Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	net/sched/act_police.c
	net/sched/sch_drr.c
	net/sched/sch_hfsc.c
	net/sched/sch_prio.c
	net/sched/sch_red.c
	net/sched/sch_tbf.c

In net-next the drop methods of the packet schedulers got removed, so
the bug fixes to them in 'net' are irrelevant.

A packet action unload crash fix conflicts with the addition of the
new firstuse timestamp.

Signed-off-by: David S. Miller <davem@davemloft.net>

68 files changed, 274 insertions, 550 deletions

diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 0dcbacfdea4b..0d3e59f56974 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -61,7 +61,7 @@ config RWSEM_GENERIC_SPINLOCK
 	def_bool y
 
 config ARCH_DISCONTIGMEM_ENABLE
-	def_bool y
+	def_bool n
 
 config ARCH_FLATMEM_ENABLE
 	def_bool y
@@ -186,9 +186,6 @@ if SMP
 config ARC_HAS_COH_CACHES
 	def_bool n
 
-config ARC_HAS_REENTRANT_IRQ_LV2
-	def_bool n
-
 config ARC_MCIP
 	bool "ARConnect Multicore IP (MCIP) Support "
 	depends on ISA_ARCV2
@@ -366,25 +363,10 @@ config NODES_SHIFT
 if ISA_ARCOMPACT
 
 config ARC_COMPACT_IRQ_LEVELS
-	bool "ARCompact IRQ Priorities: High(2)/Low(1)"
+	bool "Setup Timer IRQ as high Priority"
 	default n
-	# Timer HAS to be high priority, for any other high priority config
-	select ARC_IRQ3_LV2
 	# if SMP, LV2 enabled ONLY if ARC implementation has LV2 re-entrancy
-	depends on !SMP || ARC_HAS_REENTRANT_IRQ_LV2
-
-if ARC_COMPACT_IRQ_LEVELS
-
-config ARC_IRQ3_LV2
-	bool
-
-config ARC_IRQ5_LV2
-	bool
-
-config ARC_IRQ6_LV2
-	bool
-
-endif	#ARC_COMPACT_IRQ_LEVELS
+	depends on !SMP
 
 config ARC_FPU_SAVE_RESTORE
 	bool "Enable FPU state persistence across context switch"
@@ -407,11 +389,6 @@ config ARC_HAS_LLSC
 	default y
 	depends on !ARC_CANT_LLSC
 
-config ARC_STAR_9000923308
-	bool "Workaround for llock/scond livelock"
-	default n
-	depends on ISA_ARCV2 && SMP && ARC_HAS_LLSC
-
 config ARC_HAS_SWAPE
 	bool "Insn: SWAPE (endian-swap)"
 	default y
@@ -471,7 +448,7 @@ config LINUX_LINK_BASE
 
 config HIGHMEM
 	bool "High Memory Support"
-	select DISCONTIGMEM
+	select ARCH_DISCONTIGMEM_ENABLE
 	help
 	  With ARC 2G:2G address split, only upper 2G is directly addressable by
 	  kernel. Enable this to potentially allow access to rest of 2G and PAE
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 02fabef2891c..d4df6be66d58 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -127,7 +127,7 @@ libs-y		+= arch/arc/lib/ $(LIBGCC)
 
 boot		:= arch/arc/boot
 
-#default target for make without any arguements.
+#default target for make without any arguments.
 KBUILD_IMAGE	:= bootpImage
 
 all:	$(KBUILD_IMAGE)
diff --git a/arch/arc/boot/dts/abilis_tb100.dtsi b/arch/arc/boot/dts/abilis_tb100.dtsi
index 3942634f805a..02410b211433 100644
--- a/arch/arc/boot/dts/abilis_tb100.dtsi
+++ b/arch/arc/boot/dts/abilis_tb100.dtsi
@@ -23,8 +23,6 @@
 
 
 / {
-	clock-frequency		= <500000000>;	/* 500 MHZ */
-
 	soc100 {
 		bus-frequency	= <166666666>;
 
diff --git a/arch/arc/boot/dts/abilis_tb101.dtsi b/arch/arc/boot/dts/abilis_tb101.dtsi
index b0467229a5c4..f9e7686044eb 100644
--- a/arch/arc/boot/dts/abilis_tb101.dtsi
+++ b/arch/arc/boot/dts/abilis_tb101.dtsi
@@ -23,8 +23,6 @@
 
 
 / {
-	clock-frequency		= <500000000>;	/* 500 MHZ */
-
 	soc100 {
 		bus-frequency	= <166666666>;
 
diff --git a/arch/arc/boot/dts/axc001.dtsi b/arch/arc/boot/dts/axc001.dtsi
index 3e02f152edcb..6ae2c476ad82 100644
--- a/arch/arc/boot/dts/axc001.dtsi
+++ b/arch/arc/boot/dts/axc001.dtsi
@@ -15,7 +15,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <750000000>;	/* 750 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi
index 378e455a94c4..14df46f141bf 100644
--- a/arch/arc/boot/dts/axc003.dtsi
+++ b/arch/arc/boot/dts/axc003.dtsi
@@ -14,7 +14,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <90000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi
index 64c94b2860ab..3d6cfa32bf51 100644
--- a/arch/arc/boot/dts/axc003_idu.dtsi
+++ b/arch/arc/boot/dts/axc003_idu.dtsi
@@ -14,7 +14,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <90000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/boot/dts/eznps.dts b/arch/arc/boot/dts/eznps.dts
index b89f6c3eb352..1e0d225791c1 100644
--- a/arch/arc/boot/dts/eznps.dts
+++ b/arch/arc/boot/dts/eznps.dts
@@ -18,7 +18,6 @@
 
 / {
 	compatible = "ezchip,arc-nps";
-	clock-frequency = <83333333>;	/* 83.333333 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	interrupt-parent = <&intc>;
diff --git a/arch/arc/boot/dts/nsim_700.dts b/arch/arc/boot/dts/nsim_700.dts
index 5d5e373e0ebc..63970513e4ae 100644
--- a/arch/arc/boot/dts/nsim_700.dts
+++ b/arch/arc/boot/dts/nsim_700.dts
@@ -11,7 +11,6 @@
 
 / {
 	compatible = "snps,nsim";
-	clock-frequency = <80000000>;	/* 80 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	interrupt-parent = <&core_intc>;
diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts
index b5b060adce8a..763d66c883da 100644
--- a/arch/arc/boot/dts/nsimosci.dts
+++ b/arch/arc/boot/dts/nsimosci.dts
@@ -11,7 +11,6 @@
 
 / {
 	compatible = "snps,nsimosci";
-	clock-frequency = <20000000>;	/* 20 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	interrupt-parent = <&core_intc>;
diff --git a/arch/arc/boot/dts/nsimosci_hs.dts b/arch/arc/boot/dts/nsimosci_hs.dts
index 325e73090a18..4eb97c584b18 100644
--- a/arch/arc/boot/dts/nsimosci_hs.dts
+++ b/arch/arc/boot/dts/nsimosci_hs.dts
@@ -11,7 +11,6 @@
 
 / {
 	compatible = "snps,nsimosci_hs";
-	clock-frequency = <20000000>;	/* 20 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	interrupt-parent = <&core_intc>;
diff --git a/arch/arc/boot/dts/nsimosci_hs_idu.dts b/arch/arc/boot/dts/nsimosci_hs_idu.dts
index ee03d7126581..853f897eb2a3 100644
--- a/arch/arc/boot/dts/nsimosci_hs_idu.dts
+++ b/arch/arc/boot/dts/nsimosci_hs_idu.dts
@@ -11,7 +11,6 @@
 
 / {
 	compatible = "snps,nsimosci_hs";
-	clock-frequency = <5000000>;	/* 5 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	interrupt-parent = <&core_intc>;
diff --git a/arch/arc/boot/dts/skeleton.dtsi b/arch/arc/boot/dts/skeleton.dtsi
index 3a10cc633e2b..65808fe0a290 100644
--- a/arch/arc/boot/dts/skeleton.dtsi
+++ b/arch/arc/boot/dts/skeleton.dtsi
@@ -13,7 +13,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <80000000>;	/* 80 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	chosen { };
diff --git a/arch/arc/boot/dts/skeleton_hs.dtsi b/arch/arc/boot/dts/skeleton_hs.dtsi
index 71fd308a9298..2dfe8037dfbb 100644
--- a/arch/arc/boot/dts/skeleton_hs.dtsi
+++ b/arch/arc/boot/dts/skeleton_hs.dtsi
@@ -8,7 +8,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <80000000>;	/* 80 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	chosen { };
diff --git a/arch/arc/boot/dts/skeleton_hs_idu.dtsi b/arch/arc/boot/dts/skeleton_hs_idu.dtsi
index d1cb25a66989..4c11079f3565 100644
--- a/arch/arc/boot/dts/skeleton_hs_idu.dtsi
+++ b/arch/arc/boot/dts/skeleton_hs_idu.dtsi
@@ -8,7 +8,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <80000000>;	/* 80 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	chosen { };
diff --git a/arch/arc/boot/dts/vdk_axc003.dtsi b/arch/arc/boot/dts/vdk_axc003.dtsi
index ad4ee43bd2ac..0fd6ba985b16 100644
--- a/arch/arc/boot/dts/vdk_axc003.dtsi
+++ b/arch/arc/boot/dts/vdk_axc003.dtsi
@@ -14,7 +14,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <50000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/boot/dts/vdk_axc003_idu.dtsi b/arch/arc/boot/dts/vdk_axc003_idu.dtsi
index a3cb6263c581..82214cd7ba0c 100644
--- a/arch/arc/boot/dts/vdk_axc003_idu.dtsi
+++ b/arch/arc/boot/dts/vdk_axc003_idu.dtsi
@@ -15,7 +15,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <50000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 5f3dcbbc0cc9..dd683995bc9d 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -25,50 +25,17 @@
 
