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

Pull ARM updates from Russell King:

 - update unwinder to cope with module PLTs

 - enable UBSAN on ARM

 - improve kernel fault message

 - update UEFI runtime page tables dump

 - avoid clang's __aeabi_uldivmod generated in NWFPE code

 - disable FIQs on CPU shutdown paths

 - update XOR register usage

 - a number of build updates (using .arch, thread pointer, removal of
   lazy evaluation in Makefile)

 - conversion of stacktrace code to stackwalk

 - findbit assembly updates

 - hwcap feature updates for ARMv8 CPUs

 - instruction dump updates for big-endian platforms

 - support for function error injection

* tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm: (31 commits)
  ARM: 9279/1: support function error injection
  ARM: 9277/1: Make the dumped instructions are consistent with the disassembled ones
  ARM: 9276/1: Refactor dump_instr()
  ARM: 9275/1: Drop '-mthumb' from AFLAGS_ISA
  ARM: 9274/1: Add hwcap for Speculative Store Bypassing Safe
  ARM: 9273/1: Add hwcap for Speculation Barrier(SB)
  ARM: 9272/1: vfp: Add hwcap for FEAT_AA32I8MM
  ARM: 9271/1: vfp: Add hwcap for FEAT_AA32BF16
  ARM: 9270/1: vfp: Add hwcap for FEAT_FHM
  ARM: 9269/1: vfp: Add hwcap for FEAT_DotProd
  ARM: 9268/1: vfp: Add hwcap FPHP and ASIMDHP for FEAT_FP16
  ARM: 9267/1: Define Armv8 registers in AArch32 state
  ARM: findbit: add unwinder information
  ARM: findbit: operate by words
  ARM: findbit: convert to macros
  ARM: findbit: provide more efficient ARMv7 implementation
  ARM: findbit: document ARMv5 bit offset calculation
  ARM: 9259/1: stacktrace: Convert stacktrace to generic ARCH_STACKWALK
  ARM: 9258/1: stacktrace: Make stack walk callback consistent with generic code
  ARM: 9265/1: pass -march= only to compiler
  ...

63 files changed, 388 insertions, 329 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index a08c9d092a33..65d0daf63262 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -17,6 +17,7 @@ config ARM
 	select ARCH_HAS_PTE_SPECIAL if ARM_LPAE
 	select ARCH_HAS_SETUP_DMA_OPS
 	select ARCH_HAS_SET_MEMORY
+	select ARCH_STACKWALK
 	select ARCH_HAS_STRICT_KERNEL_RWX if MMU && !XIP_KERNEL
 	select ARCH_HAS_STRICT_MODULE_RWX if MMU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
@@ -27,6 +28,7 @@ config ARM
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG if CPU_V7 || CPU_V7M || CPU_V6K
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_KEEP_MEMBLOCK
+	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT if CPU_V7
@@ -95,6 +97,7 @@ config ARM
 	select HAVE_EXIT_THREAD
 	select HAVE_FAST_GUP if ARM_LPAE
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
+	select HAVE_FUNCTION_ERROR_INJECTION
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER if !XIP_KERNEL
 	select HAVE_GCC_PLUGINS
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index c846119c448f..4067f5169144 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -60,47 +60,54 @@ endif
 KBUILD_CFLAGS	+= $(call cc-option,-fno-ipa-sra)
 
 # This selects which instruction set is used.
+arch-$(CONFIG_CPU_32v7M)	:=-march=armv7-m
+arch-$(CONFIG_CPU_32v7)		:=-march=armv7-a
+arch-$(CONFIG_CPU_32v6)		:=-march=armv6
+# Only override the compiler option if ARMv6. The ARMv6K extensions are
+# always available in ARMv7
+ifeq ($(CONFIG_CPU_32v6),y)
+arch-$(CONFIG_CPU_32v6K)	:=-march=armv6k
+endif
+arch-$(CONFIG_CPU_32v5)		:=-march=armv5te
+arch-$(CONFIG_CPU_32v4T)	:=-march=armv4t
+arch-$(CONFIG_CPU_32v4)		:=-march=armv4
+arch-$(CONFIG_CPU_32v3)		:=-march=armv3m
+
 # Note that GCC does not numerically define an architecture version
 # macro, but instead defines a whole series of macros which makes
 # testing for a specific architecture or later rather impossible.
-arch-$(CONFIG_CPU_32v7M)	=-D__LINUX_ARM_ARCH__=7 -march=armv7-m
-arch-$(CONFIG_CPU_32v7)		=-D__LINUX_ARM_ARCH__=7 -march=armv7-a
-arch-$(CONFIG_CPU_32v6)		=-D__LINUX_ARM_ARCH__=6 -march=armv6
+cpp-$(CONFIG_CPU_32v7M)		:=-D__LINUX_ARM_ARCH__=7
+cpp-$(CONFIG_CPU_32v7)		:=-D__LINUX_ARM_ARCH__=7
+cpp-$(CONFIG_CPU_32v6)		:=-D__LINUX_ARM_ARCH__=6
 # Only override the compiler option if ARMv6. The ARMv6K extensions are
 # always available in ARMv7
 ifeq ($(CONFIG_CPU_32v6),y)
-arch-$(CONFIG_CPU_32v6K)	=-D__LINUX_ARM_ARCH__=6 -march=armv6k
+cpp-$(CONFIG_CPU_32v6K)		:=-D__LINUX_ARM_ARCH__=6
 endif
-arch-$(CONFIG_CPU_32v5)		=-D__LINUX_ARM_ARCH__=5 -march=armv5te
-arch-$(CONFIG_CPU_32v4T)	=-D__LINUX_ARM_ARCH__=4 -march=armv4t
-arch-$(CONFIG_CPU_32v4)		=-D__LINUX_ARM_ARCH__=4 -march=armv4
-arch-$(CONFIG_CPU_32v3)		=-D__LINUX_ARM_ARCH__=3 -march=armv3m
-
-# Evaluate arch cc-option calls now
-arch-y := $(arch-y)
+cpp-$(CONFIG_CPU_32v5)		:=-D__LINUX_ARM_ARCH__=5
+cpp-$(CONFIG_CPU_32v4T)		:=-D__LINUX_ARM_ARCH__=4
+cpp-$(CONFIG_CPU_32v4)		:=-D__LINUX_ARM_ARCH__=4
+cpp-$(CONFIG_CPU_32v3)		:=-D__LINUX_ARM_ARCH__=3
 
 # This selects how we optimise for the processor.
-tune-$(CONFIG_CPU_ARM7TDMI)	=-mtune=arm7tdmi
-tune-$(CONFIG_CPU_ARM720T)	=-mtune=arm7tdmi
-tune-$(CONFIG_CPU_ARM740T)	=-mtune=arm7tdmi
-tune-$(CONFIG_CPU_ARM9TDMI)	=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_ARM940T)	=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_ARM946E)	=-mtune=arm9e
-tune-$(CONFIG_CPU_ARM920T)	=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_ARM922T)	=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_ARM925T)	=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_ARM926T)	=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_FA526)	=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_SA110)	=-mtune=strongarm110
-tune-$(CONFIG_CPU_SA1100)	=-mtune=strongarm1100
-tune-$(CONFIG_CPU_XSCALE)	=-mtune=xscale
-tune-$(CONFIG_CPU_XSC3)		=-mtune=xscale
-tune-$(CONFIG_CPU_FEROCEON)	=-mtune=xscale
-tune-$(CONFIG_CPU_V6)		=-mtune=arm1136j-s
-tune-$(CONFIG_CPU_V6K)		=-mtune=arm1136j-s
-
-# Evaluate tune cc-option calls now
-tune-y := $(tune-y)
+tune-$(CONFIG_CPU_ARM7TDMI)	:=-mtune=arm7tdmi
+tune-$(CONFIG_CPU_ARM720T)	:=-mtune=arm7tdmi
+tune-$(CONFIG_CPU_ARM740T)	:=-mtune=arm7tdmi
+tune-$(CONFIG_CPU_ARM9TDMI)	:=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_ARM940T)	:=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_ARM946E)	:=-mtune=arm9e
+tune-$(CONFIG_CPU_ARM920T)	:=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_ARM922T)	:=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_ARM925T)	:=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_ARM926T)	:=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_FA526)	:=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_SA110)	:=-mtune=strongarm110
+tune-$(CONFIG_CPU_SA1100)	:=-mtune=strongarm1100
+tune-$(CONFIG_CPU_XSCALE)	:=-mtune=xscale
+tune-$(CONFIG_CPU_XSC3)		:=-mtune=xscale
+tune-$(CONFIG_CPU_FEROCEON)	:=-mtune=xscale
+tune-$(CONFIG_CPU_V6)		:=-mtune=arm1136j-s
+tune-$(CONFIG_CPU_V6K)		:=-mtune=arm1136j-s
 
 ifeq ($(CONFIG_AEABI),y)
 CFLAGS_ABI	:=-mabi=aapcs-linux -mfpu=vfp
@@ -117,23 +124,25 @@ CFLAGS_ABI	+= -meabi gnu
 endif
 
 ifeq ($(CONFIG_CURRENT_POINTER_IN_TPIDRURO),y)
-CFLAGS_ABI	+= -mtp=cp15
+KBUILD_CFLAGS	+= -mtp=cp15
 endif
 
