Merge tag 'v4.9.144' into 4.9-2.3.x-imx

This is the 4.9.144 stable release

13 files changed, 88 insertions, 28 deletions

diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 92110c2c6c59..ee94597773fa 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -10,7 +10,7 @@
 #
 # Copyright (C) 1995-2001 by Russell King
 
-LDFLAGS_vmlinux	:=-p --no-undefined -X
+LDFLAGS_vmlinux	:=--no-undefined -X
 CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET)
 GZFLAGS		:=-9
 
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
index c2b9bcb0ef61..e79f3defe002 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
@@ -249,7 +249,7 @@
 
 		sysmgr: sysmgr@ffd12000 {
 			compatible = "altr,sys-mgr", "syscon";
-			reg = <0xffd12000 0x1000>;
+			reg = <0xffd12000 0x228>;
 		};
 
 		/* Local timer */
diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
index c98e7e849f06..8550408735a0 100644
--- a/arch/arm64/crypto/sha1-ce-core.S
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -82,7 +82,8 @@ ENTRY(sha1_ce_transform)
 	ldr		dgb, [x0, #16]
 
 	/* load sha1_ce_state::finalize */
-	ldr		w4, [x0, #:lo12:sha1_ce_offsetof_finalize]
+	ldr_l		w4, sha1_ce_offsetof_finalize, x4
+	ldr		w4, [x0, x4]
 
 	/* load input */
 0:	ld1		{v8.4s-v11.4s}, [x1], #64
@@ -132,7 +133,8 @@ CPU_LE(	rev32		v11.16b, v11.16b	)
 	 * the padding is handled by the C code in that case.
 	 */
 	cbz		x4, 3f
-	ldr		x4, [x0, #:lo12:sha1_ce_offsetof_count]
+	ldr_l		w4, sha1_ce_offsetof_count, x4
+	ldr		x4, [x0, x4]
 	movi		v9.2d, #0
 	mov		x8, #0x80000000
 	movi		v10.2d, #0
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
index aefda9868627..ea319c055f5d 100644
--- a/arch/arm64/crypto/sha1-ce-glue.c
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -17,9 +17,6 @@
 #include <linux/crypto.h>
 #include <linux/module.h>
 
-#define ASM_EXPORT(sym, val) \
-	asm(".globl " #sym "; .set " #sym ", %0" :: "I"(val));
-
 MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_LICENSE("GPL v2");
@@ -32,6 +29,9 @@ struct sha1_ce_state {
 asmlinkage void sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src,
 				  int blocks);
 
+const u32 sha1_ce_offsetof_count = offsetof(struct sha1_ce_state, sst.count);
+const u32 sha1_ce_offsetof_finalize = offsetof(struct sha1_ce_state, finalize);
+
 static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
 			  unsigned int len)
 {
@@ -52,11 +52,6 @@ static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
 	struct sha1_ce_state *sctx = shash_desc_ctx(desc);
 	bool finalize = !sctx->sst.count && !(len % SHA1_BLOCK_SIZE);
 
-	ASM_EXPORT(sha1_ce_offsetof_count,
-		   offsetof(struct sha1_ce_state, sst.count));
-	ASM_EXPORT(sha1_ce_offsetof_finalize,
-		   offsetof(struct sha1_ce_state, finalize));
-
 	/*
 	 * Allow the asm code to perform the finalization if there is no
 	 * partial data and the input is a round multiple of the block size.
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
index 01cfee066837..679c6c002f4f 100644
--- a/arch/arm64/crypto/sha2-ce-core.S
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -88,7 +88,8 @@ ENTRY(sha2_ce_transform)
 	ld1		{dgav.4s, dgbv.4s}, [x0]
 
 	/* load sha256_ce_state::finalize */
-	ldr		w4, [x0, #:lo12:sha256_ce_offsetof_finalize]
+	ldr_l		w4, sha256_ce_offsetof_finalize, x4
+	ldr		w4, [x0, x4]
 
 	/* load input */
 0:	ld1		{v16.4s-v19.4s}, [x1], #64
@@ -136,7 +137,8 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
 	 * the padding is handled by the C code in that case.
 	 */
 	cbz		x4, 3f
-	ldr		x4, [x0, #:lo12:sha256_ce_offsetof_count]
+	ldr_l		w4, sha256_ce_offsetof_count, x4
+	ldr		x4, [x0, x4]
 	movi		v17.2d, #0
 	mov		x8, #0x80000000
 	movi		v18.2d, #0
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
index 7cd587564a41..0ed9486f75dd 100644
--- a/arch/arm64/crypto/sha2-ce-glue.c
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -17,9 +17,6 @@
 #include <linux/crypto.h>
 #include <linux/module.h>
 
