Merge tag 'md/4.4-rc6-fix' of git://neil.brown.name/md

Pull md bugfix from Neil Brown:
 "One more md fix for 4.4-rc

  Fix a regression which causes reshape to not start properly sometimes"

* tag 'md/4.4-rc6-fix' of git://neil.brown.name/md:
  md: remove check for MD_RECOVERY_NEEDED in action_store.
diff --git a/Makefile b/Makefile
index bc0165d..4e2b18d 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 4
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
 NAME = Blurry Fish Butt
 
 # *DOCUMENTATION*
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index cf0cf34..aeb1902 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -81,7 +81,7 @@
 LIBGCC	:= $(shell $(CC) $(cflags-y) --print-libgcc-file-name)
 
 # Modules with short calls might break for calls into builtin-kernel
-KBUILD_CFLAGS_MODULE	+= -mlong-calls
+KBUILD_CFLAGS_MODULE	+= -mlong-calls -mno-millicode
 
 # Finally dump eveything into kernel build system
 KBUILD_CFLAGS	+= $(cflags-y)
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index abf06e8..210ef3e 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -62,9 +62,7 @@
 #define ARC_REG_IC_IVIC		0x10
 #define ARC_REG_IC_CTRL		0x11
 #define ARC_REG_IC_IVIL		0x19
-#if defined(CONFIG_ARC_MMU_V3) || defined(CONFIG_ARC_MMU_V4)
 #define ARC_REG_IC_PTAG		0x1E
-#endif
 #define ARC_REG_IC_PTAG_HI	0x1F
 
 /* Bit val in IC_CTRL */
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index cf2828a..5eb7076 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -293,13 +293,13 @@
 		const u32 *cie = cie_for_fde(fde, table);
 		signed ptrType;
 
-		if (cie == &not_fde)	/* only process FDE here */
+		if (cie == &not_fde)
 			continue;
 		if (cie == NULL || cie == &bad_cie)
-			continue;	/* say FDE->CIE.version != 1 */
+			goto ret_err;
 		ptrType = fde_pointer_type(cie);
 		if (ptrType < 0)
-			continue;
+			goto ret_err;
 
 		ptr = (const u8 *)(fde + 2);
 		if (!read_pointer(&ptr, (const u8 *)(fde + 1) + *fde,
@@ -315,14 +315,14 @@
 	}
 
 	if (tableSize || !n)
-		return;
+		goto ret_err;
 
 	hdrSize = 4 + sizeof(unsigned long) + sizeof(unsigned int)
 	    + 2 * n * sizeof(unsigned long);
 
 	header = alloc(hdrSize);
 	if (!header)
-		return;
+		goto ret_err;
 
 	header->version = 1;
 	header->eh_frame_ptr_enc = DW_EH_PE_abs | DW_EH_PE_native;
@@ -343,10 +343,6 @@
 
 		if (fde[1] == 0xffffffff)
 			continue;	/* this is a CIE */
-
-		if (*(u8 *)(cie + 2) != 1)
-			continue;	/* FDE->CIE.version not supported */
-
 		ptr = (const u8 *)(fde + 2);
 		header->table[n].start = read_pointer(&ptr,
 						      (const u8 *)(fde + 1) +
@@ -365,6 +361,10 @@
 	table->hdrsz = hdrSize;
 	smp_wmb();
 	table->header = (const void *)header;
+	return;
+
+ret_err:
+	panic("Attention !!! Dwarf FDE parsing errors\n");;
 }
 
 #ifdef CONFIG_MODULES
@@ -523,8 +523,7 @@
 
 	if (*cie <= sizeof(*cie) + 4 || *cie >= fde[1] - sizeof(*fde)
 	    || (*cie & (sizeof(*cie) - 1))
-	    || (cie[1] != 0xffffffff)
-	    || ( *(u8 *)(cie + 2) != 1))   /* version 1 supported */
+	    || (cie[1] != 0xffffffff))
 		return NULL;	/* this is not a (valid) CIE */
 	return cie;
 }
@@ -605,9 +604,6 @@
 	const u8 *ptr = (const u8 *)(cie + 2);
 	unsigned version = *ptr;
 
-	if (version != 1)
-		return -1;	/* unsupported */
-
 	if (*++ptr) {
 		const char *aug;
 		const u8 *end = (const u8 *)(cie + 1) + *cie;
@@ -1019,9 +1015,7 @@
 		ptr = (const u8 *)(cie + 2);
 		end = (const u8 *)(cie + 1) + *cie;
 		frame->call_frame = 1;
-		if ((state.version = *ptr) != 1)
-			cie = NULL;	/* unsupported version */
-		else if (*++ptr) {
+		if (*++ptr) {
 			/* check if augmentation size is first (thus present) */
 			if (*ptr == 'z') {
 				while (++ptr < end && *ptr) {
diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c
index 065ee6b..92dd92c 100644
--- a/arch/arc/mm/highmem.c
+++ b/arch/arc/mm/highmem.c
@@ -111,7 +111,7 @@
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
-noinline pte_t *alloc_kmap_pgtable(unsigned long kvaddr)
+static noinline pte_t * __init alloc_kmap_pgtable(unsigned long kvaddr)
 {
 	pgd_t *pgd_k;
 	pud_t *pud_k;
@@ -127,7 +127,7 @@
 	return pte_k;
 }
 
-void kmap_init(void)
+void __init kmap_init(void)
 {
 	/* Due to recursive include hell, we can't do this in processor.h */
 	BUILD_BUG_ON(PAGE_OFFSET < (VMALLOC_END + FIXMAP_SIZE + PKMAP_SIZE));
diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c
index dc1ea79..2264f68 100644
--- a/arch/parisc/kernel/signal.c
+++ b/arch/parisc/kernel/signal.c
@@ -435,6 +435,55 @@
 		regs->gr[28]);
 }
 
+/*
+ * Check how the syscall number gets loaded into %r20 within
+ * the delay branch in userspace and adjust as needed.
+ */
+
+static void check_syscallno_in_delay_branch(struct pt_regs *regs)
+{
+	u32 opcode, source_reg;
+	u32 __user *uaddr;
+	int err;
+
+	/* Usually we don't have to restore %r20 (the system call number)
+	 * because it gets loaded in the delay slot of the branch external
+	 * instruction via the ldi instruction.
+	 * In some cases a register-to-register copy instruction might have
+	 * been used instead, in which case we need to copy the syscall
+	 * number into the source register before returning to userspace.
+	 */
+
+	/* A syscall is just a branch, so all we have to do is fiddle the
+	 * return pointer so that the ble instruction gets executed again.
+	 */
+	regs->gr[31] -= 8; /* delayed branching */
+
+	/* Get assembler opcode of code in delay branch */
+	uaddr = (unsigned int *) ((regs->gr[31] & ~3) + 4);
+	err = get_user(opcode, uaddr);
+	if (err)
+		return;
+
+	/* Check if delay branch uses "ldi int,%r20" */
+	if ((opcode & 0xffff0000) == 0x34140000)
+		return;	/* everything ok, just return */
+
+	/* Check if delay branch uses "nop" */
+	if (opcode == INSN_NOP)
+		return;
+
+	/* Check if delay branch uses "copy %rX,%r20" */
+	if ((opcode & 0xffe0ffff) == 0x08000254) {
+		source_reg = (opcode >> 16) & 31;
+		regs->gr[source_reg] = regs->gr[20];
+		return;
+	}
+
+	pr_warn("syscall restart: %s (pid %d): unexpected opcode 0x%08x\n",
+		current->comm, task_pid_nr(current), opcode);
+}
+
 static inline void
 syscall_restart(struct pt_regs *regs, struct k_sigaction *ka)
 {
@@ -457,10 +506,7 @@
 		}
 		/* fallthrough */
 	case -ERESTARTNOINTR:
-		/* A syscall is just a branch, so all
-		 * we have to do is fiddle the return pointer.
-		 */
-		regs->gr[31] -= 8; /* delayed branching */
+		check_syscallno_in_delay_branch(regs);
 		break;
 	}
 }
@@ -510,15 +556,9 @@
 	}
 	case -ERESTARTNOHAND:
 	case -ERESTARTSYS:
-	case -ERESTARTNOINTR: {
-		/* Hooray for delayed branching.  We don't
-		 * have to restore %r20 (the system call
-		 * number) because it gets loaded in the delay
-		 * slot of the branch external instruction.
-		 */
-		regs->gr[31] -= 8;
+	case -ERESTARTNOINTR:
+		check_syscallno_in_delay_branch(regs);
 		return;
-	}
 	default:
 		break;
 	}
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 54b45b7..a7352b5 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -224,6 +224,12 @@
 
 static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
 {
+	/*
+	 * Check for illegal transactional state bit combination
+	 * and if we find it, force the TS field to a safe state.
+	 */
+	if ((msr & MSR_TS_MASK) == MSR_TS_MASK)
+		msr &= ~MSR_TS_MASK;
 	vcpu->arch.shregs.msr = msr;
 	kvmppc_end_cede(vcpu);
 }
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 8140d10..6e72961 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -1920,16 +1920,23 @@
 			}
 			if (separator)
 				ptr += sprintf(ptr, "%c", separator);
+			/*
+			 * Use four '%' characters below because of the
+			 * following two conversions:
+			 *
+			 *  1) sprintf: %%%%r -> %%r
+			 *  2) printk : %%r   -> %r
+			 */
 			if (operand->flags & OPERAND_GPR)
-				ptr += sprintf(ptr, "%%r%i", value);
+				ptr += sprintf(ptr, "%%%%r%i", value);
 			else if (operand->flags & OPERAND_FPR)
-				ptr += sprintf(ptr, "%%f%i", value);
+				ptr += sprintf(ptr, "%%%%f%i", value);
 			else if (operand->flags & OPERAND_AR)
-				ptr += sprintf(ptr, "%%a%i", value);
+				ptr += sprintf(ptr, "%%%%a%i", value);
 			else if (operand->flags & OPERAND_CR)
-				ptr += sprintf(ptr, "%%c%i", value);
+				ptr += sprintf(ptr, "%%%%c%i", value);
 			else if (operand->flags & OPERAND_VR)
-				ptr += sprintf(ptr, "%%v%i", value);
+				ptr += sprintf(ptr, "%%%%v%i", value);
 			else if (operand->flags & OPERAND_PCREL)
 				ptr += sprintf(ptr, "%lx", (signed int) value
 								      + addr);
diff --git a/arch/sparc/include/asm/elf_64.h b/arch/sparc/include/asm/elf_64.h
index 370ca1e..9331083 100644
--- a/arch/sparc/include/asm/elf_64.h
+++ b/arch/sparc/include/asm/elf_64.h
@@ -95,6 +95,7 @@
  * really available.  So we simply advertise only "crypto" support.
  */
 #define HWCAP_SPARC_CRYPTO	0x04000000 /* CRYPTO insns available */
+#define HWCAP_SPARC_ADI		0x08000000 /* ADI available */
 
 #define CORE_DUMP_USE_REGSET
 
diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h
index efe9479..f31a124 100644
--- a/arch/sparc/include/uapi/asm/unistd.h
+++ b/arch/sparc/include/uapi/asm/unistd.h
@@ -417,8 +417,9 @@
 #define __NR_bpf		349
 #define __NR_execveat		350
 #define __NR_membarrier		351
+#define __NR_userfaultfd	352
 
-#define NR_syscalls		352
+#define NR_syscalls		353
 
 /* Bitmask values returned from kern_features system call.  */
 #define KERN_FEATURE_MIXED_MODE_STACK	0x00000001
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 3d61fca..f2d30ca 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -946,6 +946,12 @@
 	 mov	1, %o0
 ENDPROC(__retl_one)
 
+ENTRY(__retl_one_fp)
+	VISExitHalf
+	retl
+	 mov	1, %o0
+ENDPROC(__retl_one_fp)
+
 ENTRY(__ret_one_asi)
 	wr	%g0, ASI_AIUS, %asi
 	ret
@@ -958,6 +964,13 @@
 	 mov	1, %o0
 ENDPROC(__retl_one_asi)
 
+ENTRY(__retl_one_asi_fp)
+	wr	%g0, ASI_AIUS, %asi
+	VISExitHalf
+	retl
+	 mov	1, %o0
+ENDPROC(__retl_one_asi_fp)
+
 ENTRY(__retl_o1)
 	retl
 	 mov	%o1, %o0
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 3091267..6596f66 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1828,11 +1828,18 @@
 void
 perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
+	u64 saved_fault_address = current_thread_info()->fault_address;
+	u8 saved_fault_code = get_thread_fault_code();
+	mm_segment_t old_fs;
+
 	perf_callchain_store(entry, regs->tpc);
 
 	if (!current->mm)
 		return;
 
+	old_fs = get_fs();
+	set_fs(USER_DS);
+
 	flushw_user();
 
 	pagefault_disable();
@@ -1843,4 +1850,8 @@
 		perf_callchain_user_64(entry, regs);
 
 	pagefault_enable();
+
+	set_fs(old_fs);
+	set_thread_fault_code(saved_fault_code);
+	current_thread_info()->fault_address = saved_fault_address;
 }
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index 39f0c66..d08bdaf 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -73,7 +73,13 @@
 		andn			%l1, %l4, %l1
 		srl			%l4, 20, %l4
 		ba,pt			%xcc, rtrap_no_irq_enable
-		 wrpr			%l4, %pil
+		nop
+		/* Do not actually set the %pil here.  We will do that
+		 * below after we clear PSTATE_IE in the %pstate register.
+		 * If we re-enable interrupts here, we can recurse down
+		 * the hardirq stack potentially endlessly, causing a
+		 * stack overflow.
+		 */
 
