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

Conflicts:
	drivers/net/ethernet/cavium/Kconfig

The cavium conflict was overlapping dependency
changes.

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

89 files changed, 1217 insertions, 504 deletions

diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 91cf4055acab..bd4670d1b89b 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -313,11 +313,11 @@ config ARC_PAGE_SIZE_8K
 
 config ARC_PAGE_SIZE_16K
 	bool "16KB"
-	depends on ARC_MMU_V3
+	depends on ARC_MMU_V3 || ARC_MMU_V4
 
 config ARC_PAGE_SIZE_4K
 	bool "4KB"
-	depends on ARC_MMU_V3
+	depends on ARC_MMU_V3 || ARC_MMU_V4
 
 endchoice
 
@@ -365,6 +365,11 @@ config ARC_HAS_LLSC
 	default y
 	depends on !ARC_CANT_LLSC
 
+config ARC_STAR_9000923308
+	bool "Workaround for llock/scond livelock"
+	default y
+	depends on ISA_ARCV2 && SMP && ARC_HAS_LLSC
+
 config ARC_HAS_SWAPE
 	bool "Insn: SWAPE (endian-swap)"
 	default y
@@ -379,6 +384,10 @@ config ARC_HAS_LL64
 	  dest operands with 2 possible source operands.
 	default y
 
+config ARC_HAS_DIV_REM
+	bool "Insn: div, divu, rem, remu"
+	default y
+
 config ARC_HAS_RTC
 	bool "Local 64-bit r/o cycle counter"
 	default n
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 46d87310220d..8a27a48304a4 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -36,8 +36,16 @@ cflags-$(atleast_gcc44)			+= -fsection-anchors
 cflags-$(CONFIG_ARC_HAS_LLSC)		+= -mlock
 cflags-$(CONFIG_ARC_HAS_SWAPE)		+= -mswape
 
+ifdef CONFIG_ISA_ARCV2
+
 ifndef CONFIG_ARC_HAS_LL64
-cflags-$(CONFIG_ISA_ARCV2)		+= -mno-ll64
+cflags-y				+= -mno-ll64
+endif
+
+ifndef CONFIG_ARC_HAS_DIV_REM
+cflags-y				+= -mno-div-rem
+endif
+
 endif
 
 cflags-$(CONFIG_ARC_DW2_UNWIND)		+= -fasynchronous-unwind-tables
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index 070f58827a5c..c8f57b8449dc 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -89,11 +89,10 @@
 #define ECR_C_BIT_DTLB_LD_MISS		8
 #define ECR_C_BIT_DTLB_ST_MISS		9
 
-
 /* Auxiliary registers */
 #define AUX_IDENTITY		4
 #define AUX_INTR_VEC_BASE	0x25
-
+#define AUX_NON_VOL		0x5e
 
 /*
  * Floating Pt Registers
@@ -240,9 +239,9 @@ struct bcr_extn_xymem {
 
 struct bcr_perip {
 #ifdef CONFIG_CPU_BIG_ENDIAN
-	unsigned int start:8, pad2:8, sz:8, pad:8;
+	unsigned int start:8, pad2:8, sz:8, ver:8;
 #else
-	unsigned int pad:8, sz:8, pad2:8, start:8;
+	unsigned int ver:8, sz:8, pad2:8, start:8;
 #endif
 };
 
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 03484cb4d16d..87d18ae53115 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -23,33 +23,60 @@
 
 #define atomic_set(v, i) (((v)->counter) = (i))
 
-#ifdef CONFIG_ISA_ARCV2
-#define PREFETCHW	"	prefetchw   [%1]	\n"
-#else
-#define PREFETCHW
+#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 temp;						\
+	unsigned int val;				                \
+	SCOND_FAIL_RETRY_VAR_DEF                                        \
 									\
 	__asm__ __volatile__(						\
-	"1:				\n"				\
-	PREFETCHW							\
-	"	llock   %0, [%1]	\n"				\
-	"	" #asm_op " %0, %0, %2	\n"				\
-	"	scond   %0, [%1]	\n"				\
-	"	bnz     1b		\n"				\
-	: "=&r"(temp)	/* Early clobber, to prevent reg reuse */	\
-	: "r"(&v->counter), "ir"(i)					\
+	"1:	llock   %[val], [%[ctr]]		\n"		\
+	"	" #asm_op " %[val], %[val], %[i]	\n"		\
+	"	scond   %[val], [%[ctr]]		\n"		\
+	"						\n"		\
+	SCOND_FAIL_RETRY_ASM						\
+									\
+	: [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");							\
 }									\
 
 #define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
 static inline int atomic_##op##_return(int i, atomic_t *v)		\
 {									\
-	unsigned int temp;						\
+	unsigned int val;				                \
+	SCOND_FAIL_RETRY_VAR_DEF                                        \
 									\
 	/*								\
 	 * Explicit full memory barrier needed before/after as		\
@@ -58,19 +85,21 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	smp_mb();							\
 									\
 	__asm__ __volatile__(						\
-	"1:				\n"				\
-	PREFETCHW							\
-	"	llock   %0, [%1]	\n"				\
-	"	" #asm_op " %0, %0, %2	\n"				\
-	"	scond   %0, [%1]	\n"				\
-	"	bnz     1b		\n"				\
-	: "=&r"(temp)							\
-	: "r"(&v->counter), "ir"(i)					\
+	"1:	llock   %[val], [%[ctr]]		\n"		\
+	"	" #asm_op " %[val], %[val], %[i]	\n"		\
+	"	scond   %[val], [%[ctr]]		\n"		\
+	"						\n"		\
+	SCOND_FAIL_RETRY_ASM						\
+									\
+	: [val]	"=&r"	(val)						\
+	  SCOND_FAIL_RETRY_VARS						\
+	: [ctr]	"r"	(&v->counter),					\
+	  [i]	"ir"	(i)						\
 	: "cc");							\
 									\
 	smp_mb();							\
 									\
-	return temp;							\
+	return val;							\
 }
 
 #else	/* !CONFIG_ARC_HAS_LLSC */
@@ -150,6 +179,9 @@ ATOMIC_OP(and, &=, and)
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
+#undef SCOND_FAIL_RETRY_VAR_DEF
+#undef SCOND_FAIL_RETRY_ASM
+#undef SCOND_FAIL_RETRY_VARS
 
 /**
  * __atomic_add_unless - add unless the number is a given value
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
index 91694ec1ce95..69095da1fcfd 100644
--- a/arch/arc/include/asm/ptrace.h
+++ b/arch/arc/include/asm/ptrace.h
@@ -20,20 +20,20 @@
 struct pt_regs {
 
 	/* Real registers */
-	long bta;	/* bta_l1, bta_l2, erbta */
+	unsigned long bta;	/* bta_l1, bta_l2, erbta */
 
-	long lp_start, lp_end, lp_count;
+	unsigned long lp_start, lp_end, lp_count;
 
-	long status32;	/* status32_l1, status32_l2, erstatus */
-	long ret;	/* ilink1, ilink2 or eret */
-	long blink;
-	long fp;
-	long r26;	/* gp */
+	unsigned long status32;	/* status32_l1, status32_l2, erstatus */
+	unsigned long ret;	/* ilink1, ilink2 or eret */
+	unsigned long blink;
+	unsigned long fp;
+	unsigned long r26;	/* gp */
 
-	long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
+	unsigned long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
 
-	long sp;	/* user/kernel sp depending on where we came from  */
-	long orig_r0;
+	unsigned long sp;	/* User/Kernel depending on where we came from */
+	unsigned long orig_r0;
 
 	/*
 	 * To distinguish bet excp, syscall, irq
@@ -55,13 +55,13 @@ struct pt_regs {
 		unsigned long event;
 	};
 
-	long user_r25;
+	unsigned long user_r25;
 };
 #else
 
 struct pt_regs {
 
-	long orig_r0;
+	unsigned long orig_r0;
 
 	union {
 		struct {
@@ -76,26 +76,26 @@ struct pt_regs {
 		unsigned long event;
 	};
 
-	long bta;	/* bta_l1, bta_l2, erbta */
+	unsigned long bta;	/* bta_l1, bta_l2, erbta */
 
-	long user_r25;
+	unsigned long user_r25;
 
-	long r26;	/* gp */
-	long fp;
-	long sp;	/* user/kernel sp depending on where we came from  */
+	unsigned long r26;	/* gp */
+	unsigned long fp;
+	unsigned long sp;	/* user/kernel sp depending on where we came from  */
 
-	long r12;
+	unsigned long r12;
 
 	/*------- Below list auto saved by h/w -----------*/
-	long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11;
+	unsigned long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11;
 
-	long blink;
-	long lp_end, lp_start, lp_count;
+	unsigned long blink;
+	unsigned long lp_end, lp_start, lp_count;
 
-	long ei, ldi, jli;
+	unsigned long ei, ldi, jli;
 
-	long ret;
-	long status32;
+	unsigned long ret;
+	unsigned long status32;
 };
 
 #endif
@@ -103,10 +103,10 @@ struct pt_regs {
 /* Callee saved registers - need to be saved only when you are scheduled out */
 
 struct callee_regs {
-	long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
+	unsigned long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
 };
 
-#define instruction_pointer(regs)	(unsigned long)((regs)->ret)
+#define instruction_pointer(regs)	((regs)->ret)
 #define profile_pc(regs)		instruction_pointer(regs)
 
 /* return 1 if user mode or 0 if kernel mode */
@@ -142,7 +142,7 @@ struct callee_regs {
 
 static inline long regs_return_value(struct pt_regs *regs)
 {
-	return regs->r0;
+	return (long)regs->r0;
 }
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
index e1651df6a93d..db8c59d1eaeb 100644
--- a/arch/arc/include/asm/spinlock.h
+++ b/arch/arc/include/asm/spinlock.h
@@ -18,9 +18,518 @@
 #define arch_spin_unlock_wait(x) \
 	do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0)
 
+#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 tmp = __ARCH_SPIN_LOCK_LOCKED__;
+	unsigned int val;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[slock]]	\n"
+	"	breq	%[val], %[LOCKED], 1b	\n"	/* spin while LOCKED */
+	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [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;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[slock]]	\n"
+	"	breq	%[val], %[LOCKED], 4f	\n"	/* already LOCKED, just bail */
+	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
+	"	bnz	1b			\n"
+	"	mov	%[got_it], 1		\n"
+	"4:					\n"
+	"					\n"
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	: [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;
+
+	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__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brls	%[val], %[WR_LOCKED], 1b\n"	/* <= 0: spin while write locked */
+	"	sub	%[val], %[val], 1	\n"	/* reader lock */
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [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;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"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"
+	"	bnz	1b			\n"	/* retry if collided with someone */
+	"	mov	%[got_it], 1		\n"
+	"					\n"
+	"4: ; --- done ---			\n"
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	: [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;
+
+	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__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brne	%[val], %[UNLOCKED], 1b	\n"	/* while !UNLOCKED spin */
+	"	mov	%[val], %[WR_LOCKED]	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [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;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brne	%[val], %[UNLOCKED], 4f	\n"	/* !UNLOCKED, bail */
+	"	mov	%[val], %[WR_LOCKED]	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"	/* retry if collided with someone */
+	"	mov	%[got_it], 1		\n"
+	"					\n"
+	"4: ; --- done ---			\n"
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	: [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)
+{
+	smp_mb();
+
+	rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
+
+	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)
+{
+	unsigned int val = __ARCH_SPIN_LOCK_LOCKED__;
 
 	/*
 	 * This smp_mb() is technically superfluous, we only need the one
@@ -33,7 +542,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	__asm__ __volatile__(
 	"1:	ex  %0, [%1]		\n"
 	"	breq  %0, %2, 1b	\n"
-	: "+&r" (tmp)
+	: "+&r" (val)
 	: "r"(&(lock->slock)), "ir"(__ARCH_SPIN_LOCK_LOCKED__)
 	: "memory");
 
@@ -48,26 +557,27 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	smp_mb();
 }
 
+/* 1 - lock taken successfully */
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
-	unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
+	unsigned int val = __ARCH_SPIN_LOCK_LOCKED__;
 
 	smp_mb();
 
