Linux 3.16.7

[ Upstream commit 06090e8ed8 ]

It is not sufficient to only implement get_user_pages_fast(), you
must also implement the atomic version __get_user_pages_fast()
otherwise you end up using the weak symbol fallback implementation
which simply returns zero.

This is dangerous, because it causes the futex code to loop forever
if transparent hugepages are supported (see get_futex_key()).

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Documentation/devicetree/bindings/interrupt-controller/interrupts.txt

@@ -4,11 +4,13 @@ Specifying interrupt information for devices
 1) Interrupt client nodes
 -------------------------
 
-Nodes that describe devices which generate interrupts must contain an either an
-"interrupts" property or an "interrupts-extended" property. These properties
-contain a list of interrupt specifiers, one per output interrupt. The format of
-the interrupt specifier is determined by the interrupt controller to which the
-interrupts are routed; see section 2 below for details.
+Nodes that describe devices which generate interrupts must contain an
+"interrupts" property, an "interrupts-extended" property, or both. If both are
+present, the latter should take precedence; the former may be provided simply
+for compatibility with software that does not recognize the latter. These
+properties contain a list of interrupt specifiers, one per output interrupt. The
+format of the interrupt specifier is determined by the interrupt controller to
+which the interrupts are routed; see section 2 below for details.
 
   Example:
 	interrupt-parent = <&intc1>;

Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt

@@ -1,7 +1,7 @@
 ADI AXI-SPDIF controller
 
 Required properties:
- - compatible : Must be "adi,axi-spdif-1.00.a"
+ - compatible : Must be "adi,axi-spdif-tx-1.00.a"
  - reg : Must contain SPDIF core's registers location and length
  - clocks : Pairs of phandle and specifier referencing the controller's clocks.
    The controller expects two clocks, the clock used for the AXI interface and

Documentation/devicetree/bindings/staging/imx-drm/ldb.txt

@@ -56,6 +56,9 @@ Required properties:
  - fsl,data-width : should be <18> or <24>
  - port: A port node with endpoint definitions as defined in
    Documentation/devicetree/bindings/media/video-interfaces.txt.
+   On i.MX5, the internal two-input-multiplexer is used.
+   Due to hardware limitations, only one port (port@[0,1])
+   can be used for each channel (lvds-channel@[0,1], respectively)
    On i.MX6, there should be four ports (port@[0-3]) that correspond
    to the four LVDS multiplexer inputs.
 
@@ -78,6 +81,8 @@ ldb: ldb@53fa8008 {
 		      "di0", "di1";
 
 	lvds-channel@0 {
+		#address-cells = <1>;
+		#size-cells = <0>;
 		reg = <0>;
 		fsl,data-mapping = "spwg";
 		fsl,data-width = <24>;
@@ -86,7 +91,9 @@ ldb: ldb@53fa8008 {
 			/* ... */
 		};
 
-		port {
+		port@0 {
+			reg = <0>;
+
 			lvds0_in: endpoint {
 				remote-endpoint = <&ipu_di0_lvds0>;
 			};
@@ -94,6 +101,8 @@ ldb: ldb@53fa8008 {
 	};
 
 	lvds-channel@1 {
+		#address-cells = <1>;
+		#size-cells = <0>;
 		reg = <1>;
 		fsl,data-mapping = "spwg";
 		fsl,data-width = <24>;
@@ -102,7 +111,9 @@ ldb: ldb@53fa8008 {
 			/* ... */
 		};
 
-		port {
+		port@1 {
+			reg = <1>;
+
 			lvds1_in: endpoint {
 				remote-endpoint = <&ipu_di1_lvds1>;
 			};

Documentation/kernel-parameters.txt

@@ -3459,6 +3459,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 					READ_DISC_INFO command);
 				e = NO_READ_CAPACITY_16 (don't use
 					READ_CAPACITY_16 command);
+				f = NO_REPORT_OPCODES (don't use report opcodes
+					command, uas only);
 				h = CAPACITY_HEURISTICS (decrease the
 					reported device capacity by one
 					sector if the number is odd);
@@ -3478,6 +3480,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 					bogus residue values);
 				s = SINGLE_LUN (the device has only one
 					Logical Unit);
+				t = NO_ATA_1X (don't allow ATA(12) and ATA(16)
+					commands, uas only);
+				u = IGNORE_UAS (don't bind to the uas driver);
 				w = NO_WP_DETECT (don't test whether the
 					medium is write-protected).
 			Example: quirks=0419:aaf5:rl,0421:0433:rc

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.

Documentation/sound/alsa/ALSA-Configuration.txt

@@ -2026,8 +2026,8 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
   -------------------
 
     Module for sound cards based on the Asus AV66/AV100/AV200 chips,
-    i.e., Xonar D1, DX, D2, D2X, DS, Essence ST (Deluxe), Essence STX,
-    HDAV1.3 (Deluxe), and HDAV1.3 Slim.
+    i.e., Xonar D1, DX, D2, D2X, DS, DSX, Essence ST (Deluxe),
+    Essence STX (II), HDAV1.3 (Deluxe), and HDAV1.3 Slim.
 
     This module supports autoprobe and multiple cards.
 

Documentation/stable_kernel_rules.txt

@@ -29,6 +29,9 @@ Rules on what kind of patches are accepted, and which ones are not, into the
 
 Procedure for submitting patches to the -stable tree:
 
+ - If the patch covers files in net/ or drivers/net please follow netdev stable
+   submission guidelines as described in
+   Documentation/networking/netdev-FAQ.txt
  - Send the patch, after verifying that it follows the above rules, to
    stable@vger.kernel.org.  You must note the upstream commit ID in the
    changelog of your submission, as well as the kernel version you wish

Documentation/virtual/kvm/api.txt

@@ -1869,7 +1869,8 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_PID	| 64
   PPC   | KVM_REG_PPC_ACOP	| 64
   PPC   | KVM_REG_PPC_VRSAVE	| 32
-  PPC   | KVM_REG_PPC_LPCR	| 64
+  PPC   | KVM_REG_PPC_LPCR	| 32
+  PPC   | KVM_REG_PPC_LPCR_64	| 64
   PPC   | KVM_REG_PPC_PPR	| 64
   PPC   | KVM_REG_PPC_ARCH_COMPAT 32
   PPC   | KVM_REG_PPC_DABRX     | 32

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
 ===============

Makefile

@@ -1,8 +1,8 @@
 VERSION = 3
 PATCHLEVEL = 16
-SUBLEVEL = 0
+SUBLEVEL = 7
 EXTRAVERSION =
-NAME = Shuffling Zombie Juror
+NAME = Museum of Fishiegoodies
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"

arch/arm/boot/dts/Makefile

@@ -137,8 +137,8 @@ kirkwood := \
 	kirkwood-openrd-client.dtb \
 	kirkwood-openrd-ultimate.dtb \
 	kirkwood-rd88f6192.dtb \
-	kirkwood-rd88f6281-a0.dtb \
-	kirkwood-rd88f6281-a1.dtb \
+	kirkwood-rd88f6281-z0.dtb \
+	kirkwood-rd88f6281-a.dtb \
 	kirkwood-rs212.dtb \
 	kirkwood-rs409.dtb \
 	kirkwood-rs411.dtb \

arch/arm/boot/dts/am4372.dtsi

@@ -168,9 +168,6 @@
 			ti,hwmods = "mailbox";
 			ti,mbox-num-users = <4>;
 			ti,mbox-num-fifos = <8>;
-			ti,mbox-names = "wkup_m3";
-			ti,mbox-data = <0 0 0 0>;
-			status = "disabled";
 		};
 
 		timer1: timer@44e31000 {

arch/arm/boot/dts/armada-370-netgear-rn102.dts

@@ -143,6 +143,10 @@
 				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 */

arch/arm/boot/dts/armada-370-netgear-rn104.dts

@@ -145,6 +145,10 @@
 				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 */

arch/arm/boot/dts/armada-xp-netgear-rn2120.dts

@@ -223,6 +223,10 @@
 				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 */

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";

arch/arm/boot/dts/dra7-evm.dts

@@ -50,13 +50,13 @@
 
 	mcspi1_pins: pinmux_mcspi1_pins {
 		pinctrl-single,pins = <
-			0x3a4 (PIN_INPUT | MUX_MODE0) /* spi2_clk */
-			0x3a8 (PIN_INPUT | MUX_MODE0) /* spi2_d1 */
-			0x3ac (PIN_INPUT | MUX_MODE0) /* spi2_d0 */
-			0x3b0 (PIN_INPUT_SLEW | MUX_MODE0) /* spi2_cs0 */
-			0x3b4 (PIN_INPUT_SLEW | MUX_MODE0) /* spi2_cs1 */
-			0x3b8 (PIN_INPUT_SLEW | MUX_MODE6) /* spi2_cs2 */
-			0x3bc (PIN_INPUT_SLEW | MUX_MODE6) /* spi2_cs3 */
+			0x3a4 (PIN_INPUT | MUX_MODE0) /* spi1_sclk */
+			0x3a8 (PIN_INPUT | MUX_MODE0) /* spi1_d1 */
+			0x3ac (PIN_INPUT | MUX_MODE0) /* spi1_d0 */
+			0x3b0 (PIN_INPUT_SLEW | MUX_MODE0) /* spi1_cs0 */
+			0x3b4 (PIN_INPUT_SLEW | MUX_MODE0) /* spi1_cs1 */
+			0x3b8 (PIN_INPUT_SLEW | MUX_MODE6) /* spi1_cs2.hdmi1_hpd */
+			0x3bc (PIN_INPUT_SLEW | MUX_MODE6) /* spi1_cs3.hdmi1_cec */
 		>;
 	};
 
@@ -427,22 +427,19 @@
 		gpmc,device-width = <2>;
 		gpmc,sync-clk-ps = <0>;
 		gpmc,cs-on-ns = <0>;
-		gpmc,cs-rd-off-ns = <40>;
-		gpmc,cs-wr-off-ns = <40>;
+		gpmc,cs-rd-off-ns = <80>;
+		gpmc,cs-wr-off-ns = <80>;
 		gpmc,adv-on-ns = <0>;
-		gpmc,adv-rd-off-ns = <30>;
-		gpmc,adv-wr-off-ns = <30>;
-		gpmc,we-on-ns = <5>;
-		gpmc,we-off-ns = <25>;
-		gpmc,oe-on-ns = <2>;
-		gpmc,oe-off-ns = <20>;
-		gpmc,access-ns = <20>;
-		gpmc,wr-access-ns = <40>;
-		gpmc,rd-cycle-ns = <40>;
-		gpmc,wr-cycle-ns = <40>;
-		gpmc,wait-pin = <0>;
-		gpmc,wait-on-read;
-		gpmc,wait-on-write;
+		gpmc,adv-rd-off-ns = <60>;
+		gpmc,adv-wr-off-ns = <60>;
+		gpmc,we-on-ns = <10>;
+		gpmc,we-off-ns = <50>;
+		gpmc,oe-on-ns = <4>;
+		gpmc,oe-off-ns = <40>;
+		gpmc,access-ns = <40>;
+		gpmc,wr-access-ns = <80>;
+		gpmc,rd-cycle-ns = <80>;
+		gpmc,wr-cycle-ns = <80>;
 		gpmc,bus-turnaround-ns = <0>;
 		gpmc,cycle2cycle-delay-ns = <0>;
 		gpmc,clk-activation-ns = <0>;

arch/arm/boot/dts/dra7.dtsi

@@ -172,7 +172,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio2: gpio@48055000 {
@@ -183,7 +183,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio3: gpio@48057000 {
@@ -194,7 +194,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio4: gpio@48059000 {
@@ -205,7 +205,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio5: gpio@4805b000 {
@@ -216,7 +216,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio6: gpio@4805d000 {
@@ -227,7 +227,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio7: gpio@48051000 {
@@ -238,7 +238,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio8: gpio@48053000 {
@@ -249,7 +249,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		uart1: serial@4806a000 {

arch/arm/boot/dts/imx28-evk.dts

@@ -193,7 +193,6 @@
 			i2c0: i2c@80058000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&i2c0_pins_a>;
-				clock-frequency = <400000>;
 				status = "okay";
 
 				sgtl5000: codec@0a {

arch/arm/boot/dts/imx53-qsrb.dts

@@ -28,6 +28,12 @@
 				MX53_PAD_CSI0_DAT9__I2C1_SCL      0x400001ec
 			>;
 		};
+
+		pinctrl_pmic: pmicgrp {
+			fsl,pins = <
+				MX53_PAD_CSI0_DAT5__GPIO5_23	0x1e4 /* IRQ */
+			>;
+		};
 	};
 };
 
@@ -38,6 +44,8 @@
 
 	pmic: mc34708@8 {
 		compatible = "fsl,mc34708";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_pmic>;
 		reg = <0x08>;
 		interrupt-parent = <&gpio5>;
 		interrupts = <23 0x8>;

arch/arm/boot/dts/imx53.dtsi

@@ -419,10 +419,14 @@
 				status = "disabled";
 
 				lvds-channel@0 {
+					#address-cells = <1>;
+					#size-cells = <0>;
 					reg = <0>;
 					status = "disabled";
 
-					port {
+					port@0 {
+						reg = <0>;
+
 						lvds0_in: endpoint {
 							remote-endpoint = <&ipu_di0_lvds0>;
 						};
@@ -430,10 +434,14 @@
 				};
 
 				lvds-channel@1 {
+					#address-cells = <1>;
+					#size-cells = <0>;
 					reg = <1>;
 					status = "disabled";
 
