Merge branch 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm

Pull ARM updates from Russell King:

 - Initial round of Spectre variant 1 and variant 2 fixes for 32-bit ARM

 - Clang support improvements

 - nommu updates for v8 MPU

 - enable ARM_MODULE_PLTS by default to avoid problems loading modules
   with larger kernels

 - vmlinux.lds and dma-mapping cleanups

* 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm: (31 commits)
  ARM: spectre-v1: fix syscall entry
  ARM: spectre-v1: add array_index_mask_nospec() implementation
  ARM: spectre-v1: add speculation barrier (csdb) macros
  ARM: KVM: report support for SMCCC_ARCH_WORKAROUND_1
  ARM: KVM: Add SMCCC_ARCH_WORKAROUND_1 fast handling
  ARM: spectre-v2: KVM: invalidate icache on guest exit for Brahma B15
  ARM: KVM: invalidate icache on guest exit for Cortex-A15
  ARM: KVM: invalidate BTB on guest exit for Cortex-A12/A17
  ARM: spectre-v2: warn about incorrect context switching functions
  ARM: spectre-v2: add firmware based hardening
  ARM: spectre-v2: harden user aborts in kernel space
  ARM: spectre-v2: add Cortex A8 and A15 validation of the IBE bit
  ARM: spectre-v2: harden branch predictor on context switches
  ARM: spectre: add Kconfig symbol for CPUs vulnerable to Spectre
  ARM: bugs: add support for per-processor bug checking
  ARM: bugs: hook processor bug checking into SMP and suspend paths
  ARM: bugs: prepare processor bug infrastructure
  ARM: add more CPU part numbers for Cortex and Brahma B15 CPUs
  ARM: 8774/1: remove no-op macro VMLINUX_SYMBOL()
  ARM: 8773/1: amba: Export amba_bustype
  ...

40 files changed, 1317 insertions, 210 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index c43f5bb55ac8..8f460bdd4be1 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1698,6 +1698,7 @@ config ARCH_WANT_GENERAL_HUGETLB
 config ARM_MODULE_PLTS
 	bool "Use PLTs to allow module memory to spill over into vmalloc area"
 	depends on MODULES
+	default y
 	help
 	  Allocate PLTs when loading modules so that jumps and calls whose
 	  targets are too far away for their relative offsets to be encoded
@@ -1708,7 +1709,8 @@ config ARM_MODULE_PLTS
 	  rounding up to page size, the actual memory footprint is usually
 	  the same.
 
-	  Say y if you are getting out of memory errors while loading modules
+	  Disabling this is usually safe for small single-platform
+	  configurations. If unsure, say y.
 
 source "mm/Kconfig"
 
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index f32a5468d79f..1dc4045e1af6 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -106,7 +106,7 @@ tune-$(CONFIG_CPU_V6K)		=$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm)
 tune-y := $(tune-y)
 
 ifeq ($(CONFIG_AEABI),y)
-CFLAGS_ABI	:=-mabi=aapcs-linux -mno-thumb-interwork -mfpu=vfp
+CFLAGS_ABI	:=-mabi=aapcs-linux -mfpu=vfp
 else
 CFLAGS_ABI	:=$(call cc-option,-mapcs-32,-mabi=apcs-gnu) $(call cc-option,-mno-thumb-interwork,)
 endif
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 6a4e7341ecd3..a3c5fbcad4ab 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -113,7 +113,7 @@ CFLAGS_fdt_ro.o := $(nossp_flags)
 CFLAGS_fdt_rw.o := $(nossp_flags)
 CFLAGS_fdt_wip.o := $(nossp_flags)
 
-ccflags-y := -fpic -mno-single-pic-base -fno-builtin -I$(obj)
+ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin -I$(obj)
 asflags-y := -DZIMAGE
 
 # Supply kernel BSS size to the decompressor via a linker symbol.
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 9342904cccca..0cd4dccbae78 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -447,6 +447,14 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.size \name , . - \name
 	.endm
 