 #define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i))
 
-#ifdef CONFIG_ARC_STAR_9000923308
-
-#define SCOND_FAIL_RETRY_VAR_DEF						\
-	unsigned int delay = 1, tmp;						\
-
-#define SCOND_FAIL_RETRY_ASM							\
-	"	bz	4f			\n"				\
-	"   ; --- scond fail delay ---		\n"				\
-	"	mov	%[tmp], %[delay]	\n"	/* tmp = delay */	\
-	"2: 	brne.d	%[tmp], 0, 2b		\n"	/* while (tmp != 0) */	\
-	"	sub	%[tmp], %[tmp], 1	\n"	/* tmp-- */		\
-	"	rol	%[delay], %[delay]	\n"	/* delay *= 2 */	\
-	"	b	1b			\n"	/* start over */	\
-	"4: ; --- success ---			\n"				\
-
-#define SCOND_FAIL_RETRY_VARS							\
-	  ,[delay] "+&r" (delay),[tmp] "=&r"	(tmp)				\
-
-#else	/* !CONFIG_ARC_STAR_9000923308 */
-
-#define SCOND_FAIL_RETRY_VAR_DEF
-
-#define SCOND_FAIL_RETRY_ASM							\
-	"	bnz     1b			\n"				\
-
-#define SCOND_FAIL_RETRY_VARS
-
-#endif
-
 #define ATOMIC_OP(op, c_op, asm_op)					\
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
-	unsigned int val;				                \
-	SCOND_FAIL_RETRY_VAR_DEF                                        \
+	unsigned int val;						\
 									\
 	__asm__ __volatile__(						\
 	"1:	llock   %[val], [%[ctr]]		\n"		\
 	"	" #asm_op " %[val], %[val], %[i]	\n"		\
 	"	scond   %[val], [%[ctr]]		\n"		\
-	"						\n"		\
-	SCOND_FAIL_RETRY_ASM						\
-									\
+	"	bnz     1b				\n"		\
 	: [val]	"=&r"	(val) /* Early clobber to prevent reg reuse */	\
-	  SCOND_FAIL_RETRY_VARS						\
 	: [ctr]	"r"	(&v->counter), /* Not "m": llock only supports reg direct addr mode */	\
 	  [i]	"ir"	(i)						\
 	: "cc");							\
@@ -77,8 +44,7 @@ static inline void atomic_##op(int i, atomic_t *v)			\
 #define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
 static inline int atomic_##op##_return(int i, atomic_t *v)		\
 {									\
-	unsigned int val;				                \
-	SCOND_FAIL_RETRY_VAR_DEF                                        \
+	unsigned int val;						\
 									\
 	/*								\
 	 * Explicit full memory barrier needed before/after as		\
@@ -90,11 +56,8 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	"1:	llock   %[val], [%[ctr]]		\n"		\
 	"	" #asm_op " %[val], %[val], %[i]	\n"		\
 	"	scond   %[val], [%[ctr]]		\n"		\
-	"						\n"		\
-	SCOND_FAIL_RETRY_ASM						\
-									\
+	"	bnz     1b				\n"		\
 	: [val]	"=&r"	(val)						\
-	  SCOND_FAIL_RETRY_VARS						\
 	: [ctr]	"r"	(&v->counter),					\
 	  [i]	"ir"	(i)						\
 	: "cc");							\
diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h
index e0e1faf03c50..14c310f2e0b1 100644
--- a/arch/arc/include/asm/entry-compact.h
+++ b/arch/arc/include/asm/entry-compact.h
@@ -76,8 +76,8 @@
 	 * We need to be a bit more cautious here. What if a kernel bug in
 	 * L1 ISR, caused SP to go whaco (some small value which looks like
 	 * USER stk) and then we take L2 ISR.
-	 * Above brlo alone would treat it as a valid L1-L2 sceanrio
-	 * instead of shouting alound
+	 * Above brlo alone would treat it as a valid L1-L2 scenario
+	 * instead of shouting around
 	 * The only feasible way is to make sure this L2 happened in
 	 * L1 prelogue ONLY i.e. ilink2 is less than a pre-set marker in
 	 * L1 ISR before it switches stack
diff --git a/arch/arc/include/asm/mmu_context.h b/arch/arc/include/asm/mmu_context.h
index 1fd467ef658f..b0b87f2447f5 100644
--- a/arch/arc/include/asm/mmu_context.h
+++ b/arch/arc/include/asm/mmu_context.h
@@ -83,7 +83,7 @@ static inline void get_new_mmu_context(struct mm_struct *mm)
 		local_flush_tlb_all();
 
 		/*
-		 * Above checke for rollover of 8 bit ASID in 32 bit container.
+		 * Above check for rollover of 8 bit ASID in 32 bit container.
 		 * If the container itself wrapped around, set it to a non zero
 		 * "generation" to distinguish from no context
 		 */
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 034bbdc0ff61..858f98ef7f1b 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -47,7 +47,7 @@
  * Page Tables are purely for Linux VM's consumption and the bits below are
  * suited to that (uniqueness). Hence some are not implemented in the TLB and
  * some have different value in TLB.
- * e.g. MMU v2: K_READ bit is 8 and so is GLOBAL (possible becoz they live in
+ * e.g. MMU v2: K_READ bit is 8 and so is GLOBAL (possible because they live in
  *      seperate PD0 and PD1, which combined forms a translation entry)
  *      while for PTE perspective, they are 8 and 9 respectively
  * with MMU v3: Most bits (except SHARED) represent the exact hardware pos
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index f9048994b22f..16b630fbeb6a 100644
--- a/arch/arc/include/asm/processor.h
+++ b/arch/arc/include/asm/processor.h
@@ -78,7 +78,7 @@ struct task_struct;
 #define KSTK_ESP(tsk)   (task_pt_regs(tsk)->sp)
 
 /*
- * Where abouts of Task's sp, fp, blink when it was last seen in kernel mode.
+ * Where about of Task's sp, fp, blink when it was last seen in kernel mode.
  * Look in process.c for details of kernel stack layout
  */
 #define TSK_K_ESP(tsk)		(tsk->thread.ksp)
diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h
index 991380438d6b..89fdd1b0a76e 100644
--- a/arch/arc/include/asm/smp.h
+++ b/arch/arc/include/asm/smp.h
@@ -86,7 +86,7 @@ static inline const char *arc_platform_smp_cpuinfo(void)
  * (1) These insn were introduced only in 4.10 release. So for older released
  *	support needed.
  *
- * (2) In a SMP setup, the LLOCK/SCOND atomiticity across CPUs needs to be
+ * (2) In a SMP setup, the LLOCK/SCOND atomicity across CPUs needs to be
  *	gaurantted by the platform (not something which core handles).
  *	Assuming a platform won't, SMP Linux needs to use spinlocks + local IRQ
  *	disabling for atomicity.
diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
index 800e7c430ca5..cded4a9b5438 100644
--- a/arch/arc/include/asm/spinlock.h
+++ b/arch/arc/include/asm/spinlock.h
@@ -20,11 +20,6 @@
 
 #ifdef CONFIG_ARC_HAS_LLSC
 
-/*
- * A normal LLOCK/SCOND based system, w/o need for livelock workaround
- */
-#ifndef CONFIG_ARC_STAR_9000923308
-
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	unsigned int val;
@@ -238,293 +233,6 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 	smp_mb();
 }
 
