUN_MODE_ENCAP:
+		err = iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6);
+		if (err)
+			return err;
+
 		if (skb->protocol == htons(ETH_P_IPV6))
 			proto = IPPROTO_IPV6;
 		else if (skb->protocol == htons(ETH_P_IP))
@@ -239,6 +237,8 @@ static int seg6_do_srh(struct sk_buff *skb)
 		if (err)
 			return err;
 
+		skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+		skb_set_inner_protocol(skb, skb->protocol);
 		skb->protocol = htons(ETH_P_IPV6);
 		break;
 	case SEG6_IPTUN_MODE_L2ENCAP:
@@ -262,8 +262,6 @@ static int seg6_do_srh(struct sk_buff *skb)
 	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
 	skb_set_transport_header(skb, sizeof(struct ipv6hdr));
 
-	skb_set_inner_protocol(skb, skb->protocol);
-
 	return 0;
 }
 
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index cac815cc8600..f03c1a562135 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -244,11 +244,13 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net,
 	if (!create)
 		goto failed;
 
-	if (parms->name[0])
+	if (parms->name[0]) {
+		if (!dev_valid_name(parms->name))
+			goto failed;
 		strlcpy(name, parms->name, IFNAMSIZ);
-	else
+	} else {
 		strcpy(name, "sit%d");
-
+	}
 	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN,
 			   ipip6_tunnel_setup);
 	if (!dev)
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index c28223d8092b..fca69c3771f5 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -765,6 +765,8 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl
 
 	if ((session->ifname[0] &&
 	     nla_put_string(skb, L2TP_ATTR_IFNAME, session->ifname)) ||
+	    (session->offset &&
+	     nla_put_u16(skb, L2TP_ATTR_OFFSET, session->offset)) ||
 	    (session->cookie_len &&
 	     nla_put(skb, L2TP_ATTR_COOKIE, session->cookie_len,
 		     &session->cookie[0])) ||
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 84f757c5d91a..288640471c2f 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2373,10 +2373,17 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
 	struct ieee80211_sub_if_data *sdata;
 	enum nl80211_tx_power_setting txp_type = type;
 	bool update_txp_type = false;
+	bool has_monitor = false;
 
 	if (wdev) {
 		sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
 
+		if (sdata->vif.type == NL80211_IFTYPE_MONITOR) {
+			sdata = rtnl_dereference(local->monitor_sdata);
+			if (!sdata)
+				return -EOPNOTSUPP;
+		}
+
 		switch (type) {
 		case NL80211_TX_POWER_AUTOMATIC:
 			sdata->user_power_level = IEEE80211_UNSET_POWER_LEVEL;
@@ -2415,15 +2422,34 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
 
 	mutex_lock(&local->iflist_mtx);
 	list_for_each_entry(sdata, &local->interfaces, list) {
+		if (sdata->vif.type == NL80211_IFTYPE_MONITOR) {
+			has_monitor = true;
+			continue;
+		}
 		sdata->user_power_level = local->user_power_level;
 		if (txp_type != sdata->vif.bss_conf.txpower_type)
 			update_txp_type = true;
 		sdata->vif.bss_conf.txpower_type = txp_type;
 	}
-	list_for_each_entry(sdata, &local->interfaces, list)
+	list_for_each_entry(sdata, &local->interfaces, list) {
+		if (sdata->vif.type == NL80211_IFTYPE_MONITOR)
+			continue;
 		ieee80211_recalc_txpower(sdata, update_txp_type);
+	}
 	mutex_unlock(&local->iflist_mtx);
 
+	if (has_monitor) {
+		sdata = rtnl_dereference(local->monitor_sdata);
+		if (sdata) {
+			sdata->user_power_level = local->user_power_level;
+			if (txp_type != sdata->vif.bss_conf.txpower_type)
+				update_txp_type = true;
+			sdata->vif.bss_conf.txpower_type = txp_type;
+
+			ieee80211_recalc_txpower(sdata, update_txp_type);
+		}
+	}
+
 	return 0;
 }
 