+	.macro	csdb
+#ifdef CONFIG_THUMB2_KERNEL
+	.inst.w	0xf3af8014
+#else
+	.inst	0xe320f014
+#endif
+	.endm
+
 	.macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req
 #ifndef CONFIG_CPU_USE_DOMAINS
 	adds	\tmp, \addr, #\size - 1
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index 40f5c410fd8c..69772e742a0a 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -17,6 +17,12 @@
 #define isb(option) __asm__ __volatile__ ("isb " #option : : : "memory")
 #define dsb(option) __asm__ __volatile__ ("dsb " #option : : : "memory")
 #define dmb(option) __asm__ __volatile__ ("dmb " #option : : : "memory")
+#ifdef CONFIG_THUMB2_KERNEL
+#define CSDB	".inst.w 0xf3af8014"
+#else
+#define CSDB	".inst	0xe320f014"
+#endif
+#define csdb() __asm__ __volatile__(CSDB : : : "memory")
 #elif defined(CONFIG_CPU_XSC3) || __LINUX_ARM_ARCH__ == 6
 #define isb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
 				    : : "r" (0) : "memory")
@@ -37,6 +43,13 @@
 #define dmb(x) __asm__ __volatile__ ("" : : : "memory")
 #endif
 
+#ifndef CSDB
+#define CSDB
+#endif
+#ifndef csdb
+#define csdb()
+#endif
+
 #ifdef CONFIG_ARM_HEAVY_MB
 extern void (*soc_mb)(void);
 extern void arm_heavy_mb(void);
@@ -63,6 +76,25 @@ extern void arm_heavy_mb(void);
 #define __smp_rmb()	__smp_mb()
 #define __smp_wmb()	dmb(ishst)
 
+#ifdef CONFIG_CPU_SPECTRE
+static inline unsigned long array_index_mask_nospec(unsigned long idx,
+						    unsigned long sz)
+{
+	unsigned long mask;
+
+	asm volatile(
+		"cmp	%1, %2\n"
+	"	sbc	%0, %1, %1\n"
+	CSDB
+	: "=r" (mask)
+	: "r" (idx), "Ir" (sz)
+	: "cc");
+
+	return mask;
+}
+#define array_index_mask_nospec array_index_mask_nospec
+#endif
+
 #include <asm-generic/barrier.h>
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/arm/include/asm/bugs.h b/arch/arm/include/asm/bugs.h
index a97f1ea708d1..73a99c72a930 100644
--- a/arch/arm/include/asm/bugs.h
+++ b/arch/arm/include/asm/bugs.h
@@ -10,12 +10,14 @@
 #ifndef __ASM_BUGS_H
 #define __ASM_BUGS_H
 
-#ifdef CONFIG_MMU
 extern void check_writebuffer_bugs(void);
 
-#define check_bugs() check_writebuffer_bugs()
+#ifdef CONFIG_MMU
+extern void check_bugs(void);
+extern void check_other_bugs(void);
 #else
 #define check_bugs() do { } while (0)
+#define check_other_bugs() do { } while (0)
 #endif
 
 #endif
diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h
index 4c9fa72b59f5..07e27f212dc7 100644
--- a/arch/arm/include/asm/cp15.h
+++ b/arch/arm/include/asm/cp15.h
@@ -65,6 +65,9 @@
 #define __write_sysreg(v, r, w, c, t)	asm volatile(w " " c : : "r" ((t)(v)))
 #define write_sysreg(v, ...)		__write_sysreg(v, __VA_ARGS__)
 
