23 files changed, 377 insertions, 288 deletions

diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h
index a36e8601114d..d5da2115d78a 100644
--- a/arch/arc/include/asm/delay.h
+++ b/arch/arc/include/asm/delay.h
@@ -26,7 +26,9 @@ static inline void __delay(unsigned long loops)
 	"	lp  1f			\n"
 	"	nop			\n"
 	"1:				\n"
-	: : "r"(loops));
+	:
+        : "r"(loops)
+        : "lp_count");
 }
 
 extern void __bad_udelay(void);
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 689dd867fdff..8b90d25a15cc 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -71,14 +71,14 @@ ENTRY(stext)
 	GET_CPU_ID  r5
 	cmp	r5, 0
 	mov.nz	r0, r5
-#ifdef CONFIG_ARC_SMP_HALT_ON_RESET
-	; Non-Master can proceed as system would be booted sufficiently
-	jnz	first_lines_of_secondary
-#else
+	bz	.Lmaster_proceed
+
 	; Non-Masters wait for Master to boot enough and bring them up
-	jnz	arc_platform_smp_wait_to_boot
-#endif
-	; Master falls thru
+	; when they resume, tail-call to entry point
+	mov	blink, @first_lines_of_secondary
+	j	arc_platform_smp_wait_to_boot
+
+.Lmaster_proceed:
 #endif
 
 	; Clear BSS before updating any globals
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index 9274f8ade8c7..9f6b68fd4f3b 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -93,11 +93,10 @@ static void mcip_probe_n_setup(void)
 	READ_BCR(ARC_REG_MCIP_BCR, mp);
 
 	sprintf(smp_cpuinfo_buf,
-		"Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s%s\n",
+		"Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s\n",
 		mp.ver, mp.num_cores,
 		IS_AVAIL1(mp.ipi, "IPI "),
 		IS_AVAIL1(mp.idu, "IDU "),
-		IS_AVAIL1(mp.llm, "LLM "),
 		IS_AVAIL1(mp.dbg, "DEBUG "),
 		IS_AVAIL1(mp.gfrc, "GFRC"));
 
@@ -175,7 +174,6 @@ static void idu_irq_unmask(struct irq_data *data)
 	raw_spin_unlock_irqrestore(&mcip_lock, flags);
 }
 
-#ifdef CONFIG_SMP
 static int
 idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask,
 		     bool force)
@@ -205,12 +203,27 @@ idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask,
 
 	return IRQ_SET_MASK_OK;
 }
-#endif
+
+static void idu_irq_enable(struct irq_data *data)
+{
+	/*
+	 * By default send all common interrupts to all available online CPUs.
+	 * The affinity of common interrupts in IDU must be set manually since
+	 * in some cases the kernel will not call irq_set_affinity() by itself:
+	 *   1. When the kernel is not configured with support of SMP.
+	 *   2. When the kernel is configured with support of SMP but upper
+	 *      interrupt controllers does not support setting of the affinity
+	 *      and cannot propagate it to IDU.
+	 */
+	idu_irq_set_affinity(data, cpu_online_mask, false);
+	idu_irq_unmask(data);
+}
 
 static struct irq_chip idu_irq_chip = {
 	.name			= "MCIP IDU Intc",
 	.irq_mask		= idu_irq_mask,
 	.irq_unmask		= idu_irq_unmask,
+	.irq_enable		= idu_irq_enable,
 #ifdef CONFIG_SMP
 	.irq_set_affinity       = idu_irq_set_affinity,
 #endif
@@ -243,36 +256,14 @@ static int idu_irq_xlate(struct irq_domain *d, struct device_node *n,
 			 const u32 *intspec, unsigned int intsize,
 			 irq_hw_number_t *out_hwirq, unsigned int *out_type)
 {
-	irq_hw_number_t hwirq = *out_hwirq = intspec[0];
-	int distri = intspec[1];
-	unsigned long flags;
-
+	/*
+	 * Ignore value of interrupt distribution mode for common interrupts in
+	 * IDU which resides in intspec[1] since setting an affinity using value
+	 * from Device Tree is deprecated in ARC.
+	 */
+	*out_hwirq = intspec[0];
 	*out_type = IRQ_TYPE_NONE;
 