-					port {
+					port@1 {
+						reg = <1>;
+
 						lvds1_in: endpoint {
 							remote-endpoint = <&ipu_di1_lvds1>;
 						};
@@ -724,7 +732,7 @@
 				compatible = "fsl,imx53-vpu";
 				reg = <0x63ff4000 0x1000>;
 				interrupts = <9>;
-				clocks = <&clks IMX5_CLK_VPU_GATE>,
+				clocks = <&clks IMX5_CLK_VPU_REFERENCE_GATE>,
 				         <&clks IMX5_CLK_VPU_GATE>;
 				clock-names = "per", "ahb";
 				resets = <&src 1>;

arch/arm/boot/dts/kirkwood-mv88f6281gtw-ge.dts

@@ -123,11 +123,11 @@
 
 	dsa@0 {
 		compatible = "marvell,dsa";
-		#address-cells = <2>;
+		#address-cells = <1>;
 		#size-cells = <0>;
 
-		dsa,ethernet = <&eth0>;
-		dsa,mii-bus = <&ethphy0>;
+		dsa,ethernet = <&eth0port>;
+		dsa,mii-bus = <&mdio>;
 
 		switch@0 {
 			#address-cells = <1>;
@@ -169,17 +169,13 @@
 
 &mdio {
 	status = "okay";
-
-	ethphy0: ethernet-phy@ff {
-		reg = <0xff>; 	/* No phy attached */
-		speed = <1000>;
-		duplex = <1>;
-	};
 };
 
 &eth0 {
 	status = "okay";
+
 	ethernet0-port@0 {
-		phy-handle = <&ethphy0>;
+		speed = <1000>;
+		duplex = <1>;
 	};
 };

arch/arm/boot/dts/kirkwood-rd88f6281-a.dts

@@ -0,0 +1,43 @@
+/*
+ * Marvell RD88F6181 A Board descrition
+ *
+ * Andrew Lunn <andrew@lunn.ch>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ * This file contains the definitions for the board with the A0 or
+ * higher stepping of the SoC. The ethernet switch does not have a
+ * "wan" port.
+ */
+
+/dts-v1/;
+#include "kirkwood-rd88f6281.dtsi"
+
+/ {
+	model = "Marvell RD88f6281 Reference design, with A0 or higher SoC";
+	compatible = "marvell,rd88f6281-a", "marvell,rd88f6281","marvell,kirkwood-88f6281", "marvell,kirkwood";
+
+	dsa@0 {
+		switch@0 {
+			reg = <10 0>;	 /* MDIO address 10, switch 0 in tree */
+		};
+	};
+};
+
+&mdio {
+	status = "okay";
+
+	ethphy1: ethernet-phy@11 {
+		 reg = <11>;
+	};
+};
+
+&eth1 {
+	status = "okay";
+
+	ethernet1-port@0 {
+		 phy-handle = <&ethphy1>;
+	};
+};

arch/arm/boot/dts/kirkwood-rd88f6281-a0.dts

@@ -1,26 +0,0 @@
-/*
- * Marvell RD88F6181 A0 Board descrition
- *
- * Andrew Lunn <andrew@lunn.ch>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- *
- * This file contains the definitions for the board with the A0 variant of
- * the SoC. The ethernet switch does not have a "wan" port.
- */
-
-/dts-v1/;
-#include "kirkwood-rd88f6281.dtsi"
-
-/ {
-	model = "Marvell RD88f6281 Reference design, with A0 SoC";
-	compatible = "marvell,rd88f6281-a0", "marvell,rd88f6281","marvell,kirkwood-88f6281", "marvell,kirkwood";
-
-	dsa@0 {
-		switch@0 {
-			reg = <10 0>;    /* MDIO address 10, switch 0 in tree */
-		};
-	};
-};

arch/arm/boot/dts/kirkwood-rd88f6281-z0.dts

@@ -1,5 +1,5 @@
 /*
- * Marvell RD88F6181 A1 Board descrition
+ * Marvell RD88F6181 Z0 stepping descrition
  *
  * Andrew Lunn <andrew@lunn.ch>
  *
@@ -7,17 +7,17 @@
  * License version 2.  This program is licensed "as is" without any
  * warranty of any kind, whether express or implied.
  *
- * This file contains the definitions for the board with the A1 variant of
- * the SoC. The ethernet switch has a "wan" port.
- */
+ * This file contains the definitions for the board using the Z0
+ * stepping of the SoC. The ethernet switch has a "wan" port.
+*/
 
 /dts-v1/;
 
 #include "kirkwood-rd88f6281.dtsi"
 
 / {
-	model = "Marvell RD88f6281 Reference design, with A1 SoC";
-	compatible = "marvell,rd88f6281-a1", "marvell,rd88f6281","marvell,kirkwood-88f6281", "marvell,kirkwood";
+	model = "Marvell RD88f6281 Reference design, with Z0 SoC";
+	compatible = "marvell,rd88f6281-z0", "marvell,rd88f6281","marvell,kirkwood-88f6281", "marvell,kirkwood";
 
 	dsa@0 {
 		switch@0 {
@@ -28,4 +28,8 @@
 			};
 		};
 	};
-};
+};
+
+&eth1 {
+      status = "disabled";
+};

arch/arm/boot/dts/kirkwood-rd88f6281.dtsi

@@ -37,7 +37,6 @@
 
 	ocp@f1000000 {
 		pinctrl: pin-controller@10000 {
-			pinctrl-0 = <&pmx_sdio_cd>;
 			pinctrl-names = "default";
 
 			pmx_sdio_cd: pmx-sdio-cd {
@@ -69,8 +68,8 @@
 		#address-cells = <2>;
 		#size-cells = <0>;
 
-		dsa,ethernet = <&eth0>;
-		dsa,mii-bus = <&ethphy1>;
+		dsa,ethernet = <&eth0port>;
+		dsa,mii-bus = <&mdio>;
 
 		switch@0 {
 			#address-cells = <1>;
@@ -119,35 +118,19 @@
 	};
 
 	partition@300000 {
-		label = "data";
+		label = "rootfs";
 		reg = <0x0300000 0x500000>;
 	};
 };
 
 &mdio {
 	status = "okay";
-
-	ethphy0: ethernet-phy@0 {
-		reg = <0>;
-	};
-
-	ethphy1: ethernet-phy@ff {
-		reg = <0xff>; /* No PHY attached */
-		speed = <1000>;
-		duple = <1>;
-	};
 };
 
 &eth0 {
 	status = "okay";
 	ethernet0-port@0 {
-		phy-handle = <&ethphy0>;
-	};
-};
-
-&eth1 {
-	status = "okay";
-	ethernet1-port@0 {
-		phy-handle = <&ethphy1>;
+		speed = <1000>;
+		duplex = <1>;
 	};
 };

arch/arm/boot/dts/kirkwood.dtsi

@@ -309,7 +309,7 @@
 			marvell,tx-checksum-limit = <1600>;
 			status = "disabled";
 
-			ethernet0-port@0 {
+			eth0port: ethernet0-port@0 {
 				compatible = "marvell,kirkwood-eth-port";
 				reg = <0>;
 				interrupts = <11>;
@@ -342,7 +342,7 @@
 			pinctrl-names = "default";
 			status = "disabled";
 
-			ethernet1-port@0 {
+			eth1port: ethernet1-port@0 {
 				compatible = "marvell,kirkwood-eth-port";
 				reg = <0>;
 				interrupts = <15>;

arch/arm/boot/dts/omap3-n900.dts

@@ -353,7 +353,7 @@
 	};
 
 	twl_power: power {
-		compatible = "ti,twl4030-power-n900";
+		compatible = "ti,twl4030-power-n900", "ti,twl4030-power-idle-osc-off";
 		ti,use_poweroff;
 	};
 };

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>;

arch/arm/boot/dts/vf610-twr.dts

@@ -168,7 +168,7 @@
 		};
 
 		pinctrl_esdhc1: esdhc1grp {
-			fsl,fsl,pins = <
+			fsl,pins = <
 				VF610_PAD_PTA24__ESDHC1_CLK	0x31ef
 				VF610_PAD_PTA25__ESDHC1_CMD	0x31ef
 				VF610_PAD_PTA26__ESDHC1_DAT0	0x31ef

arch/arm/common/edma.c

@@ -1415,14 +1415,14 @@ void edma_clear_event(unsigned channel)
 EXPORT_SYMBOL(edma_clear_event);
 
 static int edma_setup_from_hw(struct device *dev, struct edma_soc_info *pdata,
-			      struct edma *edma_cc)
+			      struct edma *edma_cc, int cc_id)
 {
 	int i;
 	u32 value, cccfg;
 	s8 (*queue_priority_map)[2];
 
 	/* Decode the eDMA3 configuration from CCCFG register */
-	cccfg = edma_read(0, EDMA_CCCFG);
+	cccfg = edma_read(cc_id, EDMA_CCCFG);
 
 	value = GET_NUM_REGN(cccfg);
 	edma_cc->num_region = BIT(value);
@@ -1436,7 +1436,8 @@ static int edma_setup_from_hw(struct device *dev, struct edma_soc_info *pdata,
 	value = GET_NUM_EVQUE(cccfg);
 	edma_cc->num_tc = value + 1;
 
-	dev_dbg(dev, "eDMA3 HW configuration (cccfg: 0x%08x):\n", cccfg);
+	dev_dbg(dev, "eDMA3 CC%d HW configuration (cccfg: 0x%08x):\n", cc_id,
+		cccfg);
 	dev_dbg(dev, "num_region: %u\n", edma_cc->num_region);
 	dev_dbg(dev, "num_channel: %u\n", edma_cc->num_channels);
 	dev_dbg(dev, "num_slot: %u\n", edma_cc->num_slots);
@@ -1655,7 +1656,7 @@ static int edma_probe(struct platform_device *pdev)
 			return -ENOMEM;
 
 		/* Get eDMA3 configuration from IP */
-		ret = edma_setup_from_hw(dev, info[j], edma_cc[j]);
+		ret = edma_setup_from_hw(dev, info[j], edma_cc[j], j);
 		if (ret)
 			return ret;
 

arch/arm/include/asm/cacheflush.h

@@ -472,7 +472,6 @@ static inline void __sync_cache_range_r(volatile void *p, size_t size)
 	"mcr	p15, 0, r0, c1, c0, 0	@ set SCTLR \n\t" \
 	"isb	\n\t" \
 	"bl	v7_flush_dcache_"__stringify(level)" \n\t" \
-	"clrex	\n\t" \
 	"mrc	p15, 0, r0, c1, c0, 1	@ get ACTLR \n\t" \
 	"bic	r0, r0, #(1 << 6)	@ disable local coherency \n\t" \
 	"mcr	p15, 0, r0, c1, c0, 1	@ set ACTLR \n\t" \

arch/arm/include/asm/tls.h

@@ -1,6 +1,9 @@
 #ifndef __ASMARM_TLS_H
 #define __ASMARM_TLS_H
 
+#include <linux/compiler.h>
+#include <asm/thread_info.h>
+
 #ifdef __ASSEMBLY__
 #include <asm/asm-offsets.h>
 	.macro switch_tls_none, base, tp, tpuser, tmp1, tmp2
@@ -50,6 +53,49 @@
 #endif
 
 #ifndef __ASSEMBLY__
+
+static inline void set_tls(unsigned long val)
+{
+	struct thread_info *thread;
+
+	thread = current_thread_info();
+
+	thread->tp_value[0] = val;
+
+	/*
+	 * This code runs with preemption enabled and therefore must
+	 * be reentrant with respect to switch_tls.
+	 *
+	 * We need to ensure ordering between the shadow state and the
+	 * hardware state, so that we don't corrupt the hardware state
+	 * with a stale shadow state during context switch.
+	 *
+	 * If we're preempted here, switch_tls will load TPIDRURO from
+	 * thread_info upon resuming execution and the following mcr
+	 * is merely redundant.
+	 */
+	barrier();
+
+	if (!tls_emu) {
+		if (has_tls_reg) {
+			asm("mcr p15, 0, %0, c13, c0, 3"
+			    : : "r" (val));
+		} else {
+#ifdef CONFIG_KUSER_HELPERS
+			/*
+			 * User space must never try to access this
+			 * directly.  Expect your app to break
+			 * eventually if you do so.  The user helper
+			 * at 0xffff0fe0 must be used instead.  (see
+			 * entry-armv.S for details)
+			 */
+			*((unsigned int *)0xffff0ff0) = val;
+#endif
+		}
+
+	}
+}
+
 static inline unsigned long get_tpuser(void)
 {
 	unsigned long reg = 0;
@@ -59,5 +105,23 @@ static inline unsigned long get_tpuser(void)
 
 	return reg;
 }
+
+static inline void set_tpuser(unsigned long val)
+{
+	/* Since TPIDRURW is fully context-switched (unlike TPIDRURO),
+	 * we need not update thread_info.
+	 */
+	if (has_tls_reg && !tls_emu) {
+		asm("mcr p15, 0, %0, c13, c0, 2"
+		    : : "r" (val));
+	}
+}
+
+static inline void flush_tls(void)
+{
+	set_tls(0);
+	set_tpuser(0);
+}
+
 #endif
 #endif	/* __ASMARM_TLS_H */

arch/arm/include/asm/unistd.h

@@ -15,7 +15,17 @@
 
 #include <uapi/asm/unistd.h>
 
+/*
+ * This may need to be greater than __NR_last_syscall+1 in order to
+ * account for the padding in the syscall table
+ */
 #define __NR_syscalls  (384)
+
+/*
+ * *NOTE*: This is a ghost syscall private to the kernel.  Only the
+ * __kuser_cmpxchg code in entry-armv.S should be aware of its
+ * existence.  Don't ever use this from user code.
+ */
 #define __ARM_NR_cmpxchg		(__ARM_NR_BASE+0x00fff0)
 
