8 files changed, 36 insertions, 15 deletions
diff --git a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
index 5b4a9609e31f..2468762283a5 100644
--- a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
+++ b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
@@ -351,7 +351,7 @@
 		reg = <0>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&cp0_copper_eth_phy_reset>;
-		reset-gpios = <&cp1_gpio1 11 GPIO_ACTIVE_LOW>;
+		reset-gpios = <&cp0_gpio2 11 GPIO_ACTIVE_LOW>;
 		reset-assert-us = <10000>;
 	};
 
diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi
index 8d41b69ec2da..99bccaac31ad 100644
--- a/arch/arm64/boot/dts/qcom/msm8998.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi
@@ -37,7 +37,7 @@
 		};
 
 		memory@86200000 {
-			reg = <0x0 0x86200000 0x0 0x2600000>;
+			reg = <0x0 0x86200000 0x0 0x2d00000>;
 			no-map;
 		};
 
diff --git a/arch/arm64/crypto/chacha-neon-core.S b/arch/arm64/crypto/chacha-neon-core.S
index 021bb9e9784b..706c4e10e9e2 100644
--- a/arch/arm64/crypto/chacha-neon-core.S
+++ b/arch/arm64/crypto/chacha-neon-core.S
@@ -158,8 +158,8 @@ ENTRY(hchacha_block_neon)
 	mov		w3, w2
 	bl		chacha_permute
 
-	st1		{v0.16b}, [x1], #16
-	st1		{v3.16b}, [x1]
+	st1		{v0.4s}, [x1], #16
+	st1		{v3.4s}, [x1]
 
 	ldp		x29, x30, [sp], #16
 	ret
@@ -532,6 +532,10 @@ ENTRY(chacha_4block_xor_neon)
 	add		v3.4s, v3.4s, v19.4s
 	  add		a2, a2, w8
 	  add		a3, a3, w9
+CPU_BE(	  rev		a0, a0		)
+CPU_BE(	  rev		a1, a1		)
+CPU_BE(	  rev		a2, a2		)
+CPU_BE(	  rev		a3, a3		)
 
 	ld4r		{v24.4s-v27.4s}, [x0], #16
 	ld4r		{v28.4s-v31.4s}, [x0]
@@ -552,6 +556,10 @@ ENTRY(chacha_4block_xor_neon)
 	add		v7.4s, v7.4s, v23.4s
 	  add		a6, a6, w8
 	  add		a7, a7, w9
+CPU_BE(	  rev		a4, a4		)
+CPU_BE(	  rev		a5, a5		)
+CPU_BE(	  rev		a6, a6		)
+CPU_BE(	  rev		a7, a7		)
 
 	// x8[0-3] += s2[0]
 	// x9[0-3] += s2[1]
@@ -569,6 +577,10 @@ ENTRY(chacha_4block_xor_neon)
 	add		v11.4s, v11.4s, v27.4s
 	  add		a10, a10, w8
 	  add		a11, a11, w9
+CPU_BE(	  rev		a8, a8		)
+CPU_BE(	  rev		a9, a9		)
+CPU_BE(	  rev		a10, a10	)
+CPU_BE(	  rev		a11, a11	)
 
 	// x12[0-3] += s3[0]
 	// x13[0-3] += s3[1]
@@ -586,6 +598,10 @@ ENTRY(chacha_4block_xor_neon)
 	add		v15.4s, v15.4s, v31.4s
 	  add		a14, a14, w8
 	  add		a15, a15, w9
+CPU_BE(	  rev		a12, a12	)
+CPU_BE(	  rev		a13, a13	)
+CPU_BE(	  rev		a14, a14	)
+CPU_BE(	  rev		a15, a15	)
 
 	// interleave 32-bit words in state n, n+1
 	  ldp		w6, w7, [x2], #64
diff --git a/arch/arm64/include/asm/neon-intrinsics.h b/arch/arm64/include/asm/neon-intrinsics.h
index 2ba6c6b9541f..71abfc7612b2 100644
--- a/arch/arm64/include/asm/neon-intrinsics.h
+++ b/arch/arm64/include/asm/neon-intrinsics.h
@@ -36,4 +36,8 @@
 #include <arm_neon.h>
 #endif
 
+#ifdef CONFIG_CC_IS_CLANG
+#pragma clang diagnostic ignored "-Wincompatible-pointer-types"
+#endif
+
 #endif /* __ASM_NEON_INTRINSICS_H */
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 15d79a8e5e5e..eecf7927dab0 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -539,8 +539,7 @@ set_hcr:
 	/* GICv3 system register access */
 	mrs	x0, id_aa64pfr0_el1
 	ubfx	x0, x0, #24, #4
-	cmp	x0, #1
-	b.ne	3f
+	cbz	x0, 3f
 
 	mrs_s	x0, SYS_ICC_SRE_EL2
 	orr	x0, x0, #ICC_SRE_EL2_SRE	// Set ICC_SRE_EL2.SRE==1
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 9dce33b0e260..ddaea0fd2fa4 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1702,19 +1702,20 @@ void syscall_trace_exit(struct pt_regs *regs)
 }
 
 /*
- * SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487C.a
- * We also take into account DIT (bit 24), which is not yet documented, and
- * treat PAN and UAO as RES0 bits, as they are meaningless at EL0, and may be
- * allocated an EL0 meaning in future.
+ * SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487D.a.
+ * We permit userspace to set SSBS (AArch64 bit 12, AArch32 bit 23) which is
+ * not described in ARM DDI 0487D.a.
+ * We treat PAN and UAO as RES0 bits, as they are meaningless at EL0, and may
+ * be allocated an EL0 meaning in future.
  * Userspace cannot use these until they have an architectural meaning.
  * Note that this follows the SPSR_ELx format, not the AArch32 PSR format.
  * We also reserve IL for the kernel; SS is handled dynamically.
  */
 #define SPSR_EL1_AARCH64_RES0_BITS \
-	(GENMASK_ULL(63,32) | GENMASK_ULL(27, 25) | GENMASK_ULL(23, 22) | \
-	 GENMASK_ULL(20, 10) | GENMASK_ULL(5, 5))
+	(GENMASK_ULL(63, 32) | GENMASK_ULL(27, 25) | GENMASK_ULL(23, 22) | \
+	 GENMASK_ULL(20, 13) | GENMASK_ULL(11, 10) | GENMASK_ULL(5, 5))
 #define SPSR_EL1_AARCH32_RES0_BITS \
-	(GENMASK_ULL(63,32) | GENMASK_ULL(23, 22) | GENMASK_ULL(20,20))
+	(GENMASK_ULL(63, 32) | GENMASK_ULL(22, 22) | GENMASK_ULL(20, 20))
 
 static int valid_compat_regs(struct user_pt_regs *regs)
 {
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index d09ec76f08cf..009849328289 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -339,6 +339,9 @@ void __init setup_arch(char **cmdline_p)
 	smp_init_cpus();
 	smp_build_mpidr_hash();
 
+	/* Init percpu seeds for random tags after cpus are set up. */
+	kasan_init_tags();
+
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 	/*
 	 * Make sure init_thread_info.ttbr0 always generates translation
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index 4b55b15707a3..f37a86d2a69d 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -252,8 +252,6 @@ void __init kasan_init(void)
 	memset(kasan_early_shadow_page, KASAN_SHADOW_INIT, PAGE_SIZE);
 	cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
 
-	kasan_init_tags();
-
 	/* At this point kasan is fully initialized. Enable error messages */
 	init_task.kasan_depth = 0;
 	pr_info("KernelAddressSanitizer initialized\n");