Merge 3.12-rc3 into char-misc-next

We need/want the mei fixes in here so we can apply other updates that
are depending on them.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

230 files changed, 2355 insertions, 1253 deletions

diff --git a/CREDITS b/CREDITS
index 9416a9a8b95e..0640e1650483 100644
--- a/CREDITS
+++ b/CREDITS
@@ -2808,8 +2808,7 @@ S: Ottawa, Ontario
 S: Canada K2P 0X8
 
 N: Mikael Pettersson
-E: mikpe@it.uu.se
-W: http://user.it.uu.se/~mikpe/linux/
+E: mikpelinux@gmail.com
 D: Miscellaneous fixes
 
 N: Reed H. Petty
diff --git a/Documentation/devicetree/bindings/mmc/exynos-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/exynos-dw-mshc.txt
index 6d1c0988cfc7..c67b975c8906 100644
--- a/Documentation/devicetree/bindings/mmc/exynos-dw-mshc.txt
+++ b/Documentation/devicetree/bindings/mmc/exynos-dw-mshc.txt
@@ -1,11 +1,11 @@
-* Samsung Exynos specific extensions to the Synopsis Designware Mobile
+* Samsung Exynos specific extensions to the Synopsys Designware Mobile
   Storage Host Controller
 
-The Synopsis designware mobile storage host controller is used to interface
+The Synopsys designware mobile storage host controller is used to interface
 a SoC with storage medium such as eMMC or SD/MMC cards. This file documents
-differences between the core Synopsis dw mshc controller properties described
-by synopsis-dw-mshc.txt and the properties used by the Samsung Exynos specific
-extensions to the Synopsis Designware Mobile Storage Host Controller.
+differences between the core Synopsys dw mshc controller properties described
+by synopsys-dw-mshc.txt and the properties used by the Samsung Exynos specific
+extensions to the Synopsys Designware Mobile Storage Host Controller.
 
 Required Properties:
 
diff --git a/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt
index 8a3d91d47b6a..c559f3f36309 100644
--- a/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt
+++ b/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt
@@ -1,11 +1,11 @@
-* Rockchip specific extensions to the Synopsis Designware Mobile
+* Rockchip specific extensions to the Synopsys Designware Mobile
   Storage Host Controller
 
-The Synopsis designware mobile storage host controller is used to interface
+The Synopsys designware mobile storage host controller is used to interface
 a SoC with storage medium such as eMMC or SD/MMC cards. This file documents
-differences between the core Synopsis dw mshc controller properties described
-by synopsis-dw-mshc.txt and the properties used by the Rockchip specific
-extensions to the Synopsis Designware Mobile Storage Host Controller.
+differences between the core Synopsys dw mshc controller properties described
+by synopsys-dw-mshc.txt and the properties used by the Rockchip specific
+extensions to the Synopsys Designware Mobile Storage Host Controller.
 
 Required Properties:
 
diff --git a/Documentation/devicetree/bindings/mmc/synopsis-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt
index cdcebea9c6f5..066a78b034ca 100644
--- a/Documentation/devicetree/bindings/mmc/synopsis-dw-mshc.txt
+++ b/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt
@@ -1,14 +1,14 @@
-* Synopsis Designware Mobile Storage Host Controller
+* Synopsys Designware Mobile Storage Host Controller
 
-The Synopsis designware mobile storage host controller is used to interface
+The Synopsys designware mobile storage host controller is used to interface
 a SoC with storage medium such as eMMC or SD/MMC cards. This file documents
 differences between the core mmc properties described by mmc.txt and the
-properties used by the Synopsis Designware Mobile Storage Host Controller.
+properties used by the Synopsys Designware Mobile Storage Host Controller.
 
 Required Properties:
 
 * compatible: should be
-	- snps,dw-mshc: for controllers compliant with synopsis dw-mshc.
+	- snps,dw-mshc: for controllers compliant with synopsys dw-mshc.
 * #address-cells: should be 1.
 * #size-cells: should be 0.
 
diff --git a/Documentation/devicetree/bindings/pci/designware-pcie.txt b/Documentation/devicetree/bindings/pci/designware-pcie.txt
index eabcb4b5db6e..e216af356847 100644
--- a/Documentation/devicetree/bindings/pci/designware-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/designware-pcie.txt
@@ -1,4 +1,4 @@
-* Synopsis Designware PCIe interface
+* Synopsys Designware PCIe interface
 
 Required properties:
 - compatible: should contain "snps,dw-pcie" to identify the
diff --git a/Documentation/devicetree/bindings/tty/serial/qca,ar9330-uart.txt b/Documentation/devicetree/bindings/serial/qca,ar9330-uart.txt
index c5e032c85bf9..c5e032c85bf9 100644
--- a/Documentation/devicetree/bindings/tty/serial/qca,ar9330-uart.txt
+++ b/Documentation/devicetree/bindings/serial/qca,ar9330-uart.txt
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 1a036cd972fb..539a23631990 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3485,6 +3485,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 				the unplug protocol
 			never -- do not unplug even if version check succeeds
 
+	xen_nopvspin	[X86,XEN]
+			Disables the ticketlock slowpath using Xen PV
+			optimizations.
+
 	xirc2ps_cs=	[NET,PCMCIA]
 			Format:
 			<irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]
diff --git a/Documentation/sound/alsa/HD-Audio-Models.txt b/Documentation/sound/alsa/HD-Audio-Models.txt
index a46ddb85e83a..f911e3656209 100644
--- a/Documentation/sound/alsa/HD-Audio-Models.txt
+++ b/Documentation/sound/alsa/HD-Audio-Models.txt
@@ -296,6 +296,12 @@ Cirrus Logic CS4206/4207
   imac27	IMac 27 Inch
   auto		BIOS setup (default)
 
+Cirrus Logic CS4208
+===================
+  mba6		MacBook Air 6,1 and 6,2
+  gpio0		Enable GPIO 0 amp
+  auto		BIOS setup (default)
+
 VIA VT17xx/VT18xx/VT20xx
 ========================
   auto		BIOS setup (default)
diff --git a/MAINTAINERS b/MAINTAINERS
index e61c2e83fc2b..284969fa2896 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1812,7 +1812,8 @@ S:	Supported
 F:	drivers/net/ethernet/broadcom/bnx2x/
 
 BROADCOM BCM281XX/BCM11XXX ARM ARCHITECTURE
-M:	Christian Daudt <csd@broadcom.com>
+M:	Christian Daudt <bcm@fixthebug.org>
+L:	bcm-kernel-feedback-list@broadcom.com
 T:	git git://git.github.com/broadcom/bcm11351
 S:	Maintained
 F:	arch/arm/mach-bcm/
@@ -2639,6 +2640,18 @@ F:	include/linux/device-mapper.h
 F:	include/linux/dm-*.h
 F:	include/uapi/linux/dm-*.h
 
+DIGI NEO AND CLASSIC PCI PRODUCTS
+M:	Lidza Louina <lidza.louina@gmail.com>
+L:	driverdev-devel@linuxdriverproject.org
+S:	Maintained
+F:	drivers/staging/dgnc/
+
+DIGI EPCA PCI PRODUCTS
+M:	Lidza Louina <lidza.louina@gmail.com>
+L:	driverdev-devel@linuxdriverproject.org
+S:	Maintained
+F:	drivers/staging/dgap/
+
 DIOLAN U2C-12 I2C DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-i2c@vger.kernel.org
@@ -6595,7 +6608,7 @@ S:	Obsolete
 F:	drivers/net/wireless/prism54/
 
 PROMISE SATA TX2/TX4 CONTROLLER LIBATA DRIVER
-M:	Mikael Pettersson <mikpe@it.uu.se>
+M:	Mikael Pettersson <mikpelinux@gmail.com>
 L:	linux-ide@vger.kernel.org
 S:	Maintained
 F:	drivers/ata/sata_promise.*
@@ -8724,9 +8737,8 @@ F:	Documentation/hid/hiddev.txt
 F:	drivers/hid/usbhid/
 
 USB/IP DRIVERS
-M:	Matt Mooney <mfm@muteddisk.com>
 L:	linux-usb@vger.kernel.org
-S:	Maintained
+S:	Orphan
 F:	drivers/staging/usbip/
 
 USB ISP116X DRIVER
diff --git a/Makefile b/Makefile
index 8d0668f473ba..2ae108d4f2af 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 12
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = One Giant Leap for Frogkind
 
 # *DOCUMENTATION*
diff --git a/arch/Kconfig b/arch/Kconfig
index 1feb169274fe..af2cc6eabcc7 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -286,9 +286,6 @@ config HAVE_PERF_USER_STACK_DUMP
 config HAVE_ARCH_JUMP_LABEL
 	bool
 
-config HAVE_ARCH_MUTEX_CPU_RELAX
-	bool
-
 config HAVE_RCU_TABLE_FREE
 	bool
 
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 3f7714d8d2d2..1ad6fb6c094d 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -2217,8 +2217,7 @@ config NEON
 
 config KERNEL_MODE_NEON
 	bool "Support for NEON in kernel mode"
-	default n
-	depends on NEON
+	depends on NEON && AEABI
 	help
 	  Say Y to include support for NEON in kernel mode.
 