-	/* XXX: validate distribution scheme again online cpu mask */
-	if (distri == 0) {
-		/* 0 - Round Robin to all cpus, otherwise 1 bit per core */
-		raw_spin_lock_irqsave(&mcip_lock, flags);
-		idu_set_dest(hwirq, BIT(num_online_cpus()) - 1);
-		idu_set_mode(hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_RR);
-		raw_spin_unlock_irqrestore(&mcip_lock, flags);
-	} else {
-		/*
-		 * DEST based distribution for Level Triggered intr can only
-		 * have 1 CPU, so generalize it to always contain 1 cpu
-		 */
-		int cpu = ffs(distri);
-
-		if (cpu != fls(distri))
-			pr_warn("IDU irq %lx distri mode set to cpu %x\n",
-				hwirq, cpu);
-
-		raw_spin_lock_irqsave(&mcip_lock, flags);
-		idu_set_dest(hwirq, cpu);
-		idu_set_mode(hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_DEST);
-		raw_spin_unlock_irqrestore(&mcip_lock, flags);
-	}
-
 	return 0;
 }
 
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index 88674d972c9d..2afbafadb6ab 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -90,22 +90,37 @@ void __init smp_cpus_done(unsigned int max_cpus)
  */
 static volatile int wake_flag;
 
+#ifdef CONFIG_ISA_ARCOMPACT
+
+#define __boot_read(f)		f
+#define __boot_write(f, v)	f = v
+
+#else
+
+#define __boot_read(f)		arc_read_uncached_32(&f)
+#define __boot_write(f, v)	arc_write_uncached_32(&f, v)
+
+#endif
+
 static void arc_default_smp_cpu_kick(int cpu, unsigned long pc)
 {
 	BUG_ON(cpu == 0);
-	wake_flag = cpu;
+
+	__boot_write(wake_flag, cpu);
 }
 
 void arc_platform_smp_wait_to_boot(int cpu)
 {
-	while (wake_flag != cpu)
+	/* for halt-on-reset, we've waited already */
+	if (IS_ENABLED(CONFIG_ARC_SMP_HALT_ON_RESET))
+		return;
+
+	while (__boot_read(wake_flag) != cpu)
 		;
 
-	wake_flag = 0;
-	__asm__ __volatile__("j @first_lines_of_secondary	\n");
+	__boot_write(wake_flag, 0);
 }
 
-
 const char *arc_platform_smp_cpuinfo(void)
 {
 	return plat_smp_ops.info ? : "";
diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c
index abd961f3e763..91ebe382147f 100644
--- a/arch/arc/kernel/unaligned.c
+++ b/arch/arc/kernel/unaligned.c
@@ -241,8 +241,9 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs,
 	if (state.fault)
 		goto fault;
 
+	/* clear any remanants of delay slot */
 	if (delay_mode(regs)) {
-		regs->ret = regs->bta;
+		regs->ret = regs->bta ~1U;
 		regs->status32 &= ~STATUS_DE_MASK;
 	} else {
 		regs->ret += state.instr_len;
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
index c53dbeae79f2..838dad5c209f 100644
--- a/arch/arm64/crypto/aes-modes.S
+++ b/arch/arm64/crypto/aes-modes.S
@@ -193,15 +193,16 @@ AES_ENTRY(aes_cbc_encrypt)
 	cbz		w6, .Lcbcencloop
 
 	ld1		{v0.16b}, [x5]			/* get iv */
-	enc_prepare	w3, x2, x5
+	enc_prepare	w3, x2, x6
 
 .Lcbcencloop:
 	ld1		{v1.16b}, [x1], #16		/* get next pt block */
 	eor		v0.16b, v0.16b, v1.16b		/* ..and xor with iv */
-	encrypt_block	v0, w3, x2, x5, w6
+	encrypt_block	v0, w3, x2, x6, w7
 	st1		{v0.16b}, [x0], #16
 	subs		w4, w4, #1
 	bne		.Lcbcencloop
+	st1		{v0.16b}, [x5]			/* return iv */
 	ret
 AES_ENDPROC(aes_cbc_encrypt)
 
@@ -211,7 +212,7 @@ AES_ENTRY(aes_cbc_decrypt)
 	cbz		w6, .LcbcdecloopNx
 
 	ld1		{v7.16b}, [x5]			/* get iv */
-	dec_prepare	w3, x2, x5
+	dec_prepare	w3, x2, x6
 