 	__asm__ __volatile__(
 	"1:	ex  %0, [%1]		\n"
-	: "+r" (tmp)
+	: "+r" (val)
 	: "r"(&(lock->slock))
 	: "memory");
 
 	smp_mb();
 
-	return (tmp == __ARCH_SPIN_LOCK_UNLOCKED__);
+	return (val == __ARCH_SPIN_LOCK_UNLOCKED__);
 }
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
-	unsigned int tmp = __ARCH_SPIN_LOCK_UNLOCKED__;
+	unsigned int val = __ARCH_SPIN_LOCK_UNLOCKED__;
 
 	/*
 	 * RELEASE barrier: given the instructions avail on ARCv2, full barrier
@@ -77,7 +587,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 
 	__asm__ __volatile__(
 	"	ex  %0, [%1]		\n"
-	: "+r" (tmp)
+	: "+r" (val)
 	: "r"(&(lock->slock))
 	: "memory");
 
@@ -90,19 +600,12 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 
 /*
  * Read-write spinlocks, allowing multiple readers but only one writer.
+ * Unfair locking as Writers could be starved indefinitely by Reader(s)
  *
  * The spinlock itself is contained in @counter and access to it is
  * serialized with @lock_mutex.
- *
- * Unfair locking as Writers could be starved indefinitely by Reader(s)
  */
 
-/* Would read_trylock() succeed? */
-#define arch_read_can_lock(x)	((x)->counter > 0)
-
-/* Would write_trylock() succeed? */
-#define arch_write_can_lock(x)	((x)->counter == __ARCH_RW_LOCK_UNLOCKED__)
-
 /* 1 - lock taken successfully */
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
@@ -173,6 +676,11 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 	arch_spin_unlock(&(rw->lock_mutex));
 }
 
+#endif
+
+#define arch_read_can_lock(x)	((x)->counter > 0)
+#define arch_write_can_lock(x)	((x)->counter == __ARCH_RW_LOCK_UNLOCKED__)
+
 #define arch_read_lock_flags(lock, flags)	arch_read_lock(lock)
 #define arch_write_lock_flags(lock, flags)	arch_write_lock(lock)
 
diff --git a/arch/arc/include/asm/spinlock_types.h b/arch/arc/include/asm/spinlock_types.h
index 662627ced4f2..4e1ef5f650c6 100644
--- a/arch/arc/include/asm/spinlock_types.h
+++ b/arch/arc/include/asm/spinlock_types.h
@@ -26,7 +26,9 @@ typedef struct {
  */
 typedef struct {
 	volatile unsigned int	counter;
+#ifndef CONFIG_ARC_HAS_LLSC
 	arch_spinlock_t		lock_mutex;
+#endif
 } arch_rwlock_t;
 
 #define __ARCH_RW_LOCK_UNLOCKED__	0x01000000
diff --git a/arch/arc/include/uapi/asm/ptrace.h b/arch/arc/include/uapi/asm/ptrace.h
index 76a7739aab1c..0b3ef63d4a03 100644
--- a/arch/arc/include/uapi/asm/ptrace.h
+++ b/arch/arc/include/uapi/asm/ptrace.h
@@ -32,20 +32,20 @@
 */
 struct user_regs_struct {
 
-	long pad;
+	unsigned long pad;
 	struct {
-		long bta, lp_start, lp_end, lp_count;
-		long status32, ret, blink, fp, gp;
-		long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
-		long sp;
+		unsigned long bta, lp_start, lp_end, lp_count;
+		unsigned long status32, ret, blink, fp, gp;
+		unsigned long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
+		unsigned long sp;
 	} scratch;
-	long pad2;
+	unsigned long pad2;
 	struct {
-		long r25, r24, r23, r22, r21, r20;
-		long r19, r18, r17, r16, r15, r14, r13;
+		unsigned long r25, r24, r23, r22, r21, r20;
+		unsigned long r19, r18, r17, r16, r15, r14, r13;
 	} callee;
-	long efa;	/* break pt addr, for break points in delay slots */
-	long stop_pc;	/* give dbg stop_pc after ensuring brkpt trap */
+	unsigned long efa;	/* break pt addr, for break points in delay slots */
+	unsigned long stop_pc;	/* give dbg stop_pc after ensuring brkpt trap */
 };
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 18cc01591c96..cabde9dc0696 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -47,6 +47,7 @@ static void read_arc_build_cfg_regs(void)
 	struct bcr_perip uncached_space;
 	struct bcr_generic bcr;
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
+	unsigned long perip_space;
 	FIX_PTR(cpu);
 
 	READ_BCR(AUX_IDENTITY, cpu->core);
@@ -56,7 +57,12 @@ static void read_arc_build_cfg_regs(void)
 	cpu->vec_base = read_aux_reg(AUX_INTR_VEC_BASE);
 
 	READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space);
-	BUG_ON((uncached_space.start << 24) != ARC_UNCACHED_ADDR_SPACE);
+        if (uncached_space.ver < 3)
+		perip_space = uncached_space.start << 24;
+	else
+		perip_space = read_aux_reg(AUX_NON_VOL) & 0xF0000000;
+
+	BUG_ON(perip_space != ARC_UNCACHED_ADDR_SPACE);
 
 	READ_BCR(ARC_REG_MUL_BCR, cpu->extn_mpy);
 
@@ -330,6 +336,10 @@ static void arc_chk_core_config(void)
 		pr_warn("CONFIG_ARC_FPU_SAVE_RESTORE needed for working apps\n");
 	else if (!cpu->extn.fpu_dp && fpu_enabled)
 		panic("FPU non-existent, disable CONFIG_ARC_FPU_SAVE_RESTORE\n");
+
+	if (is_isa_arcv2() && IS_ENABLED(CONFIG_SMP) && cpu->isa.atomic &&
+	    !IS_ENABLED(CONFIG_ARC_STAR_9000923308))
+		panic("llock/scond livelock workaround missing\n");
 }
 
 /*
diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c
index 3364d2bbc515..4294761a2b3e 100644
--- a/arch/arc/kernel/time.c
+++ b/arch/arc/kernel/time.c
@@ -203,34 +203,24 @@ static int arc_clkevent_set_next_event(unsigned long delta,
 	return 0;
 }
 
-static void arc_clkevent_set_mode(enum clock_event_mode mode,
-				  struct clock_event_device *dev)
+static int arc_clkevent_set_periodic(struct clock_event_device *dev)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-                /*
-                 * At X Hz, 1 sec = 1000ms -> X cycles;
-                 *                    10ms -> X / 100 cycles
-                 */
-		arc_timer_event_setup(arc_get_core_freq() / HZ);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		break;
-	default:
-		break;
-	}
-
-	return;
+	/*
+	 * At X Hz, 1 sec = 1000ms -> X cycles;
+	 *		      10ms -> X / 100 cycles
+	 */
+	arc_timer_event_setup(arc_get_core_freq() / HZ);
+	return 0;
 }
 
 static DEFINE_PER_CPU(struct clock_event_device, arc_clockevent_device) = {
-	.name		= "ARC Timer0",
-	.features	= CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
-	.mode		= CLOCK_EVT_MODE_UNUSED,
-	.rating		= 300,
-	.irq		= TIMER0_IRQ,	/* hardwired, no need for resources */
-	.set_next_event = arc_clkevent_set_next_event,
-	.set_mode	= arc_clkevent_set_mode,
+	.name			= "ARC Timer0",
+	.features		= CLOCK_EVT_FEAT_ONESHOT |
+				  CLOCK_EVT_FEAT_PERIODIC,
+	.rating			= 300,
+	.irq			= TIMER0_IRQ,	/* hardwired, no need for resources */
+	.set_next_event		= arc_clkevent_set_next_event,
+	.set_state_periodic	= arc_clkevent_set_periodic,
 };
 
 static irqreturn_t timer_irq_handler(int irq, void *dev_id)
@@ -240,7 +230,7 @@ static irqreturn_t timer_irq_handler(int irq, void *dev_id)
 	 * irq_set_chip_and_handler() asked for handle_percpu_devid_irq()
 	 */
 	struct clock_event_device *evt = this_cpu_ptr(&arc_clockevent_device);
-	int irq_reenable = evt->mode == CLOCK_EVT_MODE_PERIODIC;
+	int irq_reenable = clockevent_state_periodic(evt);
 
 	/*
 	 * Any write to CTRL reg ACks the interrupt, we rewrite the
diff --git a/arch/arc/lib/memcpy-archs.S b/arch/arc/lib/memcpy-archs.S
index 1b2b3acfed52..0cab0b8a57c5 100644
--- a/arch/arc/lib/memcpy-archs.S
+++ b/arch/arc/lib/memcpy-archs.S
@@ -206,7 +206,7 @@ unalignedOffby3:
 	ld.ab	r6, [r1, 4]
 	prefetch [r1, 28]	;Prefetch the next read location
 	ld.ab	r8, [r1,4]
-	prefetch [r3, 32]	;Prefetch the next write location
+	prefetchw [r3, 32]	;Prefetch the next write location
 
 	SHIFT_1	(r7, r6, 8)
 	or	r7, r7, r5
diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S
index 92d573c734b5..365b18364815 100644
--- a/arch/arc/lib/memset-archs.S
+++ b/arch/arc/lib/memset-archs.S
@@ -10,12 +10,6 @@
 
 #undef PREALLOC_NOT_AVAIL
 
-#ifdef PREALLOC_NOT_AVAIL
-#define PREWRITE(A,B)	prefetchw [(A),(B)]
-#else
-#define PREWRITE(A,B)	prealloc [(A),(B)]
-#endif
-
 ENTRY(memset)
 	prefetchw [r0]		; Prefetch the write location
 	mov.f	0, r2
@@ -51,9 +45,15 @@ ENTRY(memset)
 
 ;;; Convert len to Dwords, unfold x8
 	lsr.f	lp_count, lp_count, 6
+
 	lpnz	@.Lset64bytes
 	;; LOOP START
-	PREWRITE(r3, 64)	;Prefetch the next write location
+#ifdef PREALLOC_NOT_AVAIL
+	prefetchw [r3, 64]	;Prefetch the next write location
+#else
+	prealloc  [r3, 64]
+#endif
+#ifdef CONFIG_ARC_HAS_LL64
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
@@ -62,16 +62,45 @@ ENTRY(memset)
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
+#else
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+#endif
 .Lset64bytes:
 
 	lsr.f	lp_count, r2, 5 ;Last remaining  max 124 bytes
 	lpnz	.Lset32bytes
 	;; LOOP START
 	prefetchw   [r3, 32]	;Prefetch the next write location
+#ifdef CONFIG_ARC_HAS_LL64
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
+#else
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+#endif
 .Lset32bytes:
 
 	and.f	lp_count, r2, 0x1F ;Last remaining 31 bytes
diff --git a/arch/arc/plat-axs10x/axs10x.c b/arch/arc/plat-axs10x/axs10x.c
index 99f7da513a48..e7769c3ab5f2 100644
--- a/arch/arc/plat-axs10x/axs10x.c
+++ b/arch/arc/plat-axs10x/axs10x.c
@@ -389,6 +389,21 @@ axs103_set_freq(unsigned int id, unsigned int fd, unsigned int od)
 
 static void __init axs103_early_init(void)
 {
+	/*
+	 * AXS103 configurations for SMP/QUAD configurations share device tree
+	 * which defaults to 90 MHz. However recent failures of Quad config
+	 * revealed P&R timing violations so clamp it down to safe 50 MHz
+	 * Instead of duplicating defconfig/DT for SMP/QUAD, add a small hack
+	 *
+	 * This hack is really hacky as of now. Fix it properly by getting the
+	 * number of cores as return value of platform's early SMP callback
+	 */
+#ifdef CONFIG_ARC_MCIP
+	unsigned int num_cores = (read_aux_reg(ARC_REG_MCIP_BCR) >> 16) & 0x3F;
+	if (num_cores > 2)
+		arc_set_core_freq(50 * 1000000);
+#endif
+
 	switch (arc_get_core_freq()/1000000) {
 	case 33:
 		axs103_set_freq(1, 1, 1);
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 8f1e25bcecbd..4a0718ccf68e 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1140,6 +1140,7 @@
 				ctrl-module = <&omap_control_sata>;
 				clocks = <&sys_clkin1>, <&sata_ref_clk>;
 				clock-names = "sysclk", "refclk";
+				syscon-pllreset = <&scm_conf 0x3fc>;
 				#phy-cells = <0>;
 			};
 
diff --git a/arch/arm/boot/dts/exynos3250.dtsi b/arch/arm/boot/dts/exynos3250.dtsi
index d7201333e3bc..2db99433e17f 100644
--- a/arch/arm/boot/dts/exynos3250.dtsi
+++ b/arch/arm/boot/dts/exynos3250.dtsi
@@ -138,8 +138,8 @@
 
 		mipi_phy: video-phy@10020710 {
 			compatible = "samsung,s5pv210-mipi-video-phy";
-			reg = <0x10020710 8>;
 			#phy-cells = <1>;
+			syscon = <&pmu_system_controller>;
 		};
 
 		pd_cam: cam-power-domain@10023C00 {
diff --git a/arch/arm/boot/dts/exynos4210-origen.dts b/arch/arm/boot/dts/exynos4210-origen.dts
index e0abfc3324d1..e050d85cdacd 100644
--- a/arch/arm/boot/dts/exynos4210-origen.dts
+++ b/arch/arm/boot/dts/exynos4210-origen.dts
@@ -127,6 +127,10 @@
 	};
 };
 