 		.align			64
 		.globl			rtrap_irq, rtrap, irqsz_patchme, rtrap_xcall
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index f7b2617..f3185e2 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -380,7 +380,8 @@
 	 */
 	"mul32", "div32", "fsmuld", "v8plus", "popc", "vis", "vis2",
 	"ASIBlkInit", "fmaf", "vis3", "hpc", "random", "trans", "fjfmau",
-	"ima", "cspare", "pause", "cbcond",
+	"ima", "cspare", "pause", "cbcond", NULL /*reserved for crypto */,
+	"adp",
 };
 
 static const char *crypto_hwcaps[] = {
@@ -396,7 +397,7 @@
 	seq_puts(m, "cpucaps\t\t: ");
 	for (i = 0; i < ARRAY_SIZE(hwcaps); i++) {
 		unsigned long bit = 1UL << i;
-		if (caps & bit) {
+		if (hwcaps[i] && (caps & bit)) {
 			seq_printf(m, "%s%s",
 				   printed ? "," : "", hwcaps[i]);
 			printed++;
@@ -450,7 +451,7 @@
 
 	for (i = 0; i < ARRAY_SIZE(hwcaps); i++) {
 		unsigned long bit = 1UL << i;
-		if (caps & bit)
+		if (hwcaps[i] && (caps & bit))
 			report_one_hwcap(&printed, hwcaps[i]);
 	}
 	if (caps & HWCAP_SPARC_CRYPTO)
@@ -485,7 +486,7 @@
 		for (i = 0; i < ARRAY_SIZE(hwcaps); i++) {
 			unsigned long bit = 1UL << i;
 
-			if (!strcmp(prop, hwcaps[i])) {
+			if (hwcaps[i] && !strcmp(prop, hwcaps[i])) {
 				caps |= bit;
 				break;
 			}
diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S
index cc23b62..78e8029 100644
--- a/arch/sparc/kernel/systbls_32.S
+++ b/arch/sparc/kernel/systbls_32.S
@@ -87,4 +87,4 @@
 /*335*/	.long sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev
 /*340*/	.long sys_ni_syscall, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
 /*345*/	.long sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
-/*350*/	.long sys_execveat, sys_membarrier
+/*350*/	.long sys_execveat, sys_membarrier, sys_userfaultfd
diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S
index f229468..2549c2c 100644
--- a/arch/sparc/kernel/systbls_64.S
+++ b/arch/sparc/kernel/systbls_64.S
@@ -88,7 +88,7 @@
 	.word sys_syncfs, compat_sys_sendmmsg, sys_setns, compat_sys_process_vm_readv, compat_sys_process_vm_writev
 /*340*/	.word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
 	.word sys32_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
-/*350*/	.word sys32_execveat, sys_membarrier
+/*350*/	.word sys32_execveat, sys_membarrier, sys_userfaultfd
 
 #endif /* CONFIG_COMPAT */
 
@@ -168,4 +168,4 @@
 	.word sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev
 /*340*/	.word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
 	.word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
-/*350*/	.word sys64_execveat, sys_membarrier
+/*350*/	.word sys64_execveat, sys_membarrier, sys_userfaultfd
diff --git a/arch/sparc/lib/NG2copy_from_user.S b/arch/sparc/lib/NG2copy_from_user.S
index 119ccb9..d5242b8 100644
--- a/arch/sparc/lib/NG2copy_from_user.S
+++ b/arch/sparc/lib/NG2copy_from_user.S
@@ -11,6 +11,14 @@
 	.text;			\
 	.align 4;
 
+#define EX_LD_FP(x)		\
+98:	x;			\
+	.section __ex_table,"a";\
+	.align 4;		\
+	.word 98b, __retl_one_asi_fp;\
+	.text;			\
+	.align 4;
+
 #ifndef ASI_AIUS
 #define ASI_AIUS	0x11
 #endif
diff --git a/arch/sparc/lib/NG2copy_to_user.S b/arch/sparc/lib/NG2copy_to_user.S
index 7fe1cce..4e962d9 100644
--- a/arch/sparc/lib/NG2copy_to_user.S
+++ b/arch/sparc/lib/NG2copy_to_user.S
@@ -11,6 +11,14 @@
 	.text;			\
 	.align 4;
 
+#define EX_ST_FP(x)		\
+98:	x;			\
+	.section __ex_table,"a";\
+	.align 4;		\
+	.word 98b, __retl_one_asi_fp;\
+	.text;			\
+	.align 4;
+
 #ifndef ASI_AIUS
 #define ASI_AIUS	0x11
 #endif
diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S
index 30eee6e..d5f585d 100644
--- a/arch/sparc/lib/NG2memcpy.S
+++ b/arch/sparc/lib/NG2memcpy.S
@@ -34,10 +34,16 @@
 #ifndef EX_LD
 #define EX_LD(x)	x
 #endif
+#ifndef EX_LD_FP
+#define EX_LD_FP(x)	x
+#endif
 
 #ifndef EX_ST
 #define EX_ST(x)	x
 #endif
+#ifndef EX_ST_FP
+#define EX_ST_FP(x)	x
+#endif
 
 #ifndef EX_RETVAL
 #define EX_RETVAL(x)	x
@@ -134,40 +140,40 @@
 	fsrc2		%x6, %f12; \
 	fsrc2		%x7, %f14;
 #define FREG_LOAD_1(base, x0) \
-	EX_LD(LOAD(ldd, base + 0x00, %x0))
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0))
 #define FREG_LOAD_2(base, x0, x1) \
-	EX_LD(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD(LOAD(ldd, base + 0x08, %x1));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1));
 #define FREG_LOAD_3(base, x0, x1, x2) \
-	EX_LD(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD(LOAD(ldd, base + 0x10, %x2));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2));
 #define FREG_LOAD_4(base, x0, x1, x2, x3) \
-	EX_LD(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD(LOAD(ldd, base + 0x10, %x2)); \
-	EX_LD(LOAD(ldd, base + 0x18, %x3));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
+	EX_LD_FP(LOAD(ldd, base + 0x18, %x3));
 #define FREG_LOAD_5(base, x0, x1, x2, x3, x4) \
-	EX_LD(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD(LOAD(ldd, base + 0x10, %x2)); \
-	EX_LD(LOAD(ldd, base + 0x18, %x3)); \
-	EX_LD(LOAD(ldd, base + 0x20, %x4));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
+	EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \
+	EX_LD_FP(LOAD(ldd, base + 0x20, %x4));
 #define FREG_LOAD_6(base, x0, x1, x2, x3, x4, x5) \
-	EX_LD(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD(LOAD(ldd, base + 0x10, %x2)); \
-	EX_LD(LOAD(ldd, base + 0x18, %x3)); \
-	EX_LD(LOAD(ldd, base + 0x20, %x4)); \
-	EX_LD(LOAD(ldd, base + 0x28, %x5));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
+	EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \
+	EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \
+	EX_LD_FP(LOAD(ldd, base + 0x28, %x5));
 #define FREG_LOAD_7(base, x0, x1, x2, x3, x4, x5, x6) \
-	EX_LD(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD(LOAD(ldd, base + 0x10, %x2)); \
-	EX_LD(LOAD(ldd, base + 0x18, %x3)); \
-	EX_LD(LOAD(ldd, base + 0x20, %x4)); \
-	EX_LD(LOAD(ldd, base + 0x28, %x5)); \
-	EX_LD(LOAD(ldd, base + 0x30, %x6));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
+	EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \
+	EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \
+	EX_LD_FP(LOAD(ldd, base + 0x28, %x5)); \
+	EX_LD_FP(LOAD(ldd, base + 0x30, %x6));
 
 	.register	%g2,#scratch
 	.register	%g3,#scratch
@@ -275,11 +281,11 @@
 	 nop
 	/* fall through for 0 < low bits < 8 */
 110:	sub		%o4, 64, %g2
-	EX_LD(LOAD_BLK(%g2, %f0))
-1:	EX_ST(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD(LOAD_BLK(%o4, %f16))
+	EX_LD_FP(LOAD_BLK(%g2, %f0))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f16))
 	FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f14, f16)
-	EX_ST(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
 	FREG_MOVE_8(f16, f18, f20, f22, f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -290,10 +296,10 @@
 
 120:	sub		%o4, 56, %g2
 	FREG_LOAD_7(%g2, f0, f2, f4, f6, f8, f10, f12)
-1:	EX_ST(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f16))
 	FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f16, f18)
-	EX_ST(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
 	FREG_MOVE_7(f18, f20, f22, f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -304,10 +310,10 @@
 
 130:	sub		%o4, 48, %g2
 	FREG_LOAD_6(%g2, f0, f2, f4, f6, f8, f10)
-1:	EX_ST(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f16))
 	FREG_FROB(f0, f2, f4, f6, f8, f10, f16, f18, f20)
-	EX_ST(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
 	FREG_MOVE_6(f20, f22, f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -318,10 +324,10 @@
 
 140:	sub		%o4, 40, %g2
 	FREG_LOAD_5(%g2, f0, f2, f4, f6, f8)
-1:	EX_ST(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f16))
 	FREG_FROB(f0, f2, f4, f6, f8, f16, f18, f20, f22)
-	EX_ST(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
 	FREG_MOVE_5(f22, f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -332,10 +338,10 @@
 
 150:	sub		%o4, 32, %g2
 	FREG_LOAD_4(%g2, f0, f2, f4, f6)
-1:	EX_ST(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f16))
 	FREG_FROB(f0, f2, f4, f6, f16, f18, f20, f22, f24)
-	EX_ST(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
 	FREG_MOVE_4(f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -346,10 +352,10 @@
 
 160:	sub		%o4, 24, %g2
 	FREG_LOAD_3(%g2, f0, f2, f4)
-1:	EX_ST(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f16))
 	FREG_FROB(f0, f2, f4, f16, f18, f20, f22, f24, f26)
-	EX_ST(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
 	FREG_MOVE_3(f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -360,10 +366,10 @@
 
 170:	sub		%o4, 16, %g2
 	FREG_LOAD_2(%g2, f0, f2)
-1:	EX_ST(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f16))
 	FREG_FROB(f0, f2, f16, f18, f20, f22, f24, f26, f28)
-	EX_ST(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
 	FREG_MOVE_2(f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -374,10 +380,10 @@
 
 180:	sub		%o4, 8, %g2
 	FREG_LOAD_1(%g2, f0)
-1:	EX_ST(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f16))
 	FREG_FROB(f0, f16, f18, f20, f22, f24, f26, f28, f30)
-	EX_ST(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
 	FREG_MOVE_1(f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -387,10 +393,10 @@
 	 nop
 
 190:
-1:	EX_ST(STORE_INIT(%g0, %o4 + %g3))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
 	subcc		%g1, 64, %g1
-	EX_LD(LOAD_BLK(%o4, %f0))
-	EX_ST(STORE_BLK(%f0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f0))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
 	add		%o4, 64, %o4
 	bne,pt		%xcc, 1b
 	 LOAD(prefetch, %o4 + 64, #one_read)
diff --git a/arch/sparc/lib/NG4copy_from_user.S b/arch/sparc/lib/NG4copy_from_user.S
index fd9f903..2e8ee7a 100644
--- a/arch/sparc/lib/NG4copy_from_user.S
+++ b/arch/sparc/lib/NG4copy_from_user.S
@@ -11,6 +11,14 @@
 	.text;			\
 	.align 4;
 
+#define EX_LD_FP(x)		\
+98:	x;			\
+	.section __ex_table,"a";\
+	.align 4;		\
+	.word 98b, __retl_one_asi_fp;\
+	.text;			\
+	.align 4;
+
 #ifndef ASI_AIUS
 #define ASI_AIUS	0x11
 #endif
diff --git a/arch/sparc/lib/NG4copy_to_user.S b/arch/sparc/lib/NG4copy_to_user.S
index 9744c454..be0bf45 100644
--- a/arch/sparc/lib/NG4copy_to_user.S
+++ b/arch/sparc/lib/NG4copy_to_user.S
@@ -11,6 +11,14 @@
 	.text;			\
 	.align 4;
 
+#define EX_ST_FP(x)		\
+98:	x;			\
+	.section __ex_table,"a";\
+	.align 4;		\
+	.word 98b, __retl_one_asi_fp;\
+	.text;			\
+	.align 4;
+
 #ifndef ASI_AIUS
 #define ASI_AIUS	0x11
 #endif
diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S
index 83aeeb1..8e13ee1 100644
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -48,10 +48,16 @@
 #ifndef EX_LD
 #define EX_LD(x)	x
 #endif
+#ifndef EX_LD_FP
+#define EX_LD_FP(x)	x
+#endif
 
 #ifndef EX_ST
 #define EX_ST(x)	x
 #endif
+#ifndef EX_ST_FP
+#define EX_ST_FP(x)	x
+#endif
 
