22 files changed, 172 insertions, 208 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/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 2c8d76fd7c66..38121c59cbc2 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -56,6 +56,7 @@ int main(void)
   DEFINE(VFP_CPU,		offsetof(union vfp_state, hard.cpu));
 #endif
 #endif
+  DEFINE(SOFTIRQ_DISABLE_OFFSET,SOFTIRQ_DISABLE_OFFSET);
 #ifdef CONFIG_ARM_THUMBEE
   DEFINE(TI_THUMBEE_STATE,	offsetof(struct thread_info, thumbee_state));
 #endif
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index e7ef2b5bea9c..d334c7fb672b 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -142,15 +142,15 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_WINBOND2, PCI_DEVICE_ID_WINBOND2_89C940F,
  */
 static void pci_fixup_dec21285(struct pci_dev *dev)
 {
-	int i;
-
 	if (dev->devfn == 0) {
+		struct resource *r;
+
 		dev->class &= 0xff;
 		dev->class |= PCI_CLASS_BRIDGE_HOST << 8;
-		for (i = 0; i < PCI_NUM_RESOURCES; i++) {
-			dev->resource[i].start = 0;
-			dev->resource[i].end   = 0;
-			dev->resource[i].flags = 0;
+		pci_dev_for_each_resource(dev, r) {
+			r->start = 0;
+			r->end = 0;
+			r->flags = 0;
 		}
 	}
 }
@@ -162,13 +162,11 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_DEC, PCI_DEVICE_ID_DEC_21285, pci_fixup_d
 static void pci_fixup_ide_bases(struct pci_dev *dev)
 {
 	struct resource *r;
-	int i;
 
 	if ((dev->class >> 8) != PCI_CLASS_STORAGE_IDE)
 		return;
 
-	for (i = 0; i < PCI_NUM_RESOURCES; i++) {
-		r = dev->resource + i;
+	pci_dev_for_each_resource(dev, r) {
 		if ((r->start & ~0x80) == 0x374) {
 			r->start |= 2;
 			r->end = r->start;
diff --git a/arch/arm/kernel/cpuidle.c b/arch/arm/kernel/cpuidle.c
index e1684623e1b2..fba1f8bb03b5 100644
--- a/arch/arm/kernel/cpuidle.c
+++ b/arch/arm/kernel/cpuidle.c
@@ -5,7 +5,6 @@
 
 #include <linux/cpuidle.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <asm/cpuidle.h>
 
 extern struct of_cpuidle_method __cpuidle_method_of_table[];
@@ -26,8 +25,8 @@ static struct cpuidle_ops cpuidle_ops[NR_CPUS] __ro_after_init;
  *
  * Returns the index passed as parameter
  */
-int arm_cpuidle_simple_enter(struct cpuidle_device *dev,
-		struct cpuidle_driver *drv, int index)
+__cpuidle int arm_cpuidle_simple_enter(struct cpuidle_device *dev, struct
+				       cpuidle_driver *drv, int index)
 {
 	cpu_do_idle();
 
diff --git a/arch/arm/kernel/efi.c b/arch/arm/kernel/efi.c
index e50ad7eefc02..e2b9d2618c67 100644
--- a/arch/arm/kernel/efi.c
+++ b/arch/arm/kernel/efi.c
@@ -23,7 +23,8 @@ static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data)
 }
 
 int __init efi_set_mapping_permissions(struct mm_struct *mm,
-				       efi_memory_desc_t *md)
+				       efi_memory_desc_t *md,
+				       bool ignored)
 {
 	unsigned long base, size;
 
@@ -71,42 +72,17 @@ int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
 	 * If stricter permissions were specified, apply them now.
 	 */
 	if (md->attribute & (EFI_MEMORY_RO | EFI_MEMORY_XP))
-		return efi_set_mapping_permissions(mm, md);
+		return efi_set_mapping_permissions(mm, md, false);
 	return 0;
 }
 
-static unsigned long __initdata screen_info_table = EFI_INVALID_TABLE_ADDR;
 static unsigned long __initdata cpu_state_table = EFI_INVALID_TABLE_ADDR;
 
 const efi_config_table_type_t efi_arch_tables[] __initconst = {
-	{LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID, &screen_info_table},
 	{LINUX_EFI_ARM_CPU_STATE_TABLE_GUID, &cpu_state_table},
 	{}
 };
 