+&cpu0 {
+	cpu0-supply = <&buck1_reg>;
+};
+
 &fimd {
 	pinctrl-0 = <&lcd_en &lcd_clk &lcd_data24 &pwm0_out>;
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/exynos4210-trats.dts b/arch/arm/boot/dts/exynos4210-trats.dts
index 98f3ce65cb9a..ba34886f8b65 100644
--- a/arch/arm/boot/dts/exynos4210-trats.dts
+++ b/arch/arm/boot/dts/exynos4210-trats.dts
@@ -188,6 +188,10 @@
 	};
 };
 
+&cpu0 {
+	cpu0-supply = <&varm_breg>;
+};
+
 &dsi_0 {
 	vddcore-supply = <&vusb_reg>;
 	vddio-supply = <&vmipi_reg>;
diff --git a/arch/arm/boot/dts/exynos4210-universal_c210.dts b/arch/arm/boot/dts/exynos4210-universal_c210.dts
index d4f2b11319dd..775892b2cc6a 100644
--- a/arch/arm/boot/dts/exynos4210-universal_c210.dts
+++ b/arch/arm/boot/dts/exynos4210-universal_c210.dts
@@ -548,6 +548,10 @@
 	};
 };
 
+&cpu0 {
+	cpu0-supply = <&vdd_arm_reg>;
+};
+
 &pinctrl_1 {
 	hdmi_hpd: hdmi-hpd {
 		samsung,pins = "gpx3-7";
diff --git a/arch/arm/boot/dts/exynos4210.dtsi b/arch/arm/boot/dts/exynos4210.dtsi
index 10d3c173396e..3e5ba665d200 100644
--- a/arch/arm/boot/dts/exynos4210.dtsi
+++ b/arch/arm/boot/dts/exynos4210.dtsi
@@ -40,6 +40,18 @@
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <0x900>;
+			clocks = <&clock CLK_ARM_CLK>;
+			clock-names = "cpu";
+			clock-latency = <160000>;
+
+			operating-points = <
+				1200000 1250000
+				1000000 1150000
+				800000	1075000
+				500000	975000
+				400000	975000
+				200000	950000
+			>;
 			cooling-min-level = <4>;
 			cooling-max-level = <2>;
 			#cooling-cells = <2>; /* min followed by max */
diff --git a/arch/arm/boot/dts/imx35.dtsi b/arch/arm/boot/dts/imx35.dtsi
index b6478e97d6a7..e6540b5cfa4c 100644
--- a/arch/arm/boot/dts/imx35.dtsi
+++ b/arch/arm/boot/dts/imx35.dtsi
@@ -286,8 +286,8 @@
 			can1: can@53fe4000 {
 				compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan";
 				reg = <0x53fe4000 0x1000>;
-				clocks = <&clks 33>;
-				clock-names = "ipg";
+				clocks = <&clks 33>, <&clks 33>;
+				clock-names = "ipg", "per";
 				interrupts = <43>;
 				status = "disabled";
 			};
@@ -295,8 +295,8 @@
 			can2: can@53fe8000 {
 				compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan";
 				reg = <0x53fe8000 0x1000>;
-				clocks = <&clks 34>;
-				clock-names = "ipg";
+				clocks = <&clks 34>, <&clks 34>;
+				clock-names = "ipg", "per";
 				interrupts = <44>;
 				status = "disabled";
 			};
diff --git a/arch/arm/boot/dts/k2e-clocks.dtsi b/arch/arm/boot/dts/k2e-clocks.dtsi
index 4773d6af66a0..d56d68fe7ffc 100644
--- a/arch/arm/boot/dts/k2e-clocks.dtsi
+++ b/arch/arm/boot/dts/k2e-clocks.dtsi
@@ -13,9 +13,8 @@ clocks {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,main-pll-clock";
 		clocks = <&refclksys>;
-		reg = <0x02620350 4>, <0x02310110 4>;
-		reg-names = "control", "multiplier";
-		fixed-postdiv = <2>;
+		reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>;
+		reg-names = "control", "multiplier", "post-divider";
 	};
 
 	papllclk: papllclk@2620358 {
diff --git a/arch/arm/boot/dts/k2hk-clocks.dtsi b/arch/arm/boot/dts/k2hk-clocks.dtsi
index d5adee3c0067..af9b7190533a 100644
--- a/arch/arm/boot/dts/k2hk-clocks.dtsi
+++ b/arch/arm/boot/dts/k2hk-clocks.dtsi
@@ -22,9 +22,8 @@ clocks {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,main-pll-clock";
 		clocks = <&refclksys>;
-		reg = <0x02620350 4>, <0x02310110 4>;
-		reg-names = "control", "multiplier";
-		fixed-postdiv = <2>;
+		reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>;
+		reg-names = "control", "multiplier", "post-divider";
 	};
 
 	papllclk: papllclk@2620358 {
diff --git a/arch/arm/boot/dts/k2l-clocks.dtsi b/arch/arm/boot/dts/k2l-clocks.dtsi
index eb1e3e29f073..ef8464bb11ff 100644
--- a/arch/arm/boot/dts/k2l-clocks.dtsi
+++ b/arch/arm/boot/dts/k2l-clocks.dtsi
@@ -22,9 +22,8 @@ clocks {
 		#clock-cells = <0>;
 		compatible = "ti,keystone,main-pll-clock";
 		clocks = <&refclksys>;
-		reg = <0x02620350 4>, <0x02310110 4>;
-		reg-names = "control", "multiplier";
-		fixed-postdiv = <2>;
+		reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>;
+		reg-names = "control", "multiplier", "post-divider";
 	};
 
 	papllclk: papllclk@2620358 {
diff --git a/arch/arm/boot/dts/ste-nomadik-nhk15.dts b/arch/arm/boot/dts/ste-nomadik-nhk15.dts
index 3d0b8755caee..3d25dba143a5 100644
--- a/arch/arm/boot/dts/ste-nomadik-nhk15.dts
+++ b/arch/arm/boot/dts/ste-nomadik-nhk15.dts
@@ -17,6 +17,7 @@
 	};
 
 	aliases {
+		serial1 = &uart1;
 		stmpe-i2c0 = &stmpe0;
 		stmpe-i2c1 = &stmpe1;
 	};
diff --git a/arch/arm/boot/dts/ste-nomadik-s8815.dts b/arch/arm/boot/dts/ste-nomadik-s8815.dts
index 85d3b95dfdba..3c140d05f796 100644
--- a/arch/arm/boot/dts/ste-nomadik-s8815.dts
+++ b/arch/arm/boot/dts/ste-nomadik-s8815.dts
@@ -15,6 +15,10 @@
 		bootargs = "root=/dev/ram0 console=ttyAMA1,115200n8 earlyprintk";
 	};
 
+	aliases {
+		serial1 = &uart1;
+	};
+
 	src@101e0000 {
 		/* These chrystal drivers are not used on this board */
 		disable-sxtalo;
diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
index 9a5f2ba139b7..ef794a33b4dc 100644
--- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
+++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
@@ -757,6 +757,7 @@
 			clock-names = "uartclk", "apb_pclk";
 			pinctrl-names = "default";
 			pinctrl-0 = <&uart0_default_mux>;
+			status = "disabled";
 		};
 
 		uart1: uart@101fb000 {
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index d78c12e7cb5e..486cc4ded190 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -2373,6 +2373,9 @@ static int of_dev_hwmod_lookup(struct device_node *np,
  * registers.  This address is needed early so the OCP registers that
  * are part of the device's address space can be ioremapped properly.
  *
+ * If SYSC access is not needed, the registers will not be remapped
+ * and non-availability of MPU access is not treated as an error.
+ *
  * Returns 0 on success, -EINVAL if an invalid hwmod is passed, and
  * -ENXIO on absent or invalid register target address space.
  */
@@ -2387,6 +2390,11 @@ static int __init _init_mpu_rt_base(struct omap_hwmod *oh, void *data,
 
 	_save_mpu_port_index(oh);
 
+	/* if we don't need sysc access we don't need to ioremap */
+	if (!oh->class->sysc)
+		return 0;
+
+	/* we can't continue without MPU PORT if we need sysc access */
 	if (oh->_int_flags & _HWMOD_NO_MPU_PORT)
 		return -ENXIO;
 
@@ -2396,8 +2404,10 @@ static int __init _init_mpu_rt_base(struct omap_hwmod *oh, void *data,
 			 oh->name);
 
 		/* Extract the IO space from device tree blob */
-		if (!np)
+		if (!np) {
+			pr_err("omap_hwmod: %s: no dt node\n", oh->name);
 			return -ENXIO;
+		}
 
 		va_start = of_iomap(np, index + oh->mpu_rt_idx);
 	} else {
@@ -2456,13 +2466,11 @@ static int __init _init(struct omap_hwmod *oh, void *data)
 				oh->name, np->name);
 	}
 
-	if (oh->class->sysc) {
-		r = _init_mpu_rt_base(oh, NULL, index, np);
-		if (r < 0) {
-			WARN(1, "omap_hwmod: %s: doesn't have mpu register target base\n",
-			     oh->name);
-			return 0;
-		}
+	r = _init_mpu_rt_base(oh, NULL, index, np);
+	if (r < 0) {
+		WARN(1, "omap_hwmod: %s: doesn't have mpu register target base\n",
+		     oh->name);
+		return 0;
 	}
 
 	r = _init_clocks(oh, NULL);
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 2606c6608bd8..562247bced49 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -827,8 +827,7 @@ static struct omap_hwmod_class_sysconfig dra7xx_gpmc_sysc = {
 	.syss_offs	= 0x0014,
 	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_SIDLEMODE |
 			   SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS),
-	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
-			   SIDLE_SMART_WKUP),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
 	.sysc_fields	= &omap_hwmod_sysc_type1,
 };
 