 # Accept old syntax despite ".syntax unified"
 AFLAGS_NOWARN	:=$(call as-option,-Wa$(comma)-mno-warn-deprecated,-Wa$(comma)-W)
 
 ifeq ($(CONFIG_THUMB2_KERNEL),y)
-CFLAGS_ISA	:=-mthumb -Wa,-mimplicit-it=always $(AFLAGS_NOWARN)
-AFLAGS_ISA	:=$(CFLAGS_ISA) -Wa$(comma)-mthumb
+CFLAGS_ISA	:=-Wa,-mimplicit-it=always $(AFLAGS_NOWARN)
+AFLAGS_ISA	:=$(CFLAGS_ISA) -Wa$(comma)-mthumb -D__thumb2__=2
+CFLAGS_ISA	+=-mthumb
 else
 CFLAGS_ISA	:=$(call cc-option,-marm,) $(AFLAGS_NOWARN)
 AFLAGS_ISA	:=$(CFLAGS_ISA)
 endif
 
 # Need -Uarm for gcc < 3.x
+KBUILD_CPPFLAGS	+=$(cpp-y)
 KBUILD_CFLAGS	+=$(CFLAGS_ABI) $(CFLAGS_ISA) $(arch-y) $(tune-y) $(call cc-option,-mshort-load-bytes,$(call cc-option,-malignment-traps,)) -msoft-float -Uarm
-KBUILD_AFLAGS	+=$(CFLAGS_ABI) $(AFLAGS_ISA) $(arch-y) $(tune-y) -include asm/unified.h -msoft-float
+KBUILD_AFLAGS	+=$(CFLAGS_ABI) $(AFLAGS_ISA) -Wa,$(arch-y) $(tune-y) -include asm/unified.h -msoft-float
 
 CHECKFLAGS	+= -D__arm__
 
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 41bcbb460fac..8c63f0a26f56 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -27,6 +27,7 @@ KASAN_SANITIZE		:= n
 
 # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
 KCOV_INSTRUMENT		:= n
+UBSAN_SANITIZE		:= n
 
 #
 # Architecture dependencies
@@ -163,4 +164,3 @@ $(obj)/piggy_data: $(obj)/../Image FORCE
 $(obj)/piggy.o: $(obj)/piggy_data
 
 CFLAGS_font.o := -Dstatic=
-AFLAGS_hyp-stub.o := -Wa,-march=armv7-a
diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile
index 7bae8cbaafe7..9733381074e0 100644
--- a/arch/arm/common/Makefile
+++ b/arch/arm/common/Makefile
@@ -13,7 +13,5 @@ obj-$(CONFIG_SHARP_SCOOP)	+= scoop.o
 obj-$(CONFIG_CPU_V7)		+= secure_cntvoff.o
 obj-$(CONFIG_MCPM)		+= mcpm_head.o mcpm_entry.o mcpm_platsmp.o vlock.o
 CFLAGS_REMOVE_mcpm_entry.o	= -pg
-AFLAGS_mcpm_head.o		:= -march=armv7-a
-AFLAGS_vlock.o			:= -march=armv7-a
 obj-$(CONFIG_BL_SWITCHER)	+= bL_switcher.o
 obj-$(CONFIG_BL_SWITCHER_DUMMY_IF) += bL_switcher_dummy_if.o
diff --git a/arch/arm/common/mcpm_head.S b/arch/arm/common/mcpm_head.S
index 291d969bc719..299495c43dfd 100644
--- a/arch/arm/common/mcpm_head.S
+++ b/arch/arm/common/mcpm_head.S
@@ -15,6 +15,8 @@
 
 #include "vlock.h"
 
+.arch armv7-a
+
 .if MCPM_SYNC_CLUSTER_CPUS
 .error "cpus must be the first member of struct mcpm_sync_struct"
 .endif
diff --git a/arch/arm/common/vlock.S b/arch/arm/common/vlock.S
index f1c7fd44f1b1..1fa09c4697ed 100644
--- a/arch/arm/common/vlock.S
+++ b/arch/arm/common/vlock.S
@@ -12,6 +12,8 @@
 #include <linux/linkage.h>
 #include "vlock.h"
 
+.arch armv7-a
+
 /* Select different code if voting flags  can fit in a single word. */
 #if VLOCK_VOTING_SIZE > 4
 #define FEW(x...)
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 90fbe4a3f9c8..28e18f79c300 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -761,6 +761,12 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.endif
 	.endm
 
+	.if		__LINUX_ARM_ARCH__ < 6
+	.set		.Lrev_l_uses_tmp, 1
+	.else
+	.set		.Lrev_l_uses_tmp, 0
+	.endif
+
 	/*
 	 * bl_r - branch and link to register
 	 *
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index 775cac3c02bb..0163c3e78a67 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -25,6 +25,8 @@
 #define CPUID_EXT_ISAR3	0x6c
 #define CPUID_EXT_ISAR4	0x70
 #define CPUID_EXT_ISAR5	0x74
+#define CPUID_EXT_ISAR6	0x7c
+#define CPUID_EXT_PFR2	0x90
 #else
 #define CPUID_EXT_PFR0	"c1, 0"
 #define CPUID_EXT_PFR1	"c1, 1"
@@ -40,6 +42,8 @@
 #define CPUID_EXT_ISAR3	"c2, 3"
 #define CPUID_EXT_ISAR4	"c2, 4"
 #define CPUID_EXT_ISAR5	"c2, 5"
+#define CPUID_EXT_ISAR6	"c2, 7"
+#define CPUID_EXT_PFR2	"c3, 4"
 #endif
 
 #define MPIDR_SMP_BITMASK (0x3 << 30)
diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h
index 5546c9751478..07c51a34f77d 100644
--- a/arch/arm/include/asm/module.h
+++ b/arch/arm/include/asm/module.h
@@ -37,6 +37,11 @@ struct mod_arch_specific {
 
 struct module;
 u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val);
+#ifdef CONFIG_ARM_MODULE_PLTS
+bool in_module_plt(unsigned long loc);
+#else
+static inline bool in_module_plt(unsigned long loc) { return false; }
+#endif
 
 #ifdef CONFIG_THUMB2_KERNEL
 #define HAVE_ARCH_KALLSYMS_SYMBOL_VALUE
diff --git a/arch/arm/include/asm/ptdump.h b/arch/arm/include/asm/ptdump.h
index 0c2d3d0d4cc6..aad1d034136c 100644
--- a/arch/arm/include/asm/ptdump.h
+++ b/arch/arm/include/asm/ptdump.h
@@ -21,6 +21,7 @@ struct ptdump_info {
 
 void ptdump_walk_pgd(struct seq_file *s, struct ptdump_info *info);
 #ifdef CONFIG_ARM_PTDUMP_DEBUGFS
+#define EFI_RUNTIME_MAP_END	SZ_1G
 void ptdump_debugfs_register(struct ptdump_info *info, const char *name);
 #else
 static inline void ptdump_debugfs_register(struct ptdump_info *info,
diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h
index 1408a6a15d0e..483b8ddfcb82 100644
--- a/arch/arm/include/asm/ptrace.h
+++ b/arch/arm/include/asm/ptrace.h
@@ -163,6 +163,10 @@ static inline unsigned long user_stack_pointer(struct pt_regs *regs)
 		((current_stack_pointer | (THREAD_SIZE - 1)) - 7) - 1;	\
 })
 
+static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
+{
+	regs->ARM_r0 = rc;
+}
 
 /*
  * Update ITSTATE after normal execution of an IT block instruction.
diff --git a/arch/arm/include/asm/stacktrace.h b/arch/arm/include/asm/stacktrace.h
index 36b2ff44fcbb..360f0d2406bf 100644
--- a/arch/arm/include/asm/stacktrace.h
+++ b/arch/arm/include/asm/stacktrace.h
@@ -44,7 +44,7 @@ void arm_get_current_stackframe(struct pt_regs *regs, struct stackframe *frame)
 
 extern int unwind_frame(struct stackframe *frame);
 extern void walk_stackframe(struct stackframe *frame,
-			    int (*fn)(struct stackframe *, void *), void *data);
+			    bool (*fn)(void *, unsigned long), void *data);
 extern void dump_mem(const char *lvl, const char *str, unsigned long bottom,
 		     unsigned long top);
 extern void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk,
diff --git a/arch/arm/include/asm/vfp.h b/arch/arm/include/asm/vfp.h
index 19928bfb4f9c..157ea3426158 100644
--- a/arch/arm/include/asm/vfp.h
+++ b/arch/arm/include/asm/vfp.h
@@ -87,6 +87,12 @@
 #define MVFR0_DP_BIT		(8)
 #define MVFR0_DP_MASK		(0xf << MVFR0_DP_BIT)
 
