diff --git a/Documentation/ABI/testing/ima_policy b/Documentation/ABI/testing/ima_policy
index 4c3efe434806..750ab970fa95 100644
--- a/Documentation/ABI/testing/ima_policy
+++ b/Documentation/ABI/testing/ima_policy
@@ -20,16 +20,18 @@ Description:
 		action: measure | dont_measure | appraise | dont_appraise | audit
 		condition:= base | lsm  [option]
 			base:	[[func=] [mask=] [fsmagic=] [fsuuid=] [uid=]
-				 [fowner]]
+				[euid=] [fowner=]]
 			lsm:	[[subj_user=] [subj_role=] [subj_type=]
 				 [obj_user=] [obj_role=] [obj_type=]]
 			option:	[[appraise_type=]] [permit_directio]
 
 		base: 	func:= [BPRM_CHECK][MMAP_CHECK][FILE_CHECK][MODULE_CHECK]
-			mask:= [MAY_READ] [MAY_WRITE] [MAY_APPEND] [MAY_EXEC]
+			mask:= [[^]MAY_READ] [[^]MAY_WRITE] [[^]MAY_APPEND]
+			       [[^]MAY_EXEC]
 			fsmagic:= hex value
 			fsuuid:= file system UUID (e.g 8bcbe394-4f13-4144-be8e-5aa9ea2ce2f6)
 			uid:= decimal value
+			euid:= decimal value
 			fowner:=decimal value
 		lsm:  	are LSM specific
 		option:	appraise_type:= [imasig]
diff --git a/Makefile b/Makefile
index 844b2cbbf10c..c45298b8b2d5 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 12
-SUBLEVEL = 46
+SUBLEVEL = 47
 EXTRAVERSION =
 NAME = One Giant Leap for Frogkind
 
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
index 1bfeec2c0558..2a58af7a2e3a 100644
--- a/arch/arc/include/asm/ptrace.h
+++ b/arch/arc/include/asm/ptrace.h
@@ -63,7 +63,7 @@ struct callee_regs {
 	long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
 };
 
-#define instruction_pointer(regs)	((regs)->ret)
+#define instruction_pointer(regs)	(unsigned long)((regs)->ret)
 #define profile_pc(regs)		instruction_pointer(regs)
 
 /* return 1 if user mode or 0 if kernel mode */
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index 60f15e274e6d..2f59f7443396 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -59,6 +59,21 @@
 #define smp_wmb()	dmb(ishst)
 #endif
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
 #define read_barrier_depends()		do { } while(0)
 #define smp_read_barrier_depends()	do { } while(0)
 
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 3d29fb972cd0..68a9bec32c9e 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -2402,6 +2402,9 @@ static struct device_node *of_dev_hwmod_lookup(struct device_node *np,
  * registers.  This address is needed early so the OCP registers that
  * are part of the device's address space can be ioremapped properly.
  *
+ * If SYSC access is not needed, the registers will not be remapped
+ * and non-availability of MPU access is not treated as an error.
+ *
  * Returns 0 on success, -EINVAL if an invalid hwmod is passed, and
  * -ENXIO on absent or invalid register target address space.
  */
@@ -2416,6 +2419,11 @@ static int __init _init_mpu_rt_base(struct omap_hwmod *oh, void *data)
 
 	_save_mpu_port_index(oh);
 
+	/* if we don't need sysc access we don't need to ioremap */
+	if (!oh->class->sysc)
+		return 0;
+
+	/* we can't continue without MPU PORT if we need sysc access */
 	if (oh->_int_flags & _HWMOD_NO_MPU_PORT)
 		return -ENXIO;
 
@@ -2425,8 +2433,10 @@ static int __init _init_mpu_rt_base(struct omap_hwmod *oh, void *data)
 			 oh->name);
 
 		/* Extract the IO space from device tree blob */
-		if (!of_have_populated_dt())
+		if (!of_have_populated_dt()) {
+			pr_err("omap_hwmod: %s: no dt node\n", oh->name);
 			return -ENXIO;
+		}
 
 		np = of_dev_hwmod_lookup(of_find_node_by_name(NULL, "ocp"), oh);
 		if (np)
@@ -2467,13 +2477,11 @@ static int __init _init(struct omap_hwmod *oh, void *data)
 	if (oh->_state != _HWMOD_STATE_REGISTERED)
 		return 0;
 
-	if (oh->class->sysc) {
-		r = _init_mpu_rt_base(oh, NULL);
-		if (r < 0) {
-			WARN(1, "omap_hwmod: %s: doesn't have mpu register target base\n",
-			     oh->name);
-			return 0;
-		}
+	r = _init_mpu_rt_base(oh, NULL);
+	if (r < 0) {
+		WARN(1, "omap_hwmod: %s: doesn't have mpu register target base\n",
+		     oh->name);
+		return 0;
 	}
 
 	r = _init_clocks(oh, NULL);
diff --git a/arch/arm/mach-realview/include/mach/memory.h b/arch/arm/mach-realview/include/mach/memory.h
index 2022e092f0ca..db09170e3832 100644
--- a/arch/arm/mach-realview/include/mach/memory.h
+++ b/arch/arm/mach-realview/include/mach/memory.h
@@ -56,6 +56,8 @@
 #define PAGE_OFFSET1	(PAGE_OFFSET + 0x10000000)
 #define PAGE_OFFSET2	(PAGE_OFFSET + 0x30000000)
 
+#define PHYS_OFFSET PLAT_PHYS_OFFSET
+
 #define __phys_to_virt(phys)						\
 	((phys) >= 0x80000000 ?	(phys) - 0x80000000 + PAGE_OFFSET2 :	\
 	 (phys) >= 0x20000000 ?	(phys) - 0x20000000 + PAGE_OFFSET1 :	\
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index d4a63338a53c..78e20ba8806b 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -35,10 +35,60 @@
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
 #else
+
 #define smp_mb()	asm volatile("dmb ish" : : : "memory")
 #define smp_rmb()	asm volatile("dmb ishld" : : : "memory")
 #define smp_wmb()	asm volatile("dmb ishst" : : : "memory")
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	switch (sizeof(*p)) {						\
+	case 4:								\
+		asm volatile ("stlr %w1, %0"				\
+				: "=Q" (*p) : "r" (v) : "memory");	\
+		break;							\
+	case 8:								\
+		asm volatile ("stlr %1, %0"				\
+				: "=Q" (*p) : "r" (v) : "memory");	\
+		break;							\
+	}								\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1;						\
+	compiletime_assert_atomic_type(*p);				\
+	switch (sizeof(*p)) {						\
+	case 4:								\
+		asm volatile ("ldar %w0, %1"				\
+			: "=r" (___p1) : "Q" (*p) : "memory");		\
+		break;							\
+	case 8:								\
+		asm volatile ("ldar %0, %1"				\
+			: "=r" (___p1) : "Q" (*p) : "memory");		\
+		break;							\
+	}								\
+	___p1;								\
+})
+
 #endif
 
 #define read_barrier_depends()		do { } while(0)
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 3d478102b1c0..b9564b8d6bab 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -193,7 +193,8 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
 		 * Other callers might not initialize the si_lsb field,
 		 * so check explicitely for the right codes here.
 		 */
-		if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)
+		if (from->si_signo == SIGBUS &&
+		    (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO))
 			err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
 #endif
 		break;
@@ -220,8 +221,6 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
 
 int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 {
-	memset(to, 0, sizeof *to);
-
 	if (copy_from_user(to, from, __ARCH_SI_PREAMBLE_SIZE) ||
 	    copy_from_user(to->_sifields._pad,
 			   from->_sifields._pad, SI_PAD_SIZE))
diff --git a/arch/ia64/include/asm/barrier.h b/arch/ia64/include/asm/barrier.h
index 60576e06b6fb..d0a69aa35e27 100644
--- a/arch/ia64/include/asm/barrier.h
+++ b/arch/ia64/include/asm/barrier.h
@@ -45,14 +45,37 @@
 # define smp_rmb()	rmb()
 # define smp_wmb()	wmb()
 # define smp_read_barrier_depends()	read_barrier_depends()
+
 #else
+
 # define smp_mb()	barrier()
 # define smp_rmb()	barrier()
 # define smp_wmb()	barrier()
 # define smp_read_barrier_depends()	do { } while(0)
+
 #endif
 
 /*
+ * IA64 GCC turns volatile stores into st.rel and volatile loads into ld.acq no
+ * need for asm trickery!
+ */
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	___p1;								\
+})
+
+/*
  * XXX check on this ---I suspect what Linus really wants here is
  * acquire vs release semantics but we can't discuss this stuff with
  * Linus just yet.  Grrr...
diff --git a/arch/metag/include/asm/barrier.h b/arch/metag/include/asm/barrier.h
index e355a4c10968..2d6f0de77325 100644
--- a/arch/metag/include/asm/barrier.h
+++ b/arch/metag/include/asm/barrier.h
@@ -85,4 +85,19 @@ static inline void fence(void)
 #define smp_read_barrier_depends()     do { } while (0)
 #define set_mb(var, value) do { var = value; smp_mb(); } while (0)
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
 #endif /* _ASM_METAG_BARRIER_H */
diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h
index 314ab5532019..52c5b61d7aba 100644
--- a/arch/mips/include/asm/barrier.h
+++ b/arch/mips/include/asm/barrier.h
@@ -180,4 +180,19 @@
 #define nudge_writes() mb()
 #endif
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
 #endif /* __ASM_BARRIER_H */
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 008324d1c261..b15495367d5c 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -150,8 +150,39 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
 		 * Make sure the buddy is global too (if it's !none,
 		 * it better already be global)
 		 */
+#ifdef CONFIG_SMP
+		/*
+		 * For SMP, multiple CPUs can race, so we need to do
+		 * this atomically.
+		 */
+#ifdef CONFIG_64BIT
+#define LL_INSN "lld"
+#define SC_INSN "scd"
+#else /* CONFIG_32BIT */
+#define LL_INSN "ll"
+#define SC_INSN "sc"
+#endif
+		unsigned long page_global = _PAGE_GLOBAL;
+		unsigned long tmp;
+
+		__asm__ __volatile__ (
+			"	.set	push\n"
+			"	.set	noreorder\n"
+			"1:	" LL_INSN "	%[tmp], %[buddy]\n"
+			"	bnez	%[tmp], 2f\n"
+			"	 or	%[tmp], %[tmp], %[global]\n"
+			"	" SC_INSN "	%[tmp], %[buddy]\n"
+			"	beqz	%[tmp], 1b\n"
+			"	 nop\n"
+			"2:\n"
+			"	.set pop"
+			: [buddy] "+m" (buddy->pte),
+			  [tmp] "=&r" (tmp)
+			: [global] "r" (page_global));
+#else /* !CONFIG_SMP */
 		if (pte_none(*buddy))
 			pte_val(*buddy) = pte_val(*buddy) | _PAGE_GLOBAL;
+#endif /* CONFIG_SMP */
 	}
 #endif
 }
diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c
index cb098628aee8..ca16964a2b5e 100644
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -154,7 +154,7 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len,
 				      unsigned long __user *user_mask_ptr)
 {
 	unsigned int real_len;
-	cpumask_t mask;
+	cpumask_t allowed, mask;
 	int retval;
 	struct task_struct *p;
 
@@ -173,7 +173,8 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len,
 	if (retval)
 		goto out_unlock;
 
-	cpumask_and(&mask, &p->thread.user_cpus_allowed, cpu_possible_mask);
+	cpumask_or(&allowed, &p->thread.user_cpus_allowed, &p->cpus_allowed);
+	cpumask_and(&mask, &allowed, cpu_active_mask);
 
 out_unlock:
 	read_unlock(&tasklist_lock);
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index 57de8b751627..41f8708d21a8 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -368,8 +368,6 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
 
 int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 {
-	memset(to, 0, sizeof *to);
-
 	if (copy_from_user(to, from, 3*sizeof(int)) ||
 	    copy_from_user(to->_sifields._pad,
 			   from->_sifields._pad, SI_PAD_SIZE32))
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index ae782254e731..f89da808ce31 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -45,11 +45,15 @@
 #    define SMPWMB      eieio
 #endif
 
+#define __lwsync()	__asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory")
+
 #define smp_mb()	mb()
-#define smp_rmb()	__asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory")
+#define smp_rmb()	__lwsync()
 #define smp_wmb()	__asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory")
 #define smp_read_barrier_depends()	read_barrier_depends()
 #else
+#define __lwsync()	barrier()
+
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
@@ -65,4 +69,19 @@
 #define data_barrier(x)	\
 	asm volatile("twi 0,%0,0; isync" : : "r" (x) : "memory");
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	__lwsync();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	__lwsync();							\
+	___p1;								\
+})
+
 #endif /* _ASM_POWERPC_BARRIER_H */
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 50606e4261a1..7fce77b89f6d 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -958,8 +958,6 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *d, siginfo_t *s)
 
 int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from)
 {
-	memset(to, 0, sizeof *to);
-
 	if (copy_from_user(to, from, 3*sizeof(int)) ||
 	    copy_from_user(to->_sifields._pad,
 			   from->_sifields._pad, SI_PAD_SIZE32))
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index 16760eeb79b0..578680f6207a 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -32,4 +32,19 @@
 
 #define set_mb(var, value)		do { var = value; mb(); } while (0)
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	___p1;								\
+})
+
 #endif /* __ASM_BARRIER_H */
diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S
index 29bd7bec4176..1ecd47b5e250 100644
--- a/arch/s390/kernel/sclp.S
+++ b/arch/s390/kernel/sclp.S
@@ -276,6 +276,8 @@ ENTRY(_sclp_print_early)
 	jno	.Lesa2
 	ahi	%r15,-80
 	stmh	%r6,%r15,96(%r15)		# store upper register halves
+	basr	%r13,0
+	lmh	%r0,%r15,.Lzeroes-.(%r13)	# clear upper register halves
 .Lesa2:
 #endif
 	lr	%r10,%r2			# save string pointer
@@ -299,6 +301,8 @@ ENTRY(_sclp_print_early)
 #endif
 	lm	%r6,%r15,120(%r15)		# restore registers
 	br	%r14
+.Lzeroes:
+	.fill	64,4,0
 
 .LwritedataS4:
 	.long	0x00760005			# SCLP command for write data
diff --git a/arch/sparc/include/asm/barrier_64.h b/arch/sparc/include/asm/barrier_64.h
index 95d45986f908..b5aad964558e 100644
--- a/arch/sparc/include/asm/barrier_64.h
+++ b/arch/sparc/include/asm/barrier_64.h
@@ -53,4 +53,19 @@ do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
 
 #define smp_read_barrier_depends()	do { } while(0)
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	___p1;								\
+})
+
 #endif /* !(__SPARC64_BARRIER_H) */
diff --git a/arch/sparc/include/asm/visasm.h b/arch/sparc/include/asm/visasm.h
index 11fdf0ef50bb..50d6f16a1513 100644
--- a/arch/sparc/include/asm/visasm.h
+++ b/arch/sparc/include/asm/visasm.h
@@ -28,16 +28,10 @@
  * Must preserve %o5 between VISEntryHalf and VISExitHalf */
 
 #define VISEntryHalf					\
-	rd		%fprs, %o5;			\
-	andcc		%o5, FPRS_FEF, %g0;		\
-	be,pt		%icc, 297f;			\
-	 sethi		%hi(298f), %g7;			\
-	sethi		%hi(VISenterhalf), %g1;		\
-	jmpl		%g1 + %lo(VISenterhalf), %g0;	\
-	 or		%g7, %lo(298f), %g7;		\
-	clr		%o5;				\
-297:	wr		%o5, FPRS_FEF, %fprs;		\
-298:
+	VISEntry
+
+#define VISExitHalf					\
+	VISExit
 
 #define VISEntryHalfFast(fail_label)			\
 	rd		%fprs, %o5;			\
@@ -47,7 +41,7 @@
 	ba,a,pt		%xcc, fail_label;		\
 297:	wr		%o5, FPRS_FEF, %fprs;
 