+#define BPIALL				__ACCESS_CP15(c7, 0, c5, 6)
+#define ICIALLU				__ACCESS_CP15(c7, 0, c5, 0)
+
 extern unsigned long cr_alignment;	/* defined in entry-armv.S */
 
 static inline unsigned long get_cr(void)
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index cb546425da8a..26021980504d 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -77,8 +77,16 @@
 #define ARM_CPU_PART_CORTEX_A12		0x4100c0d0
 #define ARM_CPU_PART_CORTEX_A17		0x4100c0e0
 #define ARM_CPU_PART_CORTEX_A15		0x4100c0f0
+#define ARM_CPU_PART_CORTEX_A53		0x4100d030
+#define ARM_CPU_PART_CORTEX_A57		0x4100d070
+#define ARM_CPU_PART_CORTEX_A72		0x4100d080
+#define ARM_CPU_PART_CORTEX_A73		0x4100d090
+#define ARM_CPU_PART_CORTEX_A75		0x4100d0a0
 #define ARM_CPU_PART_MASK		0xff00fff0
 
+/* Broadcom cores */
+#define ARM_CPU_PART_BRAHMA_B15		0x420000f0
+
 /* DEC implemented cores */
 #define ARM_CPU_PART_SA1100		0x4400a110
 
diff --git a/arch/arm/include/asm/kgdb.h b/arch/arm/include/asm/kgdb.h
index 3b73fdcf3627..8de1100d1067 100644
--- a/arch/arm/include/asm/kgdb.h
+++ b/arch/arm/include/asm/kgdb.h
@@ -77,7 +77,7 @@ extern int kgdb_fault_expected;
 
 #define KGDB_MAX_NO_CPUS	1
 #define BUFMAX			400
-#define NUMREGBYTES		(DBG_MAX_REG_NUM << 2)
+#define NUMREGBYTES		(GDB_MAX_REGS << 2)
 #define NUMCRITREGBYTES		(32 << 2)
 
 #define _R0			0
diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index 5a953ecb0d78..231e87ad45d5 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -61,8 +61,6 @@ struct kvm_vcpu;
 extern char __kvm_hyp_init[];
 extern char __kvm_hyp_init_end[];
 
-extern char __kvm_hyp_vector[];
-
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index c7c28c885a19..343fc9e6f78d 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -21,6 +21,7 @@
 
 #include <linux/types.h>
 #include <linux/kvm_types.h>
+#include <asm/cputype.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
@@ -311,8 +312,17 @@ static inline void kvm_arm_vhe_guest_exit(void) {}
 
 static inline bool kvm_arm_harden_branch_predictor(void)
 {
-	/* No way to detect it yet, pretend it is not there. */
-	return false;
+	switch(read_cpuid_part()) {
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	case ARM_CPU_PART_BRAHMA_B15:
+	case ARM_CPU_PART_CORTEX_A12:
+	case ARM_CPU_PART_CORTEX_A15:
+	case ARM_CPU_PART_CORTEX_A17:
+		return true;
+#endif
+	default:
+		return false;
+	}
 }
 
 static inline void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu) {}
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index f675162663f0..c94d291fd1a8 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -327,7 +327,28 @@ static inline int kvm_read_guest_lock(struct kvm *kvm,
 
 static inline void *kvm_get_hyp_vector(void)
 {
-	return kvm_ksym_ref(__kvm_hyp_vector);
+	switch(read_cpuid_part()) {
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+	case ARM_CPU_PART_CORTEX_A12:
+	case ARM_CPU_PART_CORTEX_A17:
+	{
+		extern char __kvm_hyp_vector_bp_inv[];
+		return kvm_ksym_ref(__kvm_hyp_vector_bp_inv);
+	}
+
+	case ARM_CPU_PART_BRAHMA_B15:
+	case ARM_CPU_PART_CORTEX_A15:
+	{
+		extern char __kvm_hyp_vector_ic_inv[];
+		return kvm_ksym_ref(__kvm_hyp_vector_ic_inv);
+	}
+#endif
+	default:
+	{
+		extern char __kvm_hyp_vector[];
+		return kvm_ksym_ref(__kvm_hyp_vector);
+	}
+	}
 }
 
 static inline int kvm_map_vectors(void)
diff --git a/arch/arm/include/asm/mpu.h b/arch/arm/include/asm/mpu.h
index 6d1491c8ee22..5e088c83d3d8 100644
--- a/arch/arm/include/asm/mpu.h
+++ b/arch/arm/include/asm/mpu.h
@@ -12,60 +12,101 @@
 /* ID_MMFR0 data relevant to MPU */
 #define MMFR0_PMSA		(0xF << 4)
 #define MMFR0_PMSAv7		(3 << 4)
+#define MMFR0_PMSAv8		(4 << 4)
 
