Merge branch 'akpm/master'

83 files changed, 1365 insertions, 446 deletions

diff --git a/Documentation/DMA-ISA-LPC.txt b/Documentation/DMA-ISA-LPC.txt
index c41331398752..7a065ac4a9d1 100644
--- a/Documentation/DMA-ISA-LPC.txt
+++ b/Documentation/DMA-ISA-LPC.txt
@@ -42,7 +42,7 @@ requirements you pass the flag GFP_DMA to kmalloc.
 
 Unfortunately the memory available for ISA DMA is scarce so unless you
 allocate the memory during boot-up it's a good idea to also pass
-__GFP_REPEAT and __GFP_NOWARN to make the allocator try a bit harder.
+__GFP_RETRY_MAYFAIL and __GFP_NOWARN to make the allocator try a bit harder.
 
 (This scarcity also means that you should allocate the buffer as
 early as possible and not release it until the driver is unloaded.)
diff --git a/arch/Kconfig b/arch/Kconfig
index cae0958a2298..21d0089117fe 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -198,9 +198,6 @@ config HAVE_KPROBES_ON_FTRACE
 config HAVE_NMI
 	bool
 
-config HAVE_NMI_WATCHDOG
-	depends on HAVE_NMI
-	bool
 #
 # An arch should select this if it provides all these things:
 #
@@ -226,6 +223,12 @@ config GENERIC_SMP_IDLE_THREAD
 config GENERIC_IDLE_POLL_SETUP
        bool
 
+config ARCH_HAS_FORTIFY_SOURCE
+	bool
+	help
+	  An architecture should select this when it can successfully
+	  build and run with CONFIG_FORTIFY_SOURCE.
+
 # Select if arch has all set_memory_ro/rw/x/nx() functions in asm/cacheflush.h
 config ARCH_HAS_SET_MEMORY
 	bool
@@ -288,6 +291,28 @@ config HAVE_PERF_EVENTS_NMI
 	  subsystem.  Also has support for calculating CPU cycle events
 	  to determine how many clock cycles in a given period.
 
+config HAVE_HARDLOCKUP_DETECTOR_PERF
+	bool
+	depends on HAVE_PERF_EVENTS_NMI
+	help
+	  The arch chooses to use the generic perf-NMI-based hardlockup
+	  detector. Must define HAVE_PERF_EVENTS_NMI.
+
+config HAVE_NMI_WATCHDOG
+	depends on HAVE_NMI
+	bool
+	help
+	  The arch provides a low level NMI watchdog. It provides
+	  asm/nmi.h, and defines its own arch_touch_nmi_watchdog().
+
+config HAVE_HARDLOCKUP_DETECTOR_ARCH
+	bool
+	select HAVE_NMI_WATCHDOG
+	help
+	  The arch chooses to provide its own hardlockup detector, which is
+	  a superset of the HAVE_NMI_WATCHDOG. It also conforms to config
+	  interfaces and parameters provided by hardlockup detector subsystem.
+
 config HAVE_PERF_REGS
 	bool
 	help
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 8addb851ab5e..dfd908630631 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -12,6 +12,7 @@ config ARM64
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
 	select ARCH_HAS_ELF_RANDOMIZE
+	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
 	select ARCH_HAS_KCOV
diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h
index 2eb714c4639f..d0aa42907569 100644
--- a/arch/arm64/include/asm/string.h
+++ b/arch/arm64/include/asm/string.h
@@ -63,6 +63,11 @@ extern int memcmp(const void *, const void *, size_t);
 #define memcpy(dst, src, len) __memcpy(dst, src, len)
 #define memmove(dst, src, len) __memmove(dst, src, len)
 #define memset(s, c, n) __memset(s, c, n)
+
+#ifndef __NO_FORTIFY
+#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */
+#endif
+
 #endif
 
 #endif
diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index adc208c2ae9c..decccffb03ca 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -35,7 +35,7 @@
  * Leave enough space between the mmap area and the stack to honour ulimit in
  * the face of randomisation.
  */
-#define MIN_GAP (SZ_128M + ((STACK_RND_MASK << PAGE_SHIFT) + 1))
+#define MIN_GAP (SZ_128M)
 #define MAX_GAP	(STACK_TOP/6*5)
 
 static int mmap_is_legacy(void)
@@ -65,6 +65,11 @@ unsigned long arch_mmap_rnd(void)
 static unsigned long mmap_base(unsigned long rnd)
 {
 	unsigned long gap = rlimit(RLIMIT_STACK);
+	unsigned long pad = (STACK_RND_MASK << PAGE_SHIFT) + stack_guard_gap;
+
+	/* Values close to RLIM_INFINITY can overflow. */
+	if (gap + pad > gap)
+		gap += pad;
 
 	if (gap < MIN_GAP)
 		gap = MIN_GAP;
diff --git a/arch/blackfin/include/asm/nmi.h b/arch/blackfin/include/asm/nmi.h
index b9caac4fcfd8..107d23705f46 100644
--- a/arch/blackfin/include/asm/nmi.h
+++ b/arch/blackfin/include/asm/nmi.h
@@ -9,4 +9,6 @@
 
 #include <linux/nmi.h>
 
+extern void arch_touch_nmi_watchdog(void);
+
 #endif
diff --git a/arch/blackfin/kernel/nmi.c b/arch/blackfin/kernel/nmi.c
index 633c37083e87..1e714329fe8a 100644
--- a/arch/blackfin/kernel/nmi.c
+++ b/arch/blackfin/kernel/nmi.c
@@ -190,7 +190,7 @@ static int __init init_nmi_wdt(void)
 }
 device_initcall(init_nmi_wdt);
 
-void touch_nmi_watchdog(void)
+void arch_touch_nmi_watchdog(void)
 {
 	atomic_set(&nmi_touched[smp_processor_id()], 1);
 }
diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h
index a1bdb1ea5234..39b9f311c4ef 100644
--- a/arch/mips/include/asm/pgalloc.h
+++ b/arch/mips/include/asm/pgalloc.h
@@ -116,7 +116,7 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 {
 	pud_t *pud;
 
-	pud = (pud_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT, PUD_ORDER);
+	pud = (pud_t *) __get_free_pages(GFP_KERNEL, PUD_ORDER);
 	if (pud)
 		pud_init((unsigned long)pud, (unsigned long)invalid_pmd_table);
 	return pud;
diff --git a/arch/mn10300/include/asm/nmi.h b/arch/mn10300/include/asm/nmi.h
index f3671cbbc117..b05627597b1b 100644
--- a/arch/mn10300/include/asm/nmi.h
+++ b/arch/mn10300/include/asm/nmi.h
@@ -11,4 +11,6 @@
 #ifndef _ASM_NMI_H
 #define _ASM_NMI_H
 
+extern void arch_touch_nmi_watchdog(void);
+
 #endif /* _ASM_NMI_H */
diff --git a/arch/mn10300/kernel/mn10300-watchdog-low.S b/arch/mn10300/kernel/mn10300-watchdog-low.S
index f2f5c9cfaabd..34f8773de7d0 100644
--- a/arch/mn10300/kernel/mn10300-watchdog-low.S
+++ b/arch/mn10300/kernel/mn10300-watchdog-low.S
@@ -50,9 +50,9 @@ watchdog_handler:
 #   we can't inline it)
 #
 ###############################################################################
-	.globl	touch_nmi_watchdog
-	.type	touch_nmi_watchdog,@function
-touch_nmi_watchdog:
+	.globl	arch_touch_nmi_watchdog
+	.type	arch_touch_nmi_watchdog,@function
+arch_touch_nmi_watchdog:
 	clr	d0
 	clr	d1
 	mov	watchdog_alert_counter, a0
@@ -63,4 +63,4 @@ touch_nmi_watchdog:
 	lne
 	ret	[],0
 
-	.size	touch_nmi_watchdog,.-touch_nmi_watchdog
+	.size	arch_touch_nmi_watchdog,.-arch_touch_nmi_watchdog
diff --git a/arch/mn10300/kernel/mn10300-watchdog.c b/arch/mn10300/kernel/mn10300-watchdog.c
index a2d8e6938d67..0d5641beadf5 100644
--- a/arch/mn10300/kernel/mn10300-watchdog.c
+++ b/arch/mn10300/kernel/mn10300-watchdog.c
@@ -31,7 +31,7 @@ static unsigned int watchdog;
 static unsigned int watchdog_hz = 1;
 unsigned int watchdog_alert_counter[NR_CPUS];
 
-EXPORT_SYMBOL(touch_nmi_watchdog);
+EXPORT_SYMBOL(arch_touch_nmi_watchdog);
 
 /*
  * the best way to detect whether a CPU has a 'hard lockup' problem
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index d0ee448700de..d556f9557f04 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -82,7 +82,7 @@ config NR_IRQS
 
 config NMI_IPI
 	bool
-	depends on SMP && (DEBUGGER || KEXEC_CORE)
+	depends on SMP && (DEBUGGER || KEXEC_CORE || HARDLOCKUP_DETECTOR)
 	default y
 
 config STACKTRACE_SUPPORT
@@ -125,6 +125,7 @@ config PPC
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_DMA_SET_COHERENT_MASK
 	select ARCH_HAS_ELF_RANDOMIZE
+	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE
 	select ARCH_HAS_SG_CHAIN
@@ -189,11 +190,13 @@ config PPC
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_MOD_ARCH_SPECIFIC
-	select HAVE_NMI				if PERF_EVENTS
+	select HAVE_NMI				if PERF_EVENTS || (PPC64 && PPC_BOOK3S)
+	select HAVE_HARDLOCKUP_DETECTOR_ARCH	if (PPC64 && PPC_BOOK3S)
 	select HAVE_OPROFILE
 	select HAVE_OPTPROBES			if PPC64
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_EVENTS_NMI		if PPC64
+	select HAVE_HARDLOCKUP_DETECTOR_PERF	if HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_RCU_TABLE_FREE		if SMP
diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h
index 20b1485ff1e8..e2329db9d6f4 100644
--- a/arch/powerpc/include/asm/book3s/64/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h
@@ -56,7 +56,7 @@ static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm)
 	return (pgd_t *)__get_free_page(pgtable_gfp_flags(mm, PGALLOC_GFP));
 #else
 	struct page *page;
-	page = alloc_pages(pgtable_gfp_flags(mm, PGALLOC_GFP | __GFP_REPEAT),
+	page = alloc_pages(pgtable_gfp_flags(mm, PGALLOC_GFP | __GFP_RETRY_MAYFAIL),
 				4);
 	if (!page)
 		return NULL;
diff --git a/arch/powerpc/include/asm/nmi.h b/arch/powerpc/include/asm/nmi.h
index ff1ccb375e60..6f8e79cd35d8 100644
--- a/arch/powerpc/include/asm/nmi.h
+++ b/arch/powerpc/include/asm/nmi.h
@@ -1,4 +1,15 @@
 #ifndef _ASM_NMI_H
 #define _ASM_NMI_H
 
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
+extern void arch_touch_nmi_watchdog(void);
+
+extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask,
+					   bool exclude_self);
+#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace
+
+#else
+static inline void arch_touch_nmi_watchdog(void) {}
+#endif
+
 #endif /* _ASM_NMI_H */
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index ebddb2111d87..8ea98504f900 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -55,6 +55,8 @@ struct smp_ops_t {
 	int   (*cpu_bootable)(unsigned int nr);
 };
 
+extern void smp_flush_nmi_ipi(u64 delay_us);
+extern int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us);
 extern void smp_send_debugger_break(void);
 extern void start_secondary_resume(void);
 extern void smp_generic_give_timebase(void);
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 0845eebc5af3..4aa7c147e447 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -38,6 +38,7 @@ obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 				   signal_64.o ptrace32.o \
 				   paca.o nvram_64.o firmware.o
 obj-$(CONFIG_VDSO32)		+= vdso32/
+obj-$(CONFIG_HARDLOCKUP_DETECTOR)	+= watchdog.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_ppc970.o cpu_setup_pa6t.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_power.o
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index fb4ffc773082..3ba8c4590c62 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1314,6 +1314,31 @@ EXC_REAL_NONE(0x1800, 0x100)
 EXC_VIRT_NONE(0x5800, 0x100)
 #endif
 
+#if defined(CONFIG_HARDLOCKUP_DETECTOR) && defined(CONFIG_HAVE_HARDLOCKUP_DETECTOR_ARCH)
+
+#define MASKED_DEC_HANDLER_LABEL 3f
+
+#define MASKED_DEC_HANDLER(_H)				\
+3: /* soft-nmi */					\
+	std	r12,PACA_EXGEN+EX_R12(r13);		\
+	GET_SCRATCH0(r10);				\
+	std	r10,PACA_EXGEN+EX_R13(r13);		\
+	EXCEPTION_PROLOG_PSERIES_1(soft_nmi_common, _H)
+
+EXC_COMMON_BEGIN(soft_nmi_common)
+	mr	r10,r1
+	ld	r1,PACAEMERGSP(r13)
+	ld	r1,PACA_NMI_EMERG_SP(r13)
+	subi	r1,r1,INT_FRAME_SIZE
+	EXCEPTION_COMMON_NORET_STACK(PACA_EXGEN, 0x900,
+			system_reset, soft_nmi_interrupt,
+			ADD_NVGPRS;ADD_RECONCILE)
+	b	ret_from_except
+
+#else
+#define MASKED_DEC_HANDLER_LABEL 2f /* normal return */
+#define MASKED_DEC_HANDLER(_H)
+#endif
 
 /*
  * An interrupt came in while soft-disabled. We set paca->irq_happened, then:
@@ -1336,7 +1361,7 @@ masked_##_H##interrupt:					\
 	lis	r10,0x7fff;				\
 	ori	r10,r10,0xffff;				\
 	mtspr	SPRN_DEC,r10;				\
-	b	2f;					\
+	b	MASKED_DEC_HANDLER_LABEL;		\
 1:	cmpwi	r10,PACA_IRQ_DBELL;			\
 	beq	2f;					\
 	cmpwi	r10,PACA_IRQ_HMI;			\
@@ -1351,7 +1376,8 @@ masked_##_H##interrupt:					\
 	ld	r11,PACA_EXGEN+EX_R11(r13);		\
 	GET_SCRATCH0(r13);				\
 	##_H##rfid;					\
-	b	.
+	b	.;					\
+	MASKED_DEC_HANDLER(_H)
 
 /*
  * Real mode exceptions actually use this too, but alternate
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 9ad37f827a97..1086ea37c832 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -25,6 +25,7 @@
 #include <linux/kvm_para.h>
 #include <linux/slab.h>
 #include <linux/of.h>
+#include <linux/nmi.h> /* hardlockup_detector_disable() */
 
 #include <asm/reg.h>
 #include <asm/sections.h>
@@ -718,6 +719,12 @@ static __init void kvm_free_tmp(void)
 
 static int __init kvm_guest_init(void)
 {
+	/*
+	 * The hardlockup detector is likely to get false positives in
+	 * KVM guests, so disable it by default.
+	 */
+	hardlockup_detector_disable();
+
 	if (!kvm_para_available())
 		goto free_tmp;
 
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index dd8a04f3053a..613f79f03877 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -15,6 +15,9 @@
 
 #undef DEBUG_PROM
 
+/* we cannot use FORTIFY as it brings in new symbols */
+#define __NO_FORTIFY
+
 #include <stdarg.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 4640f6d64f8b..af23d4b576ec 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -751,22 +751,3 @@ unsigned long memory_block_size_bytes(void)
 struct ppc_pci_io ppc_pci_io;
 EXPORT_SYMBOL(ppc_pci_io);
 #endif
-
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
-u64 hw_nmi_get_sample_period(int watchdog_thresh)
-{
-	return ppc_proc_freq * watchdog_thresh;
-}
-
-/*
- * The hardlockup detector breaks PMU event based branches and is likely
- * to get false positives in KVM guests, so disable it by default.
- */
-static int __init disable_hardlockup_detector(void)
-{
-	hardlockup_detector_disable();
-
-	return 0;
-}
-early_initcall(disable_hardlockup_detector);
-#endif
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 72035493c429..e4f82e1b5f67 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -434,13 +434,31 @@ static void do_smp_send_nmi_ipi(int cpu)
 	}
 }
 