@@ -844,7 +843,7 @@ static struct omap_hwmod dra7xx_gpmc_hwmod = {
 	.class		= &dra7xx_gpmc_hwmod_class,
 	.clkdm_name	= "l3main1_clkdm",
 	/* Skip reset for CONFIG_OMAP_GPMC_DEBUG for bootloader timings */
-	.flags		= HWMOD_SWSUP_SIDLE | DEBUG_OMAP_GPMC_HWMOD_FLAGS,
+	.flags		= DEBUG_OMAP_GPMC_HWMOD_FLAGS,
 	.main_clk	= "l3_iclk_div",
 	.prcm = {
 		.omap4 = {
diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi
index 0689c3fb56e3..58093edeea2e 100644
--- a/arch/arm64/boot/dts/apm/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi
@@ -823,7 +823,7 @@
 			device_type = "dma";
 			reg = <0x0 0x1f270000 0x0 0x10000>,
 			      <0x0 0x1f200000 0x0 0x10000>,
-			      <0x0 0x1b008000 0x0 0x2000>,
+			      <0x0 0x1b000000 0x0 0x400000>,
 			      <0x0 0x1054a000 0x0 0x100>;
 			interrupts = <0x0 0x82 0x4>,
 				     <0x0 0xb8 0x4>,
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 1670f15ef69e..948f0ad2de23 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -168,7 +168,8 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 		 * Other callers might not initialize the si_lsb field,
 		 * so check explicitely for the right codes here.
 		 */
-		if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)
+		if (from->si_signo == SIGBUS &&
+		    (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO))
 			err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
 #endif
 		break;
@@ -201,8 +202,6 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 
 int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 {
-	memset(to, 0, sizeof *to);
-
 	if (copy_from_user(to, from, __ARCH_SI_PREAMBLE_SIZE) ||
 	    copy_from_user(to->_sifields._pad,
 			   from->_sifields._pad, SI_PAD_SIZE))
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index ec37ab3f524f..97bc68f4c689 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -199,16 +199,15 @@ up_fail:
  */
 void update_vsyscall(struct timekeeper *tk)
 {
-	struct timespec xtime_coarse;
 	u32 use_syscall = strcmp(tk->tkr_mono.clock->name, "arch_sys_counter");
 
 	++vdso_data->tb_seq_count;
 	smp_wmb();
 
-	xtime_coarse = __current_kernel_time();
 	vdso_data->use_syscall			= use_syscall;
-	vdso_data->xtime_coarse_sec		= xtime_coarse.tv_sec;
-	vdso_data->xtime_coarse_nsec		= xtime_coarse.tv_nsec;
+	vdso_data->xtime_coarse_sec		= tk->xtime_sec;
+	vdso_data->xtime_coarse_nsec		= tk->tkr_mono.xtime_nsec >>
+							tk->tkr_mono.shift;
 	vdso_data->wtm_clock_sec		= tk->wall_to_monotonic.tv_sec;
 	vdso_data->wtm_clock_nsec		= tk->wall_to_monotonic.tv_nsec;
 
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index cee5f93e5712..199a8357838c 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -151,7 +151,6 @@ config BMIPS_GENERIC
 	select BCM7120_L2_IRQ
 	select BRCMSTB_L2_IRQ
 	select IRQ_MIPS_CPU
-	select RAW_IRQ_ACCESSORS
 	select DMA_NONCOHERENT
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_LITTLE_ENDIAN
diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c
index 01a644f174dd..1ba21204ebe0 100644
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -190,6 +190,7 @@ int get_c0_perfcount_int(void)
 {
 	return ATH79_MISC_IRQ(5);
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index 56f5d080ef9d..b7fa9ae28c36 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -42,7 +42,7 @@ static irqreturn_t mailbox_interrupt(int irq, void *dev_id)
 	cvmx_write_csr(CVMX_CIU_MBOX_CLRX(coreid), action);
 
 	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+		generic_smp_call_function_interrupt();
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 
diff --git a/arch/mips/include/asm/mach-bcm63xx/dma-coherence.h b/arch/mips/include/asm/mach-bcm63xx/dma-coherence.h
deleted file mode 100644
index 11d3b572b1b3..000000000000
--- a/arch/mips/include/asm/mach-bcm63xx/dma-coherence.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef __ASM_MACH_BCM63XX_DMA_COHERENCE_H
-#define __ASM_MACH_BCM63XX_DMA_COHERENCE_H
-
-#include <asm/bmips.h>
-
-#define plat_post_dma_flush	bmips_post_dma_flush
-
-#include <asm/mach-generic/dma-coherence.h>
-
-#endif /* __ASM_MACH_BCM63XX_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 9d8106758142..ae8569475264 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -182,8 +182,39 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
 		 * Make sure the buddy is global too (if it's !none,
 		 * it better already be global)
 		 */
+#ifdef CONFIG_SMP
+		/*
+		 * For SMP, multiple CPUs can race, so we need to do
+		 * this atomically.
+		 */
+#ifdef CONFIG_64BIT
+#define LL_INSN "lld"
+#define SC_INSN "scd"
+#else /* CONFIG_32BIT */
+#define LL_INSN "ll"
+#define SC_INSN "sc"
+#endif
+		unsigned long page_global = _PAGE_GLOBAL;
+		unsigned long tmp;
+
+		__asm__ __volatile__ (
+			"	.set	push\n"
+			"	.set	noreorder\n"
+			"1:	" LL_INSN "	%[tmp], %[buddy]\n"
+			"	bnez	%[tmp], 2f\n"
+			"	 or	%[tmp], %[tmp], %[global]\n"
+			"	" SC_INSN "	%[tmp], %[buddy]\n"
+			"	beqz	%[tmp], 1b\n"
+			"	 nop\n"
+			"2:\n"
+			"	.set pop"
+			: [buddy] "+m" (buddy->pte),
+			  [tmp] "=&r" (tmp)
+			: [global] "r" (page_global));
+#else /* !CONFIG_SMP */
 		if (pte_none(*buddy))
 			pte_val(*buddy) = pte_val(*buddy) | _PAGE_GLOBAL;
+#endif /* CONFIG_SMP */
 	}
 #endif
 }
diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h
index 16f1ea9ab191..03722d4326a1 100644
--- a/arch/mips/include/asm/smp.h
+++ b/arch/mips/include/asm/smp.h
@@ -83,8 +83,6 @@ static inline void __cpu_die(unsigned int cpu)
 extern void play_dead(void);
 #endif
 
-extern asmlinkage void smp_call_function_interrupt(void);
-
 static inline void arch_send_call_function_single_ipi(int cpu)
 {
 	extern struct plat_smp_ops *mp_ops;	/* private */
diff --git a/arch/mips/include/asm/stackframe.h b/arch/mips/include/asm/stackframe.h
index 28d6d9364bd1..a71da576883c 100644
--- a/arch/mips/include/asm/stackframe.h
+++ b/arch/mips/include/asm/stackframe.h
@@ -152,6 +152,31 @@
 		.set	noreorder
 		bltz	k0, 8f
 		 move	k1, sp
+#ifdef CONFIG_EVA
+		/*
+		 * Flush interAptiv's Return Prediction Stack (RPS) by writing
+		 * EntryHi. Toggling Config7.RPS is slower and less portable.
+		 *
+		 * The RPS isn't automatically flushed when exceptions are
+		 * taken, which can result in kernel mode speculative accesses
+		 * to user addresses if the RPS mispredicts. That's harmless
+		 * when user and kernel share the same address space, but with
+		 * EVA the same user segments may be unmapped to kernel mode,
+		 * even containing sensitive MMIO regions or invalid memory.
+		 *
+		 * This can happen when the kernel sets the return address to
+		 * ret_from_* and jr's to the exception handler, which looks
+		 * more like a tail call than a function call. If nested calls
+		 * don't evict the last user address in the RPS, it will
+		 * mispredict the return and fetch from a user controlled
+		 * address into the icache.
+		 *
+		 * More recent EVA-capable cores with MAAR to restrict
+		 * speculative accesses aren't affected.
+		 */
+		MFC0	k0, CP0_ENTRYHI
+		MTC0	k0, CP0_ENTRYHI
+#endif
 		.set	reorder
 		/* Called from user mode, new stack. */
 		get_saved_sp
diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c
index 3e4491aa6d6b..789d7bf4fef3 100644
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -154,7 +154,7 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len,
 				      unsigned long __user *user_mask_ptr)
 {
 	unsigned int real_len;
-	cpumask_t mask;
+	cpumask_t allowed, mask;
 	int retval;
 	struct task_struct *p;
 
@@ -173,7 +173,8 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len,
 	if (retval)
 		goto out_unlock;
 
-	cpumask_and(&mask, &p->thread.user_cpus_allowed, cpu_possible_mask);
+	cpumask_or(&allowed, &p->thread.user_cpus_allowed, &p->cpus_allowed);
+	cpumask_and(&mask, &allowed, cpu_active_mask);
 
 out_unlock:
 	read_unlock(&tasklist_lock);
diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c
index b130033838ba..5fcec3032f38 100644
--- a/arch/mips/kernel/prom.c
+++ b/arch/mips/kernel/prom.c
@@ -38,7 +38,7 @@ char *mips_get_machine_name(void)
 	return mips_machine_name;
 }
 
-#ifdef CONFIG_OF
+#ifdef CONFIG_USE_OF
 void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 {
 	return add_memory_region(base, size, BOOT_MEM_RAM);
diff --git a/arch/mips/kernel/relocate_kernel.S b/arch/mips/kernel/relocate_kernel.S
index 74bab9ddd0e1..c6bbf2165051 100644
--- a/arch/mips/kernel/relocate_kernel.S
+++ b/arch/mips/kernel/relocate_kernel.S
@@ -24,7 +24,7 @@ LEAF(relocate_new_kernel)
 
 process_entry:
 	PTR_L		s2, (s0)
-	PTR_ADD		s0, s0, SZREG
+	PTR_ADDIU	s0, s0, SZREG
 
 	/*
 	 * In case of a kdump/crash kernel, the indirection page is not
@@ -61,9 +61,9 @@ copy_word:
 	/* copy page word by word */
 	REG_L		s5, (s2)
 	REG_S		s5, (s4)
-	PTR_ADD		s4, s4, SZREG
-	PTR_ADD		s2, s2, SZREG
-	LONG_SUB	s6, s6, 1
+	PTR_ADDIU	s4, s4, SZREG
+	PTR_ADDIU	s2, s2, SZREG
+	LONG_ADDIU	s6, s6, -1
 	beq		s6, zero, process_entry
 	b		copy_word
 	b		process_entry
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index 19a7705f2a01..5d7f2634996f 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -409,8 +409,6 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 
 int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 {
-	memset(to, 0, sizeof *to);
-
 	if (copy_from_user(to, from, 3*sizeof(int)) ||
 	    copy_from_user(to->_sifields._pad,
 			   from->_sifields._pad, SI_PAD_SIZE32))
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index 336708ae5c5b..78cf8c2f1de0 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -284,7 +284,7 @@ static irqreturn_t bmips5000_ipi_interrupt(int irq, void *dev_id)
 	if (action == 0)
 		scheduler_ipi();
 	else
-		smp_call_function_interrupt();
+		generic_smp_call_function_interrupt();
 
 	return IRQ_HANDLED;
 }
@@ -336,7 +336,7 @@ static irqreturn_t bmips43xx_ipi_interrupt(int irq, void *dev_id)
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+		generic_smp_call_function_interrupt();
 
 	return IRQ_HANDLED;
 }
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index d0744cc77ea7..a31896c33716 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -192,16 +192,6 @@ asmlinkage void start_secondary(void)
 	cpu_startup_entry(CPUHP_ONLINE);
 }
 
-/*
- * Call into both interrupt handlers, as we share the IPI for them
- */
-void __irq_entry smp_call_function_interrupt(void)
-{
-	irq_enter();
-	generic_smp_call_function_interrupt();
-	irq_exit();
-}
-
 static void stop_this_cpu(void *dummy)
 {
 	/*
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index e207a43b5f8f..8ea28e6ab37d 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -192,6 +192,7 @@ static void show_stacktrace(struct task_struct *task,
 void show_stack(struct task_struct *task, unsigned long *sp)
 {
 	struct pt_regs regs;
+	mm_segment_t old_fs = get_fs();
 	if (sp) {
 		regs.regs[29] = (unsigned long)sp;
 		regs.regs[31] = 0;
@@ -210,7 +211,13 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 			prepare_frametrace(&regs);
 		}
 	}
+	/*
+	 * show_stack() deals exclusively with kernel mode, so be sure to access
+	 * the stack in the kernel (not user) address space.
+	 */
+	set_fs(KERNEL_DS);
 	show_stacktrace(task, &regs);
+	set_fs(old_fs);
 }
 
 static void show_code(unsigned int __user *pc)
@@ -1519,6 +1526,7 @@ asmlinkage void do_mcheck(struct pt_regs *regs)
 	const int field = 2 * sizeof(unsigned long);
 	int multi_match = regs->cp0_status & ST0_TS;
 	enum ctx_state prev_state;
+	mm_segment_t old_fs = get_fs();
 
 	prev_state = exception_enter();
 	show_regs(regs);
@@ -1540,8 +1548,13 @@ asmlinkage void do_mcheck(struct pt_regs *regs)
 		dump_tlb_all();
 	}
 