-#define VISExitHalf					\
+#define VISExitHalfFast					\
 	wr		%o5, 0, %fprs;
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S
index 140527a20e7d..83aeeb1dffdb 100644
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -240,8 +240,11 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	add		%o0, 0x40, %o0
 	bne,pt		%icc, 1b
 	 LOAD(prefetch, %g1 + 0x200, #n_reads_strong)
+#ifdef NON_USER_COPY
+	VISExitHalfFast
+#else
 	VISExitHalf
-
+#endif
 	brz,pn		%o2, .Lexit
 	 cmp		%o2, 19
 	ble,pn		%icc, .Lsmall_unaligned
diff --git a/arch/sparc/lib/VISsave.S b/arch/sparc/lib/VISsave.S
index b320ae9e2e2e..a063d84336d6 100644
--- a/arch/sparc/lib/VISsave.S
+++ b/arch/sparc/lib/VISsave.S
@@ -44,9 +44,8 @@ vis1:	ldub		[%g6 + TI_FPSAVED], %g3
 
 	 stx		%g3, [%g6 + TI_GSR]
 2:	add		%g6, %g1, %g3
-	cmp		%o5, FPRS_DU
-	be,pn		%icc, 6f
-	 sll		%g1, 3, %g1
+	mov		FPRS_DU | FPRS_DL | FPRS_FEF, %o5
+	sll		%g1, 3, %g1
 	stb		%o5, [%g3 + TI_FPSAVED]
 	rd		%gsr, %g2
 	add		%g6, %g1, %g3
@@ -80,65 +79,3 @@ vis1:	ldub		[%g6 + TI_FPSAVED], %g3
 	.align		32
 80:	jmpl		%g7 + %g0, %g0
 	 nop
-
-6:	ldub		[%g3 + TI_FPSAVED], %o5
-	or		%o5, FPRS_DU, %o5
-	add		%g6, TI_FPREGS+0x80, %g2
-	stb		%o5, [%g3 + TI_FPSAVED]
-
-	sll		%g1, 5, %g1
-	add		%g6, TI_FPREGS+0xc0, %g3
-	wr		%g0, FPRS_FEF, %fprs
-	membar		#Sync
-	stda		%f32, [%g2 + %g1] ASI_BLK_P
-	stda		%f48, [%g3 + %g1] ASI_BLK_P
-	membar		#Sync
-	ba,pt		%xcc, 80f
-	 nop
-
-	.align		32
-80:	jmpl		%g7 + %g0, %g0
-	 nop
-
-	.align		32
-VISenterhalf:
-	ldub		[%g6 + TI_FPDEPTH], %g1
-	brnz,a,pn	%g1, 1f
-	 cmp		%g1, 1
-	stb		%g0, [%g6 + TI_FPSAVED]
-	stx		%fsr, [%g6 + TI_XFSR]
-	clr		%o5
-	jmpl		%g7 + %g0, %g0
-	 wr		%g0, FPRS_FEF, %fprs
-
-1:	bne,pn		%icc, 2f
-	 srl		%g1, 1, %g1
-	ba,pt		%xcc, vis1
-	 sub		%g7, 8, %g7
-2:	addcc		%g6, %g1, %g3
-	sll		%g1, 3, %g1
-	andn		%o5, FPRS_DU, %g2
-	stb		%g2, [%g3 + TI_FPSAVED]
-
-	rd		%gsr, %g2
-	add		%g6, %g1, %g3
-	stx		%g2, [%g3 + TI_GSR]
-	add		%g6, %g1, %g2
-	stx		%fsr, [%g2 + TI_XFSR]
-	sll		%g1, 5, %g1
-3:	andcc		%o5, FPRS_DL, %g0
-	be,pn		%icc, 4f
-	 add		%g6, TI_FPREGS, %g2
-
-	add		%g6, TI_FPREGS+0x40, %g3
-	membar		#Sync
-	stda		%f0, [%g2 + %g1] ASI_BLK_P
-	stda		%f16, [%g3 + %g1] ASI_BLK_P
-	membar		#Sync
-	ba,pt		%xcc, 4f
-	 nop
-
-	.align		32
-4:	and		%o5, FPRS_DU, %o5
-	jmpl		%g7 + %g0, %g0
-	 wr		%o5, FPRS_FEF, %fprs
diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c
index 323335b9cd2b..ac094de28ccf 100644
--- a/arch/sparc/lib/ksyms.c
+++ b/arch/sparc/lib/ksyms.c
@@ -126,10 +126,6 @@ EXPORT_SYMBOL(copy_user_page);
 void VISenter(void);
 EXPORT_SYMBOL(VISenter);
 
-/* CRYPTO code needs this */
-void VISenterhalf(void);
-EXPORT_SYMBOL(VISenterhalf);
-
 extern void xor_vis_2(unsigned long, unsigned long *, unsigned long *);
 extern void xor_vis_3(unsigned long, unsigned long *, unsigned long *,
 		unsigned long *);
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index 74c91729a62a..bdb3ecf8e168 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -1146,7 +1146,7 @@ static void __init load_hv_initrd(void)
 
 void __init free_initrd_mem(unsigned long begin, unsigned long end)
 {
-	free_bootmem(__pa(begin), end - begin);
+	free_bootmem_late(__pa(begin), end - begin);
 }
 
 static int __init setup_initrd(char *str)
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index b1bd969e26aa..36ddc61182af 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -54,7 +54,7 @@ ENTRY(efi_pe_entry)
 	call	reloc
 reloc:
 	popl	%ecx
-	subl	reloc, %ecx
+	subl	$reloc, %ecx
 	movl	%ecx, BP_code32_start(%eax)
 
 	sub	$0x4, %esp
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index c6cd358a1eec..04a48903b2eb 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -92,12 +92,53 @@
 #endif
 #define smp_read_barrier_depends()	read_barrier_depends()
 #define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
-#else
+#else /* !SMP */
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
 #define smp_read_barrier_depends()	do { } while (0)
 #define set_mb(var, value) do { var = value; barrier(); } while (0)
+#endif /* SMP */
+
+#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+
+/*
+ * For either of these options x86 doesn't have a strong TSO memory
+ * model and we should fall back to full barriers.
+ */
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
+#else /* regular x86 TSO memory ordering */
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	___p1;								\
+})
+
 #endif
 
 /*
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index f6aaf7d16571..cb69cd0ba8c7 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -280,21 +280,6 @@ static inline void clear_LDT(void)
 	set_ldt(NULL, 0);
 }
 
-/*
- * load one particular LDT into the current CPU
- */
-static inline void load_LDT_nolock(mm_context_t *pc)
-{
-	set_ldt(pc->ldt, pc->size);
-}
-
-static inline void load_LDT(mm_context_t *pc)
-{
-	preempt_disable();
-	load_LDT_nolock(pc);
-	preempt_enable();
-}
-
 static inline unsigned long get_desc_base(const struct desc_struct *desc)
 {
 	return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24));
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 5f55e6962769..926f67263287 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -9,8 +9,7 @@
  * we put the segment information here.
  */
 typedef struct {
-	void *ldt;
-	int size;
+	struct ldt_struct *ldt;
 
 #ifdef CONFIG_X86_64
 	/* True if mm supports a task running in 32 bit compatibility mode. */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index be12c534fd59..86fef96f4eca 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -16,6 +16,50 @@ static inline void paravirt_activate_mm(struct mm_struct *prev,
 #endif	/* !CONFIG_PARAVIRT */
 
 /*
+ * ldt_structs can be allocated, used, and freed, but they are never
+ * modified while live.
+ */
+struct ldt_struct {
+	/*
+	 * Xen requires page-aligned LDTs with special permissions.  This is
+	 * needed to prevent us from installing evil descriptors such as
+	 * call gates.  On native, we could merge the ldt_struct and LDT
+	 * allocations, but it's not worth trying to optimize.
+	 */
+	struct desc_struct *entries;
+	int size;
+};
+
+static inline void load_mm_ldt(struct mm_struct *mm)
+{
+	struct ldt_struct *ldt;
+
+	/* lockless_dereference synchronizes with smp_store_release */
+	ldt = lockless_dereference(mm->context.ldt);
+
+	/*
+	 * Any change to mm->context.ldt is followed by an IPI to all
+	 * CPUs with the mm active.  The LDT will not be freed until
+	 * after the IPI is handled by all such CPUs.  This means that,
+	 * if the ldt_struct changes before we return, the values we see
+	 * will be safe, and the new values will be loaded before we run
+	 * any user code.
+	 *
+	 * NB: don't try to convert this to use RCU without extreme care.
+	 * We would still need IRQs off, because we don't want to change
+	 * the local LDT after an IPI loaded a newer value than the one
+	 * that we can see.
+	 */
+
+	if (unlikely(ldt))
+		set_ldt(ldt->entries, ldt->size);
+	else
+		clear_LDT();
+
+	DEBUG_LOCKS_WARN_ON(preemptible());
+}
+
+/*
  * Used for LDT copy/destruction.
  */
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
@@ -50,7 +94,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 
 		/* Load the LDT, if the LDT is different: */
 		if (unlikely(prev->context.ldt != next->context.ldt))
-			load_LDT_nolock(&next->context);
+			load_mm_ldt(next);
 	}
 #ifdef CONFIG_SMP
 	  else {
@@ -71,7 +115,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 			 * to make sure to use no freed page tables.
 			 */
 			load_cr3(next->pgd);
-			load_LDT_nolock(&next->context);
+			load_mm_ldt(next);
 		}
 	}
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 00cc6f79615d..6db4828574ef 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1309,7 +1309,7 @@ void cpu_init(void)
 	load_sp0(t, &current->thread);
 	set_tss_desc(cpu, t);
 	load_TR_desc();
-	load_LDT(&init_mm.context);
+	load_mm_ldt(&init_mm);
 
 	clear_all_debug_regs();
 	dbg_restore_debug_regs();
@@ -1356,7 +1356,7 @@ void cpu_init(void)
 	load_sp0(t, thread);
 	set_tss_desc(cpu, t);
 	load_TR_desc();
-	load_LDT(&init_mm.context);
+	load_mm_ldt(&init_mm);
 
 	t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index c7106f116fb0..0271272d55d0 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -31,6 +31,7 @@
 #include <asm/nmi.h>
 #include <asm/smp.h>
 #include <asm/alternative.h>
+#include <asm/mmu_context.h>
 #include <asm/timer.h>
 #include <asm/desc.h>
 #include <asm/ldt.h>
@@ -1953,21 +1954,25 @@ static unsigned long get_segment_base(unsigned int segment)
 	int idx = segment >> 3;
 
 	if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) {
+		struct ldt_struct *ldt;
+
 		if (idx > LDT_ENTRIES)
 			return 0;
 
-		if (idx > current->active_mm->context.size)
+		/* IRQs are off, so this synchronizes with smp_store_release */
+		ldt = lockless_dereference(current->active_mm->context.ldt);
+		if (!ldt || idx > ldt->size)
 			return 0;
 
-		desc = current->active_mm->context.ldt;
+		desc = &ldt->entries[idx];
 	} else {
 		if (idx > GDT_ENTRIES)
 			return 0;
 
-		desc = __this_cpu_ptr(&gdt_page.gdt[0]);
+		desc = __this_cpu_ptr(&gdt_page.gdt[0]) + idx;
 	}
 
-	return get_desc_base(desc + idx);
+	return get_desc_base(desc);
 }
 
 #ifdef CONFIG_COMPAT
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 7b22af265d12..691337073e1f 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1706,20 +1706,77 @@ ENTRY(nmi)
 	 * a nested NMI that updated the copy interrupt stack frame, a
 	 * jump will be made to the repeat_nmi code that will handle the second
 	 * NMI.
+	 *
+	 * However, espfix prevents us from directly returning to userspace
+	 * with a single IRET instruction.  Similarly, IRET to user mode
+	 * can fault.  We therefore handle NMIs from user space like
+	 * other IST entries.
 	 */
 
 	/* Use %rdx as out temp variable throughout */
 	pushq_cfi %rdx
 	CFI_REL_OFFSET rdx, 0
 
+	testb	$3, CS-RIP+8(%rsp)
+	jz	.Lnmi_from_kernel
+
+	/*
+	 * NMI from user mode.  We need to run on the thread stack, but we
+	 * can't go through the normal entry paths: NMIs are masked, and
+	 * we don't want to enable interrupts, because then we'll end
+	 * up in an awkward situation in which IRQs are on but NMIs
+	 * are off.
+	 */
+
+	SWAPGS
+	cld
+	movq	%rsp, %rdx
+	movq	PER_CPU_VAR(kernel_stack), %rsp
+	addq	$KERNEL_STACK_OFFSET, %rsp
+	pushq	5*8(%rdx)	/* pt_regs->ss */
+	pushq	4*8(%rdx)	/* pt_regs->rsp */
+	pushq	3*8(%rdx)	/* pt_regs->flags */
+	pushq	2*8(%rdx)	/* pt_regs->cs */
+	pushq	1*8(%rdx)	/* pt_regs->rip */
+	pushq   $-1		/* pt_regs->orig_ax */
+	pushq   %rdi		/* pt_regs->di */
+	pushq   %rsi		/* pt_regs->si */
+	pushq   (%rdx)		/* pt_regs->dx */
+	pushq   %rcx		/* pt_regs->cx */
+	pushq   %rax		/* pt_regs->ax */
+	pushq   %r8		/* pt_regs->r8 */
+	pushq   %r9		/* pt_regs->r9 */
+	pushq   %r10		/* pt_regs->r10 */
+	pushq   %r11		/* pt_regs->r11 */
+	pushq	%rbx		/* pt_regs->rbx */
+	pushq	%rbp		/* pt_regs->rbp */
+	pushq	%r12		/* pt_regs->r12 */
+	pushq	%r13		/* pt_regs->r13 */
+	pushq	%r14		/* pt_regs->r14 */
+	pushq	%r15		/* pt_regs->r15 */
+
 	/*
-	 * If %cs was not the kernel segment, then the NMI triggered in user
-	 * space, which means it is definitely not nested.
+	 * At this point we no longer need to worry about stack damage
+	 * due to nesting -- we're on the normal thread stack and we're
+	 * done with the NMI stack.
 	 */
-	cmpl $__KERNEL_CS, 16(%rsp)
-	jne first_nmi
+
+	movq	%rsp, %rdi
+	movq	$-1, %rsi
+	call	do_nmi
 
 	/*
+	 * Return back to user mode.  We must *not* do the normal exit
+	 * work, because we don't want to enable interrupts.  Fortunately,
+	 * do_nmi doesn't modify pt_regs.
+	 */
+	SWAPGS
+
+	addq	$6*8, %rsp	/* skip bx, bp, and r12-r15 */
+	jmp	restore_args
+
+.Lnmi_from_kernel:
+	/*
 	 * Check the special variable on the stack to see if NMIs are
 	 * executing.
 	 */
@@ -1876,29 +1933,11 @@ end_repeat_nmi:
 	call save_paranoid
 	DEFAULT_FRAME 0
 
-	/*
-	 * Save off the CR2 register. If we take a page fault in the NMI then
-	 * it could corrupt the CR2 value. If the NMI preempts a page fault
-	 * handler before it was able to read the CR2 register, and then the
-	 * NMI itself takes a page fault, the page fault that was preempted
-	 * will read the information from the NMI page fault and not the
-	 * origin fault. Save it off and restore it if it changes.
-	 * Use the r12 callee-saved register.
-	 */
-	movq %cr2, %r12
-
 	/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
 	movq %rsp,%rdi
 	movq $-1,%rsi
 	call do_nmi
 
-	/* Did the NMI take a page fault? Restore cr2 if it did */
-	movq %cr2, %rcx
-	cmpq %rcx, %r12
-	je 1f
-	movq %r12, %cr2
-1:
-	
 	testl %ebx,%ebx				/* swapgs needed? */
 	jnz nmi_restore
 nmi_swapgs:
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index c37886d759cc..2bcc0525f1c1 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -12,6 +12,7 @@
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
+#include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
 
@@ -20,82 +21,82 @@
 #include <asm/mmu_context.h>
 #include <asm/syscalls.h>
 
-#ifdef CONFIG_SMP
+/* context.lock is held for us, so we don't need any locking. */
 static void flush_ldt(void *current_mm)
 {
-	if (current->active_mm == current_mm)
-		load_LDT(&current->active_mm->context);
+	mm_context_t *pc;
+
+	if (current->active_mm != current_mm)
+		return;
+
+	pc = &current->active_mm->context;
+	set_ldt(pc->ldt->entries, pc->ldt->size);
 }
-#endif
 