 .LcbcdecloopNx:
 #if INTERLEAVE >= 2
@@ -248,7 +249,7 @@ AES_ENTRY(aes_cbc_decrypt)
 .Lcbcdecloop:
 	ld1		{v1.16b}, [x1], #16		/* get next ct block */
 	mov		v0.16b, v1.16b			/* ...and copy to v0 */
-	decrypt_block	v0, w3, x2, x5, w6
+	decrypt_block	v0, w3, x2, x6, w7
 	eor		v0.16b, v0.16b, v7.16b		/* xor with iv => pt */
 	mov		v7.16b, v1.16b			/* ct is next iv */
 	st1		{v0.16b}, [x0], #16
@@ -256,6 +257,7 @@ AES_ENTRY(aes_cbc_decrypt)
 	bne		.Lcbcdecloop
 .Lcbcdecout:
 	FRAME_POP
+	st1		{v7.16b}, [x5]			/* return iv */
 	ret
 AES_ENDPROC(aes_cbc_decrypt)
 
@@ -267,24 +269,15 @@ AES_ENDPROC(aes_cbc_decrypt)
 
 AES_ENTRY(aes_ctr_encrypt)
 	FRAME_PUSH
-	cbnz		w6, .Lctrfirst		/* 1st time around? */
-	umov		x5, v4.d[1]		/* keep swabbed ctr in reg */
-	rev		x5, x5
-#if INTERLEAVE >= 2
-	cmn		w5, w4			/* 32 bit overflow? */
-	bcs		.Lctrinc
-	add		x5, x5, #1		/* increment BE ctr */
-	b		.LctrincNx
-#else
-	b		.Lctrinc
-#endif
-.Lctrfirst:
+	cbz		w6, .Lctrnotfirst	/* 1st time around? */
 	enc_prepare	w3, x2, x6
 	ld1		{v4.16b}, [x5]
-	umov		x5, v4.d[1]		/* keep swabbed ctr in reg */
-	rev		x5, x5
+
+.Lctrnotfirst:
+	umov		x8, v4.d[1]		/* keep swabbed ctr in reg */
+	rev		x8, x8
 #if INTERLEAVE >= 2
-	cmn		w5, w4			/* 32 bit overflow? */
+	cmn		w8, w4			/* 32 bit overflow? */
 	bcs		.Lctrloop
 .LctrloopNx:
 	subs		w4, w4, #INTERLEAVE
@@ -292,11 +285,11 @@ AES_ENTRY(aes_ctr_encrypt)
 #if INTERLEAVE == 2
 	mov		v0.8b, v4.8b
 	mov		v1.8b, v4.8b
-	rev		x7, x5
-	add		x5, x5, #1
+	rev		x7, x8
+	add		x8, x8, #1
 	ins		v0.d[1], x7
-	rev		x7, x5
-	add		x5, x5, #1
+	rev		x7, x8
+	add		x8, x8, #1
 	ins		v1.d[1], x7
 	ld1		{v2.16b-v3.16b}, [x1], #32	/* get 2 input blocks */
 	do_encrypt_block2x
@@ -305,7 +298,7 @@ AES_ENTRY(aes_ctr_encrypt)
 	st1		{v0.16b-v1.16b}, [x0], #32
 #else
 	ldr		q8, =0x30000000200000001	/* addends 1,2,3[,0] */
-	dup		v7.4s, w5
+	dup		v7.4s, w8
 	mov		v0.16b, v4.16b
 	add		v7.4s, v7.4s, v8.4s
 	mov		v1.16b, v4.16b
@@ -323,18 +316,12 @@ AES_ENTRY(aes_ctr_encrypt)
 	eor		v2.16b, v7.16b, v2.16b
 	eor		v3.16b, v5.16b, v3.16b
 	st1		{v0.16b-v3.16b}, [x0], #64
-	add		x5, x5, #INTERLEAVE
+	add		x8, x8, #INTERLEAVE
 #endif
-	cbz		w4, .LctroutNx
-.LctrincNx:
-	rev		x7, x5
+	rev		x7, x8
 	ins		v4.d[1], x7
+	cbz		w4, .Lctrout
 	b		.LctrloopNx
-.LctroutNx:
-	sub		x5, x5, #1
-	rev		x7, x5
-	ins		v4.d[1], x7
-	b		.Lctrout
 .Lctr1x:
 	adds		w4, w4, #INTERLEAVE
 	beq		.Lctrout
@@ -342,30 +329,39 @@ AES_ENTRY(aes_ctr_encrypt)
 .Lctrloop:
 	mov		v0.16b, v4.16b
 	encrypt_block	v0, w3, x2, x6, w7
+
+	adds		x8, x8, #1		/* increment BE ctr */
+	rev		x7, x8
+	ins		v4.d[1], x7
+	bcs		.Lctrcarry		/* overflow? */
+
+.Lctrcarrydone:
 	subs		w4, w4, #1
 	bmi		.Lctrhalfblock		/* blocks < 0 means 1/2 block */
 	ld1		{v3.16b}, [x1], #16
 	eor		v3.16b, v0.16b, v3.16b
 	st1		{v3.16b}, [x0], #16
-	beq		.Lctrout
-.Lctrinc:
-	adds		x5, x5, #1		/* increment BE ctr */
-	rev		x7, x5
-	ins		v4.d[1], x7
-	bcc		.Lctrloop		/* no overflow? */
-	umov		x7, v4.d[0]		/* load upper word of ctr  */
-	rev		x7, x7			/* ... to handle the carry */
-	add		x7, x7, #1
-	rev		x7, x7
-	ins		v4.d[0], x7
-	b		.Lctrloop
+	bne		.Lctrloop
+
+.Lctrout:
+	st1		{v4.16b}, [x5]		/* return next CTR value */
+	FRAME_POP
+	ret
+
 .Lctrhalfblock:
 	ld1		{v3.8b}, [x1]
 	eor		v3.8b, v0.8b, v3.8b
 	st1		{v3.8b}, [x0]
-.Lctrout:
 	FRAME_POP
 	ret
+
+.Lctrcarry:
+	umov		x7, v4.d[0]		/* load upper word of ctr  */
+	rev		x7, x7			/* ... to handle the carry */
+	add		x7, x7, #1
+	rev		x7, x7
+	ins		v4.d[0], x7
+	b		.Lctrcarrydone
 AES_ENDPROC(aes_ctr_encrypt)
 	.ltorg
 