+void smp_flush_nmi_ipi(u64 delay_us)
+{
+	unsigned long flags;
+
+	nmi_ipi_lock_start(&flags);
+	while (nmi_ipi_busy_count) {
+		nmi_ipi_unlock_end(&flags);
+		udelay(1);
+		if (delay_us) {
+			delay_us--;
+			if (!delay_us)
+				return;
+		}
+		nmi_ipi_lock_start(&flags);
+	}
+	nmi_ipi_unlock_end(&flags);
+}
+
 /*
  * - cpu is the target CPU (must not be this CPU), or NMI_IPI_ALL_OTHERS.
  * - fn is the target callback function.
  * - delay_us > 0 is the delay before giving up waiting for targets to
  *   enter the handler, == 0 specifies indefinite delay.
  */
-static int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us)
+int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us)
 {
 	unsigned long flags;
 	int me = raw_smp_processor_id();
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
new file mode 100644
index 000000000000..ae1ed7516eae
--- /dev/null
+++ b/arch/powerpc/kernel/watchdog.c
@@ -0,0 +1,388 @@
+/*
+ * Watchdog support on powerpc systems.
+ *
+ * Copyright 2017, IBM Corporation.
+ *
+ * This uses code from arch/sparc/kernel/nmi.c and kernel/watchdog.c
+ */
+#include <linux/kernel.h>
+#include <linux/param.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/cpu.h>
+#include <linux/nmi.h>
+#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/kprobes.h>
+#include <linux/hardirq.h>
+#include <linux/reboot.h>
+#include <linux/slab.h>
+#include <linux/kdebug.h>
+#include <linux/sched/debug.h>
+#include <linux/delay.h>
+#include <linux/smp.h>
+
+#include <asm/paca.h>
+
+/*
+ * The watchdog has a simple timer that runs on each CPU, once per timer
+ * period. This is the heartbeat.
+ *
+ * Then there are checks to see if the heartbeat has not triggered on a CPU
+ * for the panic timeout period. Currently the watchdog only supports an
+ * SMP check, so the heartbeat only turns on when we have 2 or more CPUs.
+ *
+ * This is not an NMI watchdog, but Linux uses that name for a generic
+ * watchdog in some cases, so NMI gets used in some places.
+ */
+
+static cpumask_t wd_cpus_enabled __read_mostly;
+
+static u64 wd_panic_timeout_tb __read_mostly; /* timebase ticks until panic */
+static u64 wd_smp_panic_timeout_tb __read_mostly; /* panic other CPUs */
+
+static u64 wd_timer_period_ms __read_mostly;  /* interval between heartbeat */
+
+static DEFINE_PER_CPU(struct timer_list, wd_timer);
+static DEFINE_PER_CPU(u64, wd_timer_tb);
+
+/*
+ * These are for the SMP checker. CPUs clear their pending bit in their
+ * heartbeat. If the bitmask becomes empty, the time is noted and the
+ * bitmask is refilled.
+ *
+ * All CPUs clear their bit in the pending mask every timer period.
+ * Once all have cleared, the time is noted and the bits are reset.
+ * If the time since all clear was greater than the panic timeout,
+ * we can panic with the list of stuck CPUs.
+ *
+ * This will work best with NMI IPIs for crash code so the stuck CPUs
+ * can be pulled out to get their backtraces.
+ */
+static unsigned long __wd_smp_lock;
+static cpumask_t wd_smp_cpus_pending;
+static cpumask_t wd_smp_cpus_stuck;
+static u64 wd_smp_last_reset_tb;
+
+static inline void wd_smp_lock(unsigned long *flags)
+{
+	/*
+	 * Avoid locking layers if possible.
+	 * This may be called from low level interrupt handlers at some
+	 * point in future.
+	 */
+	local_irq_save(*flags);
+	while (unlikely(test_and_set_bit_lock(0, &__wd_smp_lock)))
+		cpu_relax();
+}
+
+static inline void wd_smp_unlock(unsigned long *flags)
+{
+	clear_bit_unlock(0, &__wd_smp_lock);
+	local_irq_restore(*flags);
+}
+
+static void wd_lockup_ipi(struct pt_regs *regs)
+{
+	pr_emerg("Watchdog CPU:%d Hard LOCKUP\n", raw_smp_processor_id());
+	print_modules();
+	print_irqtrace_events(current);
+	if (regs)
+		show_regs(regs);
+	else
+		dump_stack();
+
+	if (hardlockup_panic)
+		nmi_panic(regs, "Hard LOCKUP");
+}
+
+static void set_cpu_stuck(int cpu, u64 tb)
+{
+	cpumask_set_cpu(cpu, &wd_smp_cpus_stuck);
+	cpumask_clear_cpu(cpu, &wd_smp_cpus_pending);
+	if (cpumask_empty(&wd_smp_cpus_pending)) {
+		wd_smp_last_reset_tb = tb;
+		cpumask_andnot(&wd_smp_cpus_pending,
+				&wd_cpus_enabled,
+				&wd_smp_cpus_stuck);
+	}
+}
+
+static void watchdog_smp_panic(int cpu, u64 tb)
+{
+	unsigned long flags;
+	int c;
+
+	wd_smp_lock(&flags);
+	/* Double check some things under lock */
+	if ((s64)(tb - wd_smp_last_reset_tb) < (s64)wd_smp_panic_timeout_tb)
+		goto out;
+	if (cpumask_test_cpu(cpu, &wd_smp_cpus_pending))
+		goto out;
+	if (cpumask_weight(&wd_smp_cpus_pending) == 0)
+		goto out;
+
+	pr_emerg("Watchdog CPU:%d detected Hard LOCKUP other CPUS:%*pbl\n",
+			cpu, cpumask_pr_args(&wd_smp_cpus_pending));
+
+	/*
+	 * Try to trigger the stuck CPUs.
+	 */
+	for_each_cpu(c, &wd_smp_cpus_pending) {
+		if (c == cpu)
+			continue;
+		smp_send_nmi_ipi(c, wd_lockup_ipi, 1000000);
+	}
+	smp_flush_nmi_ipi(1000000);
+
+	/* Take the stuck CPU out of the watch group */
+	for_each_cpu(c, &wd_smp_cpus_pending)
+		set_cpu_stuck(c, tb);
+
+out:
+	wd_smp_unlock(&flags);
+
+	printk_safe_flush();
+	/*
+	 * printk_safe_flush() seems to require another print
+	 * before anything actually goes out to console.
+	 */
+	if (sysctl_hardlockup_all_cpu_backtrace)
+		trigger_allbutself_cpu_backtrace();
+
+	if (hardlockup_panic)
+		nmi_panic(NULL, "Hard LOCKUP");
+}
+
+static void wd_smp_clear_cpu_pending(int cpu, u64 tb)
+{
+	if (!cpumask_test_cpu(cpu, &wd_smp_cpus_pending)) {
+		if (unlikely(cpumask_test_cpu(cpu, &wd_smp_cpus_stuck))) {
+			unsigned long flags;
+
+			pr_emerg("Watchdog CPU:%d became unstuck\n", cpu);
+			wd_smp_lock(&flags);
+			cpumask_clear_cpu(cpu, &wd_smp_cpus_stuck);
+			wd_smp_unlock(&flags);
+		}
+		return;
+	}
+	cpumask_clear_cpu(cpu, &wd_smp_cpus_pending);
+	if (cpumask_empty(&wd_smp_cpus_pending)) {
+		unsigned long flags;
+
+		wd_smp_lock(&flags);
+		if (cpumask_empty(&wd_smp_cpus_pending)) {
+			wd_smp_last_reset_tb = tb;
+			cpumask_andnot(&wd_smp_cpus_pending,
+					&wd_cpus_enabled,
+					&wd_smp_cpus_stuck);
+		}
+		wd_smp_unlock(&flags);
+	}
+}
+
+static void watchdog_timer_interrupt(int cpu)
+{
+	u64 tb = get_tb();
+
+	per_cpu(wd_timer_tb, cpu) = tb;
+
+	wd_smp_clear_cpu_pending(cpu, tb);
+
+	if ((s64)(tb - wd_smp_last_reset_tb) >= (s64)wd_smp_panic_timeout_tb)
+		watchdog_smp_panic(cpu, tb);
+}
+
+void soft_nmi_interrupt(struct pt_regs *regs)
+{
+	unsigned long flags;
+	int cpu = raw_smp_processor_id();
+	u64 tb;
+
+	if (!cpumask_test_cpu(cpu, &wd_cpus_enabled))
+		return;
+
+	nmi_enter();
+	tb = get_tb();
+	if (tb - per_cpu(wd_timer_tb, cpu) >= wd_panic_timeout_tb) {
+		per_cpu(wd_timer_tb, cpu) = tb;
+
+		wd_smp_lock(&flags);
+		if (cpumask_test_cpu(cpu, &wd_smp_cpus_stuck)) {
+			wd_smp_unlock(&flags);
+			goto out;
+		}
+		set_cpu_stuck(cpu, tb);
+
+		pr_emerg("Watchdog CPU:%d Hard LOCKUP\n", cpu);
+		print_modules();
+		print_irqtrace_events(current);
+		if (regs)
+			show_regs(regs);
+		else
+			dump_stack();
+
+		wd_smp_unlock(&flags);
+
+		if (sysctl_hardlockup_all_cpu_backtrace)
+			trigger_allbutself_cpu_backtrace();
+
+		if (hardlockup_panic)
+			nmi_panic(regs, "Hard LOCKUP");
+	}
+	if (wd_panic_timeout_tb < 0x7fffffff)
+		mtspr(SPRN_DEC, wd_panic_timeout_tb);
+
+out:
+	nmi_exit();
+}
+
+static void wd_timer_reset(unsigned int cpu, struct timer_list *t)
+{
+	t->expires = jiffies + msecs_to_jiffies(wd_timer_period_ms);
+	if (wd_timer_period_ms > 1000)
+		t->expires = __round_jiffies_up(t->expires, cpu);
+	add_timer_on(t, cpu);
+}
+
+static void wd_timer_fn(unsigned long data)
+{
+	struct timer_list *t = this_cpu_ptr(&wd_timer);
+	int cpu = smp_processor_id();
+
+	watchdog_timer_interrupt(cpu);
+
+	wd_timer_reset(cpu, t);
+}
+
+void arch_touch_nmi_watchdog(void)
+{
+	int cpu = smp_processor_id();
+
+	watchdog_timer_interrupt(cpu);
+}
+EXPORT_SYMBOL(arch_touch_nmi_watchdog);
+
+static void start_watchdog_timer_on(unsigned int cpu)
+{
+	struct timer_list *t = per_cpu_ptr(&wd_timer, cpu);
+
+	per_cpu(wd_timer_tb, cpu) = get_tb();
+
+	setup_pinned_timer(t, wd_timer_fn, 0);
+	wd_timer_reset(cpu, t);
+}
+
+static void stop_watchdog_timer_on(unsigned int cpu)
+{
+	struct timer_list *t = per_cpu_ptr(&wd_timer, cpu);
+
+	del_timer_sync(t);
+}
+
+static int start_wd_on_cpu(unsigned int cpu)
+{
+	if (cpumask_test_cpu(cpu, &wd_cpus_enabled)) {
+		WARN_ON(1);
+		return 0;
+	}
+
+	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
+		return 0;
+
+	if (watchdog_suspended)
+		return 0;
+
+	if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
+		return 0;
+
+	cpumask_set_cpu(cpu, &wd_cpus_enabled);
+	if (cpumask_weight(&wd_cpus_enabled) == 1) {
+		cpumask_set_cpu(cpu, &wd_smp_cpus_pending);
+		wd_smp_last_reset_tb = get_tb();
+	}
+	smp_wmb();
+	start_watchdog_timer_on(cpu);
+
+	return 0;
+}
+
+static int stop_wd_on_cpu(unsigned int cpu)
+{
+	if (!cpumask_test_cpu(cpu, &wd_cpus_enabled)) {
+		WARN_ON(1);
+		return 0;
+	}
+
+	stop_watchdog_timer_on(cpu);
+
+	cpumask_clear_cpu(cpu, &wd_cpus_enabled);
+	wd_smp_clear_cpu_pending(cpu, get_tb());
+
+	return 0;
+}
+
+static void watchdog_calc_timeouts(void)
+{
+	wd_panic_timeout_tb = watchdog_thresh * ppc_tb_freq;
+
+	/* Have the SMP detector trigger a bit later */
+	wd_smp_panic_timeout_tb = wd_panic_timeout_tb * 3 / 2;
+
+	/* 2/5 is the factor that the perf based detector uses */
+	wd_timer_period_ms = watchdog_thresh * 1000 * 2 / 5;
+}
+
+void watchdog_nmi_reconfigure(void)
+{
+	int cpu;
+
+	watchdog_calc_timeouts();
+
+	for_each_cpu(cpu, &wd_cpus_enabled)
+		stop_wd_on_cpu(cpu);
+
+	for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask)
+		start_wd_on_cpu(cpu);
+}
+
+/*
+ * This runs after lockup_detector_init() which sets up watchdog_cpumask.
+ */
+static int __init powerpc_watchdog_init(void)
+{
+	int err;
+
+	watchdog_calc_timeouts();
+
+	err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powerpc/watchdog:online",
+				start_wd_on_cpu, stop_wd_on_cpu);
+	if (err < 0)
+		pr_warn("Watchdog could not be initialized");
+
+	return 0;
+}
+arch_initcall(powerpc_watchdog_init);
+
+static void handle_backtrace_ipi(struct pt_regs *regs)
+{
+	nmi_cpu_backtrace(regs);
+}
+
+static void raise_backtrace_ipi(cpumask_t *mask)
+{
+	unsigned int cpu;
+
+	for_each_cpu(cpu, mask) {
+		if (cpu == smp_processor_id())
+			handle_backtrace_ipi(NULL);
+		else
+			smp_send_nmi_ipi(cpu, handle_backtrace_ipi, 1000000);
+	}
+}
+
+void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)
+{
+	nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace_ipi);
+}
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 710e491206ed..8cb0190e2a73 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -93,7 +93,7 @@ int kvmppc_allocate_hpt(struct kvm_hpt_info *info, u32 order)
 	}
 
 	if (!hpt)
-		hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT
+		hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_RETRY_MAYFAIL
 				       |__GFP_NOWARN, order - PAGE_SHIFT);
 
 	if (!hpt)
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index f3917705c686..41cf5ae273cf 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -233,192 +233,192 @@ static long calc_offset(struct fixup_entry *entry, unsigned int *p)
 
 static void test_basic_patching(void)
 {
-	extern unsigned int ftr_fixup_test1;
-	extern unsigned int end_ftr_fixup_test1;
-	extern unsigned int ftr_fixup_test1_orig;
-	extern unsigned int ftr_fixup_test1_expected;
-	int size = &end_ftr_fixup_test1 - &ftr_fixup_test1;
+	extern unsigned int ftr_fixup_test1[];
+	extern unsigned int end_ftr_fixup_test1[];
+	extern unsigned int ftr_fixup_test1_orig[];
+	extern unsigned int ftr_fixup_test1_expected[];
+	int size = end_ftr_fixup_test1 - ftr_fixup_test1;
 
 	fixup.value = fixup.mask = 8;
-	fixup.start_off = calc_offset(&fixup, &ftr_fixup_test1 + 1);
-	fixup.end_off = calc_offset(&fixup, &ftr_fixup_test1 + 2);
+	fixup.start_off = calc_offset(&fixup, ftr_fixup_test1 + 1);
+	fixup.end_off = calc_offset(&fixup, ftr_fixup_test1 + 2);
 	fixup.alt_start_off = fixup.alt_end_off = 0;
 