 #ifndef EX_RETVAL
 #define EX_RETVAL(x)	x
@@ -210,17 +216,17 @@
 	sub		%o2, %o4, %o2
 	alignaddr	%o1, %g0, %g1
 	add		%o1, %o4, %o1
-	EX_LD(LOAD(ldd, %g1 + 0x00, %f0))
-1:	EX_LD(LOAD(ldd, %g1 + 0x08, %f2))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0))
+1:	EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2))
 	subcc		%o4, 0x40, %o4
-	EX_LD(LOAD(ldd, %g1 + 0x10, %f4))
-	EX_LD(LOAD(ldd, %g1 + 0x18, %f6))
-	EX_LD(LOAD(ldd, %g1 + 0x20, %f8))
-	EX_LD(LOAD(ldd, %g1 + 0x28, %f10))
-	EX_LD(LOAD(ldd, %g1 + 0x30, %f12))
-	EX_LD(LOAD(ldd, %g1 + 0x38, %f14))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14))
 	faligndata	%f0, %f2, %f16
-	EX_LD(LOAD(ldd, %g1 + 0x40, %f0))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0))
 	faligndata	%f2, %f4, %f18
 	add		%g1, 0x40, %g1
 	faligndata	%f4, %f6, %f20
@@ -229,14 +235,14 @@
 	faligndata	%f10, %f12, %f26
 	faligndata	%f12, %f14, %f28
 	faligndata	%f14, %f0, %f30
-	EX_ST(STORE(std, %f16, %o0 + 0x00))
-	EX_ST(STORE(std, %f18, %o0 + 0x08))
-	EX_ST(STORE(std, %f20, %o0 + 0x10))
-	EX_ST(STORE(std, %f22, %o0 + 0x18))
-	EX_ST(STORE(std, %f24, %o0 + 0x20))
-	EX_ST(STORE(std, %f26, %o0 + 0x28))
-	EX_ST(STORE(std, %f28, %o0 + 0x30))
-	EX_ST(STORE(std, %f30, %o0 + 0x38))
+	EX_ST_FP(STORE(std, %f16, %o0 + 0x00))
+	EX_ST_FP(STORE(std, %f18, %o0 + 0x08))
+	EX_ST_FP(STORE(std, %f20, %o0 + 0x10))
+	EX_ST_FP(STORE(std, %f22, %o0 + 0x18))
+	EX_ST_FP(STORE(std, %f24, %o0 + 0x20))
+	EX_ST_FP(STORE(std, %f26, %o0 + 0x28))
+	EX_ST_FP(STORE(std, %f28, %o0 + 0x30))
+	EX_ST_FP(STORE(std, %f30, %o0 + 0x38))
 	add		%o0, 0x40, %o0
 	bne,pt		%icc, 1b
 	 LOAD(prefetch, %g1 + 0x200, #n_reads_strong)
diff --git a/arch/sparc/lib/U1copy_from_user.S b/arch/sparc/lib/U1copy_from_user.S
index a6ae2ea..ecc5692 100644
--- a/arch/sparc/lib/U1copy_from_user.S
+++ b/arch/sparc/lib/U1copy_from_user.S
@@ -11,6 +11,14 @@
 	.text;			\
 	.align 4;
 
+#define EX_LD_FP(x)		\
+98:	x;			\
+	.section __ex_table,"a";\
+	.align 4;		\
+	.word 98b, __retl_one_fp;\
+	.text;			\
+	.align 4;
+
 #define FUNC_NAME		___copy_from_user
 #define LOAD(type,addr,dest)	type##a [addr] %asi, dest
 #define LOAD_BLK(addr,dest)	ldda [addr] ASI_BLK_AIUS, dest
diff --git a/arch/sparc/lib/U1copy_to_user.S b/arch/sparc/lib/U1copy_to_user.S
index f4b970e..9eea392 100644
--- a/arch/sparc/lib/U1copy_to_user.S
+++ b/arch/sparc/lib/U1copy_to_user.S
@@ -11,6 +11,14 @@
 	.text;			\
 	.align 4;
 
+#define EX_ST_FP(x)		\
+98:	x;			\
+	.section __ex_table,"a";\
+	.align 4;		\
+	.word 98b, __retl_one_fp;\
+	.text;			\
+	.align 4;
+
 #define FUNC_NAME		___copy_to_user
 #define STORE(type,src,addr)	type##a src, [addr] ASI_AIUS
 #define STORE_BLK(src,addr)	stda src, [addr] ASI_BLK_AIUS
diff --git a/arch/sparc/lib/U1memcpy.S b/arch/sparc/lib/U1memcpy.S
index b67142b..3e6209e 100644
--- a/arch/sparc/lib/U1memcpy.S
+++ b/arch/sparc/lib/U1memcpy.S
@@ -25,10 +25,16 @@
 #ifndef EX_LD
 #define EX_LD(x)	x
 #endif
+#ifndef EX_LD_FP
+#define EX_LD_FP(x)	x
+#endif
 
 #ifndef EX_ST
 #define EX_ST(x)	x
 #endif
+#ifndef EX_ST_FP
+#define EX_ST_FP(x)	x
+#endif
 
 #ifndef EX_RETVAL
 #define EX_RETVAL(x)	x
@@ -73,8 +79,8 @@
 	faligndata		%f8, %f9, %f62;
 
 #define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, len, jmptgt)	\
-	EX_LD(LOAD_BLK(%src, %fdest));				\
-	EX_ST(STORE_BLK(%fsrc, %dest));				\
+	EX_LD_FP(LOAD_BLK(%src, %fdest));				\
+	EX_ST_FP(STORE_BLK(%fsrc, %dest));				\
 	add			%src, 0x40, %src;		\
 	subcc			%len, 0x40, %len;		\
 	be,pn			%xcc, jmptgt;			\
@@ -89,12 +95,12 @@
 
 #define DO_SYNC			membar	#Sync;
 #define STORE_SYNC(dest, fsrc)				\
-	EX_ST(STORE_BLK(%fsrc, %dest));			\
+	EX_ST_FP(STORE_BLK(%fsrc, %dest));			\
 	add			%dest, 0x40, %dest;	\
 	DO_SYNC
 
 #define STORE_JUMP(dest, fsrc, target)			\
-	EX_ST(STORE_BLK(%fsrc, %dest));			\
+	EX_ST_FP(STORE_BLK(%fsrc, %dest));			\
 	add			%dest, 0x40, %dest;	\
 	ba,pt			%xcc, target;		\
 	 nop;
@@ -103,7 +109,7 @@
 	subcc			%left, 8, %left;\
 	bl,pn			%xcc, 95f;	\
 	 faligndata		%f0, %f1, %f48;	\
-	EX_ST(STORE(std, %f48, %dest));		\
+	EX_ST_FP(STORE(std, %f48, %dest));		\
 	add			%dest, 8, %dest;
 
 #define UNEVEN_VISCHUNK_LAST(dest, f0, f1, left)	\
@@ -160,8 +166,8 @@
 	 and		%g2, 0x38, %g2
 
 1:	subcc		%g1, 0x1, %g1
-	EX_LD(LOAD(ldub, %o1 + 0x00, %o3))
-	EX_ST(STORE(stb, %o3, %o1 + %GLOBAL_SPARE))
+	EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3))
+	EX_ST_FP(STORE(stb, %o3, %o1 + %GLOBAL_SPARE))
 	bgu,pt		%XCC, 1b
 	 add		%o1, 0x1, %o1
 
@@ -172,20 +178,20 @@
 	be,pt		%icc, 3f
 	 alignaddr	%o1, %g0, %o1
 
-	EX_LD(LOAD(ldd, %o1, %f4))
-1:	EX_LD(LOAD(ldd, %o1 + 0x8, %f6))
+	EX_LD_FP(LOAD(ldd, %o1, %f4))
+1:	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6))
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f4, %f6, %f0
-	EX_ST(STORE(std, %f0, %o0))
+	EX_ST_FP(STORE(std, %f0, %o0))
 	be,pn		%icc, 3f
 	 add		%o0, 0x8, %o0
 
-	EX_LD(LOAD(ldd, %o1 + 0x8, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4))
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f6, %f4, %f0
-	EX_ST(STORE(std, %f0, %o0))
+	EX_ST_FP(STORE(std, %f0, %o0))
 	bne,pt		%icc, 1b
 	 add		%o0, 0x8, %o0
 
@@ -208,13 +214,13 @@
 	add		%g1, %GLOBAL_SPARE, %g1
 	subcc		%o2, %g3, %o2
 
-	EX_LD(LOAD_BLK(%o1, %f0))
+	EX_LD_FP(LOAD_BLK(%o1, %f0))
 	add		%o1, 0x40, %o1
 	add		%g1, %g3, %g1
-	EX_LD(LOAD_BLK(%o1, %f16))
+	EX_LD_FP(LOAD_BLK(%o1, %f16))
 	add		%o1, 0x40, %o1
 	sub		%GLOBAL_SPARE, 0x80, %GLOBAL_SPARE
-	EX_LD(LOAD_BLK(%o1, %f32))
+	EX_LD_FP(LOAD_BLK(%o1, %f32))
 	add		%o1, 0x40, %o1
 
 	/* There are 8 instances of the unrolled loop,
@@ -426,28 +432,28 @@
 62:	FINISH_VISCHUNK(o0, f44, f46, g3)
 63:	UNEVEN_VISCHUNK_LAST(o0, f46, f0,  g3)
 
-93:	EX_LD(LOAD(ldd, %o1, %f2))
+93:	EX_LD_FP(LOAD(ldd, %o1, %f2))
 	add		%o1, 8, %o1
 	subcc		%g3, 8, %g3
 	faligndata	%f0, %f2, %f8
-	EX_ST(STORE(std, %f8, %o0))
+	EX_ST_FP(STORE(std, %f8, %o0))
 	bl,pn		%xcc, 95f
 	 add		%o0, 8, %o0
-	EX_LD(LOAD(ldd, %o1, %f0))
+	EX_LD_FP(LOAD(ldd, %o1, %f0))
 	add		%o1, 8, %o1
 	subcc		%g3, 8, %g3
 	faligndata	%f2, %f0, %f8
-	EX_ST(STORE(std, %f8, %o0))
+	EX_ST_FP(STORE(std, %f8, %o0))
 	bge,pt		%xcc, 93b
 	 add		%o0, 8, %o0
 
 95:	brz,pt		%o2, 2f
 	 mov		%g1, %o1
 
-1:	EX_LD(LOAD(ldub, %o1, %o3))
+1:	EX_LD_FP(LOAD(ldub, %o1, %o3))
 	add		%o1, 1, %o1
 	subcc		%o2, 1, %o2
-	EX_ST(STORE(stb, %o3, %o0))
+	EX_ST_FP(STORE(stb, %o3, %o0))
 	bne,pt		%xcc, 1b
 	 add		%o0, 1, %o0
 
diff --git a/arch/sparc/lib/U3copy_from_user.S b/arch/sparc/lib/U3copy_from_user.S
index b1acd13..88ad73d 100644
--- a/arch/sparc/lib/U3copy_from_user.S
+++ b/arch/sparc/lib/U3copy_from_user.S
@@ -11,6 +11,14 @@
 	.text;			\
 	.align 4;
 
+#define EX_LD_FP(x)		\
+98:	x;			\
+	.section __ex_table,"a";\
+	.align 4;		\
+	.word 98b, __retl_one_fp;\
+	.text;			\
+	.align 4;
+
 #define FUNC_NAME		U3copy_from_user
 #define LOAD(type,addr,dest)	type##a [addr] %asi, dest
 #define EX_RETVAL(x)		0
diff --git a/arch/sparc/lib/U3copy_to_user.S b/arch/sparc/lib/U3copy_to_user.S
index ef1e493..845139d 100644
--- a/arch/sparc/lib/U3copy_to_user.S
+++ b/arch/sparc/lib/U3copy_to_user.S
@@ -11,6 +11,14 @@
 	.text;			\
 	.align 4;
 
+#define EX_ST_FP(x)		\
+98:	x;			\
+	.section __ex_table,"a";\
+	.align 4;		\
+	.word 98b, __retl_one_fp;\
+	.text;			\
+	.align 4;
+
 #define FUNC_NAME		U3copy_to_user
 #define STORE(type,src,addr)	type##a src, [addr] ASI_AIUS
 #define STORE_BLK(src,addr)	stda src, [addr] ASI_BLK_AIUS
diff --git a/arch/sparc/lib/U3memcpy.S b/arch/sparc/lib/U3memcpy.S
index 7cae9cc..491ee69 100644
--- a/arch/sparc/lib/U3memcpy.S
+++ b/arch/sparc/lib/U3memcpy.S
@@ -24,10 +24,16 @@
 #ifndef EX_LD
 #define EX_LD(x)	x
 #endif
+#ifndef EX_LD_FP
+#define EX_LD_FP(x)	x
+#endif
 
 #ifndef EX_ST
 #define EX_ST(x)	x
 #endif
+#ifndef EX_ST_FP
+#define EX_ST_FP(x)	x
+#endif
 
 #ifndef EX_RETVAL
 #define EX_RETVAL(x)	x
@@ -120,8 +126,8 @@
 	 and		%g2, 0x38, %g2
 
 1:	subcc		%g1, 0x1, %g1
-	EX_LD(LOAD(ldub, %o1 + 0x00, %o3))
-	EX_ST(STORE(stb, %o3, %o1 + GLOBAL_SPARE))
+	EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3))
+	EX_ST_FP(STORE(stb, %o3, %o1 + GLOBAL_SPARE))
 	bgu,pt		%XCC, 1b
 	 add		%o1, 0x1, %o1
 