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 23e9e13bd2aa..655e65f38f31 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -11,6 +11,7 @@
  * for more details.
  */
 
+#include <linux/acpi.h>
 #include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/init.h>
@@ -209,7 +210,12 @@ static struct notifier_block init_cpu_capacity_notifier = {
 
 static int __init register_cpufreq_notifier(void)
 {
-	if (cap_parsing_failed)
+	/*
+	 * on ACPI-based systems we need to use the default cpu capacity
+	 * until we have the necessary code to parse the cpu capacity, so
+	 * skip registering cpufreq notifier.
+	 */
+	if (!acpi_disabled || cap_parsing_failed)
 		return -EINVAL;
 
 	if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL)) {
diff --git a/arch/frv/include/asm/atomic.h b/arch/frv/include/asm/atomic.h
index 1c2a5e264fc7..e93c9494503a 100644
--- a/arch/frv/include/asm/atomic.h
+++ b/arch/frv/include/asm/atomic.h
@@ -139,7 +139,7 @@ static inline void atomic64_dec(atomic64_t *v)
 #define atomic64_sub_and_test(i,v)	(atomic64_sub_return((i), (v)) == 0)
 #define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
 #define atomic64_inc_and_test(v)	(atomic64_inc_return((v)) == 0)
-
+#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
 
 #define atomic_cmpxchg(v, old, new)	(cmpxchg(&(v)->counter, old, new))
 #define atomic_xchg(v, new)		(xchg(&(v)->counter, new))
@@ -161,6 +161,39 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 	return c;
 }
 
