Upgrade to 4.4.50-rt62

The current kernel is based on rt kernel v4.4.6-rt14. We will upgrade it
to 4.4.50-rt62.
The command to achieve it is:
a) Clone a git repo from
git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-stable-rt.git

b) Get the diff between this two changesets:
git diff 640eca2901f3435e616157b11379d3223a44b391
705619beeea1b0b48219a683fd1a901a86fdaf5e

where the two commits are:
[yjiang5@jnakajim-build linux-stable-rt]$ git show --oneline --name-only
640eca2901f3435e616157b11379d3223a44b391
640eca2901f3 v4.4.6-rt14
localversion-rt
[yjiang5@jnakajim-build linux-stable-rt]$ git show --oneline --name-only
705619beeea1b0b48219a683fd1a901a86fdaf5e
705619beeea1 Linux 4.4.50-rt62
localversion-rt

c) One patch has been backported thus revert the patch before applying.

 filterdiff -p1 -x scripts/package/Makefile
~/tmp/v4.4.6-rt14-4.4.50-rt62.diff  |patch -p1 --dry-run

Upstream status: backport

Change-Id: I244d57a32f6066e5a5b9915f9fbf99e7bbca6e01
Signed-off-by: Yunhong Jiang <yunhong.jiang@linux.intel.com>

43 files changed, 517 insertions, 255 deletions

diff --git a/kernel/arch/arm64/Kconfig b/kernel/arch/arm64/Kconfig
index 1baa6537c..9196cf82f 100644
--- a/kernel/arch/arm64/Kconfig
+++ b/kernel/arch/arm64/Kconfig
@@ -392,6 +392,15 @@ config CAVIUM_ERRATUM_22375
 
 	  If unsure, say Y.
 
+config CAVIUM_ERRATUM_23144
+	bool "Cavium erratum 23144: ITS SYNC hang on dual socket system"
+	depends on NUMA
+	default y
+	help
+	  ITS SYNC command hang for cross node io and collections/cpu mapping.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_23154
 	bool "Cavium erratum 23154: Access to ICC_IAR1_EL1 is not sync'ed"
 	default y
@@ -402,6 +411,17 @@ config CAVIUM_ERRATUM_23154
 
 	  If unsure, say Y.
 
+config CAVIUM_ERRATUM_27456
+	bool "Cavium erratum 27456: Broadcast TLBI instructions may cause icache corruption"
+	default y
+	help
+	  On ThunderX T88 pass 1.x through 2.1 parts, broadcast TLBI
+	  instructions may cause the icache to become corrupted if it
+	  contains data for a non-current ASID.  The fix is to
+	  invalidate the icache when changing the mm context.
+
+	  If unsure, say Y.
+
 endmenu
 
 
diff --git a/kernel/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/kernel/arch/arm64/boot/dts/rockchip/rk3368.dtsi
index cc093a482..e0ee2b00d 100644
--- a/kernel/arch/arm64/boot/dts/rockchip/rk3368.dtsi
+++ b/kernel/arch/arm64/boot/dts/rockchip/rk3368.dtsi
@@ -262,6 +262,8 @@
 		#io-channel-cells = <1>;
 		clocks = <&cru SCLK_SARADC>, <&cru PCLK_SARADC>;
 		clock-names = "saradc", "apb_pclk";
+		resets = <&cru SRST_SARADC>;
+		reset-names = "saradc-apb";
 		status = "disabled";
 	};
 
@@ -517,7 +519,7 @@
 		#address-cells = <0>;
 
 		reg = <0x0 0xffb71000 0x0 0x1000>,
-		      <0x0 0xffb72000 0x0 0x1000>,
+		      <0x0 0xffb72000 0x0 0x2000>,
 		      <0x0 0xffb74000 0x0 0x2000>,
 		      <0x0 0xffb76000 0x0 0x2000>;
 		interrupts = <GIC_PPI 9
diff --git a/kernel/arch/arm64/crypto/aes-ce-ccm-core.S b/kernel/arch/arm64/crypto/aes-ce-ccm-core.S
index a2a7fbcac..3363560c7 100644
--- a/kernel/arch/arm64/crypto/aes-ce-ccm-core.S
+++ b/kernel/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -9,6 +9,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 	.text
 	.arch	armv8-a+crypto
@@ -19,7 +20,7 @@
 	 */
 ENTRY(ce_aes_ccm_auth_data)
 	ldr	w8, [x3]			/* leftover from prev round? */
-	ld1	{v0.2d}, [x0]			/* load mac */
+	ld1	{v0.16b}, [x0]			/* load mac */
 	cbz	w8, 1f
 	sub	w8, w8, #16
 	eor	v1.16b, v1.16b, v1.16b
@@ -31,7 +32,7 @@ ENTRY(ce_aes_ccm_auth_data)
 	beq	8f				/* out of input? */
 	cbnz	w8, 0b
 	eor	v0.16b, v0.16b, v1.16b
-1:	ld1	{v3.2d}, [x4]			/* load first round key */
+1:	ld1	{v3.16b}, [x4]			/* load first round key */
 	prfm	pldl1strm, [x1]
 	cmp	w5, #12				/* which key size? */
 	add	x6, x4, #16
@@ -41,17 +42,17 @@ ENTRY(ce_aes_ccm_auth_data)
 	mov	v5.16b, v3.16b
 	b	4f
 2:	mov	v4.16b, v3.16b
-	ld1	{v5.2d}, [x6], #16		/* load 2nd round key */
+	ld1	{v5.16b}, [x6], #16		/* load 2nd round key */
 3:	aese	v0.16b, v4.16b
 	aesmc	v0.16b, v0.16b
-4:	ld1	{v3.2d}, [x6], #16		/* load next round key */
+4:	ld1	{v3.16b}, [x6], #16		/* load next round key */
 	aese	v0.16b, v5.16b
 	aesmc	v0.16b, v0.16b
-5:	ld1	{v4.2d}, [x6], #16		/* load next round key */
+5:	ld1	{v4.16b}, [x6], #16		/* load next round key */
 	subs	w7, w7, #3
 	aese	v0.16b, v3.16b
 	aesmc	v0.16b, v0.16b
-	ld1	{v5.2d}, [x6], #16		/* load next round key */
+	ld1	{v5.16b}, [x6], #16		/* load next round key */
 	bpl	3b
 	aese	v0.16b, v4.16b
 	subs	w2, w2, #16			/* last data? */
@@ -60,7 +61,7 @@ ENTRY(ce_aes_ccm_auth_data)
 	ld1	{v1.16b}, [x1], #16		/* load next input block */
 	eor	v0.16b, v0.16b, v1.16b		/* xor with mac */
 	bne	1b
-6:	st1	{v0.2d}, [x0]			/* store mac */
+6:	st1	{v0.16b}, [x0]			/* store mac */
 	beq	10f
 	adds	w2, w2, #16
 	beq	10f
@@ -79,7 +80,7 @@ ENTRY(ce_aes_ccm_auth_data)
 	adds	w7, w7, #1
 	bne	9b
 	eor	v0.16b, v0.16b, v1.16b
-	st1	{v0.2d}, [x0]
+	st1	{v0.16b}, [x0]
 10:	str	w8, [x3]
 	ret
 ENDPROC(ce_aes_ccm_auth_data)
@@ -89,27 +90,27 @@ ENDPROC(ce_aes_ccm_auth_data)
 	 * 			 u32 rounds);
 	 */
 ENTRY(ce_aes_ccm_final)
-	ld1	{v3.2d}, [x2], #16		/* load first round key */
-	ld1	{v0.2d}, [x0]			/* load mac */
+	ld1	{v3.16b}, [x2], #16		/* load first round key */
+	ld1	{v0.16b}, [x0]			/* load mac */
 	cmp	w3, #12				/* which key size? */
 	sub	w3, w3, #2			/* modified # of rounds */
-	ld1	{v1.2d}, [x1]			/* load 1st ctriv */
+	ld1	{v1.16b}, [x1]			/* load 1st ctriv */
 	bmi	0f
 	bne	3f
 	mov	v5.16b, v3.16b
 	b	2f
 0:	mov	v4.16b, v3.16b
-1:	ld1	{v5.2d}, [x2], #16		/* load next round key */
+1:	ld1	{v5.16b}, [x2], #16		/* load next round key */
 	aese	v0.16b, v4.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v4.16b
 	aesmc	v1.16b, v1.16b
-2:	ld1	{v3.2d}, [x2], #16		/* load next round key */
+2:	ld1	{v3.16b}, [x2], #16		/* load next round key */
 	aese	v0.16b, v5.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v5.16b
 	aesmc	v1.16b, v1.16b
-3:	ld1	{v4.2d}, [x2], #16		/* load next round key */
+3:	ld1	{v4.16b}, [x2], #16		/* load next round key */
 	subs	w3, w3, #3
 	aese	v0.16b, v3.16b
 	aesmc	v0.16b, v0.16b
@@ -120,47 +121,47 @@ ENTRY(ce_aes_ccm_final)
 	aese	v1.16b, v4.16b
 	/* final round key cancels out */
 	eor	v0.16b, v0.16b, v1.16b		/* en-/decrypt the mac */
-	st1	{v0.2d}, [x0]			/* store result */
+	st1	{v0.16b}, [x0]			/* store result */
 	ret
 ENDPROC(ce_aes_ccm_final)
 