@@ -132,20 +138,20 @@
 	be,pt		%icc, 3f
 	 alignaddr	%o1, %g0, %o1
 
-	EX_LD(LOAD(ldd, %o1, %f4))
-1:	EX_LD(LOAD(ldd, %o1 + 0x8, %f6))
+	EX_LD_FP(LOAD(ldd, %o1, %f4))
+1:	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6))
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f4, %f6, %f0
-	EX_ST(STORE(std, %f0, %o0))
+	EX_ST_FP(STORE(std, %f0, %o0))
 	be,pn		%icc, 3f
 	 add		%o0, 0x8, %o0
 
-	EX_LD(LOAD(ldd, %o1 + 0x8, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4))
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f6, %f4, %f2
-	EX_ST(STORE(std, %f2, %o0))
+	EX_ST_FP(STORE(std, %f2, %o0))
 	bne,pt		%icc, 1b
 	 add		%o0, 0x8, %o0
 
@@ -155,25 +161,25 @@
 	LOAD(prefetch, %o1 + 0x080, #one_read)
 	LOAD(prefetch, %o1 + 0x0c0, #one_read)
 	LOAD(prefetch, %o1 + 0x100, #one_read)
-	EX_LD(LOAD(ldd, %o1 + 0x000, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x000, %f0))
 	LOAD(prefetch, %o1 + 0x140, #one_read)
-	EX_LD(LOAD(ldd, %o1 + 0x008, %f2))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2))
 	LOAD(prefetch, %o1 + 0x180, #one_read)
-	EX_LD(LOAD(ldd, %o1 + 0x010, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4))
 	LOAD(prefetch, %o1 + 0x1c0, #one_read)
 	faligndata	%f0, %f2, %f16
-	EX_LD(LOAD(ldd, %o1 + 0x018, %f6))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6))
 	faligndata	%f2, %f4, %f18
-	EX_LD(LOAD(ldd, %o1 + 0x020, %f8))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8))
 	faligndata	%f4, %f6, %f20
-	EX_LD(LOAD(ldd, %o1 + 0x028, %f10))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10))
 	faligndata	%f6, %f8, %f22
 
-	EX_LD(LOAD(ldd, %o1 + 0x030, %f12))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12))
 	faligndata	%f8, %f10, %f24
-	EX_LD(LOAD(ldd, %o1 + 0x038, %f14))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14))
 	faligndata	%f10, %f12, %f26
-	EX_LD(LOAD(ldd, %o1 + 0x040, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0))
 
 	subcc		GLOBAL_SPARE, 0x80, GLOBAL_SPARE
 	add		%o1, 0x40, %o1
@@ -184,26 +190,26 @@
 
 	.align		64
 1:
-	EX_LD(LOAD(ldd, %o1 + 0x008, %f2))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2))
 	faligndata	%f12, %f14, %f28
-	EX_LD(LOAD(ldd, %o1 + 0x010, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4))
 	faligndata	%f14, %f0, %f30
-	EX_ST(STORE_BLK(%f16, %o0))
-	EX_LD(LOAD(ldd, %o1 + 0x018, %f6))
+	EX_ST_FP(STORE_BLK(%f16, %o0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6))
 	faligndata	%f0, %f2, %f16
 	add		%o0, 0x40, %o0
 
-	EX_LD(LOAD(ldd, %o1 + 0x020, %f8))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8))
 	faligndata	%f2, %f4, %f18
-	EX_LD(LOAD(ldd, %o1 + 0x028, %f10))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10))
 	faligndata	%f4, %f6, %f20
-	EX_LD(LOAD(ldd, %o1 + 0x030, %f12))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12))
 	subcc		%o3, 0x01, %o3
 	faligndata	%f6, %f8, %f22
-	EX_LD(LOAD(ldd, %o1 + 0x038, %f14))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14))
 
 	faligndata	%f8, %f10, %f24
-	EX_LD(LOAD(ldd, %o1 + 0x040, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0))
 	LOAD(prefetch, %o1 + 0x1c0, #one_read)
 	faligndata	%f10, %f12, %f26
 	bg,pt		%XCC, 1b
@@ -211,29 +217,29 @@
 
 	/* Finally we copy the last full 64-byte block. */
 2:
-	EX_LD(LOAD(ldd, %o1 + 0x008, %f2))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2))
 	faligndata	%f12, %f14, %f28
-	EX_LD(LOAD(ldd, %o1 + 0x010, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4))
 	faligndata	%f14, %f0, %f30
-	EX_ST(STORE_BLK(%f16, %o0))
-	EX_LD(LOAD(ldd, %o1 + 0x018, %f6))
+	EX_ST_FP(STORE_BLK(%f16, %o0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6))
 	faligndata	%f0, %f2, %f16
-	EX_LD(LOAD(ldd, %o1 + 0x020, %f8))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8))
 	faligndata	%f2, %f4, %f18
-	EX_LD(LOAD(ldd, %o1 + 0x028, %f10))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10))
 	faligndata	%f4, %f6, %f20
-	EX_LD(LOAD(ldd, %o1 + 0x030, %f12))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12))
 	faligndata	%f6, %f8, %f22
-	EX_LD(LOAD(ldd, %o1 + 0x038, %f14))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14))
 	faligndata	%f8, %f10, %f24
 	cmp		%g1, 0
 	be,pt		%XCC, 1f
 	 add		%o0, 0x40, %o0
-	EX_LD(LOAD(ldd, %o1 + 0x040, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0))
 1:	faligndata	%f10, %f12, %f26
 	faligndata	%f12, %f14, %f28
 	faligndata	%f14, %f0, %f30
-	EX_ST(STORE_BLK(%f16, %o0))
+	EX_ST_FP(STORE_BLK(%f16, %o0))
 	add		%o0, 0x40, %o0
 	add		%o1, 0x40, %o1
 	membar		#Sync
@@ -253,20 +259,20 @@
 
 	sub		%o2, %g2, %o2
 	be,a,pt		%XCC, 1f
-	 EX_LD(LOAD(ldd, %o1 + 0x00, %f0))
+	 EX_LD_FP(LOAD(ldd, %o1 + 0x00, %f0))
 
-1:	EX_LD(LOAD(ldd, %o1 + 0x08, %f2))
+1:	EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f2))
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f0, %f2, %f8
-	EX_ST(STORE(std, %f8, %o0))
+	EX_ST_FP(STORE(std, %f8, %o0))
 	be,pn		%XCC, 2f
 	 add		%o0, 0x8, %o0
-	EX_LD(LOAD(ldd, %o1 + 0x08, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f0))
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f2, %f0, %f8
-	EX_ST(STORE(std, %f8, %o0))
+	EX_ST_FP(STORE(std, %f8, %o0))
 	bne,pn		%XCC, 1b
 	 add		%o0, 0x8, %o0
 
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 06332cb..3f5c48d 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -38,6 +38,14 @@
 	return best && (best->ecx & bit(X86_FEATURE_XSAVE));
 }
 
+static inline bool guest_cpuid_has_mtrr(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 1, 0);
+	return best && (best->edx & bit(X86_FEATURE_MTRR));
+}
+
 static inline bool guest_cpuid_has_tsc_adjust(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index 9e8bf13..3f8c732 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -120,14 +120,22 @@
 	return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK;
 }
 
-static u8 mtrr_disabled_type(void)
+static u8 mtrr_disabled_type(struct kvm_vcpu *vcpu)
 {
 	/*
 	 * Intel SDM 11.11.2.2: all MTRRs are disabled when
 	 * IA32_MTRR_DEF_TYPE.E bit is cleared, and the UC
 	 * memory type is applied to all of physical memory.
+	 *
+	 * However, virtual machines can be run with CPUID such that
+	 * there are no MTRRs.  In that case, the firmware will never
+	 * enable MTRRs and it is obviously undesirable to run the
+	 * guest entirely with UC memory and we use WB.
 	 */
-	return MTRR_TYPE_UNCACHABLE;
+	if (guest_cpuid_has_mtrr(vcpu))
+		return MTRR_TYPE_UNCACHABLE;
+	else
+		return MTRR_TYPE_WRBACK;
 }
 
 /*
@@ -267,7 +275,7 @@
 
 	for (seg = 0; seg < seg_num; seg++) {
 		mtrr_seg = &fixed_seg_table[seg];
-		if (mtrr_seg->start >= addr && addr < mtrr_seg->end)
+		if (mtrr_seg->start <= addr && addr < mtrr_seg->end)
 			return seg;
 	}
 
@@ -300,7 +308,6 @@
 	*start = range->base & PAGE_MASK;
 
 	mask = range->mask & PAGE_MASK;
-	mask |= ~0ULL << boot_cpu_data.x86_phys_bits;
 
 	/* This cannot overflow because writing to the reserved bits of
 	 * variable MTRRs causes a #GP.
@@ -356,10 +363,14 @@
 	if (var_mtrr_range_is_valid(cur))
 		list_del(&mtrr_state->var_ranges[index].node);
 
+	/* Extend the mask with all 1 bits to the left, since those
+	 * bits must implicitly be 0.  The bits are then cleared
+	 * when reading them.
+	 */
 	if (!is_mtrr_mask)
 		cur->base = data;
 	else
-		cur->mask = data;
+		cur->mask = data | (-1LL << cpuid_maxphyaddr(vcpu));
 
 	/* add it to the list if it's enabled. */
 	if (var_mtrr_range_is_valid(cur)) {
@@ -426,6 +437,8 @@
 			*pdata = vcpu->arch.mtrr_state.var_ranges[index].base;
 		else
 			*pdata = vcpu->arch.mtrr_state.var_ranges[index].mask;
+
+		*pdata &= (1ULL << cpuid_maxphyaddr(vcpu)) - 1;
 	}
 
 	return 0;
@@ -670,7 +683,7 @@
 	}
 
 	if (iter.mtrr_disabled)
-		return mtrr_disabled_type();
+		return mtrr_disabled_type(vcpu);
 
 	/* not contained in any MTRRs. */
 	if (type == -1)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 83a1c64..899c40f 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3422,6 +3422,8 @@
 	struct kvm_run *kvm_run = vcpu->run;
 	u32 exit_code = svm->vmcb->control.exit_code;
 
+	trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM);
+
 	if (!is_cr_intercept(svm, INTERCEPT_CR0_WRITE))
 		vcpu->arch.cr0 = svm->vmcb->save.cr0;
 	if (npt_enabled)
@@ -3892,8 +3894,6 @@
 	vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp;
 	vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip;
 
-	trace_kvm_exit(svm->vmcb->control.exit_code, vcpu, KVM_ISA_SVM);
-
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
 		kvm_before_handle_nmi(&svm->vcpu);
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index af823a3..44976a5 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2803,7 +2803,7 @@
 		msr_info->data = vcpu->arch.ia32_xss;
 		break;
 	case MSR_TSC_AUX:
-		if (!guest_cpuid_has_rdtscp(vcpu))
+		if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated)
 			return 1;
 		/* Otherwise falls through */
 	default:
@@ -2909,7 +2909,7 @@
 			clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
 		break;
 	case MSR_TSC_AUX:
-		if (!guest_cpuid_has_rdtscp(vcpu))
+		if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated)
 			return 1;
 		/* Check reserved bit, higher 32 bits should be zero */
 		if ((data >> 32) != 0)
@@ -8042,6 +8042,8 @@
 	u32 exit_reason = vmx->exit_reason;
 	u32 vectoring_info = vmx->idt_vectoring_info;
 
+	trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX);
+
 	/*
 	 * Flush logged GPAs PML buffer, this will make dirty_bitmap more
 	 * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before
@@ -8668,7 +8670,6 @@
 	vmx->loaded_vmcs->launched = 1;
 
 	vmx->exit_reason = vmcs_read32(VM_EXIT_REASON);
-	trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX);
 
 	/*
 	 * the KVM_REQ_EVENT optimization bit is only on for one entry, and if
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index eed3228..7ffc224 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3572,9 +3572,11 @@
 
 static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
 {
+	int i;
 	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state));
-	kvm_pit_load_count(kvm, 0, ps->channels[0].count, 0);
+	for (i = 0; i < 3; i++)
+		kvm_pit_load_count(kvm, i, ps->channels[i].count, 0);
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 	return 0;
 }
@@ -3593,6 +3595,7 @@
 static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
 {
 	int start = 0;
+	int i;
 	u32 prev_legacy, cur_legacy;
 	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
@@ -3602,7 +3605,8 @@
 	memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels,
 	       sizeof(kvm->arch.vpit->pit_state.channels));
 	kvm->arch.vpit->pit_state.flags = ps->flags;
-	kvm_pit_load_count(kvm, 0, kvm->arch.vpit->pit_state.channels[0].count, start);
+	for (i = 0; i < 3; i++)
+		kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count, start);
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 	return 0;
 }
@@ -6515,6 +6519,8 @@
 	if (req_immediate_exit)
 		smp_send_reschedule(vcpu->cpu);
 
+	trace_kvm_entry(vcpu->vcpu_id);
+	wait_lapic_expire(vcpu);
 	__kvm_guest_enter();
 
 	if (unlikely(vcpu->arch.switch_db_regs)) {
@@ -6527,8 +6533,6 @@
 		vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD;
 	}
 
-	trace_kvm_entry(vcpu->vcpu_id);
-	wait_lapic_expire(vcpu);
 	kvm_x86_ops->run(vcpu);
 