-#else	/* CONFIG_ARC_STAR_9000923308 */
-
-/*
- * HS38x4 could get into a LLOCK/SCOND livelock in case of multiple overlapping
- * coherency transactions in the SCU. The exclusive line state keeps rotating
- * among contenting cores leading to a never ending cycle. So break the cycle
- * by deferring the retry of failed exclusive access (SCOND). The actual delay
- * needed is function of number of contending cores as well as the unrelated
- * coherency traffic from other cores. To keep the code simple, start off with
- * small delay of 1 which would suffice most cases and in case of contention
- * double the delay. Eventually the delay is sufficient such that the coherency
- * pipeline is drained, thus a subsequent exclusive access would succeed.
- */
-
-#define SCOND_FAIL_RETRY_VAR_DEF						\
-	unsigned int delay, tmp;						\
-
-#define SCOND_FAIL_RETRY_ASM							\
-	"   ; --- scond fail delay ---		\n"				\
-	"	mov	%[tmp], %[delay]	\n"	/* tmp = delay */	\
-	"2: 	brne.d	%[tmp], 0, 2b		\n"	/* while (tmp != 0) */	\
-	"	sub	%[tmp], %[tmp], 1	\n"	/* tmp-- */		\
-	"	rol	%[delay], %[delay]	\n"	/* delay *= 2 */	\
-	"	b	1b			\n"	/* start over */	\
-	"					\n"				\
-	"4: ; --- done ---			\n"				\
-
-#define SCOND_FAIL_RETRY_VARS							\
-	  ,[delay] "=&r" (delay), [tmp] "=&r"	(tmp)				\
-
-static inline void arch_spin_lock(arch_spinlock_t *lock)
-{
-	unsigned int val;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[slock]]	\n"
-	"	breq	%[val], %[LOCKED], 0b	\n"	/* spin while LOCKED */
-	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
-	"	bz	4f			\n"	/* done */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val)
-	  SCOND_FAIL_RETRY_VARS
-	: [slock]	"r"	(&(lock->slock)),
-	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-/* 1 - lock taken successfully */
-static inline int arch_spin_trylock(arch_spinlock_t *lock)
-{
-	unsigned int val, got_it = 0;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[slock]]	\n"
-	"	breq	%[val], %[LOCKED], 4f	\n"	/* already LOCKED, just bail */
-	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
-	"	bz.d	4f			\n"
-	"	mov.z	%[got_it], 1		\n"	/* got it */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val),
-	  [got_it]	"+&r"	(got_it)
-	  SCOND_FAIL_RETRY_VARS
-	: [slock]	"r"	(&(lock->slock)),
-	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
-	: "memory", "cc");
-
-	smp_mb();
-
-	return got_it;
-}
-
-static inline void arch_spin_unlock(arch_spinlock_t *lock)
-{
-	smp_mb();
-
-	lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
-
-	smp_mb();
-}
-
-/*
- * Read-write spinlocks, allowing multiple readers but only one writer.
- * Unfair locking as Writers could be starved indefinitely by Reader(s)
- */
-
-static inline void arch_read_lock(arch_rwlock_t *rw)
-{
-	unsigned int val;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	/*
-	 * zero means writer holds the lock exclusively, deny Reader.
-	 * Otherwise grant lock to first/subseq reader
-	 *
-	 * 	if (rw->counter > 0) {
-	 *		rw->counter--;
-	 *		ret = 1;
-	 *	}
-	 */
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	brls	%[val], %[WR_LOCKED], 0b\n"	/* <= 0: spin while write locked */
-	"	sub	%[val], %[val], 1	\n"	/* reader lock */
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bz	4f			\n"	/* done */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val)
-	  SCOND_FAIL_RETRY_VARS
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [WR_LOCKED]	"ir"	(0)
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-/* 1 - lock taken successfully */
-static inline int arch_read_trylock(arch_rwlock_t *rw)
-{
-	unsigned int val, got_it = 0;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	brls	%[val], %[WR_LOCKED], 4f\n"	/* <= 0: already write locked, bail */
-	"	sub	%[val], %[val], 1	\n"	/* counter-- */
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bz.d	4f			\n"
-	"	mov.z	%[got_it], 1		\n"	/* got it */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val),
-	  [got_it]	"+&r"	(got_it)
-	  SCOND_FAIL_RETRY_VARS
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [WR_LOCKED]	"ir"	(0)
-	: "memory", "cc");
-
-	smp_mb();
-
-	return got_it;
-}
-
-static inline void arch_write_lock(arch_rwlock_t *rw)
-{
-	unsigned int val;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	/*
-	 * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__),
-	 * deny writer. Otherwise if unlocked grant to writer
-	 * Hence the claim that Linux rwlocks are unfair to writers.
-	 * (can be starved for an indefinite time by readers).
-	 *
-	 *	if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) {
-	 *		rw->counter = 0;
-	 *		ret = 1;
-	 *	}
-	 */
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	brne	%[val], %[UNLOCKED], 0b	\n"	/* while !UNLOCKED spin */
-	"	mov	%[val], %[WR_LOCKED]	\n"
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bz	4f			\n"
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val)
-	  SCOND_FAIL_RETRY_VARS
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
-	  [WR_LOCKED]	"ir"	(0)
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-/* 1 - lock taken successfully */
-static inline int arch_write_trylock(arch_rwlock_t *rw)
-{
-	unsigned int val, got_it = 0;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	brne	%[val], %[UNLOCKED], 4f	\n"	/* !UNLOCKED, bail */
-	"	mov	%[val], %[WR_LOCKED]	\n"
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bz.d	4f			\n"
-	"	mov.z	%[got_it], 1		\n"	/* got it */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val),
-	  [got_it]	"+&r"	(got_it)
-	  SCOND_FAIL_RETRY_VARS
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
-	  [WR_LOCKED]	"ir"	(0)
-	: "memory", "cc");
-
-	smp_mb();
-
-	return got_it;
-}
-
-static inline void arch_read_unlock(arch_rwlock_t *rw)
-{
-	unsigned int val;
-
-	smp_mb();
-
-	/*
-	 * rw->counter++;
-	 */
-	__asm__ __volatile__(
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	add	%[val], %[val], 1	\n"
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bnz	1b			\n"
-	"					\n"
-	: [val]		"=&r"	(val)
-	: [rwlock]	"r"	(&(rw->counter))
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-static inline void arch_write_unlock(arch_rwlock_t *rw)
-{
-	unsigned int val;
-
-	smp_mb();
-
-	/*
-	 * rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
-	 */
-	__asm__ __volatile__(
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	scond	%[UNLOCKED], [%[rwlock]]\n"
-	"	bnz	1b			\n"
-	"					\n"
-	: [val]		"=&r"	(val)
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [UNLOCKED]	"r"	(__ARCH_RW_LOCK_UNLOCKED__)
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-#undef SCOND_FAIL_RETRY_VAR_DEF
-#undef SCOND_FAIL_RETRY_ASM
-#undef SCOND_FAIL_RETRY_VARS
-
-#endif	/* CONFIG_ARC_STAR_9000923308 */
-
 #else	/* !CONFIG_ARC_HAS_LLSC */
 
 static inline void arch_spin_lock(arch_spinlock_t *lock)
diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h
index 3af67455659a..2d79e527fa50 100644
--- a/arch/arc/include/asm/thread_info.h
+++ b/arch/arc/include/asm/thread_info.h
@@ -103,7 +103,7 @@ static inline __attribute_const__ struct thread_info *current_thread_info(void)
 
 /*
  * _TIF_ALLWORK_MASK includes SYSCALL_TRACE, but we don't need it.
- * SYSCALL_TRACE is anways seperately/unconditionally tested right after a
+ * SYSCALL_TRACE is anyway seperately/unconditionally tested right after a
  * syscall, so all that reamins to be tested is _TIF_WORK_MASK
  */
 
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index d1da6032b715..a78d5670884f 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -32,7 +32,7 @@
 #define __kernel_ok		(segment_eq(get_fs(), KERNEL_DS))
 
 /*
- * Algorthmically, for __user_ok() we want do:
+ * Algorithmically, for __user_ok() we want do:
  * 	(start < TASK_SIZE) && (start+len < TASK_SIZE)
  * where TASK_SIZE could either be retrieved from thread_info->addr_limit or
  * emitted directly in code.
diff --git a/arch/arc/include/uapi/asm/swab.h b/arch/arc/include/uapi/asm/swab.h
index 095599a73195..71f3918b0fc3 100644
--- a/arch/arc/include/uapi/asm/swab.h
+++ b/arch/arc/include/uapi/asm/swab.h
@@ -74,7 +74,7 @@
 	__tmp ^ __in;						\
 })
 
-#elif (ARC_BSWAP_TYPE == 2)	/* Custom single cycle bwap instruction */
+#elif (ARC_BSWAP_TYPE == 2)	/* Custom single cycle bswap instruction */
 
 #define __arch_swab32(x)						\
 ({									\
diff --git a/arch/arc/kernel/entry-compact.S b/arch/arc/kernel/entry-compact.S
index 0cb0abaa0479..98812c1248df 100644
--- a/arch/arc/kernel/entry-compact.S
+++ b/arch/arc/kernel/entry-compact.S
@@ -91,27 +91,13 @@ VECTOR   mem_service             ; 0x8, Mem exception   (0x1)
 VECTOR   instr_service           ; 0x10, Instrn Error   (0x2)
 