 	.macro	aes_ccm_do_crypt,enc
 	ldr	x8, [x6, #8]			/* load lower ctr */
-	ld1	{v0.2d}, [x5]			/* load mac */
-	rev	x8, x8				/* keep swabbed ctr in reg */
+	ld1	{v0.16b}, [x5]			/* load mac */
+CPU_LE(	rev	x8, x8			)	/* keep swabbed ctr in reg */
 0:	/* outer loop */
-	ld1	{v1.1d}, [x6]			/* load upper ctr */
+	ld1	{v1.8b}, [x6]			/* load upper ctr */
 	prfm	pldl1strm, [x1]
 	add	x8, x8, #1
 	rev	x9, x8
 	cmp	w4, #12				/* which key size? */
 	sub	w7, w4, #2			/* get modified # of rounds */
 	ins	v1.d[1], x9			/* no carry in lower ctr */
-	ld1	{v3.2d}, [x3]			/* load first round key */
+	ld1	{v3.16b}, [x3]			/* load first round key */
 	add	x10, x3, #16
 	bmi	1f
 	bne	4f
 	mov	v5.16b, v3.16b
 	b	3f
 1:	mov	v4.16b, v3.16b
-	ld1	{v5.2d}, [x10], #16		/* load 2nd round key */
+	ld1	{v5.16b}, [x10], #16		/* load 2nd round key */
 2:	/* inner loop: 3 rounds, 2x interleaved */
 	aese	v0.16b, v4.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v4.16b
 	aesmc	v1.16b, v1.16b
-3:	ld1	{v3.2d}, [x10], #16		/* load next round key */
+3:	ld1	{v3.16b}, [x10], #16		/* load next round key */
 	aese	v0.16b, v5.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v5.16b
 	aesmc	v1.16b, v1.16b
-4:	ld1	{v4.2d}, [x10], #16		/* load next round key */
+4:	ld1	{v4.16b}, [x10], #16		/* load next round key */
 	subs	w7, w7, #3
 	aese	v0.16b, v3.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v3.16b
 	aesmc	v1.16b, v1.16b
-	ld1	{v5.2d}, [x10], #16		/* load next round key */
+	ld1	{v5.16b}, [x10], #16		/* load next round key */
 	bpl	2b
 	aese	v0.16b, v4.16b
 	aese	v1.16b, v4.16b
@@ -177,14 +178,14 @@ ENDPROC(ce_aes_ccm_final)
 	eor	v0.16b, v0.16b, v2.16b		/* xor mac with pt ^ rk[last] */
 	st1	{v1.16b}, [x0], #16		/* write output block */
 	bne	0b
-	rev	x8, x8
-	st1	{v0.2d}, [x5]			/* store mac */
+CPU_LE(	rev	x8, x8			)
+	st1	{v0.16b}, [x5]			/* store mac */
 	str	x8, [x6, #8]			/* store lsb end of ctr (BE) */
 5:	ret
 
 6:	eor	v0.16b, v0.16b, v5.16b		/* final round mac */
 	eor	v1.16b, v1.16b, v5.16b		/* final round enc */
-	st1	{v0.2d}, [x5]			/* store mac */
+	st1	{v0.16b}, [x5]			/* store mac */
 	add	w2, w2, #16			/* process partial tail block */
 7:	ldrb	w9, [x1], #1			/* get 1 byte of input */
 	umov	w6, v1.b[0]			/* get top crypted ctr byte */
diff --git a/kernel/arch/arm64/crypto/aes-ce-cipher.c b/kernel/arch/arm64/crypto/aes-ce-cipher.c
index f7bd9bf0b..50d9fe11d 100644
--- a/kernel/arch/arm64/crypto/aes-ce-cipher.c
+++ b/kernel/arch/arm64/crypto/aes-ce-cipher.c
@@ -47,24 +47,24 @@ static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 	kernel_neon_begin_partial(4);
 
 	__asm__("	ld1	{v0.16b}, %[in]			;"
-		"	ld1	{v1.2d}, [%[key]], #16		;"
+		"	ld1	{v1.16b}, [%[key]], #16		;"
 		"	cmp	%w[rounds], #10			;"
 		"	bmi	0f				;"
 		"	bne	3f				;"
 		"	mov	v3.16b, v1.16b			;"
 		"	b	2f				;"
 		"0:	mov	v2.16b, v1.16b			;"
-		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	ld1	{v3.16b}, [%[key]], #16		;"
 		"1:	aese	v0.16b, v2.16b			;"
 		"	aesmc	v0.16b, v0.16b			;"
-		"2:	ld1	{v1.2d}, [%[key]], #16		;"
+		"2:	ld1	{v1.16b}, [%[key]], #16		;"
 		"	aese	v0.16b, v3.16b			;"
 		"	aesmc	v0.16b, v0.16b			;"
-		"3:	ld1	{v2.2d}, [%[key]], #16		;"
+		"3:	ld1	{v2.16b}, [%[key]], #16		;"
 		"	subs	%w[rounds], %w[rounds], #3	;"
 		"	aese	v0.16b, v1.16b			;"
 		"	aesmc	v0.16b, v0.16b			;"
-		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	ld1	{v3.16b}, [%[key]], #16		;"
 		"	bpl	1b				;"
 		"	aese	v0.16b, v2.16b			;"
 		"	eor	v0.16b, v0.16b, v3.16b		;"
@@ -92,24 +92,24 @@ static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 	kernel_neon_begin_partial(4);
 
 	__asm__("	ld1	{v0.16b}, %[in]			;"
-		"	ld1	{v1.2d}, [%[key]], #16		;"
+		"	ld1	{v1.16b}, [%[key]], #16		;"
 		"	cmp	%w[rounds], #10			;"
 		"	bmi	0f				;"
 		"	bne	3f				;"
 		"	mov	v3.16b, v1.16b			;"
 		"	b	2f				;"
 		"0:	mov	v2.16b, v1.16b			;"
-		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	ld1	{v3.16b}, [%[key]], #16		;"
 		"1:	aesd	v0.16b, v2.16b			;"
 		"	aesimc	v0.16b, v0.16b			;"
-		"2:	ld1	{v1.2d}, [%[key]], #16		;"
+		"2:	ld1	{v1.16b}, [%[key]], #16		;"
 		"	aesd	v0.16b, v3.16b			;"
 		"	aesimc	v0.16b, v0.16b			;"
-		"3:	ld1	{v2.2d}, [%[key]], #16		;"
+		"3:	ld1	{v2.16b}, [%[key]], #16		;"
 		"	subs	%w[rounds], %w[rounds], #3	;"
 		"	aesd	v0.16b, v1.16b			;"
 		"	aesimc	v0.16b, v0.16b			;"
-		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	ld1	{v3.16b}, [%[key]], #16		;"
 		"	bpl	1b				;"
 		"	aesd	v0.16b, v2.16b			;"
 		"	eor	v0.16b, v0.16b, v3.16b		;"
@@ -173,7 +173,12 @@ int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
 		u32 *rki = ctx->key_enc + (i * kwords);
 		u32 *rko = rki + kwords;
 
+#ifndef CONFIG_CPU_BIG_ENDIAN
 		rko[0] = ror32(aes_sub(rki[kwords - 1]), 8) ^ rcon[i] ^ rki[0];
+#else
+		rko[0] = rol32(aes_sub(rki[kwords - 1]), 8) ^ (rcon[i] << 24) ^
+			 rki[0];
+#endif
 		rko[1] = rko[0] ^ rki[1];
 		rko[2] = rko[1] ^ rki[2];
 		rko[3] = rko[2] ^ rki[3];
diff --git a/kernel/arch/arm64/crypto/aes-ce.S b/kernel/arch/arm64/crypto/aes-ce.S
index 78f3cfe92..b46093d56 100644
--- a/kernel/arch/arm64/crypto/aes-ce.S
+++ b/kernel/arch/arm64/crypto/aes-ce.S
@@ -10,6 +10,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #define AES_ENTRY(func)		ENTRY(ce_ ## func)
 #define AES_ENDPROC(func)	ENDPROC(ce_ ## func)
diff --git a/kernel/arch/arm64/crypto/aes-glue.c b/kernel/arch/arm64/crypto/aes-glue.c
index 05d9e16c0..6a51dfccf 100644
--- a/kernel/arch/arm64/crypto/aes-glue.c
+++ b/kernel/arch/arm64/crypto/aes-glue.c
@@ -211,7 +211,7 @@ static int ctr_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		err = blkcipher_walk_done(desc, &walk,
 					  walk.nbytes % AES_BLOCK_SIZE);
 	}
-	if (nbytes) {
+	if (walk.nbytes % AES_BLOCK_SIZE) {
 		u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
 		u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
 		u8 __aligned(8) tail[AES_BLOCK_SIZE];
diff --git a/kernel/arch/arm64/crypto/aes-modes.S b/kernel/arch/arm64/crypto/aes-modes.S
index f6e372c52..838dad5c2 100644
--- a/kernel/arch/arm64/crypto/aes-modes.S
+++ b/kernel/arch/arm64/crypto/aes-modes.S
@@ -193,15 +193,16 @@ AES_ENTRY(aes_cbc_encrypt)
 	cbz		w6, .Lcbcencloop
 
 	ld1		{v0.16b}, [x5]			/* get iv */
-	enc_prepare	w3, x2, x5
+	enc_prepare	w3, x2, x6
 
 .Lcbcencloop:
 	ld1		{v1.16b}, [x1], #16		/* get next pt block */
 	eor		v0.16b, v0.16b, v1.16b		/* ..and xor with iv */
-	encrypt_block	v0, w3, x2, x5, w6
+	encrypt_block	v0, w3, x2, x6, w7
 	st1		{v0.16b}, [x0], #16
 	subs		w4, w4, #1
 	bne		.Lcbcencloop
+	st1		{v0.16b}, [x5]			/* return iv */
 	ret
 AES_ENDPROC(aes_cbc_encrypt)
 
@@ -211,7 +212,7 @@ AES_ENTRY(aes_cbc_decrypt)
 	cbz		w6, .LcbcdecloopNx
 
 	ld1		{v7.16b}, [x5]			/* get iv */
-	dec_prepare	w3, x2, x5
+	dec_prepare	w3, x2, x6
 
 .LcbcdecloopNx:
 #if INTERLEAVE >= 2
@@ -248,7 +249,7 @@ AES_ENTRY(aes_cbc_decrypt)
 .Lcbcdecloop:
 	ld1		{v1.16b}, [x1], #16		/* get next ct block */
 	mov		v0.16b, v1.16b			/* ...and copy to v0 */
-	decrypt_block	v0, w3, x2, x5, w6
+	decrypt_block	v0, w3, x2, x6, w7
 	eor		v0.16b, v0.16b, v7.16b		/* xor with iv => pt */
 	mov		v7.16b, v1.16b			/* ct is next iv */
 	st1		{v0.16b}, [x0], #16
@@ -256,6 +257,7 @@ AES_ENTRY(aes_cbc_decrypt)
 	bne		.Lcbcdecloop
 .Lcbcdecout:
 	FRAME_POP
+	st1		{v7.16b}, [x5]			/* return iv */
 	ret
 AES_ENDPROC(aes_cbc_decrypt)
 
@@ -267,24 +269,15 @@ AES_ENDPROC(aes_cbc_decrypt)
 