 	/*
diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c
index e5f854c..14fcd01 100644
--- a/arch/x86/um/signal.c
+++ b/arch/x86/um/signal.c
@@ -470,7 +470,7 @@
 	struct sigcontext __user *sc = &frame->sc;
 	int sig_size = (_NSIG_WORDS - 1) * sizeof(unsigned long);
 
-	if (copy_from_user(&set.sig[0], (void *)sc->oldmask, sizeof(set.sig[0])) ||
+	if (copy_from_user(&set.sig[0], &sc->oldmask, sizeof(set.sig[0])) ||
 	    copy_from_user(&set.sig[1], frame->extramask, sig_size))
 		goto segfault;
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 3636be4..c487b94 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1689,8 +1689,6 @@
 	struct request *req;
 	unsigned int request_count = 0;
 
-	blk_queue_split(q, &bio, q->bio_split);
-
 	/*
 	 * low level driver can indicate that it wants pages above a
 	 * certain limit bounced to low memory (ie for highmem, or even
@@ -1698,6 +1696,8 @@
 	 */
 	blk_queue_bounce(q, &bio);
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
 		bio->bi_error = -EIO;
 		bio_endio(bio);
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 8162475..a428e4e 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -219,6 +219,9 @@
 {
 	struct request_queue *q = NULL;
 
+	if (cmd->rq)
+		q = cmd->rq->q;
+
 	switch (queue_mode)  {
 	case NULL_Q_MQ:
 		blk_mq_end_request(cmd->rq, 0);
@@ -232,9 +235,6 @@
 		goto free_cmd;
 	}
 
-	if (cmd->rq)
-		q = cmd->rq->q;
-
 	/* Restart queue if needed, as we are freeing a tag */
 	if (q && !q->mq_ops && blk_queue_stopped(q)) {
 		unsigned long flags;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 5a5f04d..048cfe0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1264,7 +1264,8 @@
 	struct ww_acquire_ctx	ticket;
 
 	/* user fence */
-	struct amdgpu_user_fence uf;
+	struct amdgpu_user_fence	uf;
+	struct amdgpu_bo_list_entry	uf_entry;
 };
 
 struct amdgpu_job {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 4f352ec..25a3e248 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -127,6 +127,37 @@
 	return 0;
 }
 
+static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p,
+				      struct drm_amdgpu_cs_chunk_fence *fence_data)
+{
+	struct drm_gem_object *gobj;
+	uint32_t handle;
+
+	handle = fence_data->handle;
+	gobj = drm_gem_object_lookup(p->adev->ddev, p->filp,
+				     fence_data->handle);
+	if (gobj == NULL)
+		return -EINVAL;
+
+	p->uf.bo = amdgpu_bo_ref(gem_to_amdgpu_bo(gobj));
+	p->uf.offset = fence_data->offset;
+
+	if (amdgpu_ttm_tt_has_userptr(p->uf.bo->tbo.ttm)) {
+		drm_gem_object_unreference_unlocked(gobj);
+		return -EINVAL;
+	}
+
+	p->uf_entry.robj = amdgpu_bo_ref(p->uf.bo);
+	p->uf_entry.prefered_domains = AMDGPU_GEM_DOMAIN_GTT;
+	p->uf_entry.allowed_domains = AMDGPU_GEM_DOMAIN_GTT;
+	p->uf_entry.priority = 0;
+	p->uf_entry.tv.bo = &p->uf_entry.robj->tbo;
+	p->uf_entry.tv.shared = true;
+
+	drm_gem_object_unreference_unlocked(gobj);
+	return 0;
+}
+
 int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 {
 	union drm_amdgpu_cs *cs = data;
@@ -207,28 +238,15 @@
 
 		case AMDGPU_CHUNK_ID_FENCE:
 			size = sizeof(struct drm_amdgpu_cs_chunk_fence);
-			if (p->chunks[i].length_dw * sizeof(uint32_t) >= size) {
-				uint32_t handle;
-				struct drm_gem_object *gobj;
-				struct drm_amdgpu_cs_chunk_fence *fence_data;
-
-				fence_data = (void *)p->chunks[i].kdata;
-				handle = fence_data->handle;
-				gobj = drm_gem_object_lookup(p->adev->ddev,
-							     p->filp, handle);
-				if (gobj == NULL) {
-					ret = -EINVAL;
-					goto free_partial_kdata;
-				}
-
-				p->uf.bo = gem_to_amdgpu_bo(gobj);
-				amdgpu_bo_ref(p->uf.bo);
-				drm_gem_object_unreference_unlocked(gobj);
-				p->uf.offset = fence_data->offset;
-			} else {
+			if (p->chunks[i].length_dw * sizeof(uint32_t) < size) {
 				ret = -EINVAL;
 				goto free_partial_kdata;
 			}
+
+			ret = amdgpu_cs_user_fence_chunk(p, (void *)p->chunks[i].kdata);
+			if (ret)
+				goto free_partial_kdata;
+
 			break;
 
 		case AMDGPU_CHUNK_ID_DEPENDENCIES:
@@ -391,6 +409,9 @@
 	p->vm_bos = amdgpu_vm_get_bos(p->adev, &fpriv->vm,
 				      &p->validated);
 
+	if (p->uf.bo)
+		list_add(&p->uf_entry.tv.head, &p->validated);
+
 	if (need_mmap_lock)
 		down_read(&current->mm->mmap_sem);
 
@@ -488,8 +509,8 @@
 		for (i = 0; i < parser->num_ibs; i++)
 			amdgpu_ib_free(parser->adev, &parser->ibs[i]);
 	kfree(parser->ibs);
-	if (parser->uf.bo)
-		amdgpu_bo_unref(&parser->uf.bo);
+	amdgpu_bo_unref(&parser->uf.bo);
+	amdgpu_bo_unref(&parser->uf_entry.robj);
 }
 
 static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
index b3ba27f..e693571 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
@@ -55,6 +55,9 @@
 {
 	struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
 
+	if (!state->enable)
+		return 0;
+
 	if (exynos_crtc->ops->atomic_check)
 		return exynos_crtc->ops->atomic_check(exynos_crtc, state);
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index a01e515..f4af19a 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2193,8 +2193,17 @@
 	struct drm_i915_private *i915;
 	struct intel_engine_cs *ring;
 
-	/** GEM sequence number associated with this request. */
-	uint32_t seqno;
+	 /** GEM sequence number associated with the previous request,
+	  * when the HWS breadcrumb is equal to this the GPU is processing
+	  * this request.
+	  */
+	u32 previous_seqno;
+
+	 /** GEM sequence number associated with this request,
+	  * when the HWS breadcrumb is equal or greater than this the GPU
+	  * has finished processing this request.
+	  */
+	u32 seqno;
 
 	/** Position in the ringbuffer of the start of the request */
 	u32 head;
@@ -2839,6 +2848,7 @@
 
 int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
 		  u32 flags);
+void __i915_vma_set_map_and_fenceable(struct i915_vma *vma);
 int __must_check i915_vma_unbind(struct i915_vma *vma);
 /*
  * BEWARE: Do not use the function below unless you can _absolutely_
@@ -2910,15 +2920,17 @@
 	return (int32_t)(seq1 - seq2) >= 0;
 }
 
+static inline bool i915_gem_request_started(struct drm_i915_gem_request *req,
+					   bool lazy_coherency)
+{
+	u32 seqno = req->ring->get_seqno(req->ring, lazy_coherency);
+	return i915_seqno_passed(seqno, req->previous_seqno);
+}
+
 static inline bool i915_gem_request_completed(struct drm_i915_gem_request *req,
 					      bool lazy_coherency)
 {
-	u32 seqno;
-
-	BUG_ON(req == NULL);
-
-	seqno = req->ring->get_seqno(req->ring, lazy_coherency);
-
+	u32 seqno = req->ring->get_seqno(req->ring, lazy_coherency);
 	return i915_seqno_passed(seqno, req->seqno);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 32e6aad..f56af0a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1146,23 +1146,74 @@
 	return test_bit(ring->id, &dev_priv->gpu_error.missed_irq_rings);
 }
 
-static int __i915_spin_request(struct drm_i915_gem_request *req)
+static unsigned long local_clock_us(unsigned *cpu)
+{
+	unsigned long t;
+
+	/* Cheaply and approximately convert from nanoseconds to microseconds.
+	 * The result and subsequent calculations are also defined in the same
+	 * approximate microseconds units. The principal source of timing
+	 * error here is from the simple truncation.
+	 *
+	 * Note that local_clock() is only defined wrt to the current CPU;
+	 * the comparisons are no longer valid if we switch CPUs. Instead of
+	 * blocking preemption for the entire busywait, we can detect the CPU
+	 * switch and use that as indicator of system load and a reason to
+	 * stop busywaiting, see busywait_stop().
+	 */
+	*cpu = get_cpu();
+	t = local_clock() >> 10;
+	put_cpu();
+
+	return t;
+}
+
+static bool busywait_stop(unsigned long timeout, unsigned cpu)
+{
+	unsigned this_cpu;
+
+	if (time_after(local_clock_us(&this_cpu), timeout))
+		return true;
+
+	return this_cpu != cpu;
+}
+
+static int __i915_spin_request(struct drm_i915_gem_request *req, int state)
 {
 	unsigned long timeout;
+	unsigned cpu;
 
-	if (i915_gem_request_get_ring(req)->irq_refcount)
+	/* When waiting for high frequency requests, e.g. during synchronous
+	 * rendering split between the CPU and GPU, the finite amount of time
+	 * required to set up the irq and wait upon it limits the response
+	 * rate. By busywaiting on the request completion for a short while we
+	 * can service the high frequency waits as quick as possible. However,
+	 * if it is a slow request, we want to sleep as quickly as possible.
+	 * The tradeoff between waiting and sleeping is roughly the time it
+	 * takes to sleep on a request, on the order of a microsecond.
+	 */
+
+	if (req->ring->irq_refcount)
 		return -EBUSY;
 
-	timeout = jiffies + 1;
+	/* Only spin if we know the GPU is processing this request */
+	if (!i915_gem_request_started(req, true))
+		return -EAGAIN;
+
+	timeout = local_clock_us(&cpu) + 5;
 	while (!need_resched()) {
 		if (i915_gem_request_completed(req, true))
 			return 0;
 
-		if (time_after_eq(jiffies, timeout))
+		if (signal_pending_state(state, current))
+			break;
+
+		if (busywait_stop(timeout, cpu))
 			break;
 
 		cpu_relax_lowlatency();
 	}
+
 	if (i915_gem_request_completed(req, false))
 		return 0;
 
@@ -1197,6 +1248,7 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	const bool irq_test_in_progress =
 		ACCESS_ONCE(dev_priv->gpu_error.test_irq_rings) & intel_ring_flag(ring);
+	int state = interruptible ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE;
 	DEFINE_WAIT(wait);
 	unsigned long timeout_expire;
 	s64 before, now;
@@ -1229,7 +1281,7 @@
 	before = ktime_get_raw_ns();
 
 	/* Optimistic spin for the next jiffie before touching IRQs */
-	ret = __i915_spin_request(req);
+	ret = __i915_spin_request(req, state);
 	if (ret == 0)
 		goto out;
 
@@ -1241,8 +1293,7 @@
 	for (;;) {
 		struct timer_list timer;
 
-		prepare_to_wait(&ring->irq_queue, &wait,
-				interruptible ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
+		prepare_to_wait(&ring->irq_queue, &wait, state);
 
 		/* We need to check whether any gpu reset happened in between
 		 * the caller grabbing the seqno and now ... */
@@ -1260,7 +1311,7 @@
 			break;
 		}
 
-		if (interruptible && signal_pending(current)) {
+		if (signal_pending_state(state, current)) {
 			ret = -ERESTARTSYS;
 			break;
 		}
@@ -2554,6 +2605,7 @@
 	request->batch_obj = obj;
 
 	request->emitted_jiffies = jiffies;
+	request->previous_seqno = ring->last_submitted_seqno;
 	ring->last_submitted_seqno = request->seqno;
 	list_add_tail(&request->list, &ring->request_list);
 