 ; ******************** Device ISRs **********************
-#ifdef CONFIG_ARC_IRQ3_LV2
-VECTOR   handle_interrupt_level2
-#else
-VECTOR   handle_interrupt_level1
-#endif
-
-VECTOR   handle_interrupt_level1
-
-#ifdef CONFIG_ARC_IRQ5_LV2
-VECTOR   handle_interrupt_level2
-#else
-VECTOR   handle_interrupt_level1
-#endif
-
-#ifdef CONFIG_ARC_IRQ6_LV2
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
 VECTOR   handle_interrupt_level2
 #else
 VECTOR   handle_interrupt_level1
 #endif
 
-.rept   25
+.rept   28
 VECTOR   handle_interrupt_level1 ; Other devices
 .endr
 
diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c
index c5cceca36118..ce9deb953ca9 100644
--- a/arch/arc/kernel/intc-compact.c
+++ b/arch/arc/kernel/intc-compact.c
@@ -28,10 +28,8 @@ void arc_init_IRQ(void)
 {
 	int level_mask = 0;
 
-       /* setup any high priority Interrupts (Level2 in ARCompact jargon) */
-	level_mask |= IS_ENABLED(CONFIG_ARC_IRQ3_LV2) << 3;
-	level_mask |= IS_ENABLED(CONFIG_ARC_IRQ5_LV2) << 5;
-	level_mask |= IS_ENABLED(CONFIG_ARC_IRQ6_LV2) << 6;
+       /* Is timer high priority Interrupt (Level2 in ARCompact jargon) */
+	level_mask |= IS_ENABLED(CONFIG_ARC_COMPACT_IRQ_LEVELS) << TIMER0_IRQ;
 
 	/*
 	 * Write to register, even if no LV2 IRQs configured to reset it
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 6fd48021324b..08f03d9b5b3e 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -108,7 +108,7 @@ static void arc_perf_event_update(struct perf_event *event,
 	int64_t delta = new_raw_count - prev_raw_count;
 
 	/*
-	 * We don't afaraid of hwc->prev_count changing beneath our feet
+	 * We aren't afraid of hwc->prev_count changing beneath our feet
 	 * because there's no way for us to re-enter this function anytime.
 	 */
 	local64_set(&hwc->prev_count, new_raw_count);
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index f63b8bfefb0c..2ee7a4d758a8 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -392,7 +392,7 @@ void __init setup_arch(char **cmdline_p)
 		/*
 		 * If we are here, it is established that @uboot_arg didn't
 		 * point to DT blob. Instead if u-boot says it is cmdline,
-		 * Appent to embedded DT cmdline.
+		 * append to embedded DT cmdline.
 		 * setup_machine_fdt() would have populated @boot_command_line
 		 */
 		if (uboot_tag == 1) {
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index 004b7f0bc76c..6cb3736b6b83 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -34,7 +34,7 @@
  *  -ViXS were still seeing crashes when using insmod to load drivers.
  *   It turned out that the code to change Execute permssions for TLB entries
  *   of user was not guarded for interrupts (mod_tlb_permission)
- *   This was cauing TLB entries to be overwritten on unrelated indexes
+ *   This was causing TLB entries to be overwritten on unrelated indexes
  *
  * Vineetg: July 15th 2008: Bug #94183
  *  -Exception happens in Delay slot of a JMP, and before user space resumes,
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index a6f91e88ce36..934150e7ac48 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -276,7 +276,7 @@ static int tlb_stats_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
-/* called on user read(): display the couters */
+/* called on user read(): display the counters */
 static ssize_t tlb_stats_output(struct file *file,	/* file descriptor */
 				char __user *user_buf,	/* user buffer */
 				size_t len,		/* length of buffer */
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 9e5eddbb856f..5a294b2c3cb3 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -215,7 +215,7 @@ slc_chk:
  * ------------------
  * This ver of MMU supports variable page sizes (1k-16k): although Linux will
  * only support 8k (default), 16k and 4k.
- * However from hardware perspective, smaller page sizes aggrevate aliasing
+ * However from hardware perspective, smaller page sizes aggravate aliasing
  * meaning more vaddr bits needed to disambiguate the cache-line-op ;
  * the existing scheme of piggybacking won't work for certain configurations.
  * Two new registers IC_PTAG and DC_PTAG inttoduced.
@@ -302,7 +302,7 @@ void __cache_line_loop_v3(phys_addr_t paddr, unsigned long vaddr,
 
 	/*
 	 * This is technically for MMU v4, using the MMU v3 programming model
-	 * Special work for HS38 aliasing I-cache configuratino with PAE40
+	 * Special work for HS38 aliasing I-cache configuration with PAE40
 	 *   - upper 8 bits of paddr need to be written into PTAG_HI
 	 *   - (and needs to be written before the lower 32 bits)
 	 * Note that PTAG_HI is hoisted outside the line loop
@@ -936,7 +936,7 @@ void arc_cache_init(void)
 			      ic->ver, CONFIG_ARC_MMU_VER);
 
 		/*
-		 * In MMU v4 (HS38x) the alising icache config uses IVIL/PTAG
+		 * In MMU v4 (HS38x) the aliasing icache config uses IVIL/PTAG
 		 * pair to provide vaddr/paddr respectively, just as in MMU v3
 		 */
 		if (is_isa_arcv2() && ic->alias)
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 8c8e36fa5659..73d7e4c75b7d 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -10,7 +10,7 @@
  * DMA Coherent API Notes
  *
  * I/O is inherently non-coherent on ARC. So a coherent DMA buffer is
- * implemented by accessintg it using a kernel virtual address, with
+ * implemented by accessing it using a kernel virtual address, with
  * Cache bit off in the TLB entry.
  *
  * The default DMA address == Phy address which is 0x8000_0000 based.
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index ef9119f7462e..4d9375814b53 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -733,8 +733,8 @@ static int vfp_set(struct task_struct *target,
 	if (ret)
 		return ret;
 
-	vfp_flush_hwstate(thread);
 	thread->vfpstate.hard = new_vfp;
+	vfp_flush_hwstate(thread);
 
 	return 0;
 }
diff --git a/arch/arm/mach-vexpress/spc.c b/arch/arm/mach-vexpress/spc.c
index 5766ce2be32b..8409cab3f760 100644
--- a/arch/arm/mach-vexpress/spc.c
+++ b/arch/arm/mach-vexpress/spc.c
@@ -547,7 +547,7 @@ static struct clk *ve_spc_clk_register(struct device *cpu_dev)
 
 	init.name = dev_name(cpu_dev);
 	init.ops = &clk_spc_ops;
-	init.flags = CLK_IS_ROOT | CLK_GET_RATE_NOCACHE;
+	init.flags = CLK_GET_RATE_NOCACHE;
 	init.num_parents = 0;
 
 	return devm_clk_register(cpu_dev, &spc->hw);
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 76747d92bc72..5a0a691d4220 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -113,6 +113,18 @@ config ARCH_PHYS_ADDR_T_64BIT
 config MMU
 	def_bool y
 
+config ARM64_PAGE_SHIFT
+	int
+	default 16 if ARM64_64K_PAGES
+	default 14 if ARM64_16K_PAGES
+	default 12
+
+config ARM64_CONT_SHIFT
+	int
+	default 5 if ARM64_64K_PAGES
+	default 7 if ARM64_16K_PAGES
+	default 4
+
 config ARCH_MMAP_RND_BITS_MIN
        default 14 if ARM64_64K_PAGES
        default 16 if ARM64_16K_PAGES
@@ -426,6 +438,15 @@ config CAVIUM_ERRATUM_22375
 
 	  If unsure, say Y.
 
+config CAVIUM_ERRATUM_23144
+	bool "Cavium erratum 23144: ITS SYNC hang on dual socket system"
+	depends on NUMA
+	default y
+	help
+	  ITS SYNC command hang for cross node io and collections/cpu mapping.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_23154
 	bool "Cavium erratum 23154: Access to ICC_IAR1_EL1 is not sync'ed"
 	default y
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index 710fde4ad0f0..0cc758cdd0dc 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -12,7 +12,8 @@ config ARM64_PTDUMP
 	  who are working in architecture specific areas of the kernel.
 	  It is probably not a good idea to enable this feature in a production
 	  kernel.
-	  If in doubt, say "N"
+
+	  If in doubt, say N.
 
 config PID_IN_CONTEXTIDR
 	bool "Write the current PID to the CONTEXTIDR register"
@@ -38,15 +39,15 @@ config ARM64_RANDOMIZE_TEXT_OFFSET
 	  value.
 
 config DEBUG_SET_MODULE_RONX
-        bool "Set loadable kernel module data as NX and text as RO"
-        depends on MODULES
-        help
-          This option helps catch unintended modifications to loadable
-          kernel module's text and read-only data. It also prevents execution
-          of module data. Such protection may interfere with run-time code
-          patching and dynamic kernel tracing - and they might also protect
-          against certain classes of kernel exploits.
-          If in doubt, say "N".
+	bool "Set loadable kernel module data as NX and text as RO"
+	depends on MODULES
+	default y
+	help
+	  Is this is set, kernel module text and rodata will be made read-only.
+	  This is to help catch accidental or malicious attempts to change the
+	  kernel's executable code.
+
+	  If in doubt, say Y.
 
 config DEBUG_RODATA
 	bool "Make kernel text and rodata read-only"
@@ -56,7 +57,7 @@ config DEBUG_RODATA
 	  is to help catch accidental or malicious attempts to change the
 	  kernel's executable code.
 