 	/* Sanity check */
-	check(memcmp(&ftr_fixup_test1, &ftr_fixup_test1_orig, size) == 0);
+	check(memcmp(ftr_fixup_test1, ftr_fixup_test1_orig, size) == 0);
 
 	/* Check we don't patch if the value matches */
 	patch_feature_section(8, &fixup);
-	check(memcmp(&ftr_fixup_test1, &ftr_fixup_test1_orig, size) == 0);
+	check(memcmp(ftr_fixup_test1, ftr_fixup_test1_orig, size) == 0);
 
 	/* Check we do patch if the value doesn't match */
 	patch_feature_section(0, &fixup);
-	check(memcmp(&ftr_fixup_test1, &ftr_fixup_test1_expected, size) == 0);
+	check(memcmp(ftr_fixup_test1, ftr_fixup_test1_expected, size) == 0);
 
 	/* Check we do patch if the mask doesn't match */
-	memcpy(&ftr_fixup_test1, &ftr_fixup_test1_orig, size);
-	check(memcmp(&ftr_fixup_test1, &ftr_fixup_test1_orig, size) == 0);
+	memcpy(ftr_fixup_test1, ftr_fixup_test1_orig, size);
+	check(memcmp(ftr_fixup_test1, ftr_fixup_test1_orig, size) == 0);
 	patch_feature_section(~8, &fixup);
-	check(memcmp(&ftr_fixup_test1, &ftr_fixup_test1_expected, size) == 0);
+	check(memcmp(ftr_fixup_test1, ftr_fixup_test1_expected, size) == 0);
 }
 
 static void test_alternative_patching(void)
 {
-	extern unsigned int ftr_fixup_test2;
-	extern unsigned int end_ftr_fixup_test2;
-	extern unsigned int ftr_fixup_test2_orig;
-	extern unsigned int ftr_fixup_test2_alt;
-	extern unsigned int ftr_fixup_test2_expected;
-	int size = &end_ftr_fixup_test2 - &ftr_fixup_test2;
+	extern unsigned int ftr_fixup_test2[];
+	extern unsigned int end_ftr_fixup_test2[];
+	extern unsigned int ftr_fixup_test2_orig[];
+	extern unsigned int ftr_fixup_test2_alt[];
+	extern unsigned int ftr_fixup_test2_expected[];
+	int size = end_ftr_fixup_test2 - ftr_fixup_test2;
 
 	fixup.value = fixup.mask = 0xF;
-	fixup.start_off = calc_offset(&fixup, &ftr_fixup_test2 + 1);
-	fixup.end_off = calc_offset(&fixup, &ftr_fixup_test2 + 2);
-	fixup.alt_start_off = calc_offset(&fixup, &ftr_fixup_test2_alt);
-	fixup.alt_end_off = calc_offset(&fixup, &ftr_fixup_test2_alt + 1);
+	fixup.start_off = calc_offset(&fixup, ftr_fixup_test2 + 1);
+	fixup.end_off = calc_offset(&fixup, ftr_fixup_test2 + 2);
+	fixup.alt_start_off = calc_offset(&fixup, ftr_fixup_test2_alt);
+	fixup.alt_end_off = calc_offset(&fixup, ftr_fixup_test2_alt + 1);
 
 	/* Sanity check */
-	check(memcmp(&ftr_fixup_test2, &ftr_fixup_test2_orig, size) == 0);
+	check(memcmp(ftr_fixup_test2, ftr_fixup_test2_orig, size) == 0);
 
 	/* Check we don't patch if the value matches */
 	patch_feature_section(0xF, &fixup);
-	check(memcmp(&ftr_fixup_test2, &ftr_fixup_test2_orig, size) == 0);
+	check(memcmp(ftr_fixup_test2, ftr_fixup_test2_orig, size) == 0);
 
 	/* Check we do patch if the value doesn't match */
 	patch_feature_section(0, &fixup);
-	check(memcmp(&ftr_fixup_test2, &ftr_fixup_test2_expected, size) == 0);
+	check(memcmp(ftr_fixup_test2, ftr_fixup_test2_expected, size) == 0);
 
 	/* Check we do patch if the mask doesn't match */
-	memcpy(&ftr_fixup_test2, &ftr_fixup_test2_orig, size);
-	check(memcmp(&ftr_fixup_test2, &ftr_fixup_test2_orig, size) == 0);
+	memcpy(ftr_fixup_test2, ftr_fixup_test2_orig, size);
+	check(memcmp(ftr_fixup_test2, ftr_fixup_test2_orig, size) == 0);
 	patch_feature_section(~0xF, &fixup);
-	check(memcmp(&ftr_fixup_test2, &ftr_fixup_test2_expected, size) == 0);
+	check(memcmp(ftr_fixup_test2, ftr_fixup_test2_expected, size) == 0);
 }
 
 static void test_alternative_case_too_big(void)
 {
-	extern unsigned int ftr_fixup_test3;
-	extern unsigned int end_ftr_fixup_test3;
-	extern unsigned int ftr_fixup_test3_orig;
-	extern unsigned int ftr_fixup_test3_alt;
-	int size = &end_ftr_fixup_test3 - &ftr_fixup_test3;
+	extern unsigned int ftr_fixup_test3[];
+	extern unsigned int end_ftr_fixup_test3[];
+	extern unsigned int ftr_fixup_test3_orig[];
+	extern unsigned int ftr_fixup_test3_alt[];
+	int size = end_ftr_fixup_test3 - ftr_fixup_test3;
 
 	fixup.value = fixup.mask = 0xC;
-	fixup.start_off = calc_offset(&fixup, &ftr_fixup_test3 + 1);
-	fixup.end_off = calc_offset(&fixup, &ftr_fixup_test3 + 2);
-	fixup.alt_start_off = calc_offset(&fixup, &ftr_fixup_test3_alt);
-	fixup.alt_end_off = calc_offset(&fixup, &ftr_fixup_test3_alt + 2);
+	fixup.start_off = calc_offset(&fixup, ftr_fixup_test3 + 1);
+	fixup.end_off = calc_offset(&fixup, ftr_fixup_test3 + 2);
+	fixup.alt_start_off = calc_offset(&fixup, ftr_fixup_test3_alt);
+	fixup.alt_end_off = calc_offset(&fixup, ftr_fixup_test3_alt + 2);
 
 	/* Sanity check */
-	check(memcmp(&ftr_fixup_test3, &ftr_fixup_test3_orig, size) == 0);
+	check(memcmp(ftr_fixup_test3, ftr_fixup_test3_orig, size) == 0);
 
 	/* Expect nothing to be patched, and the error returned to us */
 	check(patch_feature_section(0xF, &fixup) == 1);
-	check(memcmp(&ftr_fixup_test3, &ftr_fixup_test3_orig, size) == 0);
+	check(memcmp(ftr_fixup_test3, ftr_fixup_test3_orig, size) == 0);
 	check(patch_feature_section(0, &fixup) == 1);
-	check(memcmp(&ftr_fixup_test3, &ftr_fixup_test3_orig, size) == 0);
+	check(memcmp(ftr_fixup_test3, ftr_fixup_test3_orig, size) == 0);
 	check(patch_feature_section(~0xF, &fixup) == 1);
-	check(memcmp(&ftr_fixup_test3, &ftr_fixup_test3_orig, size) == 0);
+	check(memcmp(ftr_fixup_test3, ftr_fixup_test3_orig, size) == 0);
 }
 
 static void test_alternative_case_too_small(void)
 {
-	extern unsigned int ftr_fixup_test4;
-	extern unsigned int end_ftr_fixup_test4;
-	extern unsigned int ftr_fixup_test4_orig;
-	extern unsigned int ftr_fixup_test4_alt;
-	extern unsigned int ftr_fixup_test4_expected;
-	int size = &end_ftr_fixup_test4 - &ftr_fixup_test4;
+	extern unsigned int ftr_fixup_test4[];
+	extern unsigned int end_ftr_fixup_test4[];
+	extern unsigned int ftr_fixup_test4_orig[];
+	extern unsigned int ftr_fixup_test4_alt[];
+	extern unsigned int ftr_fixup_test4_expected[];
+	int size = end_ftr_fixup_test4 - ftr_fixup_test4;
 	unsigned long flag;
 
 	/* Check a high-bit flag */
 	flag = 1UL << ((sizeof(unsigned long) - 1) * 8);
 	fixup.value = fixup.mask = flag;
-	fixup.start_off = calc_offset(&fixup, &ftr_fixup_test4 + 1);
-	fixup.end_off = calc_offset(&fixup, &ftr_fixup_test4 + 5);
-	fixup.alt_start_off = calc_offset(&fixup, &ftr_fixup_test4_alt);
-	fixup.alt_end_off = calc_offset(&fixup, &ftr_fixup_test4_alt + 2);
+	fixup.start_off = calc_offset(&fixup, ftr_fixup_test4 + 1);
+	fixup.end_off = calc_offset(&fixup, ftr_fixup_test4 + 5);
+	fixup.alt_start_off = calc_offset(&fixup, ftr_fixup_test4_alt);
+	fixup.alt_end_off = calc_offset(&fixup, ftr_fixup_test4_alt + 2);
 
 	/* Sanity check */
-	check(memcmp(&ftr_fixup_test4, &ftr_fixup_test4_orig, size) == 0);
+	check(memcmp(ftr_fixup_test4, ftr_fixup_test4_orig, size) == 0);
 
 	/* Check we don't patch if the value matches */
 	patch_feature_section(flag, &fixup);
-	check(memcmp(&ftr_fixup_test4, &ftr_fixup_test4_orig, size) == 0);
+	check(memcmp(ftr_fixup_test4, ftr_fixup_test4_orig, size) == 0);
 
 	/* Check we do patch if the value doesn't match */
 	patch_feature_section(0, &fixup);
-	check(memcmp(&ftr_fixup_test4, &ftr_fixup_test4_expected, size) == 0);
+	check(memcmp(ftr_fixup_test4, ftr_fixup_test4_expected, size) == 0);
 
 	/* Check we do patch if the mask doesn't match */
-	memcpy(&ftr_fixup_test4, &ftr_fixup_test4_orig, size);
-	check(memcmp(&ftr_fixup_test4, &ftr_fixup_test4_orig, size) == 0);
+	memcpy(ftr_fixup_test4, ftr_fixup_test4_orig, size);
+	check(memcmp(ftr_fixup_test4, ftr_fixup_test4_orig, size) == 0);
 	patch_feature_section(~flag, &fixup);
-	check(memcmp(&ftr_fixup_test4, &ftr_fixup_test4_expected, size) == 0);
+	check(memcmp(ftr_fixup_test4, ftr_fixup_test4_expected, size) == 0);
 }
 
 static void test_alternative_case_with_branch(void)
 {
-	extern unsigned int ftr_fixup_test5;
-	extern unsigned int end_ftr_fixup_test5;
-	extern unsigned int ftr_fixup_test5_expected;
-	int size = &end_ftr_fixup_test5 - &ftr_fixup_test5;
+	extern unsigned int ftr_fixup_test5[];
+	extern unsigned int end_ftr_fixup_test5[];
+	extern unsigned int ftr_fixup_test5_expected[];
+	int size = end_ftr_fixup_test5 - ftr_fixup_test5;
 
-	check(memcmp(&ftr_fixup_test5, &ftr_fixup_test5_expected, size) == 0);
+	check(memcmp(ftr_fixup_test5, ftr_fixup_test5_expected, size) == 0);
 }
 
 static void test_alternative_case_with_external_branch(void)
 {
-	extern unsigned int ftr_fixup_test6;
-	extern unsigned int end_ftr_fixup_test6;
-	extern unsigned int ftr_fixup_test6_expected;
-	int size = &end_ftr_fixup_test6 - &ftr_fixup_test6;
+	extern unsigned int ftr_fixup_test6[];
+	extern unsigned int end_ftr_fixup_test6[];
+	extern unsigned int ftr_fixup_test6_expected[];
+	int size = end_ftr_fixup_test6 - ftr_fixup_test6;
 
-	check(memcmp(&ftr_fixup_test6, &ftr_fixup_test6_expected, size) == 0);
+	check(memcmp(ftr_fixup_test6, ftr_fixup_test6_expected, size) == 0);
 }
 
 static void test_cpu_macros(void)
 {
-	extern u8 ftr_fixup_test_FTR_macros;
-	extern u8 ftr_fixup_test_FTR_macros_expected;
-	unsigned long size = &ftr_fixup_test_FTR_macros_expected -
-			     &ftr_fixup_test_FTR_macros;
+	extern u8 ftr_fixup_test_FTR_macros[];
+	extern u8 ftr_fixup_test_FTR_macros_expected[];
+	unsigned long size = ftr_fixup_test_FTR_macros_expected -
+			     ftr_fixup_test_FTR_macros;
 
 	/* The fixups have already been done for us during boot */
-	check(memcmp(&ftr_fixup_test_FTR_macros,
-		     &ftr_fixup_test_FTR_macros_expected, size) == 0);
+	check(memcmp(ftr_fixup_test_FTR_macros,
+		     ftr_fixup_test_FTR_macros_expected, size) == 0);
 }
 
 static void test_fw_macros(void)
 {
 #ifdef CONFIG_PPC64
-	extern u8 ftr_fixup_test_FW_FTR_macros;
-	extern u8 ftr_fixup_test_FW_FTR_macros_expected;
-	unsigned long size = &ftr_fixup_test_FW_FTR_macros_expected -
-			     &ftr_fixup_test_FW_FTR_macros;
+	extern u8 ftr_fixup_test_FW_FTR_macros[];
+	extern u8 ftr_fixup_test_FW_FTR_macros_expected[];
+	unsigned long size = ftr_fixup_test_FW_FTR_macros_expected -
+			     ftr_fixup_test_FW_FTR_macros;
 
 	/* The fixups have already been done for us during boot */
-	check(memcmp(&ftr_fixup_test_FW_FTR_macros,
-		     &ftr_fixup_test_FW_FTR_macros_expected, size) == 0);
+	check(memcmp(ftr_fixup_test_FW_FTR_macros,
+		     ftr_fixup_test_FW_FTR_macros_expected, size) == 0);
 #endif
 }
 
 static void test_lwsync_macros(void)
 {
-	extern u8 lwsync_fixup_test;
-	extern u8 end_lwsync_fixup_test;
-	extern u8 lwsync_fixup_test_expected_LWSYNC;
-	extern u8 lwsync_fixup_test_expected_SYNC;
-	unsigned long size = &end_lwsync_fixup_test -
-			     &lwsync_fixup_test;
+	extern u8 lwsync_fixup_test[];
+	extern u8 end_lwsync_fixup_test[];
+	extern u8 lwsync_fixup_test_expected_LWSYNC[];
+	extern u8 lwsync_fixup_test_expected_SYNC[];
+	unsigned long size = end_lwsync_fixup_test -
+			     lwsync_fixup_test;
 
 	/* The fixups have already been done for us during boot */
 	if (cur_cpu_spec->cpu_features & CPU_FTR_LWSYNC) {
-		check(memcmp(&lwsync_fixup_test,
-			     &lwsync_fixup_test_expected_LWSYNC, size) == 0);
+		check(memcmp(lwsync_fixup_test,
+			     lwsync_fixup_test_expected_LWSYNC, size) == 0);
 	} else {
-		check(memcmp(&lwsync_fixup_test,
-			     &lwsync_fixup_test_expected_SYNC, size) == 0);
+		check(memcmp(lwsync_fixup_test,
+			     lwsync_fixup_test_expected_SYNC, size) == 0);
 	}
 }
 
diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c
index 0ee6be4f1ba4..5d78b193fec4 100644
--- a/arch/powerpc/mm/mmap.c
+++ b/arch/powerpc/mm/mmap.c
@@ -34,16 +34,9 @@
 /*
  * Top of mmap area (just below the process stack).
  *
- * Leave at least a ~128 MB hole on 32bit applications.
- *
- * On 64bit applications we randomise the stack by 1GB so we need to
- * space our mmap start address by a further 1GB, otherwise there is a
- * chance the mmap area will end up closer to the stack than our ulimit
- * requires.
+ * Leave at least a ~128 MB hole.
  */
-#define MIN_GAP32 (128*1024*1024)
-#define MIN_GAP64 ((128 + 1024)*1024*1024UL)
-#define MIN_GAP ((is_32bit_task()) ? MIN_GAP32 : MIN_GAP64)
+#define MIN_GAP (128*1024*1024)
 #define MAX_GAP (TASK_SIZE/6*5)
 
 static inline int mmap_is_legacy(void)
@@ -71,9 +64,26 @@ unsigned long arch_mmap_rnd(void)
 	return rnd << PAGE_SHIFT;
 }
 