 /* MPU D/I Size Register fields */
-#define MPU_RSR_SZ		1
-#define MPU_RSR_EN		0
-#define MPU_RSR_SD		8
+#define PMSAv7_RSR_SZ		1
+#define PMSAv7_RSR_EN		0
+#define PMSAv7_RSR_SD		8
 
 /* Number of subregions (SD) */
-#define MPU_NR_SUBREGS		8
-#define MPU_MIN_SUBREG_SIZE	256
+#define PMSAv7_NR_SUBREGS	8
+#define PMSAv7_MIN_SUBREG_SIZE	256
 
 /* The D/I RSR value for an enabled region spanning the whole of memory */
-#define MPU_RSR_ALL_MEM		63
+#define PMSAv7_RSR_ALL_MEM	63
 
 /* Individual bits in the DR/IR ACR */
-#define MPU_ACR_XN		(1 << 12)
-#define MPU_ACR_SHARED		(1 << 2)
+#define PMSAv7_ACR_XN		(1 << 12)
+#define PMSAv7_ACR_SHARED	(1 << 2)
 
 /* C, B and TEX[2:0] bits only have semantic meanings when grouped */
-#define MPU_RGN_CACHEABLE	0xB
-#define MPU_RGN_SHARED_CACHEABLE (MPU_RGN_CACHEABLE | MPU_ACR_SHARED)
-#define MPU_RGN_STRONGLY_ORDERED 0
+#define PMSAv7_RGN_CACHEABLE		0xB
+#define PMSAv7_RGN_SHARED_CACHEABLE	(PMSAv7_RGN_CACHEABLE | PMSAv7_ACR_SHARED)
+#define PMSAv7_RGN_STRONGLY_ORDERED	0
 
 /* Main region should only be shared for SMP */
 #ifdef CONFIG_SMP
-#define MPU_RGN_NORMAL		(MPU_RGN_CACHEABLE | MPU_ACR_SHARED)
+#define PMSAv7_RGN_NORMAL	(PMSAv7_RGN_CACHEABLE | PMSAv7_ACR_SHARED)
 #else
-#define MPU_RGN_NORMAL		MPU_RGN_CACHEABLE
+#define PMSAv7_RGN_NORMAL	PMSAv7_RGN_CACHEABLE
 #endif
 
 /* Access permission bits of ACR (only define those that we use)*/
-#define MPU_AP_PL1RO_PL0NA	(0x5 << 8)
-#define MPU_AP_PL1RW_PL0RW	(0x3 << 8)
-#define MPU_AP_PL1RW_PL0R0	(0x2 << 8)
-#define MPU_AP_PL1RW_PL0NA	(0x1 << 8)
+#define PMSAv7_AP_PL1RO_PL0NA	(0x5 << 8)
+#define PMSAv7_AP_PL1RW_PL0RW	(0x3 << 8)
+#define PMSAv7_AP_PL1RW_PL0R0	(0x2 << 8)
+#define PMSAv7_AP_PL1RW_PL0NA	(0x1 << 8)
+
+#define PMSAv8_BAR_XN		1
+
+#define PMSAv8_LAR_EN		1
+#define PMSAv8_LAR_IDX(n)	(((n) & 0x7) << 1)
+
+
+#define PMSAv8_AP_PL1RW_PL0NA	(0 << 1)
+#define PMSAv8_AP_PL1RW_PL0RW	(1 << 1)
+#define PMSAv8_AP_PL1RO_PL0RO	(3 << 1)
+
+#ifdef CONFIG_SMP
+#define PMSAv8_RGN_SHARED	(3 << 3) // inner sharable
+#else
+#define PMSAv8_RGN_SHARED	(0 << 3)
+#endif
+
+#define PMSAv8_RGN_DEVICE_nGnRnE	0
+#define PMSAv8_RGN_NORMAL		1
+
+#define PMSAv8_MAIR(attr, mt)	((attr) << ((mt) * 8))
+
+#ifdef CONFIG_CPU_V7M
+#define PMSAv8_MINALIGN		32
+#else
+#define PMSAv8_MINALIGN		64
+#endif
 