 AES_ENTRY(aes_ctr_encrypt)
 	FRAME_PUSH
-	cbnz		w6, .Lctrfirst		/* 1st time around? */
-	umov		x5, v4.d[1]		/* keep swabbed ctr in reg */
-	rev		x5, x5
-#if INTERLEAVE >= 2
-	cmn		w5, w4			/* 32 bit overflow? */
-	bcs		.Lctrinc
-	add		x5, x5, #1		/* increment BE ctr */
-	b		.LctrincNx
-#else
-	b		.Lctrinc
-#endif
-.Lctrfirst:
+	cbz		w6, .Lctrnotfirst	/* 1st time around? */
 	enc_prepare	w3, x2, x6
 	ld1		{v4.16b}, [x5]
-	umov		x5, v4.d[1]		/* keep swabbed ctr in reg */
-	rev		x5, x5
+
+.Lctrnotfirst:
+	umov		x8, v4.d[1]		/* keep swabbed ctr in reg */
+	rev		x8, x8
 #if INTERLEAVE >= 2
-	cmn		w5, w4			/* 32 bit overflow? */
+	cmn		w8, w4			/* 32 bit overflow? */
 	bcs		.Lctrloop
 .LctrloopNx:
 	subs		w4, w4, #INTERLEAVE
@@ -292,11 +285,11 @@ AES_ENTRY(aes_ctr_encrypt)
 #if INTERLEAVE == 2
 	mov		v0.8b, v4.8b
 	mov		v1.8b, v4.8b
-	rev		x7, x5
-	add		x5, x5, #1
+	rev		x7, x8
+	add		x8, x8, #1
 	ins		v0.d[1], x7
-	rev		x7, x5
-	add		x5, x5, #1
+	rev		x7, x8
+	add		x8, x8, #1
 	ins		v1.d[1], x7
 	ld1		{v2.16b-v3.16b}, [x1], #32	/* get 2 input blocks */
 	do_encrypt_block2x
@@ -305,7 +298,7 @@ AES_ENTRY(aes_ctr_encrypt)
 	st1		{v0.16b-v1.16b}, [x0], #32
 #else
 	ldr		q8, =0x30000000200000001	/* addends 1,2,3[,0] */
-	dup		v7.4s, w5
+	dup		v7.4s, w8
 	mov		v0.16b, v4.16b
 	add		v7.4s, v7.4s, v8.4s
 	mov		v1.16b, v4.16b
@@ -323,18 +316,12 @@ AES_ENTRY(aes_ctr_encrypt)
 	eor		v2.16b, v7.16b, v2.16b
 	eor		v3.16b, v5.16b, v3.16b
 	st1		{v0.16b-v3.16b}, [x0], #64
-	add		x5, x5, #INTERLEAVE
+	add		x8, x8, #INTERLEAVE
 #endif
-	cbz		w4, .LctroutNx
-.LctrincNx:
-	rev		x7, x5
+	rev		x7, x8
 	ins		v4.d[1], x7
+	cbz		w4, .Lctrout
 	b		.LctrloopNx
-.LctroutNx:
-	sub		x5, x5, #1
-	rev		x7, x5
-	ins		v4.d[1], x7
-	b		.Lctrout
 .Lctr1x:
 	adds		w4, w4, #INTERLEAVE
 	beq		.Lctrout
@@ -342,30 +329,39 @@ AES_ENTRY(aes_ctr_encrypt)
 .Lctrloop:
 	mov		v0.16b, v4.16b
 	encrypt_block	v0, w3, x2, x6, w7
+
+	adds		x8, x8, #1		/* increment BE ctr */
+	rev		x7, x8
+	ins		v4.d[1], x7
+	bcs		.Lctrcarry		/* overflow? */
+
+.Lctrcarrydone:
 	subs		w4, w4, #1
 	bmi		.Lctrhalfblock		/* blocks < 0 means 1/2 block */
 	ld1		{v3.16b}, [x1], #16
 	eor		v3.16b, v0.16b, v3.16b
 	st1		{v3.16b}, [x0], #16
-	beq		.Lctrout
-.Lctrinc:
-	adds		x5, x5, #1		/* increment BE ctr */
-	rev		x7, x5
-	ins		v4.d[1], x7
-	bcc		.Lctrloop		/* no overflow? */
-	umov		x7, v4.d[0]		/* load upper word of ctr  */
-	rev		x7, x7			/* ... to handle the carry */
-	add		x7, x7, #1
-	rev		x7, x7
-	ins		v4.d[0], x7
-	b		.Lctrloop
+	bne		.Lctrloop
+
+.Lctrout:
+	st1		{v4.16b}, [x5]		/* return next CTR value */
+	FRAME_POP
+	ret
+
 .Lctrhalfblock:
 	ld1		{v3.8b}, [x1]
 	eor		v3.8b, v0.8b, v3.8b
 	st1		{v3.8b}, [x0]
-.Lctrout:
 	FRAME_POP
 	ret
+
+.Lctrcarry:
+	umov		x7, v4.d[0]		/* load upper word of ctr  */
+	rev		x7, x7			/* ... to handle the carry */
+	add		x7, x7, #1
+	rev		x7, x7
+	ins		v4.d[0], x7
+	b		.Lctrcarrydone
 AES_ENDPROC(aes_ctr_encrypt)
 	.ltorg
 
@@ -386,7 +382,8 @@ AES_ENDPROC(aes_ctr_encrypt)
 	.endm
 
 .Lxts_mul_x:
-	.word		1, 0, 0x87, 0
+CPU_LE(	.quad		1, 0x87		)
+CPU_BE(	.quad		0x87, 1		)
 
 AES_ENTRY(aes_xts_encrypt)
 	FRAME_PUSH
diff --git a/kernel/arch/arm64/crypto/aes-neon.S b/kernel/arch/arm64/crypto/aes-neon.S
index b93170e1c..85f07ead7 100644
--- a/kernel/arch/arm64/crypto/aes-neon.S
+++ b/kernel/arch/arm64/crypto/aes-neon.S
@@ -9,6 +9,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #define AES_ENTRY(func)		ENTRY(neon_ ## func)
 #define AES_ENDPROC(func)	ENDPROC(neon_ ## func)
@@ -83,13 +84,13 @@
 	.endm
 
 	.macro		do_block, enc, in, rounds, rk, rkp, i
-	ld1		{v15.16b}, [\rk]
+	ld1		{v15.4s}, [\rk]
 	add		\rkp, \rk, #16
 	mov		\i, \rounds
 1111:	eor		\in\().16b, \in\().16b, v15.16b		/* ^round key */
 	tbl		\in\().16b, {\in\().16b}, v13.16b	/* ShiftRows */
 	sub_bytes	\in
-	ld1		{v15.16b}, [\rkp], #16
+	ld1		{v15.4s}, [\rkp], #16
 	subs		\i, \i, #1
 	beq		2222f
 	.if		\enc == 1
@@ -229,7 +230,7 @@
 	.endm
 
 	.macro		do_block_2x, enc, in0, in1 rounds, rk, rkp, i
-	ld1		{v15.16b}, [\rk]
+	ld1		{v15.4s}, [\rk]
 	add		\rkp, \rk, #16
 	mov		\i, \rounds
 1111:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
@@ -237,7 +238,7 @@
 	sub_bytes_2x	\in0, \in1
 	tbl		\in0\().16b, {\in0\().16b}, v13.16b	/* ShiftRows */
 	tbl		\in1\().16b, {\in1\().16b}, v13.16b	/* ShiftRows */
-	ld1		{v15.16b}, [\rkp], #16
+	ld1		{v15.4s}, [\rkp], #16
 	subs		\i, \i, #1
 	beq		2222f
 	.if		\enc == 1
@@ -254,7 +255,7 @@
 	.endm
 
 	.macro		do_block_4x, enc, in0, in1, in2, in3, rounds, rk, rkp, i
-	ld1		{v15.16b}, [\rk]
+	ld1		{v15.4s}, [\rk]
 	add		\rkp, \rk, #16
 	mov		\i, \rounds
 1111:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
@@ -266,7 +267,7 @@
 	tbl		\in1\().16b, {\in1\().16b}, v13.16b	/* ShiftRows */
 	tbl		\in2\().16b, {\in2\().16b}, v13.16b	/* ShiftRows */
 	tbl		\in3\().16b, {\in3\().16b}, v13.16b	/* ShiftRows */
-	ld1		{v15.16b}, [\rkp], #16
+	ld1		{v15.4s}, [\rkp], #16
 	subs		\i, \i, #1
 	beq		2222f
 	.if		\enc == 1
@@ -306,12 +307,16 @@
 	.text
 	.align		4
 .LForward_ShiftRows:
-	.byte		0x0, 0x5, 0xa, 0xf, 0x4, 0x9, 0xe, 0x3
-	.byte		0x8, 0xd, 0x2, 0x7, 0xc, 0x1, 0x6, 0xb
+CPU_LE(	.byte		0x0, 0x5, 0xa, 0xf, 0x4, 0x9, 0xe, 0x3	)
+CPU_LE(	.byte		0x8, 0xd, 0x2, 0x7, 0xc, 0x1, 0x6, 0xb	)
+CPU_BE(	.byte		0xb, 0x6, 0x1, 0xc, 0x7, 0x2, 0xd, 0x8	)
+CPU_BE(	.byte		0x3, 0xe, 0x9, 0x4, 0xf, 0xa, 0x5, 0x0	)
 
 .LReverse_ShiftRows:
-	.byte		0x0, 0xd, 0xa, 0x7, 0x4, 0x1, 0xe, 0xb
-	.byte		0x8, 0x5, 0x2, 0xf, 0xc, 0x9, 0x6, 0x3
+CPU_LE(	.byte		0x0, 0xd, 0xa, 0x7, 0x4, 0x1, 0xe, 0xb	)
+CPU_LE(	.byte		0x8, 0x5, 0x2, 0xf, 0xc, 0x9, 0x6, 0x3	)
+CPU_BE(	.byte		0x3, 0x6, 0x9, 0xc, 0xf, 0x2, 0x5, 0x8	)
+CPU_BE(	.byte		0xb, 0xe, 0x1, 0x4, 0x7, 0xa, 0xd, 0x0	)
 
 .LForward_Sbox:
 	.byte		0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5
diff --git a/kernel/arch/arm64/crypto/ghash-ce-core.S b/kernel/arch/arm64/crypto/ghash-ce-core.S
index dc4570158..f0bb9f0b5 100644
--- a/kernel/arch/arm64/crypto/ghash-ce-core.S
+++ b/kernel/arch/arm64/crypto/ghash-ce-core.S
@@ -29,8 +29,8 @@
 	 *			   struct ghash_key const *k, const char *head)
 	 */
 ENTRY(pmull_ghash_update)
-	ld1		{SHASH.16b}, [x3]
-	ld1		{XL.16b}, [x1]
+	ld1		{SHASH.2d}, [x3]
+	ld1		{XL.2d}, [x1]
 	movi		MASK.16b, #0xe1
 	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
 	shl		MASK.2d, MASK.2d, #57
@@ -74,6 +74,6 @@ CPU_LE(	rev64		T1.16b, T1.16b	)
 
 	cbnz		w0, 0b
 
-	st1		{XL.16b}, [x1]
+	st1		{XL.2d}, [x1]
 	ret
 ENDPROC(pmull_ghash_update)
diff --git a/kernel/arch/arm64/crypto/sha1-ce-core.S b/kernel/arch/arm64/crypto/sha1-ce-core.S
index 033aae6d7..c98e7e849 100644
--- a/kernel/arch/arm64/crypto/sha1-ce-core.S
+++ b/kernel/arch/arm64/crypto/sha1-ce-core.S
@@ -78,7 +78,7 @@ ENTRY(sha1_ce_transform)
 	ld1r		{k3.4s}, [x6]
 