-static void __init load_screen_info_table(void)
-{
-	struct screen_info *si;
-
-	if (screen_info_table != EFI_INVALID_TABLE_ADDR) {
-		si = early_memremap_ro(screen_info_table, sizeof(*si));
-		if (!si) {
-			pr_err("Could not map screen_info config table\n");
-			return;
-		}
-		screen_info = *si;
-		early_memunmap(si, sizeof(*si));
-
-		/* dummycon on ARM needs non-zero values for columns/lines */
-		screen_info.orig_video_cols = 80;
-		screen_info.orig_video_lines = 25;
-
-		if (memblock_is_map_memory(screen_info.lfb_base))
-			memblock_mark_nomap(screen_info.lfb_base,
-					    screen_info.lfb_size);
-	}
-}
-
 static void __init load_cpu_state_table(void)
 {
 	if (cpu_state_table != EFI_INVALID_TABLE_ADDR) {
@@ -145,7 +121,11 @@ void __init arm_efi_init(void)
 {
 	efi_init();
 
-	load_screen_info_table();
+	if (screen_info.orig_video_isVGA == VIDEO_TYPE_EFI) {
+		/* dummycon on ARM needs non-zero values for columns/lines */
+		screen_info.orig_video_cols = 80;
+		screen_info.orig_video_lines = 25;
+	}
 
 	/* ARM does not permit early mappings to persist across paging_init() */
 	efi_memmap_unmap();
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 405a607b754f..03d4c5578c5c 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -16,15 +16,6 @@
 
 	.equ	NR_syscalls, __NR_syscalls
 
-	.macro  arch_ret_to_user, tmp
-#ifdef CONFIG_ARCH_IOP32X
-	mrc	p15, 0, \tmp, c15, c1, 0
-	tst	\tmp, #(1 << 6)
-	bicne	\tmp, \tmp, #(1 << 6)
-	mcrne	p15, 0, \tmp, c15, c1, 0	@ Disable cp6 access
-#endif
-	.endm
-
 #include "entry-header.S"
 
 saved_psr	.req	r8
@@ -55,10 +46,6 @@ __ret_fast_syscall:
 	movs	r1, r1, lsl #16
 	bne	fast_work_pending
 
-
-	/* perform architecture specific actions before user return */
-	arch_ret_to_user r1
-
 	restore_user_regs fast = 1, offset = S_OFF
  UNWIND(.fnend		)
 ENDPROC(ret_fast_syscall)
@@ -129,8 +116,6 @@ ENTRY(ret_to_user_from_irq)
 no_work_pending:
 	asm_trace_hardirqs_on save = 0
 
-	/* perform architecture specific actions before user return */
-	arch_ret_to_user r1
 	ct_user_enter save = 0
 
 	restore_user_regs fast = 0, offset = 0
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 29e2900178a1..656991055bc1 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -344,7 +344,7 @@ __create_page_tables:
 	ldr	r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags
 #endif
 
-#if defined(CONFIG_ARCH_NETWINDER) || defined(CONFIG_ARCH_CATS)
+#if defined(CONFIG_ARCH_NETWINDER)
 	/*
 	 * If we're using the NetWinder or CATS, we also need to map
 	 * in the 16550-type serial port for the debug messages
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/isa.c b/arch/arm/kernel/isa.c
index d8a509c5d5bd..20218876bef2 100644
--- a/arch/arm/kernel/isa.c
+++ b/arch/arm/kernel/isa.c
@@ -40,27 +40,11 @@ static struct ctl_table ctl_isa_vars[4] = {
 
 static struct ctl_table_header *isa_sysctl_header;
 