 #define __ARCH_WANT_STAT64

arch/arm/include/uapi/asm/unistd.h

@@ -410,11 +410,6 @@
 #define __NR_sched_getattr		(__NR_SYSCALL_BASE+381)
 #define __NR_renameat2			(__NR_SYSCALL_BASE+382)
 
-/*
- * This may need to be greater than __NR_last_syscall+1 in order to
- * account for the padding in the syscall table
- */
-
 /*
  * The following SWIs are ARM private.
  */
@@ -425,12 +420,6 @@
 #define __ARM_NR_usr32			(__ARM_NR_BASE+4)
 #define __ARM_NR_set_tls		(__ARM_NR_BASE+5)
 
-/*
- * *NOTE*: This is a ghost syscall private to the kernel.  Only the
- * __kuser_cmpxchg code in entry-armv.S should be aware of its
- * existence.  Don't ever use this from user code.
- */
-
 /*
  * The following syscalls are obsolete and no longer available for EABI.
  */

arch/arm/kernel/entry-header.S

@@ -208,26 +208,21 @@
 #endif
 	.endif
 	msr	spsr_cxsf, \rpsr
-#if defined(CONFIG_CPU_V6)
-	ldr	r0, [sp]
-	strex	r1, r2, [sp]			@ clear the exclusive monitor
-	ldmib	sp, {r1 - pc}^			@ load r1 - pc, cpsr
-#elif defined(CONFIG_CPU_32v6K)
-	clrex					@ clear the exclusive monitor
-	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
-#else
-	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
+	@ We must avoid clrex due to Cortex-A15 erratum #830321
+	sub	r0, sp, #4			@ uninhabited address
+	strex	r1, r2, [r0]			@ clear the exclusive monitor
 #endif
+	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
 	.endm
 
 	.macro	restore_user_regs, fast = 0, offset = 0
 	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
 	ldr	lr, [sp, #\offset + S_PC]!	@ get pc
 	msr	spsr_cxsf, r1			@ save in spsr_svc
-#if defined(CONFIG_CPU_V6)
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
+	@ We must avoid clrex due to Cortex-A15 erratum #830321
 	strex	r1, r2, [sp]			@ clear the exclusive monitor
-#elif defined(CONFIG_CPU_32v6K)
-	clrex					@ clear the exclusive monitor
 #endif
 	.if	\fast
 	ldmdb	sp, {r1 - lr}^			@ get calling r1 - lr
@@ -267,7 +262,10 @@
 	.endif
 	ldr	lr, [sp, #S_SP]			@ top of the stack
 	ldrd	r0, r1, [sp, #S_LR]		@ calling lr and pc
-	clrex					@ clear the exclusive monitor
+
+	@ We must avoid clrex due to Cortex-A15 erratum #830321
+	strex	r2, r1, [sp, #S_LR]		@ clear the exclusive monitor
+
 	stmdb	lr!, {r0, r1, \rpsr}		@ calling lr and rfe context
 	ldmia	sp, {r0 - r12}
 	mov	sp, lr
@@ -288,13 +286,16 @@
 	.endm
 #else	/* ifdef CONFIG_CPU_V7M */
 	.macro	restore_user_regs, fast = 0, offset = 0
-	clrex					@ clear the exclusive monitor
 	mov	r2, sp
 	load_user_sp_lr r2, r3, \offset + S_SP	@ calling sp, lr
 	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
 	ldr	lr, [sp, #\offset + S_PC]	@ get pc
 	add	sp, sp, #\offset + S_SP
 	msr	spsr_cxsf, r1			@ save in spsr_svc
+
+	@ We must avoid clrex due to Cortex-A15 erratum #830321
+	strex	r1, r2, [sp]			@ clear the exclusive monitor
+
 	.if	\fast
 	ldmdb	sp, {r1 - r12}			@ get calling r1 - r12
 	.else

arch/arm/kernel/irq.c

@@ -175,7 +175,7 @@ static bool migrate_one_irq(struct irq_desc *desc)
 	c = irq_data_get_irq_chip(d);
 	if (!c->irq_set_affinity)
 		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
-	else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret)
+	else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret)
 		cpumask_copy(d->affinity, affinity);
 
 	return ret;

arch/arm/kernel/perf_event_cpu.c

@@ -76,21 +76,15 @@ static struct pmu_hw_events *cpu_pmu_get_cpu_events(void)
 
 static void cpu_pmu_enable_percpu_irq(void *data)
 {
-	struct arm_pmu *cpu_pmu = data;
-	struct platform_device *pmu_device = cpu_pmu->plat_device;
-	int irq = platform_get_irq(pmu_device, 0);
+	int irq = *(int *)data;
 
 	enable_percpu_irq(irq, IRQ_TYPE_NONE);
-	cpumask_set_cpu(smp_processor_id(), &cpu_pmu->active_irqs);
 }
 
 static void cpu_pmu_disable_percpu_irq(void *data)
 {
-	struct arm_pmu *cpu_pmu = data;
-	struct platform_device *pmu_device = cpu_pmu->plat_device;
-	int irq = platform_get_irq(pmu_device, 0);
+	int irq = *(int *)data;
 
-	cpumask_clear_cpu(smp_processor_id(), &cpu_pmu->active_irqs);
 	disable_percpu_irq(irq);
 }
 
@@ -103,7 +97,7 @@ static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
 
 	irq = platform_get_irq(pmu_device, 0);
 	if (irq >= 0 && irq_is_percpu(irq)) {
-		on_each_cpu(cpu_pmu_disable_percpu_irq, cpu_pmu, 1);
+		on_each_cpu(cpu_pmu_disable_percpu_irq, &irq, 1);
 		free_percpu_irq(irq, &percpu_pmu);
 	} else {
 		for (i = 0; i < irqs; ++i) {
@@ -138,7 +132,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 				irq);
 			return err;
 		}
-		on_each_cpu(cpu_pmu_enable_percpu_irq, cpu_pmu, 1);
+		on_each_cpu(cpu_pmu_enable_percpu_irq, &irq, 1);
 	} else {
 		for (i = 0; i < irqs; ++i) {
 			err = 0;

arch/arm/kernel/perf_event_v7.c

@@ -157,6 +157,7 @@ static const unsigned armv7_a8_perf_map[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= ARMV7_A8_PERFCTR_STALL_ISIDE,
 	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_REF_CPU_CYCLES]	= HW_OP_UNSUPPORTED,
 };
 
 static const unsigned armv7_a8_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
@@ -281,6 +282,7 @@ static const unsigned armv7_a9_perf_map[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= ARMV7_A9_PERFCTR_STALL_ICACHE,
 	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= ARMV7_A9_PERFCTR_STALL_DISPATCH,
+	[PERF_COUNT_HW_REF_CPU_CYCLES]	= HW_OP_UNSUPPORTED,
 };
 
 static const unsigned armv7_a9_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
@@ -405,6 +407,7 @@ static const unsigned armv7_a5_perf_map[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_REF_CPU_CYCLES] = HW_OP_UNSUPPORTED,
 };
 
 static const unsigned armv7_a5_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
@@ -527,6 +530,7 @@ static const unsigned armv7_a15_perf_map[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV7_PERFCTR_BUS_CYCLES,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_REF_CPU_CYCLES] = HW_OP_UNSUPPORTED,
 };
 
 static const unsigned armv7_a15_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
@@ -651,6 +655,7 @@ static const unsigned armv7_a7_perf_map[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV7_PERFCTR_BUS_CYCLES,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_REF_CPU_CYCLES] = HW_OP_UNSUPPORTED,
 };
 
 static const unsigned armv7_a7_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]

arch/arm/kernel/process.c

@@ -334,6 +334,8 @@ void flush_thread(void)
 	memset(&tsk->thread.debug, 0, sizeof(struct debug_info));
 	memset(&thread->fpstate, 0, sizeof(union fp_state));
 
+	flush_tls();
+
 	thread_notify(THREAD_NOTIFY_FLUSH, thread);
 }
 

arch/arm/kernel/thumbee.c

@@ -45,7 +45,7 @@ static int thumbee_notifier(struct notifier_block *self, unsigned long cmd, void
 
 	switch (cmd) {
 	case THREAD_NOTIFY_FLUSH:
-		thread->thumbee_state = 0;
+		teehbr_write(0);
 		break;
 	case THREAD_NOTIFY_SWITCH:
 		current_thread_info()->thumbee_state = teehbr_read();

arch/arm/kernel/traps.c

@@ -579,7 +579,6 @@ do_cache_op(unsigned long start, unsigned long end, int flags)
 #define NR(x) ((__ARM_NR_##x) - __ARM_NR_BASE)
 asmlinkage int arm_syscall(int no, struct pt_regs *regs)
 {
-	struct thread_info *thread = current_thread_info();
 	siginfo_t info;
 
 	if ((no >> 16) != (__ARM_NR_BASE>> 16))
@@ -630,21 +629,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs)
 		return regs->ARM_r0;
 
 	case NR(set_tls):
-		thread->tp_value[0] = regs->ARM_r0;
-		if (tls_emu)
-			return 0;
-		if (has_tls_reg) {
-			asm ("mcr p15, 0, %0, c13, c0, 3"
-				: : "r" (regs->ARM_r0));
-		} else {
-			/*
-			 * User space must never try to access this directly.
-			 * Expect your app to break eventually if you do so.
-			 * The user helper at 0xffff0fe0 must be used instead.
-			 * (see entry-armv.S for details)
-			 */
-			*((unsigned int *)0xffff0ff0) = regs->ARM_r0;
-		}
+		set_tls(regs->ARM_r0);
 		return 0;
 
 #ifdef CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG

arch/arm/kvm/handle_exit.c

@@ -93,6 +93,8 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	else
 		kvm_vcpu_block(vcpu);
 
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+
 	return 1;
 }
 

arch/arm/kvm/init.S

@@ -98,6 +98,10 @@ __do_hyp_init:
 	mrc	p15, 0, r0, c10, c2, 1
 	mcr	p15, 4, r0, c10, c2, 1
 
+	@ Invalidate the stale TLBs from Bootloader
+	mcr	p15, 4, r0, c8, c7, 0	@ TLBIALLH
+	dsb	ish
+
 	@ Set the HSCTLR to:
 	@  - ARM/THUMB exceptions: Kernel config (Thumb-2 kernel)
 	@  - Endianness: Kernel config

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);
 

arch/arm/mach-exynos/mcpm-exynos.c

@@ -39,7 +39,6 @@
 	"mcr	p15, 0, r0, c1, c0, 0	@ set SCTLR\n\t" \
 	"isb\n\t"\
 	"bl	v7_flush_dcache_"__stringify(level)"\n\t" \
-	"clrex\n\t"\
 	"mrc	p15, 0, r0, c1, c0, 1	@ get ACTLR\n\t" \
 	"bic	r0, r0, #(1 << 6)	@ disable local coherency\n\t" \
 	/* Dummy Load of a device register to avoid Erratum 799270 */ \

arch/arm/mach-imx/clk-gate2.c

@@ -97,7 +97,7 @@ static int clk_gate2_is_enabled(struct clk_hw *hw)
 	struct clk_gate2 *gate = to_clk_gate2(hw);
 
 	if (gate->share_count)
-		return !!(*gate->share_count);
+		return !!__clk_get_enable_count(hw->clk);
 	else
 		return clk_gate2_reg_is_enabled(gate->reg, gate->bit_idx);
 }
@@ -127,10 +127,6 @@ struct clk *clk_register_gate2(struct device *dev, const char *name,
 	gate->bit_idx = bit_idx;
 	gate->flags = clk_gate2_flags;
 	gate->lock = lock;
-
-	/* Initialize share_count per hardware state */
-	if (share_count)
-		*share_count = clk_gate2_reg_is_enabled(reg, bit_idx) ? 1 : 0;
 	gate->share_count = share_count;
 
 	init.name = name;

arch/arm/mach-imx/suspend-imx6.S

@@ -172,6 +172,8 @@ ENTRY(imx6_suspend)
 	ldr	r6, [r11, #0x0]
 	ldr	r11, [r0, #PM_INFO_MX6Q_GPC_V_OFFSET]
 	ldr	r6, [r11, #0x0]
+	ldr	r11, [r0, #PM_INFO_MX6Q_IOMUXC_V_OFFSET]
+	ldr	r6, [r11, #0x0]
 
 	/* use r11 to store the IO address */
 	ldr	r11, [r0, #PM_INFO_MX6Q_SRC_V_OFFSET]

arch/arm/mach-omap2/control.c

@@ -314,7 +314,8 @@ void omap3_save_scratchpad_contents(void)
 		scratchpad_contents.public_restore_ptr =
 			virt_to_phys(omap3_restore_3630);
 	else if (omap_rev() != OMAP3430_REV_ES3_0 &&
-					omap_rev() != OMAP3430_REV_ES3_1)
+					omap_rev() != OMAP3430_REV_ES3_1 &&
+					omap_rev() != OMAP3430_REV_ES3_1_2)
 		scratchpad_contents.public_restore_ptr =
 			virt_to_phys(omap3_restore);
 	else

arch/arm/mach-omap2/omap_hwmod.c

@@ -2185,6 +2185,8 @@ static int _enable(struct omap_hwmod *oh)
 			 oh->mux->pads_dynamic))) {
 		omap_hwmod_mux(oh->mux, _HWMOD_STATE_ENABLED);
 		_reconfigure_io_chain();
+	} else if (oh->flags & HWMOD_FORCE_MSTANDBY) {
+		_reconfigure_io_chain();
 	}
 
