Merge branch 'master' into driver-core-next-test-merge-rc2

da9846ae1518 ("kernfs: make kernfs_deactivate() honor KERNFS_LOCKDEP
flag") in driver-core-linus conflicts with kernfs_drain() updates in
driver-core-next.  The former just adds the missing KERNFS_LOCKDEP
checks which are already handled by kernfs_lockdep() checks in
driver-core-next.  The conflict can be resolved by taking code from
driver-core-next.

Conflicts:
	fs/kernfs/dir.c

51 files changed, 404 insertions, 240 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index dd4327f..27bbcfc 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -36,6 +36,7 @@ config ARM64
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
 	select HAVE_MEMBLOCK
+	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
 	select IRQ_DOMAIN
 	select MODULES_USE_ELF_RELA
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 84139be..7959dd0 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -1,4 +1,3 @@
-CONFIG_EXPERIMENTAL=y
 # CONFIG_LOCALVERSION_AUTO is not set
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
@@ -19,6 +18,7 @@ CONFIG_BLK_DEV_INITRD=y
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
+CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
@@ -27,6 +27,7 @@ CONFIG_ARCH_VEXPRESS=y
 CONFIG_ARCH_XGENE=y
 CONFIG_SMP=y
 CONFIG_PREEMPT=y
+CONFIG_CMA=y
 CONFIG_CMDLINE="console=ttyAMA0"
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_COMPAT=y
@@ -42,14 +43,17 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_WIRELESS is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
-CONFIG_BLK_DEV=y
+CONFIG_DMA_CMA=y
 CONFIG_SCSI=y
 # CONFIG_SCSI_PROC_FS is not set
 CONFIG_BLK_DEV_SD=y
 # CONFIG_SCSI_LOWLEVEL is not set
+CONFIG_ATA=y
+CONFIG_PATA_PLATFORM=y
+CONFIG_PATA_OF_PLATFORM=y
 CONFIG_NETDEVICES=y
-CONFIG_MII=y
 CONFIG_SMC91X=y
+CONFIG_SMSC911X=y
 # CONFIG_WLAN is not set
 CONFIG_INPUT_EVDEV=y
 # CONFIG_SERIO_I8042 is not set
@@ -62,13 +66,19 @@ CONFIG_SERIAL_AMBA_PL011=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_FB=y
 # CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_VGA16 is not set
-# CONFIG_USB_SUPPORT is not set
+CONFIG_USB=y
+CONFIG_USB_ISP1760_HCD=y
+CONFIG_USB_STORAGE=y
+CONFIG_MMC=y
+CONFIG_MMC_ARMMMCI=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 01de5aa..0237f08 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -54,8 +54,7 @@ static inline void atomic_add(int i, atomic_t *v)
 "	stxr	%w1, %w0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "cc");
+	: "Ir" (i));
 }
 
 static inline int atomic_add_return(int i, atomic_t *v)
@@ -64,14 +63,15 @@ static inline int atomic_add_return(int i, atomic_t *v)
 	int result;
 
 	asm volatile("// atomic_add_return\n"
-"1:	ldaxr	%w0, %2\n"
+"1:	ldxr	%w0, %2\n"
 "	add	%w0, %w0, %w3\n"
 "	stlxr	%w1, %w0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
 	: "Ir" (i)
-	: "cc", "memory");
+	: "memory");
 
+	smp_mb();
 	return result;
 }
 
@@ -86,8 +86,7 @@ static inline void atomic_sub(int i, atomic_t *v)
 "	stxr	%w1, %w0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "cc");
+	: "Ir" (i));
 }
 
 static inline int atomic_sub_return(int i, atomic_t *v)
@@ -96,14 +95,15 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 	int result;
 
 	asm volatile("// atomic_sub_return\n"
-"1:	ldaxr	%w0, %2\n"
+"1:	ldxr	%w0, %2\n"
 "	sub	%w0, %w0, %w3\n"
 "	stlxr	%w1, %w0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
 	: "Ir" (i)
-	: "cc", "memory");
+	: "memory");
 
+	smp_mb();
 	return result;
 }
 
@@ -112,17 +112,20 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 	unsigned long tmp;
 	int oldval;
 
+	smp_mb();
+
 	asm volatile("// atomic_cmpxchg\n"
-"1:	ldaxr	%w1, %2\n"
+"1:	ldxr	%w1, %2\n"
 "	cmp	%w1, %w3\n"
 "	b.ne	2f\n"
-"	stlxr	%w0, %w4, %2\n"
+"	stxr	%w0, %w4, %2\n"
 "	cbnz	%w0, 1b\n"
 "2:"
 	: "=&r" (tmp), "=&r" (oldval), "+Q" (ptr->counter)
 	: "Ir" (old), "r" (new)
-	: "cc", "memory");
+	: "cc");
 
+	smp_mb();
 	return oldval;
 }
 
@@ -173,8 +176,7 @@ static inline void atomic64_add(u64 i, atomic64_t *v)
 "	stxr	%w1, %0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "cc");
+	: "Ir" (i));
 }
 
 static inline long atomic64_add_return(long i, atomic64_t *v)
@@ -183,14 +185,15 @@ static inline long atomic64_add_return(long i, atomic64_t *v)
 	unsigned long tmp;
 
 	asm volatile("// atomic64_add_return\n"
-"1:	ldaxr	%0, %2\n"
+"1:	ldxr	%0, %2\n"
 "	add	%0, %0, %3\n"
 "	stlxr	%w1, %0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
 	: "Ir" (i)
-	: "cc", "memory");
+	: "memory");
 
+	smp_mb();
 	return result;
 }
 
@@ -205,8 +208,7 @@ static inline void atomic64_sub(u64 i, atomic64_t *v)
 "	stxr	%w1, %0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "cc");
+	: "Ir" (i));
 }
 
 static inline long atomic64_sub_return(long i, atomic64_t *v)
@@ -215,14 +217,15 @@ static inline long atomic64_sub_return(long i, atomic64_t *v)
 	unsigned long tmp;
 
 	asm volatile("// atomic64_sub_return\n"
-"1:	ldaxr	%0, %2\n"
+"1:	ldxr	%0, %2\n"
 "	sub	%0, %0, %3\n"
 "	stlxr	%w1, %0, %2\n"
 "	cbnz	%w1, 1b"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
 	: "Ir" (i)
-	: "cc", "memory");
+	: "memory");
 
+	smp_mb();
 	return result;
 }
 
@@ -231,17 +234,20 @@ static inline long atomic64_cmpxchg(atomic64_t *ptr, long old, long new)
 	long oldval;
 	unsigned long res;
 
+	smp_mb();
+
 	asm volatile("// atomic64_cmpxchg\n"
-"1:	ldaxr	%1, %2\n"
+"1:	ldxr	%1, %2\n"
 "	cmp	%1, %3\n"
 "	b.ne	2f\n"
-"	stlxr	%w0, %4, %2\n"
+"	stxr	%w0, %4, %2\n"
 "	cbnz	%w0, 1b\n"
 "2:"
 	: "=&r" (res), "=&r" (oldval), "+Q" (ptr->counter)
 	: "Ir" (old), "r" (new)
-	: "cc", "memory");
+	: "cc");
 
+	smp_mb();
 	return oldval;
 }
 
@@ -253,11 +259,12 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	unsigned long tmp;
 
 	asm volatile("// atomic64_dec_if_positive\n"
-"1:	ldaxr	%0, %2\n"
+"1:	ldxr	%0, %2\n"
 "	subs	%0, %0, #1\n"
 "	b.mi	2f\n"
 "	stlxr	%w1, %0, %2\n"
 "	cbnz	%w1, 1b\n"
+"	dmb	ish\n"
 "2:"
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
 	:
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 78e20ba..409ca37 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -25,7 +25,7 @@
 #define wfi()		asm volatile("wfi" : : : "memory")
 
 #define isb()		asm volatile("isb" : : : "memory")
-#define dsb()		asm volatile("dsb sy" : : : "memory")
+#define dsb(opt)	asm volatile("dsb sy" : : : "memory")
 