+static inline unsigned long stack_maxrandom_size(void)
+{
+	if (!(current->flags & PF_RANDOMIZE))
+		return 0;
+
+	/* 8MB for 32bit, 1GB for 64bit */
+	if (is_32bit_task())
+		return (1<<23);
+	else
+		return (1<<30);
+}
+
 static inline unsigned long mmap_base(unsigned long rnd)
 {
 	unsigned long gap = rlimit(RLIMIT_STACK);
+	unsigned long pad = stack_maxrandom_size() + stack_guard_gap;
+
+	/* Values close to RLIM_INFINITY can overflow. */
+	if (gap + pad > gap)
+		gap += pad;
 
 	if (gap < MIN_GAP)
 		gap = MIN_GAP;
diff --git a/arch/sh/include/asm/bug.h b/arch/sh/include/asm/bug.h
index 1b77f068be2b..c9828f785ca0 100644
--- a/arch/sh/include/asm/bug.h
+++ b/arch/sh/include/asm/bug.h
@@ -48,6 +48,7 @@ do {							\
 		   "i" (__FILE__),			\
 		   "i" (__LINE__), "i" (0),		\
 		   "i" (sizeof(struct bug_entry)));	\
+	unreachable();					\
 } while (0)
 
 #define __WARN_FLAGS(flags)				\
diff --git a/arch/sparc/include/asm/nmi.h b/arch/sparc/include/asm/nmi.h
index 26ad2b2607c6..284eac3ffaf2 100644
--- a/arch/sparc/include/asm/nmi.h
+++ b/arch/sparc/include/asm/nmi.h
@@ -7,6 +7,7 @@ void nmi_adjust_hz(unsigned int new_hz);
 
 extern atomic_t nmi_active;
 
+void arch_touch_nmi_watchdog(void);
 void start_nmi_watchdog(void *unused);
 void stop_nmi_watchdog(void *unused);
 
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index e4b4e790bf89..fa466ce45bc9 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -205,7 +205,7 @@ static struct mdesc_handle *mdesc_kmalloc(unsigned int mdesc_size)
 	handle_size = (sizeof(struct mdesc_handle) -
 		       sizeof(struct mdesc_hdr) +
 		       mdesc_size);
-	base = kmalloc(handle_size + 15, GFP_KERNEL | __GFP_REPEAT);
+	base = kmalloc(handle_size + 15, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!base)
 		return NULL;
 
diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c
index 95e73c63c99d..048ad783ea3f 100644
--- a/arch/sparc/kernel/nmi.c
+++ b/arch/sparc/kernel/nmi.c
@@ -51,7 +51,7 @@ static DEFINE_PER_CPU(unsigned int, last_irq_sum);
 static DEFINE_PER_CPU(long, alert_counter);
 static DEFINE_PER_CPU(int, nmi_touch);
 
-void touch_nmi_watchdog(void)
+void arch_touch_nmi_watchdog(void)
 {
 	if (atomic_read(&nmi_active)) {
 		int cpu;
@@ -61,10 +61,8 @@ void touch_nmi_watchdog(void)
 				per_cpu(nmi_touch, cpu) = 1;
 		}
 	}
-
-	touch_softlockup_watchdog();
 }
-EXPORT_SYMBOL(touch_nmi_watchdog);
+EXPORT_SYMBOL(arch_touch_nmi_watchdog);
 
 static void die_nmi(const char *str, struct pt_regs *regs, int do_panic)
 {
diff --git a/arch/sparc/lib/NG4memset.S b/arch/sparc/lib/NG4memset.S
index 7c0c81f18837..c07834f3a6fc 100644
--- a/arch/sparc/lib/NG4memset.S
+++ b/arch/sparc/lib/NG4memset.S
@@ -13,14 +13,14 @@
 	.globl		NG4memset
 NG4memset:
 	andcc		%o1, 0xff, %o4
-	be,pt		%icc, 1f
+	be,pt		%xcc, 1f
 	 mov		%o2, %o1
 	sllx		%o4, 8, %g1
 	or		%g1, %o4, %o2
 	sllx		%o2, 16, %g1
 	or		%g1, %o2, %o2
 	sllx		%o2, 32, %g1
-	ba,pt		%icc, 1f
+	ba,pt		%xcc, 1f
 	 or		%g1, %o2, %o4
 	.size		NG4memset,.-NG4memset
 
@@ -29,7 +29,7 @@ NG4memset:
 NG4bzero:
 	clr		%o4
 1:	cmp		%o1, 16
-	ble		%icc, .Ltiny
+	ble		%xcc, .Ltiny
 	 mov		%o0, %o3
 	sub		%g0, %o0, %g1
 	and		%g1, 0x7, %g1
@@ -37,7 +37,7 @@ NG4bzero:
 	 sub		%o1, %g1, %o1
 1:	stb		%o4, [%o0 + 0x00]
 	subcc		%g1, 1, %g1
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 1, %o0
 .Laligned8:
 	cmp		%o1, 64 + (64 - 8)
@@ -48,7 +48,7 @@ NG4bzero:
 	 sub		%o1, %g1, %o1
 1:	stx		%o4, [%o0 + 0x00]
 	subcc		%g1, 8, %g1
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 0x8, %o0
 .Laligned64:
 	andn		%o1, 64 - 1, %g1
@@ -58,30 +58,30 @@ NG4bzero:
 1:	stxa		%o4, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
 	subcc		%g1, 0x40, %g1
 	stxa		%o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 0x40, %o0
 .Lpostloop:
 	cmp		%o1, 8
-	bl,pn		%icc, .Ltiny
+	bl,pn		%xcc, .Ltiny
 	 membar		#StoreStore|#StoreLoad
 .Lmedium:
 	andn		%o1, 0x7, %g1
 	sub		%o1, %g1, %o1
 1:	stx		%o4, [%o0 + 0x00]
 	subcc		%g1, 0x8, %g1
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 0x08, %o0
 	andcc		%o1, 0x4, %g1
-	be,pt		%icc, .Ltiny
+	be,pt		%xcc, .Ltiny
 	 sub		%o1, %g1, %o1
 	stw		%o4, [%o0 + 0x00]
 	add		%o0, 0x4, %o0
 .Ltiny:
 	cmp		%o1, 0
-	be,pn		%icc, .Lexit
+	be,pn		%xcc, .Lexit
 1:	 subcc		%o1, 1, %o1
 	stb		%o4, [%o0 + 0x00]
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 1, %o0
 .Lexit:
 	retl
@@ -99,8 +99,8 @@ NG4bzero:
 	stxa		%o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
 	stxa		%o4, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
 	stxa		%o4, [%o0 + %o5] ASI_BLK_INIT_QUAD_LDD_P
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 0x30, %o0
-	ba,a,pt		%icc, .Lpostloop
+	ba,a,pt		%xcc, .Lpostloop
 	 nop
 	.size		NG4bzero,.-NG4bzero
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2543ffc44afe..5c1f5795ed95 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -50,6 +50,7 @@ config X86
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FAST_MULTIPLIER
+	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_KCOV			if X86_64
 	select ARCH_HAS_MMIO_FLUSH
@@ -160,6 +161,7 @@ config X86
 	select HAVE_PCSPKR_PLATFORM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_EVENTS_NMI
+	select HAVE_HARDLOCKUP_DETECTOR_PERF	if HAVE_PERF_EVENTS_NMI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index b3c5a5f030ce..43691238a21d 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -409,3 +409,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 	debug_putstr("done.\nBooting the kernel.\n");
 	return output;
 }
+
+void fortify_panic(const char *name)
+{
+	error("detected buffer overflow");
+}
diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h
index 3d3e8353ee5c..e9ee84873de5 100644
--- a/arch/x86/include/asm/string_32.h
+++ b/arch/x86/include/asm/string_32.h
@@ -142,7 +142,9 @@ static __always_inline void *__constant_memcpy(void *to, const void *from,
 }
 
 #define __HAVE_ARCH_MEMCPY
+extern void *memcpy(void *, const void *, size_t);
 
+#ifndef CONFIG_FORTIFY_SOURCE
 #ifdef CONFIG_X86_USE_3DNOW
 
 #include <asm/mmx.h>
@@ -195,11 +197,15 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len)
 #endif
 
 #endif
+#endif /* !CONFIG_FORTIFY_SOURCE */
 
 #define __HAVE_ARCH_MEMMOVE
 void *memmove(void *dest, const void *src, size_t n);
 
+extern int memcmp(const void *, const void *, size_t);
+#ifndef CONFIG_FORTIFY_SOURCE
 #define memcmp __builtin_memcmp
+#endif
 
 #define __HAVE_ARCH_MEMCHR
 extern void *memchr(const void *cs, int c, size_t count);
@@ -321,6 +327,8 @@ void *__constant_c_and_count_memset(void *s, unsigned long pattern,
 	 : __memset_generic((s), (c), (count)))
 
 #define __HAVE_ARCH_MEMSET
+extern void *memset(void *, int, size_t);
+#ifndef CONFIG_FORTIFY_SOURCE
 #if (__GNUC__ >= 4)
 #define memset(s, c, count) __builtin_memset(s, c, count)
 #else
@@ -330,6 +338,7 @@ void *__constant_c_and_count_memset(void *s, unsigned long pattern,
 				 (count))				\
 	 : __memset((s), (c), (count)))
 #endif
+#endif /* !CONFIG_FORTIFY_SOURCE */
 
 /*
  * find the first occurrence of byte 'c', or 1 past the area if none
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 733bae07fb29..309fe644569f 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -31,6 +31,7 @@ static __always_inline void *__inline_memcpy(void *to, const void *from, size_t
 extern void *memcpy(void *to, const void *from, size_t len);
 extern void *__memcpy(void *to, const void *from, size_t len);
 
+#ifndef CONFIG_FORTIFY_SOURCE
 #ifndef CONFIG_KMEMCHECK
 #if (__GNUC__ == 4 && __GNUC_MINOR__ < 3) || __GNUC__ < 4
 #define memcpy(dst, src, len)					\
@@ -51,6 +52,7 @@ extern void *__memcpy(void *to, const void *from, size_t len);
  */
 #define memcpy(dst, src, len) __inline_memcpy((dst), (src), (len))
 #endif
+#endif /* !CONFIG_FORTIFY_SOURCE */
 
 #define __HAVE_ARCH_MEMSET
 void *memset(void *s, int c, size_t n);
@@ -77,6 +79,11 @@ int strcmp(const char *cs, const char *ct);
 #define memcpy(dst, src, len) __memcpy(dst, src, len)
 #define memmove(dst, src, len) __memmove(dst, src, len)
 #define memset(s, c, n) __memset(s, c, n)
+
+#ifndef __NO_FORTIFY
+#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */
+#endif
+
 #endif
 
 #define __HAVE_ARCH_MEMCPY_MCSAFE 1
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index c73c9fb281e1..d6f387780849 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -19,7 +19,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
 u64 hw_nmi_get_sample_period(int watchdog_thresh)
 {
 	return (u64)(cpu_khz) * 1000 * watchdog_thresh;
diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c
index cad12634d6bd..2eab7d0bfedd 100644
--- a/arch/x86/lib/memcpy_32.c
+++ b/arch/x86/lib/memcpy_32.c
@@ -6,7 +6,7 @@
 
 __visible void *memcpy(void *to, const void *from, size_t n)
 {
-#ifdef CONFIG_X86_USE_3DNOW
+#if defined(CONFIG_X86_USE_3DNOW) && !defined(CONFIG_FORTIFY_SOURCE)
 	return __memcpy3d(to, from, n);
 #else
 	return __memcpy(to, from, n);
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 797295e792b2..229d04a83f85 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -92,13 +92,18 @@ unsigned long arch_mmap_rnd(void)
 static unsigned long mmap_base(unsigned long rnd, unsigned long task_size)
 {
 	unsigned long gap = rlimit(RLIMIT_STACK);
+	unsigned long pad = stack_maxrandom_size(task_size) + stack_guard_gap;
 	unsigned long gap_min, gap_max;
 
+	/* Values close to RLIM_INFINITY can overflow. */
+	if (gap + pad > gap)
+		gap += pad;
+
 	/*
 	 * Top of mmap area (just below the process stack).
 	 * Leave an at least ~128 MB hole with possible stack randomization.
 	 */
-	gap_min = SIZE_128M + stack_maxrandom_size(task_size);
+	gap_min = SIZE_128M;
 	gap_max = (task_size / 6) * 5;
 
 	if (gap < gap_min)
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 30f6290109d4..bdc12d426b24 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -7,6 +7,7 @@ generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
 generic-y += extable.h
+generic-y += fb.h
 generic-y += fcntl.h
 generic-y += hardirq.h
 generic-y += ioctl.h
diff --git a/arch/xtensa/include/asm/fb.h b/arch/xtensa/include/asm/fb.h
deleted file mode 100644
index c7df38030992..000000000000
--- a/arch/xtensa/include/asm/fb.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASM_FB_H_
-#define _ASM_FB_H_
-#include <linux/fb.h>
-
-#define fb_pgprotect(...) do {} while (0)
-
-static inline int fb_is_primary_device(struct fb_info *info)
-{
-	return 0;
-}
-
-#endif /* _ASM_FB_H_ */
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index f7425960f6a5..37e24f525162 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -17,6 +17,7 @@ cflags-$(CONFIG_ARM)		:= $(subst -pg,,$(KBUILD_CFLAGS)) \
 cflags-$(CONFIG_EFI_ARMSTUB)	+= -I$(srctree)/scripts/dtc/libfdt
 
 KBUILD_CFLAGS			:= $(cflags-y) -DDISABLE_BRANCH_PROFILING \
+				   -D__NO_FORTIFY \
 				   $(call cc-option,-ffreestanding) \
 				   $(call cc-option,-fno-stack-protector)
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 7dcac3bfb771..969bac8404f1 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2434,8 +2434,9 @@ rebuild_st:
 				 * again with !__GFP_NORETRY. However, we still
 				 * want to fail this allocation rather than
 				 * trigger the out-of-memory killer and for
-				 * this we want the future __GFP_MAYFAIL.
+				 * this we want __GFP_RETRY_MAYFAIL.
 				 */
+				gfp |= __GFP_RETRY_MAYFAIL;
 			}
 		} while (1);
 
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 23039768f541..be944d5aa9af 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -995,7 +995,9 @@ static int send_atomic_ack(struct rxe_qp *qp, struct rxe_pkt_info *pkt,
 	free_rd_atomic_resource(qp, res);
 	rxe_advance_resp_resource(qp);
 