 	_add_initiator_dep(oh, mpu_oh);
@@ -2291,6 +2293,8 @@ static int _idle(struct omap_hwmod *oh)
 	if (oh->mux && oh->mux->pads_dynamic) {
 		omap_hwmod_mux(oh->mux, _HWMOD_STATE_IDLE);
 		_reconfigure_io_chain();
+	} else if (oh->flags & HWMOD_FORCE_MSTANDBY) {
+		_reconfigure_io_chain();
 	}
 
 	oh->_state = _HWMOD_STATE_IDLE;
@@ -3345,6 +3349,9 @@ int __init omap_hwmod_register_links(struct omap_hwmod_ocp_if **ois)
 	if (!ois)
 		return 0;
 
+	if (ois[0] == NULL) /* Empty list */
+		return 0;
+
 	if (!linkspace) {
 		if (_alloc_linkspace(ois)) {
 			pr_err("omap_hwmod: could not allocate link space\n");

arch/arm/mach-omap2/omap_hwmod_7xx_data.c

@@ -35,6 +35,7 @@
 #include "i2c.h"
 #include "mmc.h"
 #include "wd_timer.h"
+#include "soc.h"
 
 /* Base offset for all DRA7XX interrupts external to MPUSS */
 #define DRA7XX_IRQ_GIC_START	32
@@ -2705,7 +2706,6 @@ static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = {
 	&dra7xx_l4_per3__usb_otg_ss1,
 	&dra7xx_l4_per3__usb_otg_ss2,
 	&dra7xx_l4_per3__usb_otg_ss3,
-	&dra7xx_l4_per3__usb_otg_ss4,
 	&dra7xx_l3_main_1__vcp1,
 	&dra7xx_l4_per2__vcp1,
 	&dra7xx_l3_main_1__vcp2,
@@ -2714,8 +2714,26 @@ static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = {
 	NULL,
 };
 
+static struct omap_hwmod_ocp_if *dra74x_hwmod_ocp_ifs[] __initdata = {
+	&dra7xx_l4_per3__usb_otg_ss4,
+	NULL,
+};
+
+static struct omap_hwmod_ocp_if *dra72x_hwmod_ocp_ifs[] __initdata = {
+	NULL,
+};
+
 int __init dra7xx_hwmod_init(void)
 {
+	int ret;
+
 	omap_hwmod_init();
-	return omap_hwmod_register_links(dra7xx_hwmod_ocp_ifs);
+	ret = omap_hwmod_register_links(dra7xx_hwmod_ocp_ifs);
+
+	if (!ret && soc_is_dra74x())
+		return omap_hwmod_register_links(dra74x_hwmod_ocp_ifs);
+	else if (!ret && soc_is_dra72x())
+		return omap_hwmod_register_links(dra72x_hwmod_ocp_ifs);
+
+	return ret;
 }

arch/arm/mach-omap2/soc.h

@@ -245,6 +245,8 @@ IS_AM_SUBCLASS(437x, 0x437)
 #define soc_is_omap54xx()		0
 #define soc_is_omap543x()		0
 #define soc_is_dra7xx()			0
+#define soc_is_dra74x()			0
+#define soc_is_dra72x()			0
 
 #if defined(MULTI_OMAP2)
 # if defined(CONFIG_ARCH_OMAP2)
@@ -393,7 +395,11 @@ IS_OMAP_TYPE(3430, 0x3430)
 
 #if defined(CONFIG_SOC_DRA7XX)
 #undef soc_is_dra7xx
+#undef soc_is_dra74x
+#undef soc_is_dra72x
 #define soc_is_dra7xx()	(of_machine_is_compatible("ti,dra7"))
+#define soc_is_dra74x()	(of_machine_is_compatible("ti,dra74"))
+#define soc_is_dra72x()	(of_machine_is_compatible("ti,dra72"))
 #endif
 
 /* Various silicon revisions for omap2 */

arch/arm/mm/abort-ev6.S

@@ -17,12 +17,6 @@
  */
 	.align	5
 ENTRY(v6_early_abort)
-#ifdef CONFIG_CPU_V6
-	sub	r1, sp, #4			@ Get unused stack location
-	strex	r0, r1, [r1]			@ Clear the exclusive monitor
-#elif defined(CONFIG_CPU_32v6K)
-	clrex
-#endif
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 /*

arch/arm/mm/abort-ev7.S

@@ -13,12 +13,6 @@
  */
 	.align	5
 ENTRY(v7_early_abort)
-	/*
-	 * The effect of data aborts on on the exclusive access monitor are
-	 * UNPREDICTABLE. Do a CLREX to clear the state
-	 */
-	clrex
-
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 

arch/arm/mm/alignment.c

@@ -41,6 +41,7 @@
  * This code is not portable to processors with late data abort handling.
  */
 #define CODING_BITS(i)	(i & 0x0e000000)
+#define COND_BITS(i)	(i & 0xf0000000)
 
 #define LDST_I_BIT(i)	(i & (1 << 26))		/* Immediate constant	*/
 #define LDST_P_BIT(i)	(i & (1 << 24))		/* Preindex		*/
@@ -819,6 +820,8 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 		break;
 
 	case 0x04000000:	/* ldr or str immediate */
+		if (COND_BITS(instr) == 0xf0000000) /* NEON VLDn, VSTn */
+			goto bad;
 		offset.un = OFFSET_BITS(instr);
 		handler = do_alignment_ldrstr;
 		break;

arch/arm64/include/asm/cacheflush.h

@@ -138,19 +138,10 @@ static inline void __flush_icache_all(void)
 #define flush_icache_page(vma,page)	do { } while (0)
 
 /*
- * flush_cache_vmap() is used when creating mappings (eg, via vmap,
- * vmalloc, ioremap etc) in kernel space for pages.  On non-VIPT
- * caches, since the direct-mappings of these pages may contain cached
- * data, we need to do a full cache flush to ensure that writebacks
- * don't corrupt data placed into these pages via the new mappings.
+ * Not required on AArch64 (PIPT or VIPT non-aliasing D-cache).
  */
 static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 {
-	/*
-	 * set_pte_at() called from vmap_pte_range() does not
-	 * have a DSB after cleaning the cache line.
-	 */
-	dsb(ish);
 }
 
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)

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;

arch/arm64/include/asm/hw_breakpoint.h

@@ -79,7 +79,6 @@ static inline void decode_ctrl_reg(u32 reg,
  */
 #define ARM_MAX_BRP		16
 #define ARM_MAX_WRP		16
-#define ARM_MAX_HBP_SLOTS	(ARM_MAX_BRP + ARM_MAX_WRP)
 
 /* Virtual debug register bases. */
 #define AARCH64_DBG_REG_BVR	0

arch/arm64/include/asm/pgtable.h

@@ -138,6 +138,8 @@ extern struct page *empty_zero_page;
 
 #define pte_valid_user(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
+#define pte_valid_not_user(pte) \
+	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
 
 static inline pte_t pte_wrprotect(pte_t pte)
 {
@@ -184,6 +186,15 @@ static inline pte_t pte_mkspecial(pte_t pte)
 static inline void set_pte(pte_t *ptep, pte_t pte)
 {
 	*ptep = pte;
+
+	/*
+	 * Only if the new pte is valid and kernel, otherwise TLB maintenance
+	 * or update_mmu_cache() have the necessary barriers.
+	 */
+	if (pte_valid_not_user(pte)) {
+		dsb(ishst);
+		isb();
+	}
 }
 
 extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
@@ -303,6 +314,7 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
 	*pmdp = pmd;
 	dsb(ishst);
+	isb();
 }
 
 static inline void pmd_clear(pmd_t *pmdp)
@@ -333,6 +345,7 @@ static inline void set_pud(pud_t *pudp, pud_t pud)
 {
 	*pudp = pud;
 	dsb(ishst);
+	isb();
 }
 
 static inline void pud_clear(pud_t *pudp)

arch/arm64/include/asm/ptrace.h

@@ -137,7 +137,7 @@ struct pt_regs {
 	(!((regs)->pstate & PSR_F_BIT))
 
 #define user_stack_pointer(regs) \
-	(!compat_user_mode(regs)) ? ((regs)->sp) : ((regs)->compat_sp)
+	(!compat_user_mode(regs) ? (regs)->sp : (regs)->compat_sp)
 
 static inline unsigned long regs_return_value(struct pt_regs *regs)
 {

arch/arm64/include/asm/tlbflush.h

@@ -122,6 +122,7 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end
 	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
 		asm("tlbi vaae1is, %0" : : "r"(addr));
 	dsb(ish);
+	isb();
 }
 
 /*
@@ -131,8 +132,8 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 				    unsigned long addr, pte_t *ptep)
 {
 	/*
-	 * set_pte() does not have a DSB, so make sure that the page table
-	 * write is visible.
+	 * set_pte() does not have a DSB for user mappings, so make sure that
+	 * the page table write is visible.
 	 */
 	dsb(ishst);
 }

arch/arm64/kernel/debug-monitors.c

@@ -315,20 +315,20 @@ static int brk_handler(unsigned long addr, unsigned int esr,
 {
 	siginfo_t info;
 
-	if (call_break_hook(regs, esr) == DBG_HOOK_HANDLED)
-		return 0;
+	if (user_mode(regs)) {
+		info = (siginfo_t) {
+			.si_signo = SIGTRAP,
+			.si_errno = 0,
+			.si_code  = TRAP_BRKPT,
+			.si_addr  = (void __user *)instruction_pointer(regs),
+		};
 
-	if (!user_mode(regs))
+		force_sig_info(SIGTRAP, &info, current);
+	} else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) {
+		pr_warning("Unexpected kernel BRK exception at EL1\n");
 		return -EFAULT;
+	}
 
-	info = (siginfo_t) {
-		.si_signo = SIGTRAP,
-		.si_errno = 0,
-		.si_code  = TRAP_BRKPT,
-		.si_addr  = (void __user *)instruction_pointer(regs),
-	};
-
-	force_sig_info(SIGTRAP, &info, current);
 	return 0;
 }
 

arch/arm64/kernel/efi.c

@@ -464,6 +464,8 @@ static int __init arm64_enter_virtual_mode(void)
 
 	set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 
+	efi.runtime_version = efi.systab->hdr.revision;
+
 	return 0;
 }
 early_initcall(arm64_enter_virtual_mode);

arch/arm64/kernel/entry.S

@@ -298,7 +298,6 @@ el1_dbg:
 	mrs	x0, far_el1
 	mov	x2, sp				// struct pt_regs
 	bl	do_debug_exception
-	enable_dbg
 	kernel_exit 1
 el1_inv:
 	// TODO: add support for undefined instructions in kernel mode

arch/arm64/kernel/irq.c

@@ -97,19 +97,15 @@ static bool migrate_one_irq(struct irq_desc *desc)
 	if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity))
 		return false;
 
-	if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids)
+	if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
+		affinity = cpu_online_mask;
 		ret = true;
+	}
 
-	/*
-	 * when using forced irq_set_affinity we must ensure that the cpu
-	 * being offlined is not present in the affinity mask, it may be
-	 * selected as the target CPU otherwise
-	 */
-	affinity = cpu_online_mask;
 	c = irq_data_get_irq_chip(d);
 	if (!c->irq_set_affinity)
 		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
-	else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret)
+	else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret)
 		cpumask_copy(d->affinity, affinity);
 
 	return ret;

arch/arm64/kernel/process.c

@@ -224,9 +224,27 @@ void exit_thread(void)
 {
 }
 
+static void tls_thread_flush(void)
+{
+	asm ("msr tpidr_el0, xzr");
+
+	if (is_compat_task()) {
+		current->thread.tp_value = 0;
+
+		/*
+		 * We need to ensure ordering between the shadow state and the
+		 * hardware state, so that we don't corrupt the hardware state
+		 * with a stale shadow state during context switch.
+		 */
+		barrier();
+		asm ("msr tpidrro_el0, xzr");
+	}
+}
+
 void flush_thread(void)
 {
 	fpsimd_flush_thread();
+	tls_thread_flush();
 	flush_ptrace_hw_breakpoint(current);
 }
 

arch/arm64/kernel/ptrace.c

@@ -85,7 +85,8 @@ static void ptrace_hbptriggered(struct perf_event *bp,
 			break;
 		}
 	}
-	for (i = ARM_MAX_BRP; i < ARM_MAX_HBP_SLOTS && !bp; ++i) {
+
+	for (i = 0; i < ARM_MAX_WRP; ++i) {
 		if (current->thread.debug.hbp_watch[i] == bp) {
 			info.si_errno = -((i << 1) + 1);
 			break;

arch/arm64/kernel/sys_compat.c

@@ -79,6 +79,12 @@ long compat_arm_syscall(struct pt_regs *regs)
 
 	case __ARM_NR_compat_set_tls:
 		current->thread.tp_value = regs->regs[0];
+
+		/*
+		 * Protect against register corruption from context switch.
+		 * See comment in tls_thread_flush.
+		 */
+		barrier();
 		asm ("msr tpidrro_el0, %0" : : "r" (regs->regs[0]));
 		return 0;
 

arch/arm64/kvm/handle_exit.c

@@ -66,6 +66,8 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	else
 		kvm_vcpu_block(vcpu);
 
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+
 	return 1;
 }
 

arch/arm64/kvm/hyp-init.S

@@ -80,6 +80,10 @@ __do_hyp_init:
 	msr	mair_el2, x4
 	isb
 
+	/* Invalidate the stale TLBs from Bootloader */
+	tlbi	alle2
+	dsb	sy
+
 	mrs	x4, sctlr_el2
 	and	x4, x4, #SCTLR_EL2_EE	// preserve endianness of EL2
 	ldr	x5, =SCTLR_EL2_FLAGS

arch/ia64/pci/fixup.c

@@ -6,6 +6,7 @@
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/vgaarb.h>
+#include <linux/screen_info.h>
 