+static inline int atomic64_add_unless(atomic64_t *v, long long i, long long u)
+{
+	long long c, old;
+
+	c = atomic64_read(v);
+	for (;;) {
+		if (unlikely(c == u))
+			break;
+		old = atomic64_cmpxchg(v, c, c + i);
+		if (likely(old == c))
+			break;
+		c = old;
+	}
+	return c != u;
+}
+
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
+{
+	long long c, old, dec;
+
+	c = atomic64_read(v);
+	for (;;) {
+		dec = c - 1;
+		if (unlikely(dec < 0))
+			break;
+		old = atomic64_cmpxchg((v), c, dec);
+		if (likely(old == c))
+			break;
+		c = old;
+	}
+		return dec;
+}
+
 #define ATOMIC_OP(op)							\
 static inline int atomic_fetch_##op(int i, atomic_t *v)			\
 {									\
diff --git a/arch/mn10300/include/asm/switch_to.h b/arch/mn10300/include/asm/switch_to.h
index 393d311735c8..67e333aa7629 100644
--- a/arch/mn10300/include/asm/switch_to.h
+++ b/arch/mn10300/include/asm/switch_to.h
@@ -16,7 +16,7 @@
 struct task_struct;
 struct thread_struct;
 
-#if !defined(CONFIG_LAZY_SAVE_FPU)
+#if defined(CONFIG_FPU) && !defined(CONFIG_LAZY_SAVE_FPU)
 struct fpu_state_struct;
 extern asmlinkage void fpu_save(struct fpu_state_struct *);
 #define switch_fpu(prev, next)						\
diff --git a/arch/parisc/include/asm/bitops.h b/arch/parisc/include/asm/bitops.h
index 3f9406d9b9d6..da87943328a5 100644
--- a/arch/parisc/include/asm/bitops.h
+++ b/arch/parisc/include/asm/bitops.h
@@ -6,7 +6,7 @@
 #endif
 
 #include <linux/compiler.h>
-#include <asm/types.h>		/* for BITS_PER_LONG/SHIFT_PER_LONG */
+#include <asm/types.h>
 #include <asm/byteorder.h>
 #include <asm/barrier.h>
 #include <linux/atomic.h>
@@ -17,6 +17,12 @@
  * to include/asm-i386/bitops.h or kerneldoc
  */
 
+#if __BITS_PER_LONG == 64
+#define SHIFT_PER_LONG 6
+#else
+#define SHIFT_PER_LONG 5
+#endif
+
 #define CHOP_SHIFTCOUNT(x) (((unsigned long) (x)) & (BITS_PER_LONG - 1))
 
 
diff --git a/arch/parisc/include/uapi/asm/bitsperlong.h b/arch/parisc/include/uapi/asm/bitsperlong.h
index e0a23c7bdd43..07fa7e50bdc0 100644
--- a/arch/parisc/include/uapi/asm/bitsperlong.h
+++ b/arch/parisc/include/uapi/asm/bitsperlong.h
@@ -3,10 +3,8 @@
 
 #if defined(__LP64__)
 #define __BITS_PER_LONG 64
-#define SHIFT_PER_LONG 6
 #else
 #define __BITS_PER_LONG 32
-#define SHIFT_PER_LONG 5
 #endif
 
 #include <asm-generic/bitsperlong.h>
diff --git a/arch/parisc/include/uapi/asm/swab.h b/arch/parisc/include/uapi/asm/swab.h
index e78403b129ef..928e1bbac98f 100644
--- a/arch/parisc/include/uapi/asm/swab.h
+++ b/arch/parisc/include/uapi/asm/swab.h
@@ -1,6 +1,7 @@
 #ifndef _PARISC_SWAB_H
 #define _PARISC_SWAB_H
 
+#include <asm/bitsperlong.h>
 #include <linux/types.h>
 #include <linux/compiler.h>
 
@@ -38,7 +39,7 @@ static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
 }
 #define __arch_swab32 __arch_swab32
 
-#if BITS_PER_LONG > 32
+#if __BITS_PER_LONG > 32
 /*
 ** From "PA-RISC 2.0 Architecture", HP Professional Books.
 ** See Appendix I page 8 , "Endian Byte Swapping".
@@ -61,6 +62,6 @@ static inline __attribute_const__ __u64 __arch_swab64(__u64 x)
 	return x;
 }
 #define __arch_swab64 __arch_swab64
-#endif /* BITS_PER_LONG > 32 */
+#endif /* __BITS_PER_LONG > 32 */
 
 #endif /* _PARISC_SWAB_H */
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 7447ba509c30..12020b55887b 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -963,6 +963,11 @@ static int s390_fpregs_set(struct task_struct *target,
 	if (target == current)
 		save_fpu_regs();
 