+/* MVFR1 bits */
+#define MVFR1_ASIMDHP_BIT	(20)
+#define MVFR1_ASIMDHP_MASK	(0xf << MVFR1_ASIMDHP_BIT)
+#define MVFR1_FPHP_BIT		(24)
+#define MVFR1_FPHP_MASK		(0xf << MVFR1_FPHP_BIT)
+
 /* Bit patterns for decoding the packaged operation descriptors */
 #define VFPOPDESC_LENGTH_BIT	(9)
 #define VFPOPDESC_LENGTH_MASK	(0x07 << VFPOPDESC_LENGTH_BIT)
diff --git a/arch/arm/include/asm/xor.h b/arch/arm/include/asm/xor.h
index 669cad5194d3..934b549905f5 100644
--- a/arch/arm/include/asm/xor.h
+++ b/arch/arm/include/asm/xor.h
@@ -51,7 +51,7 @@ xor_arm4regs_2(unsigned long bytes, unsigned long * __restrict p1,
 	register unsigned int a1 __asm__("r4");
 	register unsigned int a2 __asm__("r5");
 	register unsigned int a3 __asm__("r6");
-	register unsigned int a4 __asm__("r7");
+	register unsigned int a4 __asm__("r10");
 	register unsigned int b1 __asm__("r8");
 	register unsigned int b2 __asm__("r9");
 	register unsigned int b3 __asm__("ip");
@@ -73,7 +73,7 @@ xor_arm4regs_3(unsigned long bytes, unsigned long * __restrict p1,
 	register unsigned int a1 __asm__("r4");
 	register unsigned int a2 __asm__("r5");
 	register unsigned int a3 __asm__("r6");
-	register unsigned int a4 __asm__("r7");
+	register unsigned int a4 __asm__("r10");
 	register unsigned int b1 __asm__("r8");
 	register unsigned int b2 __asm__("r9");
 	register unsigned int b3 __asm__("ip");
diff --git a/arch/arm/include/uapi/asm/hwcap.h b/arch/arm/include/uapi/asm/hwcap.h
index 990199d8b7c6..6b2023e39b6f 100644
--- a/arch/arm/include/uapi/asm/hwcap.h
+++ b/arch/arm/include/uapi/asm/hwcap.h
@@ -28,6 +28,12 @@
 #define HWCAP_IDIV	(HWCAP_IDIVA | HWCAP_IDIVT)
 #define HWCAP_LPAE	(1 << 20)
 #define HWCAP_EVTSTRM	(1 << 21)
+#define HWCAP_FPHP	(1 << 22)
+#define HWCAP_ASIMDHP	(1 << 23)
+#define HWCAP_ASIMDDP	(1 << 24)
+#define HWCAP_ASIMDFHM	(1 << 25)
+#define HWCAP_ASIMDBF16	(1 << 26)
+#define HWCAP_I8MM	(1 << 27)
 
 /*
  * HWCAP2 flags - for elf_hwcap2 (in kernel) and AT_HWCAP2
@@ -37,5 +43,7 @@
 #define HWCAP2_SHA1	(1 << 2)
 #define HWCAP2_SHA2	(1 << 3)
 #define HWCAP2_CRC32	(1 << 4)
+#define HWCAP2_SB	(1 << 5)
+#define HWCAP2_SSBS	(1 << 6)
 
 #endif /* _UAPI__ASMARM_HWCAP_H */
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 48737ec800eb..d53f56d6f840 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -70,7 +70,6 @@ obj-$(CONFIG_HAVE_TCM)		+= tcm.o
 obj-$(CONFIG_OF)		+= devtree.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_SWP_EMULATE)	+= swp_emulate.o
-CFLAGS_swp_emulate.o		:= -Wa,-march=armv7-a
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 
 obj-$(CONFIG_CPU_XSCALE)	+= xscale-cp0.o
@@ -99,7 +98,6 @@ CFLAGS_head-inflate-data.o := $(call cc-option,-Wframe-larger-than=10240)
 obj-$(CONFIG_XIP_DEFLATED_DATA) += head-inflate-data.o
 
 obj-$(CONFIG_ARM_VIRT_EXT)	+= hyp-stub.o
-AFLAGS_hyp-stub.o		:=-Wa,-march=armv7-a
 ifeq ($(CONFIG_ARM_PSCI),y)
 obj-$(CONFIG_SMP)		+= psci_smp.o
 endif
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index b699b22a4db1..3a506b9095a5 100644
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@@ -9,6 +9,8 @@
 #include <asm/assembler.h>
 #include <asm/virt.h>
 
+.arch armv7-a
+
 #ifndef ZIMAGE
 /*
  * For the kernel proper, we need to find out the CPU boot mode long after
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index a2e9ac763a9f..46364b699cc3 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -77,6 +77,8 @@ static void machine_crash_nonpanic_core(void *unused)
 {
 	struct pt_regs regs;
 
+	local_fiq_disable();
+
 	crash_setup_regs(&regs, get_irq_regs());
 	printk(KERN_DEBUG "CPU %u will stop doing anything useful since another CPU has crashed\n",
 	       smp_processor_id());
diff --git a/arch/arm/kernel/module-plts.c b/arch/arm/kernel/module-plts.c
index 1fc309b41f94..af7c322ebed6 100644
--- a/arch/arm/kernel/module-plts.c
+++ b/arch/arm/kernel/module-plts.c
@@ -284,3 +284,17 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 		 mod->arch.core.plt->sh_size, mod->arch.init.plt->sh_size);
 	return 0;
 }
+
+bool in_module_plt(unsigned long loc)
+{
+	struct module *mod;
+	bool ret;
+
+	preempt_disable();
+	mod = __module_text_address(loc);
+	ret = mod && (loc - (u32)mod->arch.core.plt_ent < mod->arch.core.plt_count * PLT_ENT_SIZE ||
+		      loc - (u32)mod->arch.init.plt_ent < mod->arch.init.plt_count * PLT_ENT_SIZE);
+	preempt_enable();
+
+	return ret;
+}
diff --git a/arch/arm/kernel/perf_callchain.c b/arch/arm/kernel/perf_callchain.c
index bc6b246ab55e..7147edbe56c6 100644
--- a/arch/arm/kernel/perf_callchain.c
+++ b/arch/arm/kernel/perf_callchain.c
@@ -81,13 +81,12 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
  * whist unwinding the stackframe and is like a subroutine return so we use
  * the PC.
  */
-static int
-callchain_trace(struct stackframe *fr,
-		void *data)
+static bool
+callchain_trace(void *data, unsigned long pc)
 {
 	struct perf_callchain_entry_ctx *entry = data;
-	perf_callchain_store(entry, fr->pc);
-	return 0;
+	perf_callchain_store(entry, pc);
+	return true;
 }
 
 void
diff --git a/arch/arm/kernel/return_address.c b/arch/arm/kernel/return_address.c
index 38f1ea9c724d..ac15db66df4c 100644
--- a/arch/arm/kernel/return_address.c
+++ b/arch/arm/kernel/return_address.c
@@ -16,17 +16,17 @@ struct return_address_data {
 	void *addr;
 };
 
-static int save_return_addr(struct stackframe *frame, void *d)
+static bool save_return_addr(void *d, unsigned long pc)
 {
 	struct return_address_data *data = d;
 
 	if (!data->level) {
-		data->addr = (void *)frame->pc;
+		data->addr = (void *)pc;
 
-		return 1;
+		return false;
 	} else {
 		--data->level;
-		return 0;
+		return true;
 	}
 }
 
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index cb88c6e69377..75cd4699e7b3 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -450,6 +450,8 @@ static void __init cpuid_init_hwcaps(void)
 {
 	int block;
 	u32 isar5;
+	u32 isar6;
+	u32 pfr2;
 
 	if (cpu_architecture() < CPU_ARCH_ARMv7)
 		return;
@@ -485,6 +487,18 @@ static void __init cpuid_init_hwcaps(void)
 	block = cpuid_feature_extract_field(isar5, 16);
 	if (block >= 1)
 		elf_hwcap2 |= HWCAP2_CRC32;
+
+	/* Check for Speculation barrier instruction */
+	isar6 = read_cpuid_ext(CPUID_EXT_ISAR6);
+	block = cpuid_feature_extract_field(isar6, 12);
+	if (block >= 1)
+		elf_hwcap2 |= HWCAP2_SB;
+
+	/* Check for Speculative Store Bypassing control */
+	pfr2 = read_cpuid_ext(CPUID_EXT_PFR2);
+	block = cpuid_feature_extract_field(pfr2, 4);
+	if (block >= 1)
+		elf_hwcap2 |= HWCAP2_SSBS;
 }
 
 static void __init elf_hwcap_fixup(void)
@@ -1249,6 +1263,12 @@ static const char *hwcap_str[] = {
 	"vfpd32",
 	"lpae",
 	"evtstrm",
+	"fphp",
+	"asimdhp",
+	"asimddp",
+	"asimdfhm",
+	"asimdbf16",
+	"i8mm",
 	NULL
 };
 