 	/* load state */
-	ldr		dga, [x0]
+	ld1		{dgav.4s}, [x0]
 	ldr		dgb, [x0, #16]
 
 	/* load sha1_ce_state::finalize */
@@ -144,7 +144,7 @@ CPU_LE(	rev32		v11.16b, v11.16b	)
 	b		1b
 
 	/* store new state */
-3:	str		dga, [x0]
+3:	st1		{dgav.4s}, [x0]
 	str		dgb, [x0, #16]
 	ret
 ENDPROC(sha1_ce_transform)
diff --git a/kernel/arch/arm64/crypto/sha2-ce-core.S b/kernel/arch/arm64/crypto/sha2-ce-core.S
index 5df9d9d47..01cfee066 100644
--- a/kernel/arch/arm64/crypto/sha2-ce-core.S
+++ b/kernel/arch/arm64/crypto/sha2-ce-core.S
@@ -85,7 +85,7 @@ ENTRY(sha2_ce_transform)
 	ld1		{v12.4s-v15.4s}, [x8]
 
 	/* load state */
-	ldp		dga, dgb, [x0]
+	ld1		{dgav.4s, dgbv.4s}, [x0]
 
 	/* load sha256_ce_state::finalize */
 	ldr		w4, [x0, #:lo12:sha256_ce_offsetof_finalize]
@@ -148,6 +148,6 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
 	b		1b
 
 	/* store new state */
-3:	stp		dga, dgb, [x0]
+3:	st1		{dgav.4s, dgbv.4s}, [x0]
 	ret
 ENDPROC(sha2_ce_transform)
diff --git a/kernel/arch/arm64/include/asm/arch_gicv3.h b/kernel/arch/arm64/include/asm/arch_gicv3.h
index 2731d3b25..8ec88e5b2 100644
--- a/kernel/arch/arm64/include/asm/arch_gicv3.h
+++ b/kernel/arch/arm64/include/asm/arch_gicv3.h
@@ -103,6 +103,7 @@ static inline u64 gic_read_iar_common(void)
 	u64 irqstat;
 
 	asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat));
+	dsb(sy);
 	return irqstat;
 }
 
diff --git a/kernel/arch/arm64/include/asm/cpufeature.h b/kernel/arch/arm64/include/asm/cpufeature.h
index 8f271b83f..8884b5d5f 100644
--- a/kernel/arch/arm64/include/asm/cpufeature.h
+++ b/kernel/arch/arm64/include/asm/cpufeature.h
@@ -30,8 +30,9 @@
 #define ARM64_HAS_LSE_ATOMICS			5
 #define ARM64_WORKAROUND_CAVIUM_23154		6
 #define ARM64_WORKAROUND_834220			7
+#define ARM64_WORKAROUND_CAVIUM_27456		8
 
-#define ARM64_NCAPS				8
+#define ARM64_NCAPS				9
 
 #ifndef __ASSEMBLY__
 
@@ -76,7 +77,7 @@ struct arm64_cpu_capabilities {
 	const char *desc;
 	u16 capability;
 	bool (*matches)(const struct arm64_cpu_capabilities *);
-	void (*enable)(void *);		/* Called on all active CPUs */
+	int (*enable)(void *);		/* Called on all active CPUs */
 	union {
 		struct {	/* To be used for erratum handling only */
 			u32 midr_model;
diff --git a/kernel/arch/arm64/include/asm/elf.h b/kernel/arch/arm64/include/asm/elf.h
index faad6df49..44dd892a4 100644
--- a/kernel/arch/arm64/include/asm/elf.h
+++ b/kernel/arch/arm64/include/asm/elf.h
@@ -136,6 +136,7 @@ typedef struct user_fpsimd_state elf_fpregset_t;
 
 #define SET_PERSONALITY(ex)		clear_thread_flag(TIF_32BIT);
 
+/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
 #define ARCH_DLINFO							\
 do {									\
 	NEW_AUX_ENT(AT_SYSINFO_EHDR,					\
@@ -156,14 +157,14 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 #define STACK_RND_MASK			(0x3ffff >> (PAGE_SHIFT - 12))
 #endif
 
-#ifdef CONFIG_COMPAT
-
 #ifdef __AARCH64EB__
 #define COMPAT_ELF_PLATFORM		("v8b")
 #else
 #define COMPAT_ELF_PLATFORM		("v8l")
 #endif
 
+#ifdef CONFIG_COMPAT
+
 #define COMPAT_ELF_ET_DYN_BASE		(2 * TASK_SIZE_32 / 3)
 
 /* AArch32 registers. */
diff --git a/kernel/arch/arm64/include/asm/futex.h b/kernel/arch/arm64/include/asm/futex.h
index 007a69fc4..5f3ab8c1d 100644
--- a/kernel/arch/arm64/include/asm/futex.h
+++ b/kernel/arch/arm64/include/asm/futex.h
@@ -121,6 +121,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		return -EFAULT;
 
 	asm volatile("// futex_atomic_cmpxchg_inatomic\n"
+ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
 "	prfm	pstl1strm, %2\n"
 "1:	ldxr	%w1, %2\n"
 "	sub	%w3, %w1, %w4\n"
@@ -137,6 +138,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 "	.align	3\n"
 "	.quad	1b, 4b, 2b, 4b\n"
 "	.popsection\n"
+ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
 	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp)
 	: "r" (oldval), "r" (newval), "Ir" (-EFAULT)
 	: "memory");
diff --git a/kernel/arch/arm64/include/asm/kvm_arm.h b/kernel/arch/arm64/include/asm/kvm_arm.h
index 5e6857b6b..2d960f858 100644
--- a/kernel/arch/arm64/include/asm/kvm_arm.h
+++ b/kernel/arch/arm64/include/asm/kvm_arm.h
@@ -107,8 +107,6 @@
 #define TCR_EL2_MASK	(TCR_EL2_TG0 | TCR_EL2_SH0 | \
 			 TCR_EL2_ORGN0 | TCR_EL2_IRGN0 | TCR_EL2_T0SZ)
 
-#define TCR_EL2_FLAGS	(TCR_EL2_RES1 | TCR_EL2_PS_40B)
-
 /* VTCR_EL2 Registers bits */
 #define VTCR_EL2_RES1		(1 << 31)
 #define VTCR_EL2_PS_MASK	(7 << 16)
diff --git a/kernel/arch/arm64/include/asm/opcodes.h b/kernel/arch/arm64/include/asm/opcodes.h
index 4e603ea36..123f45d92 100644
--- a/kernel/arch/arm64/include/asm/opcodes.h
+++ b/kernel/arch/arm64/include/asm/opcodes.h
@@ -1 +1,5 @@
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define CONFIG_CPU_ENDIAN_BE8 CONFIG_CPU_BIG_ENDIAN
+#endif
+
 #include <../../arm/include/asm/opcodes.h>
diff --git a/kernel/arch/arm64/include/asm/percpu.h b/kernel/arch/arm64/include/asm/percpu.h
index 0a456bef8..8a336852e 100644
--- a/kernel/arch/arm64/include/asm/percpu.h
+++ b/kernel/arch/arm64/include/asm/percpu.h
@@ -44,48 +44,44 @@ static inline unsigned long __percpu_##op(void *ptr,			\
 									\
 	switch (size) {							\
 	case 1:								\
-		do {							\
-			asm ("//__per_cpu_" #op "_1\n"			\
-			"ldxrb	  %w[ret], %[ptr]\n"			\
+		asm ("//__per_cpu_" #op "_1\n"				\
+		"1:	ldxrb	  %w[ret], %[ptr]\n"			\
 			#asm_op " %w[ret], %w[ret], %w[val]\n"		\
-			"stxrb	  %w[loop], %w[ret], %[ptr]\n"		\
-			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
-			  [ptr] "+Q"(*(u8 *)ptr)			\
-			: [val] "Ir" (val));				\
-		} while (loop);						\
+		"	stxrb	  %w[loop], %w[ret], %[ptr]\n"		\
+		"	cbnz	  %w[loop], 1b"				\
+		: [loop] "=&r" (loop), [ret] "=&r" (ret),		\
+		  [ptr] "+Q"(*(u8 *)ptr)				\
+		: [val] "Ir" (val));					\
 		break;							\
 	case 2:								\
-		do {							\
-			asm ("//__per_cpu_" #op "_2\n"			\
-			"ldxrh	  %w[ret], %[ptr]\n"			\
+		asm ("//__per_cpu_" #op "_2\n"				\
+		"1:	ldxrh	  %w[ret], %[ptr]\n"			\
 			#asm_op " %w[ret], %w[ret], %w[val]\n"		\
-			"stxrh	  %w[loop], %w[ret], %[ptr]\n"		\
-			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
-			  [ptr]  "+Q"(*(u16 *)ptr)			\
-			: [val] "Ir" (val));				\
-		} while (loop);						\
+		"	stxrh	  %w[loop], %w[ret], %[ptr]\n"		\
+		"	cbnz	  %w[loop], 1b"				\
+		: [loop] "=&r" (loop), [ret] "=&r" (ret),		\
+		  [ptr]  "+Q"(*(u16 *)ptr)				\
+		: [val] "Ir" (val));					\
 		break;							\
 	case 4:								\
-		do {							\
-			asm ("//__per_cpu_" #op "_4\n"			\
-			"ldxr	  %w[ret], %[ptr]\n"			\
+		asm ("//__per_cpu_" #op "_4\n"				\
+		"1:	ldxr	  %w[ret], %[ptr]\n"			\
 			#asm_op " %w[ret], %w[ret], %w[val]\n"		\
-			"stxr	  %w[loop], %w[ret], %[ptr]\n"		\
-			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
-			  [ptr] "+Q"(*(u32 *)ptr)			\
-			: [val] "Ir" (val));				\
-		} while (loop);						\
+		"	stxr	  %w[loop], %w[ret], %[ptr]\n"		\
+		"	cbnz	  %w[loop], 1b"				\
+		: [loop] "=&r" (loop), [ret] "=&r" (ret),		\
+		  [ptr] "+Q"(*(u32 *)ptr)				\
+		: [val] "Ir" (val));					\
 		break;							\
 	case 8:								\
-		do {							\
-			asm ("//__per_cpu_" #op "_8\n"			\
-			"ldxr	  %[ret], %[ptr]\n"			\
+		asm ("//__per_cpu_" #op "_8\n"				\
+		"1:	ldxr	  %[ret], %[ptr]\n"			\
 			#asm_op " %[ret], %[ret], %[val]\n"		\
-			"stxr	  %w[loop], %[ret], %[ptr]\n"		\
-			: [loop] "=&r" (loop), [ret] "=&r" (ret),	\
-			  [ptr] "+Q"(*(u64 *)ptr)			\
-			: [val] "Ir" (val));				\
-		} while (loop);						\
+		"	stxr	  %w[loop], %[ret], %[ptr]\n"		\
+		"	cbnz	  %w[loop], 1b"				\
+		: [loop] "=&r" (loop), [ret] "=&r" (ret),		\
+		  [ptr] "+Q"(*(u64 *)ptr)				\
+		: [val] "Ir" (val));					\
 		break;							\
 	default:							\
 		BUILD_BUG();						\
@@ -150,44 +146,40 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
 