+	if (!user_mode(regs))
+		set_fs(KERNEL_DS);
+
 	show_code((unsigned int __user *) regs->cp0_epc);
 
+	set_fs(old_fs);
+
 	/*
 	 * Some chips may have other causes of machine check (e.g. SB1
 	 * graduation timer)
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index af84bef0c90d..eb3efd137fd1 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -438,7 +438,7 @@ do {                                                        \
 		: "memory");                                \
 } while(0)
 
-#define     StoreDW(addr, value, res) \
+#define     _StoreDW(addr, value, res) \
 do {                                                        \
 		__asm__ __volatile__ (                      \
 			".set\tpush\n\t"		    \
diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c
index 6ab10573490d..2c218c3bbca5 100644
--- a/arch/mips/lantiq/irq.c
+++ b/arch/mips/lantiq/irq.c
@@ -293,7 +293,7 @@ static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
 
 static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
 {
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 	return IRQ_HANDLED;
 }
 
@@ -466,6 +466,7 @@ int get_c0_perfcount_int(void)
 {
 	return ltq_perfcount_irq;
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {
diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c
index 509877c6e9d9..1a4738a8f2d3 100644
--- a/arch/mips/loongson64/loongson-3/smp.c
+++ b/arch/mips/loongson64/loongson-3/smp.c
@@ -266,8 +266,11 @@ void loongson3_ipi_interrupt(struct pt_regs *regs)
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 
-	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+	if (action & SMP_CALL_FUNCTION) {
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
+	}
 
 	if (action & SMP_ASK_C0COUNT) {
 		BUG_ON(cpu != 0);
diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index 77d96db8253c..aab218c36e0d 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -160,18 +160,18 @@ static inline void setup_protection_map(void)
 		protection_map[1]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC);
 		protection_map[2]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
 		protection_map[3]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC);
-		protection_map[4]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_READ);
+		protection_map[4]  = __pgprot(_page_cachable_default | _PAGE_PRESENT);
 		protection_map[5]  = __pgprot(_page_cachable_default | _PAGE_PRESENT);
-		protection_map[6]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_READ);
+		protection_map[6]  = __pgprot(_page_cachable_default | _PAGE_PRESENT);
 		protection_map[7]  = __pgprot(_page_cachable_default | _PAGE_PRESENT);
 
 		protection_map[8]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
 		protection_map[9]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC);
 		protection_map[10] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE | _PAGE_NO_READ);
 		protection_map[11] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE);
-		protection_map[12] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_READ);
+		protection_map[12] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
 		protection_map[13] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
-		protection_map[14] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_WRITE  | _PAGE_NO_READ);
+		protection_map[14] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_WRITE);
 		protection_map[15] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_WRITE);
 
 	} else {
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 36c0f26fac6b..852a41c6da45 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -133,7 +133,8 @@ good_area:
 #endif
 				goto bad_area;
 			}
-			if (!(vma->vm_flags & VM_READ)) {
+			if (!(vma->vm_flags & VM_READ) &&
+			    exception_epc(regs) != address) {
 #if 0
 				pr_notice("Cpu%d[%s:%d:%0*lx:%ld:%0*lx] RI violation\n",
 					  raw_smp_processor_id(),
diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c
index d1392f8f5811..fa8f591f3713 100644
--- a/arch/mips/mti-malta/malta-int.c
+++ b/arch/mips/mti-malta/malta-int.c
@@ -222,7 +222,7 @@ static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
 
 static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
 {
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 
 	return IRQ_HANDLED;
 }
diff --git a/arch/mips/mti-malta/malta-time.c b/arch/mips/mti-malta/malta-time.c
index 5625b190edc0..b7bf721eabf5 100644
--- a/arch/mips/mti-malta/malta-time.c
+++ b/arch/mips/mti-malta/malta-time.c
@@ -154,6 +154,7 @@ int get_c0_perfcount_int(void)
 
 	return mips_cpu_perf_irq;
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {
@@ -171,14 +172,17 @@ unsigned int get_c0_compare_int(void)
 
 static void __init init_rtc(void)
 {
-	/* stop the clock whilst setting it up */
-	CMOS_WRITE(RTC_SET | RTC_24H, RTC_CONTROL);
+	unsigned char freq, ctrl;
 
-	/* 32KHz time base */
-	CMOS_WRITE(RTC_REF_CLCK_32KHZ, RTC_FREQ_SELECT);
+	/* Set 32KHz time base if not already set */
+	freq = CMOS_READ(RTC_FREQ_SELECT);
+	if ((freq & RTC_DIV_CTL) != RTC_REF_CLCK_32KHZ)
+		CMOS_WRITE(RTC_REF_CLCK_32KHZ, RTC_FREQ_SELECT);
 
-	/* start the clock */
-	CMOS_WRITE(RTC_24H, RTC_CONTROL);
+	/* Ensure SET bit is clear so RTC can run */
+	ctrl = CMOS_READ(RTC_CONTROL);
+	if (ctrl & RTC_SET)
+		CMOS_WRITE(ctrl & ~RTC_SET, RTC_CONTROL);
 }
 
 void __init plat_time_init(void)
diff --git a/arch/mips/mti-sead3/sead3-time.c b/arch/mips/mti-sead3/sead3-time.c
index e1d69895fb1d..a120b7a5a8fe 100644
--- a/arch/mips/mti-sead3/sead3-time.c
+++ b/arch/mips/mti-sead3/sead3-time.c
@@ -77,6 +77,7 @@ int get_c0_perfcount_int(void)
 		return MIPS_CPU_IRQ_BASE + cp0_perfcount_irq;
 	return -1;
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {
diff --git a/arch/mips/netlogic/common/smp.c b/arch/mips/netlogic/common/smp.c
index dc3e327fbbac..f5fff228b347 100644
--- a/arch/mips/netlogic/common/smp.c
+++ b/arch/mips/netlogic/common/smp.c
@@ -86,7 +86,7 @@ void nlm_smp_function_ipi_handler(unsigned int irq, struct irq_desc *desc)
 {
 	clear_c0_eimr(irq);
 	ack_c0_eirr(irq);
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 	set_c0_eimr(irq);
 }
 
diff --git a/arch/mips/paravirt/paravirt-smp.c b/arch/mips/paravirt/paravirt-smp.c
index 42181c7105df..f8d3e081b2eb 100644
--- a/arch/mips/paravirt/paravirt-smp.c
+++ b/arch/mips/paravirt/paravirt-smp.c
@@ -114,7 +114,7 @@ static irqreturn_t paravirt_reched_interrupt(int irq, void *dev_id)
 
 static irqreturn_t paravirt_function_interrupt(int irq, void *dev_id)
 {
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 	return IRQ_HANDLED;
 }
 
diff --git a/arch/mips/pistachio/time.c b/arch/mips/pistachio/time.c
index 7c73fcb92a10..8a377346f0ca 100644
--- a/arch/mips/pistachio/time.c
+++ b/arch/mips/pistachio/time.c
@@ -26,6 +26,7 @@ int get_c0_perfcount_int(void)
 {
 	return gic_get_c0_perfcount_int();
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 int get_c0_fdc_int(void)
 {
diff --git a/arch/mips/pmcs-msp71xx/msp_smp.c b/arch/mips/pmcs-msp71xx/msp_smp.c
index 10170580a2de..ffa0f7101a97 100644
--- a/arch/mips/pmcs-msp71xx/msp_smp.c
+++ b/arch/mips/pmcs-msp71xx/msp_smp.c
@@ -44,7 +44,7 @@ static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
 
 static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
 {
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 
 	return IRQ_HANDLED;
 }
diff --git a/arch/mips/ralink/irq.c b/arch/mips/ralink/irq.c
index 53707aacc0f8..8c624a8b9ea2 100644
--- a/arch/mips/ralink/irq.c
+++ b/arch/mips/ralink/irq.c
@@ -89,6 +89,7 @@ int get_c0_perfcount_int(void)
 {
 	return rt_perfcount_irq;
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {
diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c
index 3fbaef97a1b8..16ec4e12daa3 100644
--- a/arch/mips/sgi-ip27/ip27-irq.c
+++ b/arch/mips/sgi-ip27/ip27-irq.c
@@ -107,10 +107,14 @@ static void ip27_do_irq_mask0(void)
 		scheduler_ipi();
 	} else if (pend0 & (1UL << CPU_CALL_A_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_CALL_A_IRQ);
-		smp_call_function_interrupt();
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
 	} else if (pend0 & (1UL << CPU_CALL_B_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_CALL_B_IRQ);
-		smp_call_function_interrupt();
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
 	} else
 #endif
 	{
diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c
index af7d44edd9a8..4c71aea25663 100644
--- a/arch/mips/sibyte/bcm1480/smp.c
+++ b/arch/mips/sibyte/bcm1480/smp.c
@@ -29,8 +29,6 @@
 #include <asm/sibyte/bcm1480_regs.h>
 #include <asm/sibyte/bcm1480_int.h>
 
-extern void smp_call_function_interrupt(void);
-
 /*
  * These are routines for dealing with the bcm1480 smp capabilities
  * independent of board/firmware
@@ -184,6 +182,9 @@ void bcm1480_mailbox_interrupt(void)
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 
-	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+	if (action & SMP_CALL_FUNCTION) {
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
+	}
 }
diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c
index c0c4b3f88a08..1cf66f5ff23d 100644
--- a/arch/mips/sibyte/sb1250/smp.c
+++ b/arch/mips/sibyte/sb1250/smp.c
@@ -172,6 +172,9 @@ void sb1250_mailbox_interrupt(void)
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 
-	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+	if (action & SMP_CALL_FUNCTION) {
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
+	}
 }
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index d3a831ac0f92..da50e0c9c57e 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -966,8 +966,6 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *d, const siginfo_t *s)
 
 int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from)
 {
-	memset(to, 0, sizeof *to);
-
 	if (copy_from_user(to, from, 3*sizeof(int)) ||
 	    copy_from_user(to->_sifields._pad,
 			   from->_sifields._pad, SI_PAD_SIZE32))
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 5cf5e6ea213b..7cf0df859d05 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -1478,7 +1478,7 @@ static int pnv_eeh_next_error(struct eeh_pe **pe)
 	}
 
 	/* Unmask the event */
-	if (eeh_enabled())
+	if (ret == EEH_NEXT_ERR_NONE && eeh_enabled())
 		enable_irq(eeh_event_irq);
 
 	return ret;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 5738d315248b..85cbc96eff6c 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -2220,7 +2220,7 @@ static void pnv_pci_ioda_setup_opal_tce_kill(struct pnv_phb *phb)
 
 static __be64 *pnv_pci_ioda2_table_do_alloc_pages(int nid, unsigned shift,
 		unsigned levels, unsigned long limit,
-		unsigned long *current_offset)
+		unsigned long *current_offset, unsigned long *total_allocated)
 {
 	struct page *tce_mem = NULL;
 	__be64 *addr, *tmp;
@@ -2236,6 +2236,7 @@ static __be64 *pnv_pci_ioda2_table_do_alloc_pages(int nid, unsigned shift,
 	}
 	addr = page_address(tce_mem);
 	memset(addr, 0, allocated);
+	*total_allocated += allocated;
 
 	--levels;
 	if (!levels) {
@@ -2245,7 +2246,7 @@ static __be64 *pnv_pci_ioda2_table_do_alloc_pages(int nid, unsigned shift,
 
 	for (i = 0; i < entries; ++i) {
 		tmp = pnv_pci_ioda2_table_do_alloc_pages(nid, shift,
-				levels, limit, current_offset);
+				levels, limit, current_offset, total_allocated);
 		if (!tmp)
 			break;
 
@@ -2267,7 +2268,7 @@ static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
 		struct iommu_table *tbl)
 {
 	void *addr;
-	unsigned long offset = 0, level_shift;
+	unsigned long offset = 0, level_shift, total_allocated = 0;
 	const unsigned window_shift = ilog2(window_size);
 	unsigned entries_shift = window_shift - page_shift;
 	unsigned table_shift = max_t(unsigned, entries_shift + 3, PAGE_SHIFT);
@@ -2286,7 +2287,7 @@ static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
 