diff --git a/arch/arm/crypto/aes-armv4.S b/arch/arm/crypto/aes-armv4.S
index 19d6cd6f29f9..3a14ea8fe97e 100644
--- a/arch/arm/crypto/aes-armv4.S
+++ b/arch/arm/crypto/aes-armv4.S
@@ -148,7 +148,7 @@ AES_Te:
 @ 		 const AES_KEY *key) {
 .align	5
 ENTRY(AES_encrypt)
-	sub	r3,pc,#8		@ AES_encrypt
+	adr	r3,AES_encrypt
 	stmdb   sp!,{r1,r4-r12,lr}
 	mov	r12,r0		@ inp
 	mov	r11,r2
@@ -381,7 +381,7 @@ _armv4_AES_encrypt:
 .align	5
 ENTRY(private_AES_set_encrypt_key)
 _armv4_AES_set_encrypt_key:
-	sub	r3,pc,#8		@ AES_set_encrypt_key
+	adr	r3,_armv4_AES_set_encrypt_key
 	teq	r0,#0
 	moveq	r0,#-1
 	beq	.Labrt
@@ -843,7 +843,7 @@ AES_Td:
 @ 		 const AES_KEY *key) {
 .align	5
 ENTRY(AES_decrypt)
-	sub	r3,pc,#8		@ AES_decrypt
+	adr	r3,AES_decrypt
 	stmdb   sp!,{r1,r4-r12,lr}
 	mov	r12,r0		@ inp
 	mov	r11,r2
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 7e1f76027f66..72abdc541f38 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -19,6 +19,13 @@
 #include <asm/unified.h>
 #include <asm/compiler.h>
 
+#if __LINUX_ARM_ARCH__ < 6
+#include <asm-generic/uaccess-unaligned.h>
+#else
+#define __get_user_unaligned __get_user
+#define __put_user_unaligned __put_user
+#endif
+
 #define VERIFY_READ 0
 #define VERIFY_WRITE 1
 
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 74ad15d1a065..bc6bd9683ba4 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -442,10 +442,10 @@ local_restart:
 	ldrcc	pc, [tbl, scno, lsl #2]		@ call sys_* routine
 
 	add	r1, sp, #S_OFF
-	cmp	scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE)
+2:	cmp	scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE)
 	eor	r0, scno, #__NR_SYSCALL_BASE	@ put OS number back
 	bcs	arm_syscall
-2:	mov	why, #0				@ no longer a real syscall
+	mov	why, #0				@ no longer a real syscall
 	b	sys_ni_syscall			@ not private func
 
 #if defined(CONFIG_OABI_COMPAT) || !defined(CONFIG_AEABI)
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index de23a9beed13..39f89fbd5111 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -329,10 +329,10 @@
 #ifdef CONFIG_CONTEXT_TRACKING
 	.if	\save
 	stmdb   sp!, {r0-r3, ip, lr}
-	bl	user_exit
+	bl	context_tracking_user_exit
 	ldmia	sp!, {r0-r3, ip, lr}
 	.else
-	bl	user_exit
+	bl	context_tracking_user_exit
 	.endif
 #endif
 	.endm
@@ -341,10 +341,10 @@
 #ifdef CONFIG_CONTEXT_TRACKING
 	.if	\save
 	stmdb   sp!, {r0-r3, ip, lr}
-	bl	user_enter
+	bl	context_tracking_user_enter
 	ldmia	sp!, {r0-r3, ip, lr}
 	.else
-	bl	user_enter
+	bl	context_tracking_user_enter
 	.endif
 #endif
 	.endm
diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index 51680d15ca8e..d445d060e346 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -187,7 +187,7 @@
 
 /*
  * MIPS32, MIPS64, VR5500, IDT32332, IDT32334 and maybe a few other
- * pre-MIPS32/MIPS53 processors have CLO, CLZ.	The IDT RC64574 is 64-bit and
+ * pre-MIPS32/MIPS64 processors have CLO, CLZ.	The IDT RC64574 is 64-bit and
  * has CLO and CLZ but not DCLO nor DCLZ.  For 64-bit kernels
  * cpu_has_clo_clz also indicates the availability of DCLO and DCLZ.
  */
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index f25a7e9f8cbc..5f8b95512580 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -308,12 +308,10 @@ static void mips_dma_sync_sg_for_cpu(struct device *dev,
 {
 	int i;
 
-	/* Make sure that gcc doesn't leave the empty loop body.  */
-	for (i = 0; i < nelems; i++, sg++) {
-		if (cpu_needs_post_dma_flush(dev))
+	if (cpu_needs_post_dma_flush(dev))
+		for (i = 0; i < nelems; i++, sg++)
 			__dma_sync(sg_page(sg), sg->offset, sg->length,
 				   direction);
-	}
 }
 
 static void mips_dma_sync_sg_for_device(struct device *dev,
@@ -321,12 +319,10 @@ static void mips_dma_sync_sg_for_device(struct device *dev,
 {
 	int i;
 
-	/* Make sure that gcc doesn't leave the empty loop body.  */
-	for (i = 0; i < nelems; i++, sg++) {
-		if (!plat_device_is_coherent(dev))
+	if (!plat_device_is_coherent(dev))
+		for (i = 0; i < nelems; i++, sg++)
 			__dma_sync(sg_page(sg), sg->offset, sg->length,
 				   direction);
-	}
 }
 
 int mips_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
diff --git a/arch/openrisc/include/asm/prom.h b/arch/openrisc/include/asm/prom.h
index eb59bfe23e85..93c9980e1b6b 100644
--- a/arch/openrisc/include/asm/prom.h
+++ b/arch/openrisc/include/asm/prom.h
@@ -14,53 +14,9 @@
  * the Free Software Foundation; either version 2 of the License, or
  * (at your option) any later version.
  */
-
-#include <linux/of.h>	/* linux/of.h gets to determine #include ordering */
-
 #ifndef _ASM_OPENRISC_PROM_H
 #define _ASM_OPENRISC_PROM_H
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
 
-#include <linux/types.h>
-#include <asm/irq.h>
-#include <linux/irqdomain.h>
-#include <linux/atomic.h>
-#include <linux/of_irq.h>
-#include <linux/of_fdt.h>
-#include <linux/of_address.h>
-#include <linux/proc_fs.h>
-#include <linux/platform_device.h>
 #define HAVE_ARCH_DEVTREE_FIXUPS
 
-/* Other Prototypes */
-extern int early_uartlite_console(void);
-
-/* Parse the ibm,dma-window property of an OF node into the busno, phys and
- * size parameters.
- */
-void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
-		unsigned long *busno, unsigned long *phys, unsigned long *size);
-
-extern void kdump_move_device_tree(void);
-
-/* Get the MAC address */
-extern const void *of_get_mac_address(struct device_node *np);
-
-/**
- * of_irq_map_pci - Resolve the interrupt for a PCI device
- * @pdev:	the device whose interrupt is to be resolved
- * @out_irq:	structure of_irq filled by this function
- *
- * This function resolves the PCI interrupt for a given PCI device. If a
- * device-node exists for a given pci_dev, it will use normal OF tree
- * walking. If not, it will implement standard swizzling and walk up the
- * PCI tree until an device-node is found, at which point it will finish
- * resolving using the OF tree walking.
- */
-struct pci_dev;
-extern int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq);
-
-#endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
 #endif /* _ASM_OPENRISC_PROM_H */
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 6a15c968d214..15ca2255f438 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -74,7 +74,7 @@ src-wlib-$(CONFIG_8xx) += mpc8xx.c planetcore.c
 src-wlib-$(CONFIG_PPC_82xx) += pq2.c fsl-soc.c planetcore.c
 src-wlib-$(CONFIG_EMBEDDED6xx) += mv64x60.c mv64x60_i2c.c ugecon.c
 
-src-plat-y := of.c
+src-plat-y := of.c epapr.c
 src-plat-$(CONFIG_40x) += fixed-head.S ep405.c cuboot-hotfoot.c \
 				treeboot-walnut.c cuboot-acadia.c \
 				cuboot-kilauea.c simpleboot.c \
@@ -97,7 +97,7 @@ src-plat-$(CONFIG_EMBEDDED6xx) += cuboot-pq2.c cuboot-mpc7448hpc2.c \
 					prpmc2800.c
 src-plat-$(CONFIG_AMIGAONE) += cuboot-amigaone.c
 src-plat-$(CONFIG_PPC_PS3) += ps3-head.S ps3-hvcall.S ps3.c
-src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c
+src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c epapr-wrapper.c
 
 src-wlib := $(sort $(src-wlib-y))
 src-plat := $(sort $(src-plat-y))
diff --git a/arch/powerpc/boot/epapr-wrapper.c b/arch/powerpc/boot/epapr-wrapper.c
new file mode 100644
index 000000000000..c10191006673
--- /dev/null
+++ b/arch/powerpc/boot/epapr-wrapper.c
@@ -0,0 +1,9 @@
+extern void epapr_platform_init(unsigned long r3, unsigned long r4,
+				unsigned long r5, unsigned long r6,
+				unsigned long r7);
+
+void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+		   unsigned long r6, unsigned long r7)
+{
+	epapr_platform_init(r3, r4, r5, r6, r7);
+}
diff --git a/arch/powerpc/boot/epapr.c b/arch/powerpc/boot/epapr.c
index 06c1961bd124..02e91aa2194a 100644
--- a/arch/powerpc/boot/epapr.c
+++ b/arch/powerpc/boot/epapr.c
@@ -48,8 +48,8 @@ static void platform_fixups(void)
 		       fdt_addr, fdt_totalsize((void *)fdt_addr), ima_size);
 }
 
-void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
-		   unsigned long r6, unsigned long r7)
+void epapr_platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+			 unsigned long r6, unsigned long r7)
 {
 	epapr_magic = r6;
 	ima_size = r7;
diff --git a/arch/powerpc/boot/of.c b/arch/powerpc/boot/of.c
index 61d9899aa0d0..62e2f43ec1df 100644
--- a/arch/powerpc/boot/of.c
+++ b/arch/powerpc/boot/of.c
@@ -26,6 +26,9 @@
 
 static unsigned long claim_base;
 