 #include <asm/machvec.h>
 
@@ -61,8 +62,7 @@ static void pci_fixup_video(struct pci_dev *pdev)
 		pci_read_config_word(pdev, PCI_COMMAND, &config);
 		if (config & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) {
 			pdev->resource[PCI_ROM_RESOURCE].flags |= IORESOURCE_ROM_SHADOW;
-			dev_printk(KERN_DEBUG, &pdev->dev, "Boot video device\n");
-			vga_set_default_device(pdev);
+			dev_printk(KERN_DEBUG, &pdev->dev, "Video device with shadowed ROM\n");
 		}
 	}
 }

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 );
 }

arch/mips/boot/compressed/decompress.c

@@ -13,6 +13,7 @@
 
 #include <linux/types.h>
 #include <linux/kernel.h>
+#include <linux/string.h>
 
 #include <asm/addrspace.h>
 

arch/mips/cavium-octeon/setup.c

@@ -458,6 +458,18 @@ static void octeon_halt(void)
 	octeon_kill_core(NULL);
 }
 
+static char __read_mostly octeon_system_type[80];
+
+static int __init init_octeon_system_type(void)
+{
+	snprintf(octeon_system_type, sizeof(octeon_system_type), "%s (%s)",
+		cvmx_board_type_to_string(octeon_bootinfo->board_type),
+		octeon_model_get_string(read_c0_prid()));
+
+	return 0;
+}
+early_initcall(init_octeon_system_type);
+
 /**
  * Return a string representing the system type
  *
@@ -465,11 +477,7 @@ static void octeon_halt(void)
  */
 const char *octeon_board_type_string(void)
 {
-	static char name[80];
-	sprintf(name, "%s (%s)",
-		cvmx_board_type_to_string(octeon_bootinfo->board_type),
-		octeon_model_get_string(read_c0_prid()));
-	return name;
+	return octeon_system_type;
 }
 
 const char *get_system_type(void)

arch/mips/include/asm/eva.h

@@ -0,0 +1,43 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2014, Imagination Technologies Ltd.
+ *
+ * EVA functions for generic code
+ */
+
+#ifndef _ASM_EVA_H
+#define _ASM_EVA_H
+
+#include <kernel-entry-init.h>
+
+#ifdef __ASSEMBLY__
+
+#ifdef CONFIG_EVA
+
+/*
+ * EVA early init code
+ *
+ * Platforms must define their own 'platform_eva_init' macro in
+ * their kernel-entry-init.h header. This macro usually does the
+ * platform specific configuration of the segmentation registers,
+ * and it is normally called from assembly code.
+ *
+ */
+
+.macro eva_init
+platform_eva_init
+.endm
+
+#else
+
+.macro eva_init
+.endm
+
+#endif /* CONFIG_EVA */
+
+#endif /* __ASSEMBLY__ */
+
+#endif

arch/mips/include/asm/mach-malta/kernel-entry-init.h

@@ -10,14 +10,15 @@
 #ifndef __ASM_MACH_MIPS_KERNEL_ENTRY_INIT_H
 #define __ASM_MACH_MIPS_KERNEL_ENTRY_INIT_H
 
+#include <asm/regdef.h>
+#include <asm/mipsregs.h>
+
 	/*
 	 * Prepare segments for EVA boot:
 	 *
 	 * This is in case the processor boots in legacy configuration
 	 * (SI_EVAReset is de-asserted and CONFIG5.K == 0)
 	 *
-	 * On entry, t1 is loaded with CP0_CONFIG
-	 *
 	 * ========================= Mappings =============================
 	 * Virtual memory           Physical memory           Mapping
 	 * 0x00000000 - 0x7fffffff  0x80000000 - 0xfffffffff   MUSUK (kuseg)
@@ -30,12 +31,20 @@
 	 *
 	 *
 	 * Lowmem is expanded to 2GB
+	 *
+	 * The following code uses the t0, t1, t2 and ra registers without
+	 * previously preserving them.
+	 *
 	 */
-	.macro	eva_entry
+	.macro	platform_eva_init
+
+	.set	push
+	.set	reorder
 	/*
 	 * Get Config.K0 value and use it to program
 	 * the segmentation registers
 	 */
+	mfc0    t1, CP0_CONFIG
 	andi	t1, 0x7 /* CCA */
 	move	t2, t1
 	ins	t2, t1, 16, 3
@@ -77,6 +86,8 @@
 	mtc0    t0, $16, 5
 	sync
 	jal	mips_ihb
+
+	.set	pop
 	.endm
 
 	.macro	kernel_entry_setup
@@ -95,7 +106,7 @@
 	sll     t0, t0, 6   /* SC bit */
 	bgez    t0, 9f
 
-	eva_entry
+	platform_eva_init
 	b       0f
 9:
 	/* Assume we came from YAMON... */
@@ -127,8 +138,7 @@ nonsc_processor:
 #ifdef CONFIG_EVA
 	sync
 	ehb
-	mfc0    t1, CP0_CONFIG
-	eva_entry
+	platform_eva_init
 #endif
 	.endm
 

arch/mips/include/asm/ptrace.h

@@ -23,7 +23,7 @@
 struct pt_regs {
 #ifdef CONFIG_32BIT
 	/* Pad bytes for argument save space on the stack. */
-	unsigned long pad0[6];
+	unsigned long pad0[8];
 #endif
 
 	/* Saved main processor registers. */

arch/mips/include/asm/reg.h

@@ -12,116 +12,194 @@
 #ifndef __ASM_MIPS_REG_H
 #define __ASM_MIPS_REG_H
 
-
-#if defined(CONFIG_32BIT) || defined(WANT_COMPAT_REG_H)
-
-#define EF_R0			6
-#define EF_R1			7
-#define EF_R2			8
-#define EF_R3			9
-#define EF_R4			10
-#define EF_R5			11
-#define EF_R6			12
-#define EF_R7			13
-#define EF_R8			14
-#define EF_R9			15
-#define EF_R10			16
-#define EF_R11			17
-#define EF_R12			18
-#define EF_R13			19
-#define EF_R14			20
-#define EF_R15			21
-#define EF_R16			22
-#define EF_R17			23
-#define EF_R18			24
-#define EF_R19			25
-#define EF_R20			26
-#define EF_R21			27
-#define EF_R22			28
-#define EF_R23			29
-#define EF_R24			30
-#define EF_R25			31
+#define MIPS32_EF_R0		6
+#define MIPS32_EF_R1		7
+#define MIPS32_EF_R2		8
+#define MIPS32_EF_R3		9
+#define MIPS32_EF_R4		10
+#define MIPS32_EF_R5		11
+#define MIPS32_EF_R6		12
+#define MIPS32_EF_R7		13
+#define MIPS32_EF_R8		14
+#define MIPS32_EF_R9		15
+#define MIPS32_EF_R10		16
+#define MIPS32_EF_R11		17
+#define MIPS32_EF_R12		18
+#define MIPS32_EF_R13		19
+#define MIPS32_EF_R14		20
+#define MIPS32_EF_R15		21
+#define MIPS32_EF_R16		22
+#define MIPS32_EF_R17		23
+#define MIPS32_EF_R18		24
+#define MIPS32_EF_R19		25
+#define MIPS32_EF_R20		26
+#define MIPS32_EF_R21		27
+#define MIPS32_EF_R22		28
+#define MIPS32_EF_R23		29
+#define MIPS32_EF_R24		30
+#define MIPS32_EF_R25		31
 
 /*
  * k0/k1 unsaved
  */
-#define EF_R26			32
-#define EF_R27			33
+#define MIPS32_EF_R26		32
+#define MIPS32_EF_R27		33
 
-#define EF_R28			34
-#define EF_R29			35
-#define EF_R30			36
-#define EF_R31			37
+#define MIPS32_EF_R28		34
+#define MIPS32_EF_R29		35
+#define MIPS32_EF_R30		36
+#define MIPS32_EF_R31		37
 
 /*
  * Saved special registers
  */
-#define EF_LO			38
-#define EF_HI			39
+#define MIPS32_EF_LO		38
+#define MIPS32_EF_HI		39
 
-#define EF_CP0_EPC		40
-#define EF_CP0_BADVADDR		41
-#define EF_CP0_STATUS		42
-#define EF_CP0_CAUSE		43
-#define EF_UNUSED0		44
+#define MIPS32_EF_CP0_EPC	40
+#define MIPS32_EF_CP0_BADVADDR	41
+#define MIPS32_EF_CP0_STATUS	42
+#define MIPS32_EF_CP0_CAUSE	43
+#define MIPS32_EF_UNUSED0	44
 
-#define EF_SIZE			180
+#define MIPS32_EF_SIZE		180
 
-#endif
-
-#if defined(CONFIG_64BIT) && !defined(WANT_COMPAT_REG_H)
-
-#define EF_R0			 0
-#define EF_R1			 1
-#define EF_R2			 2
-#define EF_R3			 3
-#define EF_R4			 4
-#define EF_R5			 5
-#define EF_R6			 6
-#define EF_R7			 7
-#define EF_R8			 8
-#define EF_R9			 9
-#define EF_R10			10
-#define EF_R11			11
-#define EF_R12			12
-#define EF_R13			13
-#define EF_R14			14
-#define EF_R15			15
-#define EF_R16			16
-#define EF_R17			17
-#define EF_R18			18
-#define EF_R19			19
-#define EF_R20			20
-#define EF_R21			21
-#define EF_R22			22
-#define EF_R23			23
-#define EF_R24			24
-#define EF_R25			25
+#define MIPS64_EF_R0		0
+#define MIPS64_EF_R1		1
+#define MIPS64_EF_R2		2
+#define MIPS64_EF_R3		3
+#define MIPS64_EF_R4		4
+#define MIPS64_EF_R5		5
+#define MIPS64_EF_R6		6
+#define MIPS64_EF_R7		7
+#define MIPS64_EF_R8		8
+#define MIPS64_EF_R9		9
+#define MIPS64_EF_R10		10
+#define MIPS64_EF_R11		11
+#define MIPS64_EF_R12		12
+#define MIPS64_EF_R13		13
+#define MIPS64_EF_R14		14
+#define MIPS64_EF_R15		15
+#define MIPS64_EF_R16		16
+#define MIPS64_EF_R17		17
+#define MIPS64_EF_R18		18
+#define MIPS64_EF_R19		19
+#define MIPS64_EF_R20		20
+#define MIPS64_EF_R21		21
+#define MIPS64_EF_R22		22
+#define MIPS64_EF_R23		23
+#define MIPS64_EF_R24		24
+#define MIPS64_EF_R25		25
 
 /*
  * k0/k1 unsaved
  */
-#define EF_R26			26
-#define EF_R27			27
+#define MIPS64_EF_R26		26
+#define MIPS64_EF_R27		27
 
 
-#define EF_R28			28
-#define EF_R29			29
-#define EF_R30			30
-#define EF_R31			31
+#define MIPS64_EF_R28		28
+#define MIPS64_EF_R29		29
+#define MIPS64_EF_R30		30
+#define MIPS64_EF_R31		31
 
 /*
  * Saved special registers
  */
-#define EF_LO			32
-#define EF_HI			33
+#define MIPS64_EF_LO		32
+#define MIPS64_EF_HI		33
 
-#define EF_CP0_EPC		34
-#define EF_CP0_BADVADDR		35
-#define EF_CP0_STATUS		36
-#define EF_CP0_CAUSE		37
+#define MIPS64_EF_CP0_EPC	34
+#define MIPS64_EF_CP0_BADVADDR	35
+#define MIPS64_EF_CP0_STATUS	36
+#define MIPS64_EF_CP0_CAUSE	37
 