 /* For minimal static MPU region configurations */
-#define MPU_PROBE_REGION	0
-#define MPU_BG_REGION		1
-#define MPU_RAM_REGION		2
-#define MPU_ROM_REGION		3
+#define PMSAv7_PROBE_REGION	0
+#define PMSAv7_BG_REGION	1
+#define PMSAv7_RAM_REGION	2
+#define PMSAv7_ROM_REGION	3
+
+/* Fixed for PMSAv8 only */
+#define PMSAv8_XIP_REGION	0
+#define PMSAv8_KERNEL_REGION	1
 
 /* Maximum number of regions Linux is interested in */
-#define MPU_MAX_REGIONS		16
+#define MPU_MAX_REGIONS	16
 
-#define MPU_DATA_SIDE		0
-#define MPU_INSTR_SIDE		1
+#define PMSAv7_DATA_SIDE	0
+#define PMSAv7_INSTR_SIDE	1
 
 #ifndef __ASSEMBLY__
 
 struct mpu_rgn {
 	/* Assume same attributes for d/i-side  */
-	u32 drbar;
-	u32 drsr;
-	u32 dracr;
+	union {
+		u32 drbar;   /* PMSAv7 */
+		u32 prbar;   /* PMSAv8 */
+	};
+	union {
+		u32 drsr;   /* PMSAv7 */
+		u32 prlar;  /* PMSAv8 */
+	};
+	union {
+		u32 dracr;  /* PMSAv7 */
+		u32 unused; /* not used in PMSAv8 */
+	};
 };
 
 struct mpu_rgn_info {
@@ -75,16 +116,17 @@ struct mpu_rgn_info {
 extern struct mpu_rgn_info mpu_rgn_info;
 
 #ifdef CONFIG_ARM_MPU
+extern void __init pmsav7_adjust_lowmem_bounds(void);
+extern void __init pmsav8_adjust_lowmem_bounds(void);
 
-extern void __init adjust_lowmem_bounds_mpu(void);
-extern void __init mpu_setup(void);
-
+extern void __init pmsav7_setup(void);
+extern void __init pmsav8_setup(void);
 #else
-
-static inline void adjust_lowmem_bounds_mpu(void) {}
-static inline void mpu_setup(void) {}
-
-#endif /* !CONFIG_ARM_MPU */
+static inline void pmsav7_adjust_lowmem_bounds(void) {};
+static inline void pmsav8_adjust_lowmem_bounds(void) {};
+static inline void pmsav7_setup(void) {};
+static inline void pmsav8_setup(void) {};
+#endif
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h
index f2e1af45bd6f..e25f4392e1b2 100644
--- a/arch/arm/include/asm/proc-fns.h
+++ b/arch/arm/include/asm/proc-fns.h
@@ -37,6 +37,10 @@ extern struct processor {
 	 */
 	void (*_proc_init)(void);
 	/*
+	 * Check for processor bugs
+	 */
+	void (*check_bugs)(void);
+	/*
 	 * Disable any processor specifics
 	 */
 	void (*_proc_fin)(void);
diff --git a/arch/arm/include/asm/system_misc.h b/arch/arm/include/asm/system_misc.h
index 78f6db114faf..8e76db83c498 100644
--- a/arch/arm/include/asm/system_misc.h
+++ b/arch/arm/include/asm/system_misc.h
@@ -8,6 +8,7 @@
 #include <linux/linkage.h>
 #include <linux/irqflags.h>
 #include <linux/reboot.h>
+#include <linux/percpu.h>
 
 extern void cpu_init(void);
 