@@ -4080,6 +4132,29 @@
 	return false;
 }
 
+void __i915_vma_set_map_and_fenceable(struct i915_vma *vma)
+{
+	struct drm_i915_gem_object *obj = vma->obj;
+	bool mappable, fenceable;
+	u32 fence_size, fence_alignment;
+
+	fence_size = i915_gem_get_gtt_size(obj->base.dev,
+					   obj->base.size,
+					   obj->tiling_mode);
+	fence_alignment = i915_gem_get_gtt_alignment(obj->base.dev,
+						     obj->base.size,
+						     obj->tiling_mode,
+						     true);
+
+	fenceable = (vma->node.size == fence_size &&
+		     (vma->node.start & (fence_alignment - 1)) == 0);
+
+	mappable = (vma->node.start + fence_size <=
+		    to_i915(obj->base.dev)->gtt.mappable_end);
+
+	obj->map_and_fenceable = mappable && fenceable;
+}
+
 static int
 i915_gem_object_do_pin(struct drm_i915_gem_object *obj,
 		       struct i915_address_space *vm,
@@ -4147,25 +4222,7 @@
 
 	if (ggtt_view && ggtt_view->type == I915_GGTT_VIEW_NORMAL &&
 	    (bound ^ vma->bound) & GLOBAL_BIND) {
-		bool mappable, fenceable;
-		u32 fence_size, fence_alignment;
-
-		fence_size = i915_gem_get_gtt_size(obj->base.dev,
-						   obj->base.size,
-						   obj->tiling_mode);
-		fence_alignment = i915_gem_get_gtt_alignment(obj->base.dev,
-							     obj->base.size,
-							     obj->tiling_mode,
-							     true);
-
-		fenceable = (vma->node.size == fence_size &&
-			     (vma->node.start & (fence_alignment - 1)) == 0);
-
-		mappable = (vma->node.start + fence_size <=
-			    dev_priv->gtt.mappable_end);
-
-		obj->map_and_fenceable = mappable && fenceable;
-
+		__i915_vma_set_map_and_fenceable(vma);
 		WARN_ON(flags & PIN_MAPPABLE && !obj->map_and_fenceable);
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 43f35d1..86c7500 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2676,6 +2676,7 @@
 			return ret;
 		}
 		vma->bound |= GLOBAL_BIND;
+		__i915_vma_set_map_and_fenceable(vma);
 		list_add_tail(&vma->mm_list, &ggtt_vm->inactive_list);
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index cdacf3f..87e919a 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -687,6 +687,7 @@
 		}
 
 		vma->bound |= GLOBAL_BIND;
+		__i915_vma_set_map_and_fenceable(vma);
 		list_add_tail(&vma->mm_list, &ggtt->inactive_list);
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 62211ab..beb0374 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -116,6 +116,7 @@
 static void ironlake_pfit_disable(struct intel_crtc *crtc, bool force);
 static void ironlake_pfit_enable(struct intel_crtc *crtc);
 static void intel_modeset_setup_hw_state(struct drm_device *dev);
+static void intel_pre_disable_primary(struct drm_crtc *crtc);
 
 typedef struct {
 	int	min, max;
@@ -2607,6 +2608,8 @@
 	struct drm_i915_gem_object *obj;
 	struct drm_plane *primary = intel_crtc->base.primary;
 	struct drm_plane_state *plane_state = primary->state;
+	struct drm_crtc_state *crtc_state = intel_crtc->base.state;
+	struct intel_plane *intel_plane = to_intel_plane(primary);
 	struct drm_framebuffer *fb;
 
 	if (!plane_config->fb)
@@ -2643,6 +2646,18 @@
 		}
 	}
 
+	/*
+	 * We've failed to reconstruct the BIOS FB.  Current display state
+	 * indicates that the primary plane is visible, but has a NULL FB,
+	 * which will lead to problems later if we don't fix it up.  The
+	 * simplest solution is to just disable the primary plane now and
+	 * pretend the BIOS never had it enabled.
+	 */
+	to_intel_plane_state(plane_state)->visible = false;
+	crtc_state->plane_mask &= ~(1 << drm_plane_index(primary));
+	intel_pre_disable_primary(&intel_crtc->base);
+	intel_plane->disable_plane(primary, &intel_crtc->base);
+
 	return;
 
 valid_fb:
@@ -9910,14 +9925,14 @@
 	return true;
 }
 
-static void i845_update_cursor(struct drm_crtc *crtc, u32 base)
+static void i845_update_cursor(struct drm_crtc *crtc, u32 base, bool on)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	uint32_t cntl = 0, size = 0;
 
-	if (base) {
+	if (on) {
 		unsigned int width = intel_crtc->base.cursor->state->crtc_w;
 		unsigned int height = intel_crtc->base.cursor->state->crtc_h;
 		unsigned int stride = roundup_pow_of_two(width) * 4;
@@ -9972,16 +9987,15 @@
 	}
 }
 
-static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base)
+static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base, bool on)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
-	uint32_t cntl;
+	uint32_t cntl = 0;
 
-	cntl = 0;
-	if (base) {
+	if (on) {
 		cntl = MCURSOR_GAMMA_ENABLE;
 		switch (intel_crtc->base.cursor->state->crtc_w) {
 			case 64:
@@ -10032,18 +10046,17 @@
 	int y = cursor_state->crtc_y;
 	u32 base = 0, pos = 0;
 
-	if (on)
-		base = intel_crtc->cursor_addr;
+	base = intel_crtc->cursor_addr;
 
 	if (x >= intel_crtc->config->pipe_src_w)
-		base = 0;
+		on = false;
 
 	if (y >= intel_crtc->config->pipe_src_h)
-		base = 0;
+		on = false;
 
 	if (x < 0) {
 		if (x + cursor_state->crtc_w <= 0)
-			base = 0;
+			on = false;
 
 		pos |= CURSOR_POS_SIGN << CURSOR_X_SHIFT;
 		x = -x;
@@ -10052,16 +10065,13 @@
 
 	if (y < 0) {
 		if (y + cursor_state->crtc_h <= 0)
-			base = 0;
+			on = false;
 
 		pos |= CURSOR_POS_SIGN << CURSOR_Y_SHIFT;
 		y = -y;
 	}
 	pos |= y << CURSOR_Y_SHIFT;
 
-	if (base == 0 && intel_crtc->cursor_base == 0)
-		return;
-
 	I915_WRITE(CURPOS(pipe), pos);
 
 	/* ILK+ do this automagically */
@@ -10072,9 +10082,9 @@
 	}
 
 	if (IS_845G(dev) || IS_I865G(dev))
-		i845_update_cursor(crtc, base);
+		i845_update_cursor(crtc, base, on);
 	else
-		i9xx_update_cursor(crtc, base);
+		i9xx_update_cursor(crtc, base, on);
 }
 
 static bool cursor_size_ok(struct drm_device *dev,
@@ -13718,6 +13728,7 @@
 	struct drm_crtc *crtc = crtc_state->base.crtc;
 	struct drm_framebuffer *fb = state->base.fb;
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
+	enum pipe pipe = to_intel_plane(plane)->pipe;
 	unsigned stride;
 	int ret;
 
@@ -13751,6 +13762,22 @@
 		return -EINVAL;
 	}
 
+	/*
+	 * There's something wrong with the cursor on CHV pipe C.
+	 * If it straddles the left edge of the screen then
+	 * moving it away from the edge or disabling it often
+	 * results in a pipe underrun, and often that can lead to
+	 * dead pipe (constant underrun reported, and it scans
+	 * out just a solid color). To recover from that, the
+	 * display power well must be turned off and on again.
+	 * Refuse the put the cursor into that compromised position.
+	 */
+	if (IS_CHERRYVIEW(plane->dev) && pipe == PIPE_C &&
+	    state->visible && state->base.crtc_x < 0) {
+		DRM_DEBUG_KMS("CHV cursor C not allowed to straddle the left screen edge\n");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -13774,9 +13801,6 @@
 	crtc = crtc ? crtc : plane->crtc;
 	intel_crtc = to_intel_crtc(crtc);
 
-	if (intel_crtc->cursor_bo == obj)
-		goto update;
-
 	if (!obj)
 		addr = 0;
 	else if (!INTEL_INFO(dev)->cursor_needs_physical)
@@ -13785,9 +13809,7 @@
 		addr = obj->phys_handle->busaddr;
 
 	intel_crtc->cursor_addr = addr;
-	intel_crtc->cursor_bo = obj;
 
-update:
 	if (crtc->state->active)
 		intel_crtc_update_cursor(crtc, state->visible);
 }
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index f2a1142..0d00f07 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -550,7 +550,6 @@
 	int adjusted_x;
 	int adjusted_y;
 
-	struct drm_i915_gem_object *cursor_bo;
 	uint32_t cursor_addr;
 	uint32_t cursor_cntl;
 	uint32_t cursor_size;
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 81cdd9f..64086f2 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -1374,17 +1374,18 @@
 	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	bool live_status = false;
-	unsigned int retry = 3;
+	unsigned int try;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
 		      connector->base.id, connector->name);
 
 	intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
 
-	while (!live_status && --retry) {
+	for (try = 0; !live_status && try < 4; try++) {
+		if (try)
+			msleep(10);
 		live_status = intel_digital_port_connected(dev_priv,
 				hdmi_to_dig_port(intel_hdmi));
-		mdelay(10);
 	}
 
 	if (!live_status)
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/fan.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/fan.c
index 43006db..80fed7e7 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/fan.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/fan.c
@@ -83,6 +83,7 @@
 			fan->type = NVBIOS_THERM_FAN_UNK;
 		}
 
+		fan->fan_mode = NVBIOS_THERM_FAN_LINEAR;
 		fan->min_duty = nvbios_rd08(bios, data + 0x02);
 		fan->max_duty = nvbios_rd08(bios, data + 0x03);
 
diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c
index b077e43..c4cb15a 100644
--- a/drivers/mtd/ubi/debug.c
+++ b/drivers/mtd/ubi/debug.c
@@ -236,7 +236,7 @@
 
 	dfs_rootdir = debugfs_create_dir("ubi", NULL);
 	if (IS_ERR_OR_NULL(dfs_rootdir)) {
-		int err = dfs_rootdir ? -ENODEV : PTR_ERR(dfs_rootdir);
+		int err = dfs_rootdir ? PTR_ERR(dfs_rootdir) : -ENODEV;
 
 		pr_err("UBI error: cannot create \"ubi\" debugfs directory, error %d\n",
 		       err);
diff --git a/drivers/mtd/ubi/io.c b/drivers/mtd/ubi/io.c
index 1fc23e4..10cf3b5 100644
--- a/drivers/mtd/ubi/io.c
+++ b/drivers/mtd/ubi/io.c
@@ -1299,7 +1299,7 @@
 	if (err && err != UBI_IO_BITFLIPS && !mtd_is_eccerr(err))
 		goto exit;
 
-	crc = crc32(UBI_CRC32_INIT, vid_hdr, UBI_EC_HDR_SIZE_CRC);
+	crc = crc32(UBI_CRC32_INIT, vid_hdr, UBI_VID_HDR_SIZE_CRC);
 	hdr_crc = be32_to_cpu(vid_hdr->hdr_crc);
 	if (hdr_crc != crc) {
 		ubi_err(ubi, "bad VID header CRC at PEB %d, calculated %#08x, read %#08x",
diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c
index eb4489f9..5606563 100644
--- a/drivers/mtd/ubi/wl.c
+++ b/drivers/mtd/ubi/wl.c
@@ -603,6 +603,7 @@
 	return 0;
 }
 
+static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk);
 /**
  * do_sync_erase - run the erase worker synchronously.
  * @ubi: UBI device description object
@@ -615,20 +616,16 @@
 static int do_sync_erase(struct ubi_device *ubi, struct ubi_wl_entry *e,
 			 int vol_id, int lnum, int torture)
 {
-	struct ubi_work *wl_wrk;
+	struct ubi_work wl_wrk;
 
 	dbg_wl("sync erase of PEB %i", e->pnum);
 
-	wl_wrk = kmalloc(sizeof(struct ubi_work), GFP_NOFS);
-	if (!wl_wrk)
-		return -ENOMEM;
+	wl_wrk.e = e;
+	wl_wrk.vol_id = vol_id;
+	wl_wrk.lnum = lnum;
+	wl_wrk.torture = torture;
 
-	wl_wrk->e = e;
-	wl_wrk->vol_id = vol_id;
-	wl_wrk->lnum = lnum;
-	wl_wrk->torture = torture;
-
-	return erase_worker(ubi, wl_wrk, 0);
+	return __erase_worker(ubi, &wl_wrk);
 }
 
 /**
@@ -1014,7 +1011,7 @@
 }
 
 /**
- * erase_worker - physical eraseblock erase worker function.
+ * __erase_worker - physical eraseblock erase worker function.
  * @ubi: UBI device description object
  * @wl_wrk: the work object
  * @shutdown: non-zero if the worker has to free memory and exit
@@ -1025,8 +1022,7 @@
  * needed. Returns zero in case of success and a negative error code in case of
  * failure.
  */
-static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk,
-			int shutdown)
+static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk)
 {
 	struct ubi_wl_entry *e = wl_wrk->e;
 	int pnum = e->pnum;
@@ -1034,21 +1030,11 @@
 	int lnum = wl_wrk->lnum;
 	int err, available_consumed = 0;
 
-	if (shutdown) {
-		dbg_wl("cancel erasure of PEB %d EC %d", pnum, e->ec);
-		kfree(wl_wrk);
-		wl_entry_destroy(ubi, e);
-		return 0;
-	}
-
 	dbg_wl("erase PEB %d EC %d LEB %d:%d",
 	       pnum, e->ec, wl_wrk->vol_id, wl_wrk->lnum);
 
 	err = sync_erase(ubi, e, wl_wrk->torture);
 	if (!err) {
-		/* Fine, we've erased it successfully */
-		kfree(wl_wrk);
-
 		spin_lock(&ubi->wl_lock);
 		wl_tree_add(e, &ubi->free);
 		ubi->free_count++;
@@ -1066,7 +1052,6 @@
 	}
 
 	ubi_err(ubi, "failed to erase PEB %d, error %d", pnum, err);
-	kfree(wl_wrk);
 
 	if (err == -EINTR || err == -ENOMEM || err == -EAGAIN ||
 	    err == -EBUSY) {
@@ -1075,6 +1060,7 @@
 		/* Re-schedule the LEB for erasure */
 		err1 = schedule_erase(ubi, e, vol_id, lnum, 0);
 		if (err1) {
+			wl_entry_destroy(ubi, e);
 			err = err1;
 			goto out_ro;
 		}
@@ -1150,6 +1136,25 @@
 	return err;
 }
 