-static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
+/* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */
+static struct ldt_struct *alloc_ldt_struct(int size)
 {
-	void *oldldt, *newldt;
-	int oldsize;
-
-	if (mincount <= pc->size)
-		return 0;
-	oldsize = pc->size;
-	mincount = (mincount + (PAGE_SIZE / LDT_ENTRY_SIZE - 1)) &
-			(~(PAGE_SIZE / LDT_ENTRY_SIZE - 1));
-	if (mincount * LDT_ENTRY_SIZE > PAGE_SIZE)
-		newldt = vmalloc(mincount * LDT_ENTRY_SIZE);
+	struct ldt_struct *new_ldt;
+	int alloc_size;
+
+	if (size > LDT_ENTRIES)
+		return NULL;
+
+	new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL);
+	if (!new_ldt)
+		return NULL;
+
+	BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct));
+	alloc_size = size * LDT_ENTRY_SIZE;
+
+	/*
+	 * Xen is very picky: it requires a page-aligned LDT that has no
+	 * trailing nonzero bytes in any page that contains LDT descriptors.
+	 * Keep it simple: zero the whole allocation and never allocate less
+	 * than PAGE_SIZE.
+	 */
+	if (alloc_size > PAGE_SIZE)
+		new_ldt->entries = vzalloc(alloc_size);
 	else
-		newldt = (void *)__get_free_page(GFP_KERNEL);
-
-	if (!newldt)
-		return -ENOMEM;
+		new_ldt->entries = kzalloc(PAGE_SIZE, GFP_KERNEL);
 
-	if (oldsize)
-		memcpy(newldt, pc->ldt, oldsize * LDT_ENTRY_SIZE);
-	oldldt = pc->ldt;
-	memset(newldt + oldsize * LDT_ENTRY_SIZE, 0,
-	       (mincount - oldsize) * LDT_ENTRY_SIZE);
+	if (!new_ldt->entries) {
+		kfree(new_ldt);
+		return NULL;
+	}
 
-	paravirt_alloc_ldt(newldt, mincount);
+	new_ldt->size = size;
+	return new_ldt;
+}
 
-#ifdef CONFIG_X86_64
-	/* CHECKME: Do we really need this ? */
-	wmb();
-#endif
-	pc->ldt = newldt;
-	wmb();
-	pc->size = mincount;
-	wmb();
-
-	if (reload) {
-#ifdef CONFIG_SMP
-		preempt_disable();
-		load_LDT(pc);
-		if (!cpumask_equal(mm_cpumask(current->mm),
-				   cpumask_of(smp_processor_id())))
-			smp_call_function(flush_ldt, current->mm, 1);
-		preempt_enable();
-#else
-		load_LDT(pc);
-#endif
-	}
-	if (oldsize) {
-		paravirt_free_ldt(oldldt, oldsize);
-		if (oldsize * LDT_ENTRY_SIZE > PAGE_SIZE)
-			vfree(oldldt);
-		else
-			put_page(virt_to_page(oldldt));
-	}
-	return 0;
+/* After calling this, the LDT is immutable. */
+static void finalize_ldt_struct(struct ldt_struct *ldt)
+{
+	paravirt_alloc_ldt(ldt->entries, ldt->size);
 }
 
-static inline int copy_ldt(mm_context_t *new, mm_context_t *old)
+/* context.lock is held */
+static void install_ldt(struct mm_struct *current_mm,
+			struct ldt_struct *ldt)
 {
-	int err = alloc_ldt(new, old->size, 0);
-	int i;
+	/* Synchronizes with lockless_dereference in load_mm_ldt. */
+	smp_store_release(&current_mm->context.ldt, ldt);
+
+	/* Activate the LDT for all CPUs using current_mm. */
+	on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true);
+}
 
-	if (err < 0)
-		return err;
+static void free_ldt_struct(struct ldt_struct *ldt)
+{
+	if (likely(!ldt))
+		return;
 
-	for (i = 0; i < old->size; i++)
-		write_ldt_entry(new->ldt, i, old->ldt + i * LDT_ENTRY_SIZE);
-	return 0;
+	paravirt_free_ldt(ldt->entries, ldt->size);
+	if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE)
+		vfree(ldt->entries);
+	else
+		kfree(ldt->entries);
+	kfree(ldt);
 }
 
 /*
@@ -104,17 +105,37 @@ static inline int copy_ldt(mm_context_t *new, mm_context_t *old)
  */
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
+	struct ldt_struct *new_ldt;
 	struct mm_struct *old_mm;
 	int retval = 0;
 
 	mutex_init(&mm->context.lock);
-	mm->context.size = 0;
 	old_mm = current->mm;
-	if (old_mm && old_mm->context.size > 0) {
-		mutex_lock(&old_mm->context.lock);
-		retval = copy_ldt(&mm->context, &old_mm->context);
-		mutex_unlock(&old_mm->context.lock);
+	if (!old_mm) {
+		mm->context.ldt = NULL;
+		return 0;
 	}
+
+	mutex_lock(&old_mm->context.lock);
+	if (!old_mm->context.ldt) {
+		mm->context.ldt = NULL;
+		goto out_unlock;
+	}
+
+	new_ldt = alloc_ldt_struct(old_mm->context.ldt->size);
+	if (!new_ldt) {
+		retval = -ENOMEM;
+		goto out_unlock;
+	}
+
+	memcpy(new_ldt->entries, old_mm->context.ldt->entries,
+	       new_ldt->size * LDT_ENTRY_SIZE);
+	finalize_ldt_struct(new_ldt);
+
+	mm->context.ldt = new_ldt;
+
+out_unlock:
+	mutex_unlock(&old_mm->context.lock);
 	return retval;
 }
 
@@ -125,53 +146,47 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
  */
 void destroy_context(struct mm_struct *mm)
 {
-	if (mm->context.size) {
-#ifdef CONFIG_X86_32
-		/* CHECKME: Can this ever happen ? */
-		if (mm == current->active_mm)
-			clear_LDT();
-#endif
-		paravirt_free_ldt(mm->context.ldt, mm->context.size);
-		if (mm->context.size * LDT_ENTRY_SIZE > PAGE_SIZE)
-			vfree(mm->context.ldt);
-		else
-			put_page(virt_to_page(mm->context.ldt));
-		mm->context.size = 0;
-	}
+	free_ldt_struct(mm->context.ldt);
+	mm->context.ldt = NULL;
 }
 
 static int read_ldt(void __user *ptr, unsigned long bytecount)
 {
-	int err;
+	int retval;
 	unsigned long size;
 	struct mm_struct *mm = current->mm;
 
-	if (!mm->context.size)
-		return 0;
+	mutex_lock(&mm->context.lock);
+
+	if (!mm->context.ldt) {
+		retval = 0;
+		goto out_unlock;
+	}
+
 	if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES)
 		bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES;
 
-	mutex_lock(&mm->context.lock);
-	size = mm->context.size * LDT_ENTRY_SIZE;
+	size = mm->context.ldt->size * LDT_ENTRY_SIZE;
 	if (size > bytecount)
 		size = bytecount;
 
-	err = 0;
-	if (copy_to_user(ptr, mm->context.ldt, size))
-		err = -EFAULT;
-	mutex_unlock(&mm->context.lock);
-	if (err < 0)
-		goto error_return;
+	if (copy_to_user(ptr, mm->context.ldt->entries, size)) {
+		retval = -EFAULT;
+		goto out_unlock;
+	}
+
 	if (size != bytecount) {
-		/* zero-fill the rest */
-		if (clear_user(ptr + size, bytecount - size) != 0) {
-			err = -EFAULT;
-			goto error_return;
+		/* Zero-fill the rest and pretend we read bytecount bytes. */
+		if (clear_user(ptr + size, bytecount - size)) {
+			retval = -EFAULT;
+			goto out_unlock;
 		}
 	}
-	return bytecount;
-error_return:
-	return err;
+	retval = bytecount;
+
+out_unlock:
+	mutex_unlock(&mm->context.lock);
+	return retval;
 }
 
 static int read_default_ldt(void __user *ptr, unsigned long bytecount)
@@ -195,6 +210,8 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 	struct desc_struct ldt;
 	int error;
 	struct user_desc ldt_info;
+	int oldsize, newsize;
+	struct ldt_struct *new_ldt, *old_ldt;
 
 	error = -EINVAL;
 	if (bytecount != sizeof(ldt_info))
@@ -213,34 +230,39 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 			goto out;
 	}
 
-	mutex_lock(&mm->context.lock);
-	if (ldt_info.entry_number >= mm->context.size) {
-		error = alloc_ldt(&current->mm->context,
-				  ldt_info.entry_number + 1, 1);
-		if (error < 0)
-			goto out_unlock;
-	}
-
-	/* Allow LDTs to be cleared by the user. */
-	if (ldt_info.base_addr == 0 && ldt_info.limit == 0) {
-		if (oldmode || LDT_empty(&ldt_info)) {
-			memset(&ldt, 0, sizeof(ldt));
-			goto install;
+	if ((oldmode && !ldt_info.base_addr && !ldt_info.limit) ||
+	    LDT_empty(&ldt_info)) {
+		/* The user wants to clear the entry. */
+		memset(&ldt, 0, sizeof(ldt));
+	} else {
+		if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
+			error = -EINVAL;
+			goto out;
 		}
+
+		fill_ldt(&ldt, &ldt_info);
+		if (oldmode)
+			ldt.avl = 0;
 	}
 
-	if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
-		error = -EINVAL;
+	mutex_lock(&mm->context.lock);
+
+	old_ldt = mm->context.ldt;
+	oldsize = old_ldt ? old_ldt->size : 0;
+	newsize = max((int)(ldt_info.entry_number + 1), oldsize);
+
+	error = -ENOMEM;
+	new_ldt = alloc_ldt_struct(newsize);
+	if (!new_ldt)
 		goto out_unlock;
-	}
 
-	fill_ldt(&ldt, &ldt_info);
-	if (oldmode)
-		ldt.avl = 0;
+	if (old_ldt)
+		memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE);
+	new_ldt->entries[ldt_info.entry_number] = ldt;
+	finalize_ldt_struct(new_ldt);
 
-	/* Install the new entry ...  */
-install:
-	write_ldt_entry(mm->context.ldt, ldt_info.entry_number, &ldt);
+	install_ldt(mm, new_ldt);
+	free_ldt_struct(old_ldt);
 	error = 0;
 
 out_unlock:
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 6fcb49ce50a1..b82e0fdc7edb 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -392,15 +392,15 @@ static __kprobes void default_do_nmi(struct pt_regs *regs)
 }
 
 /*
- * NMIs can hit breakpoints which will cause it to lose its
- * NMI context with the CPU when the breakpoint does an iret.
- */
-#ifdef CONFIG_X86_32
-/*
- * For i386, NMIs use the same stack as the kernel, and we can
- * add a workaround to the iret problem in C (preventing nested
- * NMIs if an NMI takes a trap). Simply have 3 states the NMI
- * can be in:
+ * NMIs can hit breakpoints which will cause it to lose its NMI context
+ * with the CPU when the breakpoint or page fault does an IRET.
+ *
+ * As a result, NMIs can nest if NMIs get unmasked due an IRET during
+ * NMI processing.  On x86_64, the asm glue protects us from nested NMIs
+ * if the outer NMI came from kernel mode, but we can still nest if the
+ * outer NMI came from user mode.
+ *
+ * To handle these nested NMIs, we have three states:
  *
  *  1) not running
  *  2) executing
@@ -414,15 +414,14 @@ static __kprobes void default_do_nmi(struct pt_regs *regs)
  * (Note, the latch is binary, thus multiple NMIs triggering,
  *  when one is running, are ignored. Only one NMI is restarted.)
  *
- * If an NMI hits a breakpoint that executes an iret, another
- * NMI can preempt it. We do not want to allow this new NMI
- * to run, but we want to execute it when the first one finishes.
- * We set the state to "latched", and the exit of the first NMI will
- * perform a dec_return, if the result is zero (NOT_RUNNING), then
- * it will simply exit the NMI handler. If not, the dec_return
- * would have set the state to NMI_EXECUTING (what we want it to
- * be when we are running). In this case, we simply jump back
- * to rerun the NMI handler again, and restart the 'latched' NMI.
+ * If an NMI executes an iret, another NMI can preempt it. We do not
+ * want to allow this new NMI to run, but we want to execute it when the
+ * first one finishes.  We set the state to "latched", and the exit of
+ * the first NMI will perform a dec_return, if the result is zero
+ * (NOT_RUNNING), then it will simply exit the NMI handler. If not, the
+ * dec_return would have set the state to NMI_EXECUTING (what we want it
+ * to be when we are running). In this case, we simply jump back to
+ * rerun the NMI handler again, and restart the 'latched' NMI.
  *
  * No trap (breakpoint or page fault) should be hit before nmi_restart,
  * thus there is no race between the first check of state for NOT_RUNNING
@@ -445,49 +444,36 @@ enum nmi_states {
 static DEFINE_PER_CPU(enum nmi_states, nmi_state);
 static DEFINE_PER_CPU(unsigned long, nmi_cr2);
 
-#define nmi_nesting_preprocess(regs)					\
-	do {								\
-		if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) {	\
-			this_cpu_write(nmi_state, NMI_LATCHED);		\
-			return;						\
-		}							\
-		this_cpu_write(nmi_state, NMI_EXECUTING);		\
-		this_cpu_write(nmi_cr2, read_cr2());			\
-	} while (0);							\
-	nmi_restart:
-
-#define nmi_nesting_postprocess()					\
-	do {								\
-		if (unlikely(this_cpu_read(nmi_cr2) != read_cr2()))	\
-			write_cr2(this_cpu_read(nmi_cr2));		\
-		if (this_cpu_dec_return(nmi_state))			\
-			goto nmi_restart;				\
-	} while (0)
-#else /* x86_64 */
+#ifdef CONFIG_X86_64
 /*
- * In x86_64 things are a bit more difficult. This has the same problem
- * where an NMI hitting a breakpoint that calls iret will remove the
- * NMI context, allowing a nested NMI to enter. What makes this more
- * difficult is that both NMIs and breakpoints have their own stack.
- * When a new NMI or breakpoint is executed, the stack is set to a fixed
- * point. If an NMI is nested, it will have its stack set at that same
- * fixed address that the first NMI had, and will start corrupting the
- * stack. This is handled in entry_64.S, but the same problem exists with
- * the breakpoint stack.
+ * In x86_64, we need to handle breakpoint -> NMI -> breakpoint.  Without
+ * some care, the inner breakpoint will clobber the outer breakpoint's
+ * stack.
  *
- * If a breakpoint is being processed, and the debug stack is being used,
- * if an NMI comes in and also hits a breakpoint, the stack pointer
- * will be set to the same fixed address as the breakpoint that was
- * interrupted, causing that stack to be corrupted. To handle this case,
- * check if the stack that was interrupted is the debug stack, and if
- * so, change the IDT so that new breakpoints will use the current stack
- * and not switch to the fixed address. On return of the NMI, switch back
- * to the original IDT.
+ * If a breakpoint is being processed, and the debug stack is being
+ * used, if an NMI comes in and also hits a breakpoint, the stack
+ * pointer will be set to the same fixed address as the breakpoint that
+ * was interrupted, causing that stack to be corrupted. To handle this
+ * case, check if the stack that was interrupted is the debug stack, and
+ * if so, change the IDT so that new breakpoints will use the current
+ * stack and not switch to the fixed address. On return of the NMI,
+ * switch back to the original IDT.
  */
 static DEFINE_PER_CPU(int, update_debug_stack);
+#endif
 