@@ -15,6 +16,20 @@ void soft_restart(unsigned long);
 extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
 extern void (*arm_pm_idle)(void);
 
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+typedef void (*harden_branch_predictor_fn_t)(void);
+DECLARE_PER_CPU(harden_branch_predictor_fn_t, harden_branch_predictor_fn);
+static inline void harden_branch_predictor(void)
+{
+	harden_branch_predictor_fn_t fn = per_cpu(harden_branch_predictor_fn,
+						  smp_processor_id());
+	if (fn)
+		fn();
+}
+#else
+#define harden_branch_predictor() do { } while (0)
+#endif
+
 #define UDBG_UNDEFINED	(1 << 0)
 #define UDBG_SYSCALL	(1 << 1)
 #define UDBG_BADABORT	(1 << 2)
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 0bf2347495f1..3d614e90c19f 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -152,7 +152,7 @@ extern int __get_user_64t_4(void *);
 #define __get_user_check(x, p)						\
 	({								\
 		unsigned long __limit = current_thread_info()->addr_limit - 1; \
-		register const typeof(*(p)) __user *__p asm("r0") = (p);\
+		register typeof(*(p)) __user *__p asm("r0") = (p);	\
 		register typeof(x) __r2 asm("r2");			\
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
diff --git a/arch/arm/include/asm/v7m.h b/arch/arm/include/asm/v7m.h
index 634e77107425..187ccf6496ad 100644
--- a/arch/arm/include/asm/v7m.h
+++ b/arch/arm/include/asm/v7m.h
@@ -64,9 +64,17 @@
 #define MPU_CTRL_ENABLE		1
 #define MPU_CTRL_PRIVDEFENA	(1 << 2)
 
-#define MPU_RNR			0x98
-#define MPU_RBAR		0x9c
-#define MPU_RASR		0xa0
+#define PMSAv7_RNR		0x98
+#define PMSAv7_RBAR		0x9c
+#define PMSAv7_RASR		0xa0
+
+#define PMSAv8_RNR		0x98
+#define PMSAv8_RBAR		0x9c
+#define PMSAv8_RLAR		0xa0
+#define PMSAv8_RBAR_A(n)	(PMSAv8_RBAR + 8*(n))
+#define PMSAv8_RLAR_A(n)	(PMSAv8_RLAR + 8*(n))
+#define PMSAv8_MAIR0		0xc0
+#define PMSAv8_MAIR1		0xc4
 
 /* Cache opeartions */
 #define	V7M_SCB_ICIALLU		0x250	/* I-cache invalidate all to PoU */
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index b59ac4bf82b8..8cad59465af3 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -31,6 +31,7 @@ else
 obj-y		+= entry-armv.o
 endif
 
+obj-$(CONFIG_MMU)		+= bugs.o
 obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 obj-$(CONFIG_ISA_DMA_API)	+= dma.o
 obj-$(CONFIG_FIQ)		+= fiq.o fiqasm.o
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index f369ece99958..27c5381518d8 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -194,9 +194,11 @@ int main(void)
   DEFINE(MPU_RNG_INFO_USED,	offsetof(struct mpu_rgn_info, used));
 