 	/* Allocate TCE table */
 	addr = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift,
-			levels, tce_table_size, &offset);
+			levels, tce_table_size, &offset, &total_allocated);
 
 	/* addr==NULL means that the first level allocation failed */
 	if (!addr)
@@ -2308,7 +2309,7 @@ static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
 			page_shift);
 	tbl->it_level_size = 1ULL << (level_shift - 3);
 	tbl->it_indirect_levels = levels - 1;
-	tbl->it_allocated_size = offset;
+	tbl->it_allocated_size = total_allocated;
 
 	pr_devel("Created TCE table: ws=%08llx ts=%lx @%08llx\n",
 			window_size, tce_table_size, bus_offset);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 2078f92d15ac..f32f843a3631 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1742,10 +1742,10 @@ static bool ibs_enabled(struct kvm_vcpu *vcpu)
 
 static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->requests)
-		return 0;
 retry:
 	kvm_s390_vcpu_request_handled(vcpu);
+	if (!vcpu->requests)
+		return 0;
 	/*
 	 * We use MMU_RELOAD just to re-arm the ipte notifier for the
 	 * guest prefix page. gmap_ipte_notify will wait on the ptl lock.
diff --git a/arch/sparc/include/asm/visasm.h b/arch/sparc/include/asm/visasm.h
index 1f0aa2024e94..6424249d5f78 100644
--- a/arch/sparc/include/asm/visasm.h
+++ b/arch/sparc/include/asm/visasm.h
@@ -28,16 +28,10 @@
  * Must preserve %o5 between VISEntryHalf and VISExitHalf */
 
 #define VISEntryHalf					\
-	rd		%fprs, %o5;			\
-	andcc		%o5, FPRS_FEF, %g0;		\
-	be,pt		%icc, 297f;			\
-	 sethi		%hi(298f), %g7;			\
-	sethi		%hi(VISenterhalf), %g1;		\
-	jmpl		%g1 + %lo(VISenterhalf), %g0;	\
-	 or		%g7, %lo(298f), %g7;		\
-	clr		%o5;				\
-297:	wr		%o5, FPRS_FEF, %fprs;		\
-298:
+	VISEntry
+
+#define VISExitHalf					\
+	VISExit
 
 #define VISEntryHalfFast(fail_label)			\
 	rd		%fprs, %o5;			\
@@ -47,7 +41,7 @@
 	ba,a,pt		%xcc, fail_label;		\
 297:	wr		%o5, FPRS_FEF, %fprs;
 
-#define VISExitHalf					\
+#define VISExitHalfFast					\
 	wr		%o5, 0, %fprs;
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S
index 140527a20e7d..83aeeb1dffdb 100644
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -240,8 +240,11 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	add		%o0, 0x40, %o0
 	bne,pt		%icc, 1b
 	 LOAD(prefetch, %g1 + 0x200, #n_reads_strong)
+#ifdef NON_USER_COPY
+	VISExitHalfFast
+#else
 	VISExitHalf
-
+#endif
 	brz,pn		%o2, .Lexit
 	 cmp		%o2, 19
 	ble,pn		%icc, .Lsmall_unaligned
diff --git a/arch/sparc/lib/VISsave.S b/arch/sparc/lib/VISsave.S
index b320ae9e2e2e..a063d84336d6 100644
--- a/arch/sparc/lib/VISsave.S
+++ b/arch/sparc/lib/VISsave.S
@@ -44,9 +44,8 @@ vis1:	ldub		[%g6 + TI_FPSAVED], %g3
 
 	 stx		%g3, [%g6 + TI_GSR]
 2:	add		%g6, %g1, %g3
-	cmp		%o5, FPRS_DU
-	be,pn		%icc, 6f
-	 sll		%g1, 3, %g1
+	mov		FPRS_DU | FPRS_DL | FPRS_FEF, %o5
+	sll		%g1, 3, %g1
 	stb		%o5, [%g3 + TI_FPSAVED]
 	rd		%gsr, %g2
 	add		%g6, %g1, %g3
@@ -80,65 +79,3 @@ vis1:	ldub		[%g6 + TI_FPSAVED], %g3
 	.align		32
 80:	jmpl		%g7 + %g0, %g0
 	 nop
-
-6:	ldub		[%g3 + TI_FPSAVED], %o5
-	or		%o5, FPRS_DU, %o5
-	add		%g6, TI_FPREGS+0x80, %g2
-	stb		%o5, [%g3 + TI_FPSAVED]
-
-	sll		%g1, 5, %g1
-	add		%g6, TI_FPREGS+0xc0, %g3
-	wr		%g0, FPRS_FEF, %fprs
-	membar		#Sync
-	stda		%f32, [%g2 + %g1] ASI_BLK_P
-	stda		%f48, [%g3 + %g1] ASI_BLK_P
-	membar		#Sync
-	ba,pt		%xcc, 80f
-	 nop
-
-	.align		32
-80:	jmpl		%g7 + %g0, %g0
-	 nop
-
-	.align		32
-VISenterhalf:
-	ldub		[%g6 + TI_FPDEPTH], %g1
-	brnz,a,pn	%g1, 1f
-	 cmp		%g1, 1
-	stb		%g0, [%g6 + TI_FPSAVED]
-	stx		%fsr, [%g6 + TI_XFSR]
-	clr		%o5
-	jmpl		%g7 + %g0, %g0
-	 wr		%g0, FPRS_FEF, %fprs
-
-1:	bne,pn		%icc, 2f
-	 srl		%g1, 1, %g1
-	ba,pt		%xcc, vis1
-	 sub		%g7, 8, %g7
-2:	addcc		%g6, %g1, %g3
-	sll		%g1, 3, %g1
-	andn		%o5, FPRS_DU, %g2
-	stb		%g2, [%g3 + TI_FPSAVED]
-
-	rd		%gsr, %g2
-	add		%g6, %g1, %g3
-	stx		%g2, [%g3 + TI_GSR]
-	add		%g6, %g1, %g2
-	stx		%fsr, [%g2 + TI_XFSR]
-	sll		%g1, 5, %g1
-3:	andcc		%o5, FPRS_DL, %g0
-	be,pn		%icc, 4f
-	 add		%g6, TI_FPREGS, %g2
-
-	add		%g6, TI_FPREGS+0x40, %g3
-	membar		#Sync
-	stda		%f0, [%g2 + %g1] ASI_BLK_P
-	stda		%f16, [%g3 + %g1] ASI_BLK_P
-	membar		#Sync
-	ba,pt		%xcc, 4f
-	 nop
-
-	.align		32
-4:	and		%o5, FPRS_DU, %o5
-	jmpl		%g7 + %g0, %g0
-	 wr		%o5, FPRS_FEF, %fprs
diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c
index 1d649a95660c..8069ce12f20b 100644
--- a/arch/sparc/lib/ksyms.c
+++ b/arch/sparc/lib/ksyms.c
@@ -135,10 +135,6 @@ EXPORT_SYMBOL(copy_user_page);
 void VISenter(void);
 EXPORT_SYMBOL(VISenter);
 
-/* CRYPTO code needs this */
-void VISenterhalf(void);
-EXPORT_SYMBOL(VISenterhalf);
-
 extern void xor_vis_2(unsigned long, unsigned long *, unsigned long *);
 extern void xor_vis_3(unsigned long, unsigned long *, unsigned long *,
 		unsigned long *);
diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c
index e8c2c04143cd..c667e104a0c2 100644
--- a/arch/tile/kernel/compat_signal.c
+++ b/arch/tile/kernel/compat_signal.c
@@ -113,8 +113,6 @@ int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from)
 	if (!access_ok(VERIFY_READ, from, sizeof(struct compat_siginfo)))
 		return -EFAULT;
 
-	memset(to, 0, sizeof(*to));
-
 	err = __get_user(to->si_signo, &from->si_signo);
 	err |= __get_user(to->si_errno, &from->si_errno);
 	err |= __get_user(to->si_code, &from->si_code);
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 2c82bd150d43..7d69afd8b6fa 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -1193,6 +1193,10 @@ static efi_status_t setup_e820(struct boot_params *params,
 		unsigned int e820_type = 0;
 		unsigned long m = efi->efi_memmap;
 
+#ifdef CONFIG_X86_64
+		m |= (u64)efi->efi_memmap_hi << 32;
+#endif
+
 		d = (efi_memory_desc_t *)(m + (i * efi->efi_memdesc_size));
 		switch (d->type) {
 		case EFI_RESERVED_TYPE:
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index a0bf89fd2647..4e10d73cf018 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -280,21 +280,6 @@ static inline void clear_LDT(void)
 	set_ldt(NULL, 0);
 }
 
-/*
- * load one particular LDT into the current CPU
- */
-static inline void load_LDT_nolock(mm_context_t *pc)
-{
-	set_ldt(pc->ldt, pc->size);
-}
-
-static inline void load_LDT(mm_context_t *pc)
-{
-	preempt_disable();
-	load_LDT_nolock(pc);
-	preempt_enable();
-}
-
 static inline unsigned long get_desc_base(const struct desc_struct *desc)
 {
 	return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24));
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 09b9620a73b4..364d27481a52 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -9,8 +9,7 @@
  * we put the segment information here.
  */
 typedef struct {
-	void *ldt;
-	int size;
+	struct ldt_struct *ldt;
 
 #ifdef CONFIG_X86_64
 	/* True if mm supports a task running in 32 bit compatibility mode. */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 804a3a6030ca..984abfe47edc 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -34,6 +34,50 @@ static inline void load_mm_cr4(struct mm_struct *mm) {}
 #endif
 