-static inline void nmi_nesting_preprocess(struct pt_regs *regs)
+dotraplinkage notrace __kprobes void
+do_nmi(struct pt_regs *regs, long error_code)
 {
+	if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) {
+		this_cpu_write(nmi_state, NMI_LATCHED);
+		return;
+	}
+	this_cpu_write(nmi_state, NMI_EXECUTING);
+	this_cpu_write(nmi_cr2, read_cr2());
+nmi_restart:
+
+#ifdef CONFIG_X86_64
 	/*
 	 * If we interrupted a breakpoint, it is possible that
 	 * the nmi handler will have breakpoints too. We need to
@@ -498,22 +484,8 @@ static inline void nmi_nesting_preprocess(struct pt_regs *regs)
 		debug_stack_set_zero();
 		this_cpu_write(update_debug_stack, 1);
 	}
-}
-
-static inline void nmi_nesting_postprocess(void)
-{
-	if (unlikely(this_cpu_read(update_debug_stack))) {
-		debug_stack_reset();
-		this_cpu_write(update_debug_stack, 0);
-	}
-}
 #endif
 
-dotraplinkage notrace __kprobes void
-do_nmi(struct pt_regs *regs, long error_code)
-{
-	nmi_nesting_preprocess(regs);
-
 	nmi_enter();
 
 	inc_irq_stat(__nmi_count);
@@ -523,8 +495,17 @@ do_nmi(struct pt_regs *regs, long error_code)
 
 	nmi_exit();
 
-	/* On i386, may loop back to preprocess */
-	nmi_nesting_postprocess();
+#ifdef CONFIG_X86_64
+	if (unlikely(this_cpu_read(update_debug_stack))) {
+		debug_stack_reset();
+		this_cpu_write(update_debug_stack, 0);
+	}
+#endif
+
+	if (unlikely(this_cpu_read(nmi_cr2) != read_cr2()))
+		write_cr2(this_cpu_read(nmi_cr2));
+	if (this_cpu_dec_return(nmi_state))
+		goto nmi_restart;
 }
 
 void stop_nmi(void)
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 8e9fe8dfd37b..f99825ea4f96 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -122,11 +122,11 @@ void __show_regs(struct pt_regs *regs, int all)
 void release_thread(struct task_struct *dead_task)
 {
 	if (dead_task->mm) {
-		if (dead_task->mm->context.size) {
+		if (dead_task->mm->context.ldt) {
 			pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n",
 				dead_task->comm,
 				dead_task->mm->context.ldt,
-				dead_task->mm->context.size);
+				dead_task->mm->context.ldt->size);
 			BUG();
 		}
 	}
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 9b4d51d0c0d0..0ccb53a9fcd9 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -5,6 +5,7 @@
 #include <linux/mm.h>
 #include <linux/ptrace.h>
 #include <asm/desc.h>
+#include <asm/mmu_context.h>
 
 unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs)
 {
@@ -27,13 +28,14 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re
 		struct desc_struct *desc;
 		unsigned long base;
 
-		seg &= ~7UL;
+		seg >>= 3;
 
 		mutex_lock(&child->mm->context.lock);
-		if (unlikely((seg >> 3) >= child->mm->context.size))
+		if (unlikely(!child->mm->context.ldt ||
+			     seg >= child->mm->context.ldt->size))
 			addr = -1L; /* bogus selector, access would fault */
 		else {
-			desc = child->mm->context.ldt + seg;
+			desc = &child->mm->context.ldt->entries[seg];
 			base = get_desc_base(desc);
 
 			/* 16-bit code segment? */
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index 9b868124128d..274a52b1183e 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -29,7 +29,6 @@
 
 #include <asm/uaccess.h>
 #include <asm/traps.h>
-#include <asm/desc.h>
 #include <asm/user.h>
 #include <asm/i387.h>
 
@@ -185,7 +184,7 @@ void math_emulate(struct math_emu_info *info)
 			math_abort(FPU_info, SIGILL);
 		}
 
-		code_descriptor = LDT_DESCRIPTOR(FPU_CS);
+		code_descriptor = FPU_get_ldt_descriptor(FPU_CS);
 		if (SEG_D_SIZE(code_descriptor)) {
 			/* The above test may be wrong, the book is not clear */
 			/* Segmented 32 bit protected mode */
diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h
index 2c614410a5f3..d342fce49447 100644
--- a/arch/x86/math-emu/fpu_system.h
+++ b/arch/x86/math-emu/fpu_system.h
@@ -16,9 +16,24 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 
-/* s is always from a cpu register, and the cpu does bounds checking
- * during register load --> no further bounds checks needed */
-#define LDT_DESCRIPTOR(s)	(((struct desc_struct *)current->mm->context.ldt)[(s) >> 3])
+#include <asm/desc.h>
+#include <asm/mmu_context.h>
+
+static inline struct desc_struct FPU_get_ldt_descriptor(unsigned seg)
+{
+	static struct desc_struct zero_desc;
+	struct desc_struct ret = zero_desc;
+
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	seg >>= 3;
+	mutex_lock(&current->mm->context.lock);
+	if (current->mm->context.ldt && seg < current->mm->context.ldt->size)
+		ret = current->mm->context.ldt->entries[seg];
+	mutex_unlock(&current->mm->context.lock);
+#endif
+	return ret;
+}
+
 #define SEG_D_SIZE(x)		((x).b & (3 << 21))
 #define SEG_G_BIT(x)		((x).b & (1 << 23))
 #define SEG_GRANULARITY(x)	(((x).b & (1 << 23)) ? 4096 : 1)
diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c
index 6ef5e99380f9..8300db71c2a6 100644
--- a/arch/x86/math-emu/get_address.c
+++ b/arch/x86/math-emu/get_address.c
@@ -20,7 +20,6 @@
 #include <linux/stddef.h>
 
 #include <asm/uaccess.h>
-#include <asm/desc.h>
 
 #include "fpu_system.h"
 #include "exception.h"
@@ -158,7 +157,7 @@ static long pm_address(u_char FPU_modrm, u_char segment,
 		addr->selector = PM_REG_(segment);
 	}
 
-	descriptor = LDT_DESCRIPTOR(PM_REG_(segment));
+	descriptor = FPU_get_ldt_descriptor(addr->selector);
 	base_address = SEG_BASE_ADDR(descriptor);
 	address = base_address + offset;
 	limit = base_address
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 424f4c97a44d..6c8e2f5ce056 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -23,6 +23,7 @@
 #include <asm/debugreg.h>
 #include <asm/fpu-internal.h> /* pcntxt_mask */
 #include <asm/cpu.h>
+#include <asm/mmu_context.h>
 
 #ifdef CONFIG_X86_32
 __visible unsigned long saved_context_ebx;
@@ -157,7 +158,7 @@ static void fix_processor_context(void)
 	syscall_init();				/* This sets MSR_*STAR and related */
 #endif
 	load_TR_desc();				/* This does ltr */
-	load_LDT(&current->active_mm->context);	/* This does lldt */
+	load_mm_ldt(current->active_mm);	/* This does lldt */
 }
 
 /**
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index fa6ade76ef3f..2cbc2f2cf43e 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -480,6 +480,7 @@ static void set_aliased_prot(void *v, pgprot_t prot)
 	pte_t pte;
 	unsigned long pfn;
 	struct page *page;
+	unsigned char dummy;
 
 	ptep = lookup_address((unsigned long)v, &level);
 	BUG_ON(ptep == NULL);
@@ -489,6 +490,32 @@ static void set_aliased_prot(void *v, pgprot_t prot)
 
 	pte = pfn_pte(pfn, prot);
 
+	/*
+	 * Careful: update_va_mapping() will fail if the virtual address
+	 * we're poking isn't populated in the page tables.  We don't
+	 * need to worry about the direct map (that's always in the page
+	 * tables), but we need to be careful about vmap space.  In
+	 * particular, the top level page table can lazily propagate
+	 * entries between processes, so if we've switched mms since we
+	 * vmapped the target in the first place, we might not have the
+	 * top-level page table entry populated.
+	 *
+	 * We disable preemption because we want the same mm active when
+	 * we probe the target and when we issue the hypercall.  We'll
+	 * have the same nominal mm, but if we're a kernel thread, lazy
+	 * mm dropping could change our pgd.
+	 *
+	 * Out of an abundance of caution, this uses __get_user() to fault
+	 * in the target address just in case there's some obscure case
+	 * in which the target address isn't readable.
+	 */
+
+	preempt_disable();
+
+	pagefault_disable();	/* Avoid warnings due to being atomic. */
+	__get_user(dummy, (unsigned char __user __force *)v);
+	pagefault_enable();
+
 	if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
 		BUG();
 
@@ -500,6 +527,8 @@ static void set_aliased_prot(void *v, pgprot_t prot)
 				BUG();
 	} else
 		kmap_flush_unused();
+
+	preempt_enable();
 }
 
 static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
@@ -507,6 +536,17 @@ static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
 	const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE;
 	int i;
 
+	/*
+	 * We need to mark the all aliases of the LDT pages RO.  We
+	 * don't need to call vm_flush_aliases(), though, since that's
+	 * only responsible for flushing aliases out the TLBs, not the
+	 * page tables, and Xen will flush the TLB for us if needed.
+	 *
+	 * To avoid confusing future readers: none of this is necessary
+	 * to load the LDT.  The hypervisor only checks this when the
+	 * LDT is faulted in due to subsequent descriptor access.
+	 */
+
 	for(i = 0; i < entries; i += entries_per_page)
 		set_aliased_prot(ldt + i, PAGE_KERNEL_RO);
 }
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index a573d4bd71d9..47bf1599aa2f 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -703,8 +703,12 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 		return -EINVAL;
 
 	disk = get_gendisk(MKDEV(major, minor), &part);
-	if (!disk || part)
+	if (!disk)
 		return -EINVAL;
+	if (part) {
+		put_disk(disk);
+		return -EINVAL;
+	}
 
 	rcu_read_lock();
 	spin_lock_irq(disk->queue->queue_lock);
diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c
index 7ccc084bf1df..85aa76116a30 100644
--- a/drivers/ata/libata-pmp.c
+++ b/drivers/ata/libata-pmp.c
@@ -460,6 +460,13 @@ static void sata_pmp_quirks(struct ata_port *ap)
 				       ATA_LFLAG_NO_SRST |
 				       ATA_LFLAG_ASSUME_ATA;
 		}
+	} else if (vendor == 0x11ab && devid == 0x4140) {
+		/* Marvell 4140 quirks */
+		ata_for_each_link(link, ap, EDGE) {
+			/* port 4 is for SEMB device and it doesn't like SRST */
+			if (link->pmp == 4)
+				link->flags |= ATA_LFLAG_DISABLED;
+		}
 	}
 }
 
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 6aeaa28f94f0..63ff17fc23df 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -461,6 +461,7 @@ void rbd_warn(struct rbd_device *rbd_dev, const char *fmt, ...)
 #  define rbd_assert(expr)	((void) 0)
 #endif /* !RBD_DEBUG */
 
+static void rbd_osd_copyup_callback(struct rbd_obj_request *obj_request);
 static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request);
 static void rbd_img_parent_read(struct rbd_obj_request *obj_request);
 static void rbd_dev_remove_parent(struct rbd_device *rbd_dev);
@@ -1664,6 +1665,16 @@ static void rbd_osd_stat_callback(struct rbd_obj_request *obj_request)
 	obj_request_done_set(obj_request);
 }
 
+static void rbd_osd_call_callback(struct rbd_obj_request *obj_request)
+{
+	dout("%s: obj %p\n", __func__, obj_request);
+
+	if (obj_request_img_data_test(obj_request))
+		rbd_osd_copyup_callback(obj_request);
+	else
+		obj_request_done_set(obj_request);
+}
+
 static void rbd_osd_req_callback(struct ceph_osd_request *osd_req,
 				struct ceph_msg *msg)
 {
@@ -1702,6 +1713,8 @@ static void rbd_osd_req_callback(struct ceph_osd_request *osd_req,
 		rbd_osd_stat_callback(obj_request);
 		break;
 	case CEPH_OSD_OP_CALL:
+		rbd_osd_call_callback(obj_request);
+		break;
 	case CEPH_OSD_OP_NOTIFY_ACK:
 	case CEPH_OSD_OP_WATCH:
 		rbd_osd_trivial_callback(obj_request);
@@ -2293,13 +2306,15 @@ out_unwind:
 }
 
 static void
-rbd_img_obj_copyup_callback(struct rbd_obj_request *obj_request)
+rbd_osd_copyup_callback(struct rbd_obj_request *obj_request)
 {
 	struct rbd_img_request *img_request;
 	struct rbd_device *rbd_dev;
 	struct page **pages;
 	u32 page_count;
 
+	dout("%s: obj %p\n", __func__, obj_request);
+
 	rbd_assert(obj_request->type == OBJ_REQUEST_BIO);
 	rbd_assert(obj_request_img_data_test(obj_request));
 	img_request = obj_request->img_request;
@@ -2325,9 +2340,7 @@ rbd_img_obj_copyup_callback(struct rbd_obj_request *obj_request)
 	if (!obj_request->result)
 		obj_request->xferred = obj_request->length;
 
-	/* Finish up with the normal image object callback */
-
-	rbd_img_obj_callback(obj_request);
+	obj_request_done_set(obj_request);
 }
 
 static void
@@ -2424,7 +2437,6 @@ rbd_img_obj_parent_read_full_callback(struct rbd_img_request *img_request)
 
 	/* All set, send it off. */
 
-	orig_request->callback = rbd_img_obj_copyup_callback;
 	osdc = &rbd_dev->rbd_client->client->osdc;
 	img_result = rbd_obj_request_submit(osdc, orig_request);
 	if (!img_result)
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 3bb5efdcdc8a..7d0eb3f8d629 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1090,8 +1090,10 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
 				 * Add the used indirect page back to the list of
 				 * available pages for indirect grefs.
 				 */
-				indirect_page = pfn_to_page(s->indirect_grants[i]->pfn);
-				list_add(&indirect_page->lru, &info->indirect_pages);
+				if (!info->feature_persistent) {
+					indirect_page = pfn_to_page(s->indirect_grants[i]->pfn);
+					list_add(&indirect_page->lru, &info->indirect_pages);
+				}
 				s->indirect_grants[i]->gref = GRANT_INVALID_REF;
 				list_add_tail(&s->indirect_grants[i]->node, &info->grants);
 			}
diff --git a/drivers/char/hw_random/via-rng.c b/drivers/char/hw_random/via-rng.c
index e737772ad69a..de5a6dcfb3e2 100644
--- a/drivers/char/hw_random/via-rng.c
+++ b/drivers/char/hw_random/via-rng.c
@@ -221,7 +221,7 @@ static void __exit mod_exit(void)
 module_init(mod_init);
 module_exit(mod_exit);
 
-static struct x86_cpu_id via_rng_cpu_id[] = {
+static struct x86_cpu_id __maybe_unused via_rng_cpu_id[] = {
 	X86_FEATURE_MATCH(X86_FEATURE_XSTORE),
 	{}
 };
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index e5bdd1a2f541..25ed69ffd8dd 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -2783,7 +2783,7 @@ static int wait_for_msg_done(struct smi_info *smi_info)
 		    smi_result == SI_SM_CALL_WITH_TICK_DELAY) {
 			schedule_timeout_uninterruptible(1);
 			smi_result = smi_info->handlers->event(
-				smi_info->si_sm, 100);
+				smi_info->si_sm, jiffies_to_usecs(1));
 		} else if (smi_result == SI_SM_CALL_WITHOUT_DELAY) {
 			smi_result = smi_info->handlers->event(
 				smi_info->si_sm, 0);
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index 21180d6cad6e..7cb51b3bb79e 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -915,7 +915,6 @@ static int ablk_perform(struct ablkcipher_request *req, int encrypt)
 		crypt->mode |= NPE_OP_NOT_IN_PLACE;
 		/* This was never tested by Intel
 		 * for more than one dst buffer, I think. */
-		BUG_ON(req->dst->length < nbytes);
 		req_ctx->dst = NULL;
 		if (!chainup_buffers(dev, req->dst, nbytes, &dst_hook,
 					flags, DMA_FROM_DEVICE))
diff --git a/drivers/edac/ppc4xx_edac.c b/drivers/edac/ppc4xx_edac.c
index ef6b7e08f485..5c361f3c66aa 100644
--- a/drivers/edac/ppc4xx_edac.c
+++ b/drivers/edac/ppc4xx_edac.c
@@ -921,7 +921,7 @@ static int ppc4xx_edac_init_csrows(struct mem_ctl_info *mci, u32 mcopt1)
 	 */
 
 	for (row = 0; row < mci->nr_csrows; row++) {
-		struct csrow_info *csi = &mci->csrows[row];
+		struct csrow_info *csi = mci->csrows[row];
 