-	memcpy(SKB_TO_PKT(skb), &ack_pkt, sizeof(skb->cb));
+	memcpy(SKB_TO_PKT(skb), &ack_pkt, sizeof(ack_pkt));
+	memset((unsigned char *)SKB_TO_PKT(skb) + sizeof(ack_pkt), 0,
+	       sizeof(skb->cb) - sizeof(ack_pkt));
 
 	res->type = RXE_ATOMIC_MASK;
 	res->atomic.skb = skb;
diff --git a/drivers/mmc/host/wbsd.c b/drivers/mmc/host/wbsd.c
index e15a9733fcfd..9668616faf16 100644
--- a/drivers/mmc/host/wbsd.c
+++ b/drivers/mmc/host/wbsd.c
@@ -1386,7 +1386,7 @@ static void wbsd_request_dma(struct wbsd_host *host, int dma)
 	 * order for ISA to be able to DMA to it.
 	 */
 	host->dma_buffer = kmalloc(WBSD_DMA_SIZE,
-		GFP_NOIO | GFP_DMA | __GFP_REPEAT | __GFP_NOWARN);
+		GFP_NOIO | GFP_DMA | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
 	if (!host->dma_buffer)
 		goto free;
 
diff --git a/drivers/s390/char/vmcp.c b/drivers/s390/char/vmcp.c
index 65f5a794f26d..98749fa817da 100644
--- a/drivers/s390/char/vmcp.c
+++ b/drivers/s390/char/vmcp.c
@@ -98,7 +98,7 @@ vmcp_write(struct file *file, const char __user *buff, size_t count,
 	}
 	if (!session->response)
 		session->response = (char *)__get_free_pages(GFP_KERNEL
-						| __GFP_REPEAT | GFP_DMA,
+						| __GFP_RETRY_MAYFAIL | GFP_DMA,
 						get_order(session->bufsize));
 	if (!session->response) {
 		mutex_unlock(&session->mutex);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 28de421e3220..cf166535dd5c 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -252,7 +252,7 @@ int transport_alloc_session_tags(struct se_session *se_sess,
 	int rc;
 
 	se_sess->sess_cmd_map = kzalloc(tag_num * tag_size,
-					GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+					GFP_KERNEL | __GFP_NOWARN | __GFP_RETRY_MAYFAIL);
 	if (!se_sess->sess_cmd_map) {
 		se_sess->sess_cmd_map = vzalloc(tag_num * tag_size);
 		if (!se_sess->sess_cmd_map) {
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index e3d7ea1288c6..06d044862e58 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -897,7 +897,7 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 	struct sk_buff **queue;
 	int i;
 
-	n = kvmalloc(sizeof *n, GFP_KERNEL | __GFP_REPEAT);
+	n = kvmalloc(sizeof *n, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!n)
 		return -ENOMEM;
 	vqs = kmalloc(VHOST_NET_VQ_MAX * sizeof(*vqs), GFP_KERNEL);
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 679f8960db4b..046f6d280af5 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1399,7 +1399,7 @@ static int vhost_scsi_open(struct inode *inode, struct file *f)
 	struct vhost_virtqueue **vqs;
 	int r = -ENOMEM, i;
 
-	vs = kzalloc(sizeof(*vs), GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+	vs = kzalloc(sizeof(*vs), GFP_KERNEL | __GFP_NOWARN | __GFP_RETRY_MAYFAIL);
 	if (!vs) {
 		vs = vzalloc(sizeof(*vs));
 		if (!vs)
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 3f63e03de8e8..c9de9c41aa97 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -508,7 +508,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
 	/* This struct is large and allocation could fail, fall back to vmalloc
 	 * if there is no other way.
 	 */
-	vsock = kvmalloc(sizeof(*vsock), GFP_KERNEL | __GFP_REPEAT);
+	vsock = kvmalloc(sizeof(*vsock), GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!vsock)
 		return -ENOMEM;
 
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 8b426f83909f..245c430a2e41 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -380,8 +380,8 @@ static void inode_switch_wbs_work_fn(struct work_struct *work)
 		struct page *page = radix_tree_deref_slot_protected(slot,
 							&mapping->tree_lock);
 		if (likely(page) && PageDirty(page)) {
-			__dec_wb_stat(old_wb, WB_RECLAIMABLE);
-			__inc_wb_stat(new_wb, WB_RECLAIMABLE);
+			dec_wb_stat(old_wb, WB_RECLAIMABLE);
+			inc_wb_stat(new_wb, WB_RECLAIMABLE);
 		}
 	}
 
@@ -391,8 +391,8 @@ static void inode_switch_wbs_work_fn(struct work_struct *work)
 							&mapping->tree_lock);
 		if (likely(page)) {
 			WARN_ON_ONCE(!PageWriteback(page));
-			__dec_wb_stat(old_wb, WB_WRITEBACK);
-			__inc_wb_stat(new_wb, WB_WRITEBACK);
+			dec_wb_stat(old_wb, WB_WRITEBACK);
+			inc_wb_stat(new_wb, WB_WRITEBACK);
 		}
 	}
 
diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h
index d6ea520162b2..4d85992d75b2 100644
--- a/fs/xfs/kmem.h
+++ b/fs/xfs/kmem.h
@@ -54,6 +54,16 @@ kmem_flags_convert(xfs_km_flags_t flags)
 			lflags &= ~__GFP_FS;
 	}
 
+	/*
+	 * Default page/slab allocator behavior is to retry for ever
+	 * for small allocations. We can override this behavior by using
+	 * __GFP_RETRY_MAYFAIL which will tell the allocator to retry as long
+	 * as it is feasible but rather fail than retry forever for all
+	 * request sizes.
+	 */
+	if (flags & KM_MAYFAIL)
+		lflags |= __GFP_RETRY_MAYFAIL;
+
 	if (flags & KM_ZERO)
 		lflags |= __GFP_ZERO;
 
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 334165c911f0..854e1bdd0b2a 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -69,34 +69,14 @@ static inline void __add_wb_stat(struct bdi_writeback *wb,
 	percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH);
 }
 
-static inline void __inc_wb_stat(struct bdi_writeback *wb,
-				 enum wb_stat_item item)
-{
-	__add_wb_stat(wb, item, 1);
-}
-
 static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__inc_wb_stat(wb, item);
-	local_irq_restore(flags);
-}
-
-static inline void __dec_wb_stat(struct bdi_writeback *wb,
-				 enum wb_stat_item item)
-{
-	__add_wb_stat(wb, item, -1);
+	__add_wb_stat(wb, item, 1);
 }
 
 static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__dec_wb_stat(wb, item);
-	local_irq_restore(flags);
+	__add_wb_stat(wb, item, -1);
 }
 
 static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
diff --git a/include/linux/crc-ccitt.h b/include/linux/crc-ccitt.h
index f52696a1ff0d..7cd45a4bc224 100644
--- a/include/linux/crc-ccitt.h
+++ b/include/linux/crc-ccitt.h
@@ -4,12 +4,19 @@
 #include <linux/types.h>
 
 extern u16 const crc_ccitt_table[256];
+extern u16 const crc_ccitt_false_table[256];
 
 extern u16 crc_ccitt(u16 crc, const u8 *buffer, size_t len);
+extern u16 crc_ccitt_false(u16 crc, const u8 *buffer, size_t len);
 
 static inline u16 crc_ccitt_byte(u16 crc, const u8 c)
 {
 	return (crc >> 8) ^ crc_ccitt_table[(crc ^ c) & 0xff];
 }
 
+static inline u16 crc_ccitt_false_byte(u16 crc, const u8 c)
+{
+    return (crc << 8) ^ crc_ccitt_false_table[(crc >> 8) ^ c];
+}
+
 #endif /* _LINUX_CRC_CCITT_H */
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 4c6656f1fee7..bcfb9f7c46f5 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -25,7 +25,7 @@ struct vm_area_struct;
 #define ___GFP_FS		0x80u
 #define ___GFP_COLD		0x100u
 #define ___GFP_NOWARN		0x200u
-#define ___GFP_REPEAT		0x400u
+#define ___GFP_RETRY_MAYFAIL	0x400u
 #define ___GFP_NOFAIL		0x800u
 #define ___GFP_NORETRY		0x1000u
 #define ___GFP_MEMALLOC		0x2000u
@@ -136,26 +136,56 @@ struct vm_area_struct;
  *
  * __GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim.
  *
- * __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt
- *   _might_ fail.  This depends upon the particular VM implementation.
+ * The default allocator behavior depends on the request size. We have a concept
+ * of so called costly allocations (with order > PAGE_ALLOC_COSTLY_ORDER).
+ * !costly allocations are too essential to fail so they are implicitly
+ * non-failing by default (with some exceptions like OOM victims might fail so
+ * the caller still has to check for failures) while costly requests try to be
+ * not disruptive and back off even without invoking the OOM killer.
+ * The following three modifiers might be used to override some of these
+ * implicit rules
+ *
+ * __GFP_NORETRY: The VM implementation will try only very lightweight
+ *   memory direct reclaim to get some memory under memory pressure (thus
+ *   it can sleep). It will avoid disruptive actions like OOM killer. The
+ *   caller must handle the failure which is quite likely to happen under
+ *   heavy memory pressure. The flag is suitable when failure can easily be
+ *   handled at small cost, such as reduced throughput
+ *
+ * __GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim
+ *   procedures that have previously failed if there is some indication
+ *   that progress has been made else where.  It can wait for other
+ *   tasks to attempt high level approaches to freeing memory such as
+ *   compaction (which removes fragmentation) and page-out.
+ *   There is still a definite limit to the number of retries, but it is
+ *   a larger limit than with __GFP_NORETRY.
+ *   Allocations with this flag may fail, but only when there is
+ *   genuinely little unused memory. While these allocations do not
+ *   directly trigger the OOM killer, their failure indicates that
+ *   the system is likely to need to use the OOM killer soon.  The
+ *   caller must handle failure, but can reasonably do so by failing
+ *   a higher-level request, or completing it only in a much less
+ *   efficient manner.
+ *   If the allocation does fail, and the caller is in a position to
+ *   free some non-essential memory, doing so could benefit the system
+ *   as a whole.
  *
  * __GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller
- *   cannot handle allocation failures. New users should be evaluated carefully
- *   (and the flag should be used only when there is no reasonable failure
- *   policy) but it is definitely preferable to use the flag rather than
- *   opencode endless loop around allocator.
- *
- * __GFP_NORETRY: The VM implementation must not retry indefinitely and will
- *   return NULL when direct reclaim and memory compaction have failed to allow
- *   the allocation to succeed.  The OOM killer is not called with the current
- *   implementation.
+ *   cannot handle allocation failures. The allocation could block
+ *   indefinitely but will never return with failure. Testing for
+ *   failure is pointless.
+ *   New users should be evaluated carefully (and the flag should be
+ *   used only when there is no reasonable failure policy) but it is
+ *   definitely preferable to use the flag rather than opencode endless
+ *   loop around allocator.
+ *   Using this flag for costly allocations is _highly_ discouraged.
  */
 #define __GFP_IO	((__force gfp_t)___GFP_IO)
 #define __GFP_FS	((__force gfp_t)___GFP_FS)
 #define __GFP_DIRECT_RECLAIM	((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */
 #define __GFP_KSWAPD_RECLAIM	((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */
 #define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM))
-#define __GFP_REPEAT	((__force gfp_t)___GFP_REPEAT)
+#define __GFP_RETRY_MAYFAIL	((__force gfp_t)___GFP_RETRY_MAYFAIL)
 #define __GFP_NOFAIL	((__force gfp_t)___GFP_NOFAIL)
 #define __GFP_NORETRY	((__force gfp_t)___GFP_NORETRY)
 
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 4634da521238..3e0d405dc842 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -34,7 +34,7 @@ extern char *migrate_reason_names[MR_TYPES];
 static inline struct page *new_page_nodemask(struct page *page,
 				int preferred_nid, nodemask_t *nodemask)
 {
-	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE;
+	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL;
 
 	if (PageHuge(page))
 		return alloc_huge_page_nodemask(page_hstate(compound_head(page)),
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index aa3cd0878270..8aa01fd859fb 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -6,18 +6,26 @@
 
 #include <linux/sched.h>
 #include <asm/irq.h>
+#if defined(CONFIG_HAVE_NMI_WATCHDOG)
+#include <asm/nmi.h>
+#endif
 
 #ifdef CONFIG_LOCKUP_DETECTOR
+void lockup_detector_init(void);
+#else
+static inline void lockup_detector_init(void)
+{
+}
+#endif
+
+#ifdef CONFIG_SOFTLOCKUP_DETECTOR
 extern void touch_softlockup_watchdog_sched(void);
 extern void touch_softlockup_watchdog(void);
 extern void touch_softlockup_watchdog_sync(void);
 extern void touch_all_softlockup_watchdogs(void);
-extern int proc_dowatchdog_thresh(struct ctl_table *table, int write,
-				  void __user *buffer,
-				  size_t *lenp, loff_t *ppos);
 extern unsigned int  softlockup_panic;
-extern unsigned int  hardlockup_panic;
-void lockup_detector_init(void);
+extern int soft_watchdog_enabled;
+extern atomic_t watchdog_park_in_progress;
 #else
 static inline void touch_softlockup_watchdog_sched(void)
 {
@@ -31,9 +39,6 @@ static inline void touch_softlockup_watchdog_sync(void)
 static inline void touch_all_softlockup_watchdogs(void)
 {
 }
-static inline void lockup_detector_init(void)
-{
-}
 #endif
 
 #ifdef CONFIG_DETECT_HUNG_TASK
@@ -61,6 +66,21 @@ static inline void reset_hung_task_detector(void)
 #define NMI_WATCHDOG_ENABLED      (1 << NMI_WATCHDOG_ENABLED_BIT)
 #define SOFT_WATCHDOG_ENABLED     (1 << SOFT_WATCHDOG_ENABLED_BIT)
 
+#if defined(CONFIG_HARDLOCKUP_DETECTOR)
+extern void hardlockup_detector_disable(void);
+extern unsigned int hardlockup_panic;
+#else
+static inline void hardlockup_detector_disable(void) {}
+#endif
+
+#if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF)
+extern void arch_touch_nmi_watchdog(void);
+#else
+#if !defined(CONFIG_HAVE_NMI_WATCHDOG)
+static inline void arch_touch_nmi_watchdog(void) {}
+#endif
+#endif
+
 /**
  * touch_nmi_watchdog - restart NMI watchdog timeout.
  * 
@@ -68,21 +88,11 @@ static inline void reset_hung_task_detector(void)
  * may be used to reset the timeout - for code which intentionally
  * disables interrupts for a long time. This call is stateless.
  */
-#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
-#include <asm/nmi.h>
-extern void touch_nmi_watchdog(void);
-#else
 static inline void touch_nmi_watchdog(void)
 {
+	arch_touch_nmi_watchdog();
 	touch_softlockup_watchdog();
 }
-#endif
-
-#if defined(CONFIG_HARDLOCKUP_DETECTOR)
-extern void hardlockup_detector_disable(void);
-#else
-static inline void hardlockup_detector_disable(void) {}
-#endif
 
 /*
  * Create trigger_all_cpu_backtrace() out of the arch-provided
@@ -139,15 +149,18 @@ static inline bool trigger_single_cpu_backtrace(int cpu)
 }
 #endif
 
-#ifdef CONFIG_LOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
 u64 hw_nmi_get_sample_period(int watchdog_thresh);
+#endif
+
+#ifdef CONFIG_LOCKUP_DETECTOR
 extern int nmi_watchdog_enabled;
-extern int soft_watchdog_enabled;
 extern int watchdog_user_enabled;
 extern int watchdog_thresh;
 extern unsigned long watchdog_enabled;
+extern struct cpumask watchdog_cpumask;
 extern unsigned long *watchdog_cpumask_bits;
-extern atomic_t watchdog_park_in_progress;
+extern int __read_mostly watchdog_suspended;
 #ifdef CONFIG_SMP
 extern int sysctl_softlockup_all_cpu_backtrace;
 extern int sysctl_hardlockup_all_cpu_backtrace;
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 04a7f7993e67..41473df6dfb0 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -471,7 +471,8 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
  *
  * %__GFP_NOWARN - If allocation fails, don't issue any warnings.
  *
- * %__GFP_REPEAT - If allocation fails initially, try once more before failing.
+ * %__GFP_RETRY_MAYFAIL - Try really hard to succeed the allocation but fail
+ *   eventually.
  *
  * There are other flags available as well, but these are not intended
  * for general use, and so are not documented here. For a full list of
diff --git a/include/linux/string.h b/include/linux/string.h
index 537918f8a98e..2215431b7a04 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -187,4 +187,204 @@ static inline const char *kbasename(const char *path)
 	return tail ? tail + 1 : path;
 }
 