+	if (MACHINE_HAS_VX)
+		convert_vx_to_fp(fprs, target->thread.fpu.vxrs);
+	else
+		memcpy(&fprs, target->thread.fpu.fprs, sizeof(fprs));
+
 	/* If setting FPC, must validate it first. */
 	if (count > 0 && pos < offsetof(s390_fp_regs, fprs)) {
 		u32 ufpc[2] = { target->thread.fpu.fpc, 0 };
@@ -1067,6 +1072,9 @@ static int s390_vxrs_low_set(struct task_struct *target,
 	if (target == current)
 		save_fpu_regs();
 
+	for (i = 0; i < __NUM_VXRS_LOW; i++)
+		vxrs[i] = *((__u64 *)(target->thread.fpu.vxrs + i) + 1);
+
 	rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
 	if (rc == 0)
 		for (i = 0; i < __NUM_VXRS_LOW; i++)
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 7a1897c51c54..d56ef26d4681 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -202,7 +202,7 @@ static inline pgste_t ptep_xchg_start(struct mm_struct *mm,
 	return pgste;
 }
 
-static inline void ptep_xchg_commit(struct mm_struct *mm,
+static inline pte_t ptep_xchg_commit(struct mm_struct *mm,
 				    unsigned long addr, pte_t *ptep,
 				    pgste_t pgste, pte_t old, pte_t new)
 {
@@ -220,6 +220,7 @@ static inline void ptep_xchg_commit(struct mm_struct *mm,
 	} else {
 		*ptep = new;
 	}
+	return old;
 }
 
 pte_t ptep_xchg_direct(struct mm_struct *mm, unsigned long addr,
@@ -231,7 +232,7 @@ pte_t ptep_xchg_direct(struct mm_struct *mm, unsigned long addr,
 	preempt_disable();
 	pgste = ptep_xchg_start(mm, addr, ptep);
 	old = ptep_flush_direct(mm, addr, ptep);
-	ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
+	old = ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
 	preempt_enable();
 	return old;
 }
@@ -246,7 +247,7 @@ pte_t ptep_xchg_lazy(struct mm_struct *mm, unsigned long addr,
 	preempt_disable();
 	pgste = ptep_xchg_start(mm, addr, ptep);
 	old = ptep_flush_lazy(mm, addr, ptep);
-	ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
+	old = ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
 	preempt_enable();
 	return old;
 }
diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h
index b84be675e507..d0317993e947 100644
--- a/arch/sparc/include/asm/mmu_context_64.h
+++ b/arch/sparc/include/asm/mmu_context_64.h
@@ -35,15 +35,15 @@ void __tsb_context_switch(unsigned long pgd_pa,
 static inline void tsb_context_switch(struct mm_struct *mm)
 {
 	__tsb_context_switch(__pa(mm->pgd),
-			     &mm->context.tsb_block[0],
+			     &mm->context.tsb_block[MM_TSB_BASE],
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-			     (mm->context.tsb_block[1].tsb ?
-			      &mm->context.tsb_block[1] :
+			     (mm->context.tsb_block[MM_TSB_HUGE].tsb ?
+			      &mm->context.tsb_block[MM_TSB_HUGE] :
 			      NULL)
 #else
 			     NULL
 #endif
-			     , __pa(&mm->context.tsb_descr[0]));
+			     , __pa(&mm->context.tsb_descr[MM_TSB_BASE]));
 }
 
 void tsb_grow(struct mm_struct *mm,
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index 3bebf395252c..4d0248aa0928 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -1021,7 +1021,7 @@ static void __init alloc_one_queue(unsigned long *pa_ptr, unsigned long qmask)
 	unsigned long order = get_order(size);
 	unsigned long p;
 