 #define mb()		dsb()
 #define rmb()		asm volatile("dsb ld" : : : "memory")
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index fea9ee3..88932498 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -116,6 +116,7 @@ extern void flush_dcache_page(struct page *);
 static inline void __flush_icache_all(void)
 {
 	asm("ic	ialluis");
+	dsb();
 }
 
 #define flush_dcache_mmap_lock(mapping) \
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 56166d7..57c0fa7 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -29,44 +29,45 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 	switch (size) {
 	case 1:
 		asm volatile("//	__xchg1\n"
-		"1:	ldaxrb	%w0, %2\n"
+		"1:	ldxrb	%w0, %2\n"
 		"	stlxrb	%w1, %w3, %2\n"
 		"	cbnz	%w1, 1b\n"
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr)
 			: "r" (x)
-			: "cc", "memory");
+			: "memory");
 		break;
 	case 2:
 		asm volatile("//	__xchg2\n"
-		"1:	ldaxrh	%w0, %2\n"
+		"1:	ldxrh	%w0, %2\n"
 		"	stlxrh	%w1, %w3, %2\n"
 		"	cbnz	%w1, 1b\n"
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u16 *)ptr)
 			: "r" (x)
-			: "cc", "memory");
+			: "memory");
 		break;
 	case 4:
 		asm volatile("//	__xchg4\n"
-		"1:	ldaxr	%w0, %2\n"
+		"1:	ldxr	%w0, %2\n"
 		"	stlxr	%w1, %w3, %2\n"
 		"	cbnz	%w1, 1b\n"
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u32 *)ptr)
 			: "r" (x)
-			: "cc", "memory");
+			: "memory");
 		break;
 	case 8:
 		asm volatile("//	__xchg8\n"
-		"1:	ldaxr	%0, %2\n"
+		"1:	ldxr	%0, %2\n"
 		"	stlxr	%w1, %3, %2\n"
 		"	cbnz	%w1, 1b\n"
 			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u64 *)ptr)
 			: "r" (x)
-			: "cc", "memory");
+			: "memory");
 		break;
 	default:
 		BUILD_BUG();
 	}
 
+	smp_mb();
 	return ret;
 }
 
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 7883412..c4a7f94 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -42,7 +42,7 @@
 #define ESR_EL1_EC_SP_ALIGN	(0x26)
 #define ESR_EL1_EC_FP_EXC32	(0x28)
 #define ESR_EL1_EC_FP_EXC64	(0x2C)
-#define ESR_EL1_EC_SERRROR	(0x2F)
+#define ESR_EL1_EC_SERROR	(0x2F)
 #define ESR_EL1_EC_BREAKPT_EL0	(0x30)
 #define ESR_EL1_EC_BREAKPT_EL1	(0x31)
 #define ESR_EL1_EC_SOFTSTP_EL0	(0x32)
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index 78cc3ab..5f750dc 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -24,10 +24,11 @@
 
 #define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg)		\
 	asm volatile(							\
-"1:	ldaxr	%w1, %2\n"						\
+"1:	ldxr	%w1, %2\n"						\
 	insn "\n"							\
 "2:	stlxr	%w3, %w0, %2\n"						\
 "	cbnz	%w3, 1b\n"						\
+"	dmb	ish\n"							\
 "3:\n"									\
 "	.pushsection .fixup,\"ax\"\n"					\
 "	.align	2\n"							\
@@ -40,7 +41,7 @@
 "	.popsection\n"							\
 	: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp)	\
 	: "r" (oparg), "Ir" (-EFAULT)					\
-	: "cc", "memory")
+	: "memory")
 
 static inline int
 futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
@@ -111,11 +112,12 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		return -EFAULT;
 
 	asm volatile("// futex_atomic_cmpxchg_inatomic\n"
-"1:	ldaxr	%w1, %2\n"
+"1:	ldxr	%w1, %2\n"
 "	sub	%w3, %w1, %w4\n"
 "	cbnz	%w3, 3f\n"
 "2:	stlxr	%w3, %w5, %2\n"
 "	cbnz	%w3, 1b\n"
+"	dmb	ish\n"
 "3:\n"
 "	.pushsection .fixup,\"ax\"\n"
 "4:	mov	%w0, %w6\n"
@@ -127,7 +129,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 "	.popsection\n"
 	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp)
 	: "r" (oldval), "r" (newval), "Ir" (-EFAULT)
-	: "cc", "memory");
+	: "memory");
 
 	*uval = val;
 	return ret;
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index c98ef47..0eb3986 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -231,7 +231,7 @@
 #define ESR_EL2_EC_SP_ALIGN	(0x26)
 #define ESR_EL2_EC_FP_EXC32	(0x28)
 #define ESR_EL2_EC_FP_EXC64	(0x2C)
-#define ESR_EL2_EC_SERRROR	(0x2F)
+#define ESR_EL2_EC_SERROR	(0x2F)
 #define ESR_EL2_EC_BREAKPT	(0x30)
 #define ESR_EL2_EC_BREAKPT_HYP	(0x31)
 #define ESR_EL2_EC_SOFTSTP	(0x32)
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index 3d5cf06..c45b7b1 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -132,7 +132,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 	"	cbnz	%w0, 2b\n"
 	: "=&r" (tmp), "+Q" (rw->lock)
 	: "r" (0x80000000)
-	: "cc", "memory");
+	: "memory");
 }
 
 static inline int arch_write_trylock(arch_rwlock_t *rw)
@@ -146,7 +146,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 	"1:\n"
 	: "=&r" (tmp), "+Q" (rw->lock)
 	: "r" (0x80000000)
-	: "cc", "memory");
+	: "memory");
 
 	return !tmp;
 }
@@ -187,7 +187,7 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 	"	cbnz	%w1, 2b\n"
 	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
 	:
-	: "cc", "memory");
+	: "memory");
 }
 
 static inline void arch_read_unlock(arch_rwlock_t *rw)
@@ -201,7 +201,7 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 	"	cbnz	%w1, 1b\n"
 	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
 	:
-	: "cc", "memory");
+	: "memory");
 }
 
 static inline int arch_read_trylock(arch_rwlock_t *rw)
@@ -216,7 +216,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 	"1:\n"
 	: "=&r" (tmp), "+r" (tmp2), "+Q" (rw->lock)
 	:
-	: "cc", "memory");
+	: "memory");
 
 	return !tmp2;
 }
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 58125bf..bb8eb8a 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -399,7 +399,10 @@ __SYSCALL(374, compat_sys_sendmmsg)
 __SYSCALL(375, sys_setns)
 __SYSCALL(376, compat_sys_process_vm_readv)
 __SYSCALL(377, compat_sys_process_vm_writev)
-__SYSCALL(378, sys_ni_syscall)			/* 378 for kcmp */
+__SYSCALL(378, sys_kcmp)
+__SYSCALL(379, sys_finit_module)
+__SYSCALL(380, sys_sched_setattr)
+__SYSCALL(381, sys_sched_getattr)
 
 #define __NR_compat_syscalls		379
 
diff --git a/arch/arm64/kernel/kuser32.S b/arch/arm64/kernel/kuser32.S
index 63c48ff..7787208 100644
--- a/arch/arm64/kernel/kuser32.S
+++ b/arch/arm64/kernel/kuser32.S
@@ -38,12 +38,13 @@ __kuser_cmpxchg64:			// 0xffff0f60
 	.inst	0xe92d00f0		//	push		{r4, r5, r6, r7}
 	.inst	0xe1c040d0		//	ldrd		r4, r5, [r0]
 	.inst	0xe1c160d0		//	ldrd		r6, r7, [r1]
-	.inst	0xe1b20e9f		// 1:	ldaexd		r0, r1, [r2]
+	.inst	0xe1b20f9f		// 1:	ldrexd		r0, r1, [r2]
 	.inst	0xe0303004		//	eors		r3, r0, r4
 	.inst	0x00313005		//	eoreqs		r3, r1, r5
 	.inst	0x01a23e96		//	stlexdeq	r3, r6, [r2]
 	.inst	0x03330001		//	teqeq		r3, #1
 	.inst	0x0afffff9		//	beq		1b
+	.inst	0xf57ff05b		//	dmb		ish
 	.inst	0xe2730000		//	rsbs		r0, r3, #0
 	.inst	0xe8bd00f0		//	pop		{r4, r5, r6, r7}
 	.inst	0xe12fff1e		//	bx		lr
@@ -55,11 +56,12 @@ __kuser_memory_barrier:			// 0xffff0fa0
 