+void epapr_platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+			 unsigned long r6, unsigned long r7);
+
 static void *of_try_claim(unsigned long size)
 {
 	unsigned long addr = 0;
@@ -61,7 +64,7 @@ static void of_image_hdr(const void *hdr)
 	}
 }
 
-void platform_init(unsigned long a1, unsigned long a2, void *promptr)
+static void of_platform_init(unsigned long a1, unsigned long a2, void *promptr)
 {
 	platform_ops.image_hdr = of_image_hdr;
 	platform_ops.malloc = of_try_claim;
@@ -81,3 +84,14 @@ void platform_init(unsigned long a1, unsigned long a2, void *promptr)
 		loader_info.initrd_size = a2;
 	}
 }
+
+void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+		   unsigned long r6, unsigned long r7)
+{
+	/* Detect OF vs. ePAPR boot */
+	if (r5)
+		of_platform_init(r3, r4, (void *)r5);
+	else
+		epapr_platform_init(r3, r4, r5, r6, r7);
+}
+
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index 6761c746048d..cd7af841ba05 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -148,18 +148,18 @@ make_space=y
 
 case "$platform" in
 pseries)
-    platformo=$object/of.o
+    platformo="$object/of.o $object/epapr.o"
     link_address='0x4000000'
     ;;
 maple)
-    platformo=$object/of.o
+    platformo="$object/of.o $object/epapr.o"
     link_address='0x400000'
     ;;
 pmac|chrp)
-    platformo=$object/of.o
+    platformo="$object/of.o $object/epapr.o"
     ;;
 coff)
-    platformo="$object/crt0.o $object/of.o"
+    platformo="$object/crt0.o $object/of.o $object/epapr.o"
     lds=$object/zImage.coff.lds
     link_address='0x500000'
     pie=
@@ -253,6 +253,7 @@ treeboot-iss4xx-mpic)
     platformo="$object/treeboot-iss4xx.o"
     ;;
 epapr)
+    platformo="$object/epapr.o $object/epapr-wrapper.o"
     link_address='0x20000000'
     pie=-pie
     ;;
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index 0e40843a1c6e..41f13cec8a8f 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -69,9 +69,9 @@ extern struct thread_info *softirq_ctx[NR_CPUS];
 
 extern void irq_ctx_init(void);
 extern void call_do_softirq(struct thread_info *tp);
-extern int call_handle_irq(int irq, void *p1,
-			   struct thread_info *tp, void *func);
+extern void call_do_irq(struct pt_regs *regs, struct thread_info *tp);
 extern void do_IRQ(struct pt_regs *regs);
+extern void __do_irq(struct pt_regs *regs);
 
 int irq_choose_cpu(const struct cpumask *mask);
 
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index e378cccfca55..ce4de5aed7b5 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -149,8 +149,6 @@ typedef struct {
 
 struct thread_struct {
 	unsigned long	ksp;		/* Kernel stack pointer */
-	unsigned long	ksp_limit;	/* if ksp <= ksp_limit stack overflow */
-
 #ifdef CONFIG_PPC64
 	unsigned long	ksp_vsid;
 #endif
@@ -162,6 +160,7 @@ struct thread_struct {
 #endif
 #ifdef CONFIG_PPC32
 	void		*pgdir;		/* root of page-table tree */
+	unsigned long	ksp_limit;	/* if ksp <= ksp_limit stack overflow */
 #endif
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 	/*
@@ -321,7 +320,6 @@ struct thread_struct {
 #else
 #define INIT_THREAD  { \
 	.ksp = INIT_SP, \
-	.ksp_limit = INIT_SP_LIMIT, \
 	.regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \
 	.fs = KERNEL_DS, \
 	.fpr = {{0}}, \
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index d8958be5f31a..502c7a4e73f7 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -80,10 +80,11 @@ int main(void)
 	DEFINE(TASKTHREADPPR, offsetof(struct task_struct, thread.ppr));
 #else
 	DEFINE(THREAD_INFO, offsetof(struct task_struct, stack));
+	DEFINE(THREAD_INFO_GAP, _ALIGN_UP(sizeof(struct thread_info), 16));
+	DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit));
 #endif /* CONFIG_PPC64 */
 
 	DEFINE(KSP, offsetof(struct thread_struct, ksp));
-	DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit));
 	DEFINE(PT_REGS, offsetof(struct thread_struct, regs));
 #ifdef CONFIG_BOOKE
 	DEFINE(THREAD_NORMSAVES, offsetof(struct thread_struct, normsave[0]));
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index c69440cef7af..57d286a78f86 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -441,50 +441,6 @@ void migrate_irqs(void)
 }
 #endif
 
-static inline void handle_one_irq(unsigned int irq)
-{
-	struct thread_info *curtp, *irqtp;
-	unsigned long saved_sp_limit;
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	if (!desc)
-		return;
-
-	/* Switch to the irq stack to handle this */
-	curtp = current_thread_info();
-	irqtp = hardirq_ctx[smp_processor_id()];
-
-	if (curtp == irqtp) {
-		/* We're already on the irq stack, just handle it */
-		desc->handle_irq(irq, desc);
-		return;
-	}
-
-	saved_sp_limit = current->thread.ksp_limit;
-
-	irqtp->task = curtp->task;
-	irqtp->flags = 0;
-
-	/* Copy the softirq bits in preempt_count so that the
-	 * softirq checks work in the hardirq context. */
-	irqtp->preempt_count = (irqtp->preempt_count & ~SOFTIRQ_MASK) |
-			       (curtp->preempt_count & SOFTIRQ_MASK);
-
-	current->thread.ksp_limit = (unsigned long)irqtp +
-		_ALIGN_UP(sizeof(struct thread_info), 16);
-
-	call_handle_irq(irq, desc, irqtp, desc->handle_irq);
-	current->thread.ksp_limit = saved_sp_limit;
-	irqtp->task = NULL;
-
-	/* Set any flag that may have been set on the
-	 * alternate stack
-	 */
-	if (irqtp->flags)
-		set_bits(irqtp->flags, &curtp->flags);
-}
-
 static inline void check_stack_overflow(void)
 {
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
@@ -501,9 +457,9 @@ static inline void check_stack_overflow(void)
 #endif
 }
 
-void do_IRQ(struct pt_regs *regs)
+void __do_irq(struct pt_regs *regs)
 {
-	struct pt_regs *old_regs = set_irq_regs(regs);
+	struct irq_desc *desc;
 	unsigned int irq;
 
 	irq_enter();
@@ -519,18 +475,56 @@ void do_IRQ(struct pt_regs *regs)
 	 */
 	irq = ppc_md.get_irq();
 
-	/* We can hard enable interrupts now */
+	/* We can hard enable interrupts now to allow perf interrupts */
 	may_hard_irq_enable();
 
 	/* And finally process it */
-	if (irq != NO_IRQ)
-		handle_one_irq(irq);
-	else
+	if (unlikely(irq == NO_IRQ))
 		__get_cpu_var(irq_stat).spurious_irqs++;
+	else {
+		desc = irq_to_desc(irq);
+		if (likely(desc))
+			desc->handle_irq(irq, desc);
+	}
 
 	trace_irq_exit(regs);
 
 	irq_exit();
+}
+
+void do_IRQ(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+	struct thread_info *curtp, *irqtp;
+
+	/* Switch to the irq stack to handle this */
+	curtp = current_thread_info();
+	irqtp = hardirq_ctx[raw_smp_processor_id()];
+
+	/* Already there ? */
+	if (unlikely(curtp == irqtp)) {
+		__do_irq(regs);
+		set_irq_regs(old_regs);
+		return;
+	}
+
+	/* Prepare the thread_info in the irq stack */
+	irqtp->task = curtp->task;
+	irqtp->flags = 0;
+
+	/* Copy the preempt_count so that the [soft]irq checks work. */
+	irqtp->preempt_count = curtp->preempt_count;
+
+	/* Switch stack and call */
+	call_do_irq(regs, irqtp);
+
+	/* Restore stack limit */
+	irqtp->task = NULL;
+
+	/* Copy back updates to the thread_info */
+	if (irqtp->flags)
+		set_bits(irqtp->flags, &curtp->flags);
+
 	set_irq_regs(old_regs);
 }
 
@@ -592,28 +586,22 @@ void irq_ctx_init(void)
 		memset((void *)softirq_ctx[i], 0, THREAD_SIZE);
 		tp = softirq_ctx[i];
 		tp->cpu = i;
-		tp->preempt_count = 0;
 
 		memset((void *)hardirq_ctx[i], 0, THREAD_SIZE);
 		tp = hardirq_ctx[i];
 		tp->cpu = i;
-		tp->preempt_count = HARDIRQ_OFFSET;
 	}
 }
 
 static inline void do_softirq_onstack(void)
 {
 	struct thread_info *curtp, *irqtp;
-	unsigned long saved_sp_limit = current->thread.ksp_limit;
 
 	curtp = current_thread_info();
 	irqtp = softirq_ctx[smp_processor_id()];
 	irqtp->task = curtp->task;
 	irqtp->flags = 0;
-	current->thread.ksp_limit = (unsigned long)irqtp +
-				    _ALIGN_UP(sizeof(struct thread_info), 16);
 	call_do_softirq(irqtp);
-	current->thread.ksp_limit = saved_sp_limit;
 	irqtp->task = NULL;
 
 	/* Set any flag that may have been set on the
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 777d999f563b..2b0ad9845363 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -36,26 +36,41 @@
 