+static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk,
+			  int shutdown)
+{
+	int ret;
+
+	if (shutdown) {
+		struct ubi_wl_entry *e = wl_wrk->e;
+
+		dbg_wl("cancel erasure of PEB %d EC %d", e->pnum, e->ec);
+		kfree(wl_wrk);
+		wl_entry_destroy(ubi, e);
+		return 0;
+	}
+
+	ret = __erase_worker(ubi, wl_wrk);
+	kfree(wl_wrk);
+	return ret;
+}
+
 /**
  * ubi_wl_put_peb - return a PEB to the wear-leveling sub-system.
  * @ubi: UBI device description object
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 9e294ff..0c67b57 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2540,8 +2540,17 @@
 {
 	bool kill = nvme_io_incapable(ns->dev) && !blk_queue_dying(ns->queue);
 
-	if (kill)
+	if (kill) {
 		blk_set_queue_dying(ns->queue);
+
+		/*
+		 * The controller was shutdown first if we got here through
+		 * device removal. The shutdown may requeue outstanding
+		 * requests. These need to be aborted immediately so
+		 * del_gendisk doesn't block indefinitely for their completion.
+		 */
+		blk_mq_abort_requeue_list(ns->queue);
+	}
 	if (ns->disk->flags & GENHD_FL_UP)
 		del_gendisk(ns->disk);
 	if (kill || !blk_queue_dying(ns->queue)) {
@@ -2977,6 +2986,15 @@
 {
 	struct nvme_ns *ns, *next;
 
+	if (nvme_io_incapable(dev)) {
+		/*
+		 * If the device is not capable of IO (surprise hot-removal,
+		 * for example), we need to quiesce prior to deleting the
+		 * namespaces. This will end outstanding requests and prevent
+		 * attempts to sync dirty data.
+		 */
+		nvme_dev_shutdown(dev);
+	}
 	list_for_each_entry_safe(ns, next, &dev->namespaces, list)
 		nvme_ns_remove(ns);
 }
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 61f7685..24ec282 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -599,8 +599,10 @@
 	status = ap_sm_recv(ap_dev);
 	switch (status.response_code) {
 	case AP_RESPONSE_NORMAL:
-		if (ap_dev->queue_count > 0)
+		if (ap_dev->queue_count > 0) {
+			ap_dev->state = AP_STATE_WORKING;
 			return AP_WAIT_AGAIN;
+		}
 		ap_dev->state = AP_STATE_IDLE;
 		return AP_WAIT_NONE;
 	case AP_RESPONSE_NO_PENDING_REPLY:
diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
index b2a1a81..1b83159 100644
--- a/drivers/s390/virtio/virtio_ccw.c
+++ b/drivers/s390/virtio/virtio_ccw.c
@@ -984,32 +984,9 @@
 	return vq;
 }
 
-static void virtio_ccw_int_handler(struct ccw_device *cdev,
-				   unsigned long intparm,
-				   struct irb *irb)
+static void virtio_ccw_check_activity(struct virtio_ccw_device *vcdev,
+				      __u32 activity)
 {
-	__u32 activity = intparm & VIRTIO_CCW_INTPARM_MASK;
-	struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev);
-	int i;
-	struct virtqueue *vq;
-
-	if (!vcdev)
-		return;
-	/* Check if it's a notification from the host. */
-	if ((intparm == 0) &&
-	    (scsw_stctl(&irb->scsw) ==
-	     (SCSW_STCTL_ALERT_STATUS | SCSW_STCTL_STATUS_PEND))) {
-		/* OK */
-	}
-	if (irb_is_error(irb)) {
-		/* Command reject? */
-		if ((scsw_dstat(&irb->scsw) & DEV_STAT_UNIT_CHECK) &&
-		    (irb->ecw[0] & SNS0_CMD_REJECT))
-			vcdev->err = -EOPNOTSUPP;
-		else
-			/* Map everything else to -EIO. */
-			vcdev->err = -EIO;
-	}
 	if (vcdev->curr_io & activity) {
 		switch (activity) {
 		case VIRTIO_CCW_DOING_READ_FEAT:
@@ -1029,12 +1006,47 @@
 			break;
 		default:
 			/* don't know what to do... */
-			dev_warn(&cdev->dev, "Suspicious activity '%08x'\n",
-				 activity);
+			dev_warn(&vcdev->cdev->dev,
+				 "Suspicious activity '%08x'\n", activity);
 			WARN_ON(1);
 			break;
 		}
 	}
+}
+
+static void virtio_ccw_int_handler(struct ccw_device *cdev,
+				   unsigned long intparm,
+				   struct irb *irb)
+{
+	__u32 activity = intparm & VIRTIO_CCW_INTPARM_MASK;
+	struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev);
+	int i;
+	struct virtqueue *vq;
+
+	if (!vcdev)
+		return;
+	if (IS_ERR(irb)) {
+		vcdev->err = PTR_ERR(irb);
+		virtio_ccw_check_activity(vcdev, activity);
+		/* Don't poke around indicators, something's wrong. */
+		return;
+	}
+	/* Check if it's a notification from the host. */
+	if ((intparm == 0) &&
+	    (scsw_stctl(&irb->scsw) ==
+	     (SCSW_STCTL_ALERT_STATUS | SCSW_STCTL_STATUS_PEND))) {
+		/* OK */
+	}
+	if (irb_is_error(irb)) {
+		/* Command reject? */
+		if ((scsw_dstat(&irb->scsw) & DEV_STAT_UNIT_CHECK) &&
+		    (irb->ecw[0] & SNS0_CMD_REJECT))
+			vcdev->err = -EOPNOTSUPP;
+		else
+			/* Map everything else to -EIO. */
+			vcdev->err = -EIO;
+	}
+	virtio_ccw_check_activity(vcdev, activity);
 	for_each_set_bit(i, &vcdev->indicators,
 			 sizeof(vcdev->indicators) * BITS_PER_BYTE) {
 		/* The bit clear must happen before the vring kick. */
diff --git a/drivers/tty/serial/sunhv.c b/drivers/tty/serial/sunhv.c
index 0640318..ca0d380 100644
--- a/drivers/tty/serial/sunhv.c
+++ b/drivers/tty/serial/sunhv.c
@@ -148,8 +148,10 @@
 			uart_handle_dcd_change(port, 1);
 		}
 
-		for (i = 0; i < bytes_read; i++)
-			uart_handle_sysrq_char(port, con_read_page[i]);
+		if (port->sysrq != 0 &&  *con_read_page) {
+			for (i = 0; i < bytes_read; i++)
+				uart_handle_sysrq_char(port, con_read_page[i]);
+		}
 
 		if (port->state == NULL)
 			continue;
@@ -168,17 +170,17 @@
 	int (*receive_chars)(struct uart_port *port);
 };
 
-static struct sunhv_ops bychar_ops = {
+static const struct sunhv_ops bychar_ops = {
 	.transmit_chars = transmit_chars_putchar,
 	.receive_chars = receive_chars_getchar,
 };
 
-static struct sunhv_ops bywrite_ops = {
+static const struct sunhv_ops bywrite_ops = {
 	.transmit_chars = transmit_chars_write,
 	.receive_chars = receive_chars_read,
 };
 
-static struct sunhv_ops *sunhv_ops = &bychar_ops;
+static const struct sunhv_ops *sunhv_ops = &bychar_ops;
 
 static struct tty_port *receive_chars(struct uart_port *port)
 {
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 9ffef06..c9d6c71 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -616,6 +616,7 @@
 
 	mutex_lock(&ls->ls_mutex);
 	nfs4_inc_and_copy_stateid(&ls->ls_recall_sid, &ls->ls_stid);
+	mutex_unlock(&ls->ls_mutex);
 }
 
 static int
@@ -659,7 +660,6 @@
 
 	trace_layout_recall_release(&ls->ls_stid.sc_stateid);
 
-	mutex_unlock(&ls->ls_mutex);
 	nfsd4_return_all_layouts(ls, &reaplist);
 	nfsd4_free_layouts(&reaplist);
 	nfs4_put_stid(&ls->ls_stid);
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index 698768b..301d70b 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -48,12 +48,17 @@
 
 static int fd_map;	/* File descriptor for file being modified. */
 static int mmap_failed; /* Boolean flag. */
-static void *ehdr_curr; /* current ElfXX_Ehdr *  for resource cleanup */
 static char gpfx;	/* prefix for global symbol name (sometimes '_') */
 static struct stat sb;	/* Remember .st_size, etc. */
 static jmp_buf jmpenv;	/* setjmp/longjmp per-file error escape */
 static const char *altmcount;	/* alternate mcount symbol name */
 static int warn_on_notrace_sect; /* warn when section has mcount not being recorded */
+static void *file_map;	/* pointer of the mapped file */
+static void *file_end;	/* pointer to the end of the mapped file */
+static int file_updated; /* flag to state file was changed */
+static void *file_ptr;	/* current file pointer location */
+static void *file_append; /* added to the end of the file */
+static size_t file_append_size; /* how much is added to end of file */
 
 /* setjmp() return values */
 enum {
@@ -67,10 +72,14 @@
 cleanup(void)
 {
 	if (!mmap_failed)
-		munmap(ehdr_curr, sb.st_size);
+		munmap(file_map, sb.st_size);
 	else
-		free(ehdr_curr);
-	close(fd_map);
+		free(file_map);
+	file_map = NULL;
+	free(file_append);
+	file_append = NULL;
+	file_append_size = 0;
+	file_updated = 0;
 }
 
 static void __attribute__((noreturn))
@@ -92,12 +101,22 @@
 static off_t
 ulseek(int const fd, off_t const offset, int const whence)
 {
-	off_t const w = lseek(fd, offset, whence);
-	if (w == (off_t)-1) {
-		perror("lseek");
+	switch (whence) {
+	case SEEK_SET:
+		file_ptr = file_map + offset;
+		break;
+	case SEEK_CUR:
+		file_ptr += offset;
+		break;
+	case SEEK_END:
+		file_ptr = file_map + (sb.st_size - offset);
+		break;
+	}
+	if (file_ptr < file_map) {
+		fprintf(stderr, "lseek: seek before file\n");
 		fail_file();
 	}
-	return w;
+	return file_ptr - file_map;
 }
 
 static size_t
@@ -114,12 +133,38 @@
 static size_t
 uwrite(int const fd, void const *const buf, size_t const count)
 {
-	size_t const n = write(fd, buf, count);
-	if (n != count) {
-		perror("write");
-		fail_file();
+	size_t cnt = count;
+	off_t idx = 0;
+
+	file_updated = 1;
+
+	if (file_ptr + count >= file_end) {
+		off_t aoffset = (file_ptr + count) - file_end;
+
+		if (aoffset > file_append_size) {
+			file_append = realloc(file_append, aoffset);
+			file_append_size = aoffset;
+		}
+		if (!file_append) {
+			perror("write");
+			fail_file();
+		}
+		if (file_ptr < file_end) {
+			cnt = file_end - file_ptr;
+		} else {
+			cnt = 0;
+			idx = aoffset - count;
+		}
 	}
-	return n;
+
+	if (cnt)
+		memcpy(file_ptr, buf, cnt);
+
+	if (cnt < count)
+		memcpy(file_append + idx, buf + cnt, count - cnt);
+
+	file_ptr += count;
+	return count;
 }
 
 static void *
@@ -192,9 +237,7 @@
  */
 static void *mmap_file(char const *fname)
 {
-	void *addr;
-
-	fd_map = open(fname, O_RDWR);
+	fd_map = open(fname, O_RDONLY);
 	if (fd_map < 0 || fstat(fd_map, &sb) < 0) {
 		perror(fname);
 		fail_file();
@@ -203,15 +246,58 @@
 		fprintf(stderr, "not a regular file: %s\n", fname);
 		fail_file();
 	}
-	addr = mmap(0, sb.st_size, PROT_READ|PROT_WRITE, MAP_PRIVATE,
-		    fd_map, 0);
+	file_map = mmap(0, sb.st_size, PROT_READ|PROT_WRITE, MAP_PRIVATE,
+			fd_map, 0);
 	mmap_failed = 0;
-	if (addr == MAP_FAILED) {
+	if (file_map == MAP_FAILED) {
 		mmap_failed = 1;
-		addr = umalloc(sb.st_size);
-		uread(fd_map, addr, sb.st_size);
+		file_map = umalloc(sb.st_size);
+		uread(fd_map, file_map, sb.st_size);
 	}
-	return addr;
+	close(fd_map);
+
+	file_end = file_map + sb.st_size;
+
+	return file_map;
+}
+
+static void write_file(const char *fname)
+{
+	char tmp_file[strlen(fname) + 4];
+	size_t n;
+
+	if (!file_updated)
+		return;
+
+	sprintf(tmp_file, "%s.rc", fname);
+
+	/*
+	 * After reading the entire file into memory, delete it
+	 * and write it back, to prevent weird side effects of modifying
+	 * an object file in place.
+	 */
+	fd_map = open(tmp_file, O_WRONLY | O_TRUNC | O_CREAT, sb.st_mode);
+	if (fd_map < 0) {
+		perror(fname);
+		fail_file();
+	}
+	n = write(fd_map, file_map, sb.st_size);
+	if (n != sb.st_size) {
+		perror("write");
+		fail_file();
+	}
+	if (file_append_size) {
+		n = write(fd_map, file_append, file_append_size);
+		if (n != file_append_size) {
+			perror("write");
+			fail_file();
+		}
+	}
+	close(fd_map);
+	if (rename(tmp_file, fname) < 0) {
+		perror(fname);
+		fail_file();
+	}
 }
 