 	.align	5
 __kuser_cmpxchg:			// 0xffff0fc0
-	.inst	0xe1923e9f		// 1:	ldaex		r3, [r2]
+	.inst	0xe1923f9f		// 1:	ldrex		r3, [r2]
 	.inst	0xe0533000		//	subs		r3, r3, r0
 	.inst	0x01823e91		//	stlexeq		r3, r1, [r2]
 	.inst	0x03330001		//	teqeq		r3, #1
 	.inst	0x0afffffa		//	beq		1b
+	.inst	0xf57ff05b		//	dmb		ish
 	.inst	0xe2730000		//	rsbs		r0, r3, #0
 	.inst	0xe12fff1e		//	bx		lr
 
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 65d40cf..a7149ca 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -238,6 +238,8 @@ void update_vsyscall(struct timekeeper *tk)
 	vdso_data->use_syscall			= use_syscall;
 	vdso_data->xtime_coarse_sec		= xtime_coarse.tv_sec;
 	vdso_data->xtime_coarse_nsec		= xtime_coarse.tv_nsec;
+	vdso_data->wtm_clock_sec		= tk->wall_to_monotonic.tv_sec;
+	vdso_data->wtm_clock_nsec		= tk->wall_to_monotonic.tv_nsec;
 
 	if (!use_syscall) {
 		vdso_data->cs_cycle_last	= tk->clock->cycle_last;
@@ -245,8 +247,6 @@ void update_vsyscall(struct timekeeper *tk)
 		vdso_data->xtime_clock_nsec	= tk->xtime_nsec;
 		vdso_data->cs_mult		= tk->mult;
 		vdso_data->cs_shift		= tk->shift;
-		vdso_data->wtm_clock_sec	= tk->wall_to_monotonic.tv_sec;
-		vdso_data->wtm_clock_nsec	= tk->wall_to_monotonic.tv_nsec;
 	}
 
 	smp_wmb();
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index d8064af..6d20b7d 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -48,7 +48,7 @@ $(obj-vdso): %.o: %.S
 
 # Actual build commands
 quiet_cmd_vdsold = VDSOL $@
-      cmd_vdsold = $(CC) $(c_flags) -Wl,-T $^ -o $@
+      cmd_vdsold = $(CC) $(c_flags) -Wl,-n -Wl,-T $^ -o $@
 quiet_cmd_vdsoas = VDSOA $@
       cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $<
 
diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S
index f0a6d10..fe652ff 100644
--- a/arch/arm64/kernel/vdso/gettimeofday.S
+++ b/arch/arm64/kernel/vdso/gettimeofday.S
@@ -103,6 +103,8 @@ ENTRY(__kernel_clock_gettime)
 	bl	__do_get_tspec
 	seqcnt_check w9, 1b
 
+	mov	x30, x2
+
 	cmp	w0, #CLOCK_MONOTONIC
 	b.ne	6f
 
@@ -118,6 +120,9 @@ ENTRY(__kernel_clock_gettime)
 	ccmp	w0, #CLOCK_MONOTONIC_COARSE, #0x4, ne
 	b.ne	8f
 
+	/* xtime_coarse_nsec is already right-shifted */
+	mov	x12, #0
+
 	/* Get coarse timespec. */
 	adr	vdso_data, _vdso_data
 3:	seqcnt_acquire
@@ -156,7 +161,7 @@ ENTRY(__kernel_clock_gettime)
 	lsr	x11, x11, x12
 	stp	x10, x11, [x1, #TSPEC_TV_SEC]
 	mov	x0, xzr
-	ret	x2
+	ret
 7:
 	mov	x30, x2
 8:	/* Syscall fallback. */
diff --git a/arch/arm64/lib/bitops.S b/arch/arm64/lib/bitops.S
index e5db797..7dac371 100644
--- a/arch/arm64/lib/bitops.S
+++ b/arch/arm64/lib/bitops.S
@@ -46,11 +46,12 @@ ENTRY(	\name	)
 	mov	x2, #1
 	add	x1, x1, x0, lsr #3	// Get word offset
 	lsl	x4, x2, x3		// Create mask
-1:	ldaxr	x2, [x1]
+1:	ldxr	x2, [x1]
 	lsr	x0, x2, x3		// Save old value of bit
 	\instr	x2, x2, x4		// toggle bit
 	stlxr	w5, x2, [x1]
 	cbnz	w5, 1b
+	dmb	ish
 	and	x0, x0, #1
 3:	ret
 ENDPROC(\name	)
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 45b5ab5..fbd7678 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -45,6 +45,7 @@ static void *arm64_swiotlb_alloc_coherent(struct device *dev, size_t size,
 	if (IS_ENABLED(CONFIG_DMA_CMA)) {
 		struct page *page;
 
+		size = PAGE_ALIGN(size);
 		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
 							get_order(size));
 		if (!page)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index f557ebb..f8dc7e8 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -203,10 +203,18 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
 	do {
 		next = pmd_addr_end(addr, end);
 		/* try section mapping first */
-		if (((addr | next | phys) & ~SECTION_MASK) == 0)
+		if (((addr | next | phys) & ~SECTION_MASK) == 0) {
+			pmd_t old_pmd =*pmd;
 			set_pmd(pmd, __pmd(phys | prot_sect_kernel));
-		else
+			/*
+			 * Check for previous table entries created during
+			 * boot (__create_page_tables) and flush them.
+			 */
+			if (!pmd_none(old_pmd))
+				flush_tlb_all();
+		} else {
 			alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys));
+		}
 		phys += next - addr;
 	} while (pmd++, addr = next, addr != end);
 }
diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c
index 7083cda..62c6101 100644
--- a/arch/arm64/mm/pgd.c
+++ b/arch/arm64/mm/pgd.c
@@ -32,17 +32,10 @@
 
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	pgd_t *new_pgd;
-
 	if (PGD_SIZE == PAGE_SIZE)
-		new_pgd = (pgd_t *)get_zeroed_page(GFP_KERNEL);
+		return (pgd_t *)get_zeroed_page(GFP_KERNEL);
 	else
-		new_pgd = kzalloc(PGD_SIZE, GFP_KERNEL);
-
-	if (!new_pgd)
-		return NULL;
-
-	return new_pgd;
+		return kzalloc(PGD_SIZE, GFP_KERNEL);
 }
 
 void pgd_free(struct mm_struct *mm, pgd_t *pgd)
diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h
index afd45e0..ae763d8b 100644
--- a/arch/ia64/include/asm/unistd.h
+++ b/arch/ia64/include/asm/unistd.h
@@ -11,7 +11,7 @@
 
 
 
-#define NR_syscalls			312 /* length of syscall table */
+#define NR_syscalls			314 /* length of syscall table */
 
 /*
  * The following defines stop scripts/checksyscalls.sh from complaining about
diff --git a/arch/ia64/include/uapi/asm/unistd.h b/arch/ia64/include/uapi/asm/unistd.h
index 34fd6fe..715e85f 100644
--- a/arch/ia64/include/uapi/asm/unistd.h
+++ b/arch/ia64/include/uapi/asm/unistd.h
@@ -325,5 +325,7 @@
 #define __NR_process_vm_writev		1333
 #define __NR_accept4			1334
 #define __NR_finit_module		1335
+#define __NR_sched_setattr		1336
+#define __NR_sched_getattr		1337
 
 #endif /* _UAPI_ASM_IA64_UNISTD_H */
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index ddea607f..fa8d61a 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -1773,6 +1773,8 @@ sys_call_table:
 	data8 sys_process_vm_writev
 	data8 sys_accept4
 	data8 sys_finit_module			// 1335
+	data8 sys_sched_setattr
+	data8 sys_sched_getattr
 