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index c7f93fd9ca7a..4d82fe7d627c 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -165,7 +165,8 @@ static inline void drv_bss_info_changed(struct ieee80211_local *local,
 	if (WARN_ON_ONCE(sdata->vif.type == NL80211_IFTYPE_P2P_DEVICE ||
 			 sdata->vif.type == NL80211_IFTYPE_NAN ||
 			 (sdata->vif.type == NL80211_IFTYPE_MONITOR &&
-			  !sdata->vif.mu_mimo_owner)))
+			  !sdata->vif.mu_mimo_owner &&
+			  !(changed & BSS_CHANGED_TXPOWER))))
 		return;
 
 	if (!check_sdata_in_driver(sdata))
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 9219bc134109..1b86eccf94b6 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1053,6 +1053,9 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
 	if (addr->sa_family != AF_NETLINK)
 		return -EINVAL;
 
+	if (alen < sizeof(struct sockaddr_nl))
+		return -EINVAL;
+
 	if ((nladdr->nl_groups || nladdr->nl_pid) &&
 	    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 		return -EPERM;
diff --git a/net/rds/bind.c b/net/rds/bind.c
index 75d43dc8e96b..5aa3a64aa4f0 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -114,6 +114,7 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port)
 			  rs, &addr, (int)ntohs(*port));
 			break;
 		} else {
+			rs->rs_bound_addr = 0;
 			rds_sock_put(rs);
 			ret = -ENOMEM;
 			break;
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 8f2c63514956..4444d7e755e6 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -133,8 +133,10 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
 			continue;
 
 		nest = nla_nest_start(skb, n_i);
-		if (!nest)
+		if (!nest) {
+			index--;
 			goto nla_put_failure;
+		}
 		err = tcf_action_dump_1(skb, p, 0, 0);
 		if (err < 0) {
 			index--;
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index c0c707eb2c96..2b087623fb1d 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -248,10 +248,14 @@ static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
 
 static void tcf_bpf_cfg_cleanup(const struct tcf_bpf_cfg *cfg)
 {
-	if (cfg->is_ebpf)
-		bpf_prog_put(cfg->filter);
-	else
-		bpf_prog_destroy(cfg->filter);
+	struct bpf_prog *filter = cfg->filter;
+
+	if (filter) {
+		if (cfg->is_ebpf)
+			bpf_prog_put(filter);
+		else
+			bpf_prog_destroy(filter);
+	}
 
 	kfree(cfg->bpf_ops);
 	kfree(cfg->bpf_name);
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index b642ad3d39dd..6d10b3af479b 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -190,7 +190,8 @@ static void tcf_skbmod_cleanup(struct tc_action *a, int bind)
 	struct tcf_skbmod_params  *p;
 
 	p = rcu_dereference_protected(d->skbmod_p, 1);
-	kfree_rcu(p, rcu);
+	if (p)
+		kfree_rcu(p, rcu);
 }
 
 static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 22bf1a376b91..7cb63616805d 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -208,11 +208,12 @@ static void tunnel_key_release(struct tc_action *a, int bind)
 	struct tcf_tunnel_key_params *params;
 
 	params = rcu_dereference_protected(t->params, 1);
+	if (params) {
+		if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET)
+			dst_release(&params->tcft_enc_metadata->dst);
 
-	if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET)
-		dst_release(&params->tcft_enc_metadata->dst);
-
-	kfree_rcu(params, rcu);
+		kfree_rcu(params, rcu);
+	}
 }
 
 static int tunnel_key_dump_addresses(struct sk_buff *skb,
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index f27a9718554c..08b5705e7381 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -728,8 +728,10 @@ static int sctp_v6_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr)
 			sctp_v6_map_v4(addr);
 	}
 
-	if (addr->sa.sa_family == AF_INET)
+	if (addr->sa.sa_family == AF_INET) {
+		memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
 		return sizeof(struct sockaddr_in);
+	}
 	return sizeof(struct sockaddr_in6);
 }
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 6b3a862706de..2d6f612f32c3 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -337,11 +337,14 @@ static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt,
 	if (!opt->pf->af_supported(addr->sa.sa_family, opt))
 		return NULL;
 
-	/* V4 mapped address are really of AF_INET family */
-	if (addr->sa.sa_family == AF_INET6 &&
-	    ipv6_addr_v4mapped(&addr->v6.sin6_addr) &&
-	    !opt->pf->af_supported(AF_INET, opt))
-		return NULL;
+	if (addr->sa.sa_family == AF_INET6) {
+		if (len < SIN6_LEN_RFC2133)
+			return NULL;
+		/* V4 mapped address are really of AF_INET family */
+		if (ipv6_addr_v4mapped(&addr->v6.sin6_addr) &&
+		    !opt->pf->af_supported(AF_INET, opt))
+			return NULL;
+	}
 