 /* w8rev, w8nat, ...: Handle endianness. */
@@ -318,7 +404,6 @@
 	Elf32_Ehdr *const ehdr = mmap_file(fname);
 	unsigned int reltype = 0;
 
-	ehdr_curr = ehdr;
 	w = w4nat;
 	w2 = w2nat;
 	w8 = w8nat;
@@ -441,6 +526,7 @@
 	}
 	}  /* end switch */
 
+	write_file(fname);
 	cleanup();
 }
 
@@ -493,11 +579,14 @@
 		case SJ_SETJMP:    /* normal sequence */
 			/* Avoid problems if early cleanup() */
 			fd_map = -1;
-			ehdr_curr = NULL;
 			mmap_failed = 1;
+			file_map = NULL;
+			file_ptr = NULL;
+			file_updated = 0;
 			do_file(file);
 			break;
 		case SJ_FAIL:    /* error in do_file or below */
+			sprintf("%s: failed\n", file);
 			++n_error;
 			break;
 		case SJ_SUCCEED:    /* premature success */
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index bff5c8b..3b36582 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -954,6 +954,36 @@
 }
 #endif /* CONFIG_PM_SLEEP || SUPPORT_VGA_SWITCHEROO */
 
+#ifdef CONFIG_PM_SLEEP
+/* put codec down to D3 at hibernation for Intel SKL+;
+ * otherwise BIOS may still access the codec and screw up the driver
+ */
+#define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170)
+#define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70)
+#define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98)
+#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci))
+
+static int azx_freeze_noirq(struct device *dev)
+{
+	struct pci_dev *pci = to_pci_dev(dev);
+
+	if (IS_SKL_PLUS(pci))
+		pci_set_power_state(pci, PCI_D3hot);
+
+	return 0;
+}
+
+static int azx_thaw_noirq(struct device *dev)
+{
+	struct pci_dev *pci = to_pci_dev(dev);
+
+	if (IS_SKL_PLUS(pci))
+		pci_set_power_state(pci, PCI_D0);
+
+	return 0;
+}
+#endif /* CONFIG_PM_SLEEP */
+
 #ifdef CONFIG_PM
 static int azx_runtime_suspend(struct device *dev)
 {
@@ -1063,6 +1093,10 @@
 
 static const struct dev_pm_ops azx_pm = {
 	SET_SYSTEM_SLEEP_PM_OPS(azx_suspend, azx_resume)
+#ifdef CONFIG_PM_SLEEP
+	.freeze_noirq = azx_freeze_noirq,
+	.thaw_noirq = azx_thaw_noirq,
+#endif
 	SET_RUNTIME_PM_OPS(azx_runtime_suspend, azx_runtime_resume, azx_runtime_idle)
 };
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 6c268da..fe96428 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -1775,6 +1775,7 @@
 	ALC889_FIXUP_MBA11_VREF,
 	ALC889_FIXUP_MBA21_VREF,
 	ALC889_FIXUP_MP11_VREF,
+	ALC889_FIXUP_MP41_VREF,
 	ALC882_FIXUP_INV_DMIC,
 	ALC882_FIXUP_NO_PRIMARY_HP,
 	ALC887_FIXUP_ASUS_BASS,
@@ -1863,7 +1864,7 @@
 				  const struct hda_fixup *fix, int action)
 {
 	struct alc_spec *spec = codec->spec;
-	static hda_nid_t nids[2] = { 0x14, 0x15 };
+	static hda_nid_t nids[3] = { 0x14, 0x15, 0x19 };
 	int i;
 
 	if (action != HDA_FIXUP_ACT_INIT)
@@ -2153,6 +2154,12 @@
 		.chained = true,
 		.chain_id = ALC885_FIXUP_MACPRO_GPIO,
 	},
+	[ALC889_FIXUP_MP41_VREF] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc889_fixup_mbp_vref,
+		.chained = true,
+		.chain_id = ALC885_FIXUP_MACPRO_GPIO,
+	},
 	[ALC882_FIXUP_INV_DMIC] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_inv_dmic,
@@ -2235,7 +2242,7 @@
 	SND_PCI_QUIRK(0x106b, 0x3f00, "Macbook 5,1", ALC889_FIXUP_IMAC91_VREF),
 	SND_PCI_QUIRK(0x106b, 0x4000, "MacbookPro 5,1", ALC889_FIXUP_IMAC91_VREF),
 	SND_PCI_QUIRK(0x106b, 0x4100, "Macmini 3,1", ALC889_FIXUP_IMAC91_VREF),
-	SND_PCI_QUIRK(0x106b, 0x4200, "Mac Pro 5,1", ALC885_FIXUP_MACPRO_GPIO),
+	SND_PCI_QUIRK(0x106b, 0x4200, "Mac Pro 4,1/5,1", ALC889_FIXUP_MP41_VREF),
 	SND_PCI_QUIRK(0x106b, 0x4300, "iMac 9,1", ALC889_FIXUP_IMAC91_VREF),
 	SND_PCI_QUIRK(0x106b, 0x4600, "MacbookPro 5,2", ALC889_FIXUP_IMAC91_VREF),
 	SND_PCI_QUIRK(0x106b, 0x4900, "iMac 9,1 Aluminum", ALC889_FIXUP_IMAC91_VREF),
diff --git a/sound/soc/codecs/es8328.c b/sound/soc/codecs/es8328.c
index 84f5eb0..afa6c5d 100644
--- a/sound/soc/codecs/es8328.c
+++ b/sound/soc/codecs/es8328.c
@@ -85,7 +85,15 @@
 static const DECLARE_TLV_DB_SCALE(bypass_tlv, -1500, 300, 0);
 static const DECLARE_TLV_DB_SCALE(mic_tlv, 0, 300, 0);
 
-static const int deemph_settings[] = { 0, 32000, 44100, 48000 };
+static const struct {
+	int rate;
+	unsigned int val;
+} deemph_settings[] = {
+	{ 0,     ES8328_DACCONTROL6_DEEMPH_OFF },
+	{ 32000, ES8328_DACCONTROL6_DEEMPH_32k },
+	{ 44100, ES8328_DACCONTROL6_DEEMPH_44_1k },
+	{ 48000, ES8328_DACCONTROL6_DEEMPH_48k },
+};
 
 static int es8328_set_deemph(struct snd_soc_codec *codec)
 {
@@ -97,21 +105,22 @@
 	 * rate.
 	 */
 	if (es8328->deemph) {
-		best = 1;
-		for (i = 2; i < ARRAY_SIZE(deemph_settings); i++) {
-			if (abs(deemph_settings[i] - es8328->playback_fs) <
-			    abs(deemph_settings[best] - es8328->playback_fs))
+		best = 0;
+		for (i = 1; i < ARRAY_SIZE(deemph_settings); i++) {
+			if (abs(deemph_settings[i].rate - es8328->playback_fs) <
+			    abs(deemph_settings[best].rate - es8328->playback_fs))
 				best = i;
 		}
 
-		val = best << 1;
+		val = deemph_settings[best].val;
 	} else {
-		val = 0;
+		val = ES8328_DACCONTROL6_DEEMPH_OFF;
 	}
 
 	dev_dbg(codec->dev, "Set deemphasis %d\n", val);
 
-	return snd_soc_update_bits(codec, ES8328_DACCONTROL6, 0x6, val);
+	return snd_soc_update_bits(codec, ES8328_DACCONTROL6,
+			ES8328_DACCONTROL6_DEEMPH_MASK, val);
 }
 
 static int es8328_get_deemph(struct snd_kcontrol *kcontrol,
diff --git a/sound/soc/codecs/es8328.h b/sound/soc/codecs/es8328.h
index cb36afe..156c748 100644
--- a/sound/soc/codecs/es8328.h
+++ b/sound/soc/codecs/es8328.h
@@ -153,6 +153,7 @@
 #define ES8328_DACCONTROL6_CLICKFREE (1 << 3)
 #define ES8328_DACCONTROL6_DAC_INVR (1 << 4)
 #define ES8328_DACCONTROL6_DAC_INVL (1 << 5)
+#define ES8328_DACCONTROL6_DEEMPH_MASK (3 << 6)
 #define ES8328_DACCONTROL6_DEEMPH_OFF (0 << 6)
 #define ES8328_DACCONTROL6_DEEMPH_32k (1 << 6)
 #define ES8328_DACCONTROL6_DEEMPH_44_1k (2 << 6)
diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c
index f540f82..08b4046 100644
--- a/sound/soc/codecs/sgtl5000.c
+++ b/sound/soc/codecs/sgtl5000.c
@@ -189,6 +189,7 @@
 	case SND_SOC_DAPM_POST_PMU:
 		snd_soc_update_bits(codec, SGTL5000_CHIP_ANA_POWER,
 			SGTL5000_VAG_POWERUP, SGTL5000_VAG_POWERUP);
+		msleep(400);
 		break;
 
 	case SND_SOC_DAPM_PRE_PMD:
diff --git a/sound/soc/codecs/wm8974.c b/sound/soc/codecs/wm8974.c
index 0a60677..4c29bd2 100644
--- a/sound/soc/codecs/wm8974.c
+++ b/sound/soc/codecs/wm8974.c
@@ -574,6 +574,7 @@
 	.max_register = WM8974_MONOMIX,
 	.reg_defaults = wm8974_reg_defaults,
 	.num_reg_defaults = ARRAY_SIZE(wm8974_reg_defaults),
+	.cache_type = REGCACHE_FLAT,
 };
 
 static int wm8974_probe(struct snd_soc_codec *codec)
diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c
index c1c9c2e..2ccb8bc 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -223,8 +223,8 @@
 
 	/* wait for XDATA to be cleared */
 	cnt = 0;
-	while (!(mcasp_get_reg(mcasp, DAVINCI_MCASP_TXSTAT_REG) &
-		 ~XRDATA) && (cnt < 100000))
+	while ((mcasp_get_reg(mcasp, DAVINCI_MCASP_TXSTAT_REG) & XRDATA) &&
+	       (cnt < 100000))
 		cnt++;
 
 	/* Release TX state machine */
diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c
index ffd5f9a..08b460b 100644
--- a/sound/soc/fsl/fsl_sai.c
+++ b/sound/soc/fsl/fsl_sai.c
@@ -505,6 +505,24 @@
 					   FSL_SAI_CSR_FR, FSL_SAI_CSR_FR);
 			regmap_update_bits(sai->regmap, FSL_SAI_RCSR,
 					   FSL_SAI_CSR_FR, FSL_SAI_CSR_FR);
+
+			/*
+			 * For sai master mode, after several open/close sai,
+			 * there will be no frame clock, and can't recover
+			 * anymore. Add software reset to fix this issue.
+			 * This is a hardware bug, and will be fix in the
+			 * next sai version.
+			 */
+			if (!sai->is_slave_mode) {
+				/* Software Reset for both Tx and Rx */
+				regmap_write(sai->regmap,
+					     FSL_SAI_TCSR, FSL_SAI_CSR_SR);
+				regmap_write(sai->regmap,
+					     FSL_SAI_RCSR, FSL_SAI_CSR_SR);
+				/* Clear SR bit to finish the reset */
+				regmap_write(sai->regmap, FSL_SAI_TCSR, 0);
+				regmap_write(sai->regmap, FSL_SAI_RCSR, 0);
+			}
 		}
 		break;
 	default:
diff --git a/sound/soc/rockchip/rockchip_spdif.c b/sound/soc/rockchip/rockchip_spdif.c
index ac72ff5..5a806da 100644
--- a/sound/soc/rockchip/rockchip_spdif.c
+++ b/sound/soc/rockchip/rockchip_spdif.c
@@ -152,8 +152,10 @@
 	case SNDRV_PCM_TRIGGER_RESUME:
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
 		ret = regmap_update_bits(spdif->regmap, SPDIF_DMACR,
-				   SPDIF_DMACR_TDE_ENABLE,
-				   SPDIF_DMACR_TDE_ENABLE);
+				   SPDIF_DMACR_TDE_ENABLE |
+				   SPDIF_DMACR_TDL_MASK,
+				   SPDIF_DMACR_TDE_ENABLE |
+				   SPDIF_DMACR_TDL(16));
 
 		if (ret != 0)
 			return ret;
diff --git a/sound/soc/rockchip/rockchip_spdif.h b/sound/soc/rockchip/rockchip_spdif.h
index 921b409..3ef1277 100644
--- a/sound/soc/rockchip/rockchip_spdif.h
+++ b/sound/soc/rockchip/rockchip_spdif.h
@@ -42,7 +42,7 @@
 
 #define SPDIF_DMACR_TDL_SHIFT	0
 #define SPDIF_DMACR_TDL(x)	((x) << SPDIF_DMACR_TDL_SHIFT)
-#define SPDIF_DMACR_TDL_MASK	(0x1f << SDPIF_DMACR_TDL_SHIFT)
+#define SPDIF_DMACR_TDL_MASK	(0x1f << SPDIF_DMACR_TDL_SHIFT)
 
 /*
  * XFER
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 65461f8..7a2f449 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -1114,7 +1114,7 @@
 			return true;
 	}
 
-	return dist_active_irq(vcpu);
+	return vgic_irq_is_active(vcpu, map->virt_irq);
 }
 
 /*