 /*
+ * ldt_structs can be allocated, used, and freed, but they are never
+ * modified while live.
+ */
+struct ldt_struct {
+	/*
+	 * Xen requires page-aligned LDTs with special permissions.  This is
+	 * needed to prevent us from installing evil descriptors such as
+	 * call gates.  On native, we could merge the ldt_struct and LDT
+	 * allocations, but it's not worth trying to optimize.
+	 */
+	struct desc_struct *entries;
+	int size;
+};
+
+static inline void load_mm_ldt(struct mm_struct *mm)
+{
+	struct ldt_struct *ldt;
+
+	/* lockless_dereference synchronizes with smp_store_release */
+	ldt = lockless_dereference(mm->context.ldt);
+
+	/*
+	 * Any change to mm->context.ldt is followed by an IPI to all
+	 * CPUs with the mm active.  The LDT will not be freed until
+	 * after the IPI is handled by all such CPUs.  This means that,
+	 * if the ldt_struct changes before we return, the values we see
+	 * will be safe, and the new values will be loaded before we run
+	 * any user code.
+	 *
+	 * NB: don't try to convert this to use RCU without extreme care.
+	 * We would still need IRQs off, because we don't want to change
+	 * the local LDT after an IPI loaded a newer value than the one
+	 * that we can see.
+	 */
+
+	if (unlikely(ldt))
+		set_ldt(ldt->entries, ldt->size);
+	else
+		clear_LDT();
+
+	DEBUG_LOCKS_WARN_ON(preemptible());
+}
+
+/*
  * Used for LDT copy/destruction.
  */
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
@@ -78,12 +122,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		 * was called and then modify_ldt changed
 		 * prev->context.ldt but suppressed an IPI to this CPU.
 		 * In this case, prev->context.ldt != NULL, because we
-		 * never free an LDT while the mm still exists.  That
-		 * means that next->context.ldt != prev->context.ldt,
-		 * because mms never share an LDT.
+		 * never set context.ldt to NULL while the mm still
+		 * exists.  That means that next->context.ldt !=
+		 * prev->context.ldt, because mms never share an LDT.
 		 */
 		if (unlikely(prev->context.ldt != next->context.ldt))
-			load_LDT_nolock(&next->context);
+			load_mm_ldt(next);
 	}
 #ifdef CONFIG_SMP
 	  else {
@@ -106,7 +150,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 			load_cr3(next->pgd);
 			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 			load_mm_cr4(next);
-			load_LDT_nolock(&next->context);
+			load_mm_ldt(next);
 		}
 	}
 #endif
diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h
index 6fe6b182c998..9dfce4e0417d 100644
--- a/arch/x86/include/asm/sigcontext.h
+++ b/arch/x86/include/asm/sigcontext.h
@@ -57,9 +57,9 @@ struct sigcontext {
 	unsigned long ip;
 	unsigned long flags;
 	unsigned short cs;
-	unsigned short __pad2;	/* Was called gs, but was always zero. */
-	unsigned short __pad1;	/* Was called fs, but was always zero. */
-	unsigned short ss;
+	unsigned short gs;
+	unsigned short fs;
+	unsigned short __pad0;
 	unsigned long err;
 	unsigned long trapno;
 	unsigned long oldmask;
diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h
index 0e8a973de9ee..40836a9a7250 100644
--- a/arch/x86/include/uapi/asm/sigcontext.h
+++ b/arch/x86/include/uapi/asm/sigcontext.h
@@ -177,24 +177,9 @@ struct sigcontext {
 	__u64 rip;
 	__u64 eflags;		/* RFLAGS */
 	__u16 cs;
-
-	/*
-	 * Prior to 2.5.64 ("[PATCH] x86-64 updates for 2.5.64-bk3"),
-	 * Linux saved and restored fs and gs in these slots.  This
-	 * was counterproductive, as fsbase and gsbase were never
-	 * saved, so arch_prctl was presumably unreliable.
-	 *
-	 * If these slots are ever needed for any other purpose, there
-	 * is some risk that very old 64-bit binaries could get
-	 * confused.  I doubt that many such binaries still work,
-	 * though, since the same patch in 2.5.64 also removed the
-	 * 64-bit set_thread_area syscall, so it appears that there is
-	 * no TLS API that works in both pre- and post-2.5.64 kernels.
-	 */
-	__u16 __pad2;		/* Was gs. */
-	__u16 __pad1;		/* Was fs. */
-
-	__u16 ss;
+	__u16 gs;
+	__u16 fs;
+	__u16 __pad0;
 	__u64 err;
 	__u64 trapno;
 	__u64 oldmask;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 845dc0df2002..206052e55517 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -943,7 +943,7 @@ static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info)
 	 */
 	if (irq < nr_legacy_irqs() && data->count == 1) {
 		if (info->ioapic_trigger != data->trigger)
-			mp_register_handler(irq, data->trigger);
+			mp_register_handler(irq, info->ioapic_trigger);
 		data->entry.trigger = data->trigger = info->ioapic_trigger;
 		data->entry.polarity = data->polarity = info->ioapic_polarity;
 	}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 922c5e0cea4c..cb9e5df42dd2 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1410,7 +1410,7 @@ void cpu_init(void)
 	load_sp0(t, &current->thread);
 	set_tss_desc(cpu, t);
 	load_TR_desc();
-	load_LDT(&init_mm.context);
+	load_mm_ldt(&init_mm);
 
 	clear_all_debug_regs();
 	dbg_restore_debug_regs();
@@ -1459,7 +1459,7 @@ void cpu_init(void)
 	load_sp0(t, thread);
 	set_tss_desc(cpu, t);
 	load_TR_desc();
-	load_LDT(&init_mm.context);
+	load_mm_ldt(&init_mm);
 
 	t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 3658de47900f..9469dfa55607 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -2179,21 +2179,25 @@ static unsigned long get_segment_base(unsigned int segment)
 	int idx = segment >> 3;
 
 	if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) {
+		struct ldt_struct *ldt;
+
 		if (idx > LDT_ENTRIES)
 			return 0;
 
-		if (idx > current->active_mm->context.size)
+		/* IRQs are off, so this synchronizes with smp_store_release */
+		ldt = lockless_dereference(current->active_mm->context.ldt);
+		if (!ldt || idx > ldt->size)
 			return 0;
 
-		desc = current->active_mm->context.ldt;
+		desc = &ldt->entries[idx];
 	} else {
 		if (idx > GDT_ENTRIES)
 			return 0;
 
-		desc = raw_cpu_ptr(gdt_page.gdt);
+		desc = raw_cpu_ptr(gdt_page.gdt) + idx;
 	}
 
-	return get_desc_base(desc + idx);
+	return get_desc_base(desc);
 }
 
 #ifdef CONFIG_COMPAT
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index c37886d759cc..2bcc0525f1c1 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -12,6 +12,7 @@
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
+#include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
 
@@ -20,82 +21,82 @@
 #include <asm/mmu_context.h>
 #include <asm/syscalls.h>
 
-#ifdef CONFIG_SMP
+/* context.lock is held for us, so we don't need any locking. */
 static void flush_ldt(void *current_mm)
 {
-	if (current->active_mm == current_mm)
-		load_LDT(&current->active_mm->context);
+	mm_context_t *pc;
+
+	if (current->active_mm != current_mm)
+		return;
+
+	pc = &current->active_mm->context;
+	set_ldt(pc->ldt->entries, pc->ldt->size);
 }
-#endif
 
-static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
+/* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */
+static struct ldt_struct *alloc_ldt_struct(int size)
 {
-	void *oldldt, *newldt;
-	int oldsize;
-
-	if (mincount <= pc->size)
-		return 0;
-	oldsize = pc->size;
-	mincount = (mincount + (PAGE_SIZE / LDT_ENTRY_SIZE - 1)) &
-			(~(PAGE_SIZE / LDT_ENTRY_SIZE - 1));
-	if (mincount * LDT_ENTRY_SIZE > PAGE_SIZE)
-		newldt = vmalloc(mincount * LDT_ENTRY_SIZE);
+	struct ldt_struct *new_ldt;
+	int alloc_size;
+
+	if (size > LDT_ENTRIES)
+		return NULL;
+
+	new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL);
+	if (!new_ldt)
+		return NULL;
+
+	BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct));
+	alloc_size = size * LDT_ENTRY_SIZE;
+
+	/*
+	 * Xen is very picky: it requires a page-aligned LDT that has no
+	 * trailing nonzero bytes in any page that contains LDT descriptors.
+	 * Keep it simple: zero the whole allocation and never allocate less
+	 * than PAGE_SIZE.
+	 */
+	if (alloc_size > PAGE_SIZE)
+		new_ldt->entries = vzalloc(alloc_size);
 	else
-		newldt = (void *)__get_free_page(GFP_KERNEL);
-
-	if (!newldt)
-		return -ENOMEM;
+		new_ldt->entries = kzalloc(PAGE_SIZE, GFP_KERNEL);
 
-	if (oldsize)
-		memcpy(newldt, pc->ldt, oldsize * LDT_ENTRY_SIZE);
-	oldldt = pc->ldt;
-	memset(newldt + oldsize * LDT_ENTRY_SIZE, 0,
-	       (mincount - oldsize) * LDT_ENTRY_SIZE);
+	if (!new_ldt->entries) {
+		kfree(new_ldt);
+		return NULL;
+	}
 
-	paravirt_alloc_ldt(newldt, mincount);
+	new_ldt->size = size;
+	return new_ldt;
+}
 
-#ifdef CONFIG_X86_64
-	/* CHECKME: Do we really need this ? */
-	wmb();
-#endif
-	pc->ldt = newldt;
-	wmb();
-	pc->size = mincount;
-	wmb();
-
-	if (reload) {
-#ifdef CONFIG_SMP
-		preempt_disable();
-		load_LDT(pc);
-		if (!cpumask_equal(mm_cpumask(current->mm),
-				   cpumask_of(smp_processor_id())))
-			smp_call_function(flush_ldt, current->mm, 1);
-		preempt_enable();
-#else
-		load_LDT(pc);
-#endif
-	}
-	if (oldsize) {
-		paravirt_free_ldt(oldldt, oldsize);
-		if (oldsize * LDT_ENTRY_SIZE > PAGE_SIZE)
-			vfree(oldldt);
-		else
-			put_page(virt_to_page(oldldt));
-	}
-	return 0;
+/* After calling this, the LDT is immutable. */
+static void finalize_ldt_struct(struct ldt_struct *ldt)
+{
+	paravirt_alloc_ldt(ldt->entries, ldt->size);
 }
 
-static inline int copy_ldt(mm_context_t *new, mm_context_t *old)
+/* context.lock is held */
+static void install_ldt(struct mm_struct *current_mm,
+			struct ldt_struct *ldt)
 {
-	int err = alloc_ldt(new, old->size, 0);
-	int i;
+	/* Synchronizes with lockless_dereference in load_mm_ldt. */
+	smp_store_release(&current_mm->context.ldt, ldt);
+
+	/* Activate the LDT for all CPUs using current_mm. */
+	on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true);
+}
 
-	if (err < 0)
-		return err;
+static void free_ldt_struct(struct ldt_struct *ldt)
+{
+	if (likely(!ldt))
+		return;
 
-	for (i = 0; i < old->size; i++)
-		write_ldt_entry(new->ldt, i, old->ldt + i * LDT_ENTRY_SIZE);
-	return 0;
+	paravirt_free_ldt(ldt->entries, ldt->size);
+	if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE)
+		vfree(ldt->entries);
+	else
+		kfree(ldt->entries);
+	kfree(ldt);
 }
 
 /*
@@ -104,17 +105,37 @@ static inline int copy_ldt(mm_context_t *new, mm_context_t *old)
  */
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
+	struct ldt_struct *new_ldt;
 	struct mm_struct *old_mm;
 	int retval = 0;
 
 	mutex_init(&mm->context.lock);
-	mm->context.size = 0;
 	old_mm = current->mm;
-	if (old_mm && old_mm->context.size > 0) {
-		mutex_lock(&old_mm->context.lock);
-		retval = copy_ldt(&mm->context, &old_mm->context);
-		mutex_unlock(&old_mm->context.lock);
+	if (!old_mm) {
+		mm->context.ldt = NULL;
+		return 0;
 	}
+
+	mutex_lock(&old_mm->context.lock);
+	if (!old_mm->context.ldt) {
+		mm->context.ldt = NULL;
+		goto out_unlock;
+	}
+
+	new_ldt = alloc_ldt_struct(old_mm->context.ldt->size);
+	if (!new_ldt) {
+		retval = -ENOMEM;
+		goto out_unlock;
+	}
+
+	memcpy(new_ldt->entries, old_mm->context.ldt->entries,
+	       new_ldt->size * LDT_ENTRY_SIZE);
+	finalize_ldt_struct(new_ldt);
+
+	mm->context.ldt = new_ldt;
+
+out_unlock:
+	mutex_unlock(&old_mm->context.lock);
 	return retval;
 }
 
@@ -125,53 +146,47 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
  */
 void destroy_context(struct mm_struct *mm)
 {
-	if (mm->context.size) {
-#ifdef CONFIG_X86_32
-		/* CHECKME: Can this ever happen ? */
-		if (mm == current->active_mm)
-			clear_LDT();
-#endif
-		paravirt_free_ldt(mm->context.ldt, mm->context.size);
-		if (mm->context.size * LDT_ENTRY_SIZE > PAGE_SIZE)
-			vfree(mm->context.ldt);
-		else
-			put_page(virt_to_page(mm->context.ldt));
-		mm->context.size = 0;
-	}
+	free_ldt_struct(mm->context.ldt);
+	mm->context.ldt = NULL;
 }
 
 static int read_ldt(void __user *ptr, unsigned long bytecount)
 {
-	int err;
+	int retval;
 	unsigned long size;
 	struct mm_struct *mm = current->mm;
 
-	if (!mm->context.size)
-		return 0;
+	mutex_lock(&mm->context.lock);
+
+	if (!mm->context.ldt) {
+		retval = 0;
+		goto out_unlock;
+	}
+
 	if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES)
 		bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES;
 
-	mutex_lock(&mm->context.lock);
-	size = mm->context.size * LDT_ENTRY_SIZE;
+	size = mm->context.ldt->size * LDT_ENTRY_SIZE;
 	if (size > bytecount)
 		size = bytecount;
 