 	/* If we get this far, af is valid. */
 	af = sctp_get_af_specific(addr->sa.sa_family);
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index c5fda15ba319..4a3a3f1331ee 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -60,7 +60,7 @@ static void strp_abort_strp(struct strparser *strp, int err)
 		struct sock *sk = strp->sk;
 
 		/* Report an error on the lower socket */
-		sk->sk_err = err;
+		sk->sk_err = -err;
 		sk->sk_error_report(sk);
 	}
 }
@@ -458,7 +458,7 @@ static void strp_msg_timeout(struct work_struct *w)
 	/* Message assembly timed out */
 	STRP_STATS_INCR(strp->stats.msg_timeouts);
 	strp->cb.lock(strp);
-	strp->cb.abort_parser(strp, ETIMEDOUT);
+	strp->cb.abort_parser(strp, -ETIMEDOUT);
 	strp->cb.unlock(strp);
 }
 
diff --git a/sound/soc/intel/atom/sst/sst_stream.c b/sound/soc/intel/atom/sst/sst_stream.c
index 83d8dda15233..4eeb9afdc89f 100644
--- a/sound/soc/intel/atom/sst/sst_stream.c
+++ b/sound/soc/intel/atom/sst/sst_stream.c
@@ -221,7 +221,7 @@ int sst_send_byte_stream_mrfld(struct intel_sst_drv *sst_drv_ctx,
 		sst_free_block(sst_drv_ctx, block);
 out:
 	test_and_clear_bit(pvt_id, &sst_drv_ctx->pvt_id);
-	return 0;
+	return ret;
 }
 
 /*
diff --git a/sound/soc/intel/boards/cht_bsw_rt5645.c b/sound/soc/intel/boards/cht_bsw_rt5645.c
index 5bcde01d15e6..fbfb76ee2346 100644
--- a/sound/soc/intel/boards/cht_bsw_rt5645.c
+++ b/sound/soc/intel/boards/cht_bsw_rt5645.c
@@ -133,6 +133,7 @@ static const struct snd_soc_dapm_widget cht_dapm_widgets[] = {
 	SND_SOC_DAPM_HP("Headphone", NULL),
 	SND_SOC_DAPM_MIC("Headset Mic", NULL),
 	SND_SOC_DAPM_MIC("Int Mic", NULL),
+	SND_SOC_DAPM_MIC("Int Analog Mic", NULL),
 	SND_SOC_DAPM_SPK("Ext Spk", NULL),
 	SND_SOC_DAPM_SUPPLY("Platform Clock", SND_SOC_NOPM, 0, 0,
 			platform_clock_control, SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
@@ -143,6 +144,8 @@ static const struct snd_soc_dapm_route cht_rt5645_audio_map[] = {
 	{"IN1N", NULL, "Headset Mic"},
 	{"DMIC L1", NULL, "Int Mic"},
 	{"DMIC R1", NULL, "Int Mic"},
+	{"IN2P", NULL, "Int Analog Mic"},
+	{"IN2N", NULL, "Int Analog Mic"},
 	{"Headphone", NULL, "HPOL"},
 	{"Headphone", NULL, "HPOR"},
 	{"Ext Spk", NULL, "SPOL"},
@@ -150,6 +153,9 @@ static const struct snd_soc_dapm_route cht_rt5645_audio_map[] = {
 	{"Headphone", NULL, "Platform Clock"},
 	{"Headset Mic", NULL, "Platform Clock"},
 	{"Int Mic", NULL, "Platform Clock"},
+	{"Int Analog Mic", NULL, "Platform Clock"},
+	{"Int Analog Mic", NULL, "micbias1"},
+	{"Int Analog Mic", NULL, "micbias2"},
 	{"Ext Spk", NULL, "Platform Clock"},
 };
 
@@ -204,6 +210,7 @@ static const struct snd_kcontrol_new cht_mc_controls[] = {
 	SOC_DAPM_PIN_SWITCH("Headphone"),
 	SOC_DAPM_PIN_SWITCH("Headset Mic"),
 	SOC_DAPM_PIN_SWITCH("Int Mic"),
+	SOC_DAPM_PIN_SWITCH("Int Analog Mic"),
 	SOC_DAPM_PIN_SWITCH("Ext Spk"),
 };
 
diff --git a/sound/soc/intel/skylake/skl-messages.c b/sound/soc/intel/skylake/skl-messages.c
index 89f70133c8e4..b74a6040cd96 100644
--- a/sound/soc/intel/skylake/skl-messages.c
+++ b/sound/soc/intel/skylake/skl-messages.c
@@ -404,7 +404,11 @@ int skl_resume_dsp(struct skl *skl)
 	if (skl->skl_sst->is_first_boot == true)
 		return 0;
 