 	switch (size) {
 	case 1:
-		do {
-			asm ("//__percpu_xchg_1\n"
-			"ldxrb %w[ret], %[ptr]\n"
-			"stxrb %w[loop], %w[val], %[ptr]\n"
-			: [loop] "=&r"(loop), [ret] "=&r"(ret),
-			  [ptr] "+Q"(*(u8 *)ptr)
-			: [val] "r" (val));
-		} while (loop);
+		asm ("//__percpu_xchg_1\n"
+		"1:	ldxrb	%w[ret], %[ptr]\n"
+		"	stxrb	%w[loop], %w[val], %[ptr]\n"
+		"	cbnz	%w[loop], 1b"
+		: [loop] "=&r"(loop), [ret] "=&r"(ret),
+		  [ptr] "+Q"(*(u8 *)ptr)
+		: [val] "r" (val));
 		break;
 	case 2:
-		do {
-			asm ("//__percpu_xchg_2\n"
-			"ldxrh %w[ret], %[ptr]\n"
-			"stxrh %w[loop], %w[val], %[ptr]\n"
-			: [loop] "=&r"(loop), [ret] "=&r"(ret),
-			  [ptr] "+Q"(*(u16 *)ptr)
-			: [val] "r" (val));
-		} while (loop);
+		asm ("//__percpu_xchg_2\n"
+		"1:	ldxrh	%w[ret], %[ptr]\n"
+		"	stxrh	%w[loop], %w[val], %[ptr]\n"
+		"	cbnz	%w[loop], 1b"
+		: [loop] "=&r"(loop), [ret] "=&r"(ret),
+		  [ptr] "+Q"(*(u16 *)ptr)
+		: [val] "r" (val));
 		break;
 	case 4:
-		do {
-			asm ("//__percpu_xchg_4\n"
-			"ldxr %w[ret], %[ptr]\n"
-			"stxr %w[loop], %w[val], %[ptr]\n"
-			: [loop] "=&r"(loop), [ret] "=&r"(ret),
-			  [ptr] "+Q"(*(u32 *)ptr)
-			: [val] "r" (val));
-		} while (loop);
+		asm ("//__percpu_xchg_4\n"
+		"1:	ldxr	%w[ret], %[ptr]\n"
+		"	stxr	%w[loop], %w[val], %[ptr]\n"
+		"	cbnz	%w[loop], 1b"
+		: [loop] "=&r"(loop), [ret] "=&r"(ret),
+		  [ptr] "+Q"(*(u32 *)ptr)
+		: [val] "r" (val));
 		break;
 	case 8:
-		do {
-			asm ("//__percpu_xchg_8\n"
-			"ldxr %[ret], %[ptr]\n"
-			"stxr %w[loop], %[val], %[ptr]\n"
-			: [loop] "=&r"(loop), [ret] "=&r"(ret),
-			  [ptr] "+Q"(*(u64 *)ptr)
-			: [val] "r" (val));
-		} while (loop);
+		asm ("//__percpu_xchg_8\n"
+		"1:	ldxr	%[ret], %[ptr]\n"
+		"	stxr	%w[loop], %[val], %[ptr]\n"
+		"	cbnz	%w[loop], 1b"
+		: [loop] "=&r"(loop), [ret] "=&r"(ret),
+		  [ptr] "+Q"(*(u64 *)ptr)
+		: [val] "r" (val));
 		break;
 	default:
 		BUILD_BUG();
diff --git a/kernel/arch/arm64/include/asm/pgtable-hwdef.h b/kernel/arch/arm64/include/asm/pgtable-hwdef.h
index d6739e836..b9da9545b 100644
--- a/kernel/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/kernel/arch/arm64/include/asm/pgtable-hwdef.h
@@ -117,7 +117,6 @@
  * Section
  */
 #define PMD_SECT_VALID		(_AT(pmdval_t, 1) << 0)
-#define PMD_SECT_PROT_NONE	(_AT(pmdval_t, 1) << 58)
 #define PMD_SECT_USER		(_AT(pmdval_t, 1) << 6)		/* AP[1] */
 #define PMD_SECT_RDONLY		(_AT(pmdval_t, 1) << 7)		/* AP[2] */
 #define PMD_SECT_S		(_AT(pmdval_t, 3) << 8)
diff --git a/kernel/arch/arm64/include/asm/pgtable.h b/kernel/arch/arm64/include/asm/pgtable.h
index eaa9cabf4..67c2ad6d3 100644
--- a/kernel/arch/arm64/include/asm/pgtable.h
+++ b/kernel/arch/arm64/include/asm/pgtable.h
@@ -69,11 +69,11 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 #define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
 #define PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
 
-#define PROT_DEVICE_nGnRnE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
-#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
-#define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_NC))
-#define PROT_NORMAL_WT		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_WT))
-#define PROT_NORMAL		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL))
+#define PROT_DEVICE_nGnRnE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
+#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE))
+#define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC))
+#define PROT_NORMAL_WT		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT))
+#define PROT_NORMAL		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL))
 
 #define PROT_SECT_DEVICE_nGnRE	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE))
 #define PROT_SECT_NORMAL	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
@@ -83,7 +83,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 
 #define PAGE_KERNEL		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_RO		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
-#define PAGE_KERNEL_ROX	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
+#define PAGE_KERNEL_ROX		__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
 #define PAGE_KERNEL_EXEC	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_EXEC_CONT	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
 
@@ -155,6 +155,7 @@ extern struct page *empty_zero_page;
 #define pte_write(pte)		(!!(pte_val(pte) & PTE_WRITE))
 #define pte_exec(pte)		(!(pte_val(pte) & PTE_UXN))
 #define pte_cont(pte)		(!!(pte_val(pte) & PTE_CONT))
+#define pte_user(pte)		(!!(pte_val(pte) & PTE_USER))
 
 #ifdef CONFIG_ARM64_HW_AFDBM
 #define pte_hw_dirty(pte)	(pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
@@ -165,8 +166,6 @@ extern struct page *empty_zero_page;
 #define pte_dirty(pte)		(pte_sw_dirty(pte) || pte_hw_dirty(pte))
 
 #define pte_valid(pte)		(!!(pte_val(pte) & PTE_VALID))
-#define pte_valid_user(pte) \
-	((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
 #define pte_valid_not_user(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
 
@@ -264,13 +263,13 @@ extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pte)
 {
-	if (pte_valid_user(pte)) {
-		if (!pte_special(pte) && pte_exec(pte))
-			__sync_icache_dcache(pte, addr);
+	if (pte_present(pte)) {
 		if (pte_sw_dirty(pte) && pte_write(pte))
 			pte_val(pte) &= ~PTE_RDONLY;
 		else
 			pte_val(pte) |= PTE_RDONLY;
+		if (pte_user(pte) && pte_exec(pte) && !pte_special(pte))
+			__sync_icache_dcache(pte, addr);
 	}
 
 	/*
@@ -348,6 +347,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
 #endif /* CONFIG_HAVE_RCU_TABLE_FREE */
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+#define pmd_present(pmd)	pte_present(pmd_pte(pmd))
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
 #define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
@@ -356,7 +356,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
 #define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
-#define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) & ~PMD_TYPE_MASK))
+#define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) & ~PMD_SECT_VALID))
 
 #define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
@@ -395,7 +395,6 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 				     unsigned long size, pgprot_t vma_prot);
 
 #define pmd_none(pmd)		(!pmd_val(pmd))
-#define pmd_present(pmd)	(pmd_val(pmd))
 
 #define pmd_bad(pmd)		(!(pmd_val(pmd) & 2))
 
@@ -539,6 +538,21 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 }
 
 #ifdef CONFIG_ARM64_HW_AFDBM
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+extern int ptep_set_access_flags(struct vm_area_struct *vma,
+				 unsigned long address, pte_t *ptep,
+				 pte_t entry, int dirty);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
+					unsigned long address, pmd_t *pmdp,
+					pmd_t entry, int dirty)
+{
+	return ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty);
+}
+#endif
+
 /*
  * Atomic pte/pmd modifications.
  */
@@ -591,9 +605,9 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
-static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
-				       unsigned long address, pmd_t *pmdp)
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+					    unsigned long address, pmd_t *pmdp)
 {
 	return pte_pmd(ptep_get_and_clear(mm, address, (pte_t *)pmdp));
 }
@@ -641,6 +655,7 @@ extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
  *	bits 0-1:	present (must be zero)
  *	bits 2-7:	swap type
  *	bits 8-57:	swap offset
+ *	bit  58:	PTE_PROT_NONE (must be zero)
  */
 #define __SWP_TYPE_SHIFT	2
 #define __SWP_TYPE_BITS		6
diff --git a/kernel/arch/arm64/include/asm/processor.h b/kernel/arch/arm64/include/asm/processor.h
index 4acb7ca94..d08559528 100644
--- a/kernel/arch/arm64/include/asm/processor.h
+++ b/kernel/arch/arm64/include/asm/processor.h
@@ -186,6 +186,6 @@ static inline void spin_lock_prefetch(const void *x)
 
 #endif
 
-void cpu_enable_pan(void *__unused);
+int cpu_enable_pan(void *__unused);
 
 #endif /* __ASM_PROCESSOR_H */
diff --git a/kernel/arch/arm64/include/asm/ptrace.h b/kernel/arch/arm64/include/asm/ptrace.h
index e9e5467e0..7f9475508 100644
--- a/kernel/arch/arm64/include/asm/ptrace.h
+++ b/kernel/arch/arm64/include/asm/ptrace.h
@@ -58,6 +58,7 @@
 #define COMPAT_PSR_Z_BIT	0x40000000
 #define COMPAT_PSR_N_BIT	0x80000000
 #define COMPAT_PSR_IT_MASK	0x0600fc00	/* If-Then execution state mask */
+#define COMPAT_PSR_GE_MASK	0x000f0000
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
 #define COMPAT_PSR_ENDSTATE	COMPAT_PSR_E_BIT
@@ -116,6 +117,8 @@ struct pt_regs {
 	};
 	u64 orig_x0;
 	u64 syscallno;
+	u64 orig_addr_limit;
+	u64 unused;	// maintain 16 byte alignment
 };
 