-#define ASM_EXPORT(sym, val) \
-	asm(".globl " #sym "; .set " #sym ", %0" :: "I"(val));
-
 MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
 MODULE_LICENSE("GPL v2");
@@ -32,6 +29,11 @@ struct sha256_ce_state {
 asmlinkage void sha2_ce_transform(struct sha256_ce_state *sst, u8 const *src,
 				  int blocks);
 
+const u32 sha256_ce_offsetof_count = offsetof(struct sha256_ce_state,
+					      sst.count);
+const u32 sha256_ce_offsetof_finalize = offsetof(struct sha256_ce_state,
+						 finalize);
+
 static int sha256_ce_update(struct shash_desc *desc, const u8 *data,
 			    unsigned int len)
 {
@@ -52,11 +54,6 @@ static int sha256_ce_finup(struct shash_desc *desc, const u8 *data,
 	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
 	bool finalize = !sctx->sst.count && !(len % SHA256_BLOCK_SIZE);
 
-	ASM_EXPORT(sha256_ce_offsetof_count,
-		   offsetof(struct sha256_ce_state, sst.count));
-	ASM_EXPORT(sha256_ce_offsetof_finalize,
-		   offsetof(struct sha256_ce_state, finalize));
-
 	/*
 	 * Allow the asm code to perform the finalization if there is no
 	 * partial data and the input is a round multiple of the block size.
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index a9e54aad15ef..65615820155e 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -54,6 +54,9 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md);
 #define alloc_screen_info(x...)		&screen_info
 #define free_screen_info(x...)
 
+/* redeclare as 'hidden' so the compiler will generate relative references */
+extern struct screen_info screen_info __attribute__((__visibility__("hidden")));
+
 static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt)
 {
 }
diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
index 1b5e0e843c3a..7e2b3e360086 100644
--- a/arch/arm64/include/asm/jump_label.h
+++ b/arch/arm64/include/asm/jump_label.h
@@ -28,7 +28,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm goto("1: nop\n\t"
+	asm_volatile_goto("1: nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".align 3\n\t"
 		 ".quad 1b, %l[l_yes], %c0\n\t"
@@ -42,7 +42,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm goto("1: b %l[l_yes]\n\t"
+	asm_volatile_goto("1: b %l[l_yes]\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".align 3\n\t"
 		 ".quad 1b, %l[l_yes], %c0\n\t"
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index fe39e6841326..ba0d52c22b50 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -42,6 +42,11 @@ void kvm_inject_vabt(struct kvm_vcpu *vcpu);
 void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
 void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
 
+static inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
+{
+	return !(vcpu->arch.hcr_el2 & HCR_RW);
+}
+
 static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 0d551576eb57..4724b8f0b625 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -92,6 +92,7 @@ static inline unsigned long __percpu_##op(void *ptr,			\
 		: [val] "Ir" (val));					\
 		break;							\
 	default:							\
+		ret = 0;						\
 		BUILD_BUG();						\
 	}								\
 									\
@@ -121,6 +122,7 @@ static inline unsigned long __percpu_read(void *ptr, int size)
 		ret = ACCESS_ONCE(*(u64 *)ptr);
 		break;
 	default:
+		ret = 0;
 		BUILD_BUG();
 	}
 
@@ -190,6 +192,7 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
 		: [val] "r" (val));
 		break;
 	default:
+		ret = 0;
 		BUILD_BUG();
 	}
 
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 1d047d6c421b..f5cd96c60eb9 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -198,7 +198,7 @@ do {									\
 			       (err), ARM64_HAS_UAO);			\
 		break;							\
 	case 8:								\
-		__get_user_asm("ldr", "ldtr", "%",  __gu_val, (ptr),	\
+		__get_user_asm("ldr", "ldtr", "%x",  __gu_val, (ptr),	\
 			       (err), ARM64_HAS_UAO);			\
 		break;							\
 	default:							\
@@ -272,7 +272,7 @@ do {									\
 			       (err), ARM64_HAS_UAO);			\
 		break;							\
 	case 8:								\
-		__put_user_asm("str", "sttr", "%", __pu_val, (ptr),	\
+		__put_user_asm("str", "sttr", "%x", __pu_val, (ptr),	\
 			       (err), ARM64_HAS_UAO);			\
 		break;							\
 	default:							\
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index d3e0a2ffb383..e41a7b4f3a9b 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -57,6 +57,45 @@ static u64 core_reg_offset_from_id(u64 id)
 	return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE);
 }
 