   DEFINE(MPU_RNG_SIZE,		sizeof(struct mpu_rgn));
-  DEFINE(MPU_RGN_DRBAR,		offsetof(struct mpu_rgn, drbar));
-  DEFINE(MPU_RGN_DRSR,		offsetof(struct mpu_rgn, drsr));
-  DEFINE(MPU_RGN_DRACR,		offsetof(struct mpu_rgn, dracr));
+  DEFINE(MPU_RGN_DRBAR,	offsetof(struct mpu_rgn, drbar));
+  DEFINE(MPU_RGN_DRSR,	offsetof(struct mpu_rgn, drsr));
+  DEFINE(MPU_RGN_DRACR,	offsetof(struct mpu_rgn, dracr));
+  DEFINE(MPU_RGN_PRBAR,	offsetof(struct mpu_rgn, prbar));
+  DEFINE(MPU_RGN_PRLAR,	offsetof(struct mpu_rgn, prlar));
 #endif
   return 0; 
 }
diff --git a/arch/arm/kernel/bugs.c b/arch/arm/kernel/bugs.c
new file mode 100644
index 000000000000..7be511310191
--- /dev/null
+++ b/arch/arm/kernel/bugs.c
@@ -0,0 +1,18 @@
+// SPDX-Identifier: GPL-2.0
+#include <linux/init.h>
+#include <asm/bugs.h>
+#include <asm/proc-fns.h>
+
+void check_other_bugs(void)
+{
+#ifdef MULTI_CPU
+	if (processor.check_bugs)
+		processor.check_bugs();
+#endif
+}
+
+void __init check_bugs(void)
+{
+	check_writebuffer_bugs();
+	check_other_bugs();
+}
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 3c4f88701f22..20df608bf343 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -242,9 +242,7 @@ local_restart:
 	tst	r10, #_TIF_SYSCALL_WORK		@ are we tracing syscalls?
 	bne	__sys_trace
 
-	cmp	scno, #NR_syscalls		@ check upper syscall limit
-	badr	lr, ret_fast_syscall		@ return address
-	ldrcc	pc, [tbl, scno, lsl #2]		@ call sys_* routine
+	invoke_syscall tbl, scno, r10, ret_fast_syscall
 
 	add	r1, sp, #S_OFF
 2:	cmp	scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE)
@@ -278,14 +276,8 @@ __sys_trace:
 	mov	r1, scno
 	add	r0, sp, #S_OFF
 	bl	syscall_trace_enter
-
-	badr	lr, __sys_trace_return		@ return address
-	mov	scno, r0			@ syscall number (possibly new)
-	add	r1, sp, #S_R0 + S_OFF		@ pointer to regs
-	cmp	scno, #NR_syscalls		@ check upper syscall limit
-	ldmccia	r1, {r0 - r6}			@ have to reload r0 - r6
-	stmccia	sp, {r4, r5}			@ and update the stack args
-	ldrcc	pc, [tbl, scno, lsl #2]		@ call sys_* routine
+	mov	scno, r0
+	invoke_syscall tbl, scno, r10, __sys_trace_return, reload=1
 	cmp	scno, #-1			@ skip the syscall?
 	bne	2b
 	add	sp, sp, #S_OFF			@ restore stack
@@ -363,6 +355,10 @@ sys_syscall:
 		bic	scno, r0, #__NR_OABI_SYSCALL_BASE
 		cmp	scno, #__NR_syscall - __NR_SYSCALL_BASE
 		cmpne	scno, #NR_syscalls	@ check range
+#ifdef CONFIG_CPU_SPECTRE
+		movhs	scno, #0
+		csdb
+#endif
 		stmloia	sp, {r5, r6}		@ shuffle args
 		movlo	r0, r1
 		movlo	r1, r2
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 0f07579af472..773424843d6e 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -378,6 +378,31 @@
 #endif
 	.endm
 