+#define __FORTIFY_INLINE extern __always_inline __attribute__((gnu_inline))
+#define __RENAME(x) __asm__(#x)
+
+void fortify_panic(const char *name) __noreturn __cold;
+void __read_overflow(void) __compiletime_error("detected read beyond size of object passed as 1st parameter");
+void __read_overflow2(void) __compiletime_error("detected read beyond size of object passed as 2nd parameter");
+void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter");
+
+#if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE)
+__FORTIFY_INLINE char *strcpy(char *p, const char *q)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	size_t q_size = __builtin_object_size(q, 0);
+	if (p_size == (size_t)-1 && q_size == (size_t)-1)
+		return __builtin_strcpy(p, q);
+	if (strscpy(p, q, p_size < q_size ? p_size : q_size) < 0)
+		fortify_panic(__func__);
+	return p;
+}
+
+__FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	if (__builtin_constant_p(size) && p_size < size)
+		__write_overflow();
+	if (p_size < size)
+		fortify_panic(__func__);
+	return __builtin_strncpy(p, q, size);
+}
+
+__FORTIFY_INLINE char *strcat(char *p, const char *q)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	if (p_size == (size_t)-1)
+		return __builtin_strcat(p, q);
+	if (strlcat(p, q, p_size) >= p_size)
+		fortify_panic(__func__);
+	return p;
+}
+
+__FORTIFY_INLINE __kernel_size_t strlen(const char *p)
+{
+	__kernel_size_t ret;
+	size_t p_size = __builtin_object_size(p, 0);
+	if (p_size == (size_t)-1)
+		return __builtin_strlen(p);
+	ret = strnlen(p, p_size);
+	if (p_size <= ret)
+		fortify_panic(__func__);
+	return ret;
+}
+
+extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen);
+__FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	__kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size);
+	if (p_size <= ret && maxlen != ret)
+		fortify_panic(__func__);
+	return ret;
+}
+
+/* defined after fortified strlen to reuse it */
+extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy);
+__FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size)
+{
+	size_t ret;
+	size_t p_size = __builtin_object_size(p, 0);
+	size_t q_size = __builtin_object_size(q, 0);
+	if (p_size == (size_t)-1 && q_size == (size_t)-1)
+		return __real_strlcpy(p, q, size);
+	ret = strlen(q);
+	if (size) {
+		size_t len = (ret >= size) ? size - 1 : ret;
+		if (__builtin_constant_p(len) && len >= p_size)
+			__write_overflow();
+		if (len >= p_size)
+			fortify_panic(__func__);
+		__builtin_memcpy(p, q, len);
+		p[len] = '\0';
+	}
+	return ret;
+}
+
+/* defined after fortified strlen and strnlen to reuse them */
+__FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count)
+{
+	size_t p_len, copy_len;
+	size_t p_size = __builtin_object_size(p, 0);
+	size_t q_size = __builtin_object_size(q, 0);
+	if (p_size == (size_t)-1 && q_size == (size_t)-1)
+		return __builtin_strncat(p, q, count);
+	p_len = strlen(p);
+	copy_len = strnlen(q, count);
+	if (p_size < p_len + copy_len + 1)
+		fortify_panic(__func__);
+	__builtin_memcpy(p + p_len, q, copy_len);
+	p[p_len + copy_len] = '\0';
+	return p;
+}
+
+__FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	if (__builtin_constant_p(size) && p_size < size)
+		__write_overflow();
+	if (p_size < size)
+		fortify_panic(__func__);
+	return __builtin_memset(p, c, size);
+}
+
+__FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	size_t q_size = __builtin_object_size(q, 0);
+	if (__builtin_constant_p(size)) {
+		if (p_size < size)
+			__write_overflow();
+		if (q_size < size)
+			__read_overflow2();
+	}
+	if (p_size < size || q_size < size)
+		fortify_panic(__func__);
+	return __builtin_memcpy(p, q, size);
+}
+
+__FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	size_t q_size = __builtin_object_size(q, 0);
+	if (__builtin_constant_p(size)) {
+		if (p_size < size)
+			__write_overflow();
+		if (q_size < size)
+			__read_overflow2();
+	}
+	if (p_size < size || q_size < size)
+		fortify_panic(__func__);
+	return __builtin_memmove(p, q, size);
+}
+
+extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan);
+__FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	if (__builtin_constant_p(size) && p_size < size)
+		__read_overflow();
+	if (p_size < size)
+		fortify_panic(__func__);
+	return __real_memscan(p, c, size);
+}
+
+__FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	size_t q_size = __builtin_object_size(q, 0);
+	if (__builtin_constant_p(size)) {
+		if (p_size < size)
+			__read_overflow();
+		if (q_size < size)
+			__read_overflow2();
+	}
+	if (p_size < size || q_size < size)
+		fortify_panic(__func__);
+	return __builtin_memcmp(p, q, size);
+}
+
+__FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	if (__builtin_constant_p(size) && p_size < size)
+		__read_overflow();
+	if (p_size < size)
+		fortify_panic(__func__);
+	return __builtin_memchr(p, c, size);
+}
+
+void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv);
+__FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	if (__builtin_constant_p(size) && p_size < size)
+		__read_overflow();
+	if (p_size < size)
+		fortify_panic(__func__);
+	return __real_memchr_inv(p, c, size);
+}
+
+extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup);
+__FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp)
+{
+	size_t p_size = __builtin_object_size(p, 0);
+	if (__builtin_constant_p(size) && p_size < size)
+		__read_overflow();
+	if (p_size < size)
+		fortify_panic(__func__);
+	return __real_kmemdup(p, size, gfp);
+}
+#endif
+
 #endif /* _LINUX_STRING_H_ */
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 10e3663a75a6..8e50d01c645f 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -34,7 +34,7 @@
 	{(unsigned long)__GFP_FS,		"__GFP_FS"},		\
 	{(unsigned long)__GFP_COLD,		"__GFP_COLD"},		\
 	{(unsigned long)__GFP_NOWARN,		"__GFP_NOWARN"},	\
-	{(unsigned long)__GFP_REPEAT,		"__GFP_REPEAT"},	\
+	{(unsigned long)__GFP_RETRY_MAYFAIL,	"__GFP_RETRY_MAYFAIL"},	\
 	{(unsigned long)__GFP_NOFAIL,		"__GFP_NOFAIL"},	\
 	{(unsigned long)__GFP_NORETRY,		"__GFP_NORETRY"},	\
 	{(unsigned long)__GFP_COMP,		"__GFP_COMP"},		\
diff --git a/kernel/Makefile b/kernel/Makefile
index 72aa080f91f0..4cb8e8b23c6e 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -82,7 +82,7 @@ obj-$(CONFIG_KPROBES) += kprobes.o
 obj-$(CONFIG_KGDB) += debug/
 obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
 obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o
-obj-$(CONFIG_HARDLOCKUP_DETECTOR) += watchdog_hld.o
+obj-$(CONFIG_HARDLOCKUP_DETECTOR_PERF) += watchdog_hld.o
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index f78f719dae36..5710591a9b6d 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -26,13 +26,6 @@
 #include <linux/vmalloc.h>
 #include "kexec_internal.h"
 
-/*
- * Declare these symbols weak so that if architecture provides a purgatory,
- * these will be overridden.
- */
-char __weak kexec_purgatory[0];
-size_t __weak kexec_purgatory_size = 0;
-
 static int kexec_calculate_store_digests(struct kimage *image);
 
 /* Architectures can provide this probe function */
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index 799a8a452187..50dfcb039a41 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -17,6 +17,8 @@ extern struct mutex kexec_mutex;
 #ifdef CONFIG_KEXEC_FILE
 #include <linux/purgatory.h>
 void kimage_file_post_load_cleanup(struct kimage *image);
+extern char kexec_purgatory[];
+extern size_t kexec_purgatory_size;
 #else /* CONFIG_KEXEC_FILE */
 static inline void kimage_file_post_load_cleanup(struct kimage *image) { }
 #endif /* CONFIG_KEXEC_FILE */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index df9f2a367882..6648fbbb8157 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -901,6 +901,14 @@ static struct ctl_table kern_table[] = {
 #endif
 	},
 	{
+		.procname	= "watchdog_cpumask",
+		.data		= &watchdog_cpumask_bits,
+		.maxlen		= NR_CPUS,
+		.mode		= 0644,
+		.proc_handler	= proc_watchdog_cpumask,
+	},
+#ifdef CONFIG_SOFTLOCKUP_DETECTOR
+	{
 		.procname       = "soft_watchdog",
 		.data           = &soft_watchdog_enabled,
 		.maxlen         = sizeof (int),
@@ -910,13 +918,6 @@ static struct ctl_table kern_table[] = {
 		.extra2		= &one,
 	},
 	{
-		.procname	= "watchdog_cpumask",
-		.data		= &watchdog_cpumask_bits,
-		.maxlen		= NR_CPUS,
-		.mode		= 0644,
-		.proc_handler	= proc_watchdog_cpumask,
-	},
-	{
 		.procname	= "softlockup_panic",
 		.data		= &softlockup_panic,
 		.maxlen		= sizeof(int),
@@ -925,27 +926,29 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_SMP
 	{
-		.procname	= "hardlockup_panic",
-		.data		= &hardlockup_panic,
+		.procname	= "softlockup_all_cpu_backtrace",
+		.data		= &sysctl_softlockup_all_cpu_backtrace,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
+#endif /* CONFIG_SMP */
 #endif
-#ifdef CONFIG_SMP
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
 	{
-		.procname	= "softlockup_all_cpu_backtrace",
-		.data		= &sysctl_softlockup_all_cpu_backtrace,
+		.procname	= "hardlockup_panic",
+		.data		= &hardlockup_panic,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
+#ifdef CONFIG_SMP
 	{
 		.procname	= "hardlockup_all_cpu_backtrace",
 		.data		= &sysctl_hardlockup_all_cpu_backtrace,
@@ -957,6 +960,8 @@ static struct ctl_table kern_table[] = {
 	},
 #endif /* CONFIG_SMP */
 #endif
+#endif
+
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
 	{
 		.procname       = "unknown_nmi_panic",
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 03e0b69bb5bf..cabe3e9fb620 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -29,15 +29,58 @@
 #include <linux/kvm_para.h>
 #include <linux/kthread.h>
 
+/* Watchdog configuration */
 static DEFINE_MUTEX(watchdog_proc_mutex);
 
-#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
-unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED|NMI_WATCHDOG_ENABLED;
+int __read_mostly nmi_watchdog_enabled;
+
+#if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG)
+unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED |
+						NMI_WATCHDOG_ENABLED;
 #else
 unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED;
 #endif
-int __read_mostly nmi_watchdog_enabled;
+
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
+/* boot commands */
+/*
+ * Should we panic when a soft-lockup or hard-lockup occurs:
+ */
+unsigned int __read_mostly hardlockup_panic =
+			CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE;
+/*
+ * We may not want to enable hard lockup detection by default in all cases,
+ * for example when running the kernel as a guest on a hypervisor. In these
+ * cases this function can be called to disable hard lockup detection. This
+ * function should only be executed once by the boot processor before the
+ * kernel command line parameters are parsed, because otherwise it is not
+ * possible to override this in hardlockup_panic_setup().
+ */
+void hardlockup_detector_disable(void)
+{
+	watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
+}
+
+static int __init hardlockup_panic_setup(char *str)
+{
+	if (!strncmp(str, "panic", 5))
+		hardlockup_panic = 1;
+	else if (!strncmp(str, "nopanic", 7))
+		hardlockup_panic = 0;
+	else if (!strncmp(str, "0", 1))
+		watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
+	else if (!strncmp(str, "1", 1))
+		watchdog_enabled |= NMI_WATCHDOG_ENABLED;
+	return 1;
+}
+__setup("nmi_watchdog=", hardlockup_panic_setup);
+
+#endif
+
+#ifdef CONFIG_SOFTLOCKUP_DETECTOR
 int __read_mostly soft_watchdog_enabled;
+#endif
+
 int __read_mostly watchdog_user_enabled;
 int __read_mostly watchdog_thresh = 10;
 
@@ -45,15 +88,9 @@ int __read_mostly watchdog_thresh = 10;
 int __read_mostly sysctl_softlockup_all_cpu_backtrace;
 int __read_mostly sysctl_hardlockup_all_cpu_backtrace;
 #endif
-static struct cpumask watchdog_cpumask __read_mostly;
+struct cpumask watchdog_cpumask __read_mostly;
 unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
 
-/* Helper for online, unparked cpus. */
-#define for_each_watchdog_cpu(cpu) \
-	for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
-
-atomic_t watchdog_park_in_progress = ATOMIC_INIT(0);
-
 /*
  * The 'watchdog_running' variable is set to 1 when the watchdog threads
  * are registered/started and is set to 0 when the watchdog threads are
@@ -72,7 +109,47 @@ static int __read_mostly watchdog_running;
  * of 'watchdog_running' cannot change while the watchdog is deactivated
  * temporarily (see related code in 'proc' handlers).
  */
-static int __read_mostly watchdog_suspended;
+int __read_mostly watchdog_suspended;
+
+/*
+ * These functions can be overridden if an architecture implements its
+ * own hardlockup detector.
+ *
+ * watchdog_nmi_enable/disable can be implemented to start and stop when
+ * softlockup watchdog threads start and stop. The arch must select the
+ * SOFTLOCKUP_DETECTOR Kconfig.
+ */
+int __weak watchdog_nmi_enable(unsigned int cpu)
+{
+	return 0;
+}
+void __weak watchdog_nmi_disable(unsigned int cpu)
+{
+}
+
+/*
+ * watchdog_nmi_reconfigure can be implemented to be notified after any
+ * watchdog configuration change. The arch hardlockup watchdog should
+ * respond to the following variables:
+ * - nmi_watchdog_enabled
+ * - watchdog_thresh
+ * - watchdog_cpumask
+ * - sysctl_hardlockup_all_cpu_backtrace
+ * - hardlockup_panic
+ * - watchdog_suspended
+ */
+void __weak watchdog_nmi_reconfigure(void)
+{
+}
+
+
+#ifdef CONFIG_SOFTLOCKUP_DETECTOR
+
+/* Helper for online, unparked cpus. */
+#define for_each_watchdog_cpu(cpu) \
+	for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
+
+atomic_t watchdog_park_in_progress = ATOMIC_INIT(0);
 
 static u64 __read_mostly sample_period;
 
@@ -120,6 +197,7 @@ static int __init softlockup_all_cpu_backtrace_setup(char *str)
 	return 1;
 }
 __setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup);
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
 static int __init hardlockup_all_cpu_backtrace_setup(char *str)
 {
 	sysctl_hardlockup_all_cpu_backtrace =
@@ -128,6 +206,7 @@ static int __init hardlockup_all_cpu_backtrace_setup(char *str)
 }
 __setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup);
 #endif
+#endif
 
 /*
  * Hard-lockup warnings should be triggered after just a few seconds. Soft-
@@ -213,18 +292,6 @@ void touch_softlockup_watchdog_sync(void)
 	__this_cpu_write(watchdog_touch_ts, 0);
 }
 
-/* watchdog detector functions */
-bool is_hardlockup(void)
-{
-	unsigned long hrint = __this_cpu_read(hrtimer_interrupts);
-
-	if (__this_cpu_read(hrtimer_interrupts_saved) == hrint)
-		return true;
-
-	__this_cpu_write(hrtimer_interrupts_saved, hrint);
-	return false;
-}
-
 static int is_softlockup(unsigned long touch_ts)
 {
 	unsigned long now = get_timestamp();
@@ -237,21 +304,21 @@ static int is_softlockup(unsigned long touch_ts)
 	return 0;
 }
 