-	  If in doubt, say Y
+	  If in doubt, say Y.
 
 config DEBUG_ALIGN_RODATA
 	depends on DEBUG_RODATA
@@ -69,7 +70,7 @@ config DEBUG_ALIGN_RODATA
 	  alignment and potentially wasted space. Turn on this option if
 	  performance is more important than memory pressure.
 
-	  If in doubt, say N
+	  If in doubt, say N.
 
 source "drivers/hwtracing/coresight/Kconfig"
 
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 354d75402ace..7085e322dc42 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -60,7 +60,9 @@ head-y		:= arch/arm64/kernel/head.o
 
 # The byte offset of the kernel image in RAM from the start of RAM.
 ifeq ($(CONFIG_ARM64_RANDOMIZE_TEXT_OFFSET), y)
-TEXT_OFFSET := $(shell awk 'BEGIN {srand(); printf "0x%03x000\n", int(512 * rand())}')
+TEXT_OFFSET := $(shell awk "BEGIN {srand(); printf \"0x%06x\n\", \
+		 int(2 * 1024 * 1024 / (2 ^ $(CONFIG_ARM64_PAGE_SHIFT)) * \
+		 rand()) * (2 ^ $(CONFIG_ARM64_PAGE_SHIFT))}")
 else
 TEXT_OFFSET := 0x00080000
 endif
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index 7a09c48c0475..579b6e654f2d 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -160,14 +160,14 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 #define STACK_RND_MASK			(0x3ffff >> (PAGE_SHIFT - 12))
 #endif
 
-#ifdef CONFIG_COMPAT
-
 #ifdef __AARCH64EB__
 #define COMPAT_ELF_PLATFORM		("v8b")
 #else
 #define COMPAT_ELF_PLATFORM		("v8l")
 #endif
 
+#ifdef CONFIG_COMPAT
+
 #define COMPAT_ELF_ET_DYN_BASE		(2 * TASK_SIZE_32 / 3)
 
 /* AArch32 registers. */
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 72a3025bb583..31b73227b41f 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -55,8 +55,9 @@
 #define VMEMMAP_SIZE (UL(1) << (VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT))
 
 /*
- * PAGE_OFFSET - the virtual address of the start of the kernel image (top
+ * PAGE_OFFSET - the virtual address of the start of the linear map (top
  *		 (VA_BITS - 1))
+ * KIMAGE_VADDR - the virtual address of the start of the kernel image
  * VA_BITS - the maximum number of bits for virtual addresses.
  * VA_START - the first kernel virtual address.
  * TASK_SIZE - the maximum size of a user space task.
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 17b45f7d96d3..8472c6def5ef 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -23,16 +23,8 @@
 
 /* PAGE_SHIFT determines the page size */
 /* CONT_SHIFT determines the number of pages which can be tracked together  */
-#ifdef CONFIG_ARM64_64K_PAGES
-#define PAGE_SHIFT		16
-#define CONT_SHIFT		5
-#elif defined(CONFIG_ARM64_16K_PAGES)
-#define PAGE_SHIFT		14
-#define CONT_SHIFT		7
-#else
-#define PAGE_SHIFT		12
-#define CONT_SHIFT		4
-#endif
+#define PAGE_SHIFT		CONFIG_ARM64_PAGE_SHIFT
+#define CONT_SHIFT		CONFIG_ARM64_CONT_SHIFT
 #define PAGE_SIZE		(_AC(1, UL) << PAGE_SHIFT)
 #define PAGE_MASK		(~(PAGE_SIZE-1))
 
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 0685d74572af..9e397a542756 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -81,19 +81,6 @@ static inline void set_fs(mm_segment_t fs)
 #define segment_eq(a, b)	((a) == (b))
 
 /*
- * Return 1 if addr < current->addr_limit, 0 otherwise.
- */
-#define __addr_ok(addr)							\
-({									\
-	unsigned long flag;						\
-	asm("cmp %1, %0; cset %0, lo"					\
-		: "=&r" (flag)						\
-		: "r" (addr), "0" (current_thread_info()->addr_limit)	\
-		: "cc");						\
-	flag;								\
-})
-
-/*
  * Test whether a block of memory is a valid user space address.
  * Returns 1 if the range is valid, 0 otherwise.
  *
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 41e58fe3c041..e78ac26324bd 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -44,7 +44,7 @@
 #define __ARM_NR_compat_cacheflush	(__ARM_NR_COMPAT_BASE+2)
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE+5)
 
-#define __NR_compat_syscalls		390
+#define __NR_compat_syscalls		394
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 5b925b761a2a..b7e8ef16ff0d 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -801,6 +801,14 @@ __SYSCALL(__NR_execveat, compat_sys_execveat)
 __SYSCALL(__NR_userfaultfd, sys_userfaultfd)
 #define __NR_membarrier 389
 __SYSCALL(__NR_membarrier, sys_membarrier)
+#define __NR_mlock2 390
+__SYSCALL(__NR_mlock2, sys_mlock2)
+#define __NR_copy_file_range 391
+__SYSCALL(__NR_copy_file_range, sys_copy_file_range)
+#define __NR_preadv2 392
+__SYSCALL(__NR_preadv2, compat_sys_preadv2)
+#define __NR_pwritev2 393
+__SYSCALL(__NR_pwritev2, compat_sys_pwritev2)
 
 /*
  * Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 3808470486f3..c173d329397f 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -22,6 +22,8 @@
 
 #include <linux/bitops.h>
 #include <linux/bug.h>
+#include <linux/compat.h>
+#include <linux/elf.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/personality.h>
@@ -104,6 +106,7 @@ static const char *const compat_hwcap2_str[] = {
 static int c_show(struct seq_file *m, void *v)
 {
 	int i, j;
+	bool compat = personality(current->personality) == PER_LINUX32;
 
 	for_each_online_cpu(i) {
 		struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i);
@@ -115,6 +118,9 @@ static int c_show(struct seq_file *m, void *v)
 		 * "processor".  Give glibc what it expects.
 		 */
 		seq_printf(m, "processor\t: %d\n", i);
+		if (compat)
+			seq_printf(m, "model name\t: ARMv8 Processor rev %d (%s)\n",
+				   MIDR_REVISION(midr), COMPAT_ELF_PLATFORM);
 
 		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
 			   loops_per_jiffy / (500000UL/HZ),
@@ -127,7 +133,7 @@ static int c_show(struct seq_file *m, void *v)
 		 * software which does already (at least for 32-bit).
 		 */
 		seq_puts(m, "Features\t:");
-		if (personality(current->personality) == PER_LINUX32) {
+		if (compat) {
 #ifdef CONFIG_COMPAT
 			for (j = 0; compat_hwcap_str[j]; j++)
 				if (compat_elf_hwcap & (1 << j))
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index c5392081b49b..f7cf463107df 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -477,8 +477,9 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 	void __user *pc = (void __user *)instruction_pointer(regs);
 	console_verbose();
 
-	pr_crit("Bad mode in %s handler detected, code 0x%08x -- %s\n",
-		handler[reason], esr, esr_get_class_string(esr));
+	pr_crit("Bad mode in %s handler detected on CPU%d, code 0x%08x -- %s\n",
+		handler[reason], smp_processor_id(), esr,
+		esr_get_class_string(esr));
 	__show_regs(regs);
 
 	info.si_signo = SIGILL;
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index fff7cd42b3a3..5f8f80b4a224 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -169,7 +169,8 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 	 * Make sure stores to the GIC via the memory mapped interface
 	 * are now visible to the system register interface.
 	 */
-	dsb(st);
+	if (!cpu_if->vgic_sre)
+		dsb(st);
 
 	cpu_if->vgic_vmcr  = read_gicreg(ICH_VMCR_EL2);
 
@@ -190,12 +191,11 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 			if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
 				continue;
 
-			if (cpu_if->vgic_elrsr & (1 << i)) {
+			if (cpu_if->vgic_elrsr & (1 << i))
 				cpu_if->vgic_lr[i] &= ~ICH_LR_STATE;
-				continue;
-			}
+			else
+				cpu_if->vgic_lr[i] = __gic_v3_get_lr(i);
 