+	.macro	invoke_syscall, table, nr, tmp, ret, reload=0
+#ifdef CONFIG_CPU_SPECTRE
+	mov	\tmp, \nr
+	cmp	\tmp, #NR_syscalls		@ check upper syscall limit
+	movcs	\tmp, #0
+	csdb
+	badr	lr, \ret			@ return address
+	.if	\reload
+	add	r1, sp, #S_R0 + S_OFF		@ pointer to regs
+	ldmccia	r1, {r0 - r6}			@ reload r0-r6
+	stmccia	sp, {r4, r5}			@ update stack arguments
+	.endif
+	ldrcc	pc, [\table, \tmp, lsl #2]	@ call sys_* routine
+#else
+	cmp	\nr, #NR_syscalls		@ check upper syscall limit
+	badr	lr, \ret			@ return address
+	.if	\reload
+	add	r1, sp, #S_R0 + S_OFF		@ pointer to regs
+	ldmccia	r1, {r0 - r6}			@ reload r0-r6
+	stmccia	sp, {r4, r5}			@ update stack arguments
+	.endif
+	ldrcc	pc, [\table, \nr, lsl #2]	@ call sys_* routine
+#endif
+	.endm
+
 /*
  * These are the registers used in the syscall handler, and allow us to
  * have in theory up to 7 arguments to a function - r0 to r6.
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index 2e38f85b757a..dd546d65a383 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -68,14 +68,6 @@ ENTRY(stext)
 	beq	__error_p				@ yes, error 'p'
 
 #ifdef CONFIG_ARM_MPU
-	/* Calculate the size of a region covering just the kernel */
-	ldr	r5, =PLAT_PHYS_OFFSET		@ Region start: PHYS_OFFSET
-	ldr     r6, =(_end)			@ Cover whole kernel
-	sub	r6, r6, r5			@ Minimum size of region to map
-	clz	r6, r6				@ Region size must be 2^N...
-	rsb	r6, r6, #31			@ ...so round up region size
-	lsl	r6, r6, #MPU_RSR_SZ		@ Put size in right field
-	orr	r6, r6, #(1 << MPU_RSR_EN)	@ Set region enabled bit
 	bl	__setup_mpu
 #endif
 
@@ -83,8 +75,8 @@ ENTRY(stext)
 	ldr	r12, [r10, #PROCINFO_INITFUNC]
 	add	r12, r12, r10
 	ret	r12
-1:	bl	__after_proc_init
-	b	__mmap_switched
+1:	ldr	lr, =__mmap_switched
+	b	__after_proc_init
 ENDPROC(stext)
 
 #ifdef CONFIG_SMP
@@ -110,8 +102,6 @@ ENTRY(secondary_startup)
 	ldr	r7, __secondary_data
 
 #ifdef CONFIG_ARM_MPU
-	/* Use MPU region info supplied by __cpu_up */
-	ldr	r6, [r7]			@ get secondary_data.mpu_rgn_info
 	bl      __secondary_setup_mpu		@ Initialize the MPU
 #endif
 
@@ -133,12 +123,45 @@ __secondary_data:
 /*
  * Set the Control Register and Read the process ID.
  */
+	.text
 __after_proc_init:
+#ifdef CONFIG_ARM_MPU
+M_CLASS(movw	r12, #:lower16:BASEADDR_V7M_SCB)
+M_CLASS(movt	r12, #:upper16:BASEADDR_V7M_SCB)
+M_CLASS(ldr	r3, [r12, 0x50])
+AR_CLASS(mrc	p15, 0, r3, c0, c1, 4)          @ Read ID_MMFR0
+	and	r3, r3, #(MMFR0_PMSA)           @ PMSA field
+	teq	r3, #(MMFR0_PMSAv7)             @ PMSA v7
+	beq	1f
+	teq	r3, #(MMFR0_PMSAv8)		@ PMSA v8
+	/*
+	 * Memory region attributes for PMSAv8:
+	 *
+	 *   n = AttrIndx[2:0]
+	 *                      n       MAIR
+	 *   DEVICE_nGnRnE      000     00000000
+	 *   NORMAL             001     11111111
+	 */
+	ldreq	r3, =PMSAv8_MAIR(0x00, PMSAv8_RGN_DEVICE_nGnRnE) | \
+		     PMSAv8_MAIR(0xff, PMSAv8_RGN_NORMAL)
+AR_CLASS(mcreq	p15, 0, r3, c10, c2, 0)		@ MAIR 0
+M_CLASS(streq	r3, [r12, #PMSAv8_MAIR0])
+	moveq	r3, #0
+AR_CLASS(mcreq	p