 		/*
 		 * Get the configuration settings for this
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index 68ce36056019..8cac69819054 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -1271,10 +1271,15 @@ struct radeon_encoder_lvds *radeon_combios_get_lvds_info(struct radeon_encoder
 
 			if ((RBIOS16(tmp) == lvds->native_mode.hdisplay) &&
 			    (RBIOS16(tmp + 2) == lvds->native_mode.vdisplay)) {
+				u32 hss = (RBIOS16(tmp + 21) - RBIOS16(tmp + 19) - 1) * 8;
+
+				if (hss > lvds->native_mode.hdisplay)
+					hss = (10 - 1) * 8;
+
 				lvds->native_mode.htotal = lvds->native_mode.hdisplay +
 					(RBIOS16(tmp + 17) - RBIOS16(tmp + 19)) * 8;
 				lvds->native_mode.hsync_start = lvds->native_mode.hdisplay +
-					(RBIOS16(tmp + 21) - RBIOS16(tmp + 19) - 1) * 8;
+					hss;
 				lvds->native_mode.hsync_end = lvds->native_mode.hsync_start +
 					(RBIOS8(tmp + 23) * 8);
 
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 2e65d7791060..6da09931a987 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -218,6 +218,7 @@
 #define USB_DEVICE_ID_CHICONY_TACTICAL_PAD	0x0418
 #define USB_DEVICE_ID_CHICONY_MULTI_TOUCH	0xb19d
 #define USB_DEVICE_ID_CHICONY_WIRELESS	0x0618
+#define USB_DEVICE_ID_CHICONY_PIXART_USB_OPTICAL_MOUSE	0x1053
 #define USB_DEVICE_ID_CHICONY_WIRELESS2	0x1123
 #define USB_DEVICE_ID_CHICONY_AK1D	0x1125
 
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index 8f884a6a8a8f..7bc98db768eb 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -69,6 +69,7 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_PRO_PEDALS, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_3AXIS_5BUTTON_STICK, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_AXIS_295, HID_QUIRK_NOGET },
+	{ USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_PIXART_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_009B, HID_QUIRK_ALWAYS_POLL },
diff --git a/drivers/input/touchscreen/usbtouchscreen.c b/drivers/input/touchscreen/usbtouchscreen.c
index e565530e3596..5679cd9003cc 100644
--- a/drivers/input/touchscreen/usbtouchscreen.c
+++ b/drivers/input/touchscreen/usbtouchscreen.c
@@ -628,6 +628,9 @@ static int dmc_tsc10_init(struct usbtouch_usb *usbtouch)
 		goto err_out;
 	}
 
+	/* TSC-25 data sheet specifies a delay after the RESET command */
+	msleep(150);
+
 	/* set coordinate output rate */
 	buf[0] = buf[1] = 0xFF;
 	ret = usb_control_msg(dev, usb_rcvctrlpipe (dev, 0),
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 03b2edd35e19..64c4d0c2ca80 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -564,6 +564,8 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 	if (err)
 		return err;
 
+	err = -EINVAL;
+
 	sb = kmap_atomic(sb_page);
 
 	chunksize = le32_to_cpu(sb->chunksize);
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index b63095c73b5f..7e3da70ed646 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -1295,8 +1295,8 @@ static int __release_metadata_snap(struct dm_pool_metadata *pmd)
 		return r;
 
 	disk_super = dm_block_data(copy);
-	dm_sm_dec_block(pmd->metadata_sm, le64_to_cpu(disk_super->data_mapping_root));
-	dm_sm_dec_block(pmd->metadata_sm, le64_to_cpu(disk_super->device_details_root));
+	dm_btree_del(&pmd->info, le64_to_cpu(disk_super->data_mapping_root));
+	dm_btree_del(&pmd->details_info, le64_to_cpu(disk_super->device_details_root));
 	dm_sm_dec_block(pmd->metadata_sm, held_root);
 
 	return dm_tm_unlock(pmd->tm, copy);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 2394b5bbeab9..1c512dc1f17f 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5642,8 +5642,7 @@ static int get_bitmap_file(struct mddev * mddev, void __user * arg)
 	char *ptr, *buf = NULL;
 	int err = -ENOMEM;
 
-	file = kmalloc(sizeof(*file), GFP_NOIO);
-
+	file = kzalloc(sizeof(*file), GFP_NOIO);
 	if (!file)
 		goto out;
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 633b6e1e7d4d..1cb7642c1ba9 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -327,7 +327,7 @@ static void raid1_end_read_request(struct bio *bio, int error)
 		spin_lock_irqsave(&conf->device_lock, flags);
 		if (r1_bio->mddev->degraded == conf->raid_disks ||
 		    (r1_bio->mddev->degraded == conf->raid_disks-1 &&
-		     !test_bit(Faulty, &conf->mirrors[mirror].rdev->flags)))
+		     test_bit(In_sync, &conf->mirrors[mirror].rdev->flags)))
 			uptodate = 1;
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 	}
@@ -1382,6 +1382,7 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 {
 	char b[BDEVNAME_SIZE];
 	struct r1conf *conf = mddev->private;
+	unsigned long flags;
 
 	/*
 	 * If it is not operational, then we have already marked it as dead
@@ -1401,14 +1402,13 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 		return;
 	}
 	set_bit(Blocked, &rdev->flags);
+	spin_lock_irqsave(&conf->device_lock, flags);
 	if (test_and_clear_bit(In_sync, &rdev->flags)) {
-		unsigned long flags;
-		spin_lock_irqsave(&conf->device_lock, flags);
 		mddev->degraded++;
 		set_bit(Faulty, &rdev->flags);
-		spin_unlock_irqrestore(&conf->device_lock, flags);
 	} else
 		set_bit(Faulty, &rdev->flags);
+	spin_unlock_irqrestore(&conf->device_lock, flags);
 	/*
 	 * if recovery is running, make sure it aborts.
 	 */
@@ -1466,7 +1466,10 @@ static int raid1_spare_active(struct mddev *mddev)
 	 * Find all failed disks within the RAID1 configuration 
 	 * and mark them readable.
 	 * Called under mddev lock, so rcu protection not needed.
+	 * device_lock used to avoid races with raid1_end_read_request
+	 * which expects 'In_sync' flags and ->degraded to be consistent.
 	 */
+	spin_lock_irqsave(&conf->device_lock, flags);
 	for (i = 0; i < conf->raid_disks; i++) {
 		struct md_rdev *rdev = conf->mirrors[i].rdev;
 		struct md_rdev *repl = conf->mirrors[conf->raid_disks + i].rdev;
@@ -1496,7 +1499,6 @@ static int raid1_spare_active(struct mddev *mddev)
 			sysfs_notify_dirent_safe(rdev->sysfs_state);
 		}
 	}
-	spin_lock_irqsave(&conf->device_lock, flags);
 	mddev->degraded -= count;
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 
diff --git a/drivers/mmc/host/sdhci-esdhc.h b/drivers/mmc/host/sdhci-esdhc.h
index a2a06420e463..ebff71092743 100644
--- a/drivers/mmc/host/sdhci-esdhc.h
+++ b/drivers/mmc/host/sdhci-esdhc.h
@@ -47,7 +47,7 @@
 #define ESDHC_DMA_SYSCTL	0x40c
 #define ESDHC_DMA_SNOOP		0x00000040
 
-#define ESDHC_HOST_CONTROL_RES	0x05
+#define ESDHC_HOST_CONTROL_RES	0x01
 
 static inline void esdhc_set_clock(struct sdhci_host *host, unsigned int clock,
 				   unsigned int host_clock)
diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c
index 561c6b4907a1..b80766699249 100644
--- a/drivers/mmc/host/sdhci-pxav3.c
+++ b/drivers/mmc/host/sdhci-pxav3.c
@@ -257,6 +257,7 @@ static int sdhci_pxav3_probe(struct platform_device *pdev)
 			goto err_of_parse;
 		sdhci_get_of_property(pdev);
 		pdata = pxav3_get_mmc_pdata(dev);
+		pdev->dev.platform_data = pdata;
 	} else if (pdata) {
 		/* on-chip device */
 		if (pdata->flags & PXA_FLAG_CARD_PERMANENT)
diff --git a/drivers/scsi/3w-xxxx.h b/drivers/scsi/3w-xxxx.h
index 1d31858766ce..6f65e663d393 100644
--- a/drivers/scsi/3w-xxxx.h
+++ b/drivers/scsi/3w-xxxx.h
@@ -387,6 +387,8 @@ typedef struct TAG_TW_Passthru
 	unsigned char padding[12];
 } TW_Passthru;
 
+#pragma pack()
+
 typedef struct TAG_TW_Device_Extension {
 	u32			base_addr;
 	unsigned long		*alignment_virtual_address[TW_Q_LENGTH];
@@ -425,6 +427,4 @@ typedef struct TAG_TW_Device_Extension {
 	wait_queue_head_t	ioctl_wqueue;
 } TW_Device_Extension;
 
-#pragma pack()
-
 #endif /* _3W_XXXX_H */
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 5f841652886e..0f6412db121c 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -592,9 +592,10 @@ static void ipr_trc_hook(struct ipr_cmnd *ipr_cmd,
 {
 	struct ipr_trace_entry *trace_entry;
 	struct ipr_ioa_cfg *ioa_cfg = ipr_cmd->ioa_cfg;
+	unsigned int trace_index;
 
-	trace_entry = &ioa_cfg->trace[atomic_add_return
-			(1, &ioa_cfg->trace_index)%IPR_NUM_TRACE_ENTRIES];
+	trace_index = atomic_add_return(1, &ioa_cfg->trace_index) & IPR_TRACE_INDEX_MASK;
+	trace_entry = &ioa_cfg->trace[trace_index];
 	trace_entry->time = jiffies;
 	trace_entry->op_code = ipr_cmd->ioarcb.cmd_pkt.cdb[0];
 	trace_entry->type = type;
@@ -1044,10 +1045,15 @@ static void ipr_send_blocking_cmd(struct ipr_cmnd *ipr_cmd,
 
 static int ipr_get_hrrq_index(struct ipr_ioa_cfg *ioa_cfg)
 {
+	unsigned int hrrq;
+
 	if (ioa_cfg->hrrq_num == 1)
-		return 0;
-	else
-		return (atomic_add_return(1, &ioa_cfg->hrrq_index) % (ioa_cfg->hrrq_num - 1)) + 1;
+		hrrq = 0;
+	else {
+		hrrq = atomic_add_return(1, &ioa_cfg->hrrq_index);
+		hrrq = (hrrq % (ioa_cfg->hrrq_num - 1)) + 1;
+	}
+	return hrrq;
 }
 
 /**
@@ -6179,21 +6185,23 @@ static void ipr_scsi_done(struct ipr_cmnd *ipr_cmd)
 	struct ipr_ioa_cfg *ioa_cfg = ipr_cmd->ioa_cfg;
 	struct scsi_cmnd *scsi_cmd = ipr_cmd->scsi_cmd;
 	u32 ioasc = be32_to_cpu(ipr_cmd->s.ioasa.hdr.ioasc);
-	unsigned long hrrq_flags;
+	unsigned long lock_flags;
 
 	scsi_set_resid(scsi_cmd, be32_to_cpu(ipr_cmd->s.ioasa.hdr.residual_data_len));
 
 	if (likely(IPR_IOASC_SENSE_KEY(ioasc) == 0)) {
 		scsi_dma_unmap(scsi_cmd);
 
-		spin_lock_irqsave(ipr_cmd->hrrq->lock, hrrq_flags);
+		spin_lock_irqsave(ipr_cmd->hrrq->lock, lock_flags);
 		list_add_tail(&ipr_cmd->queue, &ipr_cmd->hrrq->hrrq_free_q);
 		scsi_cmd->scsi_done(scsi_cmd);
-		spin_unlock_irqrestore(ipr_cmd->hrrq->lock, hrrq_flags);
+		spin_unlock_irqrestore(ipr_cmd->hrrq->lock, lock_flags);
 	} else {
-		spin_lock_irqsave(ipr_cmd->hrrq->lock, hrrq_flags);
+		spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
+		spin_lock(&ipr_cmd->hrrq->_lock);
 		ipr_erp_start(ioa_cfg, ipr_cmd);
-		spin_unlock_irqrestore(ipr_cmd->hrrq->lock, hrrq_flags);
+		spin_unlock(&ipr_cmd->hrrq->_lock);
+		spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
 	}
 }
 
diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h
index f6d379725a00..06b3b4bb2911 100644
--- a/drivers/scsi/ipr.h
+++ b/drivers/scsi/ipr.h
@@ -1462,6 +1462,7 @@ struct ipr_ioa_cfg {
 
 #define IPR_NUM_TRACE_INDEX_BITS	8
 #define IPR_NUM_TRACE_ENTRIES		(1 << IPR_NUM_TRACE_INDEX_BITS)
+#define IPR_TRACE_INDEX_MASK		(IPR_NUM_TRACE_ENTRIES - 1)
 #define IPR_TRACE_SIZE	(sizeof(struct ipr_trace_entry) * IPR_NUM_TRACE_ENTRIES)
 	char trace_start[8];
 #define IPR_TRACE_START_LABEL			"trace"
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index ff44b3c2cff2..9903f1d58d3e 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -1262,9 +1262,9 @@ static int st_open(struct inode *inode, struct file *filp)
 	spin_lock(&st_use_lock);
 	STp->in_use = 0;
 	spin_unlock(&st_use_lock);
-	scsi_tape_put(STp);
 	if (resumed)
 		scsi_autopm_put_device(STp->device);
+	scsi_tape_put(STp);
 	return retval;
 
 }
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 8ac1800eef06..6f3aa50699f1 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -3933,7 +3933,13 @@ get_immediate:
 	}
 
 transport_err:
-	iscsit_take_action_for_connection_exit(conn);
+	/*
+	 * Avoid the normal connection failure code-path if this connection
+	 * is still within LOGIN mode, and iscsi_np process context is
+	 * responsible for cleaning up the early connection failure.
+	 */
+	if (conn->conn_state != TARG_CONN_STATE_IN_LOGIN)
+		iscsit_take_action_for_connection_exit(conn);
 out:
 	return 0;
 }
@@ -4019,7 +4025,7 @@ reject:
 
 int iscsi_target_rx_thread(void *arg)
 {
-	int ret;
+	int ret, rc;
 	u8 buffer[ISCSI_HDR_LEN], opcode;
 	u32 checksum = 0, digest = 0;
 	struct iscsi_conn *conn = arg;
@@ -4029,10 +4035,16 @@ int iscsi_target_rx_thread(void *arg)
 	 * connection recovery / failure event can be triggered externally.
 	 */
 	allow_signal(SIGINT);
+	/*
+	 * Wait for iscsi_post_login_handler() to complete before allowing
+	 * incoming iscsi/tcp socket I/O, and/or failing the connection.
+	 */
+	rc = wait_for_completion_interruptible(&conn->rx_login_comp);
+	if (rc < 0)
+		return 0;
 
 	if (conn->conn_transport->transport_type == ISCSI_INFINIBAND) {
 		struct completion comp;
-		int rc;
 
 		init_completion(&comp);
 		rc = wait_for_completion_interruptible(&comp);
@@ -4474,7 +4486,18 @@ static void iscsit_logout_post_handler_closesession(
 	struct iscsi_conn *conn)
 {
 	struct iscsi_session *sess = conn->sess;
-	int sleep = cmpxchg(&conn->tx_thread_active, true, false);
+	int sleep = 1;
+	/*
+	 * Traditional iscsi/tcp will invoke this logic from TX thread
+	 * context during session logout, so clear tx_thread_active and
+	 * sleep if iscsit_close_connection() has not already occured.
+	 *
+	 * Since iser-target invokes this logic from it's own workqueue,
+	 * always sleep waiting for RX/TX thread shutdown to complete
+	 * within iscsit_close_connection().
+	 */
+	if (conn->conn_transport->transport_type == ISCSI_TCP)
+		sleep = cmpxchg(&conn->tx_thread_active, true, false);
 
 	atomic_set(&conn->conn_logout_remove, 0);
 	complete(&conn->conn_logout_comp);
@@ -4488,7 +4511,10 @@ static void iscsit_logout_post_handler_closesession(
 static void iscsit_logout_post_handler_samecid(
 	struct iscsi_conn *conn)
 {
-	int sleep = cmpxchg(&conn->tx_thread_active, true, false);
+	int sleep = 1;
+
+	if (conn->conn_transport->transport_type == ISCSI_TCP)
+		sleep = cmpxchg(&conn->tx_thread_active, true, false);
 
 	atomic_set(&conn->conn_logout_remove, 0);
 	complete(&conn->conn_logout_comp);
@@ -4707,6 +4733,7 @@ int iscsit_release_sessions_for_tpg(struct iscsi_portal_group *tpg, int force)
 	struct iscsi_session *sess;
 	struct se_portal_group *se_tpg = &tpg->tpg_se_tpg;
 	struct se_session *se_sess, *se_sess_tmp;
+	LIST_HEAD(free_list);
 	int session_count = 0;
 
 	spin_lock_bh(&se_tpg->session_lock);
@@ -4728,14 +4755,17 @@ int iscsit_release_sessions_for_tpg(struct iscsi_portal_group *tpg, int force)
 		}
 		atomic_set(&sess->session_reinstatement, 1);
 		spin_unlock(&sess->conn_lock);
-		spin_unlock_bh(&se_tpg->session_lock);
 