 	.text
 
+/*
+ * We store the saved ksp_limit in the unused part
+ * of the STACK_FRAME_OVERHEAD
+ */
 _GLOBAL(call_do_softirq)
 	mflr	r0
 	stw	r0,4(r1)
+	lwz	r10,THREAD+KSP_LIMIT(r2)
+	addi	r11,r3,THREAD_INFO_GAP
 	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
 	mr	r1,r3
+	stw	r10,8(r1)
+	stw	r11,THREAD+KSP_LIMIT(r2)
 	bl	__do_softirq
+	lwz	r10,8(r1)
 	lwz	r1,0(r1)
 	lwz	r0,4(r1)
+	stw	r10,THREAD+KSP_LIMIT(r2)
 	mtlr	r0
 	blr
 
-_GLOBAL(call_handle_irq)
+_GLOBAL(call_do_irq)
 	mflr	r0
 	stw	r0,4(r1)
-	mtctr	r6
-	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r5)
-	mr	r1,r5
-	bctrl
+	lwz	r10,THREAD+KSP_LIMIT(r2)
+	addi	r11,r3,THREAD_INFO_GAP
+	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
+	mr	r1,r4
+	stw	r10,8(r1)
+	stw	r11,THREAD+KSP_LIMIT(r2)
+	bl	__do_irq
+	lwz	r10,8(r1)
 	lwz	r1,0(r1)
 	lwz	r0,4(r1)
+	stw	r10,THREAD+KSP_LIMIT(r2)
 	mtlr	r0
 	blr
 
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 971d7e78aff2..e59caf874d05 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -40,14 +40,12 @@ _GLOBAL(call_do_softirq)
 	mtlr	r0
 	blr
 
-_GLOBAL(call_handle_irq)
-	ld	r8,0(r6)
+_GLOBAL(call_do_irq)
 	mflr	r0
 	std	r0,16(r1)
-	mtctr	r8
-	stdu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r5)
-	mr	r1,r5
-	bctrl
+	stdu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
+	mr	r1,r4
+	bl	.__do_irq
 	ld	r1,0(r1)
 	ld	r0,16(r1)
 	mtlr	r0
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 6f428da53e20..96d2fdf3aa9e 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1000,9 +1000,10 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	kregs = (struct pt_regs *) sp;
 	sp -= STACK_FRAME_OVERHEAD;
 	p->thread.ksp = sp;
+#ifdef CONFIG_PPC32
 	p->thread.ksp_limit = (unsigned long)task_stack_page(p) +
 				_ALIGN_UP(sizeof(struct thread_info), 16);
-
+#endif
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	p->thread.ptrace_bps[0] = NULL;
 #endif
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 12e656ffe60e..5fe2842e8bab 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -196,6 +196,8 @@ static int __initdata mem_reserve_cnt;
 
 static cell_t __initdata regbuf[1024];
 
+static bool rtas_has_query_cpu_stopped;
+
 
 /*
  * Error results ... some OF calls will return "-1" on error, some
@@ -1574,6 +1576,11 @@ static void __init prom_instantiate_rtas(void)
 	prom_setprop(rtas_node, "/rtas", "linux,rtas-entry",
 		     &val, sizeof(val));
 
+	/* Check if it supports "query-cpu-stopped-state" */
+	if (prom_getprop(rtas_node, "query-cpu-stopped-state",
+			 &val, sizeof(val)) != PROM_ERROR)
+		rtas_has_query_cpu_stopped = true;
+
 #if defined(CONFIG_PPC_POWERNV) && defined(__BIG_ENDIAN__)
 	/* PowerVN takeover hack */
 	prom_rtas_data = base;
@@ -1815,6 +1822,18 @@ static void __init prom_hold_cpus(void)
 		= (void *) LOW_ADDR(__secondary_hold_acknowledge);
 	unsigned long secondary_hold = LOW_ADDR(__secondary_hold);
 
+	/*
+	 * On pseries, if RTAS supports "query-cpu-stopped-state",
+	 * we skip this stage, the CPUs will be started by the
+	 * kernel using RTAS.
+	 */
+	if ((of_platform == PLATFORM_PSERIES ||
+	     of_platform == PLATFORM_PSERIES_LPAR) &&
+	    rtas_has_query_cpu_stopped) {
+		prom_printf("prom_hold_cpus: skipped\n");
+		return;
+	}
+
 	prom_debug("prom_hold_cpus: start...\n");
 	prom_debug("    1) spinloop       = 0x%x\n", (unsigned long)spinloop);
 	prom_debug("    1) *spinloop      = 0x%x\n", *spinloop);
@@ -3011,6 +3030,8 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 * On non-powermacs, put all CPUs in spin-loops.
 	 *
 	 * PowerMacs use a different mechanism to spin CPUs
+	 *
+	 * (This must be done after instanciating RTAS)
 	 */
 	if (of_platform != PLATFORM_POWERMAC &&
 	    of_platform != PLATFORM_OPAL)
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index a7ee978fb860..b1faa1593c90 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1505,6 +1505,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		 */
 		if ((ra == 1) && !(regs->msr & MSR_PR) \
 			&& (val3 >= (regs->gpr[1] - STACK_INT_FRAME_SIZE))) {
+#ifdef CONFIG_PPC32
 			/*
 			 * Check if we will touch kernel sack overflow
 			 */
@@ -1513,7 +1514,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 				err = -EINVAL;
 				break;
 			}
-
+#endif /* CONFIG_PPC32 */
 			/*
 			 * Check if we already set since that means we'll
 			 * lose the previous value.
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 1c1771a40250..24f58cb0a543 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -233,18 +233,24 @@ static void __init smp_init_pseries(void)
 
 	alloc_bootmem_cpumask_var(&of_spin_mask);
 
-	/* Mark threads which are still spinning in hold loops. */
-	if (cpu_has_feature(CPU_FTR_SMT)) {
-		for_each_present_cpu(i) { 
-			if (cpu_thread_in_core(i) == 0)
-				cpumask_set_cpu(i, of_spin_mask);
-		}
-	} else {
-		cpumask_copy(of_spin_mask, cpu_present_mask);
+	/*
+	 * Mark threads which are still spinning in hold loops
+	 *
+	 * We know prom_init will not have started them if RTAS supports
+	 * query-cpu-stopped-state.
+	 */
+	if (rtas_token("query-cpu-stopped-state") == RTAS_UNKNOWN_SERVICE) {
+		if (cpu_has_feature(CPU_FTR_SMT)) {
+			for_each_present_cpu(i) {
+				if (cpu_thread_in_core(i) == 0)
+					cpumask_set_cpu(i, of_spin_mask);
+			}
+		} else
+			cpumask_copy(of_spin_mask, cpu_present_mask);
+
+		cpumask_clear_cpu(boot_cpuid, of_spin_mask);
 	}
 
-	cpumask_clear_cpu(boot_cpuid, of_spin_mask);
-
 	/* Non-lpar has additional take/give timebase */
 	if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) {
 		smp_ops->give_timebase = rtas_give_timebase;
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index dcc6ac2d8026..7143793859fa 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -93,6 +93,7 @@ config S390
 	select ARCH_INLINE_WRITE_UNLOCK_IRQ
 	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
 	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
+	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS2
@@ -102,7 +103,6 @@ config S390
 	select GENERIC_TIME_VSYSCALL_OLD
 	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
 	select HAVE_ARCH_JUMP_LABEL if !MARCH_G5
-	select HAVE_ARCH_MUTEX_CPU_RELAX
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT
diff --git a/arch/s390/include/asm/mutex.h b/arch/s390/include/asm/mutex.h
index 688271f5f2e4..458c1f7fbc18 100644
--- a/arch/s390/include/asm/mutex.h
+++ b/arch/s390/include/asm/mutex.h
@@ -7,5 +7,3 @@
  */
 
 #include <asm-generic/mutex-dec.h>
-
-#define arch_mutex_cpu_relax()	barrier()
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 0eb37505cab1..ca7821f07260 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -198,6 +198,8 @@ static inline void cpu_relax(void)
 	barrier();
 }
 
+#define arch_mutex_cpu_relax()  barrier()
+
 static inline void psw_set_key(unsigned int key)
 {
 	asm volatile("spka 0(%0)" : : "d" (key));
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index 701fe8c59e1f..83e5d216105e 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -44,6 +44,11 @@ extern void arch_spin_lock_wait_flags(arch_spinlock_t *, unsigned long flags);
 extern int arch_spin_trylock_retry(arch_spinlock_t *);
 extern void arch_spin_relax(arch_spinlock_t *lock);
 
+static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
+{
+	return lock.owner_cpu == 0;
+}
+
 static inline void arch_spin_lock(arch_spinlock_t *lp)
 {
 	int old;
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 6aef9fbc09b7..b913915e8e63 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -79,30 +79,38 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn)
 	return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY;
 }
 
-static inline unsigned long mfn_to_pfn(unsigned long mfn)
+static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn)
 {
 	unsigned long pfn;
-	int ret = 0;
+	int ret;
 
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return mfn;
 
-	if (unlikely(mfn >= machine_to_phys_nr)) {
-		pfn = ~0;
-		goto try_override;
-	}
-	pfn = 0;
+	if (unlikely(mfn >= machine_to_phys_nr))
+		return ~0;
+
 	/*
 	 * The array access can fail (e.g., device space beyond end of RAM).
 	 * In such cases it doesn't matter what we return (we return garbage),
 	 * but we must handle the fault without crashing!
 	 */
 	ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
-try_override:
-	/* ret might be < 0 if there are no entries in the m2p for mfn */
 	if (ret < 0)
-		pfn = ~0;
-	else if (get_phys_to_machine(pfn) != mfn)
+		return ~0;
+
+	return pfn;
+}
+
+static inline unsigned long mfn_to_pfn(unsigned long mfn)
+{
+	unsigned long pfn;
+
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return mfn;
+
+	pfn = mfn_to_pfn_no_overrides(mfn);
+	if (get_phys_to_machine(pfn) != mfn) {
 		/*
 		 * If this appears to be a foreign mfn (because the pfn
 		 * doesn't map back to the mfn), then check the local override
@@ -111,6 +119,7 @@ try_override:
 		 * m2p_find_override_pfn returns ~0 if it doesn't find anything.
 		 */
 		pfn = m2p_find_override_pfn(mfn, ~0);
+	}
 