+	/* disable dynamic clock gating during fw and lib download */
+	ctx->enable_miscbdcge(ctx->dev, false);
+
 	ret = skl_dsp_wake(ctx->dsp);
+	ctx->enable_miscbdcge(ctx->dev, true);
 	if (ret < 0)
 		return ret;
 
diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c
index 2b1e513b1680..7fe1e8f273a0 100644
--- a/sound/soc/intel/skylake/skl-pcm.c
+++ b/sound/soc/intel/skylake/skl-pcm.c
@@ -1332,7 +1332,11 @@ static int skl_platform_soc_probe(struct snd_soc_platform *platform)
 			return -EIO;
 		}
 
+		/* disable dynamic clock gating during fw and lib download */
+		skl->skl_sst->enable_miscbdcge(platform->dev, false);
+
 		ret = ops->init_fw(platform->dev, skl->skl_sst);
+		skl->skl_sst->enable_miscbdcge(platform->dev, true);
 		if (ret < 0) {
 			dev_err(platform->dev, "Failed to boot first fw: %d\n", ret);
 			return ret;
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 9d01d0b1084e..c8b8b7101c6f 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1385,6 +1385,17 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 				state->vals[op->dest.reg].offset = -state->stack_size;
 			}
 
+			else if (op->src.reg == CFI_BP && op->dest.reg == CFI_SP &&
+				 cfa->base == CFI_BP) {
+
+				/*
+				 * mov %rbp, %rsp
+				 *
+				 * Restore the original stack pointer (Clang).
+				 */
+				state->stack_size = -state->regs[CFI_BP].offset;
+			}
+
 			else if (op->dest.reg == cfa->base) {
 
 				/* mov %reg, %rsp */
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index 9c4e23d8c8ce..53d83d7e6a09 100644
--- a/tools/perf/arch/powerpc/util/sym-handling.c
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -64,6 +64,14 @@ int arch__compare_symbol_names_n(const char *namea, const char *nameb,
 
 	return strncmp(namea, nameb, n);
 }
+
+const char *arch__normalize_symbol_name(const char *name)
+{
+	/* Skip over initial dot */
+	if (name && *name == '.')
+		name++;
+	return name;
+}
 #endif
 
 #if defined(_CALL_ELF) && _CALL_ELF == 2
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0c95ffefb6cc..1957abc1c8cf 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1856,8 +1856,8 @@ int cmd_record(int argc, const char **argv)
 		goto out;
 	}
 
-	/* Enable ignoring missing threads when -u option is defined. */
-	rec->opts.ignore_missing_thread = rec->opts.target.uid != UINT_MAX;
+	/* Enable ignoring missing threads when -u/-p option is defined. */
+	rec->opts.ignore_missing_thread = rec->opts.target.uid != UINT_MAX || rec->opts.target.pid;
 
 	err = -ENOMEM;
 	if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index fae4b0340750..183c3ed56e08 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -162,12 +162,28 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter,
 	struct hist_entry *he = iter->he;
 	struct report *rep = arg;
 	struct branch_info *bi;
+	struct perf_sample *sample = iter->sample;
+	struct perf_evsel *evsel = iter->evsel;
+	int err;
+
+	if (!ui__has_annotation())
+		return 0;
+
+	hist__account_cycles(sample->branch_stack, al, sample,
+			     rep->nonany_branch_mode);
 
 	bi = he->branch_info;
+	err = addr_map_symbol__inc_samples(&bi->from, sample, evsel->idx);
+	if (err)
+		goto out;
+
+	err = addr_map_symbol__inc_samples(&bi->to, sample, evsel->idx);
+
 	branch_type_count(&rep->brtype_stat, &bi->flags,
 			  bi->from.addr, bi->to.addr);
 
-	return 0;
+out:
+	return err;
 }
 
 static int process_sample_event(struct perf_tool *tool,
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1f6beb3d0c68..ac19130c14d8 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1591,10 +1591,46 @@ static int __open_attr__fprintf(FILE *fp, const char *name, const char *val,
 	return fprintf(fp, "  %-32s %s\n", name, val);
 }
 