@@ -1258,6 +1278,8 @@ static const char *hwcap2_str[] = {
 	"sha1",
 	"sha2",
 	"crc32",
+	"sb",
+	"ssbs",
 	NULL
 };
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 978db2d96b44..36e6efad89f3 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -600,6 +600,8 @@ static DEFINE_RAW_SPINLOCK(stop_lock);
  */
 static void ipi_cpu_stop(unsigned int cpu)
 {
+	local_fiq_disable();
+
 	if (system_state <= SYSTEM_RUNNING) {
 		raw_spin_lock(&stop_lock);
 		pr_crit("CPU%u: stopping\n", cpu);
@@ -609,9 +611,6 @@ static void ipi_cpu_stop(unsigned int cpu)
 
 	set_cpu_online(cpu, false);
 
-	local_fiq_disable();
-	local_irq_disable();
-
 	while (1) {
 		cpu_relax();
 		wfe();
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index 85443b5d1922..620aa82e3bdd 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -127,12 +127,12 @@ int notrace unwind_frame(struct stackframe *frame)
 #endif
 
 void notrace walk_stackframe(struct stackframe *frame,
-		     int (*fn)(struct stackframe *, void *), void *data)
+		     bool (*fn)(void *, unsigned long), void *data)
 {
 	while (1) {
 		int ret;
 
-		if (fn(frame, data))
+		if (!fn(data, frame->pc))
 			break;
 		ret = unwind_frame(frame);
 		if (ret < 0)
@@ -142,41 +142,32 @@ void notrace walk_stackframe(struct stackframe *frame,
 EXPORT_SYMBOL(walk_stackframe);
 
 #ifdef CONFIG_STACKTRACE
-struct stack_trace_data {
-	struct stack_trace *trace;
-	unsigned int no_sched_functions;
-	unsigned int skip;
-};
-
-static int save_trace(struct stackframe *frame, void *d)
+static void start_stack_trace(struct stackframe *frame, struct task_struct *task,
+			      unsigned long fp, unsigned long sp,
+			      unsigned long lr, unsigned long pc)
 {
-	struct stack_trace_data *data = d;
-	struct stack_trace *trace = data->trace;
-	unsigned long addr = frame->pc;
-
-	if (data->no_sched_functions && in_sched_functions(addr))
-		return 0;
-	if (data->skip) {
-		data->skip--;
-		return 0;
-	}
-
-	trace->entries[trace->nr_entries++] = addr;
-	return trace->nr_entries >= trace->max_entries;
+	frame->fp = fp;
+	frame->sp = sp;
+	frame->lr = lr;
+	frame->pc = pc;
+#ifdef CONFIG_KRETPROBES
+	frame->kr_cur = NULL;
+	frame->tsk = task;
+#endif
+#ifdef CONFIG_UNWINDER_FRAME_POINTER
+	frame->ex_frame = in_entry_text(frame->pc);
+#endif
 }
 
-/* This must be noinline to so that our skip calculation works correctly */
-static noinline void __save_stack_trace(struct task_struct *tsk,
-	struct stack_trace *trace, unsigned int nosched)
+void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
+		     struct task_struct *task, struct pt_regs *regs)
 {
-	struct stack_trace_data data;
 	struct stackframe frame;
 
-	data.trace = trace;
-	data.skip = trace->skip;
-	data.no_sched_functions = nosched;
-
-	if (tsk != current) {
+	if (regs) {
+		start_stack_trace(&frame, NULL, regs->ARM_fp, regs->ARM_sp,
+				  regs->ARM_lr, regs->ARM_pc);
+	} else if (task != current) {
 #ifdef CONFIG_SMP
 		/*
 		 * What guarantees do we have here that 'tsk' is not
@@ -185,64 +176,22 @@ static noinline void __save_stack_trace(struct task_struct *tsk,
 		 */
 		return;
 #else
-		frame.fp = thread_saved_fp(tsk);
-		frame.sp = thread_saved_sp(tsk);
-		frame.lr = 0;		/* recovered from the stack */
-		frame.pc = thread_saved_pc(tsk);
+		start_stack_trace(&frame, task, thread_saved_fp(task),
+				  thread_saved_sp(task), 0,
+				  thread_saved_pc(task));
 #endif
 	} else {
-		/* We don't want this function nor the caller */
-		data.skip += 2;
-		frame.fp = (unsigned long)__builtin_frame_address(0);
-		frame.sp = current_stack_pointer;
-		frame.lr = (unsigned long)__builtin_return_address(0);
 here:
-		frame.pc = (unsigned long)&&here;
+		start_stack_trace(&frame, task,
+				  (unsigned long)__builtin_frame_address(0),
+				  current_stack_pointer,
+				  (unsigned long)__builtin_return_address(0),
+				  (unsigned long)&&here);
+		/* skip this function */
+		if (unwind_frame(&frame))
+			return;
 	}
-#ifdef CONFIG_KRETPROBES
-	frame.kr_cur = NULL;
-	frame.tsk = tsk;
-#endif
-#ifdef CONFIG_UNWINDER_FRAME_POINTER
-	frame.ex_frame = false;
-#endif
-
-	walk_stackframe(&frame, save_trace, &data);
-}
-
-void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
-{
-	struct stack_trace_data data;
-	struct stackframe frame;
-
-	data.trace = trace;
-	data.skip = trace->skip;
-	data.no_sched_functions = 0;
-
-	frame.fp = regs->ARM_fp;
-	frame.sp = regs->ARM_sp;
-	frame.lr = regs->ARM_lr;
-	frame.pc = regs->ARM_pc;
-#ifdef CONFIG_KRETPROBES
-	frame.kr_cur = NULL;
-	frame.tsk = current;
-#endif
-#ifdef CONFIG_UNWINDER_FRAME_POINTER
-	frame.ex_frame = in_entry_text(frame.pc);
-#endif
-
-	walk_stackframe(&frame, save_trace, &data);
-}
 
-void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
-{
-	__save_stack_trace(tsk, trace, 1);
-}
-EXPORT_SYMBOL(save_stack_trace_tsk);
-
-void save_stack_trace(struct stack_trace *trace)
-{
-	__save_stack_trace(current, trace, 0);
+	walk_stackframe(&frame, consume_entry, cookie);
 }
-EXPORT_SYMBOL_GPL(save_stack_trace);
 #endif
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
index b74bfcf94fb1..fdce83c95acb 100644
--- a/arch/arm/kernel/swp_emulate.c
+++ b/arch/arm/kernel/swp_emulate.c
@@ -34,6 +34,7 @@
  */
 #define __user_swpX_asm(data, addr, res, temp, B)		\
 	__asm__ __volatile__(					\
+	".arch armv7-a\n"					\
 	"0:	ldrex"B"	%2, [%3]\n"			\
 	"1:	strex"B"	%0, %1, [%3]\n"			\
 	"	cmp		%0, #0\n"			\
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 20b2db6dcd1c..40c7c807d67f 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -178,19 +178,22 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
 	for (i = -4; i < 1 + !!thumb; i++) {
 		unsigned int val, bad;
 
-		if (!user_mode(regs)) {
-			if (thumb) {
-				u16 val16;
-				bad = get_kernel_nofault(val16, &((u16 *)addr)[i]);
-				val = val16;
-			} else {
-				bad = get_kernel_nofault(val, &((u32 *)addr)[i]);
-			}
+		if (thumb) {
+			u16 tmp;
+
+			if (user_mode(regs))
+				bad = get_user(tmp, &((u16 __user *)addr)[i]);
+			else
+				bad = get_kernel_nofault(tmp, &((u16 *)addr)[i]);
+
+			val = __mem_to_opcode_thumb16(tmp);
 		} else {
-			if (thumb)
-				bad = get_user(val, &((u16 *)addr)[i]);
+			if (user_mode(regs))
+				bad = get_user(val, &((u32 __user *)addr)[i]);
 			else
-				bad = get_user(val, &((u32 *)addr)[i]);
+				bad = get_kernel_nofault(val, &((u32 *)addr)[i]);
+
+			val = __mem_to_opcode_arm(val);
 		}
 
 		if (!bad)
diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index a37ea6c772cd..53be7ea6181b 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/list.h>
+#include <linux/module.h>
 
 #include <asm/stacktrace.h>
 #include <asm/traps.h>
@@ -395,8 +396,18 @@ int unwind_frame(struct stackframe *frame)
 
 	idx = unwind_find_idx(frame->pc);
 	if (!idx) {
-		if (frame->pc && kernel_text_address(frame->pc))
+		if (frame->pc && kernel_text_address(frame->pc)) {
+			if (in_module_plt(frame->pc) && frame->pc != frame->lr) {
+				/*
+				 * Quoting Ard: Veneers only set PC using a
+				 * PC+immediate LDR, and so they don't affect
+				 * the state of the stack or the register file
+				 */
+				frame->pc = frame->lr;
+				return URC_OK;
+			}
 			pr_warn("unwind: Index not found %08lx\n", frame->pc);
+		}
 		return -URC_FAILURE;
 	}
 