 	/* 
 	 * pfn is ~0 if there are no entries in the m2p for mfn or if the
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8355c84b9729..897783b3302a 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1506,7 +1506,7 @@ static int __init init_hw_perf_events(void)
 		err = amd_pmu_init();
 		break;
 	default:
-		return 0;
+		err = -ENOTSUPP;
 	}
 	if (err != 0) {
 		pr_cont("no PMU driver, software events only.\n");
@@ -1883,9 +1883,9 @@ static struct pmu pmu = {
 
 void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 {
-	userpg->cap_usr_time = 0;
-	userpg->cap_usr_time_zero = 0;
-	userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc;
+	userpg->cap_user_time = 0;
+	userpg->cap_user_time_zero = 0;
+	userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc;
 	userpg->pmc_width = x86_pmu.cntval_bits;
 
 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
@@ -1894,13 +1894,13 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 	if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
 		return;
 
-	userpg->cap_usr_time = 1;
+	userpg->cap_user_time = 1;
 	userpg->time_mult = this_cpu_read(cyc2ns);
 	userpg->time_shift = CYC2NS_SCALE_FACTOR;
 	userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
 
 	if (sched_clock_stable && !check_tsc_disabled()) {
-		userpg->cap_usr_time_zero = 1;
+		userpg->cap_user_time_zero = 1;
 		userpg->time_zero = this_cpu_read(cyc2ns_offset);
 	}
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 9db76c31b3c3..f31a1655d1ff 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2325,6 +2325,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 55: /* Atom 22nm "Silvermont" */
+	case 77: /* Avoton "Silvermont" */
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 8ed44589b0e4..4118f9f68315 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -2706,14 +2706,14 @@ static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box)
 	box->hrtimer.function = uncore_pmu_hrtimer;
 }
 
-struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cpu)
+static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int node)
 {
 	struct intel_uncore_box *box;
 	int i, size;
 
 	size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg);
 
-	box = kzalloc_node(size, GFP_KERNEL, cpu_to_node(cpu));
+	box = kzalloc_node(size, GFP_KERNEL, node);
 	if (!box)
 		return NULL;
 
@@ -3031,7 +3031,7 @@ static int uncore_validate_group(struct intel_uncore_pmu *pmu,
 	struct intel_uncore_box *fake_box;
 	int ret = -EINVAL, n;
 
-	fake_box = uncore_alloc_box(pmu->type, smp_processor_id());
+	fake_box = uncore_alloc_box(pmu->type, NUMA_NO_NODE);
 	if (!fake_box)
 		return -ENOMEM;
 
@@ -3294,7 +3294,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	}
 
 	type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];
-	box = uncore_alloc_box(type, 0);
+	box = uncore_alloc_box(type, NUMA_NO_NODE);
 	if (!box)
 		return -ENOMEM;
 
@@ -3499,7 +3499,7 @@ static int uncore_cpu_prepare(int cpu, int phys_id)
 			if (pmu->func_id < 0)
 				pmu->func_id = j;
 
-			box = uncore_alloc_box(type, cpu);
+			box = uncore_alloc_box(type, cpu_to_node(cpu));
 			if (!box)
 				return -ENOMEM;
 
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 7123b5df479d..af99f71aeb7f 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -216,6 +216,7 @@ int apply_microcode_amd(int cpu)
 	/* need to apply patch? */
 	if (rev >= mc_amd->hdr.patch_id) {
 		c->microcode = rev;
+		uci->cpu_sig.rev = rev;
 		return 0;
 	}
 
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 563ed91e6faa..e643e744e4d8 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -352,12 +352,28 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 	},
 	{	/* Handle problems with rebooting on the Precision M6600. */
 		.callback = set_pci_reboot,
-		.ident = "Dell OptiPlex 990",
+		.ident = "Dell Precision M6600",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"),
 		},
 	},
+	{	/* Handle problems with rebooting on the Dell PowerEdge C6100. */
+		.callback = set_pci_reboot,
+		.ident = "Dell PowerEdge C6100",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "C6100"),
+		},
+	},
+	{	/* Some C6100 machines were shipped with vendor being 'Dell'. */
+		.callback = set_pci_reboot,
+		.ident = "Dell PowerEdge C6100",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "C6100"),
+		},
+	},
 	{ }
 };
 
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 90f6ed127096..c7e22ab29a5a 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -912,10 +912,13 @@ void __init efi_enter_virtual_mode(void)
 
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
-		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
-		    md->type != EFI_BOOT_SERVICES_CODE &&
-		    md->type != EFI_BOOT_SERVICES_DATA)
-			continue;
+		if (!(md->attribute & EFI_MEMORY_RUNTIME)) {
+#ifdef CONFIG_X86_64
+			if (md->type != EFI_BOOT_SERVICES_CODE &&
+			    md->type != EFI_BOOT_SERVICES_DATA)
+#endif
+				continue;
+		}
 
 		size = md->num_pages << EFI_PAGE_SHIFT;
 		end = md->phys_addr + size;
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 8b901e8d782d..a61c7d5811be 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -879,7 +879,6 @@ int m2p_add_override(unsigned long mfn, struct page *page,
 	unsigned long uninitialized_var(address);
 	unsigned level;
 	pte_t *ptep = NULL;
-	int ret = 0;
 
 	pfn = page_to_pfn(page);
 	if (!PageHighMem(page)) {
@@ -926,8 +925,8 @@ int m2p_add_override(unsigned long mfn, struct page *page,
 	 * frontend pages while they are being shared with the backend,
 	 * because mfn_to_pfn (that ends up being called by GUPF) will
 	 * return the backend pfn rather than the frontend pfn. */
-	ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
-	if (ret == 0 && get_phys_to_machine(pfn) == mfn)
+	pfn = mfn_to_pfn_no_overrides(mfn);
+	if (get_phys_to_machine(pfn) == mfn)
 		set_phys_to_machine(pfn, FOREIGN_FRAME(mfn));
 
 	return 0;
@@ -942,7 +941,6 @@ int m2p_remove_override(struct page *page,
 	unsigned long uninitialized_var(address);
 	unsigned level;
 	pte_t *ptep = NULL;
-	int ret = 0;
 
 	pfn = page_to_pfn(page);
 	mfn = get_phys_to_machine(pfn);
@@ -1029,8 +1027,8 @@ int m2p_remove_override(struct page *page,
 	 * the original pfn causes mfn_to_pfn(mfn) to return the frontend
 	 * pfn again. */
 	mfn &= ~FOREIGN_FRAME_BIT;
-	ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
-	if (ret == 0 && get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
+	pfn = mfn_to_pfn_no_overrides(mfn);
+	if (get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
 			m2p_find_override(mfn) == NULL)
 		set_phys_to_machine(pfn, mfn);
 
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 253f63fceea1..be6b86078957 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -259,6 +259,14 @@ void xen_uninit_lock_cpu(int cpu)
 }
 
 
+/*
+ * Our init of PV spinlocks is split in two init functions due to us
+ * using paravirt patching and jump labels patching and having to do
+ * all of this before SMP code is invoked.
+ *
+ * The paravirt patching needs to be done _before_ the alternative asm code
+ * is started, otherwise we would not patch the core kernel code.
+ */
 void __init xen_init_spinlocks(void)
 {
 
@@ -267,12 +275,26 @@ void __init xen_init_spinlocks(void)
 		return;
 	}
 
-	static_key_slow_inc(&paravirt_ticketlocks_enabled);
-
 	pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
 	pv_lock_ops.unlock_kick = xen_unlock_kick;
 }
 
+/*
+ * While the jump_label init code needs to happend _after_ the jump labels are
+ * enabled and before SMP is started. Hence we use pre-SMP initcall level
+ * init. We cannot do it in xen_init_spinlocks as that is done before
+ * jump labels are activated.
+ */
+static __init int xen_init_spinlocks_jump(void)
+{
+	if (!xen_pvspin)
+		return 0;
+
+	static_key_slow_inc(&paravirt_ticketlocks_enabled);
+	return 0;
+}
+early_initcall(xen_init_spinlocks_jump);
+
 static __init int xen_parse_nopvspin(char *arg)
 {
 	xen_pvspin = false;
diff --git a/drivers/acpi/acpi_ipmi.c b/drivers/acpi/acpi_ipmi.c
index f40acef80269..a6977e12d574 100644
--- a/drivers/acpi/acpi_ipmi.c
+++ b/drivers/acpi/acpi_ipmi.c
@@ -39,6 +39,7 @@
 #include <linux/ipmi.h>
 #include <linux/device.h>
 #include <linux/pnp.h>
+#include <linux/spinlock.h>
 