-	p = __get_free_pages(GFP_KERNEL, order);
+	p = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
 	if (!p) {
 		prom_printf("SUN4V: Error, cannot allocate queue.\n");
 		prom_halt();
diff --git a/arch/sparc/kernel/sstate.c b/arch/sparc/kernel/sstate.c
index c59af546f522..3caed4023589 100644
--- a/arch/sparc/kernel/sstate.c
+++ b/arch/sparc/kernel/sstate.c
@@ -43,8 +43,8 @@ static const char poweroff_msg[32] __attribute__((aligned(32))) =
 	"Linux powering off";
 static const char rebooting_msg[32] __attribute__((aligned(32))) =
 	"Linux rebooting";
-static const char panicing_msg[32] __attribute__((aligned(32))) =
-	"Linux panicing";
+static const char panicking_msg[32] __attribute__((aligned(32))) =
+	"Linux panicking";
 
 static int sstate_reboot_call(struct notifier_block *np, unsigned long type, void *_unused)
 {
@@ -76,7 +76,7 @@ static struct notifier_block sstate_reboot_notifier = {
 
 static int sstate_panic_event(struct notifier_block *n, unsigned long event, void *ptr)
 {
-	do_set_sstate(HV_SOFT_STATE_TRANSITION, panicing_msg);
+	do_set_sstate(HV_SOFT_STATE_TRANSITION, panicking_msg);
 
 	return NOTIFY_DONE;
 }
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 4bc10e44d1ca..dfc97a47c9a0 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2051,6 +2051,73 @@ void sun4v_resum_overflow(struct pt_regs *regs)
 	atomic_inc(&sun4v_resum_oflow_cnt);
 }
 
+/* Given a set of registers, get the virtual addressi that was being accessed
+ * by the faulting instructions at tpc.
+ */
+static unsigned long sun4v_get_vaddr(struct pt_regs *regs)
+{
+	unsigned int insn;
+
+	if (!copy_from_user(&insn, (void __user *)regs->tpc, 4)) {
+		return compute_effective_address(regs, insn,
+						 (insn >> 25) & 0x1f);
+	}
+	return 0;
+}
+
+/* Attempt to handle non-resumable errors generated from userspace.
+ * Returns true if the signal was handled, false otherwise.
+ */
+bool sun4v_nonresum_error_user_handled(struct pt_regs *regs,
+				  struct sun4v_error_entry *ent) {
+
+	unsigned int attrs = ent->err_attrs;
+
+	if (attrs & SUN4V_ERR_ATTRS_MEMORY) {
+		unsigned long addr = ent->err_raddr;
+		siginfo_t info;
+
+		if (addr == ~(u64)0) {
+			/* This seems highly unlikely to ever occur */
+			pr_emerg("SUN4V NON-RECOVERABLE ERROR: Memory error detected in unknown location!\n");
+		} else {
+			unsigned long page_cnt = DIV_ROUND_UP(ent->err_size,
+							      PAGE_SIZE);
+
+			/* Break the unfortunate news. */
+			pr_emerg("SUN4V NON-RECOVERABLE ERROR: Memory failed at %016lX\n",
+				 addr);
+			pr_emerg("SUN4V NON-RECOVERABLE ERROR:   Claiming %lu ages.\n",
+				 page_cnt);
+
+			while (page_cnt-- > 0) {
+				if (pfn_valid(addr >> PAGE_SHIFT))
+					get_page(pfn_to_page(addr >> PAGE_SHIFT));
+				addr += PAGE_SIZE;
+			}
+		}
+		info.si_signo = SIGKILL;
+		info.si_errno = 0;
+		info.si_trapno = 0;
+		force_sig_info(info.si_signo, &info, current);
+
+		return true;
+	}
+	if (attrs & SUN4V_ERR_ATTRS_PIO) {
+		siginfo_t info;
+
+		info.si_signo = SIGBUS;
+		info.si_code = BUS_ADRERR;
+		info.si_addr = (void __user *)sun4v_get_vaddr(regs);
+		force_sig_info(info.si_signo, &info, current);
+
+		return true;
+	}
+
+	/* Default to doing nothing */
+	return false;
+}
+
 /* We run with %pil set to PIL_NORMAL_MAX and PSTATE_IE enabled in %pstate.
  * Log the event, clear the first word of the entry, and die.
  */
@@ -2075,6 +2142,12 @@ void sun4v_nonresum_error(struct pt_regs *regs, unsigned long offset)
 
 	put_cpu();
 