-			cpu_if->vgic_lr[i] = __gic_v3_get_lr(i);
 			__gic_v3_set_lr(0, i);
 		}
 
@@ -236,8 +236,12 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 
 	val = read_gicreg(ICC_SRE_EL2);
 	write_gicreg(val | ICC_SRE_EL2_ENABLE, ICC_SRE_EL2);
-	isb(); /* Make sure ENABLE is set at EL2 before setting SRE at EL1 */
-	write_gicreg(1, ICC_SRE_EL1);
+
+	if (!cpu_if->vgic_sre) {
+		/* Make sure ENABLE is set at EL2 before setting SRE at EL1 */
+		isb();
+		write_gicreg(1, ICC_SRE_EL1);
+	}
 }
 
 void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
@@ -256,8 +260,10 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	 * been actually programmed with the value we want before
 	 * starting to mess with the rest of the GIC.
 	 */
-	write_gicreg(cpu_if->vgic_sre, ICC_SRE_EL1);
-	isb();
+	if (!cpu_if->vgic_sre) {
+		write_gicreg(0, ICC_SRE_EL1);
+		isb();
+	}
 
 	val = read_gicreg(ICH_VTR_EL2);
 	max_lr_idx = vtr_to_max_lr_idx(val);
@@ -306,18 +312,18 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	 * (re)distributors. This ensure the guest will read the
 	 * correct values from the memory-mapped interface.
 	 */
-	isb();
-	dsb(sy);
+	if (!cpu_if->vgic_sre) {
+		isb();
+		dsb(sy);
+	}
 	vcpu->arch.vgic_cpu.live_lrs = live_lrs;
 
 	/*
 	 * Prevent the guest from touching the GIC system registers if
 	 * SRE isn't enabled for GICv3 emulation.
 	 */
-	if (!cpu_if->vgic_sre) {
-		write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE,
-			     ICC_SRE_EL2);
-	}
+	write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE,
+		     ICC_SRE_EL2);
 }
 
 void __hyp_text __vgic_v3_init_lrs(void)
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 7bbe3ff02602..a57d650f552c 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -134,6 +134,17 @@ static bool access_gic_sgi(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static bool access_gic_sre(struct kvm_vcpu *vcpu,
+			   struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return ignore_write(vcpu, p);
+
+	p->regval = vcpu->arch.vgic_cpu.vgic_v3.vgic_sre;
+	return true;
+}
+
 static bool trap_raz_wi(struct kvm_vcpu *vcpu,
 			struct sys_reg_params *p,
 			const struct sys_reg_desc *r)
@@ -958,7 +969,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	  access_gic_sgi },
 	/* ICC_SRE_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b1100), Op2(0b101),
-	  trap_raz_wi },
+	  access_gic_sre },
 
 	/* CONTEXTIDR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b001),
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index 8404190fe2bd..ccfde237d6e6 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -150,6 +150,7 @@ static const struct prot_bits pte_bits[] = {
 
 struct pg_level {
 	const struct prot_bits *bits;
+	const char *name;
 	size_t num;
 	u64 mask;
 };
@@ -157,15 +158,19 @@ struct pg_level {
 static struct pg_level pg_level[] = {
 	{
 	}, { /* pgd */
+		.name	= "PGD",
 		.bits	= pte_bits,
 		.num	= ARRAY_SIZE(pte_bits),
 	}, { /* pud */
+		.name	= (CONFIG_PGTABLE_LEVELS > 3) ? "PUD" : "PGD",
 		.bits	= pte_bits,
 		.num	= ARRAY_SIZE(pte_bits),
 	}, { /* pmd */
+		.name	= (CONFIG_PGTABLE_LEVELS > 2) ? "PMD" : "PGD",
 		.bits	= pte_bits,
 		.num	= ARRAY_SIZE(pte_bits),
 	}, { /* pte */
+		.name	= "PTE",
 		.bits	= pte_bits,
 		.num	= ARRAY_SIZE(pte_bits),
 	},
@@ -214,7 +219,8 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level,
 				delta >>= 10;
 				unit++;
 			}
-			seq_printf(st->seq, "%9lu%c", delta, *unit);
+			seq_printf(st->seq, "%9lu%c %s", delta, *unit,
+				   pg_level[st->level].name);
 			if (pg_level[st->level].bits)
 				dump_prot(st, pg_level[st->level].bits,
 					  pg_level[st->level].num);
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index aa8aee7d6929..2e49bd252fe7 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -306,6 +306,10 @@ static __init int setup_hugepagesz(char *opt)
 		hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
 	} else if (ps == PUD_SIZE) {
 		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+	} else if (ps == (PAGE_SIZE * CONT_PTES)) {
+		hugetlb_add_hstate(CONT_PTE_SHIFT);
+	} else if (ps == (PMD_SIZE * CONT_PMDS)) {
+		hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT);
 	} else {
 		hugetlb_bad_size();
 		pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
@@ -314,3 +318,13 @@ static __init int setup_hugepagesz(char *opt)
 	return 1;
 }
 __setup("hugepagesz=", setup_hugepagesz);
+
+#ifdef CONFIG_ARM64_64K_PAGES
+static __init int add_default_hugepagesz(void)
+{
+	if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
+		hugetlb_add_hstate(CONT_PMD_SHIFT);
+	return 0;
+}
+arch_initcall(add_default_hugepagesz);
+#endif
diff --git a/arch/parisc/include/asm/traps.h b/arch/parisc/include/asm/traps.h
index 4736020ba5ea..5e953ab4530d 100644
--- a/arch/parisc/include/asm/traps.h
+++ b/arch/parisc/include/asm/traps.h
@@ -8,6 +8,8 @@ struct pt_regs;
 void parisc_terminate(char *msg, struct pt_regs *regs,
 		int code, unsigned long offset) __noreturn __cold;
 
+void die_if_kernel(char *str, struct pt_regs *regs, long err);
+
 /* mm/fault.c */
 void do_page_fault(struct pt_regs *regs, unsigned long code,
 		unsigned long address);
diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c
index e81ccf1716e9..5adc339eb7c8 100644
--- a/arch/parisc/kernel/processor.c
+++ b/arch/parisc/kernel/processor.c
@@ -324,8 +324,9 @@ int init_per_cpu(int cpunum)
 		per_cpu(cpu_data, cpunum).fp_rev = coproc_cfg.revision;
 		per_cpu(cpu_data, cpunum).fp_model = coproc_cfg.model;
 
-		printk(KERN_INFO  "FP[%d] enabled: Rev %ld Model %ld\n",
-			cpunum, coproc_cfg.revision, coproc_cfg.model);
+		if (cpunum == 0)
+			printk(KERN_INFO  "FP[%d] enabled: Rev %ld Model %ld\n",
+				cpunum, coproc_cfg.revision, coproc_cfg.model);
 
 		/*
 		** store status register to stack (hopefully aligned)
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 58dd6801f5be..31ec99a5f119 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -309,11 +309,6 @@ void __init time_init(void)
 	clocks_calc_mult_shift(&cyc2ns_mul, &cyc2ns_shift, current_cr16_khz,
 				NSEC_PER_MSEC, 0);
 
-#if defined(CONFIG_HAVE_UNSTABLE_SCHED_CLOCK) && defined(CONFIG_64BIT)
-	/* At bootup only one 64bit CPU is online and cr16 is "stable" */
-	set_sched_clock_stable();
-#endif
-
 	start_cpu_itimer();	/* get CPU 0 started */
 
 	/* register at clocksource framework */
diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c
index d7c0acb35ec2..2b65c0177778 100644
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -28,6 +28,7 @@
 #include <linux/ratelimit.h>
 #include <asm/uaccess.h>
 #include <asm/hardirq.h>
+#include <asm/traps.h>
 
 /* #define DEBUG_UNALIGNED 1 */
 
@@ -130,8 +131,6 @@
 
 int unaligned_enabled __read_mostly = 1;
 
-void die_if_kernel (char *str, struct pt_regs *regs, long err);
-
 static int emulate_ldh(struct pt_regs *regs, int toreg)
 {
 	unsigned long saddr = regs->ior;
@@ -666,7 +665,7 @@ void handle_unaligned(struct pt_regs *regs)
 		break;
 	}
 
-	if (modify && R1(regs->iir))
+	if (ret == 0 && modify && R1(regs->iir))
 		regs->gr[R1(regs->iir)] = newbase;
 