 	.org sys_call_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls
 #endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
diff --git a/arch/mips/alchemy/devboards/db1000.c b/arch/mips/alchemy/devboards/db1000.c
index 11f3ad2..5483906 100644
--- a/arch/mips/alchemy/devboards/db1000.c
+++ b/arch/mips/alchemy/devboards/db1000.c
@@ -534,13 +534,10 @@ static int __init db1000_dev_init(void)
 		s0 = AU1100_GPIO1_INT;
 		s1 = AU1100_GPIO4_INT;
 
+		gpio_request(19, "sd0_cd");
+		gpio_request(20, "sd1_cd");
 		gpio_direction_input(19);	/* sd0 cd# */
 		gpio_direction_input(20);	/* sd1 cd# */
-		gpio_direction_input(21);	/* touch pendown# */
-		gpio_direction_input(207);	/* SPI MISO */
-		gpio_direction_output(208, 0);	/* SPI MOSI */
-		gpio_direction_output(209, 1);	/* SPI SCK */
-		gpio_direction_output(210, 1);	/* SPI CS# */
 
 		/* spi_gpio on SSI0 pins */
 		pfc = __raw_readl((void __iomem *)SYS_PINFUNC);
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index cfe092f..6b97495 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -74,6 +74,8 @@ static inline int __enable_fpu(enum fpu_mode mode)
 	default:
 		BUG();
 	}
+
+	return SIGFPE;
 }
 
 #define __disable_fpu()							\
diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h
index 1dee279..d6e154a 100644
--- a/arch/mips/include/uapi/asm/unistd.h
+++ b/arch/mips/include/uapi/asm/unistd.h
@@ -369,16 +369,18 @@
 #define __NR_process_vm_writev		(__NR_Linux + 346)
 #define __NR_kcmp			(__NR_Linux + 347)
 #define __NR_finit_module		(__NR_Linux + 348)
+#define __NR_sched_setattr		(__NR_Linux + 349)
+#define __NR_sched_getattr		(__NR_Linux + 350)
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		348
+#define __NR_Linux_syscalls		350
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		348
+#define __NR_O32_Linux_syscalls		350
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -695,16 +697,18 @@
 #define __NR_kcmp			(__NR_Linux + 306)
 #define __NR_finit_module		(__NR_Linux + 307)
 #define __NR_getdents64			(__NR_Linux + 308)
+#define __NR_sched_setattr		(__NR_Linux + 309)
+#define __NR_sched_getattr		(__NR_Linux + 310)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		308
+#define __NR_Linux_syscalls		310
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		308
+#define __NR_64_Linux_syscalls		310
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -1025,15 +1029,17 @@
 #define __NR_process_vm_writev		(__NR_Linux + 310)
 #define __NR_kcmp			(__NR_Linux + 311)
 #define __NR_finit_module		(__NR_Linux + 312)
+#define __NR_sched_setattr		(__NR_Linux + 313)
+#define __NR_sched_getattr		(__NR_Linux + 314)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		312
+#define __NR_Linux_syscalls		314
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		312
+#define __NR_N32_Linux_syscalls		314
 
 #endif /* _UAPI_ASM_UNISTD_H */
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index e8e541b..a5b14f4 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -563,3 +563,5 @@ EXPORT(sys_call_table)
 	PTR	sys_process_vm_writev
 	PTR	sys_kcmp
 	PTR	sys_finit_module
+	PTR	sys_sched_setattr
+	PTR	sys_sched_getattr		/* 4350 */
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index 57e3742..b56e254 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -425,4 +425,6 @@ EXPORT(sys_call_table)
 	PTR	sys_kcmp
 	PTR	sys_finit_module
 	PTR	sys_getdents64
+	PTR	sys_sched_setattr
+	PTR	sys_sched_getattr		/* 5310 */
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 2f48f59..f7e5b72 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -418,4 +418,6 @@ EXPORT(sysn32_call_table)
 	PTR	compat_sys_process_vm_writev	/* 6310 */
 	PTR	sys_kcmp
 	PTR	sys_finit_module
+	PTR	sys_sched_setattr
+	PTR	sys_sched_getattr
 	.size	sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index f1acdb4..6788727d 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -541,4 +541,6 @@ EXPORT(sys32_call_table)
 	PTR	compat_sys_process_vm_writev
 	PTR	sys_kcmp
 	PTR	sys_finit_module
+	PTR	sys_sched_setattr
+	PTR	sys_sched_getattr		/* 4350 */
 	.size	sys32_call_table,.-sys32_call_table
diff --git a/arch/parisc/hpux/fs.c b/arch/parisc/hpux/fs.c
index 88d0962..2bedafe 100644
--- a/arch/parisc/hpux/fs.c
+++ b/arch/parisc/hpux/fs.c
@@ -33,22 +33,9 @@
 
 int hpux_execve(struct pt_regs *regs)
 {
-	int error;
-	struct filename *filename;
-
-	filename = getname((const char __user *) regs->gr[26]);
-	error = PTR_ERR(filename);
-	if (IS_ERR(filename))
-		goto out;
-
-	error = do_execve(filename->name,
+	return  do_execve(getname((const char __user *) regs->gr[26]),
 			  (const char __user *const __user *) regs->gr[25],
 			  (const char __user *const __user *) regs->gr[24]);
-
-	putname(filename);
-
-out:
-	return error;
 }
 
 struct hpux_dirent {
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index b3feabd..cf3c008 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -25,6 +25,7 @@
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/spinlock.h>
 #include "crypt_s390.h"
 
 #define AES_KEYLEN_128		1
@@ -32,6 +33,7 @@
 #define AES_KEYLEN_256		4
 
 static u8 *ctrblk;
+static DEFINE_SPINLOCK(ctrblk_lock);
 static char keylen_flag;
 
 struct s390_aes_ctx {
@@ -758,43 +760,67 @@ static int ctr_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 	return aes_set_key(tfm, in_key, key_len);
 }
 
+static unsigned int __ctrblk_init(u8 *ctrptr, unsigned int nbytes)
+{
+	unsigned int i, n;
+
+	/* only use complete blocks, max. PAGE_SIZE */
+	n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(AES_BLOCK_SIZE - 1);
+	for (i = AES_BLOCK_SIZE; i < n; i += AES_BLOCK_SIZE) {
+		memcpy(ctrptr + i, ctrptr + i - AES_BLOCK_SIZE,
+		       AES_BLOCK_SIZE);
+		crypto_inc(ctrptr + i, AES_BLOCK_SIZE);
+	}
+	return n;
+}
+
 static int ctr_aes_crypt(struct blkcipher_desc *desc, long func,
 			 struct s390_aes_ctx *sctx, struct blkcipher_walk *walk)
 {
 	int ret = blkcipher_walk_virt_block(desc, walk, AES_BLOCK_SIZE);
-	unsigned int i, n, nbytes;
-	u8 buf[AES_BLOCK_SIZE];
-	u8 *out, *in;
+	unsigned int n, nbytes;
+	u8 buf[AES_BLOCK_SIZE], ctrbuf[AES_BLOCK_SIZE];
+	u8 *out, *in, *ctrptr = ctrbuf;
 
 	if (!walk->nbytes)
 		return ret;
 
-	memcpy(ctrblk, walk->iv, AES_BLOCK_SIZE);
+	if (spin_trylock(&ctrblk_lock))
+		ctrptr = ctrblk;
+
+	memcpy(ctrptr, walk->iv, AES_BLOCK_SIZE);
 	while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
 		out = walk->dst.virt.addr;
 		in = walk->src.virt.addr;
 		while (nbytes >= AES_BLOCK_SIZE) {
-			/* only use complete blocks, max. PAGE_SIZE */
-			n = (nbytes > PAGE_SIZE) ? PAGE_SIZE :
-						 nbytes & ~(AES_BLOCK_SIZE - 1);
-			for (i = AES_BLOCK_SIZE; i < n; i += AES_BLOCK_SIZE) {
-				memcpy(ctrblk + i, ctrblk + i - AES_BLOCK_SIZE,
-				       AES_BLOCK_SIZE);
-				crypto_inc(ctrblk + i, AES_BLOCK_SIZE);
-			}
-			ret = crypt_s390_kmctr(func, sctx->key, out, in, n, ctrblk);
-			if (ret < 0 || ret != n)
+			if (ctrptr == ctrblk)
+				n = __ctrblk_init(ctrptr, nbytes);
+			else
+				n = AES_BLOCK_SIZE;
+			ret = crypt_s390_kmctr(func, sctx->key, out, in,
+					       n, ctrptr);
+			if (ret < 0 || ret != n) {
+				if (ctrptr == ctrblk)
+					spin_unlock(&ctrblk_lock);
 				return -EIO;
+			}
 			if (n > AES_BLOCK_SIZE)
-				memcpy(ctrblk, ctrblk + n - AES_BLOCK_SIZE,
+				memcpy(ctrptr, ctrptr + n - AES_BLOCK_SIZE,
 				       AES_BLOCK_SIZE);
-			crypto_inc(ctrblk, AES_BLOCK_SIZE);
+			crypto_inc(ctrptr, AES_BLOCK_SIZE);
 			out += n;
 			in += n;
 			nbytes -= n;
 		}
 		ret = blkcipher_walk_done(desc, walk, nbytes);
 	}
+	if (ctrptr == ctrblk) {
+		if (nbytes)
+			memcpy(ctrbuf, ctrptr, AES_BLOCK_SIZE);
+		else
+			memcpy(walk->iv, ctrptr, AES_BLOCK_SIZE);
+		spin_unlock(&ctrblk_lock);
+	}
 	/*
 	 * final block may be < AES_BLOCK_SIZE, copy only nbytes
 	 */
@@ -802,14 +828,15 @@ static int ctr_aes_crypt(struct blkcipher_desc *desc, long func,
 		out = walk->dst.virt.addr;
 		in = walk->src.virt.addr;
 		ret = crypt_s390_kmctr(func, sctx->key, buf, in,
-				       AES_BLOCK_SIZE, ctrblk);
+				       AES_BLOCK_SIZE, ctrbuf);
 		if (ret < 0 || ret != AES_BLOCK_SIZE)
 			return -EIO;
 		memcpy(out, buf, nbytes);
-		crypto_inc(ctrblk, AES_BLOCK_SIZE);
+		crypto_inc(ctrbuf, AES_BLOCK_SIZE);
 		ret = blkcipher_walk_done(desc, walk, 0);
+		memcpy(walk->iv, ctrbuf, AES_BLOCK_SIZE);
 	}
-	memcpy(walk->iv, ctrblk, AES_BLOCK_SIZE);
+
 	return ret;
 }
 
diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c
index 200f2a1..0a5aac8 100644
--- a/arch/s390/crypto/des_s390.c
+++ b/arch/s390/crypto/des_s390.c
@@ -25,6 +25,7 @@
 #define DES3_KEY_SIZE	(3 * DES_KEY_SIZE)
 
 static u8 *ctrblk;
+static DEFINE_SPINLOCK(ctrblk_lock);
 
 struct s390_des_ctx {
 	u8 iv[DES_BLOCK_SIZE];
@@ -105,29 +106,35 @@ static int ecb_desall_crypt(struct blkcipher_desc *desc, long func,
 }
 
 static int cbc_desall_crypt(struct blkcipher_desc *desc, long func,
-			    u8 *iv, struct blkcipher_walk *walk)
+			    struct blkcipher_walk *walk)
 {
+	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	int ret = blkcipher_walk_virt(desc, walk);
 	unsigned int nbytes = walk->nbytes;
+	struct {
+		u8 iv[DES_BLOCK_SIZE];
+		u8 key[DES3_KEY_SIZE];
+	} param;
 
 	if (!nbytes)
 		goto out;
 
-	memcpy(iv, walk->iv, DES_BLOCK_SIZE);
+	memcpy(param.iv, walk->iv, DES_BLOCK_SIZE);
+	memcpy(param.key, ctx->key, DES3_KEY_SIZE);
 	do {
 		/* only use complete blocks */
 		unsigned int n = nbytes & ~(DES_BLOCK_SIZE - 1);
 		u8 *out = walk->dst.virt.addr;
 		u8 *in = walk->src.virt.addr;
 
-		ret = crypt_s390_kmc(func, iv, out, in, n);
+		ret = crypt_s390_kmc(func, &param, out, in, n);
 		if (ret < 0 || ret != n)
 			return -EIO;
 
 		nbytes &= DES_BLOCK_SIZE - 1;
 		ret = blkcipher_walk_done(desc, walk, nbytes);
 	} while ((nbytes = walk->nbytes));
-	memcpy(walk->iv, iv, DES_BLOCK_SIZE);
+	memcpy(walk->iv, param.iv, DES_BLOCK_SIZE);
 
 out:
 	return ret;
@@ -179,22 +186,20 @@ static int cbc_des_encrypt(struct blkcipher_desc *desc,
 			   struct scatterlist *dst, struct scatterlist *src,
 			   unsigned int nbytes)
 {
-	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct blkcipher_walk walk;
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, KMC_DEA_ENCRYPT, ctx->iv, &walk);
+	return cbc_desall_crypt(desc, KMC_DEA_ENCRYPT, &walk);
 }
 
 static int cbc_des_decrypt(struct blkcipher_desc *desc,
 			   struct scatterlist *dst, struct scatterlist *src,
 			   unsigned int nbytes)
 {
-	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct blkcipher_walk walk;
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, KMC_DEA_DECRYPT, ctx->iv, &walk);
+	return cbc_desall_crypt(desc, KMC_DEA_DECRYPT, &walk);
 }
 
 static struct crypto_alg cbc_des_alg = {
@@ -327,22 +332,20 @@ static int cbc_des3_encrypt(struct blkcipher_desc *desc,
 			    struct scatterlist *dst, struct scatterlist *src,
 			    unsigned int nbytes)
 {
-	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct blkcipher_walk walk;
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, KMC_TDEA_192_ENCRYPT, ctx->iv, &walk);
+	return cbc_desall_crypt(desc, KMC_TDEA_192_ENCRYPT, &walk);
 }
 
 static int cbc_des3_decrypt(struct blkcipher_desc *desc,
 			    struct scatterlist *dst, struct scatterlist *src,
 			    unsigned int nbytes)
 {
-	struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct blkcipher_walk walk;
 
 	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return cbc_desall_crypt(desc, KMC_TDEA_192_DECRYPT, ctx->iv, &walk);
+	return cbc_desall_crypt(desc, KMC_TDEA_192_DECRYPT, &walk);
 }
 
 static struct crypto_alg cbc_des3_alg = {
@@ -366,54 +369,80 @@ static struct crypto_alg cbc_des3_alg = {
 	}
 };
 
+static unsigned int __ctrblk_init(u8 *ctrptr, unsigned int nbytes)
+{
+	unsigned int i, n;
+
+	/* align to block size, max. PAGE_SIZE */
+	n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(DES_BLOCK_SIZE - 1);
+	for (i = DES_BLOCK_SIZE; i < n; i += DES_BLOCK_SIZE) {
+		memcpy(ctrptr + i, ctrptr + i - DES_BLOCK_SIZE, DES_BLOCK_SIZE);
+		crypto_inc(ctrptr + i, DES_BLOCK_SIZE);
+	}
+	return n;
+}
+
 static int ctr_desall_crypt(struct blkcipher_desc *desc, long func,
-			    struct s390_des_ctx *ctx, struct blkcipher_walk *walk)
+			    struct s390_des_ctx *ctx,
+			    struct blkcipher_walk *walk)
 {
 	int ret = blkcipher_walk_virt_block(desc, walk, DES_BLOCK_SIZE);
-	unsigned int i, n, nbytes;
-	u8 buf[DES_BLOCK_SIZE];
-	u8 *out, *in;
+	unsigned int n, nbytes;
+	u8 buf[DES_BLOCK_SIZE], ctrbuf[DES_BLOCK_SIZE];
+	u8 *out, *in, *ctrptr = ctrbuf;
+
+	if (!walk->nbytes)
+		return ret;
 
-	memcpy(ctrblk, walk->iv, DES_BLOCK_SIZE);
+	if (spin_trylock(&ctrblk_lock))
+		ctrptr = ctrblk;
+
+	memcpy(ctrptr, walk->iv, DES_BLOCK_SIZE);
 	while ((nbytes = walk->nbytes) >= DES_BLOCK_SIZE) {
 		out = walk->dst.virt.addr;
 		in = walk->src.virt.addr;
 		while (nbytes >= DES_BLOCK_SIZE) {
-			/* align to block size, max. PAGE_SIZE */
-			n = (nbytes > PAGE_SIZE) ? PAGE_SIZE :
-				nbytes & ~(DES_BLOCK_SIZE - 1);
-			for (i = DES_BLOCK_SIZE; i < n; i += DES_BLOCK_SIZE) {
-				memcpy(ctrblk + i, ctrblk + i - DES_BLOCK_SIZE,
-				       DES_BLOCK_SIZE);
-				crypto_inc(ctrblk + i, DES_BLOCK_SIZE);
-			}
-			ret = crypt_s390_kmctr(func, ctx->key, out, in, n, ctrblk);
-			if (ret < 0 || ret != n)
+			if (ctrptr == ctrblk)
+				n = __ctrblk_init(ctrptr, nbytes);
+			else
+				n = DES_BLOCK_SIZE;
+			ret = crypt_s390_kmctr(func, ctx->key, out, in,
+					       n, ctrptr);
+			if (ret < 0 || ret != n) {
+				if (ctrptr == ctrblk)
+					spin_unlock(&ctrblk_lock);
 				return -EIO;
+			}
 			if (n > DES_BLOCK_SIZE)
-				memcpy(ctrblk, ctrblk + n - DES_BLOCK_SIZE,
+				memcpy(ctrptr, ctrptr + n - DES_BLOCK_SIZE,
 				       DES_BLOCK_SIZE);
-			crypto_inc(ctrblk, DES_BLOCK_SIZE);
+			crypto_inc(ctrptr, DES_BLOCK_SIZE);
 			out += n;
 			in += n;
 			nbytes -= n;
 		}
 		ret = blkcipher_walk_done(desc, walk, nbytes);
 	}
-
+	if (ctrptr == ctrblk) {
+		if (nbytes)
+			memcpy(ctrbuf, ctrptr, DES_BLOCK_SIZE);
+		else
+			memcpy(walk->iv, ctrptr, DES_BLOCK_SIZE);
+		spin_unlock(&ctrblk_lock);
+	}
 	/* final block may be < DES_BLOCK_SIZE, copy only nbytes */
 	if (nbytes) {
 		out = walk->dst.virt.addr;
 		in = walk->src.virt.addr;
 		ret = crypt_s390_kmctr(func, ctx->key, buf, in,
-				       DES_BLOCK_SIZE, ctrblk);
+				       DES_BLOCK_SIZE, ctrbuf);
 		if (ret < 0 || ret != DES_BLOCK_SIZE)
 			return -EIO;
 		memcpy(out, buf, nbytes);
-		crypto_inc(ctrblk, DES_BLOCK_SIZE);
+		crypto_inc(ctrbuf, DES_BLOCK_SIZE);
 		ret = blkcipher_walk_done(desc, walk, 0);
+		memcpy(walk->iv, ctrbuf, DES_BLOCK_SIZE);
 	}
-	memcpy(walk->iv, ctrblk, DES_BLOCK_SIZE);
 	return ret;
 }
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 940e50e..0af5250 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -444,6 +444,7 @@ config X86_INTEL_MID
 	bool "Intel MID platform support"
 	depends on X86_32
 	depends on X86_EXTENDED_PLATFORM
+	depends on X86_PLATFORM_DEVICES
 	depends on PCI
 	depends on PCI_GOANY
 	depends on X86_IO_APIC
@@ -1051,9 +1052,9 @@ config MICROCODE_INTEL
 	  This options enables microcode patch loading support for Intel
 	  processors.
 
-	  For latest news and information on obtaining all the required
-	  Intel ingredients for this driver, check:
-	  <http://www.urbanmyth.org/microcode/>.
+	  For the current Intel microcode data package go to
+	  <https://downloadcenter.intel.com> and search for
+	  'Linux Processor Microcode Data File'.
 
 config MICROCODE_AMD
 	bool "AMD microcode loading support"
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 0f3621e..321a52c 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -184,6 +184,7 @@ config HAVE_MMIOTRACE_SUPPORT
 config X86_DECODER_SELFTEST
 	bool "x86 instruction decoder selftest"
 	depends on DEBUG_KERNEL && KPROBES
+	depends on !COMPILE_TEST
 	---help---
 	 Perform x86 instruction decoder selftests at build time.
 	 This option is useful for checking the sanity of x86 instruction
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index a54ee1d..aaac3b2 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -19,7 +19,7 @@ extern int amd_cache_northbridges(void);
 extern void amd_flush_garts(void);
 extern int amd_numa_init(void);
 extern int amd_get_subcaches(int);
-extern int amd_set_subcaches(int, int);
+extern int amd_set_subcaches(int, unsigned long);
 
 struct amd_l3_cache {
 	unsigned indices;
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index e6d90ba..04905bfc 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -62,7 +62,7 @@ static inline void __flush_tlb_all(void)
 
 static inline void __flush_tlb_one(unsigned long addr)
 {
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
 	__flush_tlb_single(addr);
 }
 
@@ -93,13 +93,13 @@ static inline void __flush_tlb_one(unsigned long addr)
  */
 static inline void __flush_tlb_up(void)
 {
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 }
 
 static inline void flush_tlb_all(void)
 {
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb_all();
 }
 
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 787e1bb..3e276eb 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -52,8 +52,7 @@ extern unsigned long set_phys_range_identity(unsigned long pfn_s,
 extern int m2p_add_override(unsigned long mfn, struct page *page,
 			    struct gnttab_map_grant_ref *kmap_op);
 extern int m2p_remove_override(struct page *page,
-			       struct gnttab_map_grant_ref *kmap_op,
-			       unsigned long mfn);
+				struct gnttab_map_grant_ref *kmap_op);
 extern struct page *m2p_find_override(unsigned long mfn);
 extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
 
@@ -122,7 +121,7 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn)
 		pfn = m2p_find_override_pfn(mfn, ~0);
 	}
 
-	/*
+	/* 
 	 * pfn is ~0 if there are no entries in the m2p for mfn or if the
 	 * entry doesn't map back to the mfn and m2p_override doesn't have a
 	 * valid entry for it.
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 59554dc..dec8de4 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -179,7 +179,7 @@ int amd_get_subcaches(int cpu)
 	return (mask >> (4 * cuid)) & 0xf;
 }
 
-int amd_set_subcaches(int cpu, int mask)
+int amd_set_subcaches(int cpu, unsigned long mask)
 {
 	static unsigned int reset, ban;
 	struct amd_northbridge *nb = node_to_amd_nb(amd_get_nb_id(cpu));
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index d3153e2..c67ffa6 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -767,10 +767,7 @@ static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 
 static void cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c)
 {
-	tlb_flushall_shift = 5;
-
-	if (c->x86 <= 0x11)
-		tlb_flushall_shift = 4;
+	tlb_flushall_shift = 6;
 }
 
 static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 3db61c6..5cd9bfa 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -640,21 +640,17 @@ static void intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c)
 	case 0x61d: /* six-core 45 nm xeon "Dunnington" */
 		tlb_flushall_shift = -1;
 		break;
+	case 0x63a: /* Ivybridge */
+		tlb_flushall_shift = 2;
+		break;
 	case 0x61a: /* 45 nm nehalem, "Bloomfield" */
 	case 0x61e: /* 45 nm nehalem, "Lynnfield" */
 	case 0x625: /* 32 nm nehalem, "Clarkdale" */
 	case 0x62c: /* 32 nm nehalem, "Gulftown" */
 	case 0x62e: /* 45 nm nehalem-ex, "Beckton" */
 	case 0x62f: /* 32 nm Xeon E7 */
-		tlb_flushall_shift = 6;
-		break;
 	case 0x62a: /* SandyBridge */
 	case 0x62d: /* SandyBridge, "Romely-EP" */
-		tlb_flushall_shift = 5;
-		break;
-	case 0x63a: /* Ivybridge */
-		tlb_flushall_shift = 1;
-		break;
 	default:
 		tlb_flushall_shift = 6;
 	}
diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c
index 8384c0f..617a9e2 100644
--- a/arch/x86/kernel/cpu/microcode/amd_early.c
+++ b/arch/x86/kernel/cpu/microcode/amd_early.c
@@ -285,6 +285,15 @@ static void __init collect_cpu_sig_on_bsp(void *arg)
 
 	uci->cpu_sig.sig = cpuid_eax(0x00000001);
 }
+
+static void __init get_bsp_sig(void)
+{
+	unsigned int bsp = boot_cpu_data.cpu_index;
+	struct ucode_cpu_info *uci = ucode_cpu_info + bsp;
+
+	if (!uci->cpu_sig.sig)
+		smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1);
+}
 #else
 void load_ucode_amd_ap(void)
 {
@@ -337,31 +346,37 @@ void load_ucode_amd_ap(void)
 
 int __init save_microcode_in_initrd_amd(void)
 {
+	unsigned long cont;
 	enum ucode_state ret;
 	u32 eax;
 
-#ifdef CONFIG_X86_32
-	unsigned int bsp = boot_cpu_data.cpu_index;
-	struct ucode_cpu_info *uci = ucode_cpu_info + bsp;
-
-	if (!uci->cpu_sig.sig)
-		smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1);
+	if (!container)
+		return -EINVAL;
 
+#ifdef CONFIG_X86_32
+	get_bsp_sig();
+	cont = (unsigned long)container;
+#else
 	/*
-	 * Take into account the fact that the ramdisk might get relocated
-	 * and therefore we need to recompute the container's position in
-	 * virtual memory space.
+	 * We need the physical address of the container for both bitness since
+	 * boot_params.hdr.ramdisk_image is a physical address.
 	 */
-	container = (u8 *)(__va((u32)relocated_ramdisk) +
-			   ((u32)container - boot_params.hdr.ramdisk_image));
+	cont = __pa(container);
 #endif
+
+	/*
+	 * Take into account the fact that the ramdisk might get relocated and
+	 * therefore we need to recompute the container's position in virtual
+	 * memory space.
+	 */
+	if (relocated_ramdisk)
+		container = (u8 *)(__va(relocated_ramdisk) +
+			     (cont - boot_params.hdr.ramdisk_image));
+
 	if (ucode_new_rev)
 		pr_info("microcode: updated early to new patch_level=0x%08x\n",
 			ucode_new_rev);
 
-	if (!container)
-		return -EINVAL;
-
 	eax   = cpuid_eax(0x00000001);
 	eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
 
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index ce2d0a2..0e25a1b 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -683,7 +683,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 	}
 
 	/* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 
 	/* Save MTRR state */
@@ -697,7 +697,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 static void post_set(void) __releases(set_atomicity_lock)
 {
 	/* Flush TLBs (no need to flush caches - they are disabled) */
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 
 	/* Intel (P6) standard MTRRs */
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index dbb6087..d99f31d 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -266,6 +266,14 @@ __visible void smp_trace_x86_platform_ipi(struct pt_regs *regs)
 EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq);
 
 #ifdef CONFIG_HOTPLUG_CPU
+
+/* These two declarations are only used in check_irq_vectors_for_cpu_disable()
+ * below, which is protected by stop_machine().  Putting them on the stack
+ * results in a stack frame overflow.  Dynamically allocating could result in a
+ * failure so declare these two cpumasks as global.
+ */
+static struct cpumask affinity_new, online_new;
+
 /*
  * This cpu is going to be removed and its vectors migrated to the remaining
  * online cpus.  Check to see if there are enough vectors in the remaining cpus.
@@ -277,7 +285,6 @@ int check_irq_vectors_for_cpu_disable(void)
 	unsigned int this_cpu, vector, this_count, count;
 	struct irq_desc *desc;
 	struct irq_data *data;
-	struct cpumask affinity_new, online_new;
 
 	this_cpu = smp_processor_id();
 	cpumask_copy(&online_new, cpu_online_mask);
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 04ee1e2..7c6acd4 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -571,3 +571,40 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F5,
 			quirk_amd_nb_node);
 
 #endif
+
+#ifdef CONFIG_PCI
+/*
+ * Processor does not ensure DRAM scrub read/write sequence
+ * is atomic wrt accesses to CC6 save state area. Therefore
+ * if a concurrent scrub read/write access is to same address
+ * the entry may appear as if it is not written. This quirk
+ * applies to Fam16h models 00h-0Fh
+ *
+ * See "Revision Guide" for AMD F16h models 00h-0fh,
+ * document 51810 rev. 3.04, Nov 2013
+ */
+static void amd_disable_seq_and_redirect_scrub(struct pci_dev *dev)
+{
+	u32 val;
+
+	/*
+	 * Suggested workaround:
+	 * set D18F3x58[4:0] = 00h and set D18F3x5C[0] = 0b
+	 */
+	pci_read_config_dword(dev, 0x58, &val);
+	if (val & 0x1F) {
+		val &= ~(0x1F);
+		pci_write_config_dword(dev, 0x58, val);
+	}
+
+	pci_read_config_dword(dev, 0x5C, &val);
+	if (val & BIT(0)) {
+		val &= ~BIT(0);
+		pci_write_config_dword(dev, 0x5c, val);
+	}
+}
+
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3,
+			amd_disable_seq_and_redirect_scrub);
+
+#endif
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 81b2750..27aa0455 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -493,14 +493,6 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 		struct numa_memblk *mb = &mi->blk[i];
 		memblock_set_node(mb->start, mb->end - mb->start,
 				  &memblock.memory, mb->nid);
-
-		/*
-		 * At this time, all memory regions reserved by memblock are
-		 * used by the kernel. Set the nid in memblock.reserved will
-		 * mark out all the nodes the kernel resides in.
-		 */
-		memblock_set_node(mb->start, mb->end - mb->start,
-				  &memblock.reserved, mb->nid);
 	}
 
 	/*
@@ -565,10 +557,21 @@ static void __init numa_init_array(void)
 static void __init numa_clear_kernel_node_hotplug(void)
 {
 	int i, nid;
-	nodemask_t numa_kernel_nodes;
+	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
 	unsigned long start, end;
 	struct memblock_type *type = &memblock.reserved;
 
+	/*
+	 * At this time, all memory regions reserved by memblock are
+	 * used by the kernel. Set the nid in memblock.reserved will
+	 * mark out all the nodes the kernel resides in.
+	 */
+	for (i = 0; i < numa_meminfo.nr_blks; i++) {
+		struct numa_memblk *mb = &numa_meminfo.blk[i];
+		memblock_set_node(mb->start, mb->end - mb->start,
+				  &memblock.reserved, mb->nid);
+	}
+
 	/* Mark all kernel nodes. */
 	for (i = 0; i < type->cnt; i++)
 		node_set(type->regions[i].nid, numa_kernel_nodes);
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 0342d27..47b6436 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -52,6 +52,8 @@ void memory_present(int nid, unsigned long start, unsigned long end)
 			nid, start, end);
 	printk(KERN_DEBUG "  Setting physnode_map array to node %d for pfns:\n", nid);
 	printk(KERN_DEBUG "  ");
+	start = round_down(start, PAGES_PER_SECTION);
+	end = round_up(end, PAGES_PER_SECTION);
 	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
 		physnode_map[pfn / PAGES_PER_SECTION] = nid;
 		printk(KERN_CONT "%lx ", pfn);
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 1a25187..1953e9c 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -42,15 +42,25 @@ static __init inline int srat_disabled(void)
 	return acpi_numa < 0;
 }
 
-/* Callback for SLIT parsing */
+/*
+ * Callback for SLIT parsing.  pxm_to_node() returns NUMA_NO_NODE for
+ * I/O localities since SRAT does not list them.  I/O localities are
+ * not supported at this point.
+ */
 void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
 {
 	int i, j;
 
-	for (i = 0; i < slit->locality_count; i++)
-		for (j = 0; j < slit->locality_count; j++)
+	for (i = 0; i < slit->locality_count; i++) {
+		if (pxm_to_node(i) == NUMA_NO_NODE)
+			continue;
+		for (j = 0; j < slit->locality_count; j++) {
+			if (pxm_to_node(j) == NUMA_NO_NODE)
+				continue;
 			numa_set_distance(pxm_to_node(i), pxm_to_node(j),
 				slit->entry[slit->locality_count * i + j]);
+		}
+	}
 }
 
 /* Callback for Proximity Domain -> x2APIC mapping */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index ae699b3..dd8dda1 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -103,7 +103,7 @@ static void flush_tlb_func(void *info)
 	if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
 		return;
 
-	count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
 		if (f->flush_end == TLB_FLUSH_ALL)
 			local_flush_tlb();
@@ -131,7 +131,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 	info.flush_start = start;
 	info.flush_end = end;
 
-	count_vm_event(NR_TLB_REMOTE_FLUSH);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	if (is_uv_system()) {
 		unsigned int cpu;
 
@@ -151,44 +151,19 @@ void flush_tlb_current_task(void)
 
 	preempt_disable();
 
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	local_flush_tlb();
 	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
 		flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
 	preempt_enable();
 }
 
-/*
- * It can find out the THP large page, or
- * HUGETLB page in tlb_flush when THP disabled
- */
-static inline unsigned long has_large_page(struct mm_struct *mm,
-				 unsigned long start, unsigned long end)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	unsigned long addr = ALIGN(start, HPAGE_SIZE);
-	for (; addr < end; addr += HPAGE_SIZE) {
-		pgd = pgd_offset(mm, addr);
-		if (likely(!pgd_none(*pgd))) {
-			pud = pud_offset(pgd, addr);
-			if (likely(!pud_none(*pud))) {
-				pmd = pmd_offset(pud, addr);
-				if (likely(!pmd_none(*pmd)))
-					if (pmd_large(*pmd))
-						return addr;
-			}
-		}
-	}
-	return 0;
-}
-
 void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 				unsigned long end, unsigned long vmflag)
 {
 	unsigned long addr;
 	unsigned act_entries, tlb_entries = 0;
+	unsigned long nr_base_pages;
 
 	preempt_disable();
 	if (current->active_mm != mm)
@@ -210,21 +185,20 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 		tlb_entries = tlb_lli_4k[ENTRIES];
 	else
 		tlb_entries = tlb_lld_4k[ENTRIES];
+
 	/* Assume all of TLB entries was occupied by this task */
-	act_entries = mm->total_vm > tlb_entries ? tlb_entries : mm->total_vm;
+	act_entries = tlb_entries >> tlb_flushall_shift;
+	act_entries = mm->total_vm > act_entries ? act_entries : mm->total_vm;
+	nr_base_pages = (end - start) >> PAGE_SHIFT;
 
 	/* tlb_flushall_shift is on balance point, details in commit log */
-	if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) {
-		count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	if (nr_base_pages > act_entries) {
+		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 		local_flush_tlb();
 	} else {
-		if (has_large_page(mm, start, end)) {
-			local_flush_tlb();
-			goto flush_all;
-		}
 		/* flush range by one by one 'invlpg' */
 		for (addr = start; addr < end;	addr += PAGE_SIZE) {
-			count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
+			count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
 			__flush_tlb_single(addr);
 		}
 
@@ -262,7 +236,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
 
 static void do_flush_tlb_all(void *info)
 {
-	count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
 	__flush_tlb_all();
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
 		leave_mm(smp_processor_id());
@@ -270,7 +244,7 @@ static void do_flush_tlb_all(void *info)
 
 void flush_tlb_all(void)
 {
-	count_vm_event(NR_TLB_REMOTE_FLUSH);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	on_each_cpu(do_flush_tlb_all, NULL, 1);
 }
 
diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c
index 7145ec6..4df9591 100644
--- a/arch/x86/platform/efi/efi-bgrt.c
+++ b/arch/x86/platform/efi/efi-bgrt.c
@@ -49,7 +49,8 @@ void __init efi_bgrt_init(void)
 
 	image = efi_lookup_mapped_addr(bgrt_tab->image_address);
 	if (!image) {
-		image = ioremap(bgrt_tab->image_address, sizeof(bmp_header));
+		image = early_memremap(bgrt_tab->image_address,
+				       sizeof(bmp_header));
 		ioremapped = true;
 		if (!image)
 			return;
@@ -57,7 +58,7 @@ void __init efi_bgrt_init(void)
 
 	memcpy_fromio(&bmp_header, image, sizeof(bmp_header));
 	if (ioremapped)
-		iounmap(image);
+		early_iounmap(image, sizeof(bmp_header));
 	bgrt_image_size = bmp_header.size;
 
 	bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL);
@@ -65,7 +66,8 @@ void __init efi_bgrt_init(void)
 		return;
 
 	if (ioremapped) {
-		image = ioremap(bgrt_tab->image_address, bmp_header.size);
+		image = early_memremap(bgrt_tab->image_address,
+				       bmp_header.size);
 		if (!image) {
 			kfree(bgrt_image);
 			bgrt_image = NULL;
@@ -75,5 +77,5 @@ void __init efi_bgrt_init(void)
 
 	memcpy_fromio(bgrt_image, image, bgrt_image_size);
 	if (ioremapped)
-		iounmap(image);
+		early_iounmap(image, bmp_header.size);
 }
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index a4d7b64..201d09a 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1473,6 +1473,18 @@ static void xen_pvh_set_cr_flags(int cpu)
 	 * X86_CR0_TS, X86_CR0_PE, X86_CR0_ET are set by Xen for HVM guests
 	 * (which PVH shared codepaths), while X86_CR0_PG is for PVH. */
 	write_cr0(read_cr0() | X86_CR0_MP | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM);
+
+	if (!cpu)
+		return;
+	/*
+	 * For BSP, PSE PGE are set in probe_page_size_mask(), for APs
+	 * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu_init.
+	*/
+	if (cpu_has_pse)
+		set_in_cr4(X86_CR4_PSE);
+
+	if (cpu_has_pge)
+		set_in_cr4(X86_CR4_PGE);
 }
 
 /*
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 8009acb..696c694 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -899,6 +899,13 @@ int m2p_add_override(unsigned long mfn, struct page *page,
 					"m2p_add_override: pfn %lx not mapped", pfn))
 			return -EINVAL;
 	}
+	WARN_ON(PagePrivate(page));
+	SetPagePrivate(page);
+	set_page_private(page, mfn);
+	page->index = pfn_to_mfn(pfn);
+
+	if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn))))
+		return -ENOMEM;
 
 	if (kmap_op != NULL) {
 		if (!PageHighMem(page)) {
@@ -937,16 +944,19 @@ int m2p_add_override(unsigned long mfn, struct page *page,
 }
 EXPORT_SYMBOL_GPL(m2p_add_override);
 int m2p_remove_override(struct page *page,
-			struct gnttab_map_grant_ref *kmap_op,
-			unsigned long mfn)
+		struct gnttab_map_grant_ref *kmap_op)
 {
 	unsigned long flags;
+	unsigned long mfn;
 	unsigned long pfn;
 	unsigned long uninitialized_var(address);
 	unsigned level;
 	pte_t *ptep = NULL;
 
 	pfn = page_to_pfn(page);
+	mfn = get_phys_to_machine(pfn);
+	if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT))
+		return -EINVAL;
 
 	if (!PageHighMem(page)) {
 		address = (unsigned long)__va(pfn << PAGE_SHIFT);
@@ -960,7 +970,10 @@ int m2p_remove_override(struct page *page,
 	spin_lock_irqsave(&m2p_override_lock, flags);
 	list_del(&page->lru);
 	spin_unlock_irqrestore(&m2p_override_lock, flags);
+	WARN_ON(!PagePrivate(page));
+	ClearPagePrivate(page);
 
+	set_phys_to_machine(pfn, page->index);
 	if (kmap_op != NULL) {
 		if (!PageHighMem(page)) {
 			struct multicall_space mcs;