-static struct ctl_table ctl_isa[2] = {
-	{
-		.procname	= "isa",
-		.mode		= 0555,
-		.child		= ctl_isa_vars,
-	}, {}
-};
-
-static struct ctl_table ctl_bus[2] = {
-	{
-		.procname	= "bus",
-		.mode		= 0555,
-		.child		= ctl_isa,
-	}, {}
-};
-
 void __init
 register_isa_ports(unsigned int membase, unsigned int portbase, unsigned int portshift)
 {
 	isa_membase = membase;
 	isa_portbase = portbase;
 	isa_portshift = portshift;
-	isa_sysctl_header = register_sysctl_table(ctl_bus);
+	isa_sysctl_header = register_sysctl("bus/isa", ctl_isa_vars);
 }
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index f567032a09c0..46364b699cc3 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -73,10 +73,12 @@ void machine_kexec_cleanup(struct kimage *image)
 {
 }
 
-void machine_crash_nonpanic_core(void *unused)
+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..f5a43fd8c163 100644
--- a/arch/arm/kernel/module-plts.c
+++ b/arch/arm/kernel/module-plts.c
@@ -28,11 +28,6 @@ static const u32 fixed_plts[] = {
 #endif
 };
 
-static bool in_init(const struct module *mod, unsigned long loc)
-{
-	return loc - (u32)mod->init_layout.base < mod->init_layout.size;
-}
-
 static void prealloc_fixed(struct mod_plt_sec *pltsec, struct plt_entries *plt)
 {
 	int i;
@@ -50,8 +45,8 @@ static void prealloc_fixed(struct mod_plt_sec *pltsec, struct plt_entries *plt)
 
 u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val)
 {
-	struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core :
-							  &mod->arch.init;
+	struct mod_plt_sec *pltsec = !within_module_init(loc, mod) ?
+						&mod->arch.core : &mod->arch.init;
 	struct plt_entries *plt;
 	int idx;
 
@@ -284,3 +279,17 @@ 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/process.c b/arch/arm/kernel/process.c
index a2b31d91a1b6..0e8ff85890ad 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -78,7 +78,6 @@ void arch_cpu_idle(void)
 		arm_pm_idle();
 	else
 		cpu_do_idle();
-	raw_local_irq_enable();
 }
 
 void arch_cpu_idle_prepare(void)
@@ -316,7 +315,7 @@ static int __init gate_vma_init(void)
 	gate_vma.vm_page_prot = PAGE_READONLY_EXEC;
 	gate_vma.vm_start = 0xffff0000;
 	gate_vma.vm_end	= 0xffff0000 + PAGE_SIZE;
-	gate_vma.vm_flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYEXEC;
+	vm_flags_init(&gate_vma, VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYEXEC);
 	return 0;
 }
 arch_initcall(gate_vma_init);
@@ -371,7 +370,7 @@ static unsigned long sigpage_addr(const struct mm_struct *mm,
 
 	slots = ((last - first) >> PAGE_SHIFT) + 1;
 
-	offset = prandom_u32_max(slots);
+	offset = get_random_u32_below(slots);
 
 	addr = first + (offset << PAGE_SHIFT);
 
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index bfe88c6e60d5..2d8e2516906b 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -651,11 +651,9 @@ static int vfp_set(struct task_struct *target,
 	if (ret)
 		return ret;
 
-	ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
-				user_fpregs_offset + sizeof(new_vfp.fpregs),
-				user_fpscr_offset);
-	if (ret)
-		return ret;
+	user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+				  user_fpregs_offset + sizeof(new_vfp.fpregs),
+				  user_fpscr_offset);
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				 &new_vfp.fpscr,
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..87f8d0e5e314 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -48,7 +48,6 @@
 #include <asm/mach/arch.h>
 #include <asm/mpu.h>
 
-#define CREATE_TRACE_POINTS
 #include <trace/events/ipi.h>
 
 /*
@@ -320,7 +319,7 @@ void __cpu_die(unsigned int cpu)
  * of the other hotplug-cpu capable cores, so presumably coming
  * out of idle fixes this.
  */
-void arch_cpu_idle_dead(void)
+void __noreturn arch_cpu_idle_dead(void)
 {
 	unsigned int cpu = smp_processor_id();
 
@@ -382,6 +381,8 @@ void arch_cpu_idle_dead(void)
 		: "r" (task_stack_page(current) + THREAD_SIZE - 8),
 		  "r" (current)
 		: "r0");
+
+	unreachable();
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
@@ -600,6 +601,8 @@ 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 +612,6 @@ static void ipi_cpu_stop(unsigned int cpu)
 
 	set_cpu_online(cpu, false);
 