-		iscsit_free_session(sess);
-		spin_lock_bh(&se_tpg->session_lock);
+		list_move_tail(&se_sess->sess_list, &free_list);
+	}
+	spin_unlock_bh(&se_tpg->session_lock);
+
+	list_for_each_entry_safe(se_sess, se_sess_tmp, &free_list, sess_list) {
+		sess = (struct iscsi_session *)se_sess->fabric_sess_ptr;
 
+		iscsit_free_session(sess);
 		session_count++;
 	}
-	spin_unlock_bh(&se_tpg->session_lock);
 
 	pr_debug("Released %d iSCSI Session(s) from Target Portal"
 			" Group: %hu\n", session_count, tpg->tpgt);
diff --git a/drivers/target/iscsi/iscsi_target_core.h b/drivers/target/iscsi/iscsi_target_core.h
index 1c232c509dae..cc0cb60eb7bd 100644
--- a/drivers/target/iscsi/iscsi_target_core.h
+++ b/drivers/target/iscsi/iscsi_target_core.h
@@ -604,6 +604,7 @@ struct iscsi_conn {
 	int			bitmap_id;
 	int			rx_thread_active;
 	struct task_struct	*rx_thread;
+	struct completion	rx_login_comp;
 	int			tx_thread_active;
 	struct task_struct	*tx_thread;
 	/* list_head for session connection list */
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 9d5762011413..899b756fe290 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -83,6 +83,7 @@ static struct iscsi_login *iscsi_login_init_conn(struct iscsi_conn *conn)
 	init_completion(&conn->conn_logout_comp);
 	init_completion(&conn->rx_half_close_comp);
 	init_completion(&conn->tx_half_close_comp);
+	init_completion(&conn->rx_login_comp);
 	spin_lock_init(&conn->cmd_lock);
 	spin_lock_init(&conn->conn_usage_lock);
 	spin_lock_init(&conn->immed_queue_lock);
@@ -717,6 +718,7 @@ int iscsit_start_kthreads(struct iscsi_conn *conn)
 
 	return 0;
 out_tx:
+	send_sig(SIGINT, conn->tx_thread, 1);
 	kthread_stop(conn->tx_thread);
 	conn->tx_thread_active = false;
 out_bitmap:
@@ -727,7 +729,7 @@ out_bitmap:
 	return ret;
 }
 
-int iscsi_post_login_handler(
+void iscsi_post_login_handler(
 	struct iscsi_np *np,
 	struct iscsi_conn *conn,
 	u8 zero_tsih)
@@ -737,7 +739,6 @@ int iscsi_post_login_handler(
 	struct se_session *se_sess = sess->se_sess;
 	struct iscsi_portal_group *tpg = ISCSI_TPG_S(sess);
 	struct se_portal_group *se_tpg = &tpg->tpg_se_tpg;
-	int rc;
 
 	iscsit_inc_conn_usage_count(conn);
 
@@ -778,10 +779,6 @@ int iscsi_post_login_handler(
 			sess->sess_ops->InitiatorName);
 		spin_unlock_bh(&sess->conn_lock);
 
-		rc = iscsit_start_kthreads(conn);
-		if (rc)
-			return rc;
-
 		iscsi_post_login_start_timers(conn);
 		/*
 		 * Determine CPU mask to ensure connection's RX and TX kthreads
@@ -790,15 +787,20 @@ int iscsi_post_login_handler(
 		iscsit_thread_get_cpumask(conn);
 		conn->conn_rx_reset_cpumask = 1;
 		conn->conn_tx_reset_cpumask = 1;
-
+		/*
+		 * Wakeup the sleeping iscsi_target_rx_thread() now that
+		 * iscsi_conn is in TARG_CONN_STATE_LOGGED_IN state.
+		 */
+		complete(&conn->rx_login_comp);
 		iscsit_dec_conn_usage_count(conn);
+
 		if (stop_timer) {
 			spin_lock_bh(&se_tpg->session_lock);
 			iscsit_stop_time2retain_timer(sess);
 			spin_unlock_bh(&se_tpg->session_lock);
 		}
 		iscsit_dec_session_usage_count(sess);
-		return 0;
+		return;
 	}
 
 	iscsi_set_session_parameters(sess->sess_ops, conn->param_list, 1);
@@ -839,10 +841,6 @@ int iscsi_post_login_handler(
 		" iSCSI Target Portal Group: %hu\n", tpg->nsessions, tpg->tpgt);
 	spin_unlock_bh(&se_tpg->session_lock);
 
-	rc = iscsit_start_kthreads(conn);
-	if (rc)
-		return rc;
-
 	iscsi_post_login_start_timers(conn);
 	/*
 	 * Determine CPU mask to ensure connection's RX and TX kthreads
@@ -851,10 +849,12 @@ int iscsi_post_login_handler(
 	iscsit_thread_get_cpumask(conn);
 	conn->conn_rx_reset_cpumask = 1;
 	conn->conn_tx_reset_cpumask = 1;
-
+	/*
+	 * Wakeup the sleeping iscsi_target_rx_thread() now that
+	 * iscsi_conn is in TARG_CONN_STATE_LOGGED_IN state.
+	 */
+	complete(&conn->rx_login_comp);
 	iscsit_dec_conn_usage_count(conn);
-
-	return 0;
 }
 
 static void iscsi_handle_login_thread_timeout(unsigned long data)
@@ -1419,23 +1419,12 @@ static int __iscsi_target_login_thread(struct iscsi_np *np)
 	if (ret < 0)
 		goto new_sess_out;
 
-	if (!conn->sess) {
-		pr_err("struct iscsi_conn session pointer is NULL!\n");
-		goto new_sess_out;
-	}
-
 	iscsi_stop_login_thread_timer(np);
 
-	if (signal_pending(current))
-		goto new_sess_out;
-
 	if (ret == 1) {
 		tpg_np = conn->tpg_np;
 
-		ret = iscsi_post_login_handler(np, conn, zero_tsih);
-		if (ret < 0)
-			goto new_sess_out;
-
+		iscsi_post_login_handler(np, conn, zero_tsih);
 		iscsit_deaccess_np(np, tpg, tpg_np);
 	}
 
diff --git a/drivers/target/iscsi/iscsi_target_login.h b/drivers/target/iscsi/iscsi_target_login.h
index 29d098324b7f..55cbf4533544 100644
--- a/drivers/target/iscsi/iscsi_target_login.h
+++ b/drivers/target/iscsi/iscsi_target_login.h
@@ -12,7 +12,8 @@ extern int iscsit_accept_np(struct iscsi_np *, struct iscsi_conn *);
 extern int iscsit_get_login_rx(struct iscsi_conn *, struct iscsi_login *);
 extern int iscsit_put_login_tx(struct iscsi_conn *, struct iscsi_login *, u32);
 extern void iscsit_free_conn(struct iscsi_np *, struct iscsi_conn *);
-extern int iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8);
+extern int iscsit_start_kthreads(struct iscsi_conn *);
+extern void iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8);
 extern void iscsi_target_login_sess_out(struct iscsi_conn *, struct iscsi_np *,
 				bool, bool);
 extern int iscsi_target_login_thread(void *);
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index 76dc32fc5e1b..a801cad91742 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -17,6 +17,7 @@
  ******************************************************************************/
 
 #include <linux/ctype.h>
+#include <linux/kthread.h>
 #include <scsi/iscsi_proto.h>
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
@@ -361,10 +362,24 @@ static int iscsi_target_do_tx_login_io(struct iscsi_conn *conn, struct iscsi_log
 		ntohl(login_rsp->statsn), login->rsp_length);
 
 	padding = ((-login->rsp_length) & 3);
+	/*
+	 * Before sending the last login response containing the transition
+	 * bit for full-feature-phase, go ahead and start up TX/RX threads
+	 * now to avoid potential resource allocation failures after the
+	 * final login response has been sent.
+	 */
+	if (login->login_complete) {
+		int rc = iscsit_start_kthreads(conn);
+		if (rc) {
+			iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
+					    ISCSI_LOGIN_STATUS_NO_RESOURCES);
+			return -1;
+		}
+	}
 
 	if (conn->conn_transport->iscsit_put_login_tx(conn, login,
 					login->rsp_length + padding) < 0)
-		return -1;
+		goto err;
 
 	login->rsp_length		= 0;
 	mutex_lock(&sess->cmdsn_mutex);
@@ -373,6 +388,23 @@ static int iscsi_target_do_tx_login_io(struct iscsi_conn *conn, struct iscsi_log
 	mutex_unlock(&sess->cmdsn_mutex);
 
 	return 0;
+
+err:
+	if (login->login_complete) {
+		if (conn->rx_thread && conn->rx_thread_active) {
+			send_sig(SIGINT, conn->rx_thread, 1);
+			kthread_stop(conn->rx_thread);
+		}
+		if (conn->tx_thread && conn->tx_thread_active) {
+			send_sig(SIGINT, conn->tx_thread, 1);
+			kthread_stop(conn->tx_thread);
+		}
+		spin_lock(&iscsit_global->ts_bitmap_lock);
+		bitmap_release_region(iscsit_global->ts_bitmap, conn->bitmap_id,
+				      get_order(1));
+		spin_unlock(&iscsit_global->ts_bitmap_lock);
+	}
+	return -1;
 }
 
 static void iscsi_target_sk_data_ready(struct sock *sk, int count)
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index abb36165515a..55b3aa33bc06 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -480,10 +480,13 @@ static void xhci_hub_report_usb3_link_state(struct xhci_hcd *xhci,
 	u32 pls = status_reg & PORT_PLS_MASK;
 
 	/* resume state is a xHCI internal state.
-	 * Do not report it to usb core.
+	 * Do not report it to usb core, instead, pretend to be U3,
+	 * thus usb core knows it's not ready for transfer
 	 */
-	if (pls == XDEV_RESUME)
+	if (pls == XDEV_RESUME) {
+		*status |= USB_SS_PORT_LS_U3;
 		return;
+	}
 
 	/* When the CAS bit is set then warm reset
 	 * should be performed on port
@@ -583,7 +586,14 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd,
 		status |= USB_PORT_STAT_C_RESET << 16;
 	/* USB3.0 only */
 	if (hcd->speed == HCD_USB3) {
-		if ((raw_port_status & PORT_PLC))
+		/* Port link change with port in resume state should not be
+		 * reported to usbcore, as this is an internal state to be
+		 * handled by xhci driver. Reporting PLC to usbcore may
+		 * cause usbcore clearing PLC first and port change event
+		 * irq won't be generated.
+		 */
+		if ((raw_port_status & PORT_PLC) &&
+			(raw_port_status & PORT_PLS_MASK) != XDEV_RESUME)
 			status |= USB_PORT_STAT_C_LINK_STATE << 16;
 		if ((raw_port_status & PORT_WRC))
 			status |= USB_PORT_STAT_C_BH_RESET << 16;
@@ -1117,10 +1127,10 @@ int xhci_bus_suspend(struct usb_hcd *hcd)
 	spin_lock_irqsave(&xhci->lock, flags);
 
 	if (hcd->self.root_hub->do_remote_wakeup) {
-		if (bus_state->resuming_ports) {
+		if (bus_state->resuming_ports ||	/* USB2 */
+		    bus_state->port_remote_wakeup) {	/* USB3 */
 			spin_unlock_irqrestore(&xhci->lock, flags);
-			xhci_dbg(xhci, "suspend failed because "
-						"a port is resuming\n");
+			xhci_dbg(xhci, "suspend failed because a port is resuming\n");
 			return -EBUSY;
 		}
 	}
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 07aafa50f453..66deb0af258e 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -86,7 +86,7 @@ dma_addr_t xhci_trb_virt_to_dma(struct xhci_segment *seg,
 		return 0;
 	/* offset in TRBs */
 	segment_offset = trb - seg->trbs;
-	if (segment_offset > TRBS_PER_SEGMENT)
+	if (segment_offset >= TRBS_PER_SEGMENT)
 		return 0;
 	return seg->dma + (segment_offset * sizeof(*trb));
 }
@@ -1707,6 +1707,9 @@ static void handle_port_status(struct xhci_hcd *xhci,
 		usb_hcd_resume_root_hub(hcd);
 	}
 
+	if (hcd->speed == HCD_USB3 && (temp & PORT_PLS_MASK) == XDEV_INACTIVE)
+		bus_state->port_remote_wakeup &= ~(1 << faked_port_index);
+
 	if ((temp & PORT_PLC) && (temp & PORT_PLS_MASK) == XDEV_RESUME) {
 		xhci_dbg(xhci, "port resume event for port %d\n", port_id);
 
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index e0ccc95c91e2..00686a8c4fa0 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -3423,6 +3423,9 @@ int xhci_discover_or_reset_device(struct usb_hcd *hcd, struct usb_device *udev)
 			return -EINVAL;
 	}
 
+	if (virt_dev->tt_info)
+		old_active_eps = virt_dev->tt_info->active_eps;
+
 	if (virt_dev->udev != udev) {
 		/* If the virt_dev and the udev does not match, this virt_dev
 		 * may belong to another udev.
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 510e9c0efd18..8686a06d83d4 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -285,6 +285,7 @@ struct xhci_op_regs {
 #define XDEV_U0		(0x0 << 5)
 #define XDEV_U2		(0x2 << 5)
 #define XDEV_U3		(0x3 << 5)
+#define XDEV_INACTIVE	(0x6 << 5)
 #define XDEV_RESUME	(0xf << 5)
 /* true: port has power (see HCC_PPC) */
 #define PORT_POWER	(1 << 9)
diff --git a/drivers/usb/serial/sierra.c b/drivers/usb/serial/sierra.c
index d09a4e790892..f1b1f4b643e4 100644
--- a/drivers/usb/serial/sierra.c
+++ b/drivers/usb/serial/sierra.c
@@ -289,6 +289,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68AA, 0xFF, 0xFF, 0xFF),
 	  .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
 	},
+	{ USB_DEVICE(0x1199, 0x68AB) }, /* Sierra Wireless AR8550 */
 	/* AT&T Direct IP LTE modems */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x0F3D, 0x68AA, 0xFF, 0xFF, 0xFF),
 	  .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 00b47646522b..ff273d527b6e 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -2045,6 +2045,18 @@ UNUSUAL_DEV( 0x1908, 0x3335, 0x0200, 0x0200,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_READ_DISC_INFO ),
 