-#define EF_SIZE			304	/* size in bytes */
+#define MIPS64_EF_SIZE		304	/* size in bytes */
+
+#if defined(CONFIG_32BIT)
+
+#define EF_R0			MIPS32_EF_R0
+#define EF_R1			MIPS32_EF_R1
+#define EF_R2			MIPS32_EF_R2
+#define EF_R3			MIPS32_EF_R3
+#define EF_R4			MIPS32_EF_R4
+#define EF_R5			MIPS32_EF_R5
+#define EF_R6			MIPS32_EF_R6
+#define EF_R7			MIPS32_EF_R7
+#define EF_R8			MIPS32_EF_R8
+#define EF_R9			MIPS32_EF_R9
+#define EF_R10			MIPS32_EF_R10
+#define EF_R11			MIPS32_EF_R11
+#define EF_R12			MIPS32_EF_R12
+#define EF_R13			MIPS32_EF_R13
+#define EF_R14			MIPS32_EF_R14
+#define EF_R15			MIPS32_EF_R15
+#define EF_R16			MIPS32_EF_R16
+#define EF_R17			MIPS32_EF_R17
+#define EF_R18			MIPS32_EF_R18
+#define EF_R19			MIPS32_EF_R19
+#define EF_R20			MIPS32_EF_R20
+#define EF_R21			MIPS32_EF_R21
+#define EF_R22			MIPS32_EF_R22
+#define EF_R23			MIPS32_EF_R23
+#define EF_R24			MIPS32_EF_R24
+#define EF_R25			MIPS32_EF_R25
+#define EF_R26			MIPS32_EF_R26
+#define EF_R27			MIPS32_EF_R27
+#define EF_R28			MIPS32_EF_R28
+#define EF_R29			MIPS32_EF_R29
+#define EF_R30			MIPS32_EF_R30
+#define EF_R31			MIPS32_EF_R31
+#define EF_LO			MIPS32_EF_LO
+#define EF_HI			MIPS32_EF_HI
+#define EF_CP0_EPC		MIPS32_EF_CP0_EPC
+#define EF_CP0_BADVADDR		MIPS32_EF_CP0_BADVADDR
+#define EF_CP0_STATUS		MIPS32_EF_CP0_STATUS
+#define EF_CP0_CAUSE		MIPS32_EF_CP0_CAUSE
+#define EF_UNUSED0		MIPS32_EF_UNUSED0
+#define EF_SIZE			MIPS32_EF_SIZE
+
+#elif defined(CONFIG_64BIT)
+
+#define EF_R0			MIPS64_EF_R0
+#define EF_R1			MIPS64_EF_R1
+#define EF_R2			MIPS64_EF_R2
+#define EF_R3			MIPS64_EF_R3
+#define EF_R4			MIPS64_EF_R4
+#define EF_R5			MIPS64_EF_R5
+#define EF_R6			MIPS64_EF_R6
+#define EF_R7			MIPS64_EF_R7
+#define EF_R8			MIPS64_EF_R8
+#define EF_R9			MIPS64_EF_R9
+#define EF_R10			MIPS64_EF_R10
+#define EF_R11			MIPS64_EF_R11
+#define EF_R12			MIPS64_EF_R12
+#define EF_R13			MIPS64_EF_R13
+#define EF_R14			MIPS64_EF_R14
+#define EF_R15			MIPS64_EF_R15
+#define EF_R16			MIPS64_EF_R16
+#define EF_R17			MIPS64_EF_R17
+#define EF_R18			MIPS64_EF_R18
+#define EF_R19			MIPS64_EF_R19
+#define EF_R20			MIPS64_EF_R20
+#define EF_R21			MIPS64_EF_R21
+#define EF_R22			MIPS64_EF_R22
+#define EF_R23			MIPS64_EF_R23
+#define EF_R24			MIPS64_EF_R24
+#define EF_R25			MIPS64_EF_R25
+#define EF_R26			MIPS64_EF_R26
+#define EF_R27			MIPS64_EF_R27
+#define EF_R28			MIPS64_EF_R28
+#define EF_R29			MIPS64_EF_R29
+#define EF_R30			MIPS64_EF_R30
+#define EF_R31			MIPS64_EF_R31
+#define EF_LO			MIPS64_EF_LO
+#define EF_HI			MIPS64_EF_HI
+#define EF_CP0_EPC		MIPS64_EF_CP0_EPC
+#define EF_CP0_BADVADDR		MIPS64_EF_CP0_BADVADDR
+#define EF_CP0_STATUS		MIPS64_EF_CP0_STATUS
+#define EF_CP0_CAUSE		MIPS64_EF_CP0_CAUSE
+#define EF_SIZE			MIPS64_EF_SIZE
 
 #endif /* CONFIG_64BIT */
 

arch/mips/include/asm/syscall.h

@@ -131,10 +131,12 @@ static inline int syscall_get_arch(void)
 {
 	int arch = EM_MIPS;
 #ifdef CONFIG_64BIT
-	if (!test_thread_flag(TIF_32BIT_REGS))
+	if (!test_thread_flag(TIF_32BIT_REGS)) {
 		arch |= __AUDIT_ARCH_64BIT;
-	if (test_thread_flag(TIF_32BIT_ADDR))
-		arch |= __AUDIT_ARCH_CONVENTION_MIPS64_N32;
+		/* N32 sets only TIF_32BIT_ADDR */
+		if (test_thread_flag(TIF_32BIT_ADDR))
+			arch |= __AUDIT_ARCH_CONVENTION_MIPS64_N32;
+	}
 #endif
 #if defined(__LITTLE_ENDIAN)
 	arch |=  __AUDIT_ARCH_LE;

arch/mips/kernel/binfmt_elfo32.c

@@ -72,12 +72,6 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
 
 #include <asm/processor.h>
 
-/*
- * When this file is selected, we are definitely running a 64bit kernel.
- * So using the right regs define in asm/reg.h
- */
-#define WANT_COMPAT_REG_H
-
 /* These MUST be defined before elf.h gets included */
 extern void elf32_core_copy_regs(elf_gregset_t grp, struct pt_regs *regs);
 #define ELF_CORE_COPY_REGS(_dest, _regs) elf32_core_copy_regs(_dest, _regs);
@@ -149,21 +143,21 @@ void elf32_core_copy_regs(elf_gregset_t grp, struct pt_regs *regs)
 {
 	int i;
 
-	for (i = 0; i < EF_R0; i++)
+	for (i = 0; i < MIPS32_EF_R0; i++)
 		grp[i] = 0;
-	grp[EF_R0] = 0;
+	grp[MIPS32_EF_R0] = 0;
 	for (i = 1; i <= 31; i++)
-		grp[EF_R0 + i] = (elf_greg_t) regs->regs[i];
-	grp[EF_R26] = 0;
-	grp[EF_R27] = 0;
-	grp[EF_LO] = (elf_greg_t) regs->lo;
-	grp[EF_HI] = (elf_greg_t) regs->hi;
-	grp[EF_CP0_EPC] = (elf_greg_t) regs->cp0_epc;
-	grp[EF_CP0_BADVADDR] = (elf_greg_t) regs->cp0_badvaddr;
-	grp[EF_CP0_STATUS] = (elf_greg_t) regs->cp0_status;
-	grp[EF_CP0_CAUSE] = (elf_greg_t) regs->cp0_cause;
-#ifdef EF_UNUSED0
-	grp[EF_UNUSED0] = 0;
+		grp[MIPS32_EF_R0 + i] = (elf_greg_t) regs->regs[i];
+	grp[MIPS32_EF_R26] = 0;
+	grp[MIPS32_EF_R27] = 0;
+	grp[MIPS32_EF_LO] = (elf_greg_t) regs->lo;
+	grp[MIPS32_EF_HI] = (elf_greg_t) regs->hi;
+	grp[MIPS32_EF_CP0_EPC] = (elf_greg_t) regs->cp0_epc;
+	grp[MIPS32_EF_CP0_BADVADDR] = (elf_greg_t) regs->cp0_badvaddr;
+	grp[MIPS32_EF_CP0_STATUS] = (elf_greg_t) regs->cp0_status;
+	grp[MIPS32_EF_CP0_CAUSE] = (elf_greg_t) regs->cp0_cause;
+#ifdef MIPS32_EF_UNUSED0
+	grp[MIPS32_EF_UNUSED0] = 0;
 #endif
 }
 

arch/mips/kernel/cps-vec.S

@@ -13,6 +13,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/asmmacro.h>
 #include <asm/cacheops.h>
+#include <asm/eva.h>
 #include <asm/mipsregs.h>
 #include <asm/mipsmtregs.h>
 #include <asm/pm.h>
@@ -166,6 +167,9 @@ dcache_done:
 1:	jal	mips_cps_core_init
 	 nop
 
+	/* Do any EVA initialization if necessary */
+	eva_init
+
 	/*
 	 * Boot any other VPEs within this core that should be online, and
 	 * deactivate this VPE if it should be offline.

arch/mips/kernel/irq-gic.c

@@ -269,11 +269,13 @@ static void __init gic_setup_intr(unsigned int intr, unsigned int cpu,
 
 	/* Setup Intr to Pin mapping */
 	if (pin & GIC_MAP_TO_NMI_MSK) {
+		int i;
+
 		GICWRITE(GIC_REG_ADDR(SHARED, GIC_SH_MAP_TO_PIN(intr)), pin);
 		/* FIXME: hack to route NMI to all cpu's */
-		for (cpu = 0; cpu < NR_CPUS; cpu += 32) {
+		for (i = 0; i < NR_CPUS; i += 32) {
 			GICWRITE(GIC_REG_ADDR(SHARED,
-					  GIC_SH_MAP_TO_VPE_REG_OFF(intr, cpu)),
+					  GIC_SH_MAP_TO_VPE_REG_OFF(intr, i)),
 				 0xffffffff);
 		}
 	} else {

arch/mips/kernel/mcount.S

@@ -123,7 +123,11 @@ NESTED(_mcount, PT_SIZE, ra)
 	 nop
 #endif
 	b	ftrace_stub
+#ifdef CONFIG_32BIT
+	 addiu sp, sp, 8
+#else
 	 nop
+#endif
 
 static_trace:
 	MCOUNT_SAVE_REGS
@@ -133,6 +137,9 @@ static_trace:
 	 move	a1, AT		/* arg2: parent's return address */
 
 	MCOUNT_RESTORE_REGS
+#ifdef CONFIG_32BIT
+	addiu sp, sp, 8
+#endif
 	.globl ftrace_stub
 ftrace_stub:
 	RETURN_BACK
@@ -177,6 +184,11 @@ NESTED(ftrace_graph_caller, PT_SIZE, ra)
 	jal	prepare_ftrace_return
 	 nop
 	MCOUNT_RESTORE_REGS
+#ifndef CONFIG_DYNAMIC_FTRACE
+#ifdef CONFIG_32BIT
+	addiu sp, sp, 8
+#endif
+#endif
 	RETURN_BACK
 	END(ftrace_graph_caller)
 

arch/mips/kernel/ptrace.c

@@ -129,7 +129,7 @@ int ptrace_getfpregs(struct task_struct *child, __u32 __user *data)
 	}
 
 	__put_user(child->thread.fpu.fcr31, data + 64);
-	__put_user(current_cpu_data.fpu_id, data + 65);
+	__put_user(boot_cpu_data.fpu_id, data + 65);
 
 	return 0;
 }
@@ -151,6 +151,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data)
 	}
 
 	__get_user(child->thread.fpu.fcr31, data + 64);
+	child->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X;
 
 	/* FIR may not be written.  */
 
@@ -246,36 +247,160 @@ int ptrace_set_watch_regs(struct task_struct *child,
 
 /* regset get/set implementations */
 
-static int gpr_get(struct task_struct *target,
-		   const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   void *kbuf, void __user *ubuf)
+#if defined(CONFIG_32BIT) || defined(CONFIG_MIPS32_O32)
+
+static int gpr32_get(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     void *kbuf, void __user *ubuf)
 {
 	struct pt_regs *regs = task_pt_regs(target);
+	u32 uregs[ELF_NGREG] = {};
+	unsigned i;
 
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				   regs, 0, sizeof(*regs));
+	for (i = MIPS32_EF_R1; i <= MIPS32_EF_R31; i++) {
+		/* k0/k1 are copied as zero. */
+		if (i == MIPS32_EF_R26 || i == MIPS32_EF_R27)
+			continue;
+
+		uregs[i] = regs->regs[i - MIPS32_EF_R0];
+	}
+
+	uregs[MIPS32_EF_LO] = regs->lo;
+	uregs[MIPS32_EF_HI] = regs->hi;
+	uregs[MIPS32_EF_CP0_EPC] = regs->cp0_epc;
+	uregs[MIPS32_EF_CP0_BADVADDR] = regs->cp0_badvaddr;
+	uregs[MIPS32_EF_CP0_STATUS] = regs->cp0_status;
+	uregs[MIPS32_EF_CP0_CAUSE] = regs->cp0_cause;
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs, 0,
+				   sizeof(uregs));
 }
 
-static int gpr_set(struct task_struct *target,
-		   const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   const void *kbuf, const void __user *ubuf)
+static int gpr32_set(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     const void *kbuf, const void __user *ubuf)
 {
-	struct pt_regs newregs;
-	int ret;
+	struct pt_regs *regs = task_pt_regs(target);
+	u32 uregs[ELF_NGREG];
+	unsigned start, num_regs, i;
+	int err;
 
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 &newregs,
-				 0, sizeof(newregs));
-	if (ret)
-		return ret;
+	start = pos / sizeof(u32);
+	num_regs = count / sizeof(u32);
 
-	*task_pt_regs(target) = newregs;
+	if (start + num_regs > ELF_NGREG)
+		return -EIO;
+
+	err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, uregs, 0,
+				 sizeof(uregs));
+	if (err)
+		return err;
+
+	for (i = start; i < num_regs; i++) {
+		/*
+		 * Cast all values to signed here so that if this is a 64-bit
+		 * kernel, the supplied 32-bit values will be sign extended.
+		 */
+		switch (i) {
+		case MIPS32_EF_R1 ... MIPS32_EF_R25:
+			/* k0/k1 are ignored. */
+		case MIPS32_EF_R28 ... MIPS32_EF_R31:
+			regs->regs[i - MIPS32_EF_R0] = (s32)uregs[i];
+			break;
+		case MIPS32_EF_LO:
+			regs->lo = (s32)uregs[i];
+			break;
+		case MIPS32_EF_HI:
+			regs->hi = (s32)uregs[i];
+			break;
+		case MIPS32_EF_CP0_EPC:
+			regs->cp0_epc = (s32)uregs[i];
+			break;
+		}
+	}
 
 	return 0;
 }
 
+#endif /* CONFIG_32BIT || CONFIG_MIPS32_O32 */
+
+#ifdef CONFIG_64BIT
+
+static int gpr64_get(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     void *kbuf, void __user *ubuf)
+{
+	struct pt_regs *regs = task_pt_regs(target);
+	u64 uregs[ELF_NGREG] = {};
+	unsigned i;
+
+	for (i = MIPS64_EF_R1; i <= MIPS64_EF_R31; i++) {
+		/* k0/k1 are copied as zero. */
+		if (i == MIPS64_EF_R26 || i == MIPS64_EF_R27)
+			continue;
+
+		uregs[i] = regs->regs[i - MIPS64_EF_R0];
+	}
+
+	uregs[MIPS64_EF_LO] = regs->lo;
+	uregs[MIPS64_EF_HI] = regs->hi;
+	uregs[MIPS64_EF_CP0_EPC] = regs->cp0_epc;
+	uregs[MIPS64_EF_CP0_BADVADDR] = regs->cp0_badvaddr;
+	uregs[MIPS64_EF_CP0_STATUS] = regs->cp0_status;
+	uregs[MIPS64_EF_CP0_CAUSE] = regs->cp0_cause;
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs, 0,
+				   sizeof(uregs));
+}
+
+static int gpr64_set(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     const void *kbuf, const void __user *ubuf)
+{
+	struct pt_regs *regs = task_pt_regs(target);
+	u64 uregs[ELF_NGREG];
+	unsigned start, num_regs, i;
+	int err;
+
+	start = pos / sizeof(u64);
+	num_regs = count / sizeof(u64);
+
+	if (start + num_regs > ELF_NGREG)
+		return -EIO;
+
+	err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, uregs, 0,
+				 sizeof(uregs));
+	if (err)
+		return err;
+
+	for (i = start; i < num_regs; i++) {
+		switch (i) {
+		case MIPS64_EF_R1 ... MIPS64_EF_R25:
+			/* k0/k1 are ignored. */
+		case MIPS64_EF_R28 ... MIPS64_EF_R31:
+			regs->regs[i - MIPS64_EF_R0] = uregs[i];
+			break;
+		case MIPS64_EF_LO:
+			regs->lo = uregs[i];
+			break;
+		case MIPS64_EF_HI:
+			regs->hi = uregs[i];
+			break;
+		case MIPS64_EF_CP0_EPC:
+			regs->cp0_epc = uregs[i];
+			break;
+		}
+	}
+
+	return 0;
+}
+
+#endif /* CONFIG_64BIT */
+
 static int fpr_get(struct task_struct *target,
 		   const struct user_regset *regset,
 		   unsigned int pos, unsigned int count,
@@ -337,14 +462,16 @@ enum mips_regset {
 	REGSET_FPR,
 };
 