 MODULE_AUTHOR("Zhao Yakui");
 MODULE_DESCRIPTION("ACPI IPMI Opregion driver");
@@ -57,7 +58,7 @@ struct acpi_ipmi_device {
 	struct list_head head;
 	/* the IPMI request message list */
 	struct list_head tx_msg_list;
-	struct mutex	tx_msg_lock;
+	spinlock_t	tx_msg_lock;
 	acpi_handle handle;
 	struct pnp_dev *pnp_dev;
 	ipmi_user_t	user_interface;
@@ -147,6 +148,7 @@ static void acpi_format_ipmi_msg(struct acpi_ipmi_msg *tx_msg,
 	struct kernel_ipmi_msg *msg;
 	struct acpi_ipmi_buffer *buffer;
 	struct acpi_ipmi_device *device;
+	unsigned long flags;
 
 	msg = &tx_msg->tx_message;
 	/*
@@ -177,10 +179,10 @@ static void acpi_format_ipmi_msg(struct acpi_ipmi_msg *tx_msg,
 
 	/* Get the msgid */
 	device = tx_msg->device;
-	mutex_lock(&device->tx_msg_lock);
+	spin_lock_irqsave(&device->tx_msg_lock, flags);
 	device->curr_msgid++;
 	tx_msg->tx_msgid = device->curr_msgid;
-	mutex_unlock(&device->tx_msg_lock);
+	spin_unlock_irqrestore(&device->tx_msg_lock, flags);
 }
 
 static void acpi_format_ipmi_response(struct acpi_ipmi_msg *msg,
@@ -242,6 +244,7 @@ static void ipmi_msg_handler(struct ipmi_recv_msg *msg, void *user_msg_data)
 	int msg_found = 0;
 	struct acpi_ipmi_msg *tx_msg;
 	struct pnp_dev *pnp_dev = ipmi_device->pnp_dev;
+	unsigned long flags;
 
 	if (msg->user != ipmi_device->user_interface) {
 		dev_warn(&pnp_dev->dev, "Unexpected response is returned. "
@@ -250,7 +253,7 @@ static void ipmi_msg_handler(struct ipmi_recv_msg *msg, void *user_msg_data)
 		ipmi_free_recv_msg(msg);
 		return;
 	}
-	mutex_lock(&ipmi_device->tx_msg_lock);
+	spin_lock_irqsave(&ipmi_device->tx_msg_lock, flags);
 	list_for_each_entry(tx_msg, &ipmi_device->tx_msg_list, head) {
 		if (msg->msgid == tx_msg->tx_msgid) {
 			msg_found = 1;
@@ -258,7 +261,7 @@ static void ipmi_msg_handler(struct ipmi_recv_msg *msg, void *user_msg_data)
 		}
 	}
 
-	mutex_unlock(&ipmi_device->tx_msg_lock);
+	spin_unlock_irqrestore(&ipmi_device->tx_msg_lock, flags);
 	if (!msg_found) {
 		dev_warn(&pnp_dev->dev, "Unexpected response (msg id %ld) is "
 			"returned.\n", msg->msgid);
@@ -378,6 +381,7 @@ acpi_ipmi_space_handler(u32 function, acpi_physical_address address,
 	struct acpi_ipmi_device *ipmi_device = handler_context;
 	int err, rem_time;
 	acpi_status status;
+	unsigned long flags;
 	/*
 	 * IPMI opregion message.
 	 * IPMI message is firstly written to the BMC and system software
@@ -395,9 +399,9 @@ acpi_ipmi_space_handler(u32 function, acpi_physical_address address,
 		return AE_NO_MEMORY;
 
 	acpi_format_ipmi_msg(tx_msg, address, value);
-	mutex_lock(&ipmi_device->tx_msg_lock);
+	spin_lock_irqsave(&ipmi_device->tx_msg_lock, flags);
 	list_add_tail(&tx_msg->head, &ipmi_device->tx_msg_list);
-	mutex_unlock(&ipmi_device->tx_msg_lock);
+	spin_unlock_irqrestore(&ipmi_device->tx_msg_lock, flags);
 	err = ipmi_request_settime(ipmi_device->user_interface,
 					&tx_msg->addr,
 					tx_msg->tx_msgid,
@@ -413,9 +417,9 @@ acpi_ipmi_space_handler(u32 function, acpi_physical_address address,
 	status = AE_OK;
 
 end_label:
-	mutex_lock(&ipmi_device->tx_msg_lock);
+	spin_lock_irqsave(&ipmi_device->tx_msg_lock, flags);
 	list_del(&tx_msg->head);
-	mutex_unlock(&ipmi_device->tx_msg_lock);
+	spin_unlock_irqrestore(&ipmi_device->tx_msg_lock, flags);
 	kfree(tx_msg);
 	return status;
 }
@@ -457,7 +461,7 @@ static void acpi_add_ipmi_device(struct acpi_ipmi_device *ipmi_device)
 
 	INIT_LIST_HEAD(&ipmi_device->head);
 
-	mutex_init(&ipmi_device->tx_msg_lock);
+	spin_lock_init(&ipmi_device->tx_msg_lock);
 	INIT_LIST_HEAD(&ipmi_device->tx_msg_list);
 	ipmi_install_space_handler(ipmi_device);
 
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index fbdb82e70d10..611ce9061dc5 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1121,7 +1121,7 @@ int acpi_bus_register_driver(struct acpi_driver *driver)
 EXPORT_SYMBOL(acpi_bus_register_driver);
 
 /**
- * acpi_bus_unregister_driver - unregisters a driver with the APIC bus
+ * acpi_bus_unregister_driver - unregisters a driver with the ACPI bus
  * @driver: driver to unregister
  *
  * Unregisters a driver with the ACPI bus.  Searches the namespace for all
diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c
index 958ba2a420c3..97f4acb54ad6 100644
--- a/drivers/ata/sata_promise.c
+++ b/drivers/ata/sata_promise.c
@@ -2,7 +2,7 @@
  *  sata_promise.c - Promise SATA
  *
  *  Maintained by:  Tejun Heo <tj@kernel.org>
- *		    Mikael Pettersson <mikpe@it.uu.se>
+ *		    Mikael Pettersson
  *  		    Please ALWAYS copy linux-ide@vger.kernel.org
  *		    on emails.
  *
diff --git a/drivers/base/core.c b/drivers/base/core.c
index c7cfadcf6752..34abf4d8a45f 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -2017,7 +2017,7 @@ EXPORT_SYMBOL_GPL(device_move);
  */
 void device_shutdown(void)
 {
-	struct device *dev;
+	struct device *dev, *parent;
 
 	spin_lock(&devices_kset->list_lock);
 	/*
@@ -2034,7 +2034,7 @@ void device_shutdown(void)
 		 * prevent it from being freed because parent's
 		 * lock is to be held
 		 */
-		get_device(dev->parent);
+		parent = get_device(dev->parent);
 		get_device(dev);
 		/*
 		 * Make sure the device is off the kset list, in the
@@ -2044,8 +2044,8 @@ void device_shutdown(void)
 		spin_unlock(&devices_kset->list_lock);
 
 		/* hold lock to avoid race with probe/release */
-		if (dev->parent)
-			device_lock(dev->parent);
+		if (parent)
+			device_lock(parent);
 		device_lock(dev);
 
 		/* Don't allow any more runtime suspends */
@@ -2063,11 +2063,11 @@ void device_shutdown(void)
 		}
 
 		device_unlock(dev);
-		if (dev->parent)
-			device_unlock(dev->parent);
+		if (parent)
+			device_unlock(parent);
 
 		put_device(dev);
-		put_device(dev->parent);
+		put_device(parent);
 
 		spin_lock(&devices_kset->list_lock);
 	}
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index d2d95ff5353b..edfa2515bc86 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -1189,6 +1189,7 @@ static int cciss_ioctl32_passthru(struct block_device *bdev, fmode_t mode,
 	int err;
 	u32 cp;
 
+	memset(&arg64, 0, sizeof(arg64));
 	err = 0;
 	err |=
 	    copy_from_user(&arg64.LUN_info, &arg32->LUN_info,
diff --git a/drivers/block/cpqarray.c b/drivers/block/cpqarray.c
index 639d26b90b91..2b9440384536 100644
--- a/drivers/block/cpqarray.c
+++ b/drivers/block/cpqarray.c
@@ -1193,6 +1193,7 @@ out_passthru:
 		ida_pci_info_struct pciinfo;
 
 		if (!arg) return -EINVAL;
+		memset(&pciinfo, 0, sizeof(pciinfo));
 		pciinfo.bus = host->pci_dev->bus->number;
 		pciinfo.dev_fn = host->pci_dev->devfn;
 		pciinfo.board_id = host->board_id;
diff --git a/drivers/char/tpm/xen-tpmfront.c b/drivers/char/tpm/xen-tpmfront.c
index 7a7929ba2658..06189e55b4e5 100644
--- a/drivers/char/tpm/xen-tpmfront.c
+++ b/drivers/char/tpm/xen-tpmfront.c
@@ -142,32 +142,6 @@ static int vtpm_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 	return length;
 }
 
-ssize_t tpm_show_locality(struct device *dev, struct device_attribute *attr,
-			  char *buf)
-{
-	struct tpm_chip *chip = dev_get_drvdata(dev);
-	struct tpm_private *priv = TPM_VPRIV(chip);
-	u8 locality = priv->shr->locality;
-
-	return sprintf(buf, "%d\n", locality);
-}
-
-ssize_t tpm_store_locality(struct device *dev, struct device_attribute *attr,
-			const char *buf, size_t len)
-{
-	struct tpm_chip *chip = dev_get_drvdata(dev);
-	struct tpm_private *priv = TPM_VPRIV(chip);
-	u8 val;
-
-	int rv = kstrtou8(buf, 0, &val);
-	if (rv)
-		return rv;
-
-	priv->shr->locality = val;
-
-	return len;
-}
-
 static const struct file_operations vtpm_ops = {
 	.owner = THIS_MODULE,
 	.llseek = no_llseek,
@@ -188,8 +162,6 @@ static DEVICE_ATTR(caps, S_IRUGO, tpm_show_caps, NULL);
 static DEVICE_ATTR(cancel, S_IWUSR | S_IWGRP, NULL, tpm_store_cancel);
 static DEVICE_ATTR(durations, S_IRUGO, tpm_show_durations, NULL);
 static DEVICE_ATTR(timeouts, S_IRUGO, tpm_show_timeouts, NULL);
-static DEVICE_ATTR(locality, S_IRUGO | S_IWUSR, tpm_show_locality,
-		tpm_store_locality);
 
 static struct attribute *vtpm_attrs[] = {
 	&dev_attr_pubek.attr,
@@ -202,7 +174,6 @@ static struct attribute *vtpm_attrs[] = {
 	&dev_attr_cancel.attr,
 	&dev_attr_durations.attr,
 	&dev_attr_timeouts.attr,
-	&dev_attr_locality.attr,
 	NULL,
 };
 