+/* Reported by Oliver Neukum <oneukum@suse.com>
+ * This device morphes spontaneously into another device if the access
+ * pattern of Windows isn't followed. Thus writable media would be dirty
+ * if the initial instance is used. So the device is limited to its
+ * virtual CD.
+ * And yes, the concept that BCD goes up to 9 is not heeded */
+UNUSUAL_DEV( 0x19d2, 0x1225, 0x0000, 0xffff,
+		"ZTE,Incorporated",
+		"ZTE WCDMA Technologies MSM",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_SINGLE_LUN ),
+
 /* Reported by Sven Geggus <sven-usbst@geggus.net>
  * This encrypted pen drive returns bogus data for the initial READ(10).
  */
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 69068e0d8f31..384bcc8ed7ad 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -878,6 +878,7 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp)
 		}
 		if (eventfp != d->log_file) {
 			filep = d->log_file;
+			d->log_file = eventfp;
 			ctx = d->log_ctx;
 			d->log_ctx = eventfp ?
 				eventfd_ctx_fileget(eventfp) : NULL;
diff --git a/fs/dcache.c b/fs/dcache.c
index 64cfe24cdd88..4c227f81051b 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -622,6 +622,9 @@ repeat:
 	if (unlikely(d_unhashed(dentry)))
 		goto kill_it;
 
+	if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED))
+		goto kill_it;
+
 	if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) {
 		if (dentry->d_op->d_delete(dentry))
 			goto kill_it;
diff --git a/fs/namei.c b/fs/namei.c
index c0c78e193e2a..097bbeac8c66 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3202,7 +3202,7 @@ static struct file *path_openat(int dfd, struct filename *pathname,
 
 	if (unlikely(file->f_flags & __O_TMPFILE)) {
 		error = do_tmpfile(dfd, pathname, nd, flags, op, file, &opened);
-		goto out;
+		goto out2;
 	}
 
 	error = path_init(dfd, pathname->name, flags | LOOKUP_PARENT, nd, &base);
@@ -3240,6 +3240,7 @@ out:
 		path_put(&nd->root);
 	if (base)
 		fput(base);
+out2:
 	if (!(opened & FILE_OPENED)) {
 		BUG_ON(!error);
 		put_filp(file);
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 923fe4a5f503..6bffc3331df6 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -293,16 +293,36 @@ void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group,
 					 unsigned int flags)
 {
 	struct fsnotify_mark *lmark, *mark;
+	LIST_HEAD(to_free);
 
+	/*
+	 * We have to be really careful here. Anytime we drop mark_mutex, e.g.
+	 * fsnotify_clear_marks_by_inode() can come and free marks. Even in our
+	 * to_free list so we have to use mark_mutex even when accessing that
+	 * list. And freeing mark requires us to drop mark_mutex. So we can
+	 * reliably free only the first mark in the list. That's why we first
+	 * move marks to free to to_free list in one go and then free marks in
+	 * to_free list one by one.
+	 */
 	mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
 	list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) {
-		if (mark->flags & flags) {
-			fsnotify_get_mark(mark);
-			fsnotify_destroy_mark_locked(mark, group);
-			fsnotify_put_mark(mark);
-		}
+		if (mark->flags & flags)
+			list_move(&mark->g_list, &to_free);
 	}
 	mutex_unlock(&group->mark_mutex);
+
+	while (1) {
+		mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
+		if (list_empty(&to_free)) {
+			mutex_unlock(&group->mark_mutex);
+			break;
+		}
+		mark = list_first_entry(&to_free, struct fsnotify_mark, g_list);
+		fsnotify_get_mark(mark);
+		fsnotify_destroy_mark_locked(mark, group);
+		mutex_unlock(&group->mark_mutex);
+		fsnotify_put_mark(mark);
+	}
 }
 
 /*
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 3988d0aeb72c..416a2ab68ac1 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -4009,9 +4009,13 @@ static void ocfs2_downconvert_thread_do_work(struct ocfs2_super *osb)
 	osb->dc_work_sequence = osb->dc_wake_sequence;
 
 	processed = osb->blocked_lock_count;
-	while (processed) {
-		BUG_ON(list_empty(&osb->blocked_lock_list));
-
+	/*
+	 * blocked lock processing in this loop might call iput which can
+	 * remove items off osb->blocked_lock_list. Downconvert up to
+	 * 'processed' number of locks, but stop short if we had some
+	 * removed in ocfs2_mark_lockres_freeing when downconverting.
+	 */
+	while (processed && !list_empty(&osb->blocked_lock_list)) {
 		lockres = list_entry(osb->blocked_lock_list.next,
 				     struct ocfs2_lock_res, l_blocked_list);
 		list_del_init(&lockres->l_blocked_list);
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 424b7b65321f..148f8e7af882 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -121,8 +121,9 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
 		 * Other callers might not initialize the si_lsb field,
 		 * so check explicitly for the right codes here.
 		 */
-		if (kinfo->si_code == BUS_MCEERR_AR ||
-		    kinfo->si_code == BUS_MCEERR_AO)
+		if (kinfo->si_signo == SIGBUS &&
+		    (kinfo->si_code == BUS_MCEERR_AR ||
+		     kinfo->si_code == BUS_MCEERR_AO))
 			err |= __put_user((short) kinfo->si_addr_lsb,
 					  &uinfo->ssi_addr_lsb);
 #endif
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 639d7a4d033b..01613b382b0e 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -46,5 +46,20 @@
 #define read_barrier_depends()		do {} while (0)
 #define smp_read_barrier_depends()	do {} while (0)
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
 #endif /* !__ASSEMBLY__ */
 #endif /* __ASM_GENERIC_BARRIER_H */
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 7571f433f0e3..2e2804c241fa 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -172,6 +172,7 @@
 	{0x1002, 0x6610, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6611, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6613, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6617, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6620, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6621, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6623, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index a2329c5e6206..4a3caa61a002 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -302,6 +302,11 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
 # define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
 #endif
 
+/* Is this type a native word size -- useful for atomic operations */
+#ifndef __native_word
+# define __native_word(t) (sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
+#endif
+
 /* Compile time object size, -1 for unknown */
 #ifndef __compiletime_object_size
 # define __compiletime_object_size(obj) -1
@@ -341,6 +346,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
 #define compiletime_assert(condition, msg) \
 	_compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
 
+#define compiletime_assert_atomic_type(t)				\
+	compiletime_assert(__native_word(t),				\
+		"Need native word sized stores/loads for atomicity.")
+
 /*
  * Prevent the compiler from merging or refetching accesses.  The compiler
  * is also forbidden from reordering successive instances of ACCESS_ONCE(),
@@ -355,6 +364,21 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
  */
 #define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
 
+/**
+ * lockless_dereference() - safely load a pointer for later dereference
+ * @p: The pointer to load
+ *
+ * Similar to rcu_dereference(), but for situations where the pointed-to
+ * object's lifetime is managed by something other than RCU.  That
+ * "something other" might be reference counting or simple immortality.
+ */
+#define lockless_dereference(p) \
+({ \
+	typeof(p) _________p1 = ACCESS_ONCE(p); \
+	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
+	(_________p1); \
+})
+
 /* Ignore/forbid kprobes attach on very low level functions marked by this attribute: */
 #ifdef CONFIG_KPROBES
 # define __kprobes	__attribute__((__section__(".kprobes.text")))
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index f1f1bc39346b..965725f957d9 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -554,7 +554,6 @@ static inline void rcu_preempt_sleep_check(void)
 		(p) = (typeof(*v) __force space *)(v); \
 	} while (0)
 
-
 /**
  * rcu_access_pointer() - fetch RCU pointer with no dereferencing
  * @p: The pointer to read
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index bb0248fc5187..82bb5e81ef57 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -143,7 +143,6 @@ static int msg_insert(struct msg_msg *msg, struct mqueue_inode_info *info)
 		if (!leaf)
 			return -ENOMEM;
 		INIT_LIST_HEAD(&leaf->msg_list);
-		info->qsize += sizeof(*leaf);
 	}
 	leaf->priority = msg->m_type;
 	rb_link_node(&leaf->rb_node, parent, p);
@@ -188,7 +187,6 @@ try_again:
 			     "lazy leaf delete!\n");
 		rb_erase(&leaf->rb_node, &info->msg_tree);
 		if (info->node_cache) {
-			info->qsize -= sizeof(*leaf);
 			kfree(leaf);
 		} else {
 			info->node_cache = leaf;
@@ -201,7 +199,6 @@ try_again:
 		if (list_empty(&leaf->msg_list)) {
 			rb_erase(&leaf->rb_node, &info->msg_tree);
 			if (info->node_cache) {
-				info->qsize -= sizeof(*leaf);
 				kfree(leaf);
 			} else {
 				info->node_cache = leaf;
@@ -1026,7 +1023,6 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
 		/* Save our speculative allocation into the cache */
 		INIT_LIST_HEAD(&new_leaf->msg_list);
 		info->node_cache = new_leaf;
-		info->qsize += sizeof(*new_leaf);
 		new_leaf = NULL;
 	} else {
 		kfree(new_leaf);
@@ -1133,7 +1129,6 @@ SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr,
 		/* Save our speculative allocation into the cache */
 		INIT_LIST_HEAD(&new_leaf->msg_list);
 		info->node_cache = new_leaf;
-		info->qsize += sizeof(*new_leaf);
 	} else {
 		kfree(new_leaf);
 	}
diff --git a/ipc/sem.c b/ipc/sem.c
index d8456ad6131c..b064468e876f 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -253,6 +253,16 @@ static void sem_rcu_free(struct rcu_head *head)
 }
 
 /*
+ * spin_unlock_wait() and !spin_is_locked() are not memory barriers, they
+ * are only control barriers.
+ * The code must pair with spin_unlock(&sem->lock) or
+ * spin_unlock(&sem_perm.lock), thus just the control barrier is insufficient.
+ *
+ * smp_rmb() is sufficient, as writes cannot pass the control barrier.
+ */
+#define ipc_smp_acquire__after_spin_is_unlocked()	smp_rmb()
+
+/*
  * Wait until all currently ongoing simple ops have completed.
  * Caller must own sem_perm.lock.
  * New simple ops cannot start, because simple ops first check
@@ -275,6 +285,7 @@ static void sem_wait_array(struct sem_array *sma)
 		sem = sma->sem_base + i;
 		spin_unlock_wait(&sem->lock);
 	}
+	ipc_smp_acquire__after_spin_is_unlocked();
 }
 
 /*
@@ -327,13 +338,12 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
 		/* Then check that the global lock is free */
 		if (!spin_is_locked(&sma->sem_perm.lock)) {
 			/*
-			 * The ipc object lock check must be visible on all
-			 * cores before rechecking the complex count.  Otherwise
-			 * we can race with  another thread that does:
+			 * We need a memory barrier with acquire semantics,
+			 * otherwise we can race with another thread that does:
 			 *	complex_count++;
 			 *	spin_unlock(sem_perm.lock);
 			 */
-			smp_rmb();
+			ipc_smp_acquire__after_spin_is_unlocked();
 
 			/*
 			 * Now repeat the test of complex_count:
@@ -2057,17 +2067,28 @@ void exit_sem(struct task_struct *tsk)
 		rcu_read_lock();
 		un = list_entry_rcu(ulp->list_proc.next,
 				    struct sem_undo, list_proc);
-		if (&un->list_proc == &ulp->list_proc)
-			semid = -1;
-		 else
-			semid = un->semid;
+		if (&un->list_proc == &ulp->list_proc) {
+			/*
+			 * We must wait for freeary() before freeing this ulp,
+			 * in case we raced with last sem_undo. There is a small
+			 * possibility where we exit while freeary() didn't
+			 * finish unlocking sem_undo_list.
+			 */
+			spin_unlock_wait(&ulp->lock);
+			rcu_read_unlock();
+			break;
+		}
+		spin_lock(&ulp->lock);
+		semid = un->semid;
+		spin_unlock(&ulp->lock);
 
+		/* exit_sem raced with IPC_RMID, nothing to do */
 		if (semid == -1) {
 			rcu_read_unlock();
-			break;
+			continue;
 		}
 
-		sma = sem_obtain_object_check(tsk->nsproxy->ipc_ns, un->semid);
+		sma = sem_obtain_object_check(tsk->nsproxy->ipc_ns, semid);
 		/* exit_sem raced with IPC_RMID, nothing to do */
 		if (IS_ERR(sma)) {
 			rcu_read_unlock();
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 18de86cbcdac..cf9f61763ab1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4155,12 +4155,20 @@ static const struct file_operations perf_fops = {
  * to user-space before waking everybody up.
  */
 
+static inline struct fasync_struct **perf_event_fasync(struct perf_event *event)
+{
+	/* only the parent has fasync state */
+	if (event->parent)
+		event = event->parent;
+	return &event->fasync;
+}
+
 void perf_event_wakeup(struct perf_event *event)
 {
 	ring_buffer_wakeup(event);
 
 	if (event->pending_kill) {
-		kill_fasync(&event->fasync, SIGIO, event->pending_kill);
+		kill_fasync(perf_event_fasync(event), SIGIO, event->pending_kill);
 		event->pending_kill = 0;
 	}
 }
@@ -5362,7 +5370,7 @@ static int __perf_event_overflow(struct perf_event *event,
 	else
 		perf_event_output(event, data, regs);
 
-	if (event->fasync && event->pending_kill) {
+	if (*perf_event_fasync(event) && event->pending_kill) {
 		event->pending_wakeup = 1;
 		irq_work_queue(&event->pending);
 	}
diff --git a/kernel/futex.c b/kernel/futex.c
index e4b9b60e25b1..bd0bc06772f6 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -490,8 +490,14 @@ static struct futex_pi_state * alloc_pi_state(void)
 	return pi_state;
 }
 
+/*
+ * Must be called with the hb lock held.
+ */
 static void free_pi_state(struct futex_pi_state *pi_state)
 {
+	if (!pi_state)
+		return;
+
 	if (!atomic_dec_and_test(&pi_state->refcount))
 		return;
 
@@ -1405,15 +1411,6 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	}
 
 retry:
-	if (pi_state != NULL) {
-		/*
-		 * We will have to lookup the pi_state again, so free this one
-		 * to keep the accounting correct.
-		 */
-		free_pi_state(pi_state);
-		pi_state = NULL;
-	}
-
 	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out;
@@ -1501,6 +1498,8 @@ retry_private:
 		case 0:
 			break;
 		case -EFAULT:
+			free_pi_state(pi_state);
+			pi_state = NULL;
 			double_unlock_hb(hb1, hb2);
 			put_futex_key(&key2);
 			put_futex_key(&key1);
@@ -1510,6 +1509,8 @@ retry_private:
 			goto out;
 		case -EAGAIN:
 			/* The owner was exiting, try again. */
+			free_pi_state(pi_state);
+			pi_state = NULL;
 			double_unlock_hb(hb1, hb2);
 			put_futex_key(&key2);
 			put_futex_key(&key1);
@@ -1586,6 +1587,7 @@ retry_private:
 	}
 
 out_unlock:
+	free_pi_state(pi_state);
 	double_unlock_hb(hb1, hb2);
 
 	/*
@@ -1602,8 +1604,6 @@ out_put_keys:
 out_put_key1:
 	put_futex_key(&key1);
 out:
-	if (pi_state != NULL)
-		free_pi_state(pi_state);
 	return ret ? ret : task_count;
 }
 