-static void watchdog_interrupt_count(void)
+/* watchdog detector functions */
+bool is_hardlockup(void)
 {
-	__this_cpu_inc(hrtimer_interrupts);
-}
+	unsigned long hrint = __this_cpu_read(hrtimer_interrupts);
 
-/*
- * These two functions are mostly architecture specific
- * defining them as weak here.
- */
-int __weak watchdog_nmi_enable(unsigned int cpu)
-{
-	return 0;
+	if (__this_cpu_read(hrtimer_interrupts_saved) == hrint)
+		return true;
+
+	__this_cpu_write(hrtimer_interrupts_saved, hrint);
+	return false;
 }
-void __weak watchdog_nmi_disable(unsigned int cpu)
+
+static void watchdog_interrupt_count(void)
 {
+	__this_cpu_inc(hrtimer_interrupts);
 }
 
 static int watchdog_enable_all_cpus(void);
@@ -502,57 +569,6 @@ static void watchdog_unpark_threads(void)
 		kthread_unpark(per_cpu(softlockup_watchdog, cpu));
 }
 
-/*
- * Suspend the hard and soft lockup detector by parking the watchdog threads.
- */
-int lockup_detector_suspend(void)
-{
-	int ret = 0;
-
-	get_online_cpus();
-	mutex_lock(&watchdog_proc_mutex);
-	/*
-	 * Multiple suspend requests can be active in parallel (counted by
-	 * the 'watchdog_suspended' variable). If the watchdog threads are
-	 * running, the first caller takes care that they will be parked.
-	 * The state of 'watchdog_running' cannot change while a suspend
-	 * request is active (see related code in 'proc' handlers).
-	 */
-	if (watchdog_running && !watchdog_suspended)
-		ret = watchdog_park_threads();
-
-	if (ret == 0)
-		watchdog_suspended++;
-	else {
-		watchdog_disable_all_cpus();
-		pr_err("Failed to suspend lockup detectors, disabled\n");
-		watchdog_enabled = 0;
-	}
-
-	mutex_unlock(&watchdog_proc_mutex);
-
-	return ret;
-}
-
-/*
- * Resume the hard and soft lockup detector by unparking the watchdog threads.
- */
-void lockup_detector_resume(void)
-{
-	mutex_lock(&watchdog_proc_mutex);
-
-	watchdog_suspended--;
-	/*
-	 * The watchdog threads are unparked if they were previously running
-	 * and if there is no more active suspend request.
-	 */
-	if (watchdog_running && !watchdog_suspended)
-		watchdog_unpark_threads();
-
-	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
-}
-
 static int update_watchdog_all_cpus(void)
 {
 	int ret;
@@ -605,6 +621,100 @@ static void watchdog_disable_all_cpus(void)
 }
 
 #ifdef CONFIG_SYSCTL
+static int watchdog_update_cpus(void)
+{
+	return smpboot_update_cpumask_percpu_thread(
+		    &watchdog_threads, &watchdog_cpumask);
+}
+#endif
+
+#else /* SOFTLOCKUP */
+static int watchdog_park_threads(void)
+{
+	return 0;
+}
+
+static void watchdog_unpark_threads(void)
+{
+}
+
+static int watchdog_enable_all_cpus(void)
+{
+	return 0;
+}
+
+static void watchdog_disable_all_cpus(void)
+{
+}
+
+#ifdef CONFIG_SYSCTL
+static int watchdog_update_cpus(void)
+{
+	return 0;
+}
+#endif
+
+static void set_sample_period(void)
+{
+}
+#endif /* SOFTLOCKUP */
+
+/*
+ * Suspend the hard and soft lockup detector by parking the watchdog threads.
+ */
+int lockup_detector_suspend(void)
+{
+	int ret = 0;
+
+	get_online_cpus();
+	mutex_lock(&watchdog_proc_mutex);
+	/*
+	 * Multiple suspend requests can be active in parallel (counted by
+	 * the 'watchdog_suspended' variable). If the watchdog threads are
+	 * running, the first caller takes care that they will be parked.
+	 * The state of 'watchdog_running' cannot change while a suspend
+	 * request is active (see related code in 'proc' handlers).
+	 */
+	if (watchdog_running && !watchdog_suspended)
+		ret = watchdog_park_threads();
+
+	if (ret == 0)
+		watchdog_suspended++;
+	else {
+		watchdog_disable_all_cpus();
+		pr_err("Failed to suspend lockup detectors, disabled\n");
+		watchdog_enabled = 0;
+	}
+
+	watchdog_nmi_reconfigure();
+
+	mutex_unlock(&watchdog_proc_mutex);
+
+	return ret;
+}
+
+/*
+ * Resume the hard and soft lockup detector by unparking the watchdog threads.
+ */
+void lockup_detector_resume(void)
+{
+	mutex_lock(&watchdog_proc_mutex);
+
+	watchdog_suspended--;
+	/*
+	 * The watchdog threads are unparked if they were previously running
+	 * and if there is no more active suspend request.
+	 */
+	if (watchdog_running && !watchdog_suspended)
+		watchdog_unpark_threads();
+
+	watchdog_nmi_reconfigure();
+
+	mutex_unlock(&watchdog_proc_mutex);
+	put_online_cpus();
+}
+
+#ifdef CONFIG_SYSCTL
 
 /*
  * Update the run state of the lockup detectors.
@@ -625,6 +735,8 @@ static int proc_watchdog_update(void)
 	else
 		watchdog_disable_all_cpus();
 
+	watchdog_nmi_reconfigure();
+
 	return err;
 
 }
@@ -810,10 +922,11 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write,
 			 * a temporary cpumask, so we are likely not in a
 			 * position to do much else to make things better.
 			 */
-			if (smpboot_update_cpumask_percpu_thread(
-				    &watchdog_threads, &watchdog_cpumask) != 0)
+			if (watchdog_update_cpus() != 0)
 				pr_err("cpumask update failed\n");
 		}
+
+		watchdog_nmi_reconfigure();
 	}
 out:
 	mutex_unlock(&watchdog_proc_mutex);
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 54a427d1f344..295a0d84934c 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -22,41 +22,9 @@ static DEFINE_PER_CPU(bool, hard_watchdog_warn);
 static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
 
-/* boot commands */
-/*
- * Should we panic when a soft-lockup or hard-lockup occurs:
- */
-unsigned int __read_mostly hardlockup_panic =
-			CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE;
 static unsigned long hardlockup_allcpu_dumped;
-/*
- * We may not want to enable hard lockup detection by default in all cases,
- * for example when running the kernel as a guest on a hypervisor. In these
- * cases this function can be called to disable hard lockup detection. This
- * function should only be executed once by the boot processor before the
- * kernel command line parameters are parsed, because otherwise it is not
- * possible to override this in hardlockup_panic_setup().
- */
-void hardlockup_detector_disable(void)
-{
-	watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
-}
-
-static int __init hardlockup_panic_setup(char *str)
-{
-	if (!strncmp(str, "panic", 5))
-		hardlockup_panic = 1;
-	else if (!strncmp(str, "nopanic", 7))
-		hardlockup_panic = 0;
-	else if (!strncmp(str, "0", 1))
-		watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
-	else if (!strncmp(str, "1", 1))
-		watchdog_enabled |= NMI_WATCHDOG_ENABLED;
-	return 1;
-}
-__setup("nmi_watchdog=", hardlockup_panic_setup);
 
-void touch_nmi_watchdog(void)
+void arch_touch_nmi_watchdog(void)
 {
 	/*
 	 * Using __raw here because some code paths have
@@ -66,9 +34,8 @@ void touch_nmi_watchdog(void)
 	 * going off.
 	 */
 	raw_cpu_write(watchdog_nmi_touch, true);
-	touch_softlockup_watchdog();
 }
-EXPORT_SYMBOL(touch_nmi_watchdog);
+EXPORT_SYMBOL(arch_touch_nmi_watchdog);
 
 static struct perf_event_attr wd_hw_attr = {
 	.type		= PERF_TYPE_HARDWARE,
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 4121c7fdd5a8..0e0ecc8bd076 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -778,34 +778,45 @@ config DEBUG_SHIRQ
 menu "Debug Lockups and Hangs"
 
 config LOCKUP_DETECTOR
-	bool "Detect Hard and Soft Lockups"
+	bool
+
+config SOFTLOCKUP_DETECTOR
+	bool "Detect Soft Lockups"
 	depends on DEBUG_KERNEL && !S390
+	select LOCKUP_DETECTOR
 	help
 	  Say Y here to enable the kernel to act as a watchdog to detect
-	  hard and soft lockups.
+	  soft lockups.
 
 	  Softlockups are bugs that cause the kernel to loop in kernel
 	  mode for more than 20 seconds, without giving other tasks a
 	  chance to run.  The current stack trace is displayed upon
 	  detection and the system will stay locked up.
 
+config HARDLOCKUP_DETECTOR_PERF
+	bool
+	select SOFTLOCKUP_DETECTOR
+
+#
+# arch/ can define HAVE_HARDLOCKUP_DETECTOR_ARCH to provide their own hard
+# lockup detector rather than the perf based detector.
+#
+config HARDLOCKUP_DETECTOR
+	bool "Detect Hard Lockups"
+	depends on DEBUG_KERNEL && !S390
+	depends on HAVE_HARDLOCKUP_DETECTOR_PERF || HAVE_HARDLOCKUP_DETECTOR_ARCH
+	select LOCKUP_DETECTOR
+	select HARDLOCKUP_DETECTOR_PERF if HAVE_HARDLOCKUP_DETECTOR_PERF
+	select HARDLOCKUP_DETECTOR_ARCH if HAVE_HARDLOCKUP_DETECTOR_ARCH
+	help
+	  Say Y here to enable the kernel to act as a watchdog to detect
+	  hard lockups.
+
 	  Hardlockups are bugs that cause the CPU to loop in kernel mode
 	  for more than 10 seconds, without letting other interrupts have a
 	  chance to run.  The current stack trace is displayed upon detection
 	  and the system will stay locked up.
 
-	  The overhead should be minimal.  A periodic hrtimer runs to
-	  generate interrupts and kick the watchdog task every 4 seconds.
-	  An NMI is generated every 10 seconds or so to check for hardlockups.
-
-	  The frequency of hrtimer and NMI events and the soft and hard lockup
-	  thresholds can be controlled through the sysctl watchdog_thresh.
-
-config HARDLOCKUP_DETECTOR
-	def_bool y
-	depends on LOCKUP_DETECTOR && !HAVE_NMI_WATCHDOG
-	depends on PERF_EVENTS && HAVE_PERF_EVENTS_NMI
-
 config BOOTPARAM_HARDLOCKUP_PANIC
 	bool "Panic (Reboot) On Hard Lockups"
 	depends on HARDLOCKUP_DETECTOR
@@ -826,7 +837,7 @@ config BOOTPARAM_HARDLOCKUP_PANIC_VALUE
 
 config BOOTPARAM_SOFTLOCKUP_PANIC
 	bool "Panic (Reboot) On Soft Lockups"
-	depends on LOCKUP_DETECTOR
+	depends on SOFTLOCKUP_DETECTOR
 	help
 	  Say Y here to enable the kernel to panic on "soft lockups",
 	  which are bugs that cause the kernel to loop in kernel
@@ -843,7 +854,7 @@ config BOOTPARAM_SOFTLOCKUP_PANIC
 
 config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
 	int
-	depends on LOCKUP_DETECTOR
+	depends on SOFTLOCKUP_DETECTOR
 	range 0 1
 	default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC
 	default 1 if BOOTPARAM_SOFTLOCKUP_PANIC
@@ -851,7 +862,7 @@ config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
 config DETECT_HUNG_TASK
 	bool "Detect Hung Tasks"
 	depends on DEBUG_KERNEL
-	default LOCKUP_DETECTOR
+	default SOFTLOCKUP_DETECTOR
 	help
 	  Say Y here to enable the kernel to detect "hung tasks",
 	  which are bugs that cause the task to be stuck in
diff --git a/lib/crc-ccitt.c b/lib/crc-ccitt.c
index 7f6dd68d2d09..d873b34039ff 100644
--- a/lib/crc-ccitt.c
+++ b/lib/crc-ccitt.c
@@ -51,8 +51,49 @@ u16 const crc_ccitt_table[256] = {
 };
 EXPORT_SYMBOL(crc_ccitt_table);
 
+/*
+ * Similar table to calculate CRC16 variant known as CRC-CCITT-FALSE
+ * Reflected bits order, does not augment final value.
+ */
+u16 const crc_ccitt_false_table[256] = {
+    0x0000, 0x1021, 0x2042, 0x3063, 0x4084, 0x50A5, 0x60C6, 0x70E7,
+    0x8108, 0x9129, 0xA14A, 0xB16B, 0xC18C, 0xD1AD, 0xE1CE, 0xF1EF,
+    0x1231, 0x0210, 0x3273, 0x2252, 0x52B5, 0x4294, 0x72F7, 0x62D6,
+    0x9339, 0x8318, 0xB37B, 0xA35A, 0xD3BD, 0xC39C, 0xF3FF, 0xE3DE,
+    0x2462, 0x3443, 0x0420, 0x1401, 0x64E6, 0x74C7, 0x44A4, 0x5485,
+    0xA56A, 0xB54B, 0x8528, 0x9509, 0xE5EE, 0xF5CF, 0xC5AC, 0xD58D,
+    0x3653, 0x2672, 0x1611, 0x0630, 0x76D7, 0x66F6, 0x5695, 0x46B4,
+    0xB75B, 0xA77A, 0x9719, 0x8738, 0xF7DF, 0xE7FE, 0xD79D, 0xC7BC,
+    0x48C4, 0x58E5, 0x6886, 0x78A7, 0x0840, 0x1861, 0x2802, 0x3823,
+    0xC9CC, 0xD9ED, 0xE98E, 0xF9AF, 0x8948, 0x9969, 0xA90A, 0xB92B,
+    0x5AF5, 0x4AD4, 0x7AB7, 0x6A96, 0x1A71, 0x0A50, 0x3A33, 0x2A12,
+    0xDBFD, 0xCBDC, 0xFBBF, 0xEB9E, 0x9B79, 0x8B58, 0xBB3B, 0xAB1A,
+    0x6CA6, 0x7C87, 0x4CE4, 0x5CC5, 0x2C22, 0x3C03, 0x0C60, 0x1C41,
+    0xEDAE, 0xFD8F, 0xCDEC, 0xDDCD, 0xAD2A, 0xBD0B, 0x8D68, 0x9D49,
+    0x7E97, 0x6EB6, 0x5ED5, 0x4EF4, 0x3E13, 0x2E32, 0x1E51, 0x0E70,
+    0xFF9F, 0xEFBE, 0xDFDD, 0xCFFC, 0xBF1B, 0xAF3A, 0x9F59, 0x8F78,
+    0x9188, 0x81A9, 0xB1CA, 0xA1EB, 0xD10C, 0xC12D, 0xF14E, 0xE16F,
+    0x1080, 0x00A1, 0x30C2, 0x20E3, 0x5004, 0x4025, 0x7046, 0x6067,
+    0x83B9, 0x9398, 0xA3FB, 0xB3DA, 0xC33D, 0xD31C, 0xE37F, 0xF35E,
+    0x02B1, 0x1290, 0x22F3, 0x32D2, 0x4235, 0x5214, 0x6277, 0x7256,
+    0xB5EA, 0xA5CB, 0x95A8, 0x8589, 0xF56E, 0xE54F, 0xD52C, 0xC50D,
+    0x34E2, 0x24C3, 0x14A0, 0x0481, 0x7466, 0x6447, 0x5424, 0x4405,
+    0xA7DB, 0xB7FA, 0x8799, 0x97B8, 0xE75F, 0xF77E, 0xC71D, 0xD73C,
+    0x26D3, 0x36F2, 0x0691, 0x16B0, 0x6657, 0x7676, 0x4615, 0x5634,
+    0xD94C, 0xC96D, 0xF90E, 0xE92F, 0x99C8, 0x89E9, 0xB98A, 0xA9AB,
+    0x5844, 0x4865, 0x7806, 0x6827, 0x18C0, 0x08E1, 0x3882, 0x28A3,
+    0xCB7D, 0xDB5C, 0xEB3F, 0xFB1E, 0x8BF9, 0x9BD8, 0xABBB, 0xBB9A,
+    0x4A75, 0x5A54, 0x6A37, 0x7A16, 0x0AF1, 0x1AD0, 0x2AB3, 0x3A92,
+    0xFD2E, 0xED0F, 0xDD6C, 0xCD4D, 0xBDAA, 0xAD8B, 0x9DE8, 0x8DC9,
+    0x7C26, 0x6C07, 0x5C64, 0x4C45, 0x3CA2, 0x2C83, 0x1CE0, 0x0CC1,
+    0xEF1F, 0xFF3E, 0xCF5D, 0xDF7C, 0xAF9B, 0xBFBA, 0x8FD9, 0x9FF8,
+    0x6E17, 0x7E36, 0x4E55, 0x5E74, 0x2E93, 0x3EB2, 0x0ED1, 0x1EF0
+};
+EXPORT_SYMBOL(crc_ccitt_false_table);
+
 /**
- *	crc_ccitt - recompute the CRC for the data buffer
+ *	crc_ccitt - recompute the CRC (CRC-CCITT variant) for the data
+ *	buffer
  *	@crc: previous CRC value
  *	@buffer: data pointer
  *	@len: number of bytes in the buffer
@@ -65,5 +106,20 @@ u16 crc_ccitt(u16 crc, u8 const *buffer, size_t len)
 }
 EXPORT_SYMBOL(crc_ccitt);
 