+static int validate_core_offset(const struct kvm_one_reg *reg)
+{
+	u64 off = core_reg_offset_from_id(reg->id);
+	int size;
+
+	switch (off) {
+	case KVM_REG_ARM_CORE_REG(regs.regs[0]) ...
+	     KVM_REG_ARM_CORE_REG(regs.regs[30]):
+	case KVM_REG_ARM_CORE_REG(regs.sp):
+	case KVM_REG_ARM_CORE_REG(regs.pc):
+	case KVM_REG_ARM_CORE_REG(regs.pstate):
+	case KVM_REG_ARM_CORE_REG(sp_el1):
+	case KVM_REG_ARM_CORE_REG(elr_el1):
+	case KVM_REG_ARM_CORE_REG(spsr[0]) ...
+	     KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]):
+		size = sizeof(__u64);
+		break;
+
+	case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
+	     KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
+		size = sizeof(__uint128_t);
+		break;
+
+	case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
+	case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
+		size = sizeof(__u32);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (KVM_REG_SIZE(reg->id) == size &&
+	    IS_ALIGNED(off, size / sizeof(__u32)))
+		return 0;
+
+	return -EINVAL;
+}
+
 static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	/*
@@ -76,6 +115,9 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	    (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
 		return -ENOENT;
 
+	if (validate_core_offset(reg))
+		return -EINVAL;
+
 	if (copy_to_user(uaddr, ((u32 *)regs) + off, KVM_REG_SIZE(reg->id)))
 		return -EFAULT;
 
@@ -98,6 +140,9 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	    (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
 		return -ENOENT;
 
+	if (validate_core_offset(reg))
+		return -EINVAL;
+
 	if (KVM_REG_SIZE(reg->id) > sizeof(tmp))
 		return -EINVAL;
 
@@ -107,17 +152,25 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	}
 
 	if (off == KVM_REG_ARM_CORE_REG(regs.pstate)) {
-		u32 mode = (*(u32 *)valp) & COMPAT_PSR_MODE_MASK;
+		u64 mode = (*(u64 *)valp) & COMPAT_PSR_MODE_MASK;
 		switch (mode) {
 		case COMPAT_PSR_MODE_USR:
+			if (!system_supports_32bit_el0())
+				return -EINVAL;
+			break;
 		case COMPAT_PSR_MODE_FIQ:
 		case COMPAT_PSR_MODE_IRQ:
 		case COMPAT_PSR_MODE_SVC:
 		case COMPAT_PSR_MODE_ABT:
 		case COMPAT_PSR_MODE_UND:
+			if (!vcpu_el1_is_32bit(vcpu))
+				return -EINVAL;
+			break;
 		case PSR_MODE_EL0t:
 		case PSR_MODE_EL1t:
 		case PSR_MODE_EL1h:
+			if (vcpu_el1_is_32bit(vcpu))
+				return -EINVAL;
 			break;
 		default:
 			err = -EINVAL;
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index c86b7909ef31..2f7c60c8e588 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -11,7 +11,7 @@ lib-y		:= bitops.o clear_user.o delay.o copy_from_user.o	\
 # when supported by the CPU. Result and argument registers are handled
 # correctly, based on the function prototype.
 lib-$(CONFIG_ARM64_LSE_ATOMICS) += atomic_ll_sc.o
-CFLAGS_atomic_ll_sc.o	:= -fcall-used-x0 -ffixed-x1 -ffixed-x2		\
+CFLAGS_atomic_ll_sc.o	:= -ffixed-x1 -ffixed-x2        		\
 		   -ffixed-x3 -ffixed-x4 -ffixed-x5 -ffixed-x6		\
 		   -ffixed-x7 -fcall-saved-x8 -fcall-saved-x9		\
 		   -fcall-saved-x10 -fcall-saved-x11 -fcall-saved-x12	\