+static void perf_evsel__remove_fd(struct perf_evsel *pos,
+				  int nr_cpus, int nr_threads,
+				  int thread_idx)
+{
+	for (int cpu = 0; cpu < nr_cpus; cpu++)
+		for (int thread = thread_idx; thread < nr_threads - 1; thread++)
+			FD(pos, cpu, thread) = FD(pos, cpu, thread + 1);
+}
+
+static int update_fds(struct perf_evsel *evsel,
+		      int nr_cpus, int cpu_idx,
+		      int nr_threads, int thread_idx)
+{
+	struct perf_evsel *pos;
+
+	if (cpu_idx >= nr_cpus || thread_idx >= nr_threads)
+		return -EINVAL;
+
+	evlist__for_each_entry(evsel->evlist, pos) {
+		nr_cpus = pos != evsel ? nr_cpus : cpu_idx;
+
+		perf_evsel__remove_fd(pos, nr_cpus, nr_threads, thread_idx);
+
+		/*
+		 * Since fds for next evsel has not been created,
+		 * there is no need to iterate whole event list.
+		 */
+		if (pos == evsel)
+			break;
+	}
+	return 0;
+}
+
 static bool ignore_missing_thread(struct perf_evsel *evsel,
+				  int nr_cpus, int cpu,
 				  struct thread_map *threads,
 				  int thread, int err)
 {
+	pid_t ignore_pid = thread_map__pid(threads, thread);
+
 	if (!evsel->ignore_missing_thread)
 		return false;
 
@@ -1610,11 +1646,18 @@ static bool ignore_missing_thread(struct perf_evsel *evsel,
 	if (threads->nr == 1)
 		return false;
 
+	/*
+	 * We should remove fd for missing_thread first
+	 * because thread_map__remove() will decrease threads->nr.
+	 */
+	if (update_fds(evsel, nr_cpus, cpu, threads->nr, thread))
+		return false;
+
 	if (thread_map__remove(threads, thread))
 		return false;
 
 	pr_warning("WARNING: Ignored open failure for pid %d\n",
-		   thread_map__pid(threads, thread));
+		   ignore_pid);
 	return true;
 }
 
@@ -1719,7 +1762,7 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 			if (fd < 0) {
 				err = -errno;
 
-				if (ignore_missing_thread(evsel, threads, thread, err)) {
+				if (ignore_missing_thread(evsel, cpus->nr, cpu, threads, thread, err)) {
 					/*
 					 * We just removed 1 thread, so take a step
 					 * back on thread index and lower the upper
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index b7aaf9b2294d..68786bb7790e 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2625,6 +2625,14 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 
 out:
 	free(nbase);
+
+	/* Final validation */
+	if (ret >= 0 && !is_c_func_name(buf)) {
+		pr_warning("Internal error: \"%s\" is an invalid event name.\n",
+			   buf);
+		ret = -EINVAL;
+	}
+
 	return ret;
 }
 
@@ -2792,16 +2800,32 @@ static int find_probe_functions(struct map *map, char *name,
 	int found = 0;
 	struct symbol *sym;
 	struct rb_node *tmp;
+	const char *norm, *ver;
+	char *buf = NULL;
 
 	if (map__load(map) < 0)
 		return 0;
 
 	map__for_each_symbol(map, sym, tmp) {
-		if (strglobmatch(sym->name, name)) {
+		norm = arch__normalize_symbol_name(sym->name);
+		if (!norm)
+			continue;
+
+		/* We don't care about default symbol or not */
+		ver = strchr(norm, '@');
+		if (ver) {
+			buf = strndup(norm, ver - norm);
+			if (!buf)
+				return -ENOMEM;
+			norm = buf;
+		}
+		if (strglobmatch(norm, name)) {
 			found++;
 			if (syms && found < probe_conf.max_probes)
 				syms[found - 1] = sym;
 		}
+		if (buf)
+			zfree(&buf);
 	}
 
 	return found;
@@ -2847,7 +2871,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 	 * same name but different addresses, this lists all the symbols.
 	 */
 	num_matched_functions = find_probe_functions(map, pp->function, syms);
-	if (num_matched_functions == 0) {
+	if (num_matched_functions <= 0) {
 		pr_err("Failed to find symbol %s in %s\n", pp->function,
 			pev->target ? : "kernel");
 		ret = -ENOENT;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 6492ef38b090..4e8dd5fd45fd 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -93,6 +93,11 @@ static int prefix_underscores_count(const char *str)
 	return tail - str;
 }
 