 #define arch_has_single_step()	(1)
@@ -151,35 +154,9 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
 	return regs->regs[0];
 }
 
-/*
- * Are the current registers suitable for user mode? (used to maintain
- * security in signal handlers)
- */
-static inline int valid_user_regs(struct user_pt_regs *regs)
-{
-	if (user_mode(regs) && (regs->pstate & PSR_I_BIT) == 0) {
-		regs->pstate &= ~(PSR_F_BIT | PSR_A_BIT);
-
-		/* The T bit is reserved for AArch64 */
-		if (!(regs->pstate & PSR_MODE32_BIT))
-			regs->pstate &= ~COMPAT_PSR_T_BIT;
-
-		return 1;
-	}
-
-	/*
-	 * Force PSR to something logical...
-	 */
-	regs->pstate &= PSR_f | PSR_s | (PSR_x & ~PSR_A_BIT) | \
-			COMPAT_PSR_T_BIT | PSR_MODE32_BIT;
-
-	if (!(regs->pstate & PSR_MODE32_BIT)) {
-		regs->pstate &= ~COMPAT_PSR_T_BIT;
-		regs->pstate |= PSR_MODE_EL0t;
-	}
-
-	return 0;
-}
+/* We must avoid circular header include via sched.h */
+struct task_struct;
+int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task);
 
 #define instruction_pointer(regs)	((unsigned long)(regs)->pc)
 
diff --git a/kernel/arch/arm64/include/asm/spinlock.h b/kernel/arch/arm64/include/asm/spinlock.h
index c85e96d17..499e8de33 100644
--- a/kernel/arch/arm64/include/asm/spinlock.h
+++ b/kernel/arch/arm64/include/asm/spinlock.h
@@ -312,4 +312,14 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 #define arch_read_relax(lock)	cpu_relax()
 #define arch_write_relax(lock)	cpu_relax()
 
+/*
+ * Accesses appearing in program order before a spin_lock() operation
+ * can be reordered with accesses inside the critical section, by virtue
+ * of arch_spin_lock being constructed using acquire semantics.
+ *
+ * In cases where this is problematic (e.g. try_to_wake_up), an
+ * smp_mb__before_spinlock() can restore the required ordering.
+ */
+#define smp_mb__before_spinlock()	smp_mb()
+
 #endif /* __ASM_SPINLOCK_H */
diff --git a/kernel/arch/arm64/include/uapi/asm/auxvec.h b/kernel/arch/arm64/include/uapi/asm/auxvec.h
index 22d6d8885..4cf0c1778 100644
--- a/kernel/arch/arm64/include/uapi/asm/auxvec.h
+++ b/kernel/arch/arm64/include/uapi/asm/auxvec.h
@@ -19,4 +19,6 @@
 /* vDSO location */
 #define AT_SYSINFO_EHDR	33
 
+#define AT_VECTOR_SIZE_ARCH 1 /* entries in ARCH_DLINFO */
+
 #endif
diff --git a/kernel/arch/arm64/include/uapi/asm/ptrace.h b/kernel/arch/arm64/include/uapi/asm/ptrace.h
index 208db3df1..3378238b5 100644
--- a/kernel/arch/arm64/include/uapi/asm/ptrace.h
+++ b/kernel/arch/arm64/include/uapi/asm/ptrace.h
@@ -76,6 +76,7 @@ struct user_fpsimd_state {
 	__uint128_t	vregs[32];
 	__u32		fpsr;
 	__u32		fpcr;
+	__u32		__reserved[2];
 };
 
 struct user_hwdebug_state {
diff --git a/kernel/arch/arm64/kernel/asm-offsets.c b/kernel/arch/arm64/kernel/asm-offsets.c
index c5038409e..d74475928 100644
--- a/kernel/arch/arm64/kernel/asm-offsets.c
+++ b/kernel/arch/arm64/kernel/asm-offsets.c
@@ -59,6 +59,7 @@ int main(void)
   DEFINE(S_PC,			offsetof(struct pt_regs, pc));
   DEFINE(S_ORIG_X0,		offsetof(struct pt_regs, orig_x0));
   DEFINE(S_SYSCALLNO,		offsetof(struct pt_regs, syscallno));
+  DEFINE(S_ORIG_ADDR_LIMIT,	offsetof(struct pt_regs, orig_addr_limit));
   DEFINE(S_FRAME_SIZE,		sizeof(struct pt_regs));
   BLANK();
   DEFINE(MM_CONTEXT_ID,		offsetof(struct mm_struct, context.id.counter));
diff --git a/kernel/arch/arm64/kernel/cpu_errata.c b/kernel/arch/arm64/kernel/cpu_errata.c
index feb6b4efa..a3e846a28 100644
--- a/kernel/arch/arm64/kernel/cpu_errata.c
+++ b/kernel/arch/arm64/kernel/cpu_errata.c
@@ -100,6 +100,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		MIDR_RANGE(MIDR_THUNDERX, 0x00, 0x01),
 	},
 #endif
+#ifdef CONFIG_CAVIUM_ERRATUM_27456
+	{
+	/* Cavium ThunderX, T88 pass 1.x - 2.1 */
+		.desc = "Cavium erratum 27456",
+		.capability = ARM64_WORKAROUND_CAVIUM_27456,
+		MIDR_RANGE(MIDR_THUNDERX, 0x00,
+			   (1 << MIDR_VARIANT_SHIFT) | 1),
+	},
+#endif
 	{
 	}
 };
diff --git a/kernel/arch/arm64/kernel/cpufeature.c b/kernel/arch/arm64/kernel/cpufeature.c
index 0669c6328..2735bf814 100644
--- a/kernel/arch/arm64/kernel/cpufeature.c
+++ b/kernel/arch/arm64/kernel/cpufeature.c
@@ -19,7 +19,9 @@
 #define pr_fmt(fmt) "CPU features: " fmt
 
 #include <linux/bsearch.h>
+#include <linux/cpumask.h>
 #include <linux/sort.h>
+#include <linux/stop_machine.h>
 #include <linux/types.h>
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
@@ -764,7 +766,13 @@ static void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
 
 	for (i = 0; caps[i].desc; i++)
 		if (caps[i].enable && cpus_have_cap(caps[i].capability))
-			on_each_cpu(caps[i].enable, NULL, true);
+			/*
+			 * Use stop_machine() as it schedules the work allowing
+			 * us to modify PSTATE, instead of on_each_cpu() which
+			 * uses an IPI, giving us a PSTATE that disappears when
+			 * we return.
+			 */
+			stop_machine(caps[i].enable, NULL, cpu_online_mask);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/kernel/arch/arm64/kernel/cpuinfo.c b/kernel/arch/arm64/kernel/cpuinfo.c
index 212ae6361..0166cfbc8 100644
--- a/kernel/arch/arm64/kernel/cpuinfo.c
+++ b/kernel/arch/arm64/kernel/cpuinfo.c
@@ -22,6 +22,8 @@
 
 #include <linux/bitops.h>
 #include <linux/bug.h>
+#include <linux/compat.h>
+#include <linux/elf.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/personality.h>
@@ -85,7 +87,8 @@ static const char *const compat_hwcap_str[] = {
 	"idivt",
 	"vfpd32",
 	"lpae",
-	"evtstrm"
+	"evtstrm",
+	NULL
 };
 
 static const char *const compat_hwcap2_str[] = {
@@ -101,6 +104,7 @@ static const char *const compat_hwcap2_str[] = {
 static int c_show(struct seq_file *m, void *v)
 {
 	int i, j;
+	bool compat = personality(current->personality) == PER_LINUX32;
 
 	for_each_online_cpu(i) {
 		struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i);
@@ -112,6 +116,9 @@ static int c_show(struct seq_file *m, void *v)
 		 * "processor".  Give glibc what it expects.
 		 */
 		seq_printf(m, "processor\t: %d\n", i);
+		if (compat)
+			seq_printf(m, "model name\t: ARMv8 Processor rev %d (%s)\n",
+				   MIDR_REVISION(midr), COMPAT_ELF_PLATFORM);
 
 		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
 			   loops_per_jiffy / (500000UL/HZ),
@@ -124,7 +131,7 @@ static int c_show(struct seq_file *m, void *v)
 		 * software which does already (at least for 32-bit).
 		 */
 		seq_puts(m, "Features\t:");
-		if (personality(current->personality) == PER_LINUX32) {
+		if (compat) {
 #ifdef CONFIG_COMPAT
 			for (j = 0; compat_hwcap_str[j]; j++)
 				if (compat_elf_hwcap & (1 << j))
diff --git a/kernel/arch/arm64/kernel/debug-monitors.c b/kernel/arch/arm64/kernel/debug-monitors.c
index c1492ba1f..c8875b64b 100644
--- a/kernel/arch/arm64/kernel/debug-monitors.c
+++ b/kernel/arch/arm64/kernel/debug-monitors.c
@@ -152,7 +152,6 @@ static int debug_monitors_init(void)
 	/* Clear the OS lock. */
 	on_each_cpu(clear_os_lock, NULL, 1);
 	isb();
-	local_dbg_enable();
 
 	/* Register hotplug handler. */
 	__register_cpu_notifier(&os_lock_nb);
@@ -423,8 +422,10 @@ int kernel_active_single_step(void)
 /* ptrace API */
 void user_enable_single_step(struct task_struct *task)
 {
-	set_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP);
-	set_regs_spsr_ss(task_pt_regs(task));
+	struct thread_info *ti = task_thread_info(task);
+
+	if (!test_and_set_ti_thread_flag(ti, TIF_SINGLESTEP))
+		set_regs_spsr_ss(task_pt_regs(task));
 }
 
 void user_disable_single_step(struct task_struct *task)
diff --git a/kernel/arch/arm64/kernel/entry.S b/kernel/arch/arm64/kernel/entry.S
index dd8fd31f8..cf92d4ee5 100644
--- a/kernel/arch/arm64/kernel/entry.S
+++ b/kernel/arch/arm64/kernel/entry.S
@@ -27,6 +27,7 @@
 #include <asm/cpufeature.h>
 #include <asm/errno.h>
 #include <asm/esr.h>
+#include <asm/memory.h>
 #include <asm/thread_info.h>
 #include <asm/unistd.h>
 
@@ -93,7 +94,13 @@
 	disable_step_tsk x19, x20		// exceptions when scheduling.
 	.else
 	add	x21, sp, #S_FRAME_SIZE
-	.endif
+	get_thread_info tsk
+	/* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */
+	ldr	x20, [tsk, #TI_ADDR_LIMIT]
+	str	x20, [sp, #S_ORIG_ADDR_LIMIT]
+	mov	x20, #TASK_SIZE_64
+	str	x20, [tsk, #TI_ADDR_LIMIT]
+	.endif /* \el == 0 */
 	mrs	x22, elr_el1
 	mrs	x23, spsr_el1
 	stp	lr, x21, [sp, #S_LR]
@@ -117,6 +124,12 @@
 	.endm
 