+/**
+ *	crc_ccitt_false - recompute the CRC (CRC-CCITT-FALSE variant)
+ *	for the data buffer
+ *	@crc: previous CRC value
+ *	@buffer: data pointer
+ *	@len: number of bytes in the buffer
+ */
+u16 crc_ccitt_false(u16 crc, u8 const *buffer, size_t len)
+{
+	while (len--)
+		crc = crc_ccitt_false_byte(crc, *buffer++);
+	return crc;
+}
+EXPORT_SYMBOL(crc_ccitt_false);
+
 MODULE_DESCRIPTION("CRC-CCITT calculations");
 MODULE_LICENSE("GPL");
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 8ee7e5ec21be..3bf4a9984f4c 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -72,6 +72,13 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount)
 }
 EXPORT_SYMBOL(percpu_counter_set);
 
+/**
+ * This function is both preempt and irq safe. The former is due to explicit
+ * preemption disable. The latter is guaranteed by the fact that the slow path
+ * is explicitly protected by an irq-safe spinlock whereas the fast patch uses
+ * this_cpu_add which is irq-safe by definition. Hence there is no need muck
+ * with irq state before calling this one
+ */
 void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
 {
 	s64 count;
diff --git a/lib/string.c b/lib/string.c
index 1c1fc9187b05..ebbb99c775bd 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -978,3 +978,10 @@ char *strreplace(char *s, char old, char new)
 	return s;
 }
 EXPORT_SYMBOL(strreplace);
+
+void fortify_panic(const char *name)
+{
+	pr_emerg("detected buffer overflow in %s\n", name);
+	BUG();
+}
+EXPORT_SYMBOL(fortify_panic);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 1e516520433d..bc48ee783dd9 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1384,7 +1384,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 
 	page = __alloc_pages_node(nid,
 		htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE|
-						__GFP_REPEAT|__GFP_NOWARN,
+						__GFP_RETRY_MAYFAIL|__GFP_NOWARN,
 		huge_page_order(h));
 	if (page) {
 		prep_new_huge_page(h, page, nid);
@@ -1525,7 +1525,7 @@ static struct page *__hugetlb_alloc_buddy_huge_page(struct hstate *h,
 {
 	int order = huge_page_order(h);
 
-	gfp_mask |= __GFP_COMP|__GFP_REPEAT|__GFP_NOWARN;
+	gfp_mask |= __GFP_COMP|__GFP_RETRY_MAYFAIL|__GFP_NOWARN;
 	if (nid == NUMA_NO_NODE)
 		nid = numa_mem_id();
 	return __alloc_pages_nodemask(gfp_mask, order, nid, nmask);
diff --git a/mm/internal.h b/mm/internal.h
index 0e4f558412fb..24d88f084705 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -23,7 +23,7 @@
  * hints such as HIGHMEM usage.
  */
 #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\
-			__GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\
+			__GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\
 			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\
 			__GFP_ATOMIC)
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 7d8e56214ac0..d911fa5cb2a7 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1078,7 +1078,8 @@ static struct page *new_page(struct page *page, unsigned long start, int **x)
 	/*
 	 * if !vma, alloc_page_vma() will use task or system default policy
 	 */
-	return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
+	return alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL,
+			vma, address);
 }
 #else
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 0b60cc7ddac2..96e93b214d31 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -601,7 +601,7 @@ static inline void __wb_writeout_inc(struct bdi_writeback *wb)
 {
 	struct wb_domain *cgdom;
 
-	__inc_wb_stat(wb, WB_WRITTEN);
+	inc_wb_stat(wb, WB_WRITTEN);
 	wb_domain_writeout_inc(&global_wb_domain, &wb->completions,
 			       wb->bdi->max_prop_frac);
 
@@ -2435,8 +2435,8 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 		__inc_lruvec_page_state(page, NR_FILE_DIRTY);
 		__inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
 		__inc_node_page_state(page, NR_DIRTIED);
-		__inc_wb_stat(wb, WB_RECLAIMABLE);
-		__inc_wb_stat(wb, WB_DIRTIED);
+		inc_wb_stat(wb, WB_RECLAIMABLE);
+		inc_wb_stat(wb, WB_DIRTIED);
 		task_io_account_write(PAGE_SIZE);
 		current->nr_dirtied++;
 		this_cpu_inc(bdp_ratelimits);
@@ -2741,7 +2741,7 @@ int test_clear_page_writeback(struct page *page)
 			if (bdi_cap_account_writeback(bdi)) {
 				struct bdi_writeback *wb = inode_to_wb(inode);
 
-				__dec_wb_stat(wb, WB_WRITEBACK);
+				dec_wb_stat(wb, WB_WRITEBACK);
 				__wb_writeout_inc(wb);
 			}
 		}
@@ -2786,7 +2786,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 						page_index(page),
 						PAGECACHE_TAG_WRITEBACK);
 			if (bdi_cap_account_writeback(bdi))
-				__inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK);
+				inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK);
 
 			/*
 			 * We can come through here when swapping anonymous
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 35de49c3de8b..2bc48ea53cc9 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3284,6 +3284,14 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	/* The OOM killer will not help higher order allocs */
 	if (order > PAGE_ALLOC_COSTLY_ORDER)
 		goto out;
+	/*
+	 * We have already exhausted all our reclaim opportunities without any
+	 * success so it is time to admit defeat. We will skip the OOM killer
+	 * because it is very likely that the caller has a more reasonable
+	 * fallback than shooting a random task.
+	 */
+	if (gfp_mask & __GFP_RETRY_MAYFAIL)
+		goto out;
 	/* The OOM killer does not needlessly kill tasks for lowmem */
 	if (ac->high_zoneidx < ZONE_NORMAL)
 		goto out;
@@ -3413,7 +3421,7 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
 	}
 
 	/*
-	 * !costly requests are much more important than __GFP_REPEAT
+	 * !costly requests are much more important than __GFP_RETRY_MAYFAIL
 	 * costly ones because they are de facto nofail and invoke OOM
 	 * killer to move on while costly can fail and users are ready
 	 * to cope with that. 1/4 retries is rather arbitrary but we
@@ -3920,9 +3928,9 @@ retry:
 
 	/*
 	 * Do not retry costly high order allocations unless they are
-	 * __GFP_REPEAT
+	 * __GFP_RETRY_MAYFAIL
 	 */
-	if (costly_order && !(gfp_mask & __GFP_REPEAT))
+	if (costly_order && !(gfp_mask & __GFP_RETRY_MAYFAIL))
 		goto nopage;
 
 	if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags,
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index a56c3989f773..c50b1a14d55e 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -56,11 +56,11 @@ void * __meminit vmemmap_alloc_block(unsigned long size, int node)
 
 		if (node_state(node, N_HIGH_MEMORY))
 			page = alloc_pages_node(
-				node, GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT,
+				node, GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL,
 				get_order(size));
 		else
 			page = alloc_pages(
-				GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT,
+				GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL,
 				get_order(size));
 		if (page)
 			return page_address(page);
diff --git a/mm/util.c b/mm/util.c
index 26be6407abd7..ee250e2cde34 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -339,9 +339,9 @@ EXPORT_SYMBOL(vm_mmap);
  * Uses kmalloc to get the memory but if the allocation fails then falls back
  * to the vmalloc allocator. Use kvfree for freeing the memory.
  *
- * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. __GFP_REPEAT
- * is supported only for large (>32kB) allocations, and it should be used only if
- * kmalloc is preferable to the vmalloc fallback, due to visible performance drawbacks.
+ * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported.
+ * __GFP_RETRY_MAYFAIL is supported, and it should be used only if kmalloc is
+ * preferable to the vmalloc fallback, due to visible performance drawbacks.
  *
  * Any use of gfp flags outside of GFP_KERNEL should be consulted with mm people.
  */
@@ -366,13 +366,7 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node)
 	if (size > PAGE_SIZE) {
 		kmalloc_flags |= __GFP_NOWARN;
 
-		/*
-		 * We have to override __GFP_REPEAT by __GFP_NORETRY for !costly
-		 * requests because there is no other way to tell the allocator
-		 * that we want to fail rather than retry endlessly.
-		 */
-		if (!(kmalloc_flags & __GFP_REPEAT) ||
-				(size <= PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
+		if (!(kmalloc_flags & __GFP_RETRY_MAYFAIL))
 			kmalloc_flags |= __GFP_NORETRY;
 	}
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 6016ab079e2b..8698c1c86c4d 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1795,7 +1795,7 @@ fail:
  *	allocator with @gfp_mask flags.  Map them into contiguous
  *	kernel virtual space, using a pagetable protection of @prot.
  *
- *	Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_REPEAT
+ *	Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_RETRY_MAYFAIL
  *	and __GFP_NOFAIL are not supported
  *
  *	Any use of gfp flags outside of GFP_KERNEL should be consulted
diff --git a/mm/vmscan.c b/mm/vmscan.c
index f84cdd3751e1..efc9da21c5e6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2506,18 +2506,18 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat,
 		return false;
 
 	/* Consider stopping depending on scan and reclaim activity */
-	if (sc->gfp_mask & __GFP_REPEAT) {
+	if (sc->gfp_mask & __GFP_RETRY_MAYFAIL) {
 		/*
-		 * For __GFP_REPEAT allocations, stop reclaiming if the
+		 * For __GFP_RETRY_MAYFAIL allocations, stop reclaiming if the
 		 * full LRU list has been scanned and we are still failing
 		 * to reclaim pages. This full LRU scan is potentially
-		 * expensive but a __GFP_REPEAT caller really wants to succeed
+		 * expensive but a __GFP_RETRY_MAYFAIL caller really wants to succeed
 		 */
 		if (!nr_reclaimed && !nr_scanned)
 			return false;
 	} else {
 		/*
-		 * For non-__GFP_REPEAT allocations which can presumably
+		 * For non-__GFP_RETRY_MAYFAIL allocations which can presumably
 		 * fail without consequence, stop if we failed to reclaim
 		 * any pages from the last SWAP_CLUSTER_MAX number of
 		 * pages that were scanned. This will return to the
diff --git a/net/core/dev.c b/net/core/dev.c
index 9be778ba7857..73fb6a28e7de 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7373,7 +7373,7 @@ static int netif_alloc_rx_queues(struct net_device *dev)
 
 	BUG_ON(count < 1);
 
-	rx = kvzalloc(sz, GFP_KERNEL | __GFP_REPEAT);
+	rx = kvzalloc(sz, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!rx)
 		return -ENOMEM;
 
@@ -7413,7 +7413,7 @@ static int netif_alloc_netdev_queues(struct net_device *dev)
 	if (count < 1 || count > 0xffff)
 		return -EINVAL;
 
-	tx = kvzalloc(sz, GFP_KERNEL | __GFP_REPEAT);
+	tx = kvzalloc(sz, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!tx)
 		return -ENOMEM;
 
@@ -7954,7 +7954,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	/* ensure 32-byte alignment of whole construct */
 	alloc_size += NETDEV_ALIGN - 1;
 
-	p = kvzalloc(alloc_size, GFP_KERNEL | __GFP_REPEAT);
+	p = kvzalloc(alloc_size, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!p)
 		return NULL;
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f75897a33fa4..2bff10a20bc9 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4747,7 +4747,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
 
 	gfp_head = gfp_mask;
 	if (gfp_head & __GFP_DIRECT_RECLAIM)
-		gfp_head |= __GFP_REPEAT;
+		gfp_head |= __GFP_RETRY_MAYFAIL;
 
 	*errcode = -ENOBUFS;
 	skb = alloc_skb(header_len, gfp_head);
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 1770c1d9b37f..e1648238a9c9 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1003,14 +1003,10 @@ struct xt_table_info *xt_alloc_table_info(unsigned int size)
 	if ((SMP_ALIGN(size) >> PAGE_SHIFT) + 2 > totalram_pages)
 		return NULL;
 
-	if (sz <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
-		info = kmalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
-	if (!info) {
-		info = __vmalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY,
-				 PAGE_KERNEL);
-		if (!info)
-			return NULL;
-	}
+	info = kvmalloc(sz, GFP_KERNEL);
+	if (!info)
+		return NULL;
+
 	memset(info, 0, sizeof(*info));
 	info->size = size;
 	return info;
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 147fde73a0f5..263d16e3219e 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -648,7 +648,7 @@ static int fq_resize(struct Qdisc *sch, u32 log)
 		return 0;
 
 	/* If XPS was setup, we can allocate memory on right NUMA node */
-	array = kvmalloc_node(sizeof(struct rb_root) << log, GFP_KERNEL | __GFP_REPEAT,
+	array = kvmalloc_node(sizeof(struct rb_root) << log, GFP_KERNEL | __GFP_RETRY_MAYFAIL,
 			      netdev_queue_numa_node_read(sch->dev_queue));
 	if (!array)
 		return -ENOMEM;
diff --git a/security/Kconfig b/security/Kconfig
index d540bfe73190..e8e449444e65 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -163,6 +163,13 @@ config HARDENED_USERCOPY_PAGESPAN
 	  been removed. This config is intended to be used only while
 	  trying to find such users.
 
+config FORTIFY_SOURCE
+	bool "Harden common str/mem functions against buffer overflows"
+	depends on ARCH_HAS_FORTIFY_SOURCE
+	help
+	  Detect overflows of buffers in common string and memory functions
+	  where the compiler can determine and validate the buffer sizes.
+
 config STATIC_USERMODEHELPER
 	bool "Force all usermode helper calls through a single binary"
 	help
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 9409c9464667..c4222ea452e9 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -643,7 +643,7 @@ static const struct {
 	{ "__GFP_FS",			"F" },
 	{ "__GFP_COLD",			"CO" },
 	{ "__GFP_NOWARN",		"NWR" },
-	{ "__GFP_REPEAT",		"R" },
+	{ "__GFP_RETRY_MAYFAIL",	"R" },
 	{ "__GFP_NOFAIL",		"NF" },
 	{ "__GFP_NORETRY",		"NR" },
 	{ "__GFP_COMP",			"C" },