+#if defined(CONFIG_32BIT) || defined(CONFIG_MIPS32_O32)
+
 static const struct user_regset mips_regsets[] = {
 	[REGSET_GPR] = {
 		.core_note_type	= NT_PRSTATUS,
 		.n		= ELF_NGREG,
 		.size		= sizeof(unsigned int),
 		.align		= sizeof(unsigned int),
-		.get		= gpr_get,
-		.set		= gpr_set,
+		.get		= gpr32_get,
+		.set		= gpr32_set,
 	},
 	[REGSET_FPR] = {
 		.core_note_type	= NT_PRFPREG,
@@ -364,14 +491,18 @@ static const struct user_regset_view user_mips_view = {
 	.n		= ARRAY_SIZE(mips_regsets),
 };
 
+#endif /* CONFIG_32BIT || CONFIG_MIPS32_O32 */
+
+#ifdef CONFIG_64BIT
+
 static const struct user_regset mips64_regsets[] = {
 	[REGSET_GPR] = {
 		.core_note_type	= NT_PRSTATUS,
 		.n		= ELF_NGREG,
 		.size		= sizeof(unsigned long),
 		.align		= sizeof(unsigned long),
-		.get		= gpr_get,
-		.set		= gpr_set,
+		.get		= gpr64_get,
+		.set		= gpr64_set,
 	},
 	[REGSET_FPR] = {
 		.core_note_type	= NT_PRFPREG,
@@ -384,25 +515,26 @@ static const struct user_regset mips64_regsets[] = {
 };
 
 static const struct user_regset_view user_mips64_view = {
-	.name		= "mips",
+	.name		= "mips64",
 	.e_machine	= ELF_ARCH,
 	.ei_osabi	= ELF_OSABI,
 	.regsets	= mips64_regsets,
-	.n		= ARRAY_SIZE(mips_regsets),
+	.n		= ARRAY_SIZE(mips64_regsets),
 };
 
+#endif /* CONFIG_64BIT */
+
 const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 {
 #ifdef CONFIG_32BIT
 	return &user_mips_view;
-#endif
-
+#else
 #ifdef CONFIG_MIPS32_O32
-		if (test_thread_flag(TIF_32BIT_REGS))
-			return &user_mips_view;
+	if (test_tsk_thread_flag(task, TIF_32BIT_REGS))
+		return &user_mips_view;
 #endif
-
 	return &user_mips64_view;
+#endif
 }
 
 long arch_ptrace(struct task_struct *child, long request,
@@ -480,7 +612,7 @@ long arch_ptrace(struct task_struct *child, long request,
 			break;
 		case FPC_EIR:
 			/* implementation / version register */
-			tmp = current_cpu_data.fpu_id;
+			tmp = boot_cpu_data.fpu_id;
 			break;
 		case DSP_BASE ... DSP_BASE + 5: {
 			dspreg_t *dregs;
@@ -565,7 +697,7 @@ long arch_ptrace(struct task_struct *child, long request,
 			break;
 #endif
 		case FPC_CSR:
-			child->thread.fpu.fcr31 = data;
+			child->thread.fpu.fcr31 = data & ~FPU_CSR_ALL_X;
 			break;
 		case DSP_BASE ... DSP_BASE + 5: {
 			dspreg_t *dregs;

arch/mips/kernel/ptrace32.c

@@ -129,7 +129,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			break;
 		case FPC_EIR:
 			/* implementation / version register */
-			tmp = current_cpu_data.fpu_id;
+			tmp = boot_cpu_data.fpu_id;
 			break;
 		case DSP_BASE ... DSP_BASE + 5: {
 			dspreg_t *dregs;

arch/mips/kernel/scall64-o32.S

@@ -113,15 +113,19 @@ trace_a_syscall:
 	move	s0, t2			# Save syscall pointer
 	move	a0, sp
 	/*
-	 * syscall number is in v0 unless we called syscall(__NR_###)
+	 * absolute syscall number is in v0 unless we called syscall(__NR_###)
 	 * where the real syscall number is in a0
 	 * note: NR_syscall is the first O32 syscall but the macro is
 	 * only defined when compiling with -mabi=32 (CONFIG_32BIT)
 	 * therefore __NR_O32_Linux is used (4000)
 	 */
-	addiu	a1, v0,  __NR_O32_Linux
-	bnez	v0, 1f /* __NR_syscall at offset 0 */
-	lw	a1, PT_R4(sp)
+	.set	push
+	.set	reorder
+	subu	t1, v0,  __NR_O32_Linux
+	move	a1, v0
+	bnez	t1, 1f /* __NR_syscall at offset 0 */
+	lw	a1, PT_R4(sp) /* Arg1 for __NR_syscall case */
+	.set	pop
 
 1:	jal	syscall_trace_enter
 

arch/mips/kernel/smp-mt.c

@@ -288,6 +288,7 @@ struct plat_smp_ops vsmp_smp_ops = {
 	.prepare_cpus		= vsmp_prepare_cpus,
 };
 
+#ifdef CONFIG_PROC_FS
 static int proc_cpuinfo_chain_call(struct notifier_block *nfb,
 	unsigned long action_unused, void *data)
 {
@@ -309,3 +310,4 @@ static int __init proc_cpuinfo_notifier_init(void)
 }
 
 subsys_initcall(proc_cpuinfo_notifier_init);
+#endif

arch/mips/kernel/unaligned.c

@@ -690,7 +690,6 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 	case sdc1_op:
 		die_if_kernel("Unaligned FP access in kernel code", regs);
 		BUG_ON(!used_math());
-		BUG_ON(!is_fpu_owner());
 
 		lose_fpu(1);	/* Save FPU state for the emulator. */
 		res = fpu_emulator_cop1Handler(regs, &current->thread.fpu, 1,

arch/mips/math-emu/cp1emu.c

@@ -650,9 +650,9 @@ static inline int cop1_64bit(struct pt_regs *xcp)
 #define SIFROMREG(si, x)						\
 do {									\
 	if (cop1_64bit(xcp))						\
-		(si) = get_fpr32(&ctx->fpr[x], 0);			\
+		(si) = (int)get_fpr32(&ctx->fpr[x], 0);			\
 	else								\
-		(si) = get_fpr32(&ctx->fpr[(x) & ~1], (x) & 1);		\
+		(si) = (int)get_fpr32(&ctx->fpr[(x) & ~1], (x) & 1);	\
 } while (0)
 
 #define SITOREG(si, x)							\
@@ -667,7 +667,7 @@ do {									\
 	}								\
 } while (0)
 
-#define SIFROMHREG(si, x)	((si) = get_fpr32(&ctx->fpr[x], 1))
+#define SIFROMHREG(si, x)	((si) = (int)get_fpr32(&ctx->fpr[x], 1))
 
 #define SITOHREG(si, x)							\
 do {									\
@@ -1827,7 +1827,7 @@ dcopuop:
 	case -1:
 
 		if (cpu_has_mips_4_5_r)
-			cbit = fpucondbit[MIPSInst_RT(ir) >> 2];
+			cbit = fpucondbit[MIPSInst_FD(ir) >> 2];
 		else
 			cbit = FPU_CSR_COND;
 		if (rv.w)

arch/mips/mm/tlbex.c

@@ -1299,6 +1299,7 @@ static void build_r4000_tlb_refill_handler(void)
 	}
 #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 	uasm_l_tlb_huge_update(&l, p);
+	UASM_i_LW(&p, K0, 0, K1);
 	build_huge_update_entries(&p, htlb_info.huge_pte, K1);
 	build_huge_tlb_write_entry(&p, &l, &r, K0, tlb_random,
 				   htlb_info.restore_scratch);

arch/mips/mti-malta/malta-memory.c

@@ -34,13 +34,19 @@ fw_memblock_t * __init fw_getmdesc(int eva)
 	/* otherwise look in the environment */
 
 	memsize_str = fw_getenv("memsize");
-	if (memsize_str)
-		tmp = kstrtol(memsize_str, 0, &memsize);
+	if (memsize_str) {
+		tmp = kstrtoul(memsize_str, 0, &memsize);
+		if (tmp)
+			pr_warn("Failed to read the 'memsize' env variable.\n");
+	}
 	if (eva) {
 	/* Look for ememsize for EVA */
 		ememsize_str = fw_getenv("ememsize");
-		if (ememsize_str)
-			tmp = kstrtol(ememsize_str, 0, &ememsize);
+		if (ememsize_str) {
+			tmp = kstrtoul(ememsize_str, 0, &ememsize);
+			if (tmp)
+				pr_warn("Failed to read the 'ememsize' env variable.\n");
+		}
 	}
 	if (!memsize && !ememsize) {
 		pr_warn("memsize not set in YAMON, set to default (32Mb)\n");

arch/parisc/Makefile

@@ -48,7 +48,12 @@ cflags-y	:= -pipe
 
 # These flags should be implied by an hppa-linux configuration, but they
 # are not in gcc 3.2.
-cflags-y	+= -mno-space-regs -mfast-indirect-calls
+cflags-y	+= -mno-space-regs
+
+# -mfast-indirect-calls is only relevant for 32-bit kernels.
+ifndef CONFIG_64BIT
+cflags-y	+= -mfast-indirect-calls
+endif
 
 # Currently we save and restore fpregs on all kernel entry/interruption paths.
 # If that gets optimized, we might need to disable the use of fpregs in the

arch/parisc/kernel/syscall.S

@@ -74,7 +74,7 @@ ENTRY(linux_gateway_page)
 	/* ADDRESS 0xb0 to 0xb8, lws uses two insns for entry */
 	/* Light-weight-syscall entry must always be located at 0xb0 */
 	/* WARNING: Keep this number updated with table size changes */
-#define __NR_lws_entries (2)
+#define __NR_lws_entries (3)
 
 lws_entry:
 	gate	lws_start, %r0		/* increase privilege */
@@ -502,7 +502,7 @@ lws_exit:
 
 	
 	/***************************************************
-		Implementing CAS as an atomic operation:
+		Implementing 32bit CAS as an atomic operation:
 
 		%r26 - Address to examine
 		%r25 - Old value to check (old)
@@ -659,6 +659,230 @@ cas_action:
 	ASM_EXCEPTIONTABLE_ENTRY(2b-linux_gateway_page, 3b-linux_gateway_page)
 