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index 6d2ba454f25b..650404be6768 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -36,10 +36,6 @@ else
   lib-y	+= io-readsw-armv4.o io-writesw-armv4.o
 endif
 
-ifeq ($(CONFIG_ARCH_RPC),y)
-  AFLAGS_delay-loop.o		+= -march=armv4
-endif
-
 $(obj)/csumpartialcopy.o:	$(obj)/csumpartialcopygeneric.S
 $(obj)/csumpartialcopyuser.o:	$(obj)/csumpartialcopygeneric.S
 
@@ -48,3 +44,5 @@ ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
   CFLAGS_xor-neon.o		+= $(NEON_FLAGS)
   obj-$(CONFIG_XOR_BLOCKS)	+= xor-neon.o
 endif
+
+obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
diff --git a/arch/arm/lib/delay-loop.S b/arch/arm/lib/delay-loop.S
index 3ccade0f8130..3ac05177d097 100644
--- a/arch/arm/lib/delay-loop.S
+++ b/arch/arm/lib/delay-loop.S
@@ -8,6 +8,10 @@
 #include <asm/assembler.h>
 #include <asm/delay.h>
 
+#ifdef CONFIG_ARCH_RPC
+		.arch	armv4
+#endif
+
 		.text
 
 .LC0:		.word	loops_per_jiffy
diff --git a/arch/arm/lib/error-inject.c b/arch/arm/lib/error-inject.c
new file mode 100644
index 000000000000..5a5b405792ba
--- /dev/null
+++ b/arch/arm/lib/error-inject.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/error-injection.h>
+#include <linux/kprobes.h>
+
+void override_function_with_return(struct pt_regs *regs)
+{
+	instruction_pointer_set(regs, regs->ARM_lr);
+}
+NOKPROBE_SYMBOL(override_function_with_return);
diff --git a/arch/arm/lib/findbit.S b/arch/arm/lib/findbit.S
index 7fd3600db8ef..b7ac2d3c0748 100644
--- a/arch/arm/lib/findbit.S
+++ b/arch/arm/lib/findbit.S
@@ -12,182 +12,128 @@
  */
 #include <linux/linkage.h>
 #include <asm/assembler.h>
+#include <asm/unwind.h>
                 .text
 
-/*
- * Purpose  : Find a 'zero' bit
- * Prototype: int find_first_zero_bit(void *addr, unsigned int maxbit);
- */
-ENTRY(_find_first_zero_bit_le)
-		teq	r1, #0	
-		beq	3f
-		mov	r2, #0
-1:
- ARM(		ldrb	r3, [r0, r2, lsr #3]	)
- THUMB(		lsr	r3, r2, #3		)
- THUMB(		ldrb	r3, [r0, r3]		)
-		eors	r3, r3, #0xff		@ invert bits
-		bne	.L_found		@ any now set - found zero bit
-		add	r2, r2, #8		@ next bit pointer
-2:		cmp	r2, r1			@ any more?
-		blo	1b
-3:		mov	r0, r1			@ no free bits
-		ret	lr
-ENDPROC(_find_first_zero_bit_le)
-
-/*
- * Purpose  : Find next 'zero' bit
- * Prototype: int find_next_zero_bit(void *addr, unsigned int maxbit, int offset)
- */
-ENTRY(_find_next_zero_bit_le)
-		cmp	r2, r1
-		bhs	3b
-		ands	ip, r2, #7
-		beq	1b			@ If new byte, goto old routine
- ARM(		ldrb	r3, [r0, r2, lsr #3]	)
- THUMB(		lsr	r3, r2, #3		)
- THUMB(		ldrb	r3, [r0, r3]		)
-		eor	r3, r3, #0xff		@ now looking for a 1 bit
-		movs	r3, r3, lsr ip		@ shift off unused bits
-		bne	.L_found
-		orr	r2, r2, #7		@ if zero, then no bits here
-		add	r2, r2, #1		@ align bit pointer
-		b	2b			@ loop for next bit
-ENDPROC(_find_next_zero_bit_le)
+#ifdef __ARMEB__
+#define SWAB_ENDIAN le
+#else
+#define SWAB_ENDIAN be
+#endif
 
-/*
- * Purpose  : Find a 'one' bit
- * Prototype: int find_first_bit(const unsigned long *addr, unsigned int maxbit);
- */
-ENTRY(_find_first_bit_le)
-		teq	r1, #0	
+		.macro	find_first, endian, set, name
+ENTRY(_find_first_\name\()bit_\endian)
+	UNWIND(	.fnstart)
+		teq	r1, #0
 		beq	3f
 		mov	r2, #0
-1:
- ARM(		ldrb	r3, [r0, r2, lsr #3]	)
- THUMB(		lsr	r3, r2, #3		)
- THUMB(		ldrb	r3, [r0, r3]		)
-		movs	r3, r3
-		bne	.L_found		@ any now set - found zero bit
-		add	r2, r2, #8		@ next bit pointer
+1:		ldr	r3, [r0], #4
+		.ifeq \set
+		mvns	r3, r3			@ invert/test bits
+		.else
+		movs	r3, r3			@ test bits
+		.endif
+		.ifc \endian, SWAB_ENDIAN
+		bne	.L_found_swab
+		.else
+		bne	.L_found		@ found the bit?
+		.endif
+		add	r2, r2, #32		@ next index
 2:		cmp	r2, r1			@ any more?
 		blo	1b
-3:		mov	r0, r1			@ no free bits
+3:		mov	r0, r1			@ no more bits
 		ret	lr
-ENDPROC(_find_first_bit_le)
+	UNWIND(	.fnend)
+ENDPROC(_find_first_\name\()bit_\endian)
+		.endm
 
-/*
- * Purpose  : Find next 'one' bit
- * Prototype: int find_next_zero_bit(void *addr, unsigned int maxbit, int offset)
- */
-ENTRY(_find_next_bit_le)
+		.macro	find_next, endian, set, name
+ENTRY(_find_next_\name\()bit_\endian)
+	UNWIND(	.fnstart)
 		cmp	r2, r1
 		bhs	3b
-		ands	ip, r2, #7
-		beq	1b			@ If new byte, goto old routine
- ARM(		ldrb	r3, [r0, r2, lsr #3]	)
- THUMB(		lsr	r3, r2, #3		)
- THUMB(		ldrb	r3, [r0, r3]		)
+		mov	ip, r2, lsr #5		@ word index
+		add	r0, r0, ip, lsl #2
+		ands	ip, r2, #31		@ bit position
+		beq	1b
+		ldr	r3, [r0], #4
+		.ifeq \set
+		mvn	r3, r3			@ invert bits
+		.endif
+		.ifc \endian, SWAB_ENDIAN
+		rev_l	r3, ip
+		.if	.Lrev_l_uses_tmp
+		@ we need to recompute ip because rev_l will have overwritten
+		@ it.
+		and	ip, r2, #31		@ bit position
+		.endif
+		.endif
 		movs	r3, r3, lsr ip		@ shift off unused bits
 		bne	.L_found
-		orr	r2, r2, #7		@ if zero, then no bits here
+		orr	r2, r2, #31		@ no zero bits
 		add	r2, r2, #1		@ align bit pointer
 		b	2b			@ loop for next bit
-ENDPROC(_find_next_bit_le)
+	UNWIND(	.fnend)
+ENDPROC(_find_next_\name\()bit_\endian)
+		.endm
 
-#ifdef __ARMEB__
+		.macro	find_bit, endian, set, name
+		find_first \endian, \set, \name
+		find_next  \endian, \set, \name
+		.endm
 
-ENTRY(_find_first_zero_bit_be)
-		teq	r1, #0
-		beq	3f
-		mov	r2, #0
-1:		eor	r3, r2, #0x18		@ big endian byte ordering
- ARM(		ldrb	r3, [r0, r3, lsr #3]	)
- THUMB(		lsr	r3, #3			)
- THUMB(		ldrb	r3, [r0, r3]		)
-		eors	r3, r3, #0xff		@ invert bits
-		bne	.L_found		@ any now set - found zero bit
-		add	r2, r2, #8		@ next bit pointer
-2:		cmp	r2, r1			@ any more?
-		blo	1b
-3:		mov	r0, r1			@ no free bits
-		ret	lr
-ENDPROC(_find_first_zero_bit_be)
+/* _find_first_zero_bit_le and _find_next_zero_bit_le */
+		find_bit le, 0, zero_
 
-ENTRY(_find_next_zero_bit_be)
-		cmp	r2, r1
-		bhs	3b
-		ands	ip, r2, #7
-		beq	1b			@ If new byte, goto old routine
-		eor	r3, r2, #0x18		@ big endian byte ordering
- ARM(		ldrb	r3, [r0, r3, lsr #3]	)
- THUMB(		lsr	r3, #3			)
- THUMB(		ldrb	r3, [r0, r3]		)
-		eor	r3, r3, #0xff		@ now looking for a 1 bit
-		movs	r3, r3, lsr ip		@ shift off unused bits
-		bne	.L_found
-		orr	r2, r2, #7		@ if zero, then no bits here
-		add	r2, r2, #1		@ align bit pointer
-		b	2b			@ loop for next bit
-ENDPROC(_find_next_zero_bit_be)
+/* _find_first_bit_le and _find_next_bit_le */
+		find_bit le, 1
 