 	.macro	kernel_exit, el
+	.if	\el != 0
+	/* Restore the task's original addr_limit. */
+	ldr	x20, [sp, #S_ORIG_ADDR_LIMIT]
+	str	x20, [tsk, #TI_ADDR_LIMIT]
+	.endif
+
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
 	.if	\el == 0
 	ct_user_enter
@@ -555,7 +568,7 @@ el0_inv:
 	mov	x0, sp
 	mov	x1, #BAD_SYNC
 	mov	x2, x25
-	bl	bad_mode
+	bl	bad_el0_sync
 	b	ret_to_user
 ENDPROC(el0_sync)
 
diff --git a/kernel/arch/arm64/kernel/head.S b/kernel/arch/arm64/kernel/head.S
index b68525792..20ceb5edf 100644
--- a/kernel/arch/arm64/kernel/head.S
+++ b/kernel/arch/arm64/kernel/head.S
@@ -518,8 +518,9 @@ CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
 	b.lt	4f				// Skip if no PMU present
 	mrs	x0, pmcr_el0			// Disable debug access traps
 	ubfx	x0, x0, #11, #5			// to EL2 and allow access to
-	msr	mdcr_el2, x0			// all PMU counters from EL1
 4:
+	csel	x0, xzr, x0, lt			// all PMU counters from EL1
+	msr	mdcr_el2, x0			// (if they exist)
 
 	/* Stage-2 translation */
 	msr	vttbr_el2, xzr
diff --git a/kernel/arch/arm64/kernel/ptrace.c b/kernel/arch/arm64/kernel/ptrace.c
index ff7f13239..55909b220 100644
--- a/kernel/arch/arm64/kernel/ptrace.c
+++ b/kernel/arch/arm64/kernel/ptrace.c
@@ -39,6 +39,7 @@
 #include <linux/elf.h>
 
 #include <asm/compat.h>
+#include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
 #include <asm/pgtable.h>
 #include <asm/syscall.h>
@@ -449,6 +450,8 @@ static int hw_break_set(struct task_struct *target,
 	/* (address, ctrl) registers */
 	limit = regset->n * regset->size;
 	while (count && offset < limit) {
+		if (count < PTRACE_HBP_ADDR_SZ)
+			return -EINVAL;
 		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &addr,
 					 offset, offset + PTRACE_HBP_ADDR_SZ);
 		if (ret)
@@ -458,6 +461,8 @@ static int hw_break_set(struct task_struct *target,
 			return ret;
 		offset += PTRACE_HBP_ADDR_SZ;
 
+		if (!count)
+			break;
 		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl,
 					 offset, offset + PTRACE_HBP_CTRL_SZ);
 		if (ret)
@@ -494,13 +499,13 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	struct user_pt_regs newregs;
+	struct user_pt_regs newregs = task_pt_regs(target)->user_regs;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newregs, 0, -1);
 	if (ret)
 		return ret;
 
-	if (!valid_user_regs(&newregs))
+	if (!valid_user_regs(&newregs, target))
 		return -EINVAL;
 
 	task_pt_regs(target)->user_regs = newregs;
@@ -524,7 +529,8 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	struct user_fpsimd_state newstate;
+	struct user_fpsimd_state newstate =
+		target->thread.fpsimd_state.user_fpsimd;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate, 0, -1);
 	if (ret)
@@ -548,7 +554,7 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	unsigned long tls;
+	unsigned long tls = target->thread.tp_value;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
 	if (ret)
@@ -574,7 +580,8 @@ static int system_call_set(struct task_struct *target,
 			   unsigned int pos, unsigned int count,
 			   const void *kbuf, const void __user *ubuf)
 {
-	int syscallno, ret;
+	int syscallno = task_pt_regs(target)->syscallno;
+	int ret;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &syscallno, 0, -1);
 	if (ret)
@@ -770,7 +777,7 @@ static int compat_gpr_set(struct task_struct *target,
 
 	}
 
-	if (valid_user_regs(&newregs.user_regs))
+	if (valid_user_regs(&newregs.user_regs, target))
 		*task_pt_regs(target) = newregs;
 	else
 		ret = -EINVAL;
@@ -846,7 +853,7 @@ static int compat_tls_set(struct task_struct *target,
 			  const void __user *ubuf)
 {
 	int ret;
-	compat_ulong_t tls;
+	compat_ulong_t tls = target->thread.tp_value;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
 	if (ret)
@@ -1272,3 +1279,79 @@ asmlinkage void syscall_trace_exit(struct pt_regs *regs)
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
 }
+
+/*
+ * Bits which are always architecturally RES0 per ARM DDI 0487A.h
+ * Userspace cannot use these until they have an architectural meaning.
+ * We also reserve IL for the kernel; SS is handled dynamically.
+ */
+#define SPSR_EL1_AARCH64_RES0_BITS \
+	(GENMASK_ULL(63,32) | GENMASK_ULL(27, 22) | GENMASK_ULL(20, 10) | \
+	 GENMASK_ULL(5, 5))
+#define SPSR_EL1_AARCH32_RES0_BITS \
+	(GENMASK_ULL(63,32) | GENMASK_ULL(24, 22) | GENMASK_ULL(20,20))
+
+static int valid_compat_regs(struct user_pt_regs *regs)
+{
+	regs->pstate &= ~SPSR_EL1_AARCH32_RES0_BITS;
+
+	if (!system_supports_mixed_endian_el0()) {
+		if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
+			regs->pstate |= COMPAT_PSR_E_BIT;
+		else
+			regs->pstate &= ~COMPAT_PSR_E_BIT;
+	}
+
+	if (user_mode(regs) && (regs->pstate & PSR_MODE32_BIT) &&
+	    (regs->pstate & COMPAT_PSR_A_BIT) == 0 &&
+	    (regs->pstate & COMPAT_PSR_I_BIT) == 0 &&
+	    (regs->pstate & COMPAT_PSR_F_BIT) == 0) {
+		return 1;
+	}
+
+	/*
+	 * Force PSR to a valid 32-bit EL0t, preserving the same bits as
+	 * arch/arm.
+	 */
+	regs->pstate &= COMPAT_PSR_N_BIT | COMPAT_PSR_Z_BIT |
+			COMPAT_PSR_C_BIT | COMPAT_PSR_V_BIT |
+			COMPAT_PSR_Q_BIT | COMPAT_PSR_IT_MASK |
+			COMPAT_PSR_GE_MASK | COMPAT_PSR_E_BIT |
+			COMPAT_PSR_T_BIT;
+	regs->pstate |= PSR_MODE32_BIT;
+
+	return 0;
+}
+
+static int valid_native_regs(struct user_pt_regs *regs)
+{
+	regs->pstate &= ~SPSR_EL1_AARCH64_RES0_BITS;
+
+	if (user_mode(regs) && !(regs->pstate & PSR_MODE32_BIT) &&
+	    (regs->pstate & PSR_D_BIT) == 0 &&
+	    (regs->pstate & PSR_A_BIT) == 0 &&
+	    (regs->pstate & PSR_I_BIT) == 0 &&
+	    (regs->pstate & PSR_F_BIT) == 0) {
+		return 1;
+	}
+
+	/* Force PSR to a valid 64-bit EL0t */
+	regs->pstate &= PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT;
+
+	return 0;
+}
+
+/*
+ * Are the current registers suitable for user mode? (used to maintain
+ * security in signal handlers)
+ */
+int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task)
+{
+	if (!test_tsk_thread_flag(task, TIF_SINGLESTEP))
+		regs->pstate &= ~DBG_SPSR_SS;
+
+	if (is_compat_thread(task_thread_info(task)))
+		return valid_compat_regs(regs);
+	else
+		return valid_native_regs(regs);
+}
diff --git a/kernel/arch/arm64/kernel/signal.c b/kernel/arch/arm64/kernel/signal.c
index e18c48cb6..a8eafdbc7 100644
--- a/kernel/arch/arm64/kernel/signal.c
+++ b/kernel/arch/arm64/kernel/signal.c
@@ -115,7 +115,7 @@ static int restore_sigframe(struct pt_regs *regs,
 	 */
 	regs->syscallno = ~0UL;
 
-	err |= !valid_user_regs(&regs->user_regs);
+	err |= !valid_user_regs(&regs->user_regs, current);
 
 	if (err == 0) {
 		struct fpsimd_context *fpsimd_ctx =
@@ -307,7 +307,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	/*
 	 * Check that the resulting registers are actually sane.
 	 */
-	ret |= !valid_user_regs(&regs->user_regs);
+	ret |= !valid_user_regs(&regs->user_regs, current);
 
 	/*
 	 * Fast forward the stepping logic so we step into the signal
diff --git a/kernel/arch/arm64/kernel/signal32.c b/kernel/arch/arm64/kernel/signal32.c
index 71ef6dc89..107335637 100644
--- a/kernel/arch/arm64/kernel/signal32.c
+++ b/kernel/arch/arm64/kernel/signal32.c
@@ -356,7 +356,7 @@ static int compat_restore_sigframe(struct pt_regs *regs,
 	 */
 	regs->syscallno = ~0UL;
 
-	err |= !valid_user_regs(&regs->user_regs);
+	err |= !valid_user_regs(&regs->user_regs, current);
 
 	aux = (struct compat_aux_sigframe __user *) sf->uc.uc_regspace;
 	if (err == 0)
diff --git a/kernel/arch/arm64/kernel/smp.c b/kernel/arch/arm64/kernel/smp.c
index b1adc51b2..f3c3d8fee 100644
--- a/kernel/arch/arm64/kernel/smp.c
+++ b/kernel/arch/arm64/kernel/smp.c
@@ -188,7 +188,6 @@ asmlinkage void secondary_start_kernel(void)
 	set_cpu_online(cpu, true);
 	complete(&cpu_running);
 
-	local_dbg_enable();
 	local_irq_enable();
 	local_async_enable();
 
@@ -334,8 +333,8 @@ void __init smp_cpus_done(unsigned int max_cpus)
 
 void __init smp_prepare_boot_cpu(void)
 {
-	cpuinfo_store_boot_cpu();
 	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
+	cpuinfo_store_boot_cpu();
 }
 
 static u64 __init of_get_cpu_mpidr(struct device_node *dn)
diff --git a/kernel/arch/arm64/kernel/suspend.c b/kernel/arch/arm64/kernel/suspend.c
index 1095aa483..00c1372bf 100644
--- a/kernel/arch/arm64/kernel/suspend.c
+++ b/kernel/arch/arm64/kernel/suspend.c
@@ -1,7 +1,9 @@
 #include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/slab.h>
+#include <asm/alternative.h>
 #include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
 #include <asm/pgtable.h>
 #include <asm/memory.h>
@@ -111,6 +113,13 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 		set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
 