 
+	/***************************************************
+		New CAS implementation which uses pointers and variable size
+		information. The value pointed by old and new MUST NOT change
+		while performing CAS. The lock only protect the value at %r26.
+
+		%r26 - Address to examine
+		%r25 - Pointer to the value to check (old)
+		%r24 - Pointer to the value to set (new)
+		%r23 - Size of the variable (0/1/2/3 for 8/16/32/64 bit)
+		%r28 - Return non-zero on failure
+		%r21 - Kernel error code
+
+		%r21 has the following meanings:
+
+		EAGAIN - CAS is busy, ldcw failed, try again.
+		EFAULT - Read or write failed.
+
+		Scratch: r20, r22, r28, r29, r1, fr4 (32bit for 64bit CAS only)
+
+	****************************************************/
+
+	/* ELF32 Process entry path */
+lws_compare_and_swap_2:
+#ifdef CONFIG_64BIT
+	/* Clip the input registers */
+	depdi	0, 31, 32, %r26
+	depdi	0, 31, 32, %r25
+	depdi	0, 31, 32, %r24
+	depdi	0, 31, 32, %r23
+#endif
+
+	/* Check the validity of the size pointer */
+	subi,>>= 4, %r23, %r0
+	b,n	lws_exit_nosys
+
+	/* Jump to the functions which will load the old and new values into
+	   registers depending on the their size */
+	shlw	%r23, 2, %r29
+	blr	%r29, %r0
+	nop
+
+	/* 8bit load */
+4:	ldb	0(%sr3,%r25), %r25
+	b	cas2_lock_start
+5:	ldb	0(%sr3,%r24), %r24
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	/* 16bit load */
+6:	ldh	0(%sr3,%r25), %r25
+	b	cas2_lock_start
+7:	ldh	0(%sr3,%r24), %r24
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	/* 32bit load */
+8:	ldw	0(%sr3,%r25), %r25
+	b	cas2_lock_start
+9:	ldw	0(%sr3,%r24), %r24
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	/* 64bit load */
+#ifdef CONFIG_64BIT
+10:	ldd	0(%sr3,%r25), %r25
+11:	ldd	0(%sr3,%r24), %r24
+#else
+	/* Load new value into r22/r23 - high/low */
+10:	ldw	0(%sr3,%r25), %r22
+11:	ldw	4(%sr3,%r25), %r23
+	/* Load new value into fr4 for atomic store later */
+12:	flddx	0(%sr3,%r24), %fr4
+#endif
+
+cas2_lock_start:
+	/* Load start of lock table */
+	ldil	L%lws_lock_start, %r20
+	ldo	R%lws_lock_start(%r20), %r28
+
+	/* Extract four bits from r26 and hash lock (Bits 4-7) */
+	extru  %r26, 27, 4, %r20
+
+	/* Find lock to use, the hash is either one of 0 to
+	   15, multiplied by 16 (keep it 16-byte aligned)
+	   and add to the lock table offset. */
+	shlw	%r20, 4, %r20
+	add	%r20, %r28, %r20
+
+	rsm	PSW_SM_I, %r0			/* Disable interrupts */
+	/* COW breaks can cause contention on UP systems */
+	LDCW	0(%sr2,%r20), %r28		/* Try to acquire the lock */
+	cmpb,<>,n	%r0, %r28, cas2_action	/* Did we get it? */
+cas2_wouldblock:
+	ldo	2(%r0), %r28			/* 2nd case */
+	ssm	PSW_SM_I, %r0
+	b	lws_exit			/* Contended... */
+	ldo	-EAGAIN(%r0), %r21		/* Spin in userspace */
+
+	/*
+		prev = *addr;
+		if ( prev == old )
+		  *addr = new;
+		return prev;
+	*/
+
+	/* NOTES:
+		This all works becuse intr_do_signal
+		and schedule both check the return iasq
+		and see that we are on the kernel page
+		so this process is never scheduled off
+		or is ever sent any signal of any sort,
+		thus it is wholly atomic from usrspaces
+		perspective
+	*/
+cas2_action:
+	/* Jump to the correct function */
+	blr	%r29, %r0
+	/* Set %r28 as non-zero for now */
+	ldo	1(%r0),%r28
+
+	/* 8bit CAS */
+13:	ldb,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r25, %r0
+	b,n	cas2_end
+14:	stb,ma	%r24, 0(%sr3,%r26)
+	b	cas2_end
+	copy	%r0, %r28
+	nop
+	nop
+
+	/* 16bit CAS */
+15:	ldh,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r25, %r0
+	b,n	cas2_end
+16:	sth,ma	%r24, 0(%sr3,%r26)
+	b	cas2_end
+	copy	%r0, %r28
+	nop
+	nop
+
+	/* 32bit CAS */
+17:	ldw,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r25, %r0
+	b,n	cas2_end
+18:	stw,ma	%r24, 0(%sr3,%r26)
+	b	cas2_end
+	copy	%r0, %r28
+	nop
+	nop
+
+	/* 64bit CAS */
+#ifdef CONFIG_64BIT
+19:	ldd,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r25, %r0
+	b,n	cas2_end
+20:	std,ma	%r24, 0(%sr3,%r26)
+	copy	%r0, %r28
+#else
+	/* Compare first word */
+19:	ldw,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r22, %r0
+	b,n	cas2_end
+	/* Compare second word */
+20:	ldw,ma	4(%sr3,%r26), %r29
+	sub,=	%r29, %r23, %r0
+	b,n	cas2_end
+	/* Perform the store */
+21:	fstdx	%fr4, 0(%sr3,%r26)
+	copy	%r0, %r28
+#endif
+
+cas2_end:
+	/* Free lock */
+	stw,ma	%r20, 0(%sr2,%r20)
+	/* Enable interrupts */
+	ssm	PSW_SM_I, %r0
+	/* Return to userspace, set no error */
+	b	lws_exit
+	copy	%r0, %r21
+
+22:
+	/* Error occurred on load or store */
+	/* Free lock */
+	stw	%r20, 0(%sr2,%r20)
+	ssm	PSW_SM_I, %r0
+	ldo	1(%r0),%r28
+	b	lws_exit
+	ldo	-EFAULT(%r0),%r21	/* set errno */
+	nop
+	nop
+	nop
+
+	/* Exception table entries, for the load and store, return EFAULT.
+	   Each of the entries must be relocated. */
+	ASM_EXCEPTIONTABLE_ENTRY(4b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(5b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(6b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(7b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(8b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(9b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(10b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(11b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(13b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(14b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(15b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(16b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(17b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(18b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(19b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(20b-linux_gateway_page, 22b-linux_gateway_page)
+#ifndef CONFIG_64BIT
+	ASM_EXCEPTIONTABLE_ENTRY(12b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(21b-linux_gateway_page, 22b-linux_gateway_page)
+#endif
+
 	/* Make sure nothing else is placed on this page */
 	.align PAGE_SIZE
 END(linux_gateway_page)
@@ -675,8 +899,9 @@ ENTRY(end_linux_gateway_page)
 	/* Light-weight-syscall table */
 	/* Start of lws table. */
 ENTRY(lws_table)
-	LWS_ENTRY(compare_and_swap32)	/* 0 - ELF32 Atomic compare and swap */
-	LWS_ENTRY(compare_and_swap64)	/* 1 - ELF64 Atomic compare and swap */
+	LWS_ENTRY(compare_and_swap32)		/* 0 - ELF32 Atomic 32bit CAS */
+	LWS_ENTRY(compare_and_swap64)		/* 1 - ELF64 Atomic 32bit CAS */
+	LWS_ENTRY(compare_and_swap_2)		/* 2 - ELF32 Atomic 64bit CAS */
 END(lws_table)
 	/* End of lws table */
 

arch/powerpc/include/asm/machdep.h

@@ -57,10 +57,10 @@ struct machdep_calls {
 	void            (*hpte_removebolted)(unsigned long ea,
 					     int psize, int ssize);
 	void		(*flush_hash_range)(unsigned long number, int local);
-	void		(*hugepage_invalidate)(struct mm_struct *mm,
+	void		(*hugepage_invalidate)(unsigned long vsid,
+					       unsigned long addr,
 					       unsigned char *hpte_slot_array,
-					       unsigned long addr, int psize);
-
+					       int psize, int ssize);
 	/* special for kexec, to be called in real mode, linear mapping is
 	 * destroyed as well */
 	void		(*hpte_clear_all)(void);

arch/powerpc/include/asm/pgtable-ppc64.h

@@ -413,7 +413,7 @@ static inline char *get_hpte_slot_array(pmd_t *pmdp)
 }
 
 extern void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
-				   pmd_t *pmdp);
+				   pmd_t *pmdp, unsigned long old_pmd);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot);
 extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot);

arch/powerpc/include/asm/pte-hash64-64k.h

@@ -46,11 +46,31 @@
  * in order to deal with 64K made of 4K HW pages. Thus we override the
  * generic accessors and iterators here
  */
-#define __real_pte(e,p) 	((real_pte_t) { \
-			(e), (pte_val(e) & _PAGE_COMBO) ? \
-				(pte_val(*((p) + PTRS_PER_PTE))) : 0 })
-#define __rpte_to_hidx(r,index)	((pte_val((r).pte) & _PAGE_COMBO) ? \
-        (((r).hidx >> ((index)<<2)) & 0xf) : ((pte_val((r).pte) >> 12) & 0xf))
+#define __real_pte __real_pte
+static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep)
+{
+	real_pte_t rpte;
+
+	rpte.pte = pte;
+	rpte.hidx = 0;
+	if (pte_val(pte) & _PAGE_COMBO) {
+		/*
+		 * Make sure we order the hidx load against the _PAGE_COMBO
+		 * check. The store side ordering is done in __hash_page_4K
+		 */
+		smp_rmb();
+		rpte.hidx = pte_val(*((ptep) + PTRS_PER_PTE));
+	}
+	return rpte;
+}
+
+static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
+{
+	if ((pte_val(rpte.pte) & _PAGE_COMBO))
+		return (rpte.hidx >> (index<<2)) & 0xf;
+	return (pte_val(rpte.pte) >> 12) & 0xf;
+}
+
 #define __rpte_to_pte(r)	((r).pte)
 #define __rpte_sub_valid(rpte, index) \
 	(pte_val(rpte.pte) & (_PAGE_HPTE_SUB0 >> (index)))

arch/powerpc/include/asm/ptrace.h

@@ -47,6 +47,12 @@
 				 STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE)
 #define STACK_FRAME_MARKER	12
 
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define STACK_FRAME_MIN_SIZE	32
+#else
+#define STACK_FRAME_MIN_SIZE	STACK_FRAME_OVERHEAD
+#endif
+
 /* Size of dummy stack frame allocated when calling signal handler. */
 #define __SIGNAL_FRAMESIZE	128
 #define __SIGNAL_FRAMESIZE32	64
@@ -60,6 +66,7 @@
 #define STACK_FRAME_REGS_MARKER	ASM_CONST(0x72656773)
 #define STACK_INT_FRAME_SIZE	(sizeof(struct pt_regs) + STACK_FRAME_OVERHEAD)
 #define STACK_FRAME_MARKER	2
+#define STACK_FRAME_MIN_SIZE	STACK_FRAME_OVERHEAD
 
 /* Size of stack frame allocated when calling signal handler. */
 #define __SIGNAL_FRAMESIZE	64

arch/powerpc/include/asm/spinlock.h

@@ -61,6 +61,7 @@ static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 
 static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
+	smp_mb();
 	return !arch_spin_value_unlocked(*lock);
 }
 

arch/powerpc/include/uapi/asm/kvm.h

@@ -548,6 +548,7 @@ struct kvm_get_htab_header {
 
 #define KVM_REG_PPC_VRSAVE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb4)
 #define KVM_REG_PPC_LPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb5)
+#define KVM_REG_PPC_LPCR_64	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb5)
 #define KVM_REG_PPC_PPR		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb6)
 
 /* Architecture compatibility level */

arch/powerpc/kernel/eeh_pe.c

@@ -570,6 +570,8 @@ static void *__eeh_pe_state_clear(void *data, void *flag)
 {
 	struct eeh_pe *pe = (struct eeh_pe *)data;
 	int state = *((int *)flag);
+	struct eeh_dev *edev, *tmp;
+	struct pci_dev *pdev;
 
 	/* Keep the state of permanently removed PE intact */
 	if ((pe->freeze_count > EEH_MAX_ALLOWED_FREEZES) &&
@@ -578,9 +580,22 @@ static void *__eeh_pe_state_clear(void *data, void *flag)
 
 	pe->state &= ~state;
 
-	/* Clear check count since last isolation */
-	if (state & EEH_PE_ISOLATED)
-		pe->check_count = 0;
+	/*
+	 * Special treatment on clearing isolated state. Clear
+	 * check count since last isolation and put all affected
+	 * devices to normal state.
+	 */
+	if (!(state & EEH_PE_ISOLATED))
+		return NULL;
+
+	pe->check_count = 0;
+	eeh_pe_for_each_dev(pe, edev, tmp) {
+		pdev = eeh_dev_to_pci_dev(edev);
+		if (!pdev)
+			continue;
+
+		pdev->error_state = pci_channel_io_normal;
+	}
 
 	return NULL;
 }
@@ -802,53 +817,33 @@ void eeh_pe_restore_bars(struct eeh_pe *pe)
  */
 const char *eeh_pe_loc_get(struct eeh_pe *pe)
 {
-	struct pci_controller *hose;
 	struct pci_bus *bus = eeh_pe_bus_get(pe);
-	struct pci_dev *pdev;
-	struct device_node *dn;
-	const char *loc;
+	struct device_node *dn = pci_bus_to_OF_node(bus);
+	const char *loc = NULL;
 
-	if (!bus)
-		return "N/A";
+	if (!dn)
+		goto out;
 
 	/* PHB PE or root PE ? */
 	if (pci_is_root_bus(bus)) {
-		hose = pci_bus_to_host(bus);
-		loc = of_get_property(hose->dn,
-				"ibm,loc-code", NULL);
+		loc = of_get_property(dn, "ibm,loc-code", NULL);
+		if (!loc)
+			loc = of_get_property(dn, "ibm,io-base-loc-code", NULL);
 		if (loc)
-			return loc;
-		loc = of_get_property(hose->dn,
-				"ibm,io-base-loc-code", NULL);
-		if (loc)
-			return loc;
+			goto out;
 
-		pdev = pci_get_slot(bus, 0x0);
-	} else {
-		pdev = bus->self;
-	}
-
-	if (!pdev) {
-		loc = "N/A";
-		goto out;
-	}
-
-	dn = pci_device_to_OF_node(pdev);
-	if (!dn) {
-		loc = "N/A";
-		goto out;
+		/* Check the root port */
+		dn = dn->child;
+		if (!dn)
+			goto out;
 	}
 
 	loc = of_get_property(dn, "ibm,loc-code", NULL);
 	if (!loc)
 		loc = of_get_property(dn, "ibm,slot-location-code", NULL);
-	if (!loc)
-		loc = "N/A";
 
 out:
-	if (pci_is_root_bus(bus) && pdev)
-		pci_dev_put(pdev);
-	return loc;
+	return loc ? loc : "N/A";
 }
 
 /**