-	err = 0;
-	if (copy_to_user(ptr, mm->context.ldt, size))
-		err = -EFAULT;
-	mutex_unlock(&mm->context.lock);
-	if (err < 0)
-		goto error_return;
+	if (copy_to_user(ptr, mm->context.ldt->entries, size)) {
+		retval = -EFAULT;
+		goto out_unlock;
+	}
+
 	if (size != bytecount) {
-		/* zero-fill the rest */
-		if (clear_user(ptr + size, bytecount - size) != 0) {
-			err = -EFAULT;
-			goto error_return;
+		/* Zero-fill the rest and pretend we read bytecount bytes. */
+		if (clear_user(ptr + size, bytecount - size)) {
+			retval = -EFAULT;
+			goto out_unlock;
 		}
 	}
-	return bytecount;
-error_return:
-	return err;
+	retval = bytecount;
+
+out_unlock:
+	mutex_unlock(&mm->context.lock);
+	return retval;
 }
 
 static int read_default_ldt(void __user *ptr, unsigned long bytecount)
@@ -195,6 +210,8 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 	struct desc_struct ldt;
 	int error;
 	struct user_desc ldt_info;
+	int oldsize, newsize;
+	struct ldt_struct *new_ldt, *old_ldt;
 
 	error = -EINVAL;
 	if (bytecount != sizeof(ldt_info))
@@ -213,34 +230,39 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 			goto out;
 	}
 
-	mutex_lock(&mm->context.lock);
-	if (ldt_info.entry_number >= mm->context.size) {
-		error = alloc_ldt(&current->mm->context,
-				  ldt_info.entry_number + 1, 1);
-		if (error < 0)
-			goto out_unlock;
-	}
-
-	/* Allow LDTs to be cleared by the user. */
-	if (ldt_info.base_addr == 0 && ldt_info.limit == 0) {
-		if (oldmode || LDT_empty(&ldt_info)) {
-			memset(&ldt, 0, sizeof(ldt));
-			goto install;
+	if ((oldmode && !ldt_info.base_addr && !ldt_info.limit) ||
+	    LDT_empty(&ldt_info)) {
+		/* The user wants to clear the entry. */
+		memset(&ldt, 0, sizeof(ldt));
+	} else {
+		if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
+			error = -EINVAL;
+			goto out;
 		}
+
+		fill_ldt(&ldt, &ldt_info);
+		if (oldmode)
+			ldt.avl = 0;
 	}
 
-	if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
-		error = -EINVAL;
+	mutex_lock(&mm->context.lock);
+
+	old_ldt = mm->context.ldt;
+	oldsize = old_ldt ? old_ldt->size : 0;
+	newsize = max((int)(ldt_info.entry_number + 1), oldsize);
+
+	error = -ENOMEM;
+	new_ldt = alloc_ldt_struct(newsize);
+	if (!new_ldt)
 		goto out_unlock;
-	}
 
-	fill_ldt(&ldt, &ldt_info);
-	if (oldmode)
-		ldt.avl = 0;
+	if (old_ldt)
+		memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE);
+	new_ldt->entries[ldt_info.entry_number] = ldt;
+	finalize_ldt_struct(new_ldt);
 
-	/* Install the new entry ...  */
-install:
-	write_ldt_entry(mm->context.ldt, ldt_info.entry_number, &ldt);
+	install_ldt(mm, new_ldt);
+	free_ldt_struct(old_ldt);
 	error = 0;
 
 out_unlock:
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 71d7849a07f7..f6b916387590 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -121,11 +121,11 @@ void __show_regs(struct pt_regs *regs, int all)
 void release_thread(struct task_struct *dead_task)
 {
 	if (dead_task->mm) {
-		if (dead_task->mm->context.size) {
+		if (dead_task->mm->context.ldt) {
 			pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n",
 				dead_task->comm,
 				dead_task->mm->context.ldt,
-				dead_task->mm->context.size);
+				dead_task->mm->context.ldt->size);
 			BUG();
 		}
 	}
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 206996c1669d..71820c42b6ce 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -93,8 +93,15 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 		COPY(r15);
 #endif /* CONFIG_X86_64 */
 
+#ifdef CONFIG_X86_32
 		COPY_SEG_CPL3(cs);
 		COPY_SEG_CPL3(ss);
+#else /* !CONFIG_X86_32 */
+		/* Kernel saves and restores only the CS segment register on signals,
+		 * which is the bare minimum needed to allow mixed 32/64-bit code.
+		 * App's signal handler can save/restore other segments if needed. */
+		COPY_SEG_CPL3(cs);
+#endif /* CONFIG_X86_32 */
 
 		get_user_ex(tmpflags, &sc->flags);
 		regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
@@ -154,9 +161,8 @@ int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
 #else /* !CONFIG_X86_32 */
 		put_user_ex(regs->flags, &sc->flags);
 		put_user_ex(regs->cs, &sc->cs);
-		put_user_ex(0, &sc->__pad2);
-		put_user_ex(0, &sc->__pad1);
-		put_user_ex(regs->ss, &sc->ss);
+		put_user_ex(0, &sc->gs);
+		put_user_ex(0, &sc->fs);
 #endif /* CONFIG_X86_32 */
 
 		put_user_ex(fpstate, &sc->fpstate);
@@ -451,19 +457,9 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 
 	regs->sp = (unsigned long)frame;
 
-	/*
-	 * Set up the CS and SS registers to run signal handlers in
-	 * 64-bit mode, even if the handler happens to be interrupting
-	 * 32-bit or 16-bit code.
-	 *
-	 * SS is subtle.  In 64-bit mode, we don't need any particular
-	 * SS descriptor, but we do need SS to be valid.  It's possible
-	 * that the old SS is entirely bogus -- this can happen if the
-	 * signal we're trying to deliver is #GP or #SS caused by a bad
-	 * SS value.
-	 */
+	/* Set up the CS register to run signal handlers in 64-bit mode,
+	   even if the handler happens to be interrupting 32-bit code. */
 	regs->cs = __USER_CS;
-	regs->ss = __USER_DS;
 
 	return 0;
 }
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 9b4d51d0c0d0..6273324186ac 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -5,6 +5,7 @@
 #include <linux/mm.h>
 #include <linux/ptrace.h>
 #include <asm/desc.h>
+#include <asm/mmu_context.h>
 
 unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs)
 {
@@ -30,10 +31,11 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re
 		seg &= ~7UL;
 
 		mutex_lock(&child->mm->context.lock);
-		if (unlikely((seg >> 3) >= child->mm->context.size))
+		if (unlikely(!child->mm->context.ldt ||
+			     (seg >> 3) >= child->mm->context.ldt->size))
 			addr = -1L; /* bogus selector, access would fault */
 		else {
-			desc = child->mm->context.ldt + seg;
+			desc = &child->mm->context.ldt->entries[seg];
 			base = get_desc_base(desc);
 
 			/* 16-bit code segment? */
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index dc0a84a6f309..9e8bf13572e6 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -672,16 +672,16 @@ u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
 	if (iter.mtrr_disabled)
 		return mtrr_disabled_type();
 
+	/* not contained in any MTRRs. */
+	if (type == -1)
+		return mtrr_default_type(mtrr_state);
+
 	/*
 	 * We just check one page, partially covered by MTRRs is
 	 * impossible.
 	 */
 	WARN_ON(iter.partial_map);
 
-	/* not contained in any MTRRs. */
-	if (type == -1)
-		return mtrr_default_type(mtrr_state);
-
 	return type;
 }
 EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type);
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index cfba30f27392..e4308fe6afe8 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -972,6 +972,11 @@ u64 efi_mem_attributes(unsigned long phys_addr)
 
 static int __init arch_parse_efi_cmdline(char *str)
 {
+	if (!str) {
+		pr_warn("need at least one option\n");
+		return -EINVAL;
+	}
+
 	if (parse_option_str(str, "old_map"))
 		set_bit(EFI_OLD_MEMMAP, &efi.flags);
 	if (parse_option_str(str, "debug"))
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 0d7dd1f5ac36..9ab52791fed5 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -22,6 +22,7 @@
 #include <asm/fpu/internal.h>
 #include <asm/debugreg.h>
 #include <asm/cpu.h>
+#include <asm/mmu_context.h>
 
 #ifdef CONFIG_X86_32
 __visible unsigned long saved_context_ebx;
@@ -153,7 +154,7 @@ static void fix_processor_context(void)
 	syscall_init();				/* This sets MSR_*STAR and related */
 #endif
 	load_TR_desc();				/* This does ltr */
-	load_LDT(&current->active_mm->context);	/* This does lldt */
+	load_mm_ldt(current->active_mm);	/* This does lldt */
 
 	fpu__resume_cpu();
 }
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 7322755f337a..4b6e29ac0968 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -13,13 +13,13 @@ CFLAGS_mmu.o			:= $(nostackp)
 obj-y		:= enlighten.o setup.o multicalls.o mmu.o irq.o \
 			time.o xen-asm.o xen-asm_$(BITS).o \
 			grant-table.o suspend.o platform-pci-unplug.o \
-			p2m.o
+			p2m.o apic.o
 
 obj-$(CONFIG_EVENT_TRACING) += trace.o
 
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
 obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
-obj-$(CONFIG_XEN_DOM0)		+= apic.o vga.o
+obj-$(CONFIG_XEN_DOM0)		+= vga.o
 obj-$(CONFIG_SWIOTLB_XEN)	+= pci-swiotlb-xen.o
 obj-$(CONFIG_XEN_EFI)		+= efi.o
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 0b95c9b8283f..11d6fb4e8483 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -483,6 +483,7 @@ static void set_aliased_prot(void *v, pgprot_t prot)
 	pte_t pte;
 	unsigned long pfn;
 	struct page *page;
+	unsigned char dummy;
 
 	ptep = lookup_address((unsigned long)v, &level);
 	BUG_ON(ptep == NULL);
@@ -492,6 +493,32 @@ static void set_aliased_prot(void *v, pgprot_t prot)
 
 	pte = pfn_pte(pfn, prot);
 
+	/*
+	 * Careful: update_va_mapping() will fail if the virtual address
+	 * we're poking isn't populated in the page tables.  We don't
+	 * need to worry about the direct map (that's always in the page
+	 * tables), but we need to be careful about vmap space.  In
+	 * particular, the top level page table can lazily propagate
+	 * entries between processes, so if we've switched mms since we
+	 * vmapped the target in the first place, we might not have the
+	 * top-level page table entry populated.
+	 *
+	 * We disable preemption because we want the same mm active when
+	 * we probe the target and when we issue the hypercall.  We'll
+	 * have the same nominal mm, but if we're a kernel thread, lazy
+	 * mm dropping could change our pgd.
+	 *
+	 * Out of an abundance of caution, this uses __get_user() to fault
+	 * in the target address just in case there's some obscure case
+	 * in which the target address isn't readable.
+	 */
+
+	preempt_disable();
+
+	pagefault_disable();	/* Avoid warnings due to being atomic. */
+	__get_user(dummy, (unsigned char __user __force *)v);
+	pagefault_enable();
+
 	if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
 		BUG();
 
@@ -503,6 +530,8 @@ static void set_aliased_prot(void *v, pgprot_t prot)
 				BUG();
 	} else
 		kmap_flush_unused();
+
+	preempt_enable();
 }
 
 static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
@@ -510,6 +539,17 @@ static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
 	const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE;
 	int i;
 
+	/*
+	 * We need to mark the all aliases of the LDT pages RO.  We
+	 * don't need to call vm_flush_aliases(), though, since that's
+	 * only responsible for flushing aliases out the TLBs, not the
+	 * page tables, and Xen will flush the TLB for us if needed.
+	 *
+	 * To avoid confusing future readers: none of this is necessary
+	 * to load the LDT.  The hypervisor only checks this when the
+	 * LDT is faulted in due to subsequent descriptor access.
+	 */
+
 	for(i = 0; i < entries; i += entries_per_page)
 		set_aliased_prot(ldt + i, PAGE_KERNEL_RO);
 }
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index c20fe29e65f4..2292721b1d10 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -101,17 +101,15 @@ struct dom0_vga_console_info;
 
 #ifdef CONFIG_XEN_DOM0
 void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size);
-void __init xen_init_apic(void);
 #else
 static inline void __init xen_init_vga(const struct dom0_vga_console_info *info,
 				       size_t size)
 {
 }
-static inline void __init xen_init_apic(void)
-{
-}
 #endif
 
+void __init xen_init_apic(void);
+
 #ifdef CONFIG_XEN_EFI
 extern void xen_efi_init(void);
 #else