@@ -210,8 +181,6 @@ static struct attribute_group vtpm_attr_grp = {
 	.attrs = vtpm_attrs,
 };
 
-#define TPM_LONG_TIMEOUT   (10 * 60 * HZ)
-
 static const struct tpm_vendor_specific tpm_vtpm = {
 	.status = vtpm_status,
 	.recv = vtpm_recv,
@@ -224,11 +193,6 @@ static const struct tpm_vendor_specific tpm_vtpm = {
 	.miscdev = {
 		.fops = &vtpm_ops,
 	},
-	.duration = {
-		TPM_LONG_TIMEOUT,
-		TPM_LONG_TIMEOUT,
-		TPM_LONG_TIMEOUT,
-	},
 };
 
 static irqreturn_t tpmif_interrupt(int dummy, void *dev_id)
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 41c69469ce20..971d796e071d 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -26,6 +26,7 @@ config DW_APB_TIMER_OF
 
 config ARMADA_370_XP_TIMER
 	bool
+	select CLKSRC_OF
 
 config ORION_TIMER
 	select CLKSRC_OF
diff --git a/drivers/clocksource/clksrc-of.c b/drivers/clocksource/clksrc-of.c
index 37f5325bec95..b9ddd9e3a2f5 100644
--- a/drivers/clocksource/clksrc-of.c
+++ b/drivers/clocksource/clksrc-of.c
@@ -30,6 +30,9 @@ void __init clocksource_of_init(void)
 	clocksource_of_init_fn init_func;
 
 	for_each_matching_node_and_match(np, __clksrc_of_table, &match) {
+		if (!of_device_is_available(np))
+			continue;
+
 		init_func = match->data;
 		init_func(np);
 	}
diff --git a/drivers/clocksource/em_sti.c b/drivers/clocksource/em_sti.c
index b9c81b7c3a3b..3a5909c12d42 100644
--- a/drivers/clocksource/em_sti.c
+++ b/drivers/clocksource/em_sti.c
@@ -301,7 +301,7 @@ static void em_sti_register_clockevent(struct em_sti_priv *p)
 	ced->name = dev_name(&p->pdev->dev);
 	ced->features = CLOCK_EVT_FEAT_ONESHOT;
 	ced->rating = 200;
-	ced->cpumask = cpumask_of(0);
+	ced->cpumask = cpu_possible_mask;
 	ced->set_next_event = em_sti_clock_event_next;
 	ced->set_mode = em_sti_clock_event_mode;
 
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index 5b34768f4d7c..62b0de6a1837 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -428,7 +428,6 @@ static int exynos4_local_timer_setup(struct clock_event_device *evt)
 				evt->irq);
 			return -EIO;
 		}
-		irq_set_affinity(evt->irq, cpumask_of(cpu));
 	} else {
 		enable_percpu_irq(mct_irqs[MCT_L0_IRQ], 0);
 	}
@@ -449,6 +448,7 @@ static int exynos4_mct_cpu_notify(struct notifier_block *self,
 					   unsigned long action, void *hcpu)
 {
 	struct mct_clock_event_device *mevt;
+	unsigned int cpu;
 
 	/*
 	 * Grab cpu pointer in each case to avoid spurious
@@ -459,6 +459,12 @@ static int exynos4_mct_cpu_notify(struct notifier_block *self,
 		mevt = this_cpu_ptr(&percpu_mct_tick);
 		exynos4_local_timer_setup(&mevt->evt);
 		break;
+	case CPU_ONLINE:
+		cpu = (unsigned long)hcpu;
+		if (mct_int_type == MCT_INT_SPI)
+			irq_set_affinity(mct_irqs[MCT_L0_IRQ + cpu],
+						cpumask_of(cpu));
+		break;
 	case CPU_DYING:
 		mevt = this_cpu_ptr(&percpu_mct_tick);
 		exynos4_local_timer_stop(&mevt->evt);
@@ -500,6 +506,8 @@ static void __init exynos4_timer_resources(struct device_node *np, void __iomem
 					 &percpu_mct_tick);
 		WARN(err, "MCT: can't request IRQ %d (%d)\n",
 		     mct_irqs[MCT_L0_IRQ], err);
+	} else {
+		irq_set_affinity(mct_irqs[MCT_L0_IRQ], cpumask_of(0));
 	}
 
 	err = register_cpu_notifier(&exynos4_mct_cpu_nb);
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index a1260b4549db..d2c3253e015e 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -986,6 +986,10 @@ static int __init acpi_cpufreq_init(void)
 {
 	int ret;
 
+	/* don't keep reloading if cpufreq_driver exists */
+	if (cpufreq_get_current_driver())
+		return 0;
+
 	if (acpi_disabled)
 		return 0;
 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 89b3c52cd5c3..04548f7023af 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1460,6 +1460,9 @@ unsigned int cpufreq_get(unsigned int cpu)
 {
 	unsigned int ret_freq = 0;
 
+	if (cpufreq_disabled() || !cpufreq_driver)
+		return -ENOENT;
+
 	if (!down_read_trylock(&cpufreq_rwsem))
 		return 0;
 
diff --git a/drivers/cpufreq/exynos5440-cpufreq.c b/drivers/cpufreq/exynos5440-cpufreq.c
index d514c152fd1a..be5380ecdcd4 100644
--- a/drivers/cpufreq/exynos5440-cpufreq.c
+++ b/drivers/cpufreq/exynos5440-cpufreq.c
@@ -457,7 +457,7 @@ err_free_table:
 	opp_free_cpufreq_table(dvfs_info->dev, &dvfs_info->freq_table);
 err_put_node:
 	of_node_put(np);
-	dev_err(dvfs_info->dev, "%s: failed initialization\n", __func__);
+	dev_err(&pdev->dev, "%s: failed initialization\n", __func__);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index b1f8fc69023f..60e84043aa34 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -707,8 +707,7 @@ tda998x_encoder_dpms(struct drm_encoder *encoder, int mode)
 		reg_write(encoder, REG_VIP_CNTRL_2, priv->vip_cntrl_2);
 		break;
 	case DRM_MODE_DPMS_OFF:
-		/* disable audio and video ports */
-		reg_write(encoder, REG_ENA_AP, 0x00);
+		/* disable video ports */
 		reg_write(encoder, REG_ENA_VP_0, 0x00);
 		reg_write(encoder, REG_ENA_VP_1, 0x00);
 		reg_write(encoder, REG_ENA_VP_2, 0x00);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index df9253d890ee..cdfb9da0e4ce 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4800,10 +4800,10 @@ i915_gem_inactive_count(struct shrinker *shrinker, struct shrink_control *sc)
 
 	if (!mutex_trylock(&dev->struct_mutex)) {
 		if (!mutex_is_locked_by(&dev->struct_mutex, current))
-			return SHRINK_STOP;
+			return 0;
 
 		if (dev_priv->mm.shrinker_no_lock_stealing)
-			return SHRINK_STOP;
+			return 0;
 
 		unlock = false;
 	}
@@ -4901,10 +4901,10 @@ i915_gem_inactive_scan(struct shrinker *shrinker, struct shrink_control *sc)
 
 	if (!mutex_trylock(&dev->struct_mutex)) {
 		if (!mutex_is_locked_by(&dev->struct_mutex, current))
-			return 0;
+			return SHRINK_STOP;
 
 		if (dev_priv->mm.shrinker_no_lock_stealing)
-			return 0;
+			return SHRINK_STOP;
 
 		unlock = false;
 	}
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index aba9d7498996..dae364f0028c 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -143,8 +143,10 @@ static void i915_error_vprintf(struct drm_i915_error_state_buf *e,
 
 	/* Seek the first printf which is hits start position */
 	if (e->pos < e->start) {
-		len = vsnprintf(NULL, 0, f, args);
-		if (!__i915_error_seek(e, len))
+		va_list tmp;
+
+		va_copy(tmp, args);
+		if (!__i915_error_seek(e, vsnprintf(NULL, 0, f, tmp)))
 			return;
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index d8a1d98693e7..e5822e79f912 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -4775,6 +4775,10 @@ static void i9xx_set_pipeconf(struct intel_crtc *intel_crtc)
 
 	pipeconf = 0;
 