 
@@ -677,6 +676,14 @@ void handle_unaligned(struct pt_regs *regs)
 
 	if (ret)
 	{
+		/*
+		 * The unaligned handler failed.
+		 * If we were called by __get_user() or __put_user() jump
+		 * to it's exception fixup handler instead of crashing.
+		 */
+		if (!user_mode(regs) && fixup_exception(regs))
+			return;
+
 		printk(KERN_CRIT "Unaligned handler failed, ret = %d\n", ret);
 		die_if_kernel("Unaligned data reference", regs, 28);
 
diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c
index ddd988b267a9..e278a87f43cc 100644
--- a/arch/parisc/kernel/unwind.c
+++ b/arch/parisc/kernel/unwind.c
@@ -75,7 +75,10 @@ find_unwind_entry(unsigned long addr)
 	if (addr >= kernel_unwind_table.start && 
 	    addr <= kernel_unwind_table.end)
 		e = find_unwind_entry_in_table(&kernel_unwind_table, addr);
-	else 
+	else {
+		unsigned long flags;
+
+		spin_lock_irqsave(&unwind_lock, flags);
 		list_for_each_entry(table, &unwind_tables, list) {
 			if (addr >= table->start && 
 			    addr <= table->end)
@@ -86,6 +89,8 @@ find_unwind_entry(unsigned long addr)
 				break;
 			}
 		}
+		spin_unlock_irqrestore(&unwind_lock, flags);
+	}
 
 	return e;
 }
@@ -303,18 +308,16 @@ static void unwind_frame_regs(struct unwind_frame_info *info)
 
 			insn = *(unsigned int *)npc;
 
-			if ((insn & 0xffffc000) == 0x37de0000 ||
-			    (insn & 0xffe00000) == 0x6fc00000) {
+			if ((insn & 0xffffc001) == 0x37de0000 ||
+			    (insn & 0xffe00001) == 0x6fc00000) {
 				/* ldo X(sp), sp, or stwm X,D(sp) */
-				frame_size += (insn & 0x1 ? -1 << 13 : 0) | 
-					((insn & 0x3fff) >> 1);
+				frame_size += (insn & 0x3fff) >> 1;
 				dbg("analyzing func @ %lx, insn=%08x @ "
 				    "%lx, frame_size = %ld\n", info->ip,
 				    insn, npc, frame_size);
-			} else if ((insn & 0xffe00008) == 0x73c00008) {
+			} else if ((insn & 0xffe00009) == 0x73c00008) {
 				/* std,ma X,D(sp) */
-				frame_size += (insn & 0x1 ? -1 << 13 : 0) | 
-					(((insn >> 4) & 0x3ff) << 3);
+				frame_size += ((insn >> 4) & 0x3ff) << 3;
 				dbg("analyzing func @ %lx, insn=%08x @ "
 				    "%lx, frame_size = %ld\n", info->ip,
 				    insn, npc, frame_size);
@@ -333,6 +336,9 @@ static void unwind_frame_regs(struct unwind_frame_info *info)
 			}
 		}
 
+		if (frame_size > e->Total_frame_size << 3)
+			frame_size = e->Total_frame_size << 3;
+
 		if (!unwind_special(info, e->region_start, frame_size)) {
 			info->prev_sp = info->sp - frame_size;
 			if (e->Millicode)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index c1e82e968506..a0948f40bc7b 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -717,7 +717,7 @@
 #define   MMCR0_FCWAIT	0x00000002UL /* freeze counter in WAIT state */
 #define   MMCR0_FCHV	0x00000001UL /* freeze conditions in hypervisor mode */
 #define SPRN_MMCR1	798
-#define SPRN_MMCR2	769
+#define SPRN_MMCR2	785
 #define SPRN_MMCRA	0x312
 #define   MMCRA_SDSYNC	0x80000000UL /* SDAR synced with SIAR */
 #define   MMCRA_SDAR_DCACHE_MISS 0x40000000UL
@@ -754,13 +754,13 @@
 #define SPRN_PMC6	792
 #define SPRN_PMC7	793
 #define SPRN_PMC8	794
-#define SPRN_SIAR	780
-#define SPRN_SDAR	781
 #define SPRN_SIER	784
 #define   SIER_SIPR		0x2000000	/* Sampled MSR_PR */
 #define   SIER_SIHV		0x1000000	/* Sampled MSR_HV */
 #define   SIER_SIAR_VALID	0x0400000	/* SIAR contents valid */
 #define   SIER_SDAR_VALID	0x0200000	/* SDAR contents valid */
+#define SPRN_SIAR	796
+#define SPRN_SDAR	797
 #define SPRN_TACR	888
 #define SPRN_TCSCR	889
 #define SPRN_CSIGR	890
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index da5192590c44..ccd2037c797f 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -656,6 +656,7 @@ unsigned char ibm_architecture_vec[] = {
 	W(0xffff0000), W(0x003e0000),	/* POWER6 */
 	W(0xffff0000), W(0x003f0000),	/* POWER7 */
 	W(0xffff0000), W(0x004b0000),	/* POWER8E */
+	W(0xffff0000), W(0x004c0000),   /* POWER8NVL */
 	W(0xffff0000), W(0x004d0000),	/* POWER8 */
 	W(0xffffffff), W(0x0f000004),	/* all 2.07-compliant */
 	W(0xffffffff), W(0x0f000003),	/* all 2.06-compliant */
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 59268969a0bc..b2740c67e172 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -159,6 +159,19 @@ static struct mmu_psize_def mmu_psize_defaults_gp[] = {
 	},
 };
 
+/*
+ * 'R' and 'C' update notes:
+ *  - Under pHyp or KVM, the updatepp path will not set C, thus it *will*
+ *     create writeable HPTEs without C set, because the hcall H_PROTECT
+ *     that we use in that case will not update C
+ *  - The above is however not a problem, because we also don't do that
+ *     fancy "no flush" variant of eviction and we use H_REMOVE which will
+ *     do the right thing and thus we don't have the race I described earlier
+ *
+ *    - Under bare metal,  we do have the race, so we need R and C set
+ *    - We make sure R is always set and never lost
+ *    - C is _PAGE_DIRTY, and *should* always be set for a writeable mapping
+ */
 unsigned long htab_convert_pte_flags(unsigned long pteflags)
 {
 	unsigned long rflags = 0;
@@ -186,9 +199,14 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags)
 			rflags |= 0x1;
 	}
 	/*
-	 * Always add "C" bit for perf. Memory coherence is always enabled
+	 * We can't allow hardware to update hpte bits. Hence always
+	 * set 'R' bit and set 'C' if it is a write fault
+	 * Memory coherence is always enabled
 	 */
-	rflags |=  HPTE_R_C | HPTE_R_M;
+	rflags |=  HPTE_R_R | HPTE_R_M;
+
+	if (pteflags & _PAGE_DIRTY)
+		rflags |= HPTE_R_C;
 	/*
 	 * Add in WIG bits
 	 */
diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index eb4451144746..670318766545 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/pgtable-book3s64.c
@@ -33,10 +33,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 	changed = !pmd_same(*(pmdp), entry);
 	if (changed) {
 		__ptep_set_access_flags(pmdp_ptep(pmdp), pmd_pte(entry));
-		/*
-		 * Since we are not supporting SW TLB systems, we don't
-		 * have any thing similar to flush_tlb_page_nohash()
-		 */
+		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	}
 	return changed;
 }
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 18b2c11604fa..c939e6e57a9e 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -296,11 +296,6 @@ found:
 void __init radix__early_init_mmu(void)
 {
 	unsigned long lpcr;
-	/*
-	 * setup LPCR UPRT based on mmu_features
-	 */
-	lpcr = mfspr(SPRN_LPCR);
-	mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
 
 #ifdef CONFIG_PPC_64K_PAGES
 	/* PAGE_SIZE mappings */
@@ -343,8 +338,11 @@ void __init radix__early_init_mmu(void)
 	__pte_frag_size_shift = H_PTE_FRAG_SIZE_SHIFT;
 
 	radix_init_page_sizes();
-	if (!firmware_has_feature(FW_FEATURE_LPAR))
+	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+		lpcr = mfspr(SPRN_LPCR);
+		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
 		radix_init_partition_table();
+	}
 
 	radix_init_pgtable();
 }
@@ -353,16 +351,15 @@ void radix__early_init_mmu_secondary(void)
 {
 	unsigned long lpcr;
 	/*
-	 * setup LPCR UPRT based on mmu_features
+	 * update partition table control register and UPRT
 	 */
-	lpcr = mfspr(SPRN_LPCR);
-	mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
-	/*
-	 * update partition table control register, 64 K size.
-	 */
-	if (!firmware_has_feature(FW_FEATURE_LPAR))
+	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+		lpcr = mfspr(SPRN_LPCR);
+		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
+
 		mtspr(SPRN_PTCR,
 		      __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
+	}
 }
 
 void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base,
diff --git a/arch/powerpc/platforms/512x/clock-commonclk.c b/arch/powerpc/platforms/512x/clock-commonclk.c
index c50ea76ba66c..6081fbd75330 100644
--- a/arch/powerpc/platforms/512x/clock-commonclk.c
+++ b/arch/powerpc/platforms/512x/clock-commonclk.c
@@ -221,7 +221,7 @@ static bool soc_has_mclk_mux0_canin(void)
 /* convenience wrappers around the common clk API */
 static inline struct clk *mpc512x_clk_fixed(const char *name, int rate)
 {
-	return clk_register_fixed_rate(NULL, name, NULL, CLK_IS_ROOT, rate);
+	return clk_register_fixed_rate(NULL, name, NULL, 0, rate);
 }
 
 static inline struct clk *mpc512x_clk_factor(
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index 84fb984f29c1..85c85eb3e245 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -172,7 +172,7 @@ static int spufs_arch_write_note(struct spu_context *ctx, int i,
 	if (rc < 0)
 		goto out;
 