+const char * __weak arch__normalize_symbol_name(const char *name)
+{
+	return name;
+}
+
 int __weak arch__compare_symbol_names(const char *namea, const char *nameb)
 {
 	return strcmp(namea, nameb);
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 6352022593c6..698c65e603a8 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -347,6 +347,7 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr);
 void arch__sym_update(struct symbol *s, GElf_Sym *sym);
 #endif
 
+const char *arch__normalize_symbol_name(const char *name);
 #define SYMBOL_A 0
 #define SYMBOL_B 1
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 3687b720327a..cc57c246eade 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -196,7 +196,7 @@ int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
 
 		size -= ret;
 		off_in += ret;
-		off_out -= ret;
+		off_out += ret;
 	}
 	munmap(ptr, off_in + size);
 
diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c
index 3ab6ec403905..e11fe84de0fd 100644
--- a/tools/testing/selftests/net/msg_zerocopy.c
+++ b/tools/testing/selftests/net/msg_zerocopy.c
@@ -259,22 +259,28 @@ static int setup_ip6h(struct ipv6hdr *ip6h, uint16_t payload_len)
 	return sizeof(*ip6h);
 }
 
-static void setup_sockaddr(int domain, const char *str_addr, void *sockaddr)
+
+static void setup_sockaddr(int domain, const char *str_addr,
+			   struct sockaddr_storage *sockaddr)
 {
 	struct sockaddr_in6 *addr6 = (void *) sockaddr;
 	struct sockaddr_in *addr4 = (void *) sockaddr;
 
 	switch (domain) {
 	case PF_INET:
+		memset(addr4, 0, sizeof(*addr4));
 		addr4->sin_family = AF_INET;
 		addr4->sin_port = htons(cfg_port);
-		if (inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1)
+		if (str_addr &&
+		    inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1)
 			error(1, 0, "ipv4 parse error: %s", str_addr);
 		break;
 	case PF_INET6:
+		memset(addr6, 0, sizeof(*addr6));
 		addr6->sin6_family = AF_INET6;
 		addr6->sin6_port = htons(cfg_port);
-		if (inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1)
+		if (str_addr &&
+		    inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1)
 			error(1, 0, "ipv6 parse error: %s", str_addr);
 		break;
 	default:
@@ -603,6 +609,7 @@ static void parse_opts(int argc, char **argv)
 				    sizeof(struct tcphdr) -
 				    40 /* max tcp options */;
 	int c;
+	char *daddr = NULL, *saddr = NULL;
 
 	cfg_payload_len = max_payload_len;
 
@@ -627,7 +634,7 @@ static void parse_opts(int argc, char **argv)
 			cfg_cpu = strtol(optarg, NULL, 0);
 			break;
 		case 'D':
-			setup_sockaddr(cfg_family, optarg, &cfg_dst_addr);
+			daddr = optarg;
 			break;
 		case 'i':
 			cfg_ifindex = if_nametoindex(optarg);
@@ -638,7 +645,7 @@ static void parse_opts(int argc, char **argv)
 			cfg_cork_mixed = true;
 			break;
 		case 'p':
-			cfg_port = htons(strtoul(optarg, NULL, 0));
+			cfg_port = strtoul(optarg, NULL, 0);
 			break;
 		case 'r':
 			cfg_rx = true;
@@ -647,7 +654,7 @@ static void parse_opts(int argc, char **argv)
 			cfg_payload_len = strtoul(optarg, NULL, 0);
 			break;
 		case 'S':
-			setup_sockaddr(cfg_family, optarg, &cfg_src_addr);
+			saddr = optarg;
 			break;
 		case 't':
 			cfg_runtime_ms = 200 + strtoul(optarg, NULL, 10) * 1000;
@@ -660,6 +667,8 @@ static void parse_opts(int argc, char **argv)
 			break;
 		}
 	}
+	setup_sockaddr(cfg_family, daddr, &cfg_dst_addr);
+	setup_sockaddr(cfg_family, saddr, &cfg_src_addr);
 
 	if (cfg_payload_len > max_payload_len)
 		error(1, 0, "-s: payload exceeds max (%d)", max_payload_len);