+	if (!(regs->tstate & TSTATE_PRIV) &&
+	    sun4v_nonresum_error_user_handled(regs, &local_copy)) {
+		/* DON'T PANIC: This userspace error was handled. */
+		return;
+	}
+
 #ifdef CONFIG_PCI
 	/* Check for the special PCI poke sequence. */
 	if (pci_poke_in_progress && pci_poke_cpu == cpu) {
diff --git a/arch/tile/kernel/ptrace.c b/arch/tile/kernel/ptrace.c
index d89b7011667c..e279572824b1 100644
--- a/arch/tile/kernel/ptrace.c
+++ b/arch/tile/kernel/ptrace.c
@@ -111,7 +111,7 @@ static int tile_gpr_set(struct task_struct *target,
 			  const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	struct pt_regs regs;
+	struct pt_regs regs = *task_pt_regs(target);
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &regs, 0,
 				 sizeof(regs));
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 17c3564d087a..22ef4f72cf32 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -161,7 +161,13 @@ static u64 rapl_timer_ms;
 
 static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
 {
-	return rapl_pmus->pmus[topology_logical_package_id(cpu)];
+	unsigned int pkgid = topology_logical_package_id(cpu);
+
+	/*
+	 * The unsigned check also catches the '-1' return value for non
+	 * existent mappings in the topology map.
+	 */
+	return pkgid < rapl_pmus->maxpkg ? rapl_pmus->pmus[pkgid] : NULL;
 }
 
 static inline u64 rapl_read_counter(struct perf_event *event)
@@ -402,6 +408,8 @@ static int rapl_pmu_event_init(struct perf_event *event)
 
 	/* must be done before validate_group */
 	pmu = cpu_to_rapl_pmu(event->cpu);
+	if (!pmu)
+		return -EINVAL;
 	event->cpu = pmu->cpu;
 	event->pmu_private = pmu;
 	event->hw.event_base = msr;
@@ -585,6 +593,20 @@ static int rapl_cpu_online(unsigned int cpu)
 	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
 	int target;
 
+	if (!pmu) {
+		pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
+		if (!pmu)
+			return -ENOMEM;
+
+		raw_spin_lock_init(&pmu->lock);
+		INIT_LIST_HEAD(&pmu->active_list);
+		pmu->pmu = &rapl_pmus->pmu;
+		pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
+		rapl_hrtimer_init(pmu);
+
+		rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
+	}
+
 	/*
 	 * Check if there is an online cpu in the package which collects rapl
 	 * events already.
@@ -598,27 +620,6 @@ static int rapl_cpu_online(unsigned int cpu)
 	return 0;
 }
 
-static int rapl_cpu_prepare(unsigned int cpu)
-{
-	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
-
-	if (pmu)
-		return 0;
-
-	pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
-	if (!pmu)
-		return -ENOMEM;
-
-	raw_spin_lock_init(&pmu->lock);
-	INIT_LIST_HEAD(&pmu->active_list);
-	pmu->pmu = &rapl_pmus->pmu;
-	pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
-	pmu->cpu = -1;
-	rapl_hrtimer_init(pmu);
-	rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
-	return 0;
-}
-
 static int rapl_check_hw_unit(bool apply_quirk)
 {
 	u64 msr_rapl_power_unit_bits;
@@ -803,29 +804,21 @@ static int __init rapl_pmu_init(void)
 	/*
 	 * Install callbacks. Core will call them for each online cpu.
 	 */
-
-	ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "perf/x86/rapl:prepare",
-				rapl_cpu_prepare, NULL);
-	if (ret)
-		goto out;
-
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE,
 				"perf/x86/rapl:online",
 				rapl_cpu_online, rapl_cpu_offline);
 	if (ret)
-		goto out1;
+		goto out;
 
 	ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1);
 	if (ret)
-		goto out2;
+		goto out1;
 
 	rapl_advertise();
 	return 0;
 
-out2:
-	cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
 out1:
-	cpuhp_remove_state(CPUHP_PERF_X86_RAPL_PREP);
+	cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
 out:
 	pr_warn("Initialization failed (%d), disabled\n", ret);
 	cleanup_rapl_pmus();
@@ -836,7 +829,6 @@ module_init(rapl_pmu_init);
 static void __exit intel_rapl_exit(void)
 {
 	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE);
-	cpuhp_remove_state_nocalls(CPUHP_PERF_X86_RAPL_PREP);
 	perf_pmu_unregister(&rapl_pmus->pmu);
 	cleanup_rapl_pmus();
 }
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 8c4ccdc3a3f3..1ab45976474d 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -100,7 +100,13 @@ ssize_t uncore_event_show(struct kobject *kobj,
 
 struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)