-	skip = roundup(cprm->file->f_pos - total + sz, 4) - cprm->file->f_pos;
+	skip = roundup(cprm->pos - total + sz, 4) - cprm->pos;
 	if (!dump_skip(cprm, skip))
 		goto Eio;
 out:
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index ac3ffd97e059..3998e0f9a03b 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -53,7 +53,6 @@ static int ibm_read_slot_reset_state2;
 static int ibm_slot_error_detail;
 static int ibm_get_config_addr_info;
 static int ibm_get_config_addr_info2;
-static int ibm_configure_bridge;
 static int ibm_configure_pe;
 
 /*
@@ -81,7 +80,14 @@ static int pseries_eeh_init(void)
 	ibm_get_config_addr_info2	= rtas_token("ibm,get-config-addr-info2");
 	ibm_get_config_addr_info	= rtas_token("ibm,get-config-addr-info");
 	ibm_configure_pe		= rtas_token("ibm,configure-pe");
-	ibm_configure_bridge		= rtas_token("ibm,configure-bridge");
+
+	/*
+	 * ibm,configure-pe and ibm,configure-bridge have the same semantics,
+	 * however ibm,configure-pe can be faster.  If we can't find
+	 * ibm,configure-pe then fall back to using ibm,configure-bridge.
+	 */
+	if (ibm_configure_pe == RTAS_UNKNOWN_SERVICE)
+		ibm_configure_pe 	= rtas_token("ibm,configure-bridge");
 
 	/*
 	 * Necessary sanity check. We needn't check "get-config-addr-info"
@@ -93,8 +99,7 @@ static int pseries_eeh_init(void)
 	    (ibm_read_slot_reset_state2 == RTAS_UNKNOWN_SERVICE &&
 	     ibm_read_slot_reset_state == RTAS_UNKNOWN_SERVICE)	||
 	    ibm_slot_error_detail == RTAS_UNKNOWN_SERVICE	||
-	    (ibm_configure_pe == RTAS_UNKNOWN_SERVICE		&&
-	     ibm_configure_bridge == RTAS_UNKNOWN_SERVICE)) {
+	    ibm_configure_pe == RTAS_UNKNOWN_SERVICE) {
 		pr_info("EEH functionality not supported\n");
 		return -EINVAL;
 	}
@@ -615,29 +620,41 @@ static int pseries_eeh_configure_bridge(struct eeh_pe *pe)
 {
 	int config_addr;
 	int ret;
+	/* Waiting 0.2s maximum before skipping configuration */
+	int max_wait = 200;
 
 	/* Figure out the PE address */
 	config_addr = pe->config_addr;
 	if (pe->addr)
 		config_addr = pe->addr;
 
-	/* Use new configure-pe function, if supported */
-	if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) {
+	while (max_wait > 0) {
 		ret = rtas_call(ibm_configure_pe, 3, 1, NULL,
 				config_addr, BUID_HI(pe->phb->buid),
 				BUID_LO(pe->phb->buid));
-	} else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) {
-		ret = rtas_call(ibm_configure_bridge, 3, 1, NULL,
-				config_addr, BUID_HI(pe->phb->buid),
-				BUID_LO(pe->phb->buid));
-	} else {
-		return -EFAULT;
-	}
 
-	if (ret)
-		pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n",
-			__func__, pe->phb->global_number, pe->addr, ret);
+		if (!ret)
+			return ret;
+
+		/*
+		 * If RTAS returns a delay value that's above 100ms, cut it
+		 * down to 100ms in case firmware made a mistake.  For more
+		 * on how these delay values work see rtas_busy_delay_time
+		 */
+		if (ret > RTAS_EXTENDED_DELAY_MIN+2 &&
+		    ret <= RTAS_EXTENDED_DELAY_MAX)
+			ret = RTAS_EXTENDED_DELAY_MIN+2;
+
+		max_wait -= rtas_busy_delay_time(ret);
+
+		if (max_wait < 0)
+			break;
+
+		rtas_busy_delay(ret);
+	}
 
+	pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n",
+		__func__, pe->phb->global_number, pe->addr, ret);
 	return ret;
 }
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 769af907f824..7597b42a8a88 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -181,19 +181,22 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 			     struct kvm_cpuid_entry __user *entries)
 {
 	int r, i;
-	struct kvm_cpuid_entry *cpuid_entries;
+	struct kvm_cpuid_entry *cpuid_entries = NULL;
 
 	r = -E2BIG;
 	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
 		goto out;
 	r = -ENOMEM;
-	cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) * cpuid->nent);
-	if (!cpuid_entries)
-		goto out;
-	r = -EFAULT;
-	if (copy_from_user(cpuid_entries, entries,
-			   cpuid->nent * sizeof(struct kvm_cpuid_entry)))
-		goto out_free;
+	if (cpuid->nent) {
+		cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) *
+					cpuid->nent);
+		if (!cpuid_entries)
+			goto out;
+		r = -EFAULT;
+		if (copy_from_user(cpuid_entries, entries,
+				   cpuid->nent * sizeof(struct kvm_cpuid_entry)))
+			goto out;
+	}
 	for (i = 0; i < cpuid->nent; i++) {
 		vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function;
 		vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax;
@@ -212,9 +215,8 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 	kvm_x86_ops->cpuid_update(vcpu);
 	r = kvm_update_cpuid(vcpu);
 
-out_free:
-	vfree(cpuid_entries);
 out:
+	vfree(cpuid_entries);
 	return r;
 }
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 24e800116ab4..def97b3a392b 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -336,12 +336,12 @@ static gfn_t pse36_gfn_delta(u32 gpte)
 #ifdef CONFIG_X86_64
 static void __set_spte(u64 *sptep, u64 spte)
 {
-	*sptep = spte;
+	WRITE_ONCE(*sptep, spte);
 }
 
 static void __update_clear_spte_fast(u64 *sptep, u64 spte)
 {
-	*sptep = spte;
+	WRITE_ONCE(*sptep, spte);
 }
 
 static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
@@ -390,7 +390,7 @@ static void __set_spte(u64 *sptep, u64 spte)
 	 */
 	smp_wmb();
 
-	ssptep->spte_low = sspte.spte_low;
+	WRITE_ONCE(ssptep->spte_low, sspte.spte_low);
 }
 
 static void __update_clear_spte_fast(u64 *sptep, u64 spte)
@@ -400,7 +400,7 @@ static void __update_clear_spte_fast(u64 *sptep, u64 spte)
 	ssptep = (union split_spte *)sptep;
 	sspte = (union split_spte)spte;
 
-	ssptep->spte_low = sspte.spte_low;
+	WRITE_ONCE(ssptep->spte_low, sspte.spte_low);
 
 	/*
 	 * If we map the spte from present to nonpresent, we should clear
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c805cf494154..902d9da12392 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2314,6 +2314,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_AMD64_NB_CFG:
 	case MSR_FAM10H_MMIO_CONF_BASE:
 	case MSR_AMD64_BU_CFG2:
+	case MSR_IA32_PERF_CTL:
 		msr_info->data = 0;
 		break;
 	case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
@@ -2972,6 +2973,10 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 			      | KVM_VCPUEVENT_VALID_SMM))
 		return -EINVAL;
 
+	if (events->exception.injected &&
+	    (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR))
+		return -EINVAL;
+
 	process_nmi(vcpu);
 	vcpu->arch.exception.pending = events->exception.injected;
 	vcpu->arch.exception.nr = events->exception.nr;
@@ -3036,6 +3041,11 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
 	if (dbgregs->flags)
 		return -EINVAL;
 
+	if (dbgregs->dr6 & ~0xffffffffull)
+		return -EINVAL;
+	if (dbgregs->dr7 & ~0xffffffffull)
+		return -EINVAL;
+
 	memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db));
 	kvm_update_dr0123(vcpu);
 	vcpu->arch.dr6 = dbgregs->dr6;
@@ -7815,7 +7825,7 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 
 	slot = id_to_memslot(slots, id);
 	if (size) {
-		if (WARN_ON(slot->npages))
+		if (slot->npages)
 			return -EEXIST;
 
 		/*