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
  ...

12 files changed, 111 insertions, 111 deletions

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;
 	}