-ENTRY(_find_first_bit_be)
-		teq	r1, #0
-		beq	3f
-		mov	r2, #0
-1:		eor	r3, r2, #0x18		@ big endian byte ordering
- ARM(		ldrb	r3, [r0, r3, lsr #3]	)
- THUMB(		lsr	r3, #3			)
- THUMB(		ldrb	r3, [r0, r3]		)
-		movs	r3, r3
-		bne	.L_found		@ any now set - found zero bit
-		add	r2, r2, #8		@ next bit pointer
-2:		cmp	r2, r1			@ any more?
-		blo	1b
-3:		mov	r0, r1			@ no free bits
-		ret	lr
-ENDPROC(_find_first_bit_be)
+#ifdef __ARMEB__
 
-ENTRY(_find_next_bit_be)
-		cmp	r2, r1
-		bhs	3b
-		ands	ip, r2, #7
-		beq	1b			@ If new byte, goto old routine
-		eor	r3, r2, #0x18		@ big endian byte ordering
- ARM(		ldrb	r3, [r0, r3, lsr #3]	)
- THUMB(		lsr	r3, #3			)
- THUMB(		ldrb	r3, [r0, r3]		)
-		movs	r3, r3, lsr ip		@ shift off unused bits
-		bne	.L_found
-		orr	r2, r2, #7		@ if zero, then no bits here
-		add	r2, r2, #1		@ align bit pointer
-		b	2b			@ loop for next bit
-ENDPROC(_find_next_bit_be)
+/* _find_first_zero_bit_be and _find_next_zero_bit_be */
+		find_bit be, 0, zero_
+
+/* _find_first_bit_be and _find_next_bit_be */
+		find_bit be, 1
 
 #endif
 
 /*
  * One or more bits in the LSB of r3 are assumed to be set.
  */
+.L_found_swab:
+	UNWIND(	.fnstart)
+		rev_l	r3, ip
 .L_found:
-#if __LINUX_ARM_ARCH__ >= 5
+#if __LINUX_ARM_ARCH__ >= 7
+		rbit	r3, r3			@ reverse bits
+		clz	r3, r3			@ count high zero bits
+		add	r0, r2, r3		@ add offset of first set bit
+#elif __LINUX_ARM_ARCH__ >= 5
 		rsb	r0, r3, #0
-		and	r3, r3, r0
-		clz	r3, r3
-		rsb	r3, r3, #31
-		add	r0, r2, r3
+		and	r3, r3, r0		@ mask out lowest bit set
+		clz	r3, r3			@ count high zero bits
+		rsb	r3, r3, #31		@ offset of first set bit
+		add	r0, r2, r3		@ add offset of first set bit
 #else
-		tst	r3, #0x0f
+		mov	ip, #~0
+		tst	r3, ip, lsr #16		@ test bits 0-15
+		addeq	r2, r2, #16
+		moveq	r3, r3, lsr #16
+		tst	r3, #0x00ff
+		addeq	r2, r2, #8
+		moveq	r3, r3, lsr #8
+		tst	r3, #0x000f
 		addeq	r2, r2, #4
-		movne	r3, r3, lsl #4
-		tst	r3, #0x30
+		moveq	r3, r3, lsr #4
+		tst	r3, #0x0003
 		addeq	r2, r2, #2
-		movne	r3, r3, lsl #2
-		tst	r3, #0x40
+		moveq	r3, r3, lsr #2
+		tst	r3, #0x0001
 		addeq	r2, r2, #1
 		mov	r0, r2
 #endif
 		cmp	r1, r0			@ Clamp to maxbit
 		movlo	r0, r1
 		ret	lr
-
+	UNWIND(	.fnend)
diff --git a/arch/arm/mach-at91/Makefile b/arch/arm/mach-at91/Makefile
index 0dcc37180588..794bd12ab0a8 100644
--- a/arch/arm/mach-at91/Makefile
+++ b/arch/arm/mach-at91/Makefile
@@ -14,9 +14,6 @@ obj-$(CONFIG_SOC_SAMV7)		+= samv7.o
 # Power Management
 obj-$(CONFIG_ATMEL_PM)		+= pm.o pm_suspend.o
 
-ifeq ($(CONFIG_CPU_V7),y)
-AFLAGS_pm_suspend.o := -march=armv7-a
-endif
 ifeq ($(CONFIG_PM_DEBUG),y)
 CFLAGS_pm.o += -DDEBUG
 endif
diff --git a/arch/arm/mach-at91/pm_suspend.S b/arch/arm/mach-at91/pm_suspend.S
index e4904faf1753..e5869cca5e79 100644
--- a/arch/arm/mach-at91/pm_suspend.S
+++ b/arch/arm/mach-at91/pm_suspend.S
@@ -12,6 +12,10 @@
 #include "pm.h"
 #include "pm_data-offsets.h"
 
+#ifdef CONFIG_CPU_V7
+.arch armv7-a
+#endif
+
 #define	SRAMC_SELF_FRESH_ACTIVE		0x01
 #define	SRAMC_SELF_FRESH_EXIT		0x00
 
diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile
index 6fb3965b9ae6..5c650bf40e02 100644
--- a/arch/arm/mach-imx/Makefile
+++ b/arch/arm/mach-imx/Makefile
@@ -34,7 +34,6 @@ obj-$(CONFIG_HAVE_IMX_GPC) += gpc.o
 obj-$(CONFIG_HAVE_IMX_MMDC) += mmdc.o
 obj-$(CONFIG_HAVE_IMX_SRC) += src.o
 ifneq ($(CONFIG_SOC_IMX6)$(CONFIG_SOC_IMX7D_CA7)$(CONFIG_SOC_LS1021A),)
-AFLAGS_headsmp.o :=-Wa,-march=armv7-a
 obj-$(CONFIG_SMP) += headsmp.o platsmp.o
 obj-$(CONFIG_HOTPLUG_CPU) += hotplug.o
 endif
@@ -48,12 +47,10 @@ obj-$(CONFIG_SOC_IMX7D_CM4) += mach-imx7d-cm4.o
 obj-$(CONFIG_SOC_IMX7ULP) += mach-imx7ulp.o pm-imx7ulp.o
 
 ifeq ($(CONFIG_SUSPEND),y)
-AFLAGS_suspend-imx6.o :=-Wa,-march=armv7-a
 obj-$(CONFIG_SOC_IMX6) += suspend-imx6.o
 obj-$(CONFIG_SOC_IMX53) += suspend-imx53.o
 endif
 ifeq ($(CONFIG_ARM_CPU_SUSPEND),y)
-AFLAGS_resume-imx6.o :=-Wa,-march=armv7-a
 obj-$(CONFIG_SOC_IMX6) += resume-imx6.o
 endif
 obj-$(CONFIG_SOC_IMX6) += pm-imx6.o
diff --git a/arch/arm/mach-imx/headsmp.S b/arch/arm/mach-imx/headsmp.S
index fcba58be8e79..5f9c7b48ae80 100644
--- a/arch/arm/mach-imx/headsmp.S
+++ b/arch/arm/mach-imx/headsmp.S
@@ -8,6 +8,8 @@
 #include <linux/init.h>
 #include <asm/assembler.h>
 
+.arch armv7-a
+
 diag_reg_offset:
 	.word	g_diag_reg - .
 
diff --git a/arch/arm/mach-imx/resume-imx6.S b/arch/arm/mach-imx/resume-imx6.S
index 5bd1ba7ef15b..2c0c5c771251 100644
--- a/arch/arm/mach-imx/resume-imx6.S
+++ b/arch/arm/mach-imx/resume-imx6.S
@@ -9,6 +9,8 @@
 #include <asm/hardware/cache-l2x0.h>
 #include "hardware.h"
 
+.arch armv7-a
+
 /*
  * The following code must assume it is running from physical address
  * where absolute virtual addresses to the data section have to be
diff --git a/arch/arm/mach-imx/suspend-imx6.S b/arch/arm/mach-imx/suspend-imx6.S
index e06f946b75b9..63ccc2d0e920 100644
--- a/arch/arm/mach-imx/suspend-imx6.S
+++ b/arch/arm/mach-imx/suspend-imx6.S
@@ -9,6 +9,8 @@
 #include <asm/hardware/cache-l2x0.h>
 #include "hardware.h"
 
+.arch armv7-a
+
 /*
  * ==================== low level suspend ====================
  *
diff --git a/arch/arm/mach-mvebu/Makefile b/arch/arm/mach-mvebu/Makefile
index c21733cbb4fa..569768a69ffc 100644
--- a/arch/arm/mach-mvebu/Makefile
+++ b/arch/arm/mach-mvebu/Makefile
@@ -1,9 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 ccflags-y := -I$(srctree)/arch/arm/plat-orion/include
 
-AFLAGS_coherency_ll.o		:= -Wa,-march=armv7-a
-CFLAGS_pmsu.o			:= -march=armv7-a
-
 obj-$(CONFIG_MACH_MVEBU_ANY)	 += system-controller.o mvebu-soc-id.o
 
 ifeq ($(CONFIG_MACH_MVEBU_V7),y)
diff --git a/arch/arm/mach-mvebu/coherency_ll.S b/arch/arm/mach-mvebu/coherency_ll.S
index eb81656e32d4..35930e03d9c6 100644
--- a/arch/arm/mach-mvebu/coherency_ll.S
+++ b/arch/arm/mach-mvebu/coherency_ll.S
@@ -20,6 +20,7 @@
 #include <asm/assembler.h>
 #include <asm/cp15.h>
 
+	.arch armv7-a
 	.text
 /*
  * Returns the coherency base address in r1 (r0 is untouched), or 0 if
diff --git a/arch/arm/mach-mvebu/pmsu.c b/arch/arm/mach-mvebu/pmsu.c
index af27a7156675..6f366d8c4231 100644
--- a/arch/arm/mach-mvebu/pmsu.c
+++ b/arch/arm/mach-mvebu/pmsu.c
@@ -291,6 +291,7 @@ int armada_370_xp_pmsu_idle_enter(unsigned long deepidle)
 
 	/* Test the CR_C bit and set it if it was cleared */
 	asm volatile(
+	".arch	armv7-a\n\t"
 	"mrc	p15, 0, r0, c1, c0, 0 \n\t"
 	"tst	r0, %0 \n\t"
 	"orreq	r0, r0, #(1 << 2) \n\t"
diff --git a/arch/arm/mach-npcm/Makefile b/arch/arm/mach-npcm/Makefile
index 8d61fcd42fb1..ac83e1caf2ee 100644
--- a/arch/arm/mach-npcm/Makefile
+++ b/arch/arm/mach-npcm/Makefile
@@ -1,6 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-AFLAGS_headsmp.o		+= -march=armv7-a
-
 obj-$(CONFIG_ARCH_WPCM450)	+= wpcm450.o
 obj-$(CONFIG_ARCH_NPCM7XX)	+= npcm7xx.o
 obj-$(CONFIG_SMP)		+= platsmp.o headsmp.o
diff --git a/arch/arm/mach-npcm/headsmp.S b/arch/arm/mach-npcm/headsmp.S
index c083fe09a07b..84d2b6daaf0b 100644
--- a/arch/arm/mach-npcm/headsmp.S
+++ b/arch/arm/mach-npcm/headsmp.S
@@ -6,6 +6,8 @@
 #include <linux/init.h>
 #include <asm/assembler.h>
 
+.arch armv7-a
+
 /*
  * The boot ROM does not start secondary CPUs in SVC mode, so we need to do that
  * here.
diff --git a/arch/arm/mach-tegra/Makefile b/arch/arm/mach-tegra/Makefile
index 07572b5373b8..a2bb55bc0081 100644
--- a/arch/arm/mach-tegra/Makefile
+++ b/arch/arm/mach-tegra/Makefile
@@ -1,6 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-asflags-y				+= -march=armv7-a
-
 obj-y                                   += io.o
 obj-y                                   += irq.o
 obj-y					+= pm.o
diff --git a/arch/arm/mach-tegra/reset-handler.S b/arch/arm/mach-tegra/reset-handler.S
index 06ca44b09381..0ea456264f3e 100644
--- a/arch/arm/mach-tegra/reset-handler.S
+++ b/arch/arm/mach-tegra/reset-handler.S
@@ -19,6 +19,8 @@
 
 #define PMC_SCRATCH41	0x140
 
+.arch armv7-a
+
 #ifdef CONFIG_PM_SLEEP
 /*
  *	tegra_resume
diff --git a/arch/arm/mach-tegra/sleep-tegra20.S b/arch/arm/mach-tegra/sleep-tegra20.S
index a5a36cce142a..d8cd487a8f63 100644
--- a/arch/arm/mach-tegra/sleep-tegra20.S
+++ b/arch/arm/mach-tegra/sleep-tegra20.S
@@ -47,6 +47,8 @@
 #define PLLM_STORE_MASK			(1 << 1)
 #define PLLP_STORE_MASK			(1 << 2)
 
+.arch armv7-a
+
 .macro test_pll_state, rd, test_mask
 	ldr	\rd, tegra_pll_state
 	tst	\rd, #\test_mask
diff --git a/arch/arm/mach-tegra/sleep-tegra30.S b/arch/arm/mach-tegra/sleep-tegra30.S
index 0cc40b6b2ba3..134ea5fe49b2 100644
--- a/arch/arm/mach-tegra/sleep-tegra30.S
+++ b/arch/arm/mach-tegra/sleep-tegra30.S
@@ -78,6 +78,8 @@
 #define PLLX_STORE_MASK			(1 << 4)
 #define PLLM_PMC_STORE_MASK		(1 << 5)
 
+.arch armv7-a
+
 .macro emc_device_mask, rd, base
 	ldr	\rd, [\base, #EMC_ADR_CFG]
 	tst	\rd, #0x1
diff --git a/arch/arm/mach-tegra/sleep.S b/arch/arm/mach-tegra/sleep.S
index 8f88944831c5..945f2c1474f7 100644
--- a/arch/arm/mach-tegra/sleep.S
+++ b/arch/arm/mach-tegra/sleep.S
@@ -22,6 +22,8 @@
 #define CLK_RESET_CCLK_BURST	0x20
 #define CLK_RESET_CCLK_DIVIDER  0x24
 
+.arch armv7-a
+
 #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PM_SLEEP)
 /*
  * tegra_disable_clean_inv_dcache
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 3510503bc5e6..71b858c9b10c 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -33,9 +33,6 @@ obj-$(CONFIG_CPU_ABRT_EV5TJ)	+= abort-ev5tj.o
 obj-$(CONFIG_CPU_ABRT_EV6)	+= abort-ev6.o
 obj-$(CONFIG_CPU_ABRT_EV7)	+= abort-ev7.o
 
-AFLAGS_abort-ev6.o	:=-Wa,-march=armv6k
-AFLAGS_abort-ev7.o	:=-Wa,-march=armv7-a
-
 obj-$(CONFIG_CPU_PABRT_LEGACY)	+= pabort-legacy.o
 obj-$(CONFIG_CPU_PABRT_V6)	+= pabort-v6.o
 obj-$(CONFIG_CPU_PABRT_V7)	+= pabort-v7.o
@@ -49,10 +46,6 @@ obj-$(CONFIG_CPU_CACHE_FA)	+= cache-fa.o
 obj-$(CONFIG_CPU_CACHE_NOP)	+= cache-nop.o
 obj-$(CONFIG_CPU_CACHE_V7M)	+= cache-v7m.o
 
-AFLAGS_cache-v6.o	:=-Wa,-march=armv6
-AFLAGS_cache-v7.o	:=-Wa,-march=armv7-a
-AFLAGS_cache-v7m.o	:=-Wa,-march=armv7-m
-
 obj-$(CONFIG_CPU_COPY_V4WT)	+= copypage-v4wt.o
 obj-$(CONFIG_CPU_COPY_V4WB)	+= copypage-v4wb.o
 obj-$(CONFIG_CPU_COPY_FEROCEON)	+= copypage-feroceon.o
@@ -62,8 +55,6 @@ obj-$(CONFIG_CPU_XSCALE)	+= copypage-xscale.o
 obj-$(CONFIG_CPU_XSC3)		+= copypage-xsc3.o
 obj-$(CONFIG_CPU_COPY_FA)	+= copypage-fa.o
 
-CFLAGS_copypage-feroceon.o := -march=armv5te
-
 obj-$(CONFIG_CPU_TLB_V4WT)	+= tlb-v4.o
 obj-$(CONFIG_CPU_TLB_V4WB)	+= tlb-v4wb.o
 obj-$(CONFIG_CPU_TLB_V4WBI)	+= tlb-v4wbi.o
@@ -72,9 +63,6 @@ obj-$(CONFIG_CPU_TLB_V6)	+= tlb-v6.o
 obj-$(CONFIG_CPU_TLB_V7)	+= tlb-v7.o
 obj-$(CONFIG_CPU_TLB_FA)	+= tlb-fa.o
 
-AFLAGS_tlb-v6.o		:=-Wa,-march=armv6
-AFLAGS_tlb-v7.o		:=-Wa,-march=armv7-a
-
 obj-$(CONFIG_CPU_ARM7TDMI)	+= proc-arm7tdmi.o
 obj-$(CONFIG_CPU_ARM720T)	+= proc-arm720.o
 obj-$(CONFIG_CPU_ARM740T)	+= proc-arm740.o
@@ -101,9 +89,6 @@ obj-$(CONFIG_CPU_V6K)		+= proc-v6.o
 obj-$(CONFIG_CPU_V7)		+= proc-v7.o proc-v7-bugs.o
 obj-$(CONFIG_CPU_V7M)		+= proc-v7m.o
 
-AFLAGS_proc-v6.o	:=-Wa,-march=armv6
-AFLAGS_proc-v7.o	:=-Wa,-march=armv7-a
-
 obj-$(CONFIG_OUTER_CACHE)	+= l2c-common.o
 obj-$(CONFIG_CACHE_B15_RAC)	+= cache-b15-rac.o
 obj-$(CONFIG_CACHE_FEROCEON_L2)	+= cache-feroceon-l2.o
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index c58bf8b43fea..836dc1299243 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -16,6 +16,7 @@
  * abort here if the I-TLB and D-TLB aren't seeing the same
  * picture.  Unfortunately, this does happen.  We live with it.
  */
+	.arch	armv6k
 	.align	5
 ENTRY(v6_early_abort)
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S
index f81bceacc660..53fb41c24774 100644
--- a/arch/arm/mm/abort-ev7.S
+++ b/arch/arm/mm/abort-ev7.S
@@ -12,6 +12,7 @@
  *
  * Purpose : obtain information about current aborted instruction.
  */
+	.arch	armv7-a
 	.align	5
 ENTRY(v7_early_abort)
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index f0f65eb073e4..250c83bf7158 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -19,6 +19,8 @@
 #define D_CACHE_LINE_SIZE	32
 #define BTB_FLUSH_SIZE		8
 
+.arch armv6
+
 /*
  *	v6_flush_icache_all()
  *
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 7c9499b728c4..127afe2096ba 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -16,6 +16,8 @@
 
 #include "proc-macros.S"
 
+.arch armv7-a
+
 #ifdef CONFIG_CPU_ICACHE_MISMATCH_WORKAROUND
 .globl icache_size
 	.data
diff --git a/arch/arm/mm/cache-v7m.S b/arch/arm/mm/cache-v7m.S
index 1bc3a0a50753..eb60b5e5e2ad 100644
--- a/arch/arm/mm/cache-v7m.S
+++ b/arch/arm/mm/cache-v7m.S
@@ -18,6 +18,8 @@
 
 #include "proc-macros.S"
 
+.arch armv7-m
+
 /* Generic V7M read/write macros for memory mapped cache operations */
 .macro v7m_cache_read, rt, reg
 	movw	\rt, #:lower16:BASEADDR_V7M_SCB + \reg
diff --git a/arch/arm/mm/copypage-feroceon.c b/arch/arm/mm/copypage-feroceon.c
index 064b19e63571..5fc8ef1e665f 100644
--- a/arch/arm/mm/copypage-feroceon.c
+++ b/arch/arm/mm/copypage-feroceon.c
@@ -15,6 +15,7 @@ static void feroceon_copy_user_page(void *kto, const void *kfrom)
 	int tmp;
 
 	asm volatile ("\
+.arch	armv5te					\n\
 1:	ldmia	%1!, {r2 - r7, ip, lr}		\n\
 	pld	[%1, #0]			\n\
 	pld	[%1, #32]			\n\
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index de988cba9a4b..2418f1efabd8 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -124,8 +124,9 @@ static void die_kernel_fault(const char *msg, struct mm_struct *mm,
 {
 	bust_spinlocks(1);
 	pr_alert("8<--- cut here ---\n");
-	pr_alert("Unable to handle kernel %s at virtual address %08lx\n",
-		 msg, addr);
+	pr_alert("Unable to handle kernel %s at virtual address %08lx when %s\n",
+		 msg, addr, fsr & FSR_LNX_PF ? "execute" :
+		 fsr & FSR_WRITE ? "write" : "read");
 
 	show_pte(KERN_ALERT, mm, addr);
 	die("Oops", regs, fsr);
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index a0618f3e6836..203dff89ab1a 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -32,6 +32,8 @@
 #define TTB_FLAGS_SMP	TTB_RGN_WBWA|TTB_S
 #define PMD_FLAGS_SMP	PMD_SECT_WBWA|PMD_SECT_S
 
+.arch armv6
+
 ENTRY(cpu_v6_proc_init)
 	ret	lr
 
diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
index 5db029c8f987..0a3083ad19c2 100644
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -24,6 +24,8 @@
 #define TTB_FLAGS_SMP	TTB_IRGN_WBWA|TTB_S|TTB_NOS|TTB_RGN_OC_WBWA
 #define PMD_FLAGS_SMP	PMD_SECT_WBWA|PMD_SECT_S
 
+.arch armv7-a
+
 /*
  *	cpu_v7_switch_mm(pgd_phys, tsk)
  *
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 26d726a08a34..6b4ef9539b68 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -24,6 +24,8 @@
 #include "proc-v7-2level.S"
 #endif
 
+.arch armv7-a
+
 ENTRY(cpu_v7_proc_init)
 	ret	lr
 ENDPROC(cpu_v7_proc_init)
diff --git a/arch/arm/mm/tlb-v6.S b/arch/arm/mm/tlb-v6.S
index 74f4b383afe3..1d91e49b2c2d 100644
--- a/arch/arm/mm/tlb-v6.S
+++ b/arch/arm/mm/tlb-v6.S
@@ -17,6 +17,8 @@
 
 #define HARVARD_TLB
 
+.arch armv6
+
 /*
  *	v6wbi_flush_user_tlb_range(start, end, vma)
  *
diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S
index 87bf4ab17721..35fd6d4f0d03 100644
--- a/arch/arm/mm/tlb-v7.S
+++ b/arch/arm/mm/tlb-v7.S
@@ -16,6 +16,8 @@
 #include <asm/tlbflush.h>
 #include "proc-macros.S"
 
+.arch armv7-a
+
 /*
  *	v7wbi_flush_user_tlb_range(start, end, vma)
  *
diff --git a/arch/arm/nwfpe/Makefile b/arch/arm/nwfpe/Makefile
index 303400fa2cdf..2aec85ab1e8b 100644
--- a/arch/arm/nwfpe/Makefile
+++ b/arch/arm/nwfpe/Makefile
@@ -11,3 +11,9 @@ nwfpe-y				+= fpa11.o fpa11_cpdo.o fpa11_cpdt.o \
 				   entry.o
 
 nwfpe-$(CONFIG_FPE_NWFPE_XP)	+= extended_cpdo.o
+
+# Try really hard to avoid generating calls to __aeabi_uldivmod() from
+# float64_rem() due to loop elision.
+ifdef CONFIG_CC_IS_CLANG
+CFLAGS_softfloat.o	+= -mllvm -replexitval=never
+endif
diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile
index 8ca1c9f262a2..a7ec06ce3785 100644
--- a/arch/arm/vdso/Makefile
+++ b/arch/arm/vdso/Makefile
@@ -37,6 +37,7 @@ endif
 
 # Disable gcov profiling for VDSO code
 GCOV_PROFILE := n
+UBSAN_SANITIZE := n
 
 # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
 KCOV_INSTRUMENT := n
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 2cb355c1b5b7..281110423871 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -774,6 +774,7 @@ static int __init vfp_init(void)
 {
 	unsigned int vfpsid;
 	unsigned int cpu_arch = cpu_architecture();
+	unsigned int isar6;
 
 	/*
 	 * Enable the access to the VFP on all online CPUs so the
@@ -831,7 +832,38 @@ static int __init vfp_init(void)
 
 			if ((fmrx(MVFR1) & 0xf0000000) == 0x10000000)
 				elf_hwcap |= HWCAP_VFPv4;
+			if (((fmrx(MVFR1) & MVFR1_ASIMDHP_MASK) >> MVFR1_ASIMDHP_BIT) == 0x2)
+				elf_hwcap |= HWCAP_ASIMDHP;
+			if (((fmrx(MVFR1) & MVFR1_FPHP_MASK) >> MVFR1_FPHP_BIT) == 0x3)
+				elf_hwcap |= HWCAP_FPHP;
 		}
+
+		/*
+		 * Check for the presence of Advanced SIMD Dot Product
+		 * instructions.
+		 */
+		isar6 = read_cpuid_ext(CPUID_EXT_ISAR6);
+		if (cpuid_feature_extract_field(isar6, 4) == 0x1)
+			elf_hwcap |= HWCAP_ASIMDDP;
+		/*
+		 * Check for the presence of Advanced SIMD Floating point
+		 * half-precision multiplication instructions.
+		 */
+		if (cpuid_feature_extract_field(isar6, 8) == 0x1)
+			elf_hwcap |= HWCAP_ASIMDFHM;
+		/*
+		 * Check for the presence of Advanced SIMD Bfloat16
+		 * floating point instructions.
+		 */
+		if (cpuid_feature_extract_field(isar6, 20) == 0x1)
+			elf_hwcap |= HWCAP_ASIMDBF16;
+		/*
+		 * Check for the presence of Advanced SIMD and floating point
+		 * Int8 matrix multiplication instructions instructions.
+		 */
+		if (cpuid_feature_extract_field(isar6, 24) == 0x1)
+			elf_hwcap |= HWCAP_I8MM;
+
 	/* Extract the architecture version on pre-cpuid scheme */
 	} else {
 		if (vfpsid & FPSID_NODOUBLE) {