 		/*
+		 * PSTATE was not saved over suspend/resume, re-enable any
+		 * detected features that might not have been set correctly.
+		 */
+		asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,
+				CONFIG_ARM64_PAN));
+
+		/*
 		 * Restore HW breakpoint registers to sane values
 		 * before debug exceptions are possibly reenabled
 		 * through local_dbg_restore.
diff --git a/kernel/arch/arm64/kernel/traps.c b/kernel/arch/arm64/kernel/traps.c
index e9b9b5364..ca7f0ac5f 100644
--- a/kernel/arch/arm64/kernel/traps.c
+++ b/kernel/arch/arm64/kernel/traps.c
@@ -434,16 +434,33 @@ const char *esr_get_class_string(u32 esr)
 }
 
 /*
- * bad_mode handles the impossible case in the exception vector.
+ * bad_mode handles the impossible case in the exception vector. This is always
+ * fatal.
  */
 asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 {
-	siginfo_t info;
-	void __user *pc = (void __user *)instruction_pointer(regs);
 	console_verbose();
 
 	pr_crit("Bad mode in %s handler detected, code 0x%08x -- %s\n",
 		handler[reason], esr, esr_get_class_string(esr));
+
+	die("Oops - bad mode", regs, 0);
+	local_irq_disable();
+	panic("bad mode");
+}
+
+/*
+ * bad_el0_sync handles unexpected, but potentially recoverable synchronous
+ * exceptions taken from EL0. Unlike bad_mode, this returns.
+ */
+asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
+{
+	siginfo_t info;
+	void __user *pc = (void __user *)instruction_pointer(regs);
+	console_verbose();
+
+	pr_crit("Bad EL0 synchronous exception detected on CPU%d, code 0x%08x -- %s\n",
+		smp_processor_id(), esr, esr_get_class_string(esr));
 	__show_regs(regs);
 
 	info.si_signo = SIGILL;
@@ -451,7 +468,10 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 	info.si_code  = ILL_ILLOPC;
 	info.si_addr  = pc;
 
-	arm64_notify_die("Oops - bad mode", regs, &info, 0);
+	current->thread.fault_address = 0;
+	current->thread.fault_code = 0;
+
+	force_sig_info(info.si_signo, &info, current);
 }
 
 void __pte_error(const char *file, int line, unsigned long val)
diff --git a/kernel/arch/arm64/kvm/hyp-init.S b/kernel/arch/arm64/kvm/hyp-init.S
index 178ba2248..84c338f01 100644
--- a/kernel/arch/arm64/kvm/hyp-init.S
+++ b/kernel/arch/arm64/kvm/hyp-init.S
@@ -64,7 +64,7 @@ __do_hyp_init:
 	mrs	x4, tcr_el1
 	ldr	x5, =TCR_EL2_MASK
 	and	x4, x4, x5
-	ldr	x5, =TCR_EL2_FLAGS
+	mov	x5, #TCR_EL2_RES1
 	orr	x4, x4, x5
 
 #ifndef CONFIG_ARM64_VA_BITS_48
@@ -85,15 +85,18 @@ __do_hyp_init:
 	ldr_l	x5, idmap_t0sz
 	bfi	x4, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
 #endif
-	msr	tcr_el2, x4
-
-	ldr	x4, =VTCR_EL2_FLAGS
 	/*
 	 * Read the PARange bits from ID_AA64MMFR0_EL1 and set the PS bits in
-	 * VTCR_EL2.
+	 * TCR_EL2 and VTCR_EL2.
 	 */
 	mrs	x5, ID_AA64MMFR0_EL1
 	bfi	x4, x5, #16, #3
+
+	msr	tcr_el2, x4
+
+	ldr	x4, =VTCR_EL2_FLAGS
+	bfi	x4, x5, #16, #3
+
 	msr	vtcr_el2, x4
 
 	mrs	x4, mair_el1
diff --git a/kernel/arch/arm64/kvm/inject_fault.c b/kernel/arch/arm64/kvm/inject_fault.c
index 648112e90..3972e65fb 100644
--- a/kernel/arch/arm64/kvm/inject_fault.c
+++ b/kernel/arch/arm64/kvm/inject_fault.c
@@ -130,7 +130,7 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr
 		esr |= (ESR_ELx_EC_IABT_CUR << ESR_ELx_EC_SHIFT);
 
 	if (!is_iabt)
-		esr |= ESR_ELx_EC_DABT_LOW;
+		esr |= ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT;
 
 	vcpu_sys_reg(vcpu, ESR_EL1) = esr | ESR_ELx_FSC_EXTABT;
 }
diff --git a/kernel/arch/arm64/mm/fault.c b/kernel/arch/arm64/mm/fault.c
index 92ddac1e8..247bae758 100644
--- a/kernel/arch/arm64/mm/fault.c
+++ b/kernel/arch/arm64/mm/fault.c
@@ -29,7 +29,9 @@
 #include <linux/sched.h>
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
+#include <linux/preempt.h>
 
+#include <asm/bug.h>
 #include <asm/cpufeature.h>
 #include <asm/exception.h>
 #include <asm/debug-monitors.h>
@@ -81,6 +83,56 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
 	printk("\n");
 }
 
+#ifdef CONFIG_ARM64_HW_AFDBM
+/*
+ * This function sets the access flags (dirty, accessed), as well as write
+ * permission, and only to a more permissive setting.
+ *
+ * It needs to cope with hardware update of the accessed/dirty state by other
+ * agents in the system and can safely skip the __sync_icache_dcache() call as,
+ * like set_pte_at(), the PTE is never changed from no-exec to exec here.
+ *
+ * Returns whether or not the PTE actually changed.
+ */
+int ptep_set_access_flags(struct vm_area_struct *vma,
+			  unsigned long address, pte_t *ptep,
+			  pte_t entry, int dirty)
+{
+	pteval_t old_pteval;
+	unsigned int tmp;
+
+	if (pte_same(*ptep, entry))
+		return 0;
+
+	/* only preserve the access flags and write permission */
+	pte_val(entry) &= PTE_AF | PTE_WRITE | PTE_DIRTY;
+
+	/*
+	 * PTE_RDONLY is cleared by default in the asm below, so set it in
+	 * back if necessary (read-only or clean PTE).
+	 */
+	if (!pte_write(entry) || !pte_sw_dirty(entry))
+		pte_val(entry) |= PTE_RDONLY;
+
+	/*
+	 * Setting the flags must be done atomically to avoid racing with the
+	 * hardware update of the access/dirty state.
+	 */
+	asm volatile("//	ptep_set_access_flags\n"
+	"	prfm	pstl1strm, %2\n"
+	"1:	ldxr	%0, %2\n"
+	"	and	%0, %0, %3		// clear PTE_RDONLY\n"
+	"	orr	%0, %0, %4		// set flags\n"
+	"	stxr	%w1, %0, %2\n"
+	"	cbnz	%w1, 1b\n"
+	: "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
+	: "L" (~PTE_RDONLY), "r" (pte_val(entry)));
+
+	flush_tlb_fix_spurious_fault(vma, address);
+	return 1;
+}
+#endif
+
 /*
  * The kernel tried to access some page that wasn't present.
  */
@@ -556,8 +608,16 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
 }
 
 #ifdef CONFIG_ARM64_PAN
-void cpu_enable_pan(void *__unused)
+int cpu_enable_pan(void *__unused)
 {
+	/*
+	 * We modify PSTATE. This won't work from irq context as the PSTATE
+	 * is discarded once we return from the exception.
+	 */
+	WARN_ON_ONCE(in_interrupt());
+
 	config_sctlr_el1(SCTLR_EL1_SPAN, 0);
+	asm(SET_PSTATE_PAN(1));
+	return 0;
 }
 #endif /* CONFIG_ARM64_PAN */
diff --git a/kernel/arch/arm64/mm/mmu.c b/kernel/arch/arm64/mm/mmu.c
index 116ad654d..653735a8c 100644
--- a/kernel/arch/arm64/mm/mmu.c
+++ b/kernel/arch/arm64/mm/mmu.c
@@ -652,9 +652,9 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys)
 	/*
 	 * Check whether the physical FDT address is set and meets the minimum
 	 * alignment requirement. Since we are relying on MIN_FDT_ALIGN to be
-	 * at least 8 bytes so that we can always access the size field of the
-	 * FDT header after mapping the first chunk, double check here if that
-	 * is indeed the case.
+	 * at least 8 bytes so that we can always access the magic and size
+	 * fields of the FDT header after mapping the first chunk, double check
+	 * here if that is indeed the case.
 	 */
 	BUILD_BUG_ON(MIN_FDT_ALIGN < 8);
 	if (!dt_phys || dt_phys % MIN_FDT_ALIGN)
@@ -682,7 +682,7 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys)
 	create_mapping(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base,
 		       SWAPPER_BLOCK_SIZE, prot);
 
-	if (fdt_check_header(dt_virt) != 0)
+	if (fdt_magic(dt_virt) != FDT_MAGIC)
 		return NULL;
 
 	size = fdt_totalsize(dt_virt);
diff --git a/kernel/arch/arm64/mm/proc.S b/kernel/arch/arm64/mm/proc.S
index b8f04b3f2..18201e9e8 100644
--- a/kernel/arch/arm64/mm/proc.S
+++ b/kernel/arch/arm64/mm/proc.S
@@ -25,6 +25,8 @@
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative.h>
 
 #include "proc-macros.S"
 
@@ -137,7 +139,17 @@ ENTRY(cpu_do_switch_mm)
 	bfi	x0, x1, #48, #16		// set the ASID
 	msr	ttbr0_el1, x0			// set TTBR0
 	isb
+alternative_if_not ARM64_WORKAROUND_CAVIUM_27456
 	ret
+	nop
+	nop
+	nop
+alternative_else
+	ic	iallu
+	dsb	nsh
+	isb
+	ret
+alternative_endif
 ENDPROC(cpu_do_switch_mm)
 
 	.section ".text.init", #alloc, #execinstr
@@ -156,6 +168,8 @@ ENTRY(__cpu_setup)
 	msr	cpacr_el1, x0			// Enable FP/ASIMD
 	mov	x0, #1 << 12			// Reset mdscr_el1 and disable
 	msr	mdscr_el1, x0			// access to the DCC from EL0
+	isb					// Unmask debug exceptions now,
+	enable_dbg				// since this is per-cpu
 	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
 	/*
 	 * Memory region attributes for LPAE: