diff --git a/Documentation/lzo.txt b/Documentation/lzo.txt
new file mode 100644
index 000000000000..ea45dd3901e3
--- /dev/null
+++ b/Documentation/lzo.txt
@@ -0,0 +1,164 @@
+
+LZO stream format as understood by Linux's LZO decompressor
+===========================================================
+
+Introduction
+
+  This is not a specification. No specification seems to be publicly available
+  for the LZO stream format. This document describes what input format the LZO
+  decompressor as implemented in the Linux kernel understands. The file subject
+  of this analysis is lib/lzo/lzo1x_decompress_safe.c. No analysis was made on
+  the compressor nor on any other implementations though it seems likely that
+  the format matches the standard one. The purpose of this document is to
+  better understand what the code does in order to propose more efficient fixes
+  for future bug reports.
+
+Description
+
+  The stream is composed of a series of instructions, operands, and data. The
+  instructions consist in a few bits representing an opcode, and bits forming
+  the operands for the instruction, whose size and position depend on the
+  opcode and on the number of literals copied by previous instruction. The
+  operands are used to indicate :
+
+    - a distance when copying data from the dictionary (past output buffer)
+    - a length (number of bytes to copy from dictionary)
+    - the number of literals to copy, which is retained in variable "state"
+      as a piece of information for next instructions.
+
+  Optionally depending on the opcode and operands, extra data may follow. These
+  extra data can be a complement for the operand (eg: a length or a distance
+  encoded on larger values), or a literal to be copied to the output buffer.
+
+  The first byte of the block follows a different encoding from other bytes, it
+  seems to be optimized for literal use only, since there is no dictionary yet
+  prior to that byte.
+
+  Lengths are always encoded on a variable size starting with a small number
+  of bits in the operand. If the number of bits isn't enough to represent the
+  length, up to 255 may be added in increments by consuming more bytes with a
+  rate of at most 255 per extra byte (thus the compression ratio cannot exceed
+  around 255:1). The variable length encoding using #bits is always the same :
+
+       length = byte & ((1 << #bits) - 1)
+       if (!length) {
+               length = ((1 << #bits) - 1)
+               length += 255*(number of zero bytes)
+               length += first-non-zero-byte
+       }
+       length += constant (generally 2 or 3)
+
+  For references to the dictionary, distances are relative to the output
+  pointer. Distances are encoded using very few bits belonging to certain
+  ranges, resulting in multiple copy instructions using different encodings.
+  Certain encodings involve one extra byte, others involve two extra bytes
+  forming a little-endian 16-bit quantity (marked LE16 below).
+
+  After any instruction except the large literal copy, 0, 1, 2 or 3 literals
+  are copied before starting the next instruction. The number of literals that
+  were copied may change the meaning and behaviour of the next instruction. In
+  practice, only one instruction needs to know whether 0, less than 4, or more
+  literals were copied. This is the information stored in the <state> variable
+  in this implementation. This number of immediate literals to be copied is
+  generally encoded in the last two bits of the instruction but may also be
+  taken from the last two bits of an extra operand (eg: distance).
+
+  End of stream is declared when a block copy of distance 0 is seen. Only one
+  instruction may encode this distance (0001HLLL), it takes one LE16 operand
+  for the distance, thus requiring 3 bytes.
+
+  IMPORTANT NOTE : in the code some length checks are missing because certain
+  instructions are called under the assumption that a certain number of bytes
+  follow because it has already been garanteed before parsing the instructions.
+  They just have to "refill" this credit if they consume extra bytes. This is
+  an implementation design choice independant on the algorithm or encoding.
+
+Byte sequences
+
+  First byte encoding :
+
+      0..17   : follow regular instruction encoding, see below. It is worth
+                noting that codes 16 and 17 will represent a block copy from
+                the dictionary which is empty, and that they will always be
+                invalid at this place.
+
+      18..21  : copy 0..3 literals
+                state = (byte - 17) = 0..3  [ copy <state> literals ]
+                skip byte
+
+      22..255 : copy literal string
+                length = (byte - 17) = 4..238
+                state = 4 [ don't copy extra literals ]
+                skip byte
+
+  Instruction encoding :
+
+      0 0 0 0 X X X X  (0..15)
+        Depends on the number of literals copied by the last instruction.
+        If last instruction did not copy any literal (state == 0), this
+        encoding will be a copy of 4 or more literal, and must be interpreted
+        like this :
+
+           0 0 0 0 L L L L  (0..15)  : copy long literal string
+           length = 3 + (L ?: 15 + (zero_bytes * 255) + non_zero_byte)
+           state = 4  (no extra literals are copied)
+
+        If last instruction used to copy between 1 to 3 literals (encoded in
+        the instruction's opcode or distance), the instruction is a copy of a
+        2-byte block from the dictionary within a 1kB distance. It is worth
+        noting that this instruction provides little savings since it uses 2
+        bytes to encode a copy of 2 other bytes but it encodes the number of
+        following literals for free. It must be interpreted like this :
+
+           0 0 0 0 D D S S  (0..15)  : copy 2 bytes from <= 1kB distance
+           length = 2
+           state = S (copy S literals after this block)
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 2) + D + 1
+
+        If last instruction used to copy 4 or more literals (as detected by
+        state == 4), the instruction becomes a copy of a 3-byte block from the
+        dictionary from a 2..3kB distance, and must be interpreted like this :
+
+           0 0 0 0 D D S S  (0..15)  : copy 3 bytes from 2..3 kB distance
+           length = 3
+           state = S (copy S literals after this block)
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 2) + D + 2049
+
+      0 0 0 1 H L L L  (16..31)
+           Copy of a block within 16..48kB distance (preferably less than 10B)
+           length = 2 + (L ?: 7 + (zero_bytes * 255) + non_zero_byte)
+        Always followed by exactly one LE16 :  D D D D D D D D : D D D D D D S S
+           distance = 16384 + (H << 14) + D
+           state = S (copy S literals after this block)
+           End of stream is reached if distance == 16384
+
+      0 0 1 L L L L L  (32..63)
+           Copy of small block within 16kB distance (preferably less than 34B)
+           length = 2 + (L ?: 31 + (zero_bytes * 255) + non_zero_byte)
+        Always followed by exactly one LE16 :  D D D D D D D D : D D D D D D S S
+           distance = D + 1
+           state = S (copy S literals after this block)
+
+      0 1 L D D D S S  (64..127)
+           Copy 3-4 bytes from block within 2kB distance
+           state = S (copy S literals after this block)
+           length = 3 + L
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 3) + D + 1
+
+      1 L L D D D S S  (128..255)
+           Copy 5-8 bytes from block within 2kB distance
+           state = S (copy S literals after this block)
+           length = 5 + L
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 3) + D + 1
+
+Authors
+
+  This document was written by Willy Tarreau <w@1wt.eu> on 2014/07/19 during an
+  analysis of the decompression code available in Linux 3.16-rc5. The code is
+  tricky, it is possible that this document contains mistakes or that a few
+  corner cases were overlooked. In any case, please report any doubt, fix, or
+  proposed updates to the author(s) so that the document can be updated.
diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt
index 290894176142..53838d9c6295 100644
--- a/Documentation/virtual/kvm/mmu.txt
+++ b/Documentation/virtual/kvm/mmu.txt
@@ -425,6 +425,20 @@ fault through the slow path.
 Since only 19 bits are used to store generation-number on mmio spte, all
 pages are zapped when there is an overflow.
 
+Unfortunately, a single memory access might access kvm_memslots(kvm) multiple
+times, the last one happening when the generation number is retrieved and
+stored into the MMIO spte.  Thus, the MMIO spte might be created based on
+out-of-date information, but with an up-to-date generation number.
+
+To avoid this, the generation number is incremented again after synchronize_srcu
+returns; thus, the low bit of kvm_memslots(kvm)->generation is only 1 during a
+memslot update, while some SRCU readers might be using the old copy.  We do not
+want to use an MMIO sptes created with an odd generation number, and we can do
+this without losing a bit in the MMIO spte.  The low bit of the generation
+is not stored in MMIO spte, and presumed zero when it is extracted out of the
+spte.  If KVM is unlucky and creates an MMIO spte while the low bit is 1,
+the next access to the spte will always be a cache miss.
+
 
 Further reading
 ===============
diff --git a/Makefile b/Makefile
index a59980eb4557..135a04a26076 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 14
-SUBLEVEL = 22
+SUBLEVEL = 23
 EXTRAVERSION =
 NAME = Remembering Coco
 
diff --git a/arch/arm/boot/dts/armada-370-netgear-rn102.dts b/arch/arm/boot/dts/armada-370-netgear-rn102.dts
index 651aeb5ef439..f3188e953de4 100644
--- a/arch/arm/boot/dts/armada-370-netgear-rn102.dts
+++ b/arch/arm/boot/dts/armada-370-netgear-rn102.dts
@@ -144,6 +144,10 @@
 				marvell,nand-enable-arbiter;
 				nand-on-flash-bbt;
 
+				/* Use Hardware BCH ECC */
+				nand-ecc-strength = <4>;
+				nand-ecc-step-size = <512>;
+
 				partition@0 {
 					label = "u-boot";
 					reg = <0x0000000 0x180000>;  /* 1.5MB */
diff --git a/arch/arm/boot/dts/armada-370-netgear-rn104.dts b/arch/arm/boot/dts/armada-370-netgear-rn104.dts
index 4e27587667bf..da406c1c726a 100644
--- a/arch/arm/boot/dts/armada-370-netgear-rn104.dts
+++ b/arch/arm/boot/dts/armada-370-netgear-rn104.dts
@@ -146,6 +146,10 @@
 				marvell,nand-enable-arbiter;
 				nand-on-flash-bbt;
 
+				/* Use Hardware BCH ECC */
+				nand-ecc-strength = <4>;
+				nand-ecc-step-size = <512>;
+
 				partition@0 {
 					label = "u-boot";
 					reg = <0x0000000 0x180000>;  /* 1.5MB */
diff --git a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts
index ff049ee862eb..b4aba09de911 100644
--- a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts
+++ b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts
@@ -224,6 +224,10 @@
 				marvell,nand-enable-arbiter;
 				nand-on-flash-bbt;
 
+				/* Use Hardware BCH ECC */
+				nand-ecc-strength = <4>;
+				nand-ecc-step-size = <512>;
+
 				partition@0 {
 					label = "u-boot";
 					reg = <0x0000000 0x180000>;  /* 1.5MB */
diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi
index fece8665fb63..b8f234bf7de8 100644
--- a/arch/arm/boot/dts/at91sam9263.dtsi
+++ b/arch/arm/boot/dts/at91sam9263.dtsi
@@ -535,6 +535,7 @@
 				compatible = "atmel,hsmci";
 				reg = <0xfff80000 0x600>;
 				interrupts = <10 IRQ_TYPE_LEVEL_HIGH 0>;
+				pinctrl-names = "default";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -544,6 +545,7 @@
 				compatible = "atmel,hsmci";
 				reg = <0xfff84000 0x600>;
 				interrupts = <11 IRQ_TYPE_LEVEL_HIGH 0>;
+				pinctrl-names = "default";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
diff --git a/arch/arm/boot/dts/sama5d3_can.dtsi b/arch/arm/boot/dts/sama5d3_can.dtsi
index a0775851cce5..eaf41451ad0c 100644
--- a/arch/arm/boot/dts/sama5d3_can.dtsi
+++ b/arch/arm/boot/dts/sama5d3_can.dtsi
@@ -40,7 +40,7 @@
 						atmel,clk-output-range = <0 66000000>;
 					};
 
-					can1_clk: can0_clk {
+					can1_clk: can1_clk {
 						#clock-cells = <0>;
 						reg = <41>;
 						atmel,clk-output-range = <0 66000000>;
diff --git a/arch/arm/mach-at91/clock.c b/arch/arm/mach-at91/clock.c
index 034529d801b2..d66f102c352a 100644
--- a/arch/arm/mach-at91/clock.c
+++ b/arch/arm/mach-at91/clock.c
@@ -962,6 +962,7 @@ static int __init at91_clock_reset(void)
 	}
 
 	at91_pmc_write(AT91_PMC_SCDR, scdr);
+	at91_pmc_write(AT91_PMC_PCDR, pcdr);
 	if (cpu_is_sama5d3())
 		at91_pmc_write(AT91_PMC_PCDR1, pcdr1);
 
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index fda2704b3f9f..e72289a97367 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -37,8 +37,8 @@ typedef s32		compat_ssize_t;
 typedef s32		compat_time_t;
 typedef s32		compat_clock_t;
 typedef s32		compat_pid_t;
-typedef u32		__compat_uid_t;
-typedef u32		__compat_gid_t;
+typedef u16		__compat_uid_t;
+typedef u16		__compat_gid_t;
 typedef u16		__compat_uid16_t;
 typedef u16		__compat_gid16_t;
 typedef u32		__compat_uid32_t;
diff --git a/arch/m68k/mm/hwtest.c b/arch/m68k/mm/hwtest.c
index 2c7dde3c6430..2a5259fd23eb 100644
--- a/arch/m68k/mm/hwtest.c
+++ b/arch/m68k/mm/hwtest.c
@@ -28,9 +28,11 @@
 int hwreg_present( volatile void *regp )
 {
     int	ret = 0;
+    unsigned long flags;
     long	save_sp, save_vbr;
     long	tmp_vectors[3];
 
+    local_irq_save(flags);
     __asm__ __volatile__
 	(	"movec	%/vbr,%2\n\t"
 		"movel	#Lberr1,%4@(8)\n\t"
@@ -46,6 +48,7 @@ int hwreg_present( volatile void *regp )
 		: "=&d" (ret), "=&r" (save_sp), "=&r" (save_vbr)
 		: "a" (regp), "a" (tmp_vectors)
                 );
+    local_irq_restore(flags);
 
     return( ret );
 }
@@ -58,9 +61,11 @@ EXPORT_SYMBOL(hwreg_present);
 int hwreg_write( volatile void *regp, unsigned short val )
 {
 	int		ret;
+	unsigned long flags;
 	long	save_sp, save_vbr;
 	long	tmp_vectors[3];
 
+	local_irq_save(flags);
 	__asm__ __volatile__
 	(	"movec	%/vbr,%2\n\t"
 		"movel	#Lberr2,%4@(8)\n\t"
@@ -78,6 +83,7 @@ int hwreg_write( volatile void *regp, unsigned short val )
 		: "=&d" (ret), "=&r" (save_sp), "=&r" (save_vbr)
 		: "a" (regp), "a" (tmp_vectors), "g" (val)
 	);
+	local_irq_restore(flags);
 
 	return( ret );
 }
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 4642d6a4d356..de1ec54a2a57 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -329,16 +329,16 @@ struct direct_window {
 
 /* Dynamic DMA Window support */
 struct ddw_query_response {
-	__be32 windows_available;
-	__be32 largest_available_block;
-	__be32 page_size;
-	__be32 migration_capable;
+	u32 windows_available;
+	u32 largest_available_block;
+	u32 page_size;
+	u32 migration_capable;
 };
 
 struct ddw_create_response {
-	__be32 liobn;
-	__be32 addr_hi;
-	__be32 addr_lo;
+	u32 liobn;
+	u32 addr_hi;
+	u32 addr_lo;
 };
 
 static LIST_HEAD(direct_window_list);
@@ -725,16 +725,18 @@ static void remove_ddw(struct device_node *np, bool remove_prop)
 {
 	struct dynamic_dma_window_prop *dwp;
 	struct property *win64;
-	const u32 *ddw_avail;
+	u32 ddw_avail[3];
 	u64 liobn;
-	int len, ret = 0;
+	int ret = 0;
+
+	ret = of_property_read_u32_array(np, "ibm,ddw-applicable",
+					 &ddw_avail[0], 3);
 
-	ddw_avail = of_get_property(np, "ibm,ddw-applicable", &len);
 	win64 = of_find_property(np, DIRECT64_PROPNAME, NULL);
 	if (!win64)
 		return;
 
-	if (!ddw_avail || len < 3 * sizeof(u32) || win64->length < sizeof(*dwp))
+	if (ret || win64->length < sizeof(*dwp))
 		goto delprop;
 
 	dwp = win64->value;
@@ -872,8 +874,9 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail,
 
 	do {
 		/* extra outputs are LIOBN and dma-addr (hi, lo) */
-		ret = rtas_call(ddw_avail[1], 5, 4, (u32 *)create, cfg_addr,
-				BUID_HI(buid), BUID_LO(buid), page_shift, window_shift);
+		ret = rtas_call(ddw_avail[1], 5, 4, (u32 *)create,
+				cfg_addr, BUID_HI(buid), BUID_LO(buid),
+				page_shift, window_shift);
 	} while (rtas_busy_delay(ret));
 	dev_info(&dev->dev,
 		"ibm,create-pe-dma-window(%x) %x %x %x %x %x returned %d "
@@ -910,7 +913,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	int page_shift;
 	u64 dma_addr, max_addr;
 	struct device_node *dn;
-	const u32 *uninitialized_var(ddw_avail);
+	u32 ddw_avail[3];
 	struct direct_window *window;
 	struct property *win64;
 	struct dynamic_dma_window_prop *ddwprop;
@@ -942,8 +945,9 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	 * for the given node in that order.
 	 * the property is actually in the parent, not the PE
 	 */
-	ddw_avail = of_get_property(pdn, "ibm,ddw-applicable", &len);
-	if (!ddw_avail || len < 3 * sizeof(u32))
+	ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable",
+					 &ddw_avail[0], 3);
+	if (ret)
 		goto out_failed;
 
        /*
@@ -966,11 +970,11 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 		dev_dbg(&dev->dev, "no free dynamic windows");
 		goto out_failed;
 	}
-	if (be32_to_cpu(query.page_size) & 4) {
+	if (query.page_size & 4) {
 		page_shift = 24; /* 16MB */
-	} else if (be32_to_cpu(query.page_size) & 2) {
+	} else if (query.page_size & 2) {
 		page_shift = 16; /* 64kB */
-	} else if (be32_to_cpu(query.page_size) & 1) {
+	} else if (query.page_size & 1) {
 		page_shift = 12; /* 4kB */
 	} else {
 		dev_dbg(&dev->dev, "no supported direct page size in mask %x",
@@ -980,7 +984,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	/* verify the window * number of ptes will map the partition */
 	/* check largest block * page size > max memory hotplug addr */
 	max_addr = memory_hotplug_max();
-	if (be32_to_cpu(query.largest_available_block) < (max_addr >> page_shift)) {
+	if (query.largest_available_block < (max_addr >> page_shift)) {
 		dev_dbg(&dev->dev, "can't map partiton max 0x%llx with %u "
 			  "%llu-sized pages\n", max_addr,  query.largest_available_block,
 			  1ULL << page_shift);
@@ -1006,8 +1010,9 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	if (ret != 0)
 		goto out_free_prop;
 
-	ddwprop->liobn = create.liobn;
-	ddwprop->dma_base = cpu_to_be64(of_read_number(&create.addr_hi, 2));
+	ddwprop->liobn = cpu_to_be32(create.liobn);
+	ddwprop->dma_base = cpu_to_be64(((u64)create.addr_hi << 32) |
+			create.addr_lo);
 	ddwprop->tce_shift = cpu_to_be32(page_shift);
 	ddwprop->window_shift = cpu_to_be32(len);
 
@@ -1039,7 +1044,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	list_add(&window->list, &direct_window_list);
 	spin_unlock(&direct_window_list_lock);
 
-	dma_addr = of_read_number(&create.addr_hi, 2);
+	dma_addr = be64_to_cpu(ddwprop->dma_base);
 	goto out_unlock;
 
 out_free_window:
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 5f79d2d79ca7..f1ba119878ec 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -71,6 +71,7 @@ static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
 			return 0;
 		if (vcpu->arch.sie_block->gcr[0] & 0x2000ul)
 			return 1;
+		return 0;
 	case KVM_S390_INT_EMERGENCY:
 		if (psw_extint_disabled(vcpu))
 			return 0;
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index b398c68b2713..a38513c33a62 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -67,6 +67,7 @@ config SPARC64
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_DEBUG_KMEMLEAK
+	select SPARSE_IRQ
 	select RTC_DRV_CMOS
 	select RTC_DRV_BQ4802
 	select RTC_DRV_SUN4V
diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h
index ca121f0fa3ec..17be9d618335 100644
--- a/arch/sparc/include/asm/hypervisor.h
+++ b/arch/sparc/include/asm/hypervisor.h
@@ -2944,6 +2944,16 @@ extern unsigned long sun4v_vt_set_perfreg(unsigned long reg_num,
 					  unsigned long reg_val);
 #endif
 
+#define	HV_FAST_T5_GET_PERFREG		0x1a8
+#define	HV_FAST_T5_SET_PERFREG		0x1a9
+
+#ifndef	__ASSEMBLY__
+unsigned long sun4v_t5_get_perfreg(unsigned long reg_num,
+				   unsigned long *reg_val);
+unsigned long sun4v_t5_set_perfreg(unsigned long reg_num,
+				   unsigned long reg_val);
+#endif
+
 /* Function numbers for HV_CORE_TRAP.  */
 #define HV_CORE_SET_VER			0x00
 #define HV_CORE_PUTCHAR			0x01
@@ -2975,6 +2985,7 @@ extern unsigned long sun4v_vt_set_perfreg(unsigned long reg_num,
 #define HV_GRP_VF_CPU			0x0205
 #define HV_GRP_KT_CPU			0x0209
 #define HV_GRP_VT_CPU			0x020c
+#define HV_GRP_T5_CPU			0x0211
 #define HV_GRP_DIAG			0x0300
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/include/asm/irq_64.h b/arch/sparc/include/asm/irq_64.h
index abf6afe82ca8..3deb07ff1e00 100644
--- a/arch/sparc/include/asm/irq_64.h
+++ b/arch/sparc/include/asm/irq_64.h
@@ -37,7 +37,7 @@
  *
  * ino_bucket->irq allocation is made during {sun4v_,}build_irq().
  */
-#define NR_IRQS    255
+#define NR_IRQS		(2048)
 
 extern void irq_install_pre_handler(int irq,
 				    void (*func)(unsigned int, void *, void *),
@@ -57,11 +57,8 @@ extern unsigned int sun4u_build_msi(u32 portid, unsigned int *irq_p,
 				    unsigned long iclr_base);
 extern void sun4u_destroy_msi(unsigned int irq);
 
-extern unsigned char irq_alloc(unsigned int dev_handle,
-				    unsigned int dev_ino);
-#ifdef CONFIG_PCI_MSI
-extern void irq_free(unsigned int irq);
-#endif
+unsigned int irq_alloc(unsigned int dev_handle, unsigned int dev_ino);
+void irq_free(unsigned int irq);
 
 extern void __init init_IRQ(void);
 extern void fixup_irqs(void);
diff --git a/arch/sparc/include/asm/ldc.h b/arch/sparc/include/asm/ldc.h
index bdb524a7b814..8732ed391aff 100644
--- a/arch/sparc/include/asm/ldc.h
+++ b/arch/sparc/include/asm/ldc.h
@@ -53,13 +53,14 @@ struct ldc_channel;
 /* Allocate state for a channel.  */
 extern struct ldc_channel *ldc_alloc(unsigned long id,
 				     const struct ldc_channel_config *cfgp,
-				     void *event_arg);
+				     void *event_arg,
+				     const char *name);
 
 /* Shut down and free state for a channel.  */
 extern void ldc_free(struct ldc_channel *lp);
 
 /* Register TX and RX queues of the link with the hypervisor.  */
-extern int ldc_bind(struct ldc_channel *lp, const char *name);
+extern int ldc_bind(struct ldc_channel *lp);
 
 /* For non-RAW protocols we need to complete a handshake before
  * communication can proceed.  ldc_connect() does that, if the
diff --git a/arch/sparc/include/asm/oplib_64.h b/arch/sparc/include/asm/oplib_64.h
index a12dbe3b7762..e48fdf4e16ff 100644
--- a/arch/sparc/include/asm/oplib_64.h
+++ b/arch/sparc/include/asm/oplib_64.h
@@ -62,7 +62,8 @@ struct linux_mem_p1275 {
 /* You must call prom_init() before using any of the library services,
  * preferably as early as possible.  Pass it the romvec pointer.
  */
-extern void prom_init(void *cif_handler, void *cif_stack);
+extern void prom_init(void *cif_handler);
+extern void prom_init_report(void);
 
 /* Boot argument acquisition, returns the boot command line string. */
 extern char *prom_getbootargs(void);
diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h
index aac53fcea807..b18e602fcac4 100644
--- a/arch/sparc/include/asm/page_64.h
+++ b/arch/sparc/include/asm/page_64.h
@@ -57,18 +57,21 @@ extern void copy_user_page(void *to, void *from, unsigned long vaddr, struct pag
 typedef struct { unsigned long pte; } pte_t;
 typedef struct { unsigned long iopte; } iopte_t;
 typedef struct { unsigned long pmd; } pmd_t;
+typedef struct { unsigned long pud; } pud_t;
 typedef struct { unsigned long pgd; } pgd_t;
 typedef struct { unsigned long pgprot; } pgprot_t;
 
 #define pte_val(x)	((x).pte)
 #define iopte_val(x)	((x).iopte)
 #define pmd_val(x)      ((x).pmd)
+#define pud_val(x)      ((x).pud)
 #define pgd_val(x)	((x).pgd)
 #define pgprot_val(x)	((x).pgprot)
 
 #define __pte(x)	((pte_t) { (x) } )
 #define __iopte(x)	((iopte_t) { (x) } )
 #define __pmd(x)        ((pmd_t) { (x) } )
+#define __pud(x)        ((pud_t) { (x) } )
 #define __pgd(x)	((pgd_t) { (x) } )
 #define __pgprot(x)	((pgprot_t) { (x) } )
 
@@ -77,18 +80,21 @@ typedef struct { unsigned long pgprot; } pgprot_t;
 typedef unsigned long pte_t;
 typedef unsigned long iopte_t;
 typedef unsigned long pmd_t;
+typedef unsigned long pud_t;
 typedef unsigned long pgd_t;
 typedef unsigned long pgprot_t;
 
 #define pte_val(x)	(x)
 #define iopte_val(x)	(x)
 #define pmd_val(x)      (x)
+#define pud_val(x)      (x)
 #define pgd_val(x)	(x)
 #define pgprot_val(x)	(x)
 
 #define __pte(x)	(x)
 #define __iopte(x)	(x)
 #define __pmd(x)        (x)
+#define __pud(x)        (x)
 #define __pgd(x)	(x)
 #define __pgprot(x)	(x)
 
@@ -96,21 +102,14 @@ typedef unsigned long pgprot_t;
 
 typedef pte_t *pgtable_t;
 
-/* These two values define the virtual address space range in which we
- * must forbid 64-bit user processes from making mappings.  It used to
- * represent precisely the virtual address space hole present in most
- * early sparc64 chips including UltraSPARC-I.  But now it also is
- * further constrained by the limits of our page tables, which is
- * 43-bits of virtual address.
- */
-#define SPARC64_VA_HOLE_TOP	_AC(0xfffffc0000000000,UL)
-#define SPARC64_VA_HOLE_BOTTOM	_AC(0x0000040000000000,UL)
+extern unsigned long sparc64_va_hole_top;
+extern unsigned long sparc64_va_hole_bottom;
 
 /* The next two defines specify the actual exclusion region we
  * enforce, wherein we use a 4GB red zone on each side of the VA hole.
  */
-#define VA_EXCLUDE_START (SPARC64_VA_HOLE_BOTTOM - (1UL << 32UL))
-#define VA_EXCLUDE_END   (SPARC64_VA_HOLE_TOP + (1UL << 32UL))
+#define VA_EXCLUDE_START (sparc64_va_hole_bottom - (1UL << 32UL))
+#define VA_EXCLUDE_END   (sparc64_va_hole_top + (1UL << 32UL))
 
 #define TASK_UNMAPPED_BASE	(test_thread_flag(TIF_32BIT) ? \
 				 _AC(0x0000000070000000,UL) : \
@@ -118,20 +117,16 @@ typedef pte_t *pgtable_t;
 
 #include <asm-generic/memory_model.h>
 
-#define PAGE_OFFSET_BY_BITS(X)	(-(_AC(1,UL) << (X)))
 extern unsigned long PAGE_OFFSET;
 
 #endif /* !(__ASSEMBLY__) */
 
-/* The maximum number of physical memory address bits we support, this
- * is used to size various tables used to manage kernel TLB misses and
- * also the sparsemem code.
+/* The maximum number of physical memory address bits we support.  The
+ * largest value we can support is whatever "KPGD_SHIFT + KPTE_BITS"
+ * evaluates to.
  */
-#define MAX_PHYS_ADDRESS_BITS	47
+#define MAX_PHYS_ADDRESS_BITS	53
 
-/* These two shift counts are used when indexing sparc64_valid_addr_bitmap
- * and kpte_linear_bitmap.
- */
 #define ILOG2_4MB		22
 #define ILOG2_256MB		28
 
diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h
index bcfe063bce23..2c8d41fb13a4 100644
--- a/arch/sparc/include/asm/pgalloc_64.h
+++ b/arch/sparc/include/asm/pgalloc_64.h
@@ -15,6 +15,13 @@
 
 extern struct kmem_cache *pgtable_cache;
 
+static inline void __pgd_populate(pgd_t *pgd, pud_t *pud)
+{
+	pgd_set(pgd, pud);
+}
+
+#define pgd_populate(MM, PGD, PUD)	__pgd_populate(PGD, PUD)
+
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	return kmem_cache_alloc(pgtable_cache, GFP_KERNEL);
@@ -25,7 +32,23 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 	kmem_cache_free(pgtable_cache, pgd);
 }
 
-#define pud_populate(MM, PUD, PMD)	pud_set(PUD, PMD)
+static inline void __pud_populate(pud_t *pud, pmd_t *pmd)
+{
+	pud_set(pud, pmd);
+}
+
+#define pud_populate(MM, PUD, PMD)	__pud_populate(PUD, PMD)
+
+static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	return kmem_cache_alloc(pgtable_cache,
+				GFP_KERNEL|__GFP_REPEAT);
+}
+
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	kmem_cache_free(pgtable_cache, pud);
+}
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
@@ -91,4 +114,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pte_t *pte,
 #define __pmd_free_tlb(tlb, pmd, addr)		      \
 	pgtable_free_tlb(tlb, pmd, false)
 
+#define __pud_free_tlb(tlb, pud, addr)		      \
+	pgtable_free_tlb(tlb, pud, false)
+
 #endif /* _SPARC64_PGALLOC_H */
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 1a49ffdf9da9..e8dfabf156c7 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -20,8 +20,6 @@
 #include <asm/page.h>
 #include <asm/processor.h>
 
-#include <asm-generic/pgtable-nopud.h>
-
 /* The kernel image occupies 0x4000000 to 0x6000000 (4MB --> 96MB).
  * The page copy blockops can use 0x6000000 to 0x8000000.
  * The 8K TSB is mapped in the 0x8000000 to 0x8400000 range.
@@ -42,10 +40,7 @@
 #define LOW_OBP_ADDRESS		_AC(0x00000000f0000000,UL)
 #define HI_OBP_ADDRESS		_AC(0x0000000100000000,UL)
 #define VMALLOC_START		_AC(0x0000000100000000,UL)
-#define VMALLOC_END		_AC(0x0000010000000000,UL)
-#define VMEMMAP_BASE		_AC(0x0000010000000000,UL)
-
-#define vmemmap			((struct page *)VMEMMAP_BASE)
+#define VMEMMAP_BASE		VMALLOC_END
 
 /* PMD_SHIFT determines the size of the area a second-level page
  * table can map
@@ -55,13 +50,25 @@
 #define PMD_MASK	(~(PMD_SIZE-1))
 #define PMD_BITS	(PAGE_SHIFT - 3)
 
-/* PGDIR_SHIFT determines what a third-level page table entry can map */
-#define PGDIR_SHIFT	(PAGE_SHIFT + (PAGE_SHIFT-3) + PMD_BITS)
+/* PUD_SHIFT determines the size of the area a third-level page
+ * table can map
+ */
+#define PUD_SHIFT	(PMD_SHIFT + PMD_BITS)
+#define PUD_SIZE	(_AC(1,UL) << PUD_SHIFT)
+#define PUD_MASK	(~(PUD_SIZE-1))
+#define PUD_BITS	(PAGE_SHIFT - 3)
+
+/* PGDIR_SHIFT determines what a fourth-level page table entry can map */
+#define PGDIR_SHIFT	(PUD_SHIFT + PUD_BITS)
 #define PGDIR_SIZE	(_AC(1,UL) << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 #define PGDIR_BITS	(PAGE_SHIFT - 3)
 
-#if (PGDIR_SHIFT + PGDIR_BITS) != 43
+#if (MAX_PHYS_ADDRESS_BITS > PGDIR_SHIFT + PGDIR_BITS)
+#error MAX_PHYS_ADDRESS_BITS exceeds what kernel page tables can support
+#endif
+
+#if (PGDIR_SHIFT + PGDIR_BITS) != 53
 #error Page table parameters do not cover virtual address space properly.
 #endif
 
@@ -71,28 +78,18 @@
 
 #ifndef __ASSEMBLY__
 
-#include <linux/sched.h>
-
-extern unsigned long sparc64_valid_addr_bitmap[];
+extern unsigned long VMALLOC_END;
 
-/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
-static inline bool __kern_addr_valid(unsigned long paddr)
-{
-	if ((paddr >> MAX_PHYS_ADDRESS_BITS) != 0UL)
-		return false;
-	return test_bit(paddr >> ILOG2_4MB, sparc64_valid_addr_bitmap);
-}
+#define vmemmap			((struct page *)VMEMMAP_BASE)
 
-static inline bool kern_addr_valid(unsigned long addr)
-{
-	unsigned long paddr = __pa(addr);
+#include <linux/sched.h>
 
-	return __kern_addr_valid(paddr);
-}
+bool kern_addr_valid(unsigned long addr);
 
 /* Entries per page directory level. */
 #define PTRS_PER_PTE	(1UL << (PAGE_SHIFT-3))
 #define PTRS_PER_PMD	(1UL << PMD_BITS)
+#define PTRS_PER_PUD	(1UL << PUD_BITS)
 #define PTRS_PER_PGD	(1UL << PGDIR_BITS)
 
 /* Kernel has a separate 44bit address space. */
@@ -101,6 +98,9 @@ static inline bool kern_addr_valid(unsigned long addr)
 #define pmd_ERROR(e)							\
 	pr_err("%s:%d: bad pmd %p(%016lx) seen at (%pS)\n",		\
 	       __FILE__, __LINE__, &(e), pmd_val(e), __builtin_return_address(0))
+#define pud_ERROR(e)							\
+	pr_err("%s:%d: bad pud %p(%016lx) seen at (%pS)\n",		\
+	       __FILE__, __LINE__, &(e), pud_val(e), __builtin_return_address(0))
 #define pgd_ERROR(e)							\
 	pr_err("%s:%d: bad pgd %p(%016lx) seen at (%pS)\n",		\
 	       __FILE__, __LINE__, &(e), pgd_val(e), __builtin_return_address(0))
@@ -112,6 +112,7 @@ static inline bool kern_addr_valid(unsigned long addr)
 #define _PAGE_R	  	  _AC(0x8000000000000000,UL) /* Keep ref bit uptodate*/
 #define _PAGE_SPECIAL     _AC(0x0200000000000000,UL) /* Special page         */
 #define _PAGE_PMD_HUGE    _AC(0x0100000000000000,UL) /* Huge page            */
+#define _PAGE_PUD_HUGE    _PAGE_PMD_HUGE
 
 /* Advertise support for _PAGE_SPECIAL */
 #define __HAVE_ARCH_PTE_SPECIAL
@@ -658,26 +659,26 @@ static inline unsigned long pmd_large(pmd_t pmd)
 	return pte_val(pte) & _PAGE_PMD_HUGE;
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline unsigned long pmd_young(pmd_t pmd)
+static inline unsigned long pmd_pfn(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_young(pte);
+	return pte_pfn(pte);
 }
 
-static inline unsigned long pmd_write(pmd_t pmd)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline unsigned long pmd_young(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_write(pte);
+	return pte_young(pte);
 }
 
-static inline unsigned long pmd_pfn(pmd_t pmd)
+static inline unsigned long pmd_write(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_pfn(pte);
+	return pte_write(pte);
 }
 
 static inline unsigned long pmd_trans_huge(pmd_t pmd)
@@ -771,13 +772,15 @@ static inline int pmd_present(pmd_t pmd)
  * the top bits outside of the range of any physical address size we
  * support are clear as well.  We also validate the physical itself.
  */
-#define pmd_bad(pmd)			((pmd_val(pmd) & ~PAGE_MASK) || \
-					 !__kern_addr_valid(pmd_val(pmd)))
+#define pmd_bad(pmd)			(pmd_val(pmd) & ~PAGE_MASK)
 
 #define pud_none(pud)			(!pud_val(pud))
 
-#define pud_bad(pud)			((pud_val(pud) & ~PAGE_MASK) || \
-					 !__kern_addr_valid(pud_val(pud)))
+#define pud_bad(pud)			(pud_val(pud) & ~PAGE_MASK)
+
+#define pgd_none(pgd)			(!pgd_val(pgd))
+
+#define pgd_bad(pgd)			(pgd_val(pgd) & ~PAGE_MASK)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
@@ -815,10 +818,31 @@ static inline unsigned long __pmd_page(pmd_t pmd)
 #define pmd_clear(pmdp)			(pmd_val(*(pmdp)) = 0UL)
 #define pud_present(pud)		(pud_val(pud) != 0U)
 #define pud_clear(pudp)			(pud_val(*(pudp)) = 0UL)
+#define pgd_page_vaddr(pgd)		\
+	((unsigned long) __va(pgd_val(pgd)))
+#define pgd_present(pgd)		(pgd_val(pgd) != 0U)
+#define pgd_clear(pgdp)			(pgd_val(*(pgd)) = 0UL)
+
+static inline unsigned long pud_large(pud_t pud)
+{
+	pte_t pte = __pte(pud_val(pud));
+
+	return pte_val(pte) & _PAGE_PMD_HUGE;
+}
+
+static inline unsigned long pud_pfn(pud_t pud)
+{
+	pte_t pte = __pte(pud_val(pud));
+
+	return pte_pfn(pte);
+}
 
 /* Same in both SUN4V and SUN4U.  */
 #define pte_none(pte) 			(!pte_val(pte))
 
+#define pgd_set(pgdp, pudp)	\
+	(pgd_val(*(pgdp)) = (__pa((unsigned long) (pudp))))
+
 /* to find an entry in a page-table-directory. */
 #define pgd_index(address)	(((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
 #define pgd_offset(mm, address)	((mm)->pgd + pgd_index(address))
@@ -826,6 +850,11 @@ static inline unsigned long __pmd_page(pmd_t pmd)
 /* to find an entry in a kernel page-table-directory */
 #define pgd_offset_k(address) pgd_offset(&init_mm, address)
 
+/* Find an entry in the third-level page table.. */
+#define pud_index(address)	(((address) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
+#define pud_offset(pgdp, address)	\
+	((pud_t *) pgd_page_vaddr(*(pgdp)) + pud_index(address))
+
 /* Find an entry in the second-level page table.. */
 #define pmd_offset(pudp, address)	\
 	((pmd_t *) pud_page_vaddr(*(pudp)) + \
@@ -898,7 +927,6 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 #endif
 
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
-extern pmd_t swapper_low_pmd_dir[PTRS_PER_PMD];
 
 extern void paging_init(void);
 extern unsigned long find_ecache_flush_span(unsigned long size);
diff --git a/arch/sparc/include/asm/setup.h b/arch/sparc/include/asm/setup.h
index 5e35e0517318..acd614668ec1 100644
--- a/arch/sparc/include/asm/setup.h
+++ b/arch/sparc/include/asm/setup.h
@@ -24,6 +24,10 @@ static inline int con_is_present(void)
 }
 #endif
 
+#ifdef CONFIG_SPARC64
+extern void __init start_early_boot(void);
+#endif
+
 extern void sun_do_break(void);
 extern int stop_a_enabled;
 extern int scons_pwroff;
diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h
index 6b67e50fb9b4..69424d48cbb7 100644
--- a/arch/sparc/include/asm/spitfire.h
+++ b/arch/sparc/include/asm/spitfire.h
@@ -45,6 +45,8 @@
 #define SUN4V_CHIP_NIAGARA3	0x03
 #define SUN4V_CHIP_NIAGARA4	0x04
 #define SUN4V_CHIP_NIAGARA5	0x05
+#define SUN4V_CHIP_SPARC_M6	0x06
+#define SUN4V_CHIP_SPARC_M7	0x07
 #define SUN4V_CHIP_SPARC64X	0x8a
 #define SUN4V_CHIP_UNKNOWN	0xff
 
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index a5f01ac6d0f1..cc6275c931a5 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -63,7 +63,8 @@ struct thread_info {
 	struct pt_regs		*kern_una_regs;
 	unsigned int		kern_una_insn;
 
-	unsigned long		fpregs[0] __attribute__ ((aligned(64)));
+	unsigned long		fpregs[(7 * 256) / sizeof(unsigned long)]
+		__attribute__ ((aligned(64)));
 };
 
 #endif /* !(__ASSEMBLY__) */
@@ -102,6 +103,7 @@ struct thread_info {
 #define FAULT_CODE_ITLB		0x04	/* Miss happened in I-TLB	   */
 #define FAULT_CODE_WINFIXUP	0x08	/* Miss happened during spill/fill */
 #define FAULT_CODE_BLKCOMMIT	0x10	/* Use blk-commit ASI in copy_page */
+#define	FAULT_CODE_BAD_RA	0x20	/* Bad RA for sun4v		   */
 
 #if PAGE_SHIFT == 13
 #define THREAD_SIZE (2*PAGE_SIZE)
diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h
index 90916f955cac..ecb49cfa3be9 100644
--- a/arch/sparc/include/asm/tsb.h
+++ b/arch/sparc/include/asm/tsb.h
@@ -133,9 +133,24 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	sub	TSB, 0x8, TSB;   \
 	TSB_STORE(TSB, TAG);
 
-	/* Do a kernel page table walk.  Leaves physical PTE pointer in
-	 * REG1.  Jumps to FAIL_LABEL on early page table walk termination.
-	 * VADDR will not be clobbered, but REG2 will.
+	/* Do a kernel page table walk.  Leaves valid PTE value in
+	 * REG1.  Jumps to FAIL_LABEL on early page table walk
+	 * termination.  VADDR will not be clobbered, but REG2 will.
+	 *
+	 * There are two masks we must apply to propagate bits from
+	 * the virtual address into the PTE physical address field
+	 * when dealing with huge pages.  This is because the page
+	 * table boundaries do not match the huge page size(s) the
+	 * hardware supports.
+	 *
+	 * In these cases we propagate the bits that are below the
+	 * page table level where we saw the huge page mapping, but
+	 * are still within the relevant physical bits for the huge
+	 * page size in question.  So for PMD mappings (which fall on
+	 * bit 23, for 8MB per PMD) we must propagate bit 22 for a
+	 * 4MB huge page.  For huge PUDs (which fall on bit 33, for
+	 * 8GB per PUD), we have to accomodate 256MB and 2GB huge
+	 * pages.  So for those we propagate bits 32 to 28.
 	 */
 #define KERN_PGTABLE_WALK(VADDR, REG1, REG2, FAIL_LABEL)	\
 	sethi		%hi(swapper_pg_dir), REG1; \
@@ -145,15 +160,40 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	andn		REG2, 0x7, REG2; \
 	ldx		[REG1 + REG2], REG1; \
 	brz,pn		REG1, FAIL_LABEL; \
-	 sllx		VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \
+	 sllx		VADDR, 64 - (PUD_SHIFT + PUD_BITS), REG2; \
 	srlx		REG2, 64 - PAGE_SHIFT, REG2; \
 	andn		REG2, 0x7, REG2; \
 	ldxa		[REG1 + REG2] ASI_PHYS_USE_EC, REG1; \
 	brz,pn		REG1, FAIL_LABEL; \
-	 sllx		VADDR, 64 - PMD_SHIFT, REG2; \
+	sethi		%uhi(_PAGE_PUD_HUGE), REG2; \
+	brz,pn		REG1, FAIL_LABEL; \
+	 sllx		REG2, 32, REG2; \
+	andcc		REG1, REG2, %g0; \
+	sethi		%hi(0xf8000000), REG2; \
+	bne,pt		%xcc, 697f; \
+	 sllx		REG2, 1, REG2; \
+	sllx		VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \
 	srlx		REG2, 64 - PAGE_SHIFT, REG2; \
 	andn		REG2, 0x7, REG2; \
-	add		REG1, REG2, REG1;
+	ldxa		[REG1 + REG2] ASI_PHYS_USE_EC, REG1; \
+	sethi		%uhi(_PAGE_PMD_HUGE), REG2; \
+	brz,pn		REG1, FAIL_LABEL; \
+	 sllx		REG2, 32, REG2; \
+	andcc		REG1, REG2, %g0; \
+	be,pn		%xcc, 698f; \
+	 sethi		%hi(0x400000), REG2; \
+697:	brgez,pn	REG1, FAIL_LABEL; \
+	 andn		REG1, REG2, REG1; \
+	and		VADDR, REG2, REG2; \
+	ba,pt		%xcc, 699f; \
+	 or		REG1, REG2, REG1; \
+698:	sllx		VADDR, 64 - PMD_SHIFT, REG2; \
+	srlx		REG2, 64 - PAGE_SHIFT, REG2; \
+	andn		REG2, 0x7, REG2; \
+	ldxa		[REG1 + REG2] ASI_PHYS_USE_EC, REG1; \
+	brgez,pn	REG1, FAIL_LABEL; \
+	 nop; \
+699:
 
 	/* PMD has been loaded into REG1, interpret the value, seeing
 	 * if it is a HUGE PMD or a normal one.  If it is not valid
@@ -198,6 +238,11 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	andn		REG2, 0x7, REG2; \
 	ldxa		[PHYS_PGD + REG2] ASI_PHYS_USE_EC, REG1; \
 	brz,pn		REG1, FAIL_LABEL; \
+	 sllx		VADDR, 64 - (PUD_SHIFT + PUD_BITS), REG2; \
+	srlx		REG2, 64 - PAGE_SHIFT, REG2; \
+	andn		REG2, 0x7, REG2; \
+	ldxa		[REG1 + REG2] ASI_PHYS_USE_EC, REG1; \
+	brz,pn		REG1, FAIL_LABEL; \
 	 sllx		VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \
 	srlx		REG2, 64 - PAGE_SHIFT, REG2; \
 	andn		REG2, 0x7, REG2; \
@@ -246,8 +291,6 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	(KERNEL_TSB_SIZE_BYTES / 16)
 #define KERNEL_TSB4M_NENTRIES	4096
 
-#define KTSB_PHYS_SHIFT		15
-
 	/* Do a kernel TSB lookup at tl>0 on VADDR+TAG, branch to OK_LABEL
 	 * on TSB hit.  REG1, REG2, REG3, and REG4 are used as temporaries
 	 * and the found TTE will be left in REG1.  REG3 and REG4 must
@@ -256,17 +299,15 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	 * VADDR and TAG will be preserved and not clobbered by this macro.
 	 */
 #define KERN_TSB_LOOKUP_TL1(VADDR, TAG, REG1, REG2, REG3, REG4, OK_LABEL) \
-661:	sethi		%hi(swapper_tsb), REG1;			\
-	or		REG1, %lo(swapper_tsb), REG1; \
+661:	sethi		%uhi(swapper_tsb), REG1; \
+	sethi		%hi(swapper_tsb), REG2; \
+	or		REG1, %ulo(swapper_tsb), REG1; \
+	or		REG2, %lo(swapper_tsb), REG2; \
 	.section	.swapper_tsb_phys_patch, "ax"; \
 	.word		661b; \
 	.previous; \
-661:	nop; \
-	.section	.tsb_ldquad_phys_patch, "ax"; \
-	.word		661b; \
-	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
-	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
-	.previous; \
+	sllx		REG1, 32, REG1; \
+	or		REG1, REG2, REG1; \
 	srlx		VADDR, PAGE_SHIFT, REG2; \
 	and		REG2, (KERNEL_TSB_NENTRIES - 1), REG2; \
 	sllx		REG2, 4, REG2; \
@@ -281,17 +322,15 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	 * we can make use of that for the index computation.
 	 */
 #define KERN_TSB4M_LOOKUP_TL1(TAG, REG1, REG2, REG3, REG4, OK_LABEL) \
-661:	sethi		%hi(swapper_4m_tsb), REG1;	     \
-	or		REG1, %lo(swapper_4m_tsb), REG1; \
+661:	sethi		%uhi(swapper_4m_tsb), REG1; \
+	sethi		%hi(swapper_4m_tsb), REG2; \
+	or		REG1, %ulo(swapper_4m_tsb), REG1; \
+	or		REG2, %lo(swapper_4m_tsb), REG2; \
 	.section	.swapper_4m_tsb_phys_patch, "ax"; \
 	.word		661b; \
 	.previous; \
-661:	nop; \
-	.section	.tsb_ldquad_phys_patch, "ax"; \
-	.word		661b; \
-	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
-	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
-	.previous; \
+	sllx		REG1, 32, REG1; \
+	or		REG1, REG2, REG1; \
 	and		TAG, (KERNEL_TSB4M_NENTRIES - 1), REG2; \
 	sllx		REG2, 4, REG2; \
 	add		REG1, REG2, REG2; \
diff --git a/arch/sparc/include/asm/visasm.h b/arch/sparc/include/asm/visasm.h
index 39ca301920db..11fdf0ef50bb 100644
--- a/arch/sparc/include/asm/visasm.h
+++ b/arch/sparc/include/asm/visasm.h
@@ -39,6 +39,14 @@
 297:	wr		%o5, FPRS_FEF, %fprs;		\
 298:
 
+#define VISEntryHalfFast(fail_label)			\
+	rd		%fprs, %o5;			\
+	andcc		%o5, FPRS_FEF, %g0;		\
+	be,pt		%icc, 297f;			\
+	 nop;						\
+	ba,a,pt		%xcc, fail_label;		\
+297:	wr		%o5, FPRS_FEF, %fprs;
+
 #define VISExitHalf					\
 	wr		%o5, 0, %fprs;
 
diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c
index 5c5125895db8..52e10defedc4 100644
--- a/arch/sparc/kernel/cpu.c
+++ b/arch/sparc/kernel/cpu.c
@@ -493,6 +493,18 @@ static void __init sun4v_cpu_probe(void)
 		sparc_pmu_type = "niagara5";
 		break;
 
+	case SUN4V_CHIP_SPARC_M6:
+		sparc_cpu_type = "SPARC-M6";
+		sparc_fpu_type = "SPARC-M6 integrated FPU";
+		sparc_pmu_type = "sparc-m6";
+		break;
+
+	case SUN4V_CHIP_SPARC_M7:
+		sparc_cpu_type = "SPARC-M7";
+		sparc_fpu_type = "SPARC-M7 integrated FPU";
+		sparc_pmu_type = "sparc-m7";
+		break;
+
 	case SUN4V_CHIP_SPARC64X:
 		sparc_cpu_type = "SPARC64-X";
 		sparc_fpu_type = "SPARC64-X integrated FPU";
diff --git a/arch/sparc/kernel/cpumap.c b/arch/sparc/kernel/cpumap.c
index de1c844dfabc..e69ec0e3f155 100644
--- a/arch/sparc/kernel/cpumap.c
+++ b/arch/sparc/kernel/cpumap.c
@@ -326,6 +326,8 @@ static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index)
 	case SUN4V_CHIP_NIAGARA3:
 	case SUN4V_CHIP_NIAGARA4:
 	case SUN4V_CHIP_NIAGARA5:
+	case SUN4V_CHIP_SPARC_M6:
+	case SUN4V_CHIP_SPARC_M7:
 	case SUN4V_CHIP_SPARC64X:
 		rover_inc_table = niagara_iterate_method;
 		break;
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index dff60abbea01..f87a55d77094 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -1200,14 +1200,14 @@ static int ds_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	ds_cfg.tx_irq = vdev->tx_irq;
 	ds_cfg.rx_irq = vdev->rx_irq;
 
-	lp = ldc_alloc(vdev->channel_id, &ds_cfg, dp);
+	lp = ldc_alloc(vdev->channel_id, &ds_cfg, dp, "DS");
 	if (IS_ERR(lp)) {
 		err = PTR_ERR(lp);
 		goto out_free_ds_states;
 	}
 	dp->lp = lp;
 
-	err = ldc_bind(lp, "DS");
+	err = ldc_bind(lp);
 	if (err)
 		goto out_free_ldc;
 
diff --git a/arch/sparc/kernel/dtlb_prot.S b/arch/sparc/kernel/dtlb_prot.S
index b2c2c5be281c..d668ca149e64 100644
--- a/arch/sparc/kernel/dtlb_prot.S
+++ b/arch/sparc/kernel/dtlb_prot.S
@@ -24,11 +24,11 @@
 	mov		TLB_TAG_ACCESS, %g4		! For reload of vaddr
 
 /* PROT ** ICACHE line 2: More real fault processing */
+	ldxa		[%g4] ASI_DMMU, %g5		! Put tagaccess in %g5
 	bgu,pn		%xcc, winfix_trampoline		! Yes, perform winfixup
-	 ldxa		[%g4] ASI_DMMU, %g5		! Put tagaccess in %g5
-	ba,pt		%xcc, sparc64_realfault_common	! Nope, normal fault
 	 mov		FAULT_CODE_DTLB | FAULT_CODE_WRITE, %g4
-	nop
+	ba,pt		%xcc, sparc64_realfault_common	! Nope, normal fault
+	 nop
 	nop
 	nop
 	nop
diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h
index 140966fbd303..c88ffb9ee482 100644
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -66,13 +66,10 @@ struct pause_patch_entry {
 extern struct pause_patch_entry __pause_3insn_patch,
 	__pause_3insn_patch_end;
 
-extern void __init per_cpu_patch(void);
 extern void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *,
 				    struct sun4v_1insn_patch_entry *);
 extern void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *,
 				    struct sun4v_2insn_patch_entry *);
-extern void __init sun4v_patch(void);
-extern void __init boot_cpu_id_too_large(int cpu);
 extern unsigned int dcache_parity_tl1_occurred;
 extern unsigned int icache_parity_tl1_occurred;
 
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 452f04fe8da6..3d61fcae7ee3 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -427,6 +427,12 @@ sun4v_chip_type:
 	cmp	%g2, '5'
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_NIAGARA5, %g4
+	cmp	%g2, '6'
+	be,pt	%xcc, 5f
+	 mov	SUN4V_CHIP_SPARC_M6, %g4
+	cmp	%g2, '7'
+	be,pt	%xcc, 5f
+	 mov	SUN4V_CHIP_SPARC_M7, %g4
 	ba,pt	%xcc, 49f
 	 nop
 
@@ -585,6 +591,12 @@ niagara_tlb_fixup:
 	cmp	%g1, SUN4V_CHIP_NIAGARA5
 	be,pt	%xcc, niagara4_patch
 	 nop
+	cmp	%g1, SUN4V_CHIP_SPARC_M6
+	be,pt	%xcc, niagara4_patch
+	 nop
+	cmp	%g1, SUN4V_CHIP_SPARC_M7
+	be,pt	%xcc, niagara4_patch
+	 nop
 
 	call	generic_patch_copyops
 	 nop
@@ -660,14 +672,12 @@ tlb_fixup_done:
 	sethi	%hi(init_thread_union), %g6
 	or	%g6, %lo(init_thread_union), %g6
 	ldx	[%g6 + TI_TASK], %g4
-	mov	%sp, %l6
 
 	wr	%g0, ASI_P, %asi
 	mov	1, %g1
 	sllx	%g1, THREAD_SHIFT, %g1
 	sub	%g1, (STACKFRAME_SZ + STACK_BIAS), %g1
 	add	%g6, %g1, %sp
-	mov	0, %fp
 
 	/* Set per-cpu pointer initially to zero, this makes
 	 * the boot-cpu use the in-kernel-image per-cpu areas
@@ -694,44 +704,14 @@ tlb_fixup_done:
 	 nop
 #endif
 
-	mov	%l6, %o1			! OpenPROM stack
 	call	prom_init
 	 mov	%l7, %o0			! OpenPROM cif handler
 
-	/* Initialize current_thread_info()->cpu as early as possible.
-	 * In order to do that accurately we have to patch up the get_cpuid()
-	 * assembler sequences.  And that, in turn, requires that we know
-	 * if we are on a Starfire box or not.  While we're here, patch up
-	 * the sun4v sequences as well.
+	/* To create a one-register-window buffer between the kernel's
+	 * initial stack and the last stack frame we use from the firmware,
+	 * do the rest of the boot from a C helper function.
 	 */
-	call	check_if_starfire
-	 nop
-	call	per_cpu_patch
-	 nop
-	call	sun4v_patch
-	 nop
-
-#ifdef CONFIG_SMP
-	call	hard_smp_processor_id
-	 nop
-	cmp	%o0, NR_CPUS
-	blu,pt	%xcc, 1f
-	 nop
-	call	boot_cpu_id_too_large
-	 nop
-	/* Not reached... */
-
-1:
-#else
-	mov	0, %o0
-#endif
-	sth	%o0, [%g6 + TI_CPU]
-
-	call	prom_init_report
-	 nop
-
-	/* Off we go.... */
-	call	start_kernel
+	call	start_early_boot
 	 nop
 	/* Not reached... */
 
diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c
index c0a2de0fd624..5c55145bfbf0 100644
--- a/arch/sparc/kernel/hvapi.c
+++ b/arch/sparc/kernel/hvapi.c
@@ -46,6 +46,7 @@ static struct api_info api_table[] = {
 	{ .group = HV_GRP_VF_CPU,				},
 	{ .group = HV_GRP_KT_CPU,				},
 	{ .group = HV_GRP_VT_CPU,				},
+	{ .group = HV_GRP_T5_CPU,				},
 	{ .group = HV_GRP_DIAG,		.flags = FLAG_PRE_API	},
 };
 
diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S
index f3ab509b76a8..caedf8320416 100644
--- a/arch/sparc/kernel/hvcalls.S
+++ b/arch/sparc/kernel/hvcalls.S
@@ -821,3 +821,19 @@ ENTRY(sun4v_vt_set_perfreg)
 	retl
 	 nop
 ENDPROC(sun4v_vt_set_perfreg)
+
+ENTRY(sun4v_t5_get_perfreg)
+	mov	%o1, %o4
+	mov	HV_FAST_T5_GET_PERFREG, %o5
+	ta	HV_FAST_TRAP
+	stx	%o1, [%o4]
+	retl
+	 nop
+ENDPROC(sun4v_t5_get_perfreg)
+
+ENTRY(sun4v_t5_set_perfreg)
+	mov	HV_FAST_T5_SET_PERFREG, %o5
+	ta	HV_FAST_TRAP
+	retl
+	 nop
+ENDPROC(sun4v_t5_set_perfreg)
diff --git a/arch/sparc/kernel/hvtramp.S b/arch/sparc/kernel/hvtramp.S
index b7ddcdd1dea9..cdbfec299f2f 100644
--- a/arch/sparc/kernel/hvtramp.S
+++ b/arch/sparc/kernel/hvtramp.S
@@ -109,7 +109,6 @@ hv_cpu_startup:
 	sllx		%g5, THREAD_SHIFT, %g5
 	sub		%g5, (STACKFRAME_SZ + STACK_BIAS), %g5
 	add		%g6, %g5, %sp
-	mov		0, %fp
 
 	call		init_irqwork_curcpu
 	 nop
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index e7e215dfa866..c2d81ad62e78 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -278,7 +278,8 @@ static void *sbus_alloc_coherent(struct device *dev, size_t len,
 	}
 
 	order = get_order(len_total);
-	if ((va = __get_free_pages(GFP_KERNEL|__GFP_COMP, order)) == 0)
+	va = __get_free_pages(gfp, order);
+	if (va == 0)
 		goto err_nopages;
 
 	if ((res = kzalloc(sizeof(struct resource), GFP_KERNEL)) == NULL)
@@ -443,7 +444,7 @@ static void *pci32_alloc_coherent(struct device *dev, size_t len,
 	}
 
 	order = get_order(len_total);
-	va = (void *) __get_free_pages(GFP_KERNEL, order);
+	va = (void *) __get_free_pages(gfp, order);
 	if (va == NULL) {
 		printk("pci_alloc_consistent: no %ld pages\n", len_total>>PAGE_SHIFT);
 		goto err_nopages;
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index 666193f4e8bb..4033c23bdfa6 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -47,8 +47,6 @@
 #include "cpumap.h"
 #include "kstack.h"
 
-#define NUM_IVECS	(IMAP_INR + 1)
-
 struct ino_bucket *ivector_table;
 unsigned long ivector_table_pa;
 
@@ -107,55 +105,196 @@ static void bucket_set_irq(unsigned long bucket_pa, unsigned int irq)
 
 #define irq_work_pa(__cpu)	&(trap_block[(__cpu)].irq_worklist_pa)
 
-static struct {
-	unsigned int dev_handle;
-	unsigned int dev_ino;
-	unsigned int in_use;
-} irq_table[NR_IRQS];
-static DEFINE_SPINLOCK(irq_alloc_lock);
+static unsigned long hvirq_major __initdata;
+static int __init early_hvirq_major(char *p)
+{
+	int rc = kstrtoul(p, 10, &hvirq_major);
+
+	return rc;
+}
+early_param("hvirq", early_hvirq_major);
+
+static int hv_irq_version;
+
+/* Major version 2.0 of HV_GRP_INTR added support for the VIRQ cookie
+ * based interfaces, but:
+ *
+ * 1) Several OSs, Solaris and Linux included, use them even when only
+ *    negotiating version 1.0 (or failing to negotiate at all).  So the
+ *    hypervisor has a workaround that provides the VIRQ interfaces even
+ *    when only verion 1.0 of the API is in use.
+ *
+ * 2) Second, and more importantly, with major version 2.0 these VIRQ
+ *    interfaces only were actually hooked up for LDC interrupts, even
+ *    though the Hypervisor specification clearly stated:
+ *
+ *	The new interrupt API functions will be available to a guest
+ *	when it negotiates version 2.0 in the interrupt API group 0x2. When
+ *	a guest negotiates version 2.0, all interrupt sources will only
+ *	support using the cookie interface, and any attempt to use the
+ *	version 1.0 interrupt APIs numbered 0xa0 to 0xa6 will result in the
+ *	ENOTSUPPORTED error being returned.
+ *
+ *   with an emphasis on "all interrupt sources".
+ *
+ * To correct this, major version 3.0 was created which does actually
+ * support VIRQs for all interrupt sources (not just LDC devices).  So
+ * if we want to move completely over the cookie based VIRQs we must
+ * negotiate major version 3.0 or later of HV_GRP_INTR.
+ */
+static bool sun4v_cookie_only_virqs(void)
+{
+	if (hv_irq_version >= 3)
+		return true;
+	return false;
+}
 
-unsigned char irq_alloc(unsigned int dev_handle, unsigned int dev_ino)
+static void __init irq_init_hv(void)
 {
-	unsigned long flags;
-	unsigned char ent;
+	unsigned long hv_error, major, minor = 0;
+
+	if (tlb_type != hypervisor)
+		return;
 
-	BUILD_BUG_ON(NR_IRQS >= 256);
+	if (hvirq_major)
+		major = hvirq_major;
+	else
+		major = 3;
 
-	spin_lock_irqsave(&irq_alloc_lock, flags);
+	hv_error = sun4v_hvapi_register(HV_GRP_INTR, major, &minor);
+	if (!hv_error)
+		hv_irq_version = major;
+	else
+		hv_irq_version = 1;
 
-	for (ent = 1; ent < NR_IRQS; ent++) {
-		if (!irq_table[ent].in_use)
+	pr_info("SUN4V: Using IRQ API major %d, cookie only virqs %s\n",
+		hv_irq_version,
+		sun4v_cookie_only_virqs() ? "enabled" : "disabled");
+}
+
+/* This function is for the timer interrupt.*/
+int __init arch_probe_nr_irqs(void)
+{
+	return 1;
+}
+
+#define DEFAULT_NUM_IVECS	(0xfffU)
+static unsigned int nr_ivec = DEFAULT_NUM_IVECS;
+#define NUM_IVECS (nr_ivec)
+
+static unsigned int __init size_nr_ivec(void)
+{
+	if (tlb_type == hypervisor) {
+		switch (sun4v_chip_type) {
+		/* Athena's devhandle|devino is large.*/
+		case SUN4V_CHIP_SPARC64X:
+			nr_ivec = 0xffff;
 			break;
+		}
 	}
-	if (ent >= NR_IRQS) {
-		printk(KERN_ERR "IRQ: Out of virtual IRQs.\n");
-		ent = 0;
-	} else {
-		irq_table[ent].dev_handle = dev_handle;
-		irq_table[ent].dev_ino = dev_ino;
-		irq_table[ent].in_use = 1;
-	}
+	return nr_ivec;
+}
+
+struct irq_handler_data {
+	union {
+		struct {
+			unsigned int dev_handle;
+			unsigned int dev_ino;
+		};
+		unsigned long sysino;
+	};
+	struct ino_bucket bucket;
+	unsigned long	iclr;
+	unsigned long	imap;
+};
+
+static inline unsigned int irq_data_to_handle(struct irq_data *data)
+{
+	struct irq_handler_data *ihd = data->handler_data;
+
+	return ihd->dev_handle;
+}
+
+static inline unsigned int irq_data_to_ino(struct irq_data *data)
+{
+	struct irq_handler_data *ihd = data->handler_data;
 
-	spin_unlock_irqrestore(&irq_alloc_lock, flags);
+	return ihd->dev_ino;
+}
+
+static inline unsigned long irq_data_to_sysino(struct irq_data *data)
+{
+	struct irq_handler_data *ihd = data->handler_data;
 
-	return ent;
+	return ihd->sysino;
 }
 
-#ifdef CONFIG_PCI_MSI
 void irq_free(unsigned int irq)
 {
-	unsigned long flags;
+	void *data = irq_get_handler_data(irq);
 
-	if (irq >= NR_IRQS)
-		return;
+	kfree(data);
+	irq_set_handler_data(irq, NULL);
+	irq_free_descs(irq, 1);
+}
 
-	spin_lock_irqsave(&irq_alloc_lock, flags);
+unsigned int irq_alloc(unsigned int dev_handle, unsigned int dev_ino)
+{
+	int irq;
 
-	irq_table[irq].in_use = 0;
+	irq = __irq_alloc_descs(-1, 1, 1, numa_node_id(), NULL);
+	if (irq <= 0)
+		goto out;
 
-	spin_unlock_irqrestore(&irq_alloc_lock, flags);
+	return irq;
+out:
+	return 0;
+}
+
+static unsigned int cookie_exists(u32 devhandle, unsigned int devino)
+{
+	unsigned long hv_err, cookie;
+	struct ino_bucket *bucket;
+	unsigned int irq = 0U;
+
+	hv_err = sun4v_vintr_get_cookie(devhandle, devino, &cookie);
+	if (hv_err) {
+		pr_err("HV get cookie failed hv_err = %ld\n", hv_err);
+		goto out;
+	}
+
+	if (cookie & ((1UL << 63UL))) {
+		cookie = ~cookie;
+		bucket = (struct ino_bucket *) __va(cookie);
+		irq = bucket->__irq;
+	}
+out:
+	return irq;
+}
+
+static unsigned int sysino_exists(u32 devhandle, unsigned int devino)
+{
+	unsigned long sysino = sun4v_devino_to_sysino(devhandle, devino);
+	struct ino_bucket *bucket;
+	unsigned int irq;
+
+	bucket = &ivector_table[sysino];
+	irq = bucket_get_irq(__pa(bucket));
+
+	return irq;
+}
+
+void ack_bad_irq(unsigned int irq)
+{
+	pr_crit("BAD IRQ ack %d\n", irq);
+}
+
+void irq_install_pre_handler(int irq,
+			     void (*func)(unsigned int, void *, void *),
+			     void *arg1, void *arg2)
+{
+	pr_warn("IRQ pre handler NOT supported.\n");
 }
-#endif
 
 /*
  * /proc/interrupts printing:
@@ -206,15 +345,6 @@ static unsigned int sun4u_compute_tid(unsigned long imap, unsigned long cpuid)
 	return tid;
 }
 
-struct irq_handler_data {
-	unsigned long	iclr;
-	unsigned long	imap;
-
-	void		(*pre_handler)(unsigned int, void *, void *);
-	void		*arg1;
-	void		*arg2;
-};
-
 #ifdef CONFIG_SMP
 static int irq_choose_cpu(unsigned int irq, const struct cpumask *affinity)
 {
@@ -316,8 +446,8 @@ static void sun4u_irq_eoi(struct irq_data *data)
 
 static void sun4v_irq_enable(struct irq_data *data)
 {
-	unsigned int ino = irq_table[data->irq].dev_ino;
 	unsigned long cpuid = irq_choose_cpu(data->irq, data->affinity);
+	unsigned int ino = irq_data_to_sysino(data);
 	int err;
 
 	err = sun4v_intr_settarget(ino, cpuid);
@@ -337,8 +467,8 @@ static void sun4v_irq_enable(struct irq_data *data)
 static int sun4v_set_affinity(struct irq_data *data,
 			       const struct cpumask *mask, bool force)
 {
-	unsigned int ino = irq_table[data->irq].dev_ino;
 	unsigned long cpuid = irq_choose_cpu(data->irq, mask);
+	unsigned int ino = irq_data_to_sysino(data);
 	int err;
 
 	err = sun4v_intr_settarget(ino, cpuid);
@@ -351,7 +481,7 @@ static int sun4v_set_affinity(struct irq_data *data,
 
 static void sun4v_irq_disable(struct irq_data *data)
 {
-	unsigned int ino = irq_table[data->irq].dev_ino;
+	unsigned int ino = irq_data_to_sysino(data);
 	int err;
 
 	err = sun4v_intr_setenabled(ino, HV_INTR_DISABLED);
@@ -362,7 +492,7 @@ static void sun4v_irq_disable(struct irq_data *data)
 
 static void sun4v_irq_eoi(struct irq_data *data)
 {
-	unsigned int ino = irq_table[data->irq].dev_ino;
+	unsigned int ino = irq_data_to_sysino(data);
 	int err;
 
 	err = sun4v_intr_setstate(ino, HV_INTR_STATE_IDLE);
@@ -373,14 +503,13 @@ static void sun4v_irq_eoi(struct irq_data *data)
 
 static void sun4v_virq_enable(struct irq_data *data)
 {
-	unsigned long cpuid, dev_handle, dev_ino;
+	unsigned long dev_handle = irq_data_to_handle(data);
+	unsigned long dev_ino = irq_data_to_ino(data);
+	unsigned long cpuid;
 	int err;
 
 	cpuid = irq_choose_cpu(data->irq, data->affinity);
 
-	dev_handle = irq_table[data->irq].dev_handle;
-	dev_ino = irq_table[data->irq].dev_ino;
-
 	err = sun4v_vintr_set_target(dev_handle, dev_ino, cpuid);
 	if (err != HV_EOK)
 		printk(KERN_ERR "sun4v_vintr_set_target(%lx,%lx,%lu): "
@@ -403,14 +532,13 @@ static void sun4v_virq_enable(struct irq_data *data)
 static int sun4v_virt_set_affinity(struct irq_data *data,
 				    const struct cpumask *mask, bool force)
 {
-	unsigned long cpuid, dev_handle, dev_ino;
+	unsigned long dev_handle = irq_data_to_handle(data);
+	unsigned long dev_ino = irq_data_to_ino(data);
+	unsigned long cpuid;
 	int err;
 
 	cpuid = irq_choose_cpu(data->irq, mask);
 
-	dev_handle = irq_table[data->irq].dev_handle;
-	dev_ino = irq_table[data->irq].dev_ino;
-
 	err = sun4v_vintr_set_target(dev_handle, dev_ino, cpuid);
 	if (err != HV_EOK)
 		printk(KERN_ERR "sun4v_vintr_set_target(%lx,%lx,%lu): "
@@ -422,11 +550,10 @@ static int sun4v_virt_set_affinity(struct irq_data *data,
 
 static void sun4v_virq_disable(struct irq_data *data)
 {
-	unsigned long dev_handle, dev_ino;
+	unsigned long dev_handle = irq_data_to_handle(data);
+	unsigned long dev_ino = irq_data_to_ino(data);
 	int err;
 
-	dev_handle = irq_table[data->irq].dev_handle;
-	dev_ino = irq_table[data->irq].dev_ino;
 
 	err = sun4v_vintr_set_valid(dev_handle, dev_ino,
 				    HV_INTR_DISABLED);
@@ -438,12 +565,10 @@ static void sun4v_virq_disable(struct irq_data *data)
 
 static void sun4v_virq_eoi(struct irq_data *data)
 {
-	unsigned long dev_handle, dev_ino;
+	unsigned long dev_handle = irq_data_to_handle(data);
+	unsigned long dev_ino = irq_data_to_ino(data);
 	int err;
 
-	dev_handle = irq_table[data->irq].dev_handle;
-	dev_ino = irq_table[data->irq].dev_ino;
-
 	err = sun4v_vintr_set_state(dev_handle, dev_ino,
 				    HV_INTR_STATE_IDLE);
 	if (err != HV_EOK)
@@ -479,31 +604,10 @@ static struct irq_chip sun4v_virq = {
 	.flags			= IRQCHIP_EOI_IF_HANDLED,
 };
 
-static void pre_flow_handler(struct irq_data *d)
-{
-	struct irq_handler_data *handler_data = irq_data_get_irq_handler_data(d);
-	unsigned int ino = irq_table[d->irq].dev_ino;
-
-	handler_data->pre_handler(ino, handler_data->arg1, handler_data->arg2);
-}
-
-void irq_install_pre_handler(int irq,
-			     void (*func)(unsigned int, void *, void *),
-			     void *arg1, void *arg2)
-{
-	struct irq_handler_data *handler_data = irq_get_handler_data(irq);
-
-	handler_data->pre_handler = func;
-	handler_data->arg1 = arg1;
-	handler_data->arg2 = arg2;
-
-	__irq_set_preflow_handler(irq, pre_flow_handler);
-}
-
 unsigned int build_irq(int inofixup, unsigned long iclr, unsigned long imap)
 {
-	struct ino_bucket *bucket;
 	struct irq_handler_data *handler_data;
+	struct ino_bucket *bucket;
 	unsigned int irq;
 	int ino;
 
@@ -537,119 +641,166 @@ out:
 	return irq;
 }
 
-static unsigned int sun4v_build_common(unsigned long sysino,
-				       struct irq_chip *chip)
+static unsigned int sun4v_build_common(u32 devhandle, unsigned int devino,
+		void (*handler_data_init)(struct irq_handler_data *data,
+		u32 devhandle, unsigned int devino),
+		struct irq_chip *chip)
 {
-	struct ino_bucket *bucket;
-	struct irq_handler_data *handler_data;
+	struct irq_handler_data *data;
 	unsigned int irq;
 
-	BUG_ON(tlb_type != hypervisor);
+	irq = irq_alloc(devhandle, devino);
+	if (!irq)
+		goto out;
 
-	bucket = &ivector_table[sysino];
-	irq = bucket_get_irq(__pa(bucket));
-	if (!irq) {
-		irq = irq_alloc(0, sysino);
-		bucket_set_irq(__pa(bucket), irq);
-		irq_set_chip_and_handler_name(irq, chip, handle_fasteoi_irq,
-					      "IVEC");
+	data = kzalloc(sizeof(struct irq_handler_data), GFP_ATOMIC);
+	if (unlikely(!data)) {
+		pr_err("IRQ handler data allocation failed.\n");
+		irq_free(irq);
+		irq = 0;
+		goto out;
 	}
 
-	handler_data = irq_get_handler_data(irq);
-	if (unlikely(handler_data))
-		goto out;
+	irq_set_handler_data(irq, data);
+	handler_data_init(data, devhandle, devino);
+	irq_set_chip_and_handler_name(irq, chip, handle_fasteoi_irq, "IVEC");
+	data->imap = ~0UL;
+	data->iclr = ~0UL;
+out:
+	return irq;
+}
 
-	handler_data = kzalloc(sizeof(struct irq_handler_data), GFP_ATOMIC);
-	if (unlikely(!handler_data)) {
-		prom_printf("IRQ: kzalloc(irq_handler_data) failed.\n");
-		prom_halt();
-	}
-	irq_set_handler_data(irq, handler_data);
+static unsigned long cookie_assign(unsigned int irq, u32 devhandle,
+		unsigned int devino)
+{
+	struct irq_handler_data *ihd = irq_get_handler_data(irq);
+	unsigned long hv_error, cookie;
 
-	/* Catch accidental accesses to these things.  IMAP/ICLR handling
-	 * is done by hypervisor calls on sun4v platforms, not by direct
-	 * register accesses.
+	/* handler_irq needs to find the irq. cookie is seen signed in
+	 * sun4v_dev_mondo and treated as a non ivector_table delivery.
 	 */
-	handler_data->imap = ~0UL;
-	handler_data->iclr = ~0UL;
+	ihd->bucket.__irq = irq;
+	cookie = ~__pa(&ihd->bucket);
 
-out:
-	return irq;
+	hv_error = sun4v_vintr_set_cookie(devhandle, devino, cookie);
+	if (hv_error)
+		pr_err("HV vintr set cookie failed = %ld\n", hv_error);
+
+	return hv_error;
 }
 
-unsigned int sun4v_build_irq(u32 devhandle, unsigned int devino)
+static void cookie_handler_data(struct irq_handler_data *data,
+				u32 devhandle, unsigned int devino)
 {
-	unsigned long sysino = sun4v_devino_to_sysino(devhandle, devino);
+	data->dev_handle = devhandle;
+	data->dev_ino = devino;
+}
 
-	return sun4v_build_common(sysino, &sun4v_irq);
+static unsigned int cookie_build_irq(u32 devhandle, unsigned int devino,
+				     struct irq_chip *chip)
+{
+	unsigned long hv_error;
+	unsigned int irq;
+
+	irq = sun4v_build_common(devhandle, devino, cookie_handler_data, chip);
+
+	hv_error = cookie_assign(irq, devhandle, devino);
+	if (hv_error) {
+		irq_free(irq);
+		irq = 0;
+	}
+
+	return irq;
 }
 
-unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino)
+static unsigned int sun4v_build_cookie(u32 devhandle, unsigned int devino)
 {
-	struct irq_handler_data *handler_data;
-	unsigned long hv_err, cookie;
-	struct ino_bucket *bucket;
 	unsigned int irq;
 
-	bucket = kzalloc(sizeof(struct ino_bucket), GFP_ATOMIC);
-	if (unlikely(!bucket))
-		return 0;
+	irq = cookie_exists(devhandle, devino);
+	if (irq)
+		goto out;
 
-	/* The only reference we store to the IRQ bucket is
-	 * by physical address which kmemleak can't see, tell
-	 * it that this object explicitly is not a leak and
-	 * should be scanned.
-	 */
-	kmemleak_not_leak(bucket);
+	irq = cookie_build_irq(devhandle, devino, &sun4v_virq);
 
-	__flush_dcache_range((unsigned long) bucket,
-			     ((unsigned long) bucket +
-			      sizeof(struct ino_bucket)));
+out:
+	return irq;
+}
 
-	irq = irq_alloc(devhandle, devino);
+static void sysino_set_bucket(unsigned int irq)
+{
+	struct irq_handler_data *ihd = irq_get_handler_data(irq);
+	struct ino_bucket *bucket;
+	unsigned long sysino;
+
+	sysino = sun4v_devino_to_sysino(ihd->dev_handle, ihd->dev_ino);
+	BUG_ON(sysino >= nr_ivec);
+	bucket = &ivector_table[sysino];
 	bucket_set_irq(__pa(bucket), irq);
+}
 
-	irq_set_chip_and_handler_name(irq, &sun4v_virq, handle_fasteoi_irq,
-				      "IVEC");
+static void sysino_handler_data(struct irq_handler_data *data,
+				u32 devhandle, unsigned int devino)
+{
+	unsigned long sysino;
 
-	handler_data = kzalloc(sizeof(struct irq_handler_data), GFP_ATOMIC);
-	if (unlikely(!handler_data))
-		return 0;
+	sysino = sun4v_devino_to_sysino(devhandle, devino);
+	data->sysino = sysino;
+}
 
-	/* In order to make the LDC channel startup sequence easier,
-	 * especially wrt. locking, we do not let request_irq() enable
-	 * the interrupt.
-	 */
-	irq_set_status_flags(irq, IRQ_NOAUTOEN);
-	irq_set_handler_data(irq, handler_data);
+static unsigned int sysino_build_irq(u32 devhandle, unsigned int devino,
+				     struct irq_chip *chip)
+{
+	unsigned int irq;
 
-	/* Catch accidental accesses to these things.  IMAP/ICLR handling
-	 * is done by hypervisor calls on sun4v platforms, not by direct
-	 * register accesses.
-	 */
-	handler_data->imap = ~0UL;
-	handler_data->iclr = ~0UL;
+	irq = sun4v_build_common(devhandle, devino, sysino_handler_data, chip);
+	if (!irq)
+		goto out;
 
-	cookie = ~__pa(bucket);
-	hv_err = sun4v_vintr_set_cookie(devhandle, devino, cookie);
-	if (hv_err) {
-		prom_printf("IRQ: Fatal, cannot set cookie for [%x:%x] "
-			    "err=%lu\n", devhandle, devino, hv_err);
-		prom_halt();
-	}
+	sysino_set_bucket(irq);
+out:
+	return irq;
+}
 
+static int sun4v_build_sysino(u32 devhandle, unsigned int devino)
+{
+	int irq;
+
+	irq = sysino_exists(devhandle, devino);
+	if (irq)
+		goto out;
+
+	irq = sysino_build_irq(devhandle, devino, &sun4v_irq);
+out:
 	return irq;
 }
 
-void ack_bad_irq(unsigned int irq)
+unsigned int sun4v_build_irq(u32 devhandle, unsigned int devino)
 {
-	unsigned int ino = irq_table[irq].dev_ino;
+	unsigned int irq;
 
-	if (!ino)
-		ino = 0xdeadbeef;
+	if (sun4v_cookie_only_virqs())
+		irq = sun4v_build_cookie(devhandle, devino);
+	else
+		irq = sun4v_build_sysino(devhandle, devino);
 
-	printk(KERN_CRIT "Unexpected IRQ from ino[%x] irq[%u]\n",
-	       ino, irq);
+	return irq;
+}
+
+unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino)
+{
+	int irq;
+
+	irq = cookie_build_irq(devhandle, devino, &sun4v_virq);
+	if (!irq)
+		goto out;
+
+	/* This is borrowed from the original function.
+	 */
+	irq_set_status_flags(irq, IRQ_NOAUTOEN);
+
+out:
+	return irq;
 }
 
 void *hardirq_stack[NR_CPUS];
@@ -720,9 +871,12 @@ void fixup_irqs(void)
 
 	for (irq = 0; irq < NR_IRQS; irq++) {
 		struct irq_desc *desc = irq_to_desc(irq);
-		struct irq_data *data = irq_desc_get_irq_data(desc);
+		struct irq_data *data;
 		unsigned long flags;
 
+		if (!desc)
+			continue;
+		data = irq_desc_get_irq_data(desc);
 		raw_spin_lock_irqsave(&desc->lock, flags);
 		if (desc->action && !irqd_is_per_cpu(data)) {
 			if (data->chip->irq_set_affinity)
@@ -922,16 +1076,22 @@ static struct irqaction timer_irq_action = {
 	.name = "timer",
 };
 
-/* Only invoked on boot processor. */
-void __init init_IRQ(void)
+static void __init irq_ivector_init(void)
 {
-	unsigned long size;
+	unsigned long size, order;
+	unsigned int ivecs;
 
-	map_prom_timers();
-	kill_prom_timer();
+	/* If we are doing cookie only VIRQs then we do not need the ivector
+	 * table to process interrupts.
+	 */
+	if (sun4v_cookie_only_virqs())
+		return;
 
-	size = sizeof(struct ino_bucket) * NUM_IVECS;
-	ivector_table = kzalloc(size, GFP_KERNEL);
+	ivecs = size_nr_ivec();
+	size = sizeof(struct ino_bucket) * ivecs;
+	order = get_order(size);
+	ivector_table = (struct ino_bucket *)
+		__get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
 	if (!ivector_table) {
 		prom_printf("Fatal error, cannot allocate ivector_table\n");
 		prom_halt();
@@ -940,6 +1100,15 @@ void __init init_IRQ(void)
 			     ((unsigned long) ivector_table) + size);
 
 	ivector_table_pa = __pa(ivector_table);
+}
+
+/* Only invoked on boot processor.*/
+void __init init_IRQ(void)
+{
+	irq_init_hv();
+	irq_ivector_init();
+	map_prom_timers();
+	kill_prom_timer();
 
 	if (tlb_type == hypervisor)
 		sun4v_init_mondo_queues();
diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S
index 605d49204580..ef0d8e9e1210 100644
--- a/arch/sparc/kernel/ktlb.S
+++ b/arch/sparc/kernel/ktlb.S
@@ -47,14 +47,6 @@ kvmap_itlb_vmalloc_addr:
 	KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_itlb_longpath)
 
 	TSB_LOCK_TAG(%g1, %g2, %g7)
-
-	/* Load and check PTE.  */
-	ldxa		[%g5] ASI_PHYS_USE_EC, %g5
-	mov		1, %g7
-	sllx		%g7, TSB_TAG_INVALID_BIT, %g7
-	brgez,a,pn	%g5, kvmap_itlb_longpath
-	 TSB_STORE(%g1, %g7)
-
 	TSB_WRITE(%g1, %g5, %g6)
 
 	/* fallthrough to TLB load */
@@ -118,6 +110,12 @@ kvmap_dtlb_obp:
 	ba,pt		%xcc, kvmap_dtlb_load
 	 nop
 
+kvmap_linear_early:
+	sethi		%hi(kern_linear_pte_xor), %g7
+	ldx		[%g7 + %lo(kern_linear_pte_xor)], %g2
+	ba,pt		%xcc, kvmap_dtlb_tsb4m_load
+	 xor		%g2, %g4, %g5
+
 	.align		32
 kvmap_dtlb_tsb4m_load:
 	TSB_LOCK_TAG(%g1, %g2, %g7)
@@ -146,105 +144,17 @@ kvmap_dtlb_4v:
 	/* Correct TAG_TARGET is already in %g6, check 4mb TSB.  */
 	KERN_TSB4M_LOOKUP_TL1(%g6, %g5, %g1, %g2, %g3, kvmap_dtlb_load)
 #endif
-	/* TSB entry address left in %g1, lookup linear PTE.
-	 * Must preserve %g1 and %g6 (TAG).
-	 */
-kvmap_dtlb_tsb4m_miss:
-	/* Clear the PAGE_OFFSET top virtual bits, shift
-	 * down to get PFN, and make sure PFN is in range.
-	 */
-661:	sllx		%g4, 0, %g5
-	.section	.page_offset_shift_patch, "ax"
-	.word		661b
-	.previous
-
-	/* Check to see if we know about valid memory at the 4MB
-	 * chunk this physical address will reside within.
+	/* Linear mapping TSB lookup failed.  Fallthrough to kernel
+	 * page table based lookup.
 	 */
-661:	srlx		%g5, MAX_PHYS_ADDRESS_BITS, %g2
-	.section	.page_offset_shift_patch, "ax"
-	.word		661b
-	.previous
-
-	brnz,pn		%g2, kvmap_dtlb_longpath
-	 nop
-
-	/* This unconditional branch and delay-slot nop gets patched
-	 * by the sethi sequence once the bitmap is properly setup.
-	 */
-	.globl		valid_addr_bitmap_insn
-valid_addr_bitmap_insn:
-	ba,pt		%xcc, 2f
-	 nop
-	.subsection	2
-	.globl		valid_addr_bitmap_patch
-valid_addr_bitmap_patch:
-	sethi		%hi(sparc64_valid_addr_bitmap), %g7
-	or		%g7, %lo(sparc64_valid_addr_bitmap), %g7
-	.previous
-
-661:	srlx		%g5, ILOG2_4MB, %g2
-	.section	.page_offset_shift_patch, "ax"
-	.word		661b
-	.previous
-
-	srlx		%g2, 6, %g5
-	and		%g2, 63, %g2
-	sllx		%g5, 3, %g5
-	ldx		[%g7 + %g5], %g5
-	mov		1, %g7
-	sllx		%g7, %g2, %g7
-	andcc		%g5, %g7, %g0
-	be,pn		%xcc, kvmap_dtlb_longpath
-
-2:	 sethi		%hi(kpte_linear_bitmap), %g2
-
-	/* Get the 256MB physical address index. */
-661:	sllx		%g4, 0, %g5
-	.section	.page_offset_shift_patch, "ax"
-	.word		661b
-	.previous
-
-	or		%g2, %lo(kpte_linear_bitmap), %g2
-
-661:	srlx		%g5, ILOG2_256MB, %g5
-	.section	.page_offset_shift_patch, "ax"
-	.word		661b
-	.previous
-
-	and		%g5, (32 - 1), %g7
-
-	/* Divide by 32 to get the offset into the bitmask.  */
-	srlx		%g5, 5, %g5
-	add		%g7, %g7, %g7
-	sllx		%g5, 3, %g5
-
-	/* kern_linear_pte_xor[(mask >> shift) & 3)] */
-	ldx		[%g2 + %g5], %g2
-	srlx		%g2, %g7, %g7
-	sethi		%hi(kern_linear_pte_xor), %g5
-	and		%g7, 3, %g7
-	or		%g5, %lo(kern_linear_pte_xor), %g5
-	sllx		%g7, 3, %g7
-	ldx		[%g5 + %g7], %g2
-
 	.globl		kvmap_linear_patch
 kvmap_linear_patch:
-	ba,pt		%xcc, kvmap_dtlb_tsb4m_load
-	 xor		%g2, %g4, %g5
+	ba,a,pt		%xcc, kvmap_linear_early
 
 kvmap_dtlb_vmalloc_addr:
 	KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath)
 
 	TSB_LOCK_TAG(%g1, %g2, %g7)
-
-	/* Load and check PTE.  */
-	ldxa		[%g5] ASI_PHYS_USE_EC, %g5
-	mov		1, %g7
-	sllx		%g7, TSB_TAG_INVALID_BIT, %g7
-	brgez,a,pn	%g5, kvmap_dtlb_longpath
-	 TSB_STORE(%g1, %g7)
-
 	TSB_WRITE(%g1, %g5, %g6)
 
 	/* fallthrough to TLB load */
@@ -276,13 +186,8 @@ kvmap_dtlb_load:
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 kvmap_vmemmap:
-	sub		%g4, %g5, %g5
-	srlx		%g5, ILOG2_4MB, %g5
-	sethi		%hi(vmemmap_table), %g1
-	sllx		%g5, 3, %g5
-	or		%g1, %lo(vmemmap_table), %g1
-	ba,pt		%xcc, kvmap_dtlb_load
-	 ldx		[%g1 + %g5], %g5
+	KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath)
+	ba,a,pt		%xcc, kvmap_dtlb_load
 #endif
 
 kvmap_dtlb_nonlinear:
@@ -294,8 +199,8 @@ kvmap_dtlb_nonlinear:
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 	/* Do not use the TSB for vmemmap.  */
-	mov		(VMEMMAP_BASE >> 40), %g5
-	sllx		%g5, 40, %g5
+	sethi		%hi(VMEMMAP_BASE), %g5
+	ldx		[%g5 + %lo(VMEMMAP_BASE)], %g5
 	cmp		%g4,%g5
 	bgeu,pn		%xcc, kvmap_vmemmap
 	 nop
@@ -307,8 +212,8 @@ kvmap_dtlb_tsbmiss:
 	sethi		%hi(MODULES_VADDR), %g5
 	cmp		%g4, %g5
 	blu,pn		%xcc, kvmap_dtlb_longpath
-	 mov		(VMALLOC_END >> 40), %g5
-	sllx		%g5, 40, %g5
+	 sethi		%hi(VMALLOC_END), %g5
+	ldx		[%g5 + %lo(VMALLOC_END)], %g5
 	cmp		%g4, %g5
 	bgeu,pn		%xcc, kvmap_dtlb_longpath
 	 nop
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index 66dacd56bb10..27bb55485472 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -1078,7 +1078,8 @@ static void ldc_iommu_release(struct ldc_channel *lp)
 
 struct ldc_channel *ldc_alloc(unsigned long id,
 			      const struct ldc_channel_config *cfgp,
-			      void *event_arg)
+			      void *event_arg,
+			      const char *name)
 {
 	struct ldc_channel *lp;
 	const struct ldc_mode_ops *mops;
@@ -1093,6 +1094,8 @@ struct ldc_channel *ldc_alloc(unsigned long id,
 	err = -EINVAL;
 	if (!cfgp)
 		goto out_err;
+	if (!name)
+		goto out_err;
 
 	switch (cfgp->mode) {
 	case LDC_MODE_RAW:
@@ -1185,6 +1188,21 @@ struct ldc_channel *ldc_alloc(unsigned long id,
 
 	INIT_HLIST_HEAD(&lp->mh_list);
 
+	snprintf(lp->rx_irq_name, LDC_IRQ_NAME_MAX, "%s RX", name);
+	snprintf(lp->tx_irq_name, LDC_IRQ_NAME_MAX, "%s TX", name);
+
+	err = request_irq(lp->cfg.rx_irq, ldc_rx, 0,
+			  lp->rx_irq_name, lp);
+	if (err)
+		goto out_free_txq;
+
+	err = request_irq(lp->cfg.tx_irq, ldc_tx, 0,
+			  lp->tx_irq_name, lp);
+	if (err) {
+		free_irq(lp->cfg.rx_irq, lp);
+		goto out_free_txq;
+	}
+
 	return lp;
 
 out_free_txq:
@@ -1237,31 +1255,14 @@ EXPORT_SYMBOL(ldc_free);
  * state.  This does not initiate a handshake, ldc_connect() does
  * that.
  */
-int ldc_bind(struct ldc_channel *lp, const char *name)
+int ldc_bind(struct ldc_channel *lp)
 {
 	unsigned long hv_err, flags;
 	int err = -EINVAL;
 
-	if (!name ||
-	    (lp->state != LDC_STATE_INIT))
+	if (lp->state != LDC_STATE_INIT)
 		return -EINVAL;
 
-	snprintf(lp->rx_irq_name, LDC_IRQ_NAME_MAX, "%s RX", name);
-	snprintf(lp->tx_irq_name, LDC_IRQ_NAME_MAX, "%s TX", name);
-
-	err = request_irq(lp->cfg.rx_irq, ldc_rx, 0,
-			  lp->rx_irq_name, lp);
-	if (err)
-		return err;
-
-	err = request_irq(lp->cfg.tx_irq, ldc_tx, 0,
-			  lp->tx_irq_name, lp);
-	if (err) {
-		free_irq(lp->cfg.rx_irq, lp);
-		return err;
-	}
-
-
 	spin_lock_irqsave(&lp->lock, flags);
 
 	enable_irq(lp->cfg.rx_irq);
diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c
index 6479256fd5a4..fce8ab17bcbb 100644
--- a/arch/sparc/kernel/nmi.c
+++ b/arch/sparc/kernel/nmi.c
@@ -141,7 +141,6 @@ static inline unsigned int get_nmi_count(int cpu)
 
 static __init void nmi_cpu_busy(void *data)
 {
-	local_irq_enable_in_hardirq();
 	while (endflag == 0)
 		mb();
 }
diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c
index 269af58497aa..7e967c8018c8 100644
--- a/arch/sparc/kernel/pcr.c
+++ b/arch/sparc/kernel/pcr.c
@@ -191,12 +191,41 @@ static const struct pcr_ops n4_pcr_ops = {
 	.pcr_nmi_disable	= PCR_N4_PICNPT,
 };
 
+static u64 n5_pcr_read(unsigned long reg_num)
+{
+	unsigned long val;
+
+	(void) sun4v_t5_get_perfreg(reg_num, &val);
+
+	return val;
+}
+
+static void n5_pcr_write(unsigned long reg_num, u64 val)
+{
+	(void) sun4v_t5_set_perfreg(reg_num, val);
+}
+
+static const struct pcr_ops n5_pcr_ops = {
+	.read_pcr		= n5_pcr_read,
+	.write_pcr		= n5_pcr_write,
+	.read_pic		= n4_pic_read,
+	.write_pic		= n4_pic_write,
+	.nmi_picl_value		= n4_picl_value,
+	.pcr_nmi_enable		= (PCR_N4_PICNPT | PCR_N4_STRACE |
+				   PCR_N4_UTRACE | PCR_N4_TOE |
+				   (26 << PCR_N4_SL_SHIFT)),
+	.pcr_nmi_disable	= PCR_N4_PICNPT,
+};
+
+
 static unsigned long perf_hsvc_group;
 static unsigned long perf_hsvc_major;
 static unsigned long perf_hsvc_minor;
 
 static int __init register_perf_hsvc(void)
 {
+	unsigned long hverror;
+
 	if (tlb_type == hypervisor) {
 		switch (sun4v_chip_type) {
 		case SUN4V_CHIP_NIAGARA1:
@@ -215,6 +244,10 @@ static int __init register_perf_hsvc(void)
 			perf_hsvc_group = HV_GRP_VT_CPU;
 			break;
 
+		case SUN4V_CHIP_NIAGARA5:
+			perf_hsvc_group = HV_GRP_T5_CPU;
+			break;
+
 		default:
 			return -ENODEV;
 		}
@@ -222,10 +255,12 @@ static int __init register_perf_hsvc(void)
 
 		perf_hsvc_major = 1;
 		perf_hsvc_minor = 0;
-		if (sun4v_hvapi_register(perf_hsvc_group,
-					 perf_hsvc_major,
-					 &perf_hsvc_minor)) {
-			printk("perfmon: Could not register hvapi.\n");
+		hverror = sun4v_hvapi_register(perf_hsvc_group,
+					       perf_hsvc_major,
+					       &perf_hsvc_minor);
+		if (hverror) {
+			pr_err("perfmon: Could not register hvapi(0x%lx).\n",
+			       hverror);
 			return -ENODEV;
 		}
 	}
@@ -254,6 +289,10 @@ static int __init setup_sun4v_pcr_ops(void)
 		pcr_ops = &n4_pcr_ops;
 		break;
 
+	case SUN4V_CHIP_NIAGARA5:
+		pcr_ops = &n5_pcr_ops;
+		break;
+
 	default:
 		ret = -ENODEV;
 		break;
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index b5c38faa4ead..617b9fe33771 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1662,7 +1662,8 @@ static bool __init supported_pmu(void)
 		sparc_pmu = &niagara2_pmu;
 		return true;
 	}
-	if (!strcmp(sparc_pmu_type, "niagara4")) {
+	if (!strcmp(sparc_pmu_type, "niagara4") ||
+	    !strcmp(sparc_pmu_type, "niagara5")) {
 		sparc_pmu = &niagara4_pmu;
 		return true;
 	}
@@ -1671,9 +1672,12 @@ static bool __init supported_pmu(void)
 
 int __init init_hw_perf_events(void)
 {
+	int err;
+
 	pr_info("Performance events: ");
 
-	if (!supported_pmu()) {
+	err = pcr_arch_init();
+	if (err || !supported_pmu()) {
 		pr_cont("No support for PMU type '%s'\n", sparc_pmu_type);
 		return 0;
 	}
@@ -1685,7 +1689,7 @@ int __init init_hw_perf_events(void)
 
 	return 0;
 }
-early_initcall(init_hw_perf_events);
+pure_initcall(init_hw_perf_events);
 
 void perf_callchain_kernel(struct perf_callchain_entry *entry,
 			   struct pt_regs *regs)
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index d7b4967f8fa6..c6f7113b6e2f 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -306,6 +306,9 @@ static void __global_pmu_self(int this_cpu)
 	struct global_pmu_snapshot *pp;
 	int i, num;
 
+	if (!pcr_ops)
+		return;
+
 	pp = &global_cpu_snapshot[this_cpu].pmu;
 
 	num = 1;
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 3fdb455e3318..61a519808cb7 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -30,6 +30,7 @@
 #include <linux/cpu.h>
 #include <linux/initrd.h>
 #include <linux/module.h>
+#include <linux/start_kernel.h>
 
 #include <asm/io.h>
 #include <asm/processor.h>
@@ -174,7 +175,7 @@ char reboot_command[COMMAND_LINE_SIZE];
 
 static struct pt_regs fake_swapper_regs = { { 0, }, 0, 0, 0, 0 };
 
-void __init per_cpu_patch(void)
+static void __init per_cpu_patch(void)
 {
 	struct cpuid_patch_entry *p;
 	unsigned long ver;
@@ -266,7 +267,7 @@ void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *start,
 	}
 }
 
-void __init sun4v_patch(void)
+static void __init sun4v_patch(void)
 {
 	extern void sun4v_hvapi_init(void);
 
@@ -335,14 +336,25 @@ static void __init pause_patch(void)
 	}
 }
 
-#ifdef CONFIG_SMP
-void __init boot_cpu_id_too_large(int cpu)
+void __init start_early_boot(void)
 {
-	prom_printf("Serious problem, boot cpu id (%d) >= NR_CPUS (%d)\n",
-		    cpu, NR_CPUS);
-	prom_halt();
+	int cpu;
+
+	check_if_starfire();
+	per_cpu_patch();
+	sun4v_patch();
+
+	cpu = hard_smp_processor_id();
+	if (cpu >= NR_CPUS) {
+		prom_printf("Serious problem, boot cpu id (%d) >= NR_CPUS (%d)\n",
+			    cpu, NR_CPUS);
+		prom_halt();
+	}
+	current_thread_info()->cpu = cpu;
+
+	prom_init_report();
+	start_kernel();
 }
-#endif
 
 /* On Ultra, we support all of the v8 capabilities. */
 unsigned long sparc64_elf_hwcap = (HWCAP_SPARC_FLUSH | HWCAP_SPARC_STBAR |
@@ -500,12 +512,16 @@ static void __init init_sparc64_elf_hwcap(void)
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 			cap |= HWCAP_SPARC_BLKINIT;
 		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 			cap |= HWCAP_SPARC_N2;
 	}
@@ -533,6 +549,8 @@ static void __init init_sparc64_elf_hwcap(void)
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 				cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 |
 					AV_SPARC_ASI_BLK_INIT |
@@ -540,6 +558,8 @@ static void __init init_sparc64_elf_hwcap(void)
 			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 				cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC |
 					AV_SPARC_FMAF);
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 8416d7fadcce..50c3dd03be31 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1395,7 +1395,6 @@ void __cpu_die(unsigned int cpu)
 
 void __init smp_cpus_done(unsigned int max_cpus)
 {
-	pcr_arch_init();
 }
 
 void smp_send_reschedule(int cpu)
@@ -1480,6 +1479,13 @@ static void __init pcpu_populate_pte(unsigned long addr)
 	pud_t *pud;
 	pmd_t *pmd;
 
+	if (pgd_none(*pgd)) {
+		pud_t *new;
+
+		new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
+		pgd_populate(&init_mm, pgd, new);
+	}
+
 	pud = pud_offset(pgd, addr);
 	if (pud_none(*pud)) {
 		pmd_t *new;
diff --git a/arch/sparc/kernel/sun4v_tlb_miss.S b/arch/sparc/kernel/sun4v_tlb_miss.S
index e0c09bf85610..6179e19bc9b9 100644
--- a/arch/sparc/kernel/sun4v_tlb_miss.S
+++ b/arch/sparc/kernel/sun4v_tlb_miss.S
@@ -195,6 +195,11 @@ sun4v_tsb_miss_common:
 	 ldx	[%g2 + TRAP_PER_CPU_PGD_PADDR], %g7
 
 sun4v_itlb_error:
+	rdpr	%tl, %g1
+	cmp	%g1, 1
+	ble,pt	%icc, sun4v_bad_ra
+	 or	%g0, FAULT_CODE_BAD_RA | FAULT_CODE_ITLB, %g1
+
 	sethi	%hi(sun4v_err_itlb_vaddr), %g1
 	stx	%g4, [%g1 + %lo(sun4v_err_itlb_vaddr)]
 	sethi	%hi(sun4v_err_itlb_ctx), %g1
@@ -206,15 +211,10 @@ sun4v_itlb_error:
 	sethi	%hi(sun4v_err_itlb_error), %g1
 	stx	%o0, [%g1 + %lo(sun4v_err_itlb_error)]
 
+	sethi	%hi(1f), %g7
 	rdpr	%tl, %g4
-	cmp	%g4, 1
-	ble,pt	%icc, 1f
-	 sethi	%hi(2f), %g7
 	ba,pt	%xcc, etraptl1
-	 or	%g7, %lo(2f), %g7
-
-1:	ba,pt	%xcc, etrap
-2:	 or	%g7, %lo(2b), %g7
+1:	 or	%g7, %lo(1f), %g7
 	mov	%l4, %o1
 	call	sun4v_itlb_error_report
 	 add	%sp, PTREGS_OFF, %o0
@@ -222,6 +222,11 @@ sun4v_itlb_error:
 	/* NOTREACHED */
 
 sun4v_dtlb_error:
+	rdpr	%tl, %g1
+	cmp	%g1, 1
+	ble,pt	%icc, sun4v_bad_ra
+	 or	%g0, FAULT_CODE_BAD_RA | FAULT_CODE_DTLB, %g1
+
 	sethi	%hi(sun4v_err_dtlb_vaddr), %g1
 	stx	%g4, [%g1 + %lo(sun4v_err_dtlb_vaddr)]
 	sethi	%hi(sun4v_err_dtlb_ctx), %g1
@@ -233,21 +238,23 @@ sun4v_dtlb_error:
 	sethi	%hi(sun4v_err_dtlb_error), %g1
 	stx	%o0, [%g1 + %lo(sun4v_err_dtlb_error)]
 
+	sethi	%hi(1f), %g7
 	rdpr	%tl, %g4
-	cmp	%g4, 1
-	ble,pt	%icc, 1f
-	 sethi	%hi(2f), %g7
 	ba,pt	%xcc, etraptl1
-	 or	%g7, %lo(2f), %g7
-
-1:	ba,pt	%xcc, etrap
-2:	 or	%g7, %lo(2b), %g7
+1:	 or	%g7, %lo(1f), %g7
 	mov	%l4, %o1
 	call	sun4v_dtlb_error_report
 	 add	%sp, PTREGS_OFF, %o0
 
 	/* NOTREACHED */
 
+sun4v_bad_ra:
+	or	%g0, %g4, %g5
+	ba,pt	%xcc, sparc64_realfault_common
+	 or	%g1, %g0, %g4
+
+	/* NOTREACHED */
+
 	/* Instruction Access Exception, tl0. */
 sun4v_iacc:
 	ldxa	[%g0] ASI_SCRATCHPAD, %g2
diff --git a/arch/sparc/kernel/trampoline_64.S b/arch/sparc/kernel/trampoline_64.S
index 737f8cbc7d56..88ede1d53b4c 100644
--- a/arch/sparc/kernel/trampoline_64.S
+++ b/arch/sparc/kernel/trampoline_64.S
@@ -109,10 +109,13 @@ startup_continue:
 	brnz,pn		%g1, 1b
 	 nop
 
-	sethi		%hi(p1275buf), %g2
-	or		%g2, %lo(p1275buf), %g2
-	ldx		[%g2 + 0x10], %l2
-	add		%l2, -(192 + 128), %sp
+	/* Get onto temporary stack which will be in the locked
+	 * kernel image.
+	 */
+	sethi		%hi(tramp_stack), %g1
+	or		%g1, %lo(tramp_stack), %g1
+	add		%g1, TRAMP_STACK_SIZE, %g1
+	sub		%g1, STACKFRAME_SZ + STACK_BIAS + 256, %sp
 	flushw
 
 	/* Setup the loop variables:
@@ -394,7 +397,6 @@ after_lock_tlb:
 	sllx		%g5, THREAD_SHIFT, %g5
 	sub		%g5, (STACKFRAME_SZ + STACK_BIAS), %g5
 	add		%g6, %g5, %sp
-	mov		0, %fp
 
 	rdpr		%pstate, %o1
 	or		%o1, PSTATE_IE, %o1
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 4ced92f05358..25d0c7ece9cc 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2102,6 +2102,11 @@ void sun4v_nonresum_overflow(struct pt_regs *regs)
 	atomic_inc(&sun4v_nonresum_oflow_cnt);
 }
 
+static void sun4v_tlb_error(struct pt_regs *regs)
+{
+	die_if_kernel("TLB/TSB error", regs);
+}
+
 unsigned long sun4v_err_itlb_vaddr;
 unsigned long sun4v_err_itlb_ctx;
 unsigned long sun4v_err_itlb_pte;
@@ -2109,8 +2114,7 @@ unsigned long sun4v_err_itlb_error;
 
 void sun4v_itlb_error_report(struct pt_regs *regs, int tl)
 {
-	if (tl > 1)
-		dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
+	dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
 
 	printk(KERN_EMERG "SUN4V-ITLB: Error at TPC[%lx], tl %d\n",
 	       regs->tpc, tl);
@@ -2123,7 +2127,7 @@ void sun4v_itlb_error_report(struct pt_regs *regs, int tl)
 	       sun4v_err_itlb_vaddr, sun4v_err_itlb_ctx,
 	       sun4v_err_itlb_pte, sun4v_err_itlb_error);
 
-	prom_halt();
+	sun4v_tlb_error(regs);
 }
 
 unsigned long sun4v_err_dtlb_vaddr;
@@ -2133,8 +2137,7 @@ unsigned long sun4v_err_dtlb_error;
 
 void sun4v_dtlb_error_report(struct pt_regs *regs, int tl)
 {
-	if (tl > 1)
-		dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
+	dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
 
 	printk(KERN_EMERG "SUN4V-DTLB: Error at TPC[%lx], tl %d\n",
 	       regs->tpc, tl);
@@ -2147,7 +2150,7 @@ void sun4v_dtlb_error_report(struct pt_regs *regs, int tl)
 	       sun4v_err_dtlb_vaddr, sun4v_err_dtlb_ctx,
 	       sun4v_err_dtlb_pte, sun4v_err_dtlb_error);
 
-	prom_halt();
+	sun4v_tlb_error(regs);
 }
 
 void hypervisor_tlbop_error(unsigned long err, unsigned long op)
diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S
index 14158d40ba76..be98685c14c6 100644
--- a/arch/sparc/kernel/tsb.S
+++ b/arch/sparc/kernel/tsb.S
@@ -162,10 +162,10 @@ tsb_miss_page_table_walk_sun4v_fastpath:
 	nop
 	.previous
 
-	rdpr	%tl, %g3
-	cmp	%g3, 1
+	rdpr	%tl, %g7
+	cmp	%g7, 1
 	bne,pn	%xcc, winfix_trampoline
-	 nop
+	 mov	%g3, %g4
 	ba,pt	%xcc, etrap
 	 rd	%pc, %g7
 	call	hugetlb_setup
diff --git a/arch/sparc/kernel/viohs.c b/arch/sparc/kernel/viohs.c
index f8e7dd53e1c7..9c5fbd0b8a04 100644
--- a/arch/sparc/kernel/viohs.c
+++ b/arch/sparc/kernel/viohs.c
@@ -714,7 +714,7 @@ int vio_ldc_alloc(struct vio_driver_state *vio,
 	cfg.tx_irq = vio->vdev->tx_irq;
 	cfg.rx_irq = vio->vdev->rx_irq;
 
-	lp = ldc_alloc(vio->vdev->channel_id, &cfg, event_arg);
+	lp = ldc_alloc(vio->vdev->channel_id, &cfg, event_arg, vio->name);
 	if (IS_ERR(lp))
 		return PTR_ERR(lp);
 
@@ -746,7 +746,7 @@ void vio_port_up(struct vio_driver_state *vio)
 
 	err = 0;
 	if (state == LDC_STATE_INIT) {
-		err = ldc_bind(vio->lp, vio->name);
+		err = ldc_bind(vio->lp);
 		if (err)
 			printk(KERN_WARNING "%s: Port %lu bind failed, "
 			       "err=%d\n",
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 932ff90fd760..09243057cb0b 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -35,8 +35,9 @@ jiffies = jiffies_64;
 
 SECTIONS
 {
-	/* swapper_low_pmd_dir is sparc64 only */
-	swapper_low_pmd_dir = 0x0000000000402000;
+#ifdef CONFIG_SPARC64
+	swapper_pg_dir = 0x0000000000402000;
+#endif
 	. = INITIAL_ADDRESS;
 	.text TEXTSTART :
 	{
@@ -122,11 +123,6 @@ SECTIONS
 		*(.swapper_4m_tsb_phys_patch)
 		__swapper_4m_tsb_phys_patch_end = .;
 	}
-	.page_offset_shift_patch : {
-		__page_offset_shift_patch = .;
-		*(.page_offset_shift_patch)
-		__page_offset_shift_patch_end = .;
-	}
 	.popc_3insn_patch : {
 		__popc_3insn_patch = .;
 		*(.popc_3insn_patch)
diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S
index 9cf2ee01cee3..140527a20e7d 100644
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -41,6 +41,10 @@
 #endif
 #endif
 
+#if !defined(EX_LD) && !defined(EX_ST)
+#define NON_USER_COPY
+#endif
+
 #ifndef EX_LD
 #define EX_LD(x)	x
 #endif
@@ -197,9 +201,13 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 mov		EX_RETVAL(%o3), %o0
 
 .Llarge_src_unaligned:
+#ifdef NON_USER_COPY
+	VISEntryHalfFast(.Lmedium_vis_entry_fail)
+#else
+	VISEntryHalf
+#endif
 	andn		%o2, 0x3f, %o4
 	sub		%o2, %o4, %o2
-	VISEntryHalf
 	alignaddr	%o1, %g0, %g1
 	add		%o1, %o4, %o1
 	EX_LD(LOAD(ldd, %g1 + 0x00, %f0))
@@ -240,6 +248,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 nop
 	ba,a,pt		%icc, .Lmedium_unaligned
 
+#ifdef NON_USER_COPY
+.Lmedium_vis_entry_fail:
+	 or		%o0, %o1, %g2
+#endif
 .Lmedium:
 	LOAD(prefetch, %o1 + 0x40, #n_reads_strong)
 	andcc		%g2, 0x7, %g0
diff --git a/arch/sparc/lib/memset.S b/arch/sparc/lib/memset.S
index 99c017be8719..f75e6906df14 100644
--- a/arch/sparc/lib/memset.S
+++ b/arch/sparc/lib/memset.S
@@ -3,8 +3,9 @@
  * Copyright (C) 1996,1997 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
  * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
  *
- * Returns 0, if ok, and number of bytes not yet set if exception
- * occurs and we were called as clear_user.
+ * Calls to memset returns initial %o0. Calls to bzero returns 0, if ok, and
+ * number of bytes not yet set if exception occurs and we were called as
+ * clear_user.
  */
 
 #include <asm/ptrace.h>
@@ -65,6 +66,8 @@ __bzero_begin:
 	.globl	__memset_start, __memset_end
 __memset_start:
 memset:
+	mov	%o0, %g1
+	mov	1, %g4
 	and	%o1, 0xff, %g3
 	sll	%g3, 8, %g2
 	or	%g3, %g2, %g3
@@ -89,6 +92,7 @@ memset:
 	 sub	%o0, %o2, %o0
 
 __bzero:
+	clr	%g4
 	mov	%g0, %g3
 1:
 	cmp	%o1, 7
@@ -151,8 +155,8 @@ __bzero:
 	bne,a	8f
 	 EX(stb	%g3, [%o0], and %o1, 1)
 8:
-	retl
-	 clr	%o0
+	b	0f
+	 nop
 7:
 	be	13b
 	 orcc	%o1, 0, %g0
@@ -164,6 +168,12 @@ __bzero:
 	bne	8b
 	 EX(stb	%g3, [%o0 - 1], add %o1, 1)
 0:
+	andcc	%g4, 1, %g0
+	be	5f
+	 nop
+	retl
+	 mov	%g1, %o0
+5:
 	retl
 	 clr	%o0
 __memset_end:
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 4ced3fc66130..45a413e4380a 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -348,6 +348,9 @@ retry:
 		down_read(&mm->mmap_sem);
 	}
 
+	if (fault_code & FAULT_CODE_BAD_RA)
+		goto do_sigbus;
+
 	vma = find_vma(mm, address);
 	if (!vma)
 		goto bad_area;
diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
index 1aed0432c64b..ae6ce383d4df 100644
--- a/arch/sparc/mm/gup.c
+++ b/arch/sparc/mm/gup.c
@@ -160,6 +160,36 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
 	return 1;
 }
 
+int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
+			  struct page **pages)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long addr, len, end;
+	unsigned long next, flags;
+	pgd_t *pgdp;
+	int nr = 0;
+
+	start &= PAGE_MASK;
+	addr = start;
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+
+	local_irq_save(flags);
+	pgdp = pgd_offset(mm, addr);
+	do {
+		pgd_t pgd = *pgdp;
+
+		next = pgd_addr_end(addr, end);
+		if (pgd_none(pgd))
+			break;
+		if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+			break;
+	} while (pgdp++, addr = next, addr != end);
+	local_irq_restore(flags);
+
+	return nr;
+}
+
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages)
 {
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 96862241b342..34506f292533 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -73,7 +73,6 @@ unsigned long kern_linear_pte_xor[4] __read_mostly;
  * 'cpu' properties, but we need to have this table setup before the
  * MDESC is initialized.
  */
-unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)];
 
 #ifndef CONFIG_DEBUG_PAGEALLOC
 /* A special kernel TSB for 4MB, 256MB, 2GB and 16GB linear mappings.
@@ -82,10 +81,11 @@ unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)];
  */
 extern struct tsb swapper_4m_tsb[KERNEL_TSB4M_NENTRIES];
 #endif
+extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES];
 
 static unsigned long cpu_pgsz_mask;
 
-#define MAX_BANKS	32
+#define MAX_BANKS	1024
 
 static struct linux_prom64_registers pavail[MAX_BANKS];
 static int pavail_ents;
@@ -163,10 +163,6 @@ static void __init read_obp_memory(const char *property,
 	     cmp_p64, NULL);
 }
 
-unsigned long sparc64_valid_addr_bitmap[VALID_ADDR_BITMAP_BYTES /
-					sizeof(unsigned long)];
-EXPORT_SYMBOL(sparc64_valid_addr_bitmap);
-
 /* Kernel physical address base and size in bytes.  */
 unsigned long kern_base __read_mostly;
 unsigned long kern_size __read_mostly;
@@ -838,7 +834,10 @@ static int find_node(unsigned long addr)
 		if ((addr & p->mask) == p->val)
 			return i;
 	}
-	return -1;
+	/* The following condition has been observed on LDOM guests.*/
+	WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node"
+		" rule. Some physical memory will be owned by node 0.");
+	return 0;
 }
 
 static u64 memblock_nid_range(u64 start, u64 end, int *nid)
@@ -1360,9 +1359,144 @@ static unsigned long __init bootmem_init(unsigned long phys_base)
 static struct linux_prom64_registers pall[MAX_BANKS] __initdata;
 static int pall_ents __initdata;
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
+static unsigned long max_phys_bits = 40;
+
+bool kern_addr_valid(unsigned long addr)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	if ((long)addr < 0L) {
+		unsigned long pa = __pa(addr);
+
+		if ((addr >> max_phys_bits) != 0UL)
+			return false;
+
+		return pfn_valid(pa >> PAGE_SHIFT);
+	}
+
+	if (addr >= (unsigned long) KERNBASE &&
+	    addr < (unsigned long)&_end)
+		return true;
+
+	pgd = pgd_offset_k(addr);
+	if (pgd_none(*pgd))
+		return 0;
+
+	pud = pud_offset(pgd, addr);
+	if (pud_none(*pud))
+		return 0;
+
+	if (pud_large(*pud))
+		return pfn_valid(pud_pfn(*pud));
+
+	pmd = pmd_offset(pud, addr);
+	if (pmd_none(*pmd))
+		return 0;
+
+	if (pmd_large(*pmd))
+		return pfn_valid(pmd_pfn(*pmd));
+
+	pte = pte_offset_kernel(pmd, addr);
+	if (pte_none(*pte))
+		return 0;
+
+	return pfn_valid(pte_pfn(*pte));
+}
+EXPORT_SYMBOL(kern_addr_valid);
+
+static unsigned long __ref kernel_map_hugepud(unsigned long vstart,
+					      unsigned long vend,
+					      pud_t *pud)
+{
+	const unsigned long mask16gb = (1UL << 34) - 1UL;
+	u64 pte_val = vstart;
+
+	/* Each PUD is 8GB */
+	if ((vstart & mask16gb) ||
+	    (vend - vstart <= mask16gb)) {
+		pte_val ^= kern_linear_pte_xor[2];
+		pud_val(*pud) = pte_val | _PAGE_PUD_HUGE;
+
+		return vstart + PUD_SIZE;
+	}
+
+	pte_val ^= kern_linear_pte_xor[3];
+	pte_val |= _PAGE_PUD_HUGE;
+
+	vend = vstart + mask16gb + 1UL;
+	while (vstart < vend) {
+		pud_val(*pud) = pte_val;
+
+		pte_val += PUD_SIZE;
+		vstart += PUD_SIZE;
+		pud++;
+	}
+	return vstart;
+}
+
+static bool kernel_can_map_hugepud(unsigned long vstart, unsigned long vend,
+				   bool guard)
+{
+	if (guard && !(vstart & ~PUD_MASK) && (vend - vstart) >= PUD_SIZE)
+		return true;
+
+	return false;
+}
+
+static unsigned long __ref kernel_map_hugepmd(unsigned long vstart,
+					      unsigned long vend,
+					      pmd_t *pmd)
+{
+	const unsigned long mask256mb = (1UL << 28) - 1UL;
+	const unsigned long mask2gb = (1UL << 31) - 1UL;
+	u64 pte_val = vstart;
+
+	/* Each PMD is 8MB */
+	if ((vstart & mask256mb) ||
+	    (vend - vstart <= mask256mb)) {
+		pte_val ^= kern_linear_pte_xor[0];
+		pmd_val(*pmd) = pte_val | _PAGE_PMD_HUGE;
+
+		return vstart + PMD_SIZE;
+	}
+
+	if ((vstart & mask2gb) ||
+	    (vend - vstart <= mask2gb)) {
+		pte_val ^= kern_linear_pte_xor[1];
+		pte_val |= _PAGE_PMD_HUGE;
+		vend = vstart + mask256mb + 1UL;
+	} else {
+		pte_val ^= kern_linear_pte_xor[2];
+		pte_val |= _PAGE_PMD_HUGE;
+		vend = vstart + mask2gb + 1UL;
+	}
+
+	while (vstart < vend) {
+		pmd_val(*pmd) = pte_val;
+
+		pte_val += PMD_SIZE;
+		vstart += PMD_SIZE;
+		pmd++;
+	}
+
+	return vstart;
+}
+
+static bool kernel_can_map_hugepmd(unsigned long vstart, unsigned long vend,
+				   bool guard)
+{
+	if (guard && !(vstart & ~PMD_MASK) && (vend - vstart) >= PMD_SIZE)
+		return true;
+
+	return false;
+}
+
 static unsigned long __ref kernel_map_range(unsigned long pstart,
-					    unsigned long pend, pgprot_t prot)
+					    unsigned long pend, pgprot_t prot,
+					    bool use_huge)
 {
 	unsigned long vstart = PAGE_OFFSET + pstart;
 	unsigned long vend = PAGE_OFFSET + pend;
@@ -1381,19 +1515,34 @@ static unsigned long __ref kernel_map_range(unsigned long pstart,
 		pmd_t *pmd;
 		pte_t *pte;
 
+		if (pgd_none(*pgd)) {
+			pud_t *new;
+
+			new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
+			alloc_bytes += PAGE_SIZE;
+			pgd_populate(&init_mm, pgd, new);
+		}
 		pud = pud_offset(pgd, vstart);
 		if (pud_none(*pud)) {
 			pmd_t *new;
 
+			if (kernel_can_map_hugepud(vstart, vend, use_huge)) {
+				vstart = kernel_map_hugepud(vstart, vend, pud);
+				continue;
+			}
 			new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
 			alloc_bytes += PAGE_SIZE;
 			pud_populate(&init_mm, pud, new);
 		}
 
 		pmd = pmd_offset(pud, vstart);
-		if (!pmd_present(*pmd)) {
+		if (pmd_none(*pmd)) {
 			pte_t *new;
 
+			if (kernel_can_map_hugepmd(vstart, vend, use_huge)) {
+				vstart = kernel_map_hugepmd(vstart, vend, pmd);
+				continue;
+			}
 			new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
 			alloc_bytes += PAGE_SIZE;
 			pmd_populate_kernel(&init_mm, pmd, new);
@@ -1416,100 +1565,34 @@ static unsigned long __ref kernel_map_range(unsigned long pstart,
 	return alloc_bytes;
 }
 
-extern unsigned int kvmap_linear_patch[1];
-#endif /* CONFIG_DEBUG_PAGEALLOC */
-
-static void __init kpte_set_val(unsigned long index, unsigned long val)
+static void __init flush_all_kernel_tsbs(void)
 {
-	unsigned long *ptr = kpte_linear_bitmap;
-
-	val <<= ((index % (BITS_PER_LONG / 2)) * 2);
-	ptr += (index / (BITS_PER_LONG / 2));
-
-	*ptr |= val;
-}
-
-static const unsigned long kpte_shift_min = 28; /* 256MB */
-static const unsigned long kpte_shift_max = 34; /* 16GB */
-static const unsigned long kpte_shift_incr = 3;
-
-static unsigned long kpte_mark_using_shift(unsigned long start, unsigned long end,
-					   unsigned long shift)
-{
-	unsigned long size = (1UL << shift);
-	unsigned long mask = (size - 1UL);
-	unsigned long remains = end - start;
-	unsigned long val;
-
-	if (remains < size || (start & mask))
-		return start;
-
-	/* VAL maps:
-	 *
-	 *	shift 28 --> kern_linear_pte_xor index 1
-	 *	shift 31 --> kern_linear_pte_xor index 2
-	 *	shift 34 --> kern_linear_pte_xor index 3
-	 */
-	val = ((shift - kpte_shift_min) / kpte_shift_incr) + 1;
-
-	remains &= ~mask;
-	if (shift != kpte_shift_max)
-		remains = size;
-
-	while (remains) {
-		unsigned long index = start >> kpte_shift_min;
+	int i;
 
-		kpte_set_val(index, val);
+	for (i = 0; i < KERNEL_TSB_NENTRIES; i++) {
+		struct tsb *ent = &swapper_tsb[i];
 
-		start += 1UL << kpte_shift_min;
-		remains -= 1UL << kpte_shift_min;
+		ent->tag = (1UL << TSB_TAG_INVALID_BIT);
 	}
+#ifndef CONFIG_DEBUG_PAGEALLOC
+	for (i = 0; i < KERNEL_TSB4M_NENTRIES; i++) {
+		struct tsb *ent = &swapper_4m_tsb[i];
 
-	return start;
-}
-
-static void __init mark_kpte_bitmap(unsigned long start, unsigned long end)
-{
-	unsigned long smallest_size, smallest_mask;
-	unsigned long s;
-
-	smallest_size = (1UL << kpte_shift_min);
-	smallest_mask = (smallest_size - 1UL);
-
-	while (start < end) {
-		unsigned long orig_start = start;
-
-		for (s = kpte_shift_max; s >= kpte_shift_min; s -= kpte_shift_incr) {
-			start = kpte_mark_using_shift(start, end, s);
-
-			if (start != orig_start)
-				break;
-		}
-
-		if (start == orig_start)
-			start = (start + smallest_size) & ~smallest_mask;
+		ent->tag = (1UL << TSB_TAG_INVALID_BIT);
 	}
+#endif
 }
 
-static void __init init_kpte_bitmap(void)
-{
-	unsigned long i;
-
-	for (i = 0; i < pall_ents; i++) {
-		unsigned long phys_start, phys_end;
-
-		phys_start = pall[i].phys_addr;
-		phys_end = phys_start + pall[i].reg_size;
-
-		mark_kpte_bitmap(phys_start, phys_end);
-	}
-}
+extern unsigned int kvmap_linear_patch[1];
 
 static void __init kernel_physical_mapping_init(void)
 {
-#ifdef CONFIG_DEBUG_PAGEALLOC
 	unsigned long i, mem_alloced = 0UL;
+	bool use_huge = true;
 
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	use_huge = false;
+#endif
 	for (i = 0; i < pall_ents; i++) {
 		unsigned long phys_start, phys_end;
 
@@ -1517,7 +1600,7 @@ static void __init kernel_physical_mapping_init(void)
 		phys_end = phys_start + pall[i].reg_size;
 
 		mem_alloced += kernel_map_range(phys_start, phys_end,
-						PAGE_KERNEL);
+						PAGE_KERNEL, use_huge);
 	}
 
 	printk("Allocated %ld bytes for kernel page tables.\n",
@@ -1526,8 +1609,9 @@ static void __init kernel_physical_mapping_init(void)
 	kvmap_linear_patch[0] = 0x01000000; /* nop */
 	flushi(&kvmap_linear_patch[0]);
 
+	flush_all_kernel_tsbs();
+
 	__flush_tlb_all();
-#endif
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
@@ -1537,7 +1621,7 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
 	unsigned long phys_end = phys_start + (numpages * PAGE_SIZE);
 
 	kernel_map_range(phys_start, phys_end,
-			 (enable ? PAGE_KERNEL : __pgprot(0)));
+			 (enable ? PAGE_KERNEL : __pgprot(0)), false);
 
 	flush_tsb_kernel_range(PAGE_OFFSET + phys_start,
 			       PAGE_OFFSET + phys_end);
@@ -1565,76 +1649,56 @@ unsigned long __init find_ecache_flush_span(unsigned long size)
 unsigned long PAGE_OFFSET;
 EXPORT_SYMBOL(PAGE_OFFSET);
 
-static void __init page_offset_shift_patch_one(unsigned int *insn, unsigned long phys_bits)
-{
-	unsigned long final_shift;
-	unsigned int val = *insn;
-	unsigned int cnt;
-
-	/* We are patching in ilog2(max_supported_phys_address), and
-	 * we are doing so in a manner similar to a relocation addend.
-	 * That is, we are adding the shift value to whatever value
-	 * is in the shift instruction count field already.
-	 */
-	cnt = (val & 0x3f);
-	val &= ~0x3f;
-
-	/* If we are trying to shift >= 64 bits, clear the destination
-	 * register.  This can happen when phys_bits ends up being equal
-	 * to MAX_PHYS_ADDRESS_BITS.
-	 */
-	final_shift = (cnt + (64 - phys_bits));
-	if (final_shift >= 64) {
-		unsigned int rd = (val >> 25) & 0x1f;
-
-		val = 0x80100000 | (rd << 25);
-	} else {
-		val |= final_shift;
-	}
-	*insn = val;
-
-	__asm__ __volatile__("flush	%0"
-			     : /* no outputs */
-			     : "r" (insn));
-}
-
-static void __init page_offset_shift_patch(unsigned long phys_bits)
-{
-	extern unsigned int __page_offset_shift_patch;
-	extern unsigned int __page_offset_shift_patch_end;
-	unsigned int *p;
-
-	p = &__page_offset_shift_patch;
-	while (p < &__page_offset_shift_patch_end) {
-		unsigned int *insn = (unsigned int *)(unsigned long)*p;
+unsigned long VMALLOC_END   = 0x0000010000000000UL;
+EXPORT_SYMBOL(VMALLOC_END);
 
-		page_offset_shift_patch_one(insn, phys_bits);
-
-		p++;
-	}
-}
+unsigned long sparc64_va_hole_top =    0xfffff80000000000UL;
+unsigned long sparc64_va_hole_bottom = 0x0000080000000000UL;
 
 static void __init setup_page_offset(void)
 {
-	unsigned long max_phys_bits = 40;
-
 	if (tlb_type == cheetah || tlb_type == cheetah_plus) {
+		/* Cheetah/Panther support a full 64-bit virtual
+		 * address, so we can use all that our page tables
+		 * support.
+		 */
+		sparc64_va_hole_top =    0xfff0000000000000UL;
+		sparc64_va_hole_bottom = 0x0010000000000000UL;
+
 		max_phys_bits = 42;
 	} else if (tlb_type == hypervisor) {
 		switch (sun4v_chip_type) {
 		case SUN4V_CHIP_NIAGARA1:
 		case SUN4V_CHIP_NIAGARA2:
+			/* T1 and T2 support 48-bit virtual addresses.  */
+			sparc64_va_hole_top =    0xffff800000000000UL;
+			sparc64_va_hole_bottom = 0x0000800000000000UL;
+
 			max_phys_bits = 39;
 			break;
 		case SUN4V_CHIP_NIAGARA3:
+			/* T3 supports 48-bit virtual addresses.  */
+			sparc64_va_hole_top =    0xffff800000000000UL;
+			sparc64_va_hole_bottom = 0x0000800000000000UL;
+
 			max_phys_bits = 43;
 			break;
 		case SUN4V_CHIP_NIAGARA4:
 		case SUN4V_CHIP_NIAGARA5:
 		case SUN4V_CHIP_SPARC64X:
-		default:
+		case SUN4V_CHIP_SPARC_M6:
+			/* T4 and later support 52-bit virtual addresses.  */
+			sparc64_va_hole_top =    0xfff8000000000000UL;
+			sparc64_va_hole_bottom = 0x0008000000000000UL;
 			max_phys_bits = 47;
 			break;
+		case SUN4V_CHIP_SPARC_M7:
+		default:
+			/* M7 and later support 52-bit virtual addresses.  */
+			sparc64_va_hole_top =    0xfff8000000000000UL;
+			sparc64_va_hole_bottom = 0x0008000000000000UL;
+			max_phys_bits = 49;
+			break;
 		}
 	}
 
@@ -1644,12 +1708,16 @@ static void __init setup_page_offset(void)
 		prom_halt();
 	}
 
-	PAGE_OFFSET = PAGE_OFFSET_BY_BITS(max_phys_bits);
+	PAGE_OFFSET = sparc64_va_hole_top;
+	VMALLOC_END = ((sparc64_va_hole_bottom >> 1) +
+		       (sparc64_va_hole_bottom >> 2));
 
-	pr_info("PAGE_OFFSET is 0x%016lx (max_phys_bits == %lu)\n",
+	pr_info("MM: PAGE_OFFSET is 0x%016lx (max_phys_bits == %lu)\n",
 		PAGE_OFFSET, max_phys_bits);
-
-	page_offset_shift_patch(max_phys_bits);
+	pr_info("MM: VMALLOC [0x%016lx --> 0x%016lx]\n",
+		VMALLOC_START, VMALLOC_END);
+	pr_info("MM: VMEMMAP [0x%016lx --> 0x%016lx]\n",
+		VMEMMAP_BASE, VMEMMAP_BASE << 1);
 }
 
 static void __init tsb_phys_patch(void)
@@ -1694,21 +1762,42 @@ static void __init tsb_phys_patch(void)
 #define NUM_KTSB_DESCR	1
 #endif
 static struct hv_tsb_descr ktsb_descr[NUM_KTSB_DESCR];
-extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES];
+
+/* The swapper TSBs are loaded with a base sequence of:
+ *
+ *	sethi	%uhi(SYMBOL), REG1
+ *	sethi	%hi(SYMBOL), REG2
+ *	or	REG1, %ulo(SYMBOL), REG1
+ *	or	REG2, %lo(SYMBOL), REG2
+ *	sllx	REG1, 32, REG1
+ *	or	REG1, REG2, REG1
+ *
+ * When we use physical addressing for the TSB accesses, we patch the
+ * first four instructions in the above sequence.
+ */
 
 static void patch_one_ktsb_phys(unsigned int *start, unsigned int *end, unsigned long pa)
 {
-	pa >>= KTSB_PHYS_SHIFT;
+	unsigned long high_bits, low_bits;
+
+	high_bits = (pa >> 32) & 0xffffffff;
+	low_bits = (pa >> 0) & 0xffffffff;
 
 	while (start < end) {
 		unsigned int *ia = (unsigned int *)(unsigned long)*start;
 
-		ia[0] = (ia[0] & ~0x3fffff) | (pa >> 10);
+		ia[0] = (ia[0] & ~0x3fffff) | (high_bits >> 10);
 		__asm__ __volatile__("flush	%0" : : "r" (ia));
 
-		ia[1] = (ia[1] & ~0x3ff) | (pa & 0x3ff);
+		ia[1] = (ia[1] & ~0x3fffff) | (low_bits >> 10);
 		__asm__ __volatile__("flush	%0" : : "r" (ia + 1));
 
+		ia[2] = (ia[2] & ~0x1fff) | (high_bits & 0x3ff);
+		__asm__ __volatile__("flush	%0" : : "r" (ia + 2));
+
+		ia[3] = (ia[3] & ~0x1fff) | (low_bits & 0x3ff);
+		__asm__ __volatile__("flush	%0" : : "r" (ia + 3));
+
 		start++;
 	}
 }
@@ -1847,7 +1936,6 @@ static void __init sun4v_linear_pte_xor_finalize(void)
 /* paging_init() sets up the page tables */
 
 static unsigned long last_valid_pfn;
-pgd_t swapper_pg_dir[PTRS_PER_PGD];
 
 static void sun4u_pgprot_init(void);
 static void sun4v_pgprot_init(void);
@@ -1950,16 +2038,10 @@ void __init paging_init(void)
 	 */
 	init_mm.pgd += ((shift) / (sizeof(pgd_t)));
 	
-	memset(swapper_low_pmd_dir, 0, sizeof(swapper_low_pmd_dir));
+	memset(swapper_pg_dir, 0, sizeof(swapper_pg_dir));
 
-	/* Now can init the kernel/bad page tables. */
-	pud_set(pud_offset(&swapper_pg_dir[0], 0),
-		swapper_low_pmd_dir + (shift / sizeof(pgd_t)));
-	
 	inherit_prom_mappings();
 	
-	init_kpte_bitmap();
-
 	/* Ok, we can use our TLB miss and window trap handlers safely.  */
 	setup_tba();
 
@@ -2066,70 +2148,6 @@ int page_in_phys_avail(unsigned long paddr)
 	return 0;
 }
 
-static struct linux_prom64_registers pavail_rescan[MAX_BANKS] __initdata;
-static int pavail_rescan_ents __initdata;
-
-/* Certain OBP calls, such as fetching "available" properties, can
- * claim physical memory.  So, along with initializing the valid
- * address bitmap, what we do here is refetch the physical available
- * memory list again, and make sure it provides at least as much
- * memory as 'pavail' does.
- */
-static void __init setup_valid_addr_bitmap_from_pavail(unsigned long *bitmap)
-{
-	int i;
-
-	read_obp_memory("available", &pavail_rescan[0], &pavail_rescan_ents);
-
-	for (i = 0; i < pavail_ents; i++) {
-		unsigned long old_start, old_end;
-
-		old_start = pavail[i].phys_addr;
-		old_end = old_start + pavail[i].reg_size;
-		while (old_start < old_end) {
-			int n;
-
-			for (n = 0; n < pavail_rescan_ents; n++) {
-				unsigned long new_start, new_end;
-
-				new_start = pavail_rescan[n].phys_addr;
-				new_end = new_start +
-					pavail_rescan[n].reg_size;
-
-				if (new_start <= old_start &&
-				    new_end >= (old_start + PAGE_SIZE)) {
-					set_bit(old_start >> ILOG2_4MB, bitmap);
-					goto do_next_page;
-				}
-			}
-
-			prom_printf("mem_init: Lost memory in pavail\n");
-			prom_printf("mem_init: OLD start[%lx] size[%lx]\n",
-				    pavail[i].phys_addr,
-				    pavail[i].reg_size);
-			prom_printf("mem_init: NEW start[%lx] size[%lx]\n",
-				    pavail_rescan[i].phys_addr,
-				    pavail_rescan[i].reg_size);
-			prom_printf("mem_init: Cannot continue, aborting.\n");
-			prom_halt();
-
-		do_next_page:
-			old_start += PAGE_SIZE;
-		}
-	}
-}
-
-static void __init patch_tlb_miss_handler_bitmap(void)
-{
-	extern unsigned int valid_addr_bitmap_insn[];
-	extern unsigned int valid_addr_bitmap_patch[];
-
-	valid_addr_bitmap_insn[1] = valid_addr_bitmap_patch[1];
-	mb();
-	valid_addr_bitmap_insn[0] = valid_addr_bitmap_patch[0];
-	flushi(&valid_addr_bitmap_insn[0]);
-}
-
 static void __init register_page_bootmem_info(void)
 {
 #ifdef CONFIG_NEED_MULTIPLE_NODES
@@ -2142,18 +2160,6 @@ static void __init register_page_bootmem_info(void)
 }
 void __init mem_init(void)
 {
-	unsigned long addr, last;
-
-	addr = PAGE_OFFSET + kern_base;
-	last = PAGE_ALIGN(kern_size) + addr;
-	while (addr < last) {
-		set_bit(__pa(addr) >> ILOG2_4MB, sparc64_valid_addr_bitmap);
-		addr += PAGE_SIZE;
-	}
-
-	setup_valid_addr_bitmap_from_pavail(sparc64_valid_addr_bitmap);
-	patch_tlb_miss_handler_bitmap();
-
 	high_memory = __va(last_valid_pfn << PAGE_SHIFT);
 
 	register_page_bootmem_info();
@@ -2243,18 +2249,9 @@ unsigned long _PAGE_CACHE __read_mostly;
 EXPORT_SYMBOL(_PAGE_CACHE);
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-unsigned long vmemmap_table[VMEMMAP_SIZE];
-
-static long __meminitdata addr_start, addr_end;
-static int __meminitdata node_start;
-
 int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend,
 			       int node)
 {
-	unsigned long phys_start = (vstart - VMEMMAP_BASE);
-	unsigned long phys_end = (vend - VMEMMAP_BASE);
-	unsigned long addr = phys_start & VMEMMAP_CHUNK_MASK;
-	unsigned long end = VMEMMAP_ALIGN(phys_end);
 	unsigned long pte_base;
 
 	pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4U |
@@ -2265,47 +2262,52 @@ int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend,
 			    _PAGE_CP_4V | _PAGE_CV_4V |
 			    _PAGE_P_4V | _PAGE_W_4V);
 
-	for (; addr < end; addr += VMEMMAP_CHUNK) {
-		unsigned long *vmem_pp =
-			vmemmap_table + (addr >> VMEMMAP_CHUNK_SHIFT);
-		void *block;
+	pte_base |= _PAGE_PMD_HUGE;
 
-		if (!(*vmem_pp & _PAGE_VALID)) {
-			block = vmemmap_alloc_block(1UL << ILOG2_4MB, node);
-			if (!block)
+	vstart = vstart & PMD_MASK;
+	vend = ALIGN(vend, PMD_SIZE);
+	for (; vstart < vend; vstart += PMD_SIZE) {
+		pgd_t *pgd = pgd_offset_k(vstart);
+		unsigned long pte;
+		pud_t *pud;
+		pmd_t *pmd;
+
+		if (pgd_none(*pgd)) {
+			pud_t *new = vmemmap_alloc_block(PAGE_SIZE, node);
+
+			if (!new)
 				return -ENOMEM;
+			pgd_populate(&init_mm, pgd, new);
+		}
 
-			*vmem_pp = pte_base | __pa(block);
+		pud = pud_offset(pgd, vstart);
+		if (pud_none(*pud)) {
+			pmd_t *new = vmemmap_alloc_block(PAGE_SIZE, node);
 
-			/* check to see if we have contiguous blocks */
-			if (addr_end != addr || node_start != node) {
-				if (addr_start)
-					printk(KERN_DEBUG " [%lx-%lx] on node %d\n",
-					       addr_start, addr_end-1, node_start);
-				addr_start = addr;
-				node_start = node;
-			}
-			addr_end = addr + VMEMMAP_CHUNK;
+			if (!new)
+				return -ENOMEM;
+			pud_populate(&init_mm, pud, new);
 		}
-	}
-	return 0;
-}
 
-void __meminit vmemmap_populate_print_last(void)
-{
-	if (addr_start) {
-		printk(KERN_DEBUG " [%lx-%lx] on node %d\n",
-		       addr_start, addr_end-1, node_start);
-		addr_start = 0;
-		addr_end = 0;
-		node_start = 0;
+		pmd = pmd_offset(pud, vstart);
+
+		pte = pmd_val(*pmd);
+		if (!(pte & _PAGE_VALID)) {
+			void *block = vmemmap_alloc_block(PMD_SIZE, node);
+
+			if (!block)
+				return -ENOMEM;
+
+			pmd_val(*pmd) = pte_base | __pa(block);
+		}
 	}
+
+	return 0;
 }
 
 void vmemmap_free(unsigned long start, unsigned long end)
 {
 }
-
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
 static void prot_init_common(unsigned long page_none,
@@ -2717,8 +2719,8 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 			do_flush_tlb_kernel_range(start, LOW_OBP_ADDRESS);
 		}
 		if (end > HI_OBP_ADDRESS) {
-			flush_tsb_kernel_range(end, HI_OBP_ADDRESS);
-			do_flush_tlb_kernel_range(end, HI_OBP_ADDRESS);
+			flush_tsb_kernel_range(HI_OBP_ADDRESS, end);
+			do_flush_tlb_kernel_range(HI_OBP_ADDRESS, end);
 		}
 	} else {
 		flush_tsb_kernel_range(start, end);
diff --git a/arch/sparc/mm/init_64.h b/arch/sparc/mm/init_64.h
index 5d3782deb403..ac491193cb54 100644
--- a/arch/sparc/mm/init_64.h
+++ b/arch/sparc/mm/init_64.h
@@ -8,15 +8,8 @@
  */
 
 #define MAX_PHYS_ADDRESS	(1UL << MAX_PHYS_ADDRESS_BITS)
-#define KPTE_BITMAP_CHUNK_SZ		(256UL * 1024UL * 1024UL)
-#define KPTE_BITMAP_BYTES	\
-	((MAX_PHYS_ADDRESS / KPTE_BITMAP_CHUNK_SZ) / 4)
-#define VALID_ADDR_BITMAP_CHUNK_SZ	(4UL * 1024UL * 1024UL)
-#define VALID_ADDR_BITMAP_BYTES	\
-	((MAX_PHYS_ADDRESS / VALID_ADDR_BITMAP_CHUNK_SZ) / 8)
 
 extern unsigned long kern_linear_pte_xor[4];
-extern unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)];
 extern unsigned int sparc64_highest_unlocked_tlb_ent;
 extern unsigned long sparc64_kern_pri_context;
 extern unsigned long sparc64_kern_pri_nuc_bits;
@@ -38,15 +31,4 @@ extern unsigned long kern_locked_tte_data;
 
 extern void prom_world(int enter);
 
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-#define VMEMMAP_CHUNK_SHIFT	22
-#define VMEMMAP_CHUNK		(1UL << VMEMMAP_CHUNK_SHIFT)
-#define VMEMMAP_CHUNK_MASK	~(VMEMMAP_CHUNK - 1UL)
-#define VMEMMAP_ALIGN(x)	(((x)+VMEMMAP_CHUNK-1UL)&VMEMMAP_CHUNK_MASK)
-
-#define VMEMMAP_SIZE	((((1UL << MAX_PHYSADDR_BITS) >> PAGE_SHIFT) * \
-			  sizeof(struct page)) >> VMEMMAP_CHUNK_SHIFT)
-extern unsigned long vmemmap_table[VMEMMAP_SIZE];
-#endif
-
 #endif /* _SPARC64_MM_INIT_H */
diff --git a/arch/sparc/power/hibernate_asm.S b/arch/sparc/power/hibernate_asm.S
index 79942166df84..d7d9017dcb15 100644
--- a/arch/sparc/power/hibernate_asm.S
+++ b/arch/sparc/power/hibernate_asm.S
@@ -54,8 +54,8 @@ ENTRY(swsusp_arch_resume)
 	 nop
 
 	/* Write PAGE_OFFSET to %g7 */
-	sethi	%uhi(PAGE_OFFSET), %g7
-	sllx	%g7, 32, %g7
+	sethi	%hi(PAGE_OFFSET), %g7
+	ldx	[%g7 + %lo(PAGE_OFFSET)], %g7
 
 	setuw	(PAGE_SIZE-8), %g3
 
diff --git a/arch/sparc/prom/bootstr_64.c b/arch/sparc/prom/bootstr_64.c
index ab9ccc63b388..7149e77714a4 100644
--- a/arch/sparc/prom/bootstr_64.c
+++ b/arch/sparc/prom/bootstr_64.c
@@ -14,7 +14,10 @@
  *          the .bss section or it will break things.
  */
 
-#define BARG_LEN  256
+/* We limit BARG_LEN to 1024 because this is the size of the
+ * 'barg_out' command line buffer in the SILO bootloader.
+ */
+#define BARG_LEN 1024
 struct {
 	int bootstr_len;
 	int bootstr_valid;
diff --git a/arch/sparc/prom/cif.S b/arch/sparc/prom/cif.S
index 9c86b4b7d429..8050f381f518 100644
--- a/arch/sparc/prom/cif.S
+++ b/arch/sparc/prom/cif.S
@@ -11,11 +11,10 @@
 	.text
 	.globl	prom_cif_direct
 prom_cif_direct:
+	save	%sp, -192, %sp
 	sethi	%hi(p1275buf), %o1
 	or	%o1, %lo(p1275buf), %o1
-	ldx	[%o1 + 0x0010], %o2	! prom_cif_stack
-	save	%o2, -192, %sp
-	ldx	[%i1 + 0x0008], %l2	! prom_cif_handler
+	ldx	[%o1 + 0x0008], %l2	! prom_cif_handler
 	mov	%g4, %l0
 	mov	%g5, %l1
 	mov	%g6, %l3
diff --git a/arch/sparc/prom/init_64.c b/arch/sparc/prom/init_64.c
index d95db755828f..110b0d78b864 100644
--- a/arch/sparc/prom/init_64.c
+++ b/arch/sparc/prom/init_64.c
@@ -26,13 +26,13 @@ phandle prom_chosen_node;
  * It gets passed the pointer to the PROM vector.
  */
 
-extern void prom_cif_init(void *, void *);
+extern void prom_cif_init(void *);
 
-void __init prom_init(void *cif_handler, void *cif_stack)
+void __init prom_init(void *cif_handler)
 {
 	phandle node;
 
-	prom_cif_init(cif_handler, cif_stack);
+	prom_cif_init(cif_handler);
 
 	prom_chosen_node = prom_finddevice(prom_chosen_path);
 	if (!prom_chosen_node || (s32)prom_chosen_node == -1)
diff --git a/arch/sparc/prom/p1275.c b/arch/sparc/prom/p1275.c
index e58b81726319..545d8bb79b65 100644
--- a/arch/sparc/prom/p1275.c
+++ b/arch/sparc/prom/p1275.c
@@ -9,6 +9,7 @@
 #include <linux/smp.h>
 #include <linux/string.h>
 #include <linux/spinlock.h>
+#include <linux/irqflags.h>
 
 #include <asm/openprom.h>
 #include <asm/oplib.h>
@@ -19,7 +20,6 @@
 struct {
 	long prom_callback;			/* 0x00 */
 	void (*prom_cif_handler)(long *);	/* 0x08 */
-	unsigned long prom_cif_stack;		/* 0x10 */
 } p1275buf;
 
 extern void prom_world(int);
@@ -36,8 +36,8 @@ void p1275_cmd_direct(unsigned long *args)
 {
 	unsigned long flags;
 
-	raw_local_save_flags(flags);
-	raw_local_irq_restore((unsigned long)PIL_NMI);
+	local_save_flags(flags);
+	local_irq_restore((unsigned long)PIL_NMI);
 	raw_spin_lock(&prom_entry_lock);
 
 	prom_world(1);
@@ -45,11 +45,10 @@ void p1275_cmd_direct(unsigned long *args)
 	prom_world(0);
 
 	raw_spin_unlock(&prom_entry_lock);
-	raw_local_irq_restore(flags);
+	local_irq_restore(flags);
 }
 
 void prom_cif_init(void *cif_handler, void *cif_stack)
 {
 	p1275buf.prom_cif_handler = (void (*)(long *))cif_handler;
-	p1275buf.prom_cif_stack = (unsigned long)cif_stack;
 }
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d71d5ac78e42..ac63ea4af5b0 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -480,6 +480,7 @@ struct kvm_vcpu_arch {
 	u64 mmio_gva;
 	unsigned access;
 	gfn_t mmio_gfn;
+	u64 mmio_gen;
 
 	struct kvm_pmu pmu;
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 5cd9bfabd645..c1a07d33e67e 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -153,6 +153,21 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 			setup_clear_cpu_cap(X86_FEATURE_ERMS);
 		}
 	}
+
+	/*
+	 * Intel Quark Core DevMan_001.pdf section 6.4.11
+	 * "The operating system also is required to invalidate (i.e., flush)
+	 *  the TLB when any changes are made to any of the page table entries.
+	 *  The operating system must reload CR3 to cause the TLB to be flushed"
+	 *
+	 * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should
+	 * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE
+	 * to be modified
+	 */
+	if (c->x86 == 5 && c->x86_model == 9) {
+		pr_info("Disabling PGE capability bit\n");
+		setup_clear_cpu_cap(X86_FEATURE_PGE);
+	}
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 9b531351a587..49088b8a3ee3 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -198,16 +198,20 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask)
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);
 
 /*
- * spte bits of bit 3 ~ bit 11 are used as low 9 bits of generation number,
- * the bits of bits 52 ~ bit 61 are used as high 10 bits of generation
- * number.
+ * the low bit of the generation number is always presumed to be zero.
+ * This disables mmio caching during memslot updates.  The concept is
+ * similar to a seqcount but instead of retrying the access we just punt
+ * and ignore the cache.
+ *
+ * spte bits 3-11 are used as bits 1-9 of the generation number,
+ * the bits 52-61 are used as bits 10-19 of the generation number.
  */
-#define MMIO_SPTE_GEN_LOW_SHIFT		3
+#define MMIO_SPTE_GEN_LOW_SHIFT		2
 #define MMIO_SPTE_GEN_HIGH_SHIFT	52
 
-#define MMIO_GEN_SHIFT			19
-#define MMIO_GEN_LOW_SHIFT		9
-#define MMIO_GEN_LOW_MASK		((1 << MMIO_GEN_LOW_SHIFT) - 1)
+#define MMIO_GEN_SHIFT			20
+#define MMIO_GEN_LOW_SHIFT		10
+#define MMIO_GEN_LOW_MASK		((1 << MMIO_GEN_LOW_SHIFT) - 2)
 #define MMIO_GEN_MASK			((1 << MMIO_GEN_SHIFT) - 1)
 #define MMIO_MAX_GEN			((1 << MMIO_GEN_SHIFT) - 1)
 
@@ -3157,7 +3161,7 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu)
 	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
 		return;
 
-	vcpu_clear_mmio_info(vcpu, ~0ul);
+	vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
 	kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
 	if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) {
 		hpa_t root = vcpu->arch.mmu.root_hpa;
@@ -4379,7 +4383,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm)
 	 * The very rare case: if the generation-number is round,
 	 * zap all shadow pages.
 	 */
-	if (unlikely(kvm_current_mmio_generation(kvm) >= MMIO_MAX_GEN)) {
+	if (unlikely(kvm_current_mmio_generation(kvm) == 0)) {
 		printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n");
 		kvm_mmu_invalidate_zap_all_pages(kvm);
 	}
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 8da5823bcde6..21ea4fc91b5b 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -78,15 +78,23 @@ static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu,
 	vcpu->arch.mmio_gva = gva & PAGE_MASK;
 	vcpu->arch.access = access;
 	vcpu->arch.mmio_gfn = gfn;
+	vcpu->arch.mmio_gen = kvm_memslots(vcpu->kvm)->generation;
+}
+
+static inline bool vcpu_match_mmio_gen(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.mmio_gen == kvm_memslots(vcpu->kvm)->generation;
 }
 
 /*
- * Clear the mmio cache info for the given gva,
- * specially, if gva is ~0ul, we clear all mmio cache info.
+ * Clear the mmio cache info for the given gva. If gva is MMIO_GVA_ANY, we
+ * clear all mmio cache info.
  */
+#define MMIO_GVA_ANY (~(gva_t)0)
+
 static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva)
 {
-	if (gva != (~0ul) && vcpu->arch.mmio_gva != (gva & PAGE_MASK))
+	if (gva != MMIO_GVA_ANY && vcpu->arch.mmio_gva != (gva & PAGE_MASK))
 		return;
 
 	vcpu->arch.mmio_gva = 0;
@@ -94,7 +102,8 @@ static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva)
 
 static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva)
 {
-	if (vcpu->arch.mmio_gva && vcpu->arch.mmio_gva == (gva & PAGE_MASK))
+	if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gva &&
+	      vcpu->arch.mmio_gva == (gva & PAGE_MASK))
 		return true;
 
 	return false;
@@ -102,7 +111,8 @@ static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva)
 
 static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
 {
-	if (vcpu->arch.mmio_gfn && vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT)
+	if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gfn &&
+	      vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT)
 		return true;
 
 	return false;
diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c
index 3c562f5a60bb..e1bce26cd4f9 100644
--- a/crypto/async_tx/async_xor.c
+++ b/crypto/async_tx/async_xor.c
@@ -78,8 +78,6 @@ do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap,
 		tx = dma->device_prep_dma_xor(chan, dma_dest, src_list,
 					      xor_src_cnt, unmap->len,
 					      dma_flags);
-		src_list[0] = tmp;
-
 
 		if (unlikely(!tx))
 			async_tx_quiesce(&submit->depend_tx);
@@ -92,6 +90,7 @@ do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap,
 						      xor_src_cnt, unmap->len,
 						      dma_flags);
 		}
+		src_list[0] = tmp;
 
 		dma_set_unmap(tx, unmap);
 		async_tx_submit(chan, tx, submit);
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index c30df50e4440..2495ee577a64 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -1081,6 +1081,9 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
 	if (!firmware_p)
 		return -EINVAL;
 
+	if (!name || name[0] == '\0')
+		return -EINVAL;
+
 	ret = _request_firmware_prepare(&fw, name, device);
 	if (ret <= 0) /* error or already assigned */
 		goto out;
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index c5471cd6ebb7..d39fd610aa3b 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -473,6 +473,7 @@ void regmap_debugfs_init(struct regmap *map, const char *name)
 {
 	struct rb_node *next;
 	struct regmap_range_node *range_node;
+	const char *devname = "dummy";
 
 	/* If we don't have the debugfs root yet, postpone init */
 	if (!regmap_debugfs_root) {
@@ -491,12 +492,15 @@ void regmap_debugfs_init(struct regmap *map, const char *name)
 	INIT_LIST_HEAD(&map->debugfs_off_cache);
 	mutex_init(&map->cache_lock);
 
+	if (map->dev)
+		devname = dev_name(map->dev);
+
 	if (name) {
 		map->debugfs_name = kasprintf(GFP_KERNEL, "%s-%s",
-					      dev_name(map->dev), name);
+					      devname, name);
 		name = map->debugfs_name;
 	} else {
-		name = dev_name(map->dev);
+		name = devname;
 	}
 
 	map->debugfs = debugfs_create_dir(name, regmap_debugfs_root);
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 2ea056c09aeb..f6cff3be0ed7 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -1308,7 +1308,7 @@ int _regmap_write(struct regmap *map, unsigned int reg,
 	}
 
 #ifdef LOG_DEVICE
-	if (strcmp(dev_name(map->dev), LOG_DEVICE) == 0)
+	if (map->dev && strcmp(dev_name(map->dev), LOG_DEVICE) == 0)
 		dev_info(map->dev, "%x <= %x\n", reg, val);
 #endif
 
@@ -1557,6 +1557,9 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val,
 	} else {
 		void *wval;
 
+		if (!val_count)
+			return -EINVAL;
+
 		wval = kmemdup(val, val_count * val_bytes, GFP_KERNEL);
 		if (!wval) {
 			ret = -ENOMEM;
@@ -1739,7 +1742,7 @@ static int _regmap_read(struct regmap *map, unsigned int reg,
 	ret = map->reg_read(context, reg, val);
 	if (ret == 0) {
 #ifdef LOG_DEVICE
-		if (strcmp(dev_name(map->dev), LOG_DEVICE) == 0)
+		if (map->dev && strcmp(dev_name(map->dev), LOG_DEVICE) == 0)
 			dev_info(map->dev, "%x => %x\n", reg, *val);
 #endif
 
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 1c7b5040d921..e00c3f84a4cf 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -309,6 +309,9 @@ static void btusb_intr_complete(struct urb *urb)
 			BT_ERR("%s corrupted event packet", hdev->name);
 			hdev->stat.err_rx++;
 		}
+	} else if (urb->status == -ENOENT) {
+		/* Avoid suspend failed when usb_kill_urb */
+		return;
 	}
 
 	if (!test_bit(BTUSB_INTR_RUNNING, &data->flags))
@@ -397,6 +400,9 @@ static void btusb_bulk_complete(struct urb *urb)
 			BT_ERR("%s corrupted ACL packet", hdev->name);
 			hdev->stat.err_rx++;
 		}
+	} else if (urb->status == -ENOENT) {
+		/* Avoid suspend failed when usb_kill_urb */
+		return;
 	}
 
 	if (!test_bit(BTUSB_BULK_RUNNING, &data->flags))
@@ -491,6 +497,9 @@ static void btusb_isoc_complete(struct urb *urb)
 				hdev->stat.err_rx++;
 			}
 		}
+	} else if (urb->status == -ENOENT) {
+		/* Avoid suspend failed when usb_kill_urb */
+		return;
 	}
 
 	if (!test_bit(BTUSB_ISOC_RUNNING, &data->flags))
diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index e36a0245f2c1..56519927479f 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -237,7 +237,7 @@ static void h5_pkt_cull(struct h5 *h5)
 			break;
 
 		to_remove--;
-		seq = (seq - 1) % 8;
+		seq = (seq - 1) & 0x07;
 	}
 
 	if (seq != h5->rx_ack)
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 69ea36f07b4d..e99e71a6ea59 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -164,8 +164,10 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 	ret = vmbus_post_msg(open_msg,
 			       sizeof(struct vmbus_channel_open_channel));
 
-	if (ret != 0)
+	if (ret != 0) {
+		err = ret;
 		goto error1;
+	}
 
 	t = wait_for_completion_timeout(&open_info->waitevent, 5*HZ);
 	if (t == 0) {
@@ -362,7 +364,6 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 	u32 next_gpadl_handle;
 	unsigned long flags;
 	int ret = 0;
-	int t;
 
 	next_gpadl_handle = atomic_read(&vmbus_connection.next_gpadl_handle);
 	atomic_inc(&vmbus_connection.next_gpadl_handle);
@@ -409,9 +410,7 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 
 		}
 	}
-	t = wait_for_completion_timeout(&msginfo->waitevent, 5*HZ);
-	BUG_ON(t == 0);
-
+	wait_for_completion(&msginfo->waitevent);
 
 	/* At this point, we received the gpadl created msg */
 	*gpadl_handle = gpadlmsg->gpadl;
@@ -434,7 +433,7 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 	struct vmbus_channel_gpadl_teardown *msg;
 	struct vmbus_channel_msginfo *info;
 	unsigned long flags;
-	int ret, t;
+	int ret;
 
 	info = kmalloc(sizeof(*info) +
 		       sizeof(struct vmbus_channel_gpadl_teardown), GFP_KERNEL);
@@ -456,11 +455,12 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 	ret = vmbus_post_msg(msg,
 			       sizeof(struct vmbus_channel_gpadl_teardown));
 
-	BUG_ON(ret != 0);
-	t = wait_for_completion_timeout(&info->waitevent, 5*HZ);
-	BUG_ON(t == 0);
+	if (ret)
+		goto post_msg_err;
+
+	wait_for_completion(&info->waitevent);
 
-	/* Received a torndown response */
+post_msg_err:
 	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
 	list_del(&info->msglistentry);
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
@@ -470,7 +470,7 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 }
 EXPORT_SYMBOL_GPL(vmbus_teardown_gpadl);
 
-static void vmbus_close_internal(struct vmbus_channel *channel)
+static int vmbus_close_internal(struct vmbus_channel *channel)
 {
 	struct vmbus_channel_close_channel *msg;
 	int ret;
@@ -492,11 +492,28 @@ static void vmbus_close_internal(struct vmbus_channel *channel)
 
 	ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_close_channel));
 
-	BUG_ON(ret != 0);
+	if (ret) {
+		pr_err("Close failed: close post msg return is %d\n", ret);
+		/*
+		 * If we failed to post the close msg,
+		 * it is perhaps better to leak memory.
+		 */
+		return ret;
+	}
+
 	/* Tear down the gpadl for the channel's ring buffer */
-	if (channel->ringbuffer_gpadlhandle)
-		vmbus_teardown_gpadl(channel,
-					  channel->ringbuffer_gpadlhandle);
+	if (channel->ringbuffer_gpadlhandle) {
+		ret = vmbus_teardown_gpadl(channel,
+					   channel->ringbuffer_gpadlhandle);
+		if (ret) {
+			pr_err("Close failed: teardown gpadl return %d\n", ret);
+			/*
+			 * If we failed to teardown gpadl,
+			 * it is perhaps better to leak memory.
+			 */
+			return ret;
+		}
+	}
 
 	/* Cleanup the ring buffers for this channel */
 	hv_ringbuffer_cleanup(&channel->outbound);
@@ -505,7 +522,7 @@ static void vmbus_close_internal(struct vmbus_channel *channel)
 	free_pages((unsigned long)channel->ringbuffer_pages,
 		get_order(channel->ringbuffer_pagecount * PAGE_SIZE));
 
-
+	return ret;
 }
 
 /*
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index ce5a9f2584f3..d8fd95cb0456 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -408,10 +408,21 @@ int vmbus_post_msg(void *buffer, size_t buflen)
 	 * insufficient resources. Retry the operation a couple of
 	 * times before giving up.
 	 */
-	while (retries < 3) {
-		ret =  hv_post_message(conn_id, 1, buffer, buflen);
-		if (ret != HV_STATUS_INSUFFICIENT_BUFFERS)
+	while (retries < 10) {
+		ret = hv_post_message(conn_id, 1, buffer, buflen);
+
+		switch (ret) {
+		case HV_STATUS_INSUFFICIENT_BUFFERS:
+			ret = -ENOMEM;
+		case -ENOMEM:
+			break;
+		case HV_STATUS_SUCCESS:
 			return ret;
+		default:
+			pr_err("hv_post_msg() failed; error code:%d\n", ret);
+			return -EINVAL;
+		}
+
 		retries++;
 		msleep(100);
 	}
diff --git a/drivers/message/fusion/mptspi.c b/drivers/message/fusion/mptspi.c
index 5653e505f91f..424f51d1e2ce 100644
--- a/drivers/message/fusion/mptspi.c
+++ b/drivers/message/fusion/mptspi.c
@@ -1422,6 +1422,11 @@ mptspi_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto out_mptspi_probe;
         }
 
+	/* VMWare emulation doesn't properly implement WRITE_SAME
+	 */
+	if (pdev->subsystem_vendor == 0x15AD)
+		sh->no_write_same = 1;
+
 	spin_lock_irqsave(&ioc->FreeQlock, flags);
 
 	/* Attach the SCSI Host to the IOC structure
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index 4bc7d620d695..9a07bba3ade4 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -71,7 +71,7 @@ static int mei_cl_device_probe(struct device *dev)
 
 	dev_dbg(dev, "Device probe\n");
 
-	strncpy(id.name, dev_name(dev), sizeof(id.name));
+	strlcpy(id.name, dev_name(dev), sizeof(id.name));
 
 	return driver->probe(device, &id);
 }
diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c
index df1f5e732ab5..1ac33d9cd396 100644
--- a/drivers/net/wireless/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/iwlwifi/pcie/drv.c
@@ -272,6 +272,8 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = {
 	{IWL_PCI_DEVICE(0x08B1, 0x4070, iwl7260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x08B1, 0x4072, iwl7260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x08B1, 0x4170, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4C60, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4C70, iwl7260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x08B1, 0x4060, iwl7260_2n_cfg)},
 	{IWL_PCI_DEVICE(0x08B1, 0x406A, iwl7260_2n_cfg)},
 	{IWL_PCI_DEVICE(0x08B1, 0x4160, iwl7260_2n_cfg)},
@@ -315,6 +317,8 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = {
 	{IWL_PCI_DEVICE(0x08B1, 0xC770, iwl7260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x08B1, 0xC760, iwl7260_2n_cfg)},
 	{IWL_PCI_DEVICE(0x08B2, 0xC270, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xCC70, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xCC60, iwl7260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x08B2, 0xC272, iwl7260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x08B2, 0xC260, iwl7260_2n_cfg)},
 	{IWL_PCI_DEVICE(0x08B2, 0xC26A, iwl7260_n_cfg)},
diff --git a/drivers/net/wireless/rt2x00/rt2800.h b/drivers/net/wireless/rt2x00/rt2800.h
index a394a9a95919..7cf6081a05a1 100644
--- a/drivers/net/wireless/rt2x00/rt2800.h
+++ b/drivers/net/wireless/rt2x00/rt2800.h
@@ -2039,7 +2039,7 @@ struct mac_iveiv_entry {
  * 2 - drop tx power by 12dBm,
  * 3 - increase tx power by 6dBm
  */
-#define BBP1_TX_POWER_CTRL		FIELD8(0x07)
+#define BBP1_TX_POWER_CTRL		FIELD8(0x03)
 #define BBP1_TX_ANTENNA			FIELD8(0x18)
 
 /*
diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c
index 483d9ad89705..97736674ddcd 100644
--- a/drivers/pci/host/pci-mvebu.c
+++ b/drivers/pci/host/pci-mvebu.c
@@ -855,7 +855,7 @@ static int mvebu_get_tgt_attr(struct device_node *np, int devfn,
 	rangesz = pna + na + ns;
 	nranges = rlen / sizeof(__be32) / rangesz;
 
-	for (i = 0; i < nranges; i++) {
+	for (i = 0; i < nranges; i++, range += rangesz) {
 		u32 flags = of_read_number(range, 1);
 		u32 slot = of_read_number(range + 1, 1);
 		u64 cpuaddr = of_read_number(range + na, pna);
@@ -865,14 +865,14 @@ static int mvebu_get_tgt_attr(struct device_node *np, int devfn,
 			rtype = IORESOURCE_IO;
 		else if (DT_FLAGS_TO_TYPE(flags) == DT_TYPE_MEM32)
 			rtype = IORESOURCE_MEM;
+		else
+			continue;
 
 		if (slot == PCI_SLOT(devfn) && type == rtype) {
 			*tgt = DT_CPUADDR_TO_TARGET(cpuaddr);
 			*attr = DT_CPUADDR_TO_ATTR(cpuaddr);
 			return 0;
 		}
-
-		range += rangesz;
 	}
 
 	return -ENOENT;
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 276ef9c18802..39a207abaa10 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -178,7 +178,7 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 
-	return sprintf(buf, "pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02x\n",
+	return sprintf(buf, "pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02X\n",
 		       pci_dev->vendor, pci_dev->device,
 		       pci_dev->subsystem_vendor, pci_dev->subsystem_device,
 		       (u8)(pci_dev->class >> 16), (u8)(pci_dev->class >> 8),
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 813f437f3ee8..6e8776b59a2c 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -24,6 +24,7 @@
 #include <linux/ioport.h>
 #include <linux/sched.h>
 #include <linux/ktime.h>
+#include <linux/mm.h>
 #include <asm/dma.h>	/* isa_dma_bridge_buggy */
 #include "pci.h"
 
@@ -287,6 +288,25 @@ static void quirk_citrine(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM,	PCI_DEVICE_ID_IBM_CITRINE,	quirk_citrine);
 
+/*  On IBM Crocodile ipr SAS adapters, expand BAR to system page size */
+static void quirk_extend_bar_to_page(struct pci_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < PCI_STD_RESOURCE_END; i++) {
+		struct resource *r = &dev->resource[i];
+
+		if (r->flags & IORESOURCE_MEM && resource_size(r) < PAGE_SIZE) {
+			r->end = PAGE_SIZE - 1;
+			r->start = 0;
+			r->flags |= IORESOURCE_UNSET;
+			dev_info(&dev->dev, "expanded BAR %d to page size: %pR\n",
+				 i, r);
+		}
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM, 0x034a, quirk_extend_bar_to_page);
+
 /*
  *  S3 868 and 968 chips report region size equal to 32M, but they decode 64M.
  *  If it's needed, re-allocate the region.
diff --git a/drivers/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c
index b2fcac78feaa..5bb9406688c9 100644
--- a/drivers/scsi/be2iscsi/be_mgmt.c
+++ b/drivers/scsi/be2iscsi/be_mgmt.c
@@ -897,17 +897,20 @@ mgmt_static_ip_modify(struct beiscsi_hba *phba,
 
 	if (ip_action == IP_ACTION_ADD) {
 		memcpy(req->ip_params.ip_record.ip_addr.addr, ip_param->value,
-		       ip_param->len);
+		       sizeof(req->ip_params.ip_record.ip_addr.addr));
 
 		if (subnet_param)
 			memcpy(req->ip_params.ip_record.ip_addr.subnet_mask,
-			       subnet_param->value, subnet_param->len);
+			       subnet_param->value,
+			       sizeof(req->ip_params.ip_record.ip_addr.subnet_mask));
 	} else {
 		memcpy(req->ip_params.ip_record.ip_addr.addr,
-		       if_info->ip_addr.addr, ip_param->len);
+		       if_info->ip_addr.addr,
+		       sizeof(req->ip_params.ip_record.ip_addr.addr));
 
 		memcpy(req->ip_params.ip_record.ip_addr.subnet_mask,
-		       if_info->ip_addr.subnet_mask, ip_param->len);
+		       if_info->ip_addr.subnet_mask,
+		       sizeof(req->ip_params.ip_record.ip_addr.subnet_mask));
 	}
 
 	rc = mgmt_exec_nonemb_cmd(phba, &nonemb_cmd, NULL, 0);
@@ -935,7 +938,7 @@ static int mgmt_modify_gateway(struct beiscsi_hba *phba, uint8_t *gt_addr,
 	req->action = gtway_action;
 	req->ip_addr.ip_type = BE2_IPV4;
 
-	memcpy(req->ip_addr.addr, gt_addr, param_len);
+	memcpy(req->ip_addr.addr, gt_addr, sizeof(req->ip_addr.addr));
 
 	return mgmt_exec_nonemb_cmd(phba, &nonemb_cmd, NULL, 0);
 }
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 83cb61266979..23c1b0cd3074 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -3039,10 +3039,8 @@ qla2x00_unmap_iobases(struct qla_hw_data *ha)
 }
 
 static void
-qla2x00_clear_drv_active(scsi_qla_host_t *vha)
+qla2x00_clear_drv_active(struct qla_hw_data *ha)
 {
-	struct qla_hw_data *ha = vha->hw;
-
 	if (IS_QLA8044(ha)) {
 		qla8044_idc_lock(ha);
 		qla8044_clear_drv_active(ha);
@@ -3111,7 +3109,7 @@ qla2x00_remove_one(struct pci_dev *pdev)
 
 	scsi_host_put(base_vha->host);
 
-	qla2x00_clear_drv_active(base_vha);
+	qla2x00_clear_drv_active(ha);
 
 	qla2x00_unmap_iobases(ha);
 
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 0cb73074c199..2f264ac79546 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1382,12 +1382,10 @@ static inline void qlt_unmap_sg(struct scsi_qla_host *vha,
 static int qlt_check_reserve_free_req(struct scsi_qla_host *vha,
 	uint32_t req_cnt)
 {
-	struct qla_hw_data *ha = vha->hw;
-	device_reg_t __iomem *reg = ha->iobase;
 	uint32_t cnt;
 
 	if (vha->req->cnt < (req_cnt + 2)) {
-		cnt = (uint16_t)RD_REG_DWORD(&reg->isp24.req_q_out);
+		cnt = (uint16_t)RD_REG_DWORD(vha->req->req_q_out);
 
 		ql_dbg(ql_dbg_tgt, vha, 0xe00a,
 		    "Request ring circled: cnt=%d, vha->->ring_index=%d, "
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
index 6d207afec8cb..a4c45ea8f688 100644
--- a/drivers/spi/spi-dw-mid.c
+++ b/drivers/spi/spi-dw-mid.c
@@ -89,7 +89,13 @@ err_exit:
 
 static void mid_spi_dma_exit(struct dw_spi *dws)
 {
+	if (!dws->dma_inited)
+		return;
+
+	dmaengine_terminate_all(dws->txchan);
 	dma_release_channel(dws->txchan);
+
+	dmaengine_terminate_all(dws->rxchan);
 	dma_release_channel(dws->rxchan);
 }
 
@@ -136,7 +142,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change)
 	txconf.dst_addr = dws->dma_addr;
 	txconf.dst_maxburst = LNW_DMA_MSIZE_16;
 	txconf.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
-	txconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+	txconf.dst_addr_width = dws->dma_width;
 	txconf.device_fc = false;
 
 	txchan->device->device_control(txchan, DMA_SLAVE_CONFIG,
@@ -159,7 +165,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change)
 	rxconf.src_addr = dws->dma_addr;
 	rxconf.src_maxburst = LNW_DMA_MSIZE_16;
 	rxconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
-	rxconf.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+	rxconf.src_addr_width = dws->dma_width;
 	rxconf.device_fc = false;
 
 	rxchan->device->device_control(rxchan, DMA_SLAVE_CONFIG,
diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index db8434d3def9..f4e68b3fc39d 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -260,8 +260,16 @@ serial_omap_baud_is_mode16(struct uart_port *port, unsigned int baud)
 {
 	unsigned int n13 = port->uartclk / (13 * baud);
 	unsigned int n16 = port->uartclk / (16 * baud);
-	int baudAbsDiff13 = baud - (port->uartclk / (13 * n13));
-	int baudAbsDiff16 = baud - (port->uartclk / (16 * n16));
+	int baudAbsDiff13;
+	int baudAbsDiff16;
+
+	if (n13 == 0)
+		n13 = 1;
+	if (n16 == 0)
+		n16 = 1;
+
+	baudAbsDiff13 = baud - (port->uartclk / (13 * n13));
+	baudAbsDiff16 = baud - (port->uartclk / (16 * n16));
 	if (baudAbsDiff13 < 0)
 		baudAbsDiff13 = -baudAbsDiff13;
 	if (baudAbsDiff16 < 0)
diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig
index 8154165aa601..fd13ef0a96c9 100644
--- a/drivers/usb/gadget/Kconfig
+++ b/drivers/usb/gadget/Kconfig
@@ -445,7 +445,7 @@ config USB_GOKU
 	   gadget drivers to also be dynamically linked.
 
 config USB_EG20T
-	tristate "Intel EG20T PCH/LAPIS Semiconductor IOH(ML7213/ML7831) UDC"
+	tristate "Intel QUARK X1000/EG20T PCH/LAPIS Semiconductor IOH(ML7213/ML7831) UDC"
 	depends on PCI
 	help
 	  This is a USB device driver for EG20T PCH.
@@ -466,6 +466,7 @@ config USB_EG20T
 	  ML7213/ML7831 is companion chip for Intel Atom E6xx series.
 	  ML7213/ML7831 is completely compatible for Intel EG20T PCH.
 
+	  This driver can be used with Intel's Quark X1000 SOC platform
 #
 # LAST -- dummy/emulated controller
 #
diff --git a/drivers/usb/gadget/pch_udc.c b/drivers/usb/gadget/pch_udc.c
index eb8c3bedb57a..460d953c91b6 100644
--- a/drivers/usb/gadget/pch_udc.c
+++ b/drivers/usb/gadget/pch_udc.c
@@ -343,6 +343,7 @@ struct pch_vbus_gpio_data {
  * @setup_data:		Received setup data
  * @phys_addr:		of device memory
  * @base_addr:		for mapped device memory
+ * @bar:		Indicates which PCI BAR for USB regs
  * @irq:		IRQ line for the device
  * @cfg_data:		current cfg, intf, and alt in use
  * @vbus_gpio:		GPIO informaton for detecting VBUS
@@ -370,14 +371,17 @@ struct pch_udc_dev {
 	struct usb_ctrlrequest		setup_data;
 	unsigned long			phys_addr;
 	void __iomem			*base_addr;
+	unsigned			bar;
 	unsigned			irq;
 	struct pch_udc_cfg_data		cfg_data;
 	struct pch_vbus_gpio_data	vbus_gpio;
 };
 #define to_pch_udc(g)	(container_of((g), struct pch_udc_dev, gadget))
 
+#define PCH_UDC_PCI_BAR_QUARK_X1000	0
 #define PCH_UDC_PCI_BAR			1
 #define PCI_DEVICE_ID_INTEL_EG20T_UDC	0x8808
+#define PCI_DEVICE_ID_INTEL_QUARK_X1000_UDC	0x0939
 #define PCI_VENDOR_ID_ROHM		0x10DB
 #define PCI_DEVICE_ID_ML7213_IOH_UDC	0x801D
 #define PCI_DEVICE_ID_ML7831_IOH_UDC	0x8808
@@ -3076,7 +3080,7 @@ static void pch_udc_remove(struct pci_dev *pdev)
 		iounmap(dev->base_addr);
 	if (dev->mem_region)
 		release_mem_region(dev->phys_addr,
-				   pci_resource_len(pdev, PCH_UDC_PCI_BAR));
+				   pci_resource_len(pdev, dev->bar));
 	if (dev->active)
 		pci_disable_device(pdev);
 	kfree(dev);
@@ -3144,9 +3148,15 @@ static int pch_udc_probe(struct pci_dev *pdev,
 	dev->active = 1;
 	pci_set_drvdata(pdev, dev);
 
+	/* Determine BAR based on PCI ID */
+	if (id->device == PCI_DEVICE_ID_INTEL_QUARK_X1000_UDC)
+		dev->bar = PCH_UDC_PCI_BAR_QUARK_X1000;
+	else
+		dev->bar = PCH_UDC_PCI_BAR;
+
 	/* PCI resource allocation */
-	resource = pci_resource_start(pdev, 1);
-	len = pci_resource_len(pdev, 1);
+	resource = pci_resource_start(pdev, dev->bar);
+	len = pci_resource_len(pdev, dev->bar);
 
 	if (!request_mem_region(resource, len, KBUILD_MODNAME)) {
 		dev_err(&pdev->dev, "%s: pci device used already\n", __func__);
@@ -3212,6 +3222,12 @@ finished:
 
 static const struct pci_device_id pch_udc_pcidev_id[] = {
 	{
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL,
+			   PCI_DEVICE_ID_INTEL_QUARK_X1000_UDC),
+		.class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe,
+		.class_mask = 0xffffffff,
+	},
+	{
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_EG20T_UDC),
 		.class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe,
 		.class_mask = 0xffffffff,
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 0165b8672f09..a9a881ed8cbe 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2510,23 +2510,28 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct extent_map *em = NULL;
 	struct extent_state *cached_state = NULL;
-	u64 lockstart = *offset;
-	u64 lockend = i_size_read(inode);
-	u64 start = *offset;
-	u64 len = i_size_read(inode);
+	u64 lockstart;
+	u64 lockend;
+	u64 start;
+	u64 len;
 	int ret = 0;
 
-	lockend = max_t(u64, root->sectorsize, lockend);
+	if (inode->i_size == 0)
+		return -ENXIO;
+
+	/*
+	 * *offset can be negative, in this case we start finding DATA/HOLE from
+	 * the very start of the file.
+	 */
+	start = max_t(loff_t, 0, *offset);
+
+	lockstart = round_down(start, root->sectorsize);
+	lockend = round_up(i_size_read(inode), root->sectorsize);
 	if (lockend <= lockstart)
 		lockend = lockstart + root->sectorsize;
-
 	lockend--;
 	len = lockend - lockstart + 1;
 
-	len = max_t(u64, len, root->sectorsize);
-	if (inode->i_size == 0)
-		return -ENXIO;
-
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, 0,
 			 &cached_state);
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index c69c76351f12..d68a7250f00b 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3596,7 +3596,8 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans,
 	 * without delay
 	 */
 	if (!btrfs_is_free_space_inode(inode)
-	    && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) {
+	    && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
+	    && !root->fs_info->log_root_recovering) {
 		btrfs_update_root_times(trans, root);
 
 		ret = btrfs_delayed_update_inode(trans, root, inode);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index a6d8efa46bfe..0b72006aecbe 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -302,6 +302,9 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 			goto out_drop;
 
 	} else {
+		ret = btrfs_set_prop(inode, "btrfs.compression", NULL, 0, 0);
+		if (ret && ret != -ENODATA)
+			goto out_drop;
 		ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
 	}
 
@@ -4750,6 +4753,12 @@ long btrfs_ioctl(struct file *file, unsigned int
 		if (ret)
 			return ret;
 		ret = btrfs_sync_fs(file->f_dentry->d_sb, 1);
+		/*
+		 * The transaction thread may want to do more work,
+		 * namely it pokes the cleaner ktread that will start
+		 * processing uncleaned subvols.
+		 */
+		wake_up_process(root->fs_info->transaction_kthread);
 		return ret;
 	}
 	case BTRFS_IOC_START_SYNC:
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 07b3b36f40ee..01f977e3ce09 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -736,7 +736,8 @@ again:
 		err = ret;
 		goto out;
 	}
-	BUG_ON(!ret || !path1->slots[0]);
+	ASSERT(ret);
+	ASSERT(path1->slots[0]);
 
 	path1->slots[0]--;
 
@@ -746,10 +747,10 @@ again:
 		 * the backref was added previously when processing
 		 * backref of type BTRFS_TREE_BLOCK_REF_KEY
 		 */
-		BUG_ON(!list_is_singular(&cur->upper));
+		ASSERT(list_is_singular(&cur->upper));
 		edge = list_entry(cur->upper.next, struct backref_edge,
 				  list[LOWER]);
-		BUG_ON(!list_empty(&edge->list[UPPER]));
+		ASSERT(list_empty(&edge->list[UPPER]));
 		exist = edge->node[UPPER];
 		/*
 		 * add the upper level block to pending list if we need
@@ -831,7 +832,7 @@ again:
 					cur->cowonly = 1;
 			}
 #else
-		BUG_ON(key.type == BTRFS_EXTENT_REF_V0_KEY);
+		ASSERT(key.type != BTRFS_EXTENT_REF_V0_KEY);
 		if (key.type == BTRFS_SHARED_BLOCK_REF_KEY) {
 #endif
 			if (key.objectid == key.offset) {
@@ -840,7 +841,7 @@ again:
 				 * backref of this type.
 				 */
 				root = find_reloc_root(rc, cur->bytenr);
-				BUG_ON(!root);
+				ASSERT(root);
 				cur->root = root;
 				break;
 			}
@@ -868,7 +869,7 @@ again:
 			} else {
 				upper = rb_entry(rb_node, struct backref_node,
 						 rb_node);
-				BUG_ON(!upper->checked);
+				ASSERT(upper->checked);
 				INIT_LIST_HEAD(&edge->list[UPPER]);
 			}
 			list_add_tail(&edge->list[LOWER], &cur->upper);
@@ -892,7 +893,7 @@ again:
 
 		if (btrfs_root_level(&root->root_item) == cur->level) {
 			/* tree root */
-			BUG_ON(btrfs_root_bytenr(&root->root_item) !=
+			ASSERT(btrfs_root_bytenr(&root->root_item) ==
 			       cur->bytenr);
 			if (should_ignore_root(root))
 				list_add(&cur->list, &useless);
@@ -927,7 +928,7 @@ again:
 		need_check = true;
 		for (; level < BTRFS_MAX_LEVEL; level++) {
 			if (!path2->nodes[level]) {
-				BUG_ON(btrfs_root_bytenr(&root->root_item) !=
+				ASSERT(btrfs_root_bytenr(&root->root_item) ==
 				       lower->bytenr);
 				if (should_ignore_root(root))
 					list_add(&lower->list, &useless);
@@ -976,12 +977,15 @@ again:
 					need_check = false;
 					list_add_tail(&edge->list[UPPER],
 						      &list);
-				} else
+				} else {
+					if (upper->checked)
+						need_check = true;
 					INIT_LIST_HEAD(&edge->list[UPPER]);
+				}
 			} else {
 				upper = rb_entry(rb_node, struct backref_node,
 						 rb_node);
-				BUG_ON(!upper->checked);
+				ASSERT(upper->checked);
 				INIT_LIST_HEAD(&edge->list[UPPER]);
 				if (!upper->owner)
 					upper->owner = btrfs_header_owner(eb);
@@ -1025,7 +1029,7 @@ next:
 	 * everything goes well, connect backref nodes and insert backref nodes
 	 * into the cache.
 	 */
-	BUG_ON(!node->checked);
+	ASSERT(node->checked);
 	cowonly = node->cowonly;
 	if (!cowonly) {
 		rb_node = tree_insert(&cache->rb_root, node->bytenr,
@@ -1061,8 +1065,21 @@ next:
 			continue;
 		}
 
-		BUG_ON(!upper->checked);
-		BUG_ON(cowonly != upper->cowonly);
+		if (!upper->checked) {
+			/*
+			 * Still want to blow up for developers since this is a
+			 * logic bug.
+			 */
+			ASSERT(0);
+			err = -EINVAL;
+			goto out;
+		}
+		if (cowonly != upper->cowonly) {
+			ASSERT(0);
+			err = -EINVAL;
+			goto out;
+		}
+
 		if (!cowonly) {
 			rb_node = tree_insert(&cache->rb_root, upper->bytenr,
 					      &upper->rb_node);
@@ -1085,7 +1102,7 @@ next:
 	while (!list_empty(&useless)) {
 		upper = list_entry(useless.next, struct backref_node, list);
 		list_del_init(&upper->list);
-		BUG_ON(!list_empty(&upper->upper));
+		ASSERT(list_empty(&upper->upper));
 		if (upper == node)
 			node = NULL;
 		if (upper->lowest) {
@@ -1118,29 +1135,45 @@ out:
 	if (err) {
 		while (!list_empty(&useless)) {
 			lower = list_entry(useless.next,
-					   struct backref_node, upper);
-			list_del_init(&lower->upper);
+					   struct backref_node, list);
+			list_del_init(&lower->list);
 		}
-		upper = node;
-		INIT_LIST_HEAD(&list);
-		while (upper) {
-			if (RB_EMPTY_NODE(&upper->rb_node)) {
-				list_splice_tail(&upper->upper, &list);
-				free_backref_node(cache, upper);
-			}
-
-			if (list_empty(&list))
-				break;
-
-			edge = list_entry(list.next, struct backref_edge,
-					  list[LOWER]);
+		while (!list_empty(&list)) {
+			edge = list_first_entry(&list, struct backref_edge,
+						list[UPPER]);
+			list_del(&edge->list[UPPER]);
 			list_del(&edge->list[LOWER]);
+			lower = edge->node[LOWER];
 			upper = edge->node[UPPER];
 			free_backref_edge(cache, edge);
+
+			/*
+			 * Lower is no longer linked to any upper backref nodes
+			 * and isn't in the cache, we can free it ourselves.
+			 */
+			if (list_empty(&lower->upper) &&
+			    RB_EMPTY_NODE(&lower->rb_node))
+				list_add(&lower->list, &useless);
+
+			if (!RB_EMPTY_NODE(&upper->rb_node))
+				continue;
+
+			/* Add this guy's upper edges to the list to proces */
+			list_for_each_entry(edge, &upper->upper, list[LOWER])
+				list_add_tail(&edge->list[UPPER], &list);
+			if (list_empty(&upper->upper))
+				list_add(&upper->list, &useless);
+		}
+
+		while (!list_empty(&useless)) {
+			lower = list_entry(useless.next,
+					   struct backref_node, list);
+			list_del_init(&lower->list);
+			free_backref_node(cache, lower);
 		}
 		return ERR_PTR(err);
 	}
-	BUG_ON(node && node->detached);
+	ASSERT(!node || !node->detached);
 	return node;
 }
 
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index a65ed4cb436b..20d793542096 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -4728,7 +4728,9 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 
 	if (S_ISREG(sctx->cur_inode_mode)) {
 		if (need_send_hole(sctx)) {
-			if (sctx->cur_inode_last_extent == (u64)-1) {
+			if (sctx->cur_inode_last_extent == (u64)-1 ||
+			    sctx->cur_inode_last_extent <
+			    sctx->cur_inode_size) {
 				ret = get_last_extent(sctx, (u64)-1);
 				if (ret)
 					goto out;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index b05bf58b9395..a0b65a01fed7 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -592,7 +592,6 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid)
 		if (transid <= root->fs_info->last_trans_committed)
 			goto out;
 
-		ret = -EINVAL;
 		/* find specified transaction */
 		spin_lock(&root->fs_info->trans_lock);
 		list_for_each_entry(t, &root->fs_info->trans_list, list) {
@@ -608,9 +607,16 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid)
 			}
 		}
 		spin_unlock(&root->fs_info->trans_lock);
-		/* The specified transaction doesn't exist */
-		if (!cur_trans)
+
+		/*
+		 * The specified transaction doesn't exist, or we
+		 * raced with btrfs_commit_transaction
+		 */
+		if (!cur_trans) {
+			if (transid > root->fs_info->last_trans_committed)
+				ret = -EINVAL;
 			goto out;
+		}
 	} else {
 		/* find newest transaction that is committing | committed */
 		spin_lock(&root->fs_info->trans_lock);
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index b167ca48b8ee..a85ceb7c91bc 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -1039,7 +1039,7 @@ ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 	}
 
 	rc = vfs_setxattr(lower_dentry, name, value, size, flags);
-	if (!rc)
+	if (!rc && dentry->d_inode)
 		fsstack_copy_attr_all(dentry->d_inode, lower_dentry->d_inode);
 out:
 	return rc;
diff --git a/fs/namespace.c b/fs/namespace.c
index 75536db4b69b..c7d4a0ae2c65 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1365,6 +1365,8 @@ static int do_umount(struct mount *mnt, int flags)
 		 * Special case for "unmounting" root ...
 		 * we just try to remount it readonly.
 		 */
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
 		down_write(&sb->s_umount);
 		if (!(sb->s_flags & MS_RDONLY))
 			retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 2e9662ea5451..da657b7804a5 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7242,7 +7242,7 @@ static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cr
 	int ret = 0;
 
 	if ((renew_flags & NFS4_RENEW_TIMEOUT) == 0)
-		return 0;
+		return -EAGAIN;
 	task = _nfs41_proc_sequence(clp, cred, false);
 	if (IS_ERR(task))
 		ret = PTR_ERR(task);
diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c
index 1720d32ffa54..e1ba58c3d1ad 100644
--- a/fs/nfs/nfs4renewd.c
+++ b/fs/nfs/nfs4renewd.c
@@ -88,10 +88,18 @@ nfs4_renew_state(struct work_struct *work)
 			}
 			nfs_expire_all_delegations(clp);
 		} else {
+			int ret;
+
 			/* Queue an asynchronous RENEW. */
-			ops->sched_state_renewal(clp, cred, renew_flags);
+			ret = ops->sched_state_renewal(clp, cred, renew_flags);
 			put_rpccred(cred);
-			goto out_exp;
+			switch (ret) {
+			default:
+				goto out_exp;
+			case -EAGAIN:
+			case -ENOMEM:
+				break;
+			}
 		}
 	} else {
 		dprintk("%s: failed to call renewd. Reason: lease not expired \n",
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 27f5f858502b..b4f177f1d405 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1732,7 +1732,8 @@ restart:
 			if (status < 0) {
 				set_bit(ops->owner_flag_bit, &sp->so_flags);
 				nfs4_put_state_owner(sp);
-				return nfs4_recovery_handle_error(clp, status);
+				status = nfs4_recovery_handle_error(clp, status);
+				return (status != 0) ? status : -EAGAIN;
 			}
 
 			nfs4_put_state_owner(sp);
@@ -1741,7 +1742,7 @@ restart:
 		spin_unlock(&clp->cl_lock);
 	}
 	rcu_read_unlock();
-	return status;
+	return 0;
 }
 
 static int nfs4_check_lease(struct nfs_client *clp)
@@ -1788,7 +1789,6 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
 		break;
 	case -NFS4ERR_STALE_CLIENTID:
 		clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
-		nfs4_state_clear_reclaim_reboot(clp);
 		nfs4_state_start_reclaim_reboot(clp);
 		break;
 	case -NFS4ERR_CLID_INUSE:
@@ -2370,6 +2370,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			status = nfs4_check_lease(clp);
 			if (status < 0)
 				goto out_error;
+			continue;
 		}
 
 		if (test_and_clear_bit(NFS4CLNT_MOVED, &clp->cl_state)) {
@@ -2391,14 +2392,11 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			section = "reclaim reboot";
 			status = nfs4_do_reclaim(clp,
 				clp->cl_mvops->reboot_recovery_ops);
-			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
-			    test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state))
-				continue;
-			nfs4_state_end_reclaim_reboot(clp);
-			if (test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state))
+			if (status == -EAGAIN)
 				continue;
 			if (status < 0)
 				goto out_error;
+			nfs4_state_end_reclaim_reboot(clp);
 		}
 
 		/* Now recover expired state... */
@@ -2406,9 +2404,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			section = "reclaim nograce";
 			status = nfs4_do_reclaim(clp,
 				clp->cl_mvops->nograce_recovery_ops);
-			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
-			    test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) ||
-			    test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state))
+			if (status == -EAGAIN)
 				continue;
 			if (status < 0)
 				goto out_error;
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 287a22c04149..de6323eb0113 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -71,7 +71,7 @@ static int create_fd(struct fsnotify_group *group,
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
-	client_fd = get_unused_fd();
+	client_fd = get_unused_fd_flags(group->fanotify_data.f_flags);
 	if (client_fd < 0)
 		return client_fd;
 
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 5d2518b24cea..0461fbe405b7 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -434,10 +434,22 @@ xfs_start_page_writeback(
 {
 	ASSERT(PageLocked(page));
 	ASSERT(!PageWriteback(page));
-	if (clear_dirty)
+
+	/*
+	 * if the page was not fully cleaned, we need to ensure that the higher
+	 * layers come back to it correctly. That means we need to keep the page
+	 * dirty, and for WB_SYNC_ALL writeback we need to ensure the
+	 * PAGECACHE_TAG_TOWRITE index mark is not removed so another attempt to
+	 * write this page in this writeback sweep will be made.
+	 */
+	if (clear_dirty) {
 		clear_page_dirty_for_io(page);
-	set_page_writeback(page);
+		set_page_writeback(page);
+	} else
+		set_page_writeback_keepwrite(page);
+
 	unlock_page(page);
+
 	/* If no buffers on the page are to be written, finish it here */
 	if (!buffers)
 		end_page_writeback(page);
diff --git a/include/linux/compiler-gcc5.h b/include/linux/compiler-gcc5.h
new file mode 100644
index 000000000000..cdd1cc202d51
--- /dev/null
+++ b/include/linux/compiler-gcc5.h
@@ -0,0 +1,66 @@
+#ifndef __LINUX_COMPILER_H
+#error "Please don't include <linux/compiler-gcc5.h> directly, include <linux/compiler.h> instead."
+#endif
+
+#define __used				__attribute__((__used__))
+#define __must_check			__attribute__((warn_unused_result))
+#define __compiler_offsetof(a, b)	__builtin_offsetof(a, b)
+
+/* Mark functions as cold. gcc will assume any path leading to a call
+   to them will be unlikely.  This means a lot of manual unlikely()s
+   are unnecessary now for any paths leading to the usual suspects
+   like BUG(), printk(), panic() etc. [but let's keep them for now for
+   older compilers]
+
+   Early snapshots of gcc 4.3 don't support this and we can't detect this
+   in the preprocessor, but we can live with this because they're unreleased.
+   Maketime probing would be overkill here.
+
+   gcc also has a __attribute__((__hot__)) to move hot functions into
+   a special section, but I don't see any sense in this right now in
+   the kernel context */
+#define __cold			__attribute__((__cold__))
+
+#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
+
+#ifndef __CHECKER__
+# define __compiletime_warning(message) __attribute__((warning(message)))
+# define __compiletime_error(message) __attribute__((error(message)))
+#endif /* __CHECKER__ */
+
+/*
+ * Mark a position in code as unreachable.  This can be used to
+ * suppress control flow warnings after asm blocks that transfer
+ * control elsewhere.
+ *
+ * Early snapshots of gcc 4.5 don't support this and we can't detect
+ * this in the preprocessor, but we can live with this because they're
+ * unreleased.  Really, we need to have autoconf for the kernel.
+ */
+#define unreachable() __builtin_unreachable()
+
+/* Mark a function definition as prohibited from being cloned. */
+#define __noclone	__attribute__((__noclone__))
+
+/*
+ * Tell the optimizer that something else uses this function or variable.
+ */
+#define __visible __attribute__((externally_visible))
+
+/*
+ * GCC 'asm goto' miscompiles certain code sequences:
+ *
+ *   http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670
+ *
+ * Work it around via a compiler barrier quirk suggested by Jakub Jelinek.
+ * Fixed in GCC 4.8.2 and later versions.
+ *
+ * (asm goto is automatically volatile - the naming reflects this.)
+ */
+#define asm_volatile_goto(x...)	do { asm goto(x); asm (""); } while (0)
+
+#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP
+#define __HAVE_BUILTIN_BSWAP32__
+#define __HAVE_BUILTIN_BSWAP64__
+#define __HAVE_BUILTIN_BSWAP16__
+#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 97fbecdd7a40..057c1d8c77e5 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2551,6 +2551,7 @@
 #define PCI_DEVICE_ID_INTEL_MFD_EMMC0	0x0823
 #define PCI_DEVICE_ID_INTEL_MFD_EMMC1	0x0824
 #define PCI_DEVICE_ID_INTEL_MRST_SD2	0x084F
+#define PCI_DEVICE_ID_INTEL_QUARK_X1000_ILB	0x095E
 #define PCI_DEVICE_ID_INTEL_I960	0x0960
 #define PCI_DEVICE_ID_INTEL_I960RM	0x0962
 #define PCI_DEVICE_ID_INTEL_CENTERTON_ILB	0x0c60
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d7ca410ace93..218b058060f1 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1876,11 +1876,13 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
 #define used_math() tsk_used_math(current)
 
-/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags */
+/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags
+ * __GFP_FS is also cleared as it implies __GFP_IO.
+ */
 static inline gfp_t memalloc_noio_flags(gfp_t flags)
 {
 	if (unlikely(current->flags & PF_MEMALLOC_NOIO))
-		flags &= ~__GFP_IO;
+		flags &= ~(__GFP_IO | __GFP_FS);
 	return flags;
 }
 
diff --git a/kernel/futex.c b/kernel/futex.c
index 0b0dc02aabce..fda2950f2ce4 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -329,6 +329,8 @@ static void get_futex_key_refs(union futex_key *key)
 	case FUT_OFF_MMSHARED:
 		futex_get_mm(key); /* implies MB (B) */
 		break;
+	default:
+		smp_mb(); /* explicit MB (B) */
 	}
 }
 
diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c
index 8563081e8da3..a1c387f6afba 100644
--- a/lib/lzo/lzo1x_decompress_safe.c
+++ b/lib/lzo/lzo1x_decompress_safe.c
@@ -19,31 +19,21 @@
 #include <linux/lzo.h>
 #include "lzodefs.h"
 
-#define HAVE_IP(t, x)					\
-	(((size_t)(ip_end - ip) >= (size_t)(t + x)) &&	\
-	 (((t + x) >= t) && ((t + x) >= x)))
+#define HAVE_IP(x)      ((size_t)(ip_end - ip) >= (size_t)(x))
+#define HAVE_OP(x)      ((size_t)(op_end - op) >= (size_t)(x))
+#define NEED_IP(x)      if (!HAVE_IP(x)) goto input_overrun
+#define NEED_OP(x)      if (!HAVE_OP(x)) goto output_overrun
+#define TEST_LB(m_pos)  if ((m_pos) < out) goto lookbehind_overrun
 
-#define HAVE_OP(t, x)					\
-	(((size_t)(op_end - op) >= (size_t)(t + x)) &&	\
-	 (((t + x) >= t) && ((t + x) >= x)))
-
-#define NEED_IP(t, x)					\
-	do {						\
-		if (!HAVE_IP(t, x))			\
-			goto input_overrun;		\
-	} while (0)
-
-#define NEED_OP(t, x)					\
-	do {						\
-		if (!HAVE_OP(t, x))			\
-			goto output_overrun;		\
-	} while (0)
-
-#define TEST_LB(m_pos)					\
-	do {						\
-		if ((m_pos) < out)			\
-			goto lookbehind_overrun;	\
-	} while (0)
+/* This MAX_255_COUNT is the maximum number of times we can add 255 to a base
+ * count without overflowing an integer. The multiply will overflow when
+ * multiplying 255 by more than MAXINT/255. The sum will overflow earlier
+ * depending on the base count. Since the base count is taken from a u8
+ * and a few bits, it is safe to assume that it will always be lower than
+ * or equal to 2*255, thus we can always prevent any overflow by accepting
+ * two less 255 steps. See Documentation/lzo.txt for more information.
+ */
+#define MAX_255_COUNT      ((((size_t)~0) / 255) - 2)
 
 int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
 			  unsigned char *out, size_t *out_len)
@@ -75,17 +65,24 @@ int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
 		if (t < 16) {
 			if (likely(state == 0)) {
 				if (unlikely(t == 0)) {
+					size_t offset;
+					const unsigned char *ip_last = ip;
+
 					while (unlikely(*ip == 0)) {
-						t += 255;
 						ip++;
-						NEED_IP(1, 0);
+						NEED_IP(1);
 					}
-					t += 15 + *ip++;
+					offset = ip - ip_last;
+					if (unlikely(offset > MAX_255_COUNT))
+						return LZO_E_ERROR;
+
+					offset = (offset << 8) - offset;
+					t += offset + 15 + *ip++;
 				}
 				t += 3;
 copy_literal_run:
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
-				if (likely(HAVE_IP(t, 15) && HAVE_OP(t, 15))) {
+				if (likely(HAVE_IP(t + 15) && HAVE_OP(t + 15))) {
 					const unsigned char *ie = ip + t;
 					unsigned char *oe = op + t;
 					do {
@@ -101,8 +98,8 @@ copy_literal_run:
 				} else
 #endif
 				{
-					NEED_OP(t, 0);
-					NEED_IP(t, 3);
+					NEED_OP(t);
+					NEED_IP(t + 3);
 					do {
 						*op++ = *ip++;
 					} while (--t > 0);
@@ -115,7 +112,7 @@ copy_literal_run:
 				m_pos -= t >> 2;
 				m_pos -= *ip++ << 2;
 				TEST_LB(m_pos);
-				NEED_OP(2, 0);
+				NEED_OP(2);
 				op[0] = m_pos[0];
 				op[1] = m_pos[1];
 				op += 2;
@@ -136,13 +133,20 @@ copy_literal_run:
 		} else if (t >= 32) {
 			t = (t & 31) + (3 - 1);
 			if (unlikely(t == 2)) {
+				size_t offset;
+				const unsigned char *ip_last = ip;
+
 				while (unlikely(*ip == 0)) {
-					t += 255;
 					ip++;
-					NEED_IP(1, 0);
+					NEED_IP(1);
 				}
-				t += 31 + *ip++;
-				NEED_IP(2, 0);
+				offset = ip - ip_last;
+				if (unlikely(offset > MAX_255_COUNT))
+					return LZO_E_ERROR;
+
+				offset = (offset << 8) - offset;
+				t += offset + 31 + *ip++;
+				NEED_IP(2);
 			}
 			m_pos = op - 1;
 			next = get_unaligned_le16(ip);
@@ -154,13 +158,20 @@ copy_literal_run:
 			m_pos -= (t & 8) << 11;
 			t = (t & 7) + (3 - 1);
 			if (unlikely(t == 2)) {
+				size_t offset;
+				const unsigned char *ip_last = ip;
+
 				while (unlikely(*ip == 0)) {
-					t += 255;
 					ip++;
-					NEED_IP(1, 0);
+					NEED_IP(1);
 				}
-				t += 7 + *ip++;
-				NEED_IP(2, 0);
+				offset = ip - ip_last;
+				if (unlikely(offset > MAX_255_COUNT))
+					return LZO_E_ERROR;
+
+				offset = (offset << 8) - offset;
+				t += offset + 7 + *ip++;
+				NEED_IP(2);
 			}
 			next = get_unaligned_le16(ip);
 			ip += 2;
@@ -174,7 +185,7 @@ copy_literal_run:
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
 		if (op - m_pos >= 8) {
 			unsigned char *oe = op + t;
-			if (likely(HAVE_OP(t, 15))) {
+			if (likely(HAVE_OP(t + 15))) {
 				do {
 					COPY8(op, m_pos);
 					op += 8;
@@ -184,7 +195,7 @@ copy_literal_run:
 					m_pos += 8;
 				} while (op < oe);
 				op = oe;
-				if (HAVE_IP(6, 0)) {
+				if (HAVE_IP(6)) {
 					state = next;
 					COPY4(op, ip);
 					op += next;
@@ -192,7 +203,7 @@ copy_literal_run:
 					continue;
 				}
 			} else {
-				NEED_OP(t, 0);
+				NEED_OP(t);
 				do {
 					*op++ = *m_pos++;
 				} while (op < oe);
@@ -201,7 +212,7 @@ copy_literal_run:
 #endif
 		{
 			unsigned char *oe = op + t;
-			NEED_OP(t, 0);
+			NEED_OP(t);
 			op[0] = m_pos[0];
 			op[1] = m_pos[1];
 			op += 2;
@@ -214,15 +225,15 @@ match_next:
 		state = next;
 		t = next;
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
-		if (likely(HAVE_IP(6, 0) && HAVE_OP(4, 0))) {
+		if (likely(HAVE_IP(6) && HAVE_OP(4))) {
 			COPY4(op, ip);
 			op += t;
 			ip += t;
 		} else
 #endif
 		{
-			NEED_IP(t, 3);
-			NEED_OP(t, 0);
+			NEED_IP(t + 3);
+			NEED_OP(t);
 			while (t > 0) {
 				*op++ = *ip++;
 				t--;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 6afa3b45f25a..0007c9e9853a 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -2608,12 +2608,8 @@ static int l2cap_segment_le_sdu(struct l2cap_chan *chan,
 
 	BT_DBG("chan %p, msg %p, len %zu", chan, msg, len);
 
-	pdu_len = chan->conn->mtu - L2CAP_HDR_SIZE;
-
-	pdu_len = min_t(size_t, pdu_len, chan->remote_mps);
-
 	sdu_len = len;
-	pdu_len -= L2CAP_SDULEN_SIZE;
+	pdu_len = chan->remote_mps - L2CAP_SDULEN_SIZE;
 
 	while (len > 0) {
 		if (len <= pdu_len)
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index 734e9468aca0..6df1b2527d02 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -194,8 +194,11 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 			goto out;
 
 		cause = "missing-hash";
-		status =
-		    (inode->i_size == 0) ? INTEGRITY_PASS : INTEGRITY_NOLABEL;
+		status = INTEGRITY_NOLABEL;
+		if (inode->i_size == 0) {
+			iint->flags |= IMA_NEW_FILE;
+			status = INTEGRITY_PASS;
+		}
 		goto out;
 	}
 
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 76d8aad146a8..9f70efd08058 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -131,11 +131,13 @@ static void ima_check_last_writer(struct integrity_iint_cache *iint,
 		return;
 
 	mutex_lock(&inode->i_mutex);
-	if (atomic_read(&inode->i_writecount) == 1 &&
-	    iint->version != inode->i_version) {
-		iint->flags &= ~IMA_DONE_MASK;
-		if (iint->flags & IMA_APPRAISE)
-			ima_update_xattr(iint, file);
+	if (atomic_read(&inode->i_writecount) == 1) {
+		if ((iint->version != inode->i_version) ||
+		    (iint->flags & IMA_NEW_FILE)) {
+			iint->flags &= ~(IMA_DONE_MASK | IMA_NEW_FILE);
+			if (iint->flags & IMA_APPRAISE)
+				ima_update_xattr(iint, file);
+		}
 	}
 	mutex_unlock(&inode->i_mutex);
 }
diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h
index 33c0a70f6b15..2f8715d77a5a 100644
--- a/security/integrity/integrity.h
+++ b/security/integrity/integrity.h
@@ -31,6 +31,7 @@
 #define IMA_DIGSIG		0x01000000
 #define IMA_DIGSIG_REQUIRED	0x02000000
 #define IMA_PERMIT_DIRECTIO	0x04000000
+#define IMA_NEW_FILE		0x08000000
 
 #define IMA_DO_MASK		(IMA_MEASURE | IMA_APPRAISE | IMA_AUDIT | \
 				 IMA_APPRAISE_SUBMASK)
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 01a5e05ede95..566b0f69d628 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -3189,7 +3189,7 @@ static const struct vm_operations_struct snd_pcm_vm_ops_data_fault = {
 
 #ifndef ARCH_HAS_DMA_MMAP_COHERENT
 /* This should be defined / handled globally! */
-#ifdef CONFIG_ARM
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
 #define ARCH_HAS_DMA_MMAP_COHERENT
 #endif
 #endif
diff --git a/sound/pci/emu10k1/emu10k1_callback.c b/sound/pci/emu10k1/emu10k1_callback.c
index cae36597aa71..0a34b5f1c475 100644
--- a/sound/pci/emu10k1/emu10k1_callback.c
+++ b/sound/pci/emu10k1/emu10k1_callback.c
@@ -85,6 +85,8 @@ snd_emu10k1_ops_setup(struct snd_emux *emux)
  * get more voice for pcm
  *
  * terminate most inactive voice and give it as a pcm voice.
+ *
+ * voice_lock is already held.
  */
 int
 snd_emu10k1_synth_get_voice(struct snd_emu10k1 *hw)
@@ -92,12 +94,10 @@ snd_emu10k1_synth_get_voice(struct snd_emu10k1 *hw)
 	struct snd_emux *emu;
 	struct snd_emux_voice *vp;
 	struct best_voice best[V_END];
-	unsigned long flags;
 	int i;
 
 	emu = hw->synth;
 
-	spin_lock_irqsave(&emu->voice_lock, flags);
 	lookup_voices(emu, hw, best, 1); /* no OFF voices */
 	for (i = 0; i < V_END; i++) {
 		if (best[i].voice >= 0) {
@@ -113,11 +113,9 @@ snd_emu10k1_synth_get_voice(struct snd_emu10k1 *hw)
 			vp->emu->num_voices--;
 			vp->ch = -1;
 			vp->state = SNDRV_EMUX_ST_OFF;
-			spin_unlock_irqrestore(&emu->voice_lock, flags);
 			return ch;
 		}
 	}
-	spin_unlock_irqrestore(&emu->voice_lock, flags);
 
 	/* not found */
 	return -ENOMEM;
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index d135c906caff..8253b48a435b 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -1557,19 +1557,22 @@ static bool hdmi_present_sense(struct hdmi_spec_per_pin *per_pin, int repoll)
 		}
 	}
 
-	if (pin_eld->eld_valid && !eld->eld_valid) {
-		update_eld = true;
+	if (pin_eld->eld_valid != eld->eld_valid)
 		eld_changed = true;
-	}
+
+	if (pin_eld->eld_valid && !eld->eld_valid)
+		update_eld = true;
+
 	if (update_eld) {
 		bool old_eld_valid = pin_eld->eld_valid;
 		pin_eld->eld_valid = eld->eld_valid;
-		eld_changed = pin_eld->eld_size != eld->eld_size ||
+		if (pin_eld->eld_size != eld->eld_size ||
 			      memcmp(pin_eld->eld_buffer, eld->eld_buffer,
-				     eld->eld_size) != 0;
-		if (eld_changed)
+				     eld->eld_size) != 0) {
 			memcpy(pin_eld->eld_buffer, eld->eld_buffer,
 			       eld->eld_size);
+			eld_changed = true;
+		}
 		pin_eld->eld_size = eld->eld_size;
 		pin_eld->info = eld->info;
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 5d0058bd6259..4c826a40705c 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -2926,6 +2926,9 @@ static void alc283_shutup(struct hda_codec *codec)
 
 	alc_write_coef_idx(codec, 0x43, 0x9004);
 
+	/*depop hp during suspend*/
+	alc_write_coef_idx(codec, 0x06, 0x2100);
+
 	snd_hda_codec_write(codec, hp_pin, 0,
 			    AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE);
 
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index 223c47b33ba3..c657752a420c 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -385,6 +385,36 @@ YAMAHA_DEVICE(0x105d, NULL),
 	}
 },
 {
+	USB_DEVICE(0x0499, 0x1509),
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+		/* .vendor_name = "Yamaha", */
+		/* .product_name = "Steinberg UR22", */
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = (const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 1,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 2,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 3,
+				.type = QUIRK_MIDI_YAMAHA
+			},
+			{
+				.ifnum = 4,
+				.type = QUIRK_IGNORE_INTERFACE
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
+{
 	USB_DEVICE(0x0499, 0x150a),
 	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
 		/* .vendor_name = "Yamaha", */
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 03a0381b1cb7..66112533b1e9 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -52,6 +52,7 @@
 
 #include <asm/processor.h>
 #include <asm/io.h>
+#include <asm/ioctl.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 
@@ -95,8 +96,6 @@ static int hardware_enable_all(void);
 static void hardware_disable_all(void);
 
 static void kvm_io_bus_destroy(struct kvm_io_bus *bus);
-static void update_memslots(struct kvm_memslots *slots,
-			    struct kvm_memory_slot *new, u64 last_generation);
 
 static void kvm_release_pfn_dirty(pfn_t pfn);
 static void mark_page_dirty_in_slot(struct kvm *kvm,
@@ -682,8 +681,7 @@ static void sort_memslots(struct kvm_memslots *slots)
 }
 
 static void update_memslots(struct kvm_memslots *slots,
-			    struct kvm_memory_slot *new,
-			    u64 last_generation)
+			    struct kvm_memory_slot *new)
 {
 	if (new) {
 		int id = new->id;
@@ -694,8 +692,6 @@ static void update_memslots(struct kvm_memslots *slots,
 		if (new->npages != npages)
 			sort_memslots(slots);
 	}
-
-	slots->generation = last_generation + 1;
 }
 
 static int check_memory_region_flags(struct kvm_userspace_memory_region *mem)
@@ -717,10 +713,24 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm,
 {
 	struct kvm_memslots *old_memslots = kvm->memslots;
 
-	update_memslots(slots, new, kvm->memslots->generation);
+	/*
+	 * Set the low bit in the generation, which disables SPTE caching
+	 * until the end of synchronize_srcu_expedited.
+	 */
+	WARN_ON(old_memslots->generation & 1);
+	slots->generation = old_memslots->generation + 1;
+
+	update_memslots(slots, new);
 	rcu_assign_pointer(kvm->memslots, slots);
 	synchronize_srcu_expedited(&kvm->srcu);
 
+	/*
+	 * Increment the new memslot generation a second time. This prevents
+	 * vm exits that race with memslot updates from caching a memslot
+	 * generation that will (potentially) be valid forever.
+	 */
+	slots->generation++;
+
 	kvm_arch_memslots_updated(kvm);
 
 	return old_memslots;
@@ -1970,6 +1980,9 @@ static long kvm_vcpu_ioctl(struct file *filp,
 	if (vcpu->kvm->mm != current->mm)
 		return -EIO;
 
+	if (unlikely(_IOC_TYPE(ioctl) != KVMIO))
+		return -EINVAL;
+
 #if defined(CONFIG_S390) || defined(CONFIG_PPC) || defined(CONFIG_MIPS)
 	/*
 	 * Special cases: vcpu ioctls that are asynchronous to vcpu execution,