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 9065107f083e..7a5237a1bce5 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -75,13 +75,21 @@ void check_irq_resend(struct irq_desc *desc, unsigned int irq)
 		    !desc->irq_data.chip->irq_retrigger(&desc->irq_data)) {
 #ifdef CONFIG_HARDIRQS_SW_RESEND
 			/*
-			 * If the interrupt has a parent irq and runs
-			 * in the thread context of the parent irq,
-			 * retrigger the parent.
+			 * If the interrupt is running in the thread
+			 * context of the parent irq we need to be
+			 * careful, because we cannot trigger it
+			 * directly.
 			 */
-			if (desc->parent_irq &&
-			    irq_settings_is_nested_thread(desc))
+			if (irq_settings_is_nested_thread(desc)) {
+				/*
+				 * If the parent_irq is valid, we
+				 * retrigger the parent, otherwise we
+				 * do nothing.
+				 */
+				if (!desc->parent_irq)
+					return;
 				irq = desc->parent_irq;
+			}
 			/* Set it pending and activate the softirq: */
 			set_bit(irq, irqs_resend);
 			tasklet_schedule(&resend_tasklet);
diff --git a/kernel/signal.c b/kernel/signal.c
index ded28b91fa53..fca2decd695e 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2768,7 +2768,8 @@ int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from)
 		 * Other callers might not initialize the si_lsb field,
 		 * so check explicitly for the right codes here.
 		 */
-		if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)
+		if (from->si_signo == SIGBUS &&
+		    (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO))
 			err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
 #endif
 		break;
@@ -3035,7 +3036,7 @@ COMPAT_SYSCALL_DEFINE3(rt_sigqueueinfo,
 			int, sig,
 			struct compat_siginfo __user *, uinfo)
 {
-	siginfo_t info;
+	siginfo_t info = {};
 	int ret = copy_siginfo_from_user32(&info, uinfo);
 	if (unlikely(ret))
 		return ret;
@@ -3081,7 +3082,7 @@ COMPAT_SYSCALL_DEFINE4(rt_tgsigqueueinfo,
 			int, sig,
 			struct compat_siginfo __user *, uinfo)
 {
-	siginfo_t info;
+	siginfo_t info = {};
 
 	if (copy_siginfo_from_user32(&info, uinfo))
 		return -EFAULT;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 5785b59620ef..cb08faa72b77 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1524,6 +1524,8 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags)
 		 */
 		ret = __get_any_page(page, pfn, 0);
 		if (!PageLRU(page)) {
+			/* Drop page reference which is from __get_any_page() */
+			put_page(page);
 			pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n",
 				pfn, page->flags);
 			return -EIO;
diff --git a/mm/memory.c b/mm/memory.c
index 38617f049b9f..d0d84c36cd5c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3213,6 +3213,10 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	pte_unmap(page_table);
 
+	/* File mapping without ->vm_ops ? */
+	if (vma->vm_flags & VM_SHARED)
+		return VM_FAULT_SIGBUS;
+
 	/* Check if we need to add a guard page to the stack */
 	if (check_stack_guard_page(vma, address) < 0)
 		return VM_FAULT_SIGSEGV;
@@ -3480,6 +3484,9 @@ static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			- vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
 
 	pte_unmap(page_table);
+	/* The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */
+	if (!vma->vm_ops->fault)
+		return VM_FAULT_SIGBUS;
 	return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
 }
 
@@ -3691,11 +3698,9 @@ static int handle_pte_fault(struct mm_struct *mm,
 	entry = ACCESS_ONCE(*pte);
 	if (!pte_present(entry)) {
 		if (pte_none(entry)) {
-			if (vma->vm_ops) {
-				if (likely(vma->vm_ops->fault))
-					return do_linear_fault(mm, vma, address,
+			if (vma->vm_ops)
+				return do_linear_fault(mm, vma, address,
 						pte, pmd, flags, entry);
-			}
 			return do_anonymous_page(mm, vma, address,
 						 pte, pmd, flags);
 		}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index ee8363f73cab..04c33d5fb079 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -871,21 +871,17 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 *
 		 * 2) Global reclaim encounters a page, memcg encounters a
 		 *    page that is not marked for immediate reclaim or
-		 *    the caller does not have __GFP_IO. In this case mark
+		 *    the caller does not have __GFP_FS (or __GFP_IO if it's
+		 *    simply going to swap, not to fs). In this case mark
 		 *    the page for immediate reclaim and continue scanning.
 		 *
-		 *    __GFP_IO is checked  because a loop driver thread might
+		 *    Require may_enter_fs because we would wait on fs, which
+		 *    may not have submitted IO yet. And the loop driver might
 		 *    enter reclaim, and deadlock if it waits on a page for
 		 *    which it is needed to do the write (loop masks off
 		 *    __GFP_IO|__GFP_FS for this reason); but more thought
 		 *    would probably show more reasons.
 		 *
-		 *    Don't require __GFP_FS, since we're not going into the
-		 *    FS, just waiting on its writeback completion. Worryingly,
-		 *    ext4 gfs2 and xfs allocate pages with
-		 *    grab_cache_page_write_begin(,,AOP_FLAG_NOFS), so testing
-		 *    may_enter_fs here is liable to OOM on them.
-		 *
 		 * 3) memcg encounters a page that is not already marked
 		 *    PageReclaim. memcg does not have any dirty pages
 		 *    throttling so we could easily OOM just because too many
@@ -902,7 +898,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 
 			/* Case 2 above */
 			} else if (global_reclaim(sc) ||
-			    !PageReclaim(page) || !(sc->gfp_mask & __GFP_IO)) {
+			    !PageReclaim(page) || !may_enter_fs) {
 				/*
 				 * This is slightly racy - end_page_writeback()
 				 * might have just cleared PageReclaim, then
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index 8e41f0163c5a..92be2863b7db 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -698,6 +698,7 @@ void ieee80211_debugfs_remove_netdev(struct ieee80211_sub_if_data *sdata)
 
 	debugfs_remove_recursive(sdata->vif.debugfs_dir);
 	sdata->vif.debugfs_dir = NULL;
+	sdata->debugfs.subdir_stations = NULL;
 }
 
 void ieee80211_debugfs_rename_netdev(struct ieee80211_sub_if_data *sdata)
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index e8fdb172adbb..a985158d95d5 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -759,8 +759,10 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
 	}
 
 	ibmr = rds_ib_alloc_fmr(rds_ibdev);
-	if (IS_ERR(ibmr))
+	if (IS_ERR(ibmr)) {
+		rds_ib_dev_put(rds_ibdev);
 		return ibmr;
+	}
 
 	ret = rds_ib_map_fmr(rds_ibdev, ibmr, sg, nents);
 	if (ret == 0)
diff --git a/scripts/kconfig/streamline_config.pl b/scripts/kconfig/streamline_config.pl
index 4606cdfb859d..7dd7c391b4d8 100644
--- a/scripts/kconfig/streamline_config.pl
+++ b/scripts/kconfig/streamline_config.pl
@@ -137,7 +137,7 @@ my $ksource = ($ARGV[0] ? $ARGV[0] : '.');
 my $kconfig = $ARGV[1];
 my $lsmod_file = $ENV{'LSMOD'};
 
-my @makefiles = `find $ksource -name Makefile 2>/dev/null`;
+my @makefiles = `find $ksource -name Makefile -or -name Kbuild 2>/dev/null`;
 chomp @makefiles;
 
 my %depends;
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index 085c4964be99..9d8e420a80d9 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -27,6 +27,8 @@
 #define IMA_UID		0x0008
 #define IMA_FOWNER	0x0010
 #define IMA_FSUUID	0x0020
+#define IMA_INMASK	0x0040
+#define IMA_EUID	0x0080
 
 #define UNKNOWN		0
 #define MEASURE		0x0001	/* same as IMA_MEASURE */
@@ -171,6 +173,9 @@ static bool ima_match_rules(struct ima_rule_entry *rule,
 		return false;
 	if ((rule->flags & IMA_MASK) && rule->mask != mask)
 		return false;
+	if ((rule->flags & IMA_INMASK) &&
+	    (!(rule->mask & mask) && func != POST_SETATTR))
+		return false;
 	if ((rule->flags & IMA_FSMAGIC)
 	    && rule->fsmagic != inode->i_sb->s_magic)
 		return false;
@@ -179,6 +184,16 @@ static bool ima_match_rules(struct ima_rule_entry *rule,
 		return false;
 	if ((rule->flags & IMA_UID) && !uid_eq(rule->uid, cred->uid))
 		return false;
+	if (rule->flags & IMA_EUID) {
+		if (has_capability_noaudit(current, CAP_SETUID)) {
+			if (!uid_eq(rule->uid, cred->euid)
+			    && !uid_eq(rule->uid, cred->suid)
+			    && !uid_eq(rule->uid, cred->uid))
+				return false;
+		} else if (!uid_eq(rule->uid, cred->euid))
+			return false;
+	}
+
 	if ((rule->flags & IMA_FOWNER) && !uid_eq(rule->fowner, inode->i_uid))
 		return false;
 	for (i = 0; i < MAX_LSM_RULES; i++) {
@@ -350,7 +365,8 @@ enum {
 	Opt_audit,
 	Opt_obj_user, Opt_obj_role, Opt_obj_type,
 	Opt_subj_user, Opt_subj_role, Opt_subj_type,
-	Opt_func, Opt_mask, Opt_fsmagic, Opt_uid, Opt_fowner,
+	Opt_func, Opt_mask, Opt_fsmagic,
+	Opt_uid, Opt_euid, Opt_fowner,
 	Opt_appraise_type, Opt_fsuuid, Opt_permit_directio
 };
 
@@ -371,6 +387,7 @@ static match_table_t policy_tokens = {
 	{Opt_fsmagic, "fsmagic=%s"},
 	{Opt_fsuuid, "fsuuid=%s"},
 	{Opt_uid, "uid=%s"},
+	{Opt_euid, "euid=%s"},
 	{Opt_fowner, "fowner=%s"},
 	{Opt_appraise_type, "appraise_type=%s"},
 	{Opt_permit_directio, "permit_directio"},
@@ -412,6 +429,7 @@ static void ima_log_string(struct audit_buffer *ab, char *key, char *value)
 static int ima_parse_rule(char *rule, struct ima_rule_entry *entry)
 {
 	struct audit_buffer *ab;
+	char *from;
 	char *p;
 	int result = 0;
 
@@ -500,18 +518,23 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry)
 			if (entry->mask)
 				result = -EINVAL;
 
-			if ((strcmp(args[0].from, "MAY_EXEC")) == 0)
+			from = args[0].from;
+			if (*from == '^')
+				from++;
+
+			if ((strcmp(from, "MAY_EXEC")) == 0)
 				entry->mask = MAY_EXEC;
-			else if (strcmp(args[0].from, "MAY_WRITE") == 0)
+			else if (strcmp(from, "MAY_WRITE") == 0)
 				entry->mask = MAY_WRITE;
-			else if (strcmp(args[0].from, "MAY_READ") == 0)
+			else if (strcmp(from, "MAY_READ") == 0)
 				entry->mask = MAY_READ;
-			else if (strcmp(args[0].from, "MAY_APPEND") == 0)
+			else if (strcmp(from, "MAY_APPEND") == 0)
 				entry->mask = MAY_APPEND;
 			else
 				result = -EINVAL;
 			if (!result)
-				entry->flags |= IMA_MASK;
+				entry->flags |= (*args[0].from == '^')
+				     ? IMA_INMASK : IMA_MASK;
 			break;
 		case Opt_fsmagic:
 			ima_log_string(ab, "fsmagic", args[0].from);
@@ -542,6 +565,9 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry)
 			break;
 		case Opt_uid:
 			ima_log_string(ab, "uid", args[0].from);
+		case Opt_euid:
+			if (token == Opt_euid)
+				ima_log_string(ab, "euid", args[0].from);
 
 			if (uid_valid(entry->uid)) {
 				result = -EINVAL;
@@ -550,11 +576,14 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry)
 
 			result = strict_strtoul(args[0].from, 10, &lnum);
 			if (!result) {
-				entry->uid = make_kuid(current_user_ns(), (uid_t)lnum);
-				if (!uid_valid(entry->uid) || (((uid_t)lnum) != lnum))
+				entry->uid = make_kuid(current_user_ns(),
+						       (uid_t) lnum);
+				if (!uid_valid(entry->uid) ||
+				    (uid_t)lnum != lnum)
 					result = -EINVAL;
 				else
-					entry->flags |= IMA_UID;
+					entry->flags |= (token == Opt_uid)
+					    ? IMA_UID : IMA_EUID;
 			}
 			break;
 		case Opt_fowner:
diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c
index ab0d0a384c15..d54d218fe810 100644
--- a/sound/pci/hda/patch_cirrus.c
+++ b/sound/pci/hda/patch_cirrus.c
@@ -948,9 +948,7 @@ static void cs4210_spdif_automute(struct hda_codec *codec,
 
 	spec->spdif_present = spdif_present;
 	/* SPDIF TX on/off */
-	if (spdif_present)
-		snd_hda_set_pin_ctl(codec, spdif_pin,
-				    spdif_present ? PIN_OUT : 0);
+	snd_hda_set_pin_ctl(codec, spdif_pin, spdif_present ? PIN_OUT : 0);
 
 	cs_automute(codec);
 }
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index a2e6f3ec7d26..f92057919273 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -2213,7 +2213,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	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),
-	SND_PCI_QUIRK(0x106b, 0x4a00, "Macbook 5,2", ALC889_FIXUP_IMAC91_VREF),
+	SND_PCI_QUIRK(0x106b, 0x4a00, "Macbook 5,2", ALC889_FIXUP_MBA11_VREF),
 
 	SND_PCI_QUIRK(0x1071, 0x8258, "Evesham Voyaeger", ALC882_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD),
diff --git a/sound/soc/codecs/pcm1681.c b/sound/soc/codecs/pcm1681.c
index 0819fa2ff710..a7a34613c828 100644
--- a/sound/soc/codecs/pcm1681.c
+++ b/sound/soc/codecs/pcm1681.c
@@ -101,7 +101,7 @@ static int pcm1681_set_deemph(struct snd_soc_codec *codec)
 
 	if (val != -1) {
 		regmap_update_bits(priv->regmap, PCM1681_DEEMPH_CONTROL,
-					PCM1681_DEEMPH_RATE_MASK, val);
+				   PCM1681_DEEMPH_RATE_MASK, val << 3);
 		enable = 1;
 	} else
 		enable = 0;
diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index d06fbd9f7cbe..2d17f40fb16d 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -330,6 +330,20 @@ static const struct usbmix_name_map scms_usb3318_map[] = {
 	{ 0 }
 };
 
+/* Bose companion 5, the dB conversion factor is 16 instead of 256 */
+static struct usbmix_dB_map bose_companion5_dB = {-5006, -6};
+static struct usbmix_name_map bose_companion5_map[] = {
+	{ 3, NULL, .dB = &bose_companion5_dB },
+	{ 0 }	/* terminator */
+};
+
+/* Dragonfly DAC 1.2, the dB conversion factor is 1 instead of 256 */
+static struct usbmix_dB_map dragonfly_1_2_dB = {0, 5000};
+static struct usbmix_name_map dragonfly_1_2_map[] = {
+	{ 7, NULL, .dB = &dragonfly_1_2_dB },
+	{ 0 }	/* terminator */
+};
+
 /*
  * Control map entries
  */
@@ -432,6 +446,16 @@ static struct usbmix_ctl_map usbmix_ctl_maps[] = {
 		.id = USB_ID(0x25c4, 0x0003),
 		.map = scms_usb3318_map,
 	},
+	{
+		/* Bose Companion 5 */
+		.id = USB_ID(0x05a7, 0x1020),
+		.map = bose_companion5_map,
+	},
+	{
+		/* Dragonfly DAC 1.2 */
+		.id = USB_ID(0x21b4, 0x0081),
+		.map = dragonfly_1_2_map,
+	},
 	{ 0 } /* terminator */
 };
 
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index 5293b5ac8b9d..7c24088bcaa4 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -2516,6 +2516,74 @@ YAMAHA_DEVICE(0x7010, "UB99"),
 	}
 },
 
+/* Steinberg devices */
+{
+	/* Steinberg MI2 */
+	USB_DEVICE_VENDOR_SPEC(0x0a4e, 0x2040),
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = & (const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 0,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 1,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 2,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 3,
+				.type = QUIRK_MIDI_FIXED_ENDPOINT,
+				.data = &(const struct snd_usb_midi_endpoint_info) {
+					.out_cables = 0x0001,
+					.in_cables  = 0x0001
+				}
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
+{
+	/* Steinberg MI4 */
+	USB_DEVICE_VENDOR_SPEC(0x0a4e, 0x4040),
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = & (const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 0,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 1,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 2,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 3,
+				.type = QUIRK_MIDI_FIXED_ENDPOINT,
+				.data = &(const struct snd_usb_midi_endpoint_info) {
+					.out_cables = 0x0001,
+					.in_cables  = 0x0001
+				}
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
+
 /* TerraTec devices */
 {
 	USB_DEVICE_VENDOR_SPEC(0x0ccd, 0x0012),