-	local_fiq_disable();
-	local_irq_disable();
-
 	while (1) {
 		cpu_relax();
 		wfe();
@@ -639,7 +639,7 @@ static void do_handle_IPI(int ipinr)
 	unsigned int cpu = smp_processor_id();
 
 	if ((unsigned)ipinr < NR_IPI)
-		trace_ipi_entry_rcuidle(ipi_types[ipinr]);
+		trace_ipi_entry(ipi_types[ipinr]);
 
 	switch (ipinr) {
 	case IPI_WAKEUP:
@@ -686,7 +686,7 @@ static void do_handle_IPI(int ipinr)
 	}
 
 	if ((unsigned)ipinr < NR_IPI)
-		trace_ipi_exit_rcuidle(ipi_types[ipinr]);
+		trace_ipi_exit(ipi_types[ipinr]);
 }
 
 /* Legacy version, should go away once all irqchips have been converted */
@@ -709,7 +709,7 @@ static irqreturn_t ipi_handler(int irq, void *data)
 
 static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
 {
-	trace_ipi_raise_rcuidle(target, ipi_types[ipinr]);
+	trace_ipi_raise(target, ipi_types[ipinr]);
 	__ipi_send_mask(ipi_desc[ipinr], target);
 }
 
@@ -748,7 +748,7 @@ void __init set_smp_ipi_range(int ipi_base, int n)
 	ipi_setup(smp_processor_id());
 }
 
-void smp_send_reschedule(int cpu)
+void arch_smp_send_reschedule(int cpu)
 {
 	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
 }
@@ -778,7 +778,7 @@ void smp_send_stop(void)
  * kdump fails. So split out the panic_smp_self_stop() and add
  * set_cpu_online(smp_processor_id(), false).
  */
-void panic_smp_self_stop(void)
+void __noreturn panic_smp_self_stop(void)
 {
 	pr_debug("CPU %u will stop doing anything useful since another CPU has paniced\n",
 	         smp_processor_id());
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/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c
index 68112c172025..006163195d67 100644
--- a/arch/arm/kernel/sys_oabi-compat.c
+++ b/arch/arm/kernel/sys_oabi-compat.c
@@ -73,6 +73,7 @@
 #include <linux/syscalls.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
+#include <linux/filelock.h>
 #include <linux/cred.h>
 #include <linux/fcntl.h>
 #include <linux/eventpoll.h>
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..9d2192156087 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>
@@ -307,6 +308,29 @@ static int unwind_exec_pop_subset_r0_to_r3(struct unwind_ctrl_block *ctrl,
 	return URC_OK;
 }
 
+static unsigned long unwind_decode_uleb128(struct unwind_ctrl_block *ctrl)
+{
+	unsigned long bytes = 0;
+	unsigned long insn;
+	unsigned long result = 0;
+
+	/*
+	 * unwind_get_byte() will advance `ctrl` one instruction at a time, so
+	 * loop until we get an instruction byte where bit 7 is not set.
+	 *
+	 * Note: This decodes a maximum of 4 bytes to output 28 bits data where
+	 * max is 0xfffffff: that will cover a vsp increment of 1073742336, hence
+	 * it is sufficient for unwinding the stack.
+	 */
+	do {
+		insn = unwind_get_byte(ctrl);
+		result |= (insn & 0x7f) << (bytes * 7);
+		bytes++;
+	} while (!!(insn & 0x80) && (bytes != sizeof(result)));
+
+	return result;
+}
+
 /*
  * Execute the current unwind instruction.
  */
@@ -360,7 +384,7 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
 		if (ret)
 			goto error;
 	} else if (insn == 0xb2) {
-		unsigned long uleb128 = unwind_get_byte(ctrl);
+		unsigned long uleb128 = unwind_decode_uleb128(ctrl);
 
 		ctrl->vrs[SP] += 0x204 + (uleb128 << 2);
 	} else {
@@ -395,8 +419,18 @@ 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;
 	}