+	if (dev_priv->quirks & QUIRK_PIPEA_FORCE &&
+	    I915_READ(PIPECONF(intel_crtc->pipe)) & PIPECONF_ENABLE)
+		pipeconf |= PIPECONF_ENABLE;
+
 	if (intel_crtc->pipe == 0 && INTEL_INFO(dev)->gen < 4) {
 		/* Enable pixel doubling when the dot clock is > 90% of the (display)
 		 * core speed.
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 2151d13772b8..79c14e298ba6 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -588,7 +588,18 @@ intel_dp_i2c_aux_ch(struct i2c_adapter *adapter, int mode,
 			DRM_DEBUG_KMS("aux_ch native nack\n");
 			return -EREMOTEIO;
 		case AUX_NATIVE_REPLY_DEFER:
-			udelay(100);
+			/*
+			 * For now, just give more slack to branch devices. We
+			 * could check the DPCD for I2C bit rate capabilities,
+			 * and if available, adjust the interval. We could also
+			 * be more careful with DP-to-Legacy adapters where a
+			 * long legacy cable may force very low I2C bit rates.
+			 */
+			if (intel_dp->dpcd[DP_DOWNSTREAMPORT_PRESENT] &
+			    DP_DWN_STRM_PORT_PRESENT)
+				usleep_range(500, 600);
+			else
+				usleep_range(300, 400);
 			continue;
 		default:
 			DRM_ERROR("aux_ch invalid native reply 0x%02x\n",
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index f2c6d7909ae2..dd6f84bf6c22 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -916,6 +916,14 @@ intel_tv_compute_config(struct intel_encoder *encoder,
 	DRM_DEBUG_KMS("forcing bpc to 8 for TV\n");
 	pipe_config->pipe_bpp = 8*3;
 
+	/* TV has it's own notion of sync and other mode flags, so clear them. */
+	pipe_config->adjusted_mode.flags = 0;
+
+	/*
+	 * FIXME: We don't check whether the input mode is actually what we want
+	 * or whether userspace is doing something stupid.
+	 */
+
 	return true;
 }
 
diff --git a/drivers/gpu/drm/msm/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/mdp4/mdp4_kms.c
index 5db5bbaedae2..bc7fd11ad8be 100644
--- a/drivers/gpu/drm/msm/mdp4/mdp4_kms.c
+++ b/drivers/gpu/drm/msm/mdp4/mdp4_kms.c
@@ -19,8 +19,6 @@
 #include "msm_drv.h"
 #include "mdp4_kms.h"
 
-#include <mach/iommu.h>
-
 static struct mdp4_platform_config *mdp4_get_config(struct platform_device *dev);
 
 static int mdp4_hw_init(struct msm_kms *kms)
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 008d772384c7..b3a2f1629041 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -18,8 +18,6 @@
 #include "msm_drv.h"
 #include "msm_gpu.h"
 
-#include <mach/iommu.h>
-
 static void msm_fb_output_poll_changed(struct drm_device *dev)
 {
 	struct msm_drm_private *priv = dev->dev_private;
@@ -62,6 +60,8 @@ int msm_iommu_attach(struct drm_device *dev, struct iommu_domain *iommu,
 	int i, ret;
 
 	for (i = 0; i < cnt; i++) {
+		/* TODO maybe some day msm iommu won't require this hack: */
+		struct device *msm_iommu_get_ctx(const char *ctx_name);
 		struct device *ctx = msm_iommu_get_ctx(names[i]);
 		if (!ctx)
 			continue;
@@ -199,7 +199,7 @@ static int msm_load(struct drm_device *dev, unsigned long flags)
 		 * imx drm driver on iMX5
 		 */
 		dev_err(dev->dev, "failed to load kms\n");
-		ret = PTR_ERR(priv->kms);
+		ret = PTR_ERR(kms);
 		goto fail;
 	}
 
@@ -697,7 +697,7 @@ static struct drm_driver msm_driver = {
 	.gem_vm_ops         = &vm_ops,
 	.dumb_create        = msm_gem_dumb_create,
 	.dumb_map_offset    = msm_gem_dumb_map_offset,
-	.dumb_destroy       = msm_gem_dumb_destroy,
+	.dumb_destroy       = drm_gem_dumb_destroy,
 #ifdef CONFIG_DEBUG_FS
 	.debugfs_init       = msm_debugfs_init,
 	.debugfs_cleanup    = msm_debugfs_cleanup,
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 29eacfa29cfb..2bae46c66a30 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -319,13 +319,6 @@ int msm_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
 			MSM_BO_SCANOUT | MSM_BO_WC, &args->handle);
 }
 
-int msm_gem_dumb_destroy(struct drm_file *file, struct drm_device *dev,
-		uint32_t handle)
-{
-	/* No special work needed, drop the reference and see what falls out */
-	return drm_gem_handle_delete(file, handle);
-}
-
 int msm_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev,
 		uint32_t handle, uint64_t *offset)
 {
diff --git a/drivers/gpu/drm/radeon/btc_dpm.c b/drivers/gpu/drm/radeon/btc_dpm.c
index 05ff315e8e9e..b162e98a2953 100644
--- a/drivers/gpu/drm/radeon/btc_dpm.c
+++ b/drivers/gpu/drm/radeon/btc_dpm.c
@@ -1168,6 +1168,23 @@ static const struct radeon_blacklist_clocks btc_blacklist_clocks[] =
         { 25000, 30000, RADEON_SCLK_UP }
 };
 
+void btc_get_max_clock_from_voltage_dependency_table(struct radeon_clock_voltage_dependency_table *table,
+						     u32 *max_clock)
+{
+	u32 i, clock = 0;
+
+	if ((table == NULL) || (table->count == 0)) {
+		*max_clock = clock;
+		return;
+	}
+
+	for (i = 0; i < table->count; i++) {
+		if (clock < table->entries[i].clk)
+			clock = table->entries[i].clk;
+	}
+	*max_clock = clock;
+}
+
 void btc_apply_voltage_dependency_rules(struct radeon_clock_voltage_dependency_table *table,
 					u32 clock, u16 max_voltage, u16 *voltage)
 {
@@ -2080,6 +2097,7 @@ static void btc_apply_state_adjust_rules(struct radeon_device *rdev,
 	bool disable_mclk_switching;
 	u32 mclk, sclk;
 	u16 vddc, vddci;
+	u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc;
 
 	if ((rdev->pm.dpm.new_active_crtc_count > 1) ||
 	    btc_dpm_vblank_too_short(rdev))
@@ -2121,6 +2139,39 @@ static void btc_apply_state_adjust_rules(struct radeon_device *rdev,
 			ps->low.vddci = max_limits->vddci;
 	}
 
+	/* limit clocks to max supported clocks based on voltage dependency tables */
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk,
+							&max_sclk_vddc);
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk,
+							&max_mclk_vddci);
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk,
+							&max_mclk_vddc);
+
+	if (max_sclk_vddc) {
+		if (ps->low.sclk > max_sclk_vddc)
+			ps->low.sclk = max_sclk_vddc;
+		if (ps->medium.sclk > max_sclk_vddc)
+			ps->medium.sclk = max_sclk_vddc;
+		if (ps->high.sclk > max_sclk_vddc)
+			ps->high.sclk = max_sclk_vddc;
+	}
+	if (max_mclk_vddci) {
+		if (ps->low.mclk > max_mclk_vddci)
+			ps->low.mclk = max_mclk_vddci;
+		if (ps->medium.mclk > max_mclk_vddci)
+			ps->medium.mclk = max_mclk_vddci;
+		if (ps->high.mclk > max_mclk_vddci)
+			ps->high.mclk = max_mclk_vddci;
+	}
+	if (max_mclk_vddc) {
+		if (ps->low.mclk > max_mclk_vddc)
+			ps->low.mclk = max_mclk_vddc;
+		if (ps->medium.mclk > max_mclk_vddc)
+			ps->medium.mclk = max_mclk_vddc;
+		if (ps->high.mclk > max_mclk_vddc)
+			ps->high.mclk = max_mclk_vddc;
+	}
+
 	/* XXX validate the min clocks required for display */
 
 	if (disable_mclk_switching) {
diff --git a/drivers/gpu/drm/radeon/btc_dpm.h b/drivers/gpu/drm/radeon/btc_dpm.h
index 1a15e0e41950..3b6f12b7760b 100644
--- a/drivers/gpu/drm/radeon/btc_dpm.h
+++ b/drivers/gpu/drm/radeon/btc_dpm.h
@@ -46,6 +46,8 @@ void btc_adjust_clock_combinations(struct radeon_device *rdev,
 				   struct rv7xx_pl *pl);
 void btc_apply_voltage_dependency_rules(struct radeon_clock_voltage_dependency_table *table,
 					u32 clock, u16 max_voltage, u16 *voltage);
+void btc_get_max_clock_from_voltage_dependency_table(struct radeon_clock_voltage_dependency_table *table,
+						     u32 *max_clock);
 void btc_apply_voltage_delta_rules(struct radeon_device *rdev,
 				   u16 max_vddc, u16 max_vddci,
 				   u16 *vddc, u16 *vddci);
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index 899627443030..51e947a97edf 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -146,6 +146,8 @@ static const struct ci_pt_config_reg didt_config_ci[] =
 };
 
 extern u8 rv770_get_memory_module_index(struct radeon_device *rdev);
+extern void btc_get_max_clock_from_voltage_dependency_table(struct radeon_clock_voltage_dependency_table *table,
+							    u32 *max_clock);
 extern int ni_copy_and_switch_arb_sets(struct radeon_device *rdev,
 				       u32 arb_freq_src, u32 arb_freq_dest);
 extern u8 si_get_ddr3_mclk_frequency_ratio(u32 memory_clock);
@@ -712,6 +714,7 @@ static void ci_apply_state_adjust_rules(struct radeon_device *rdev,
 	struct radeon_clock_and_voltage_limits *max_limits;
 	bool disable_mclk_switching;
 	u32 sclk, mclk;
+	u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc;
 	int i;
 
 	if ((rdev->pm.dpm.new_active_crtc_count > 1) ||
@@ -739,6 +742,29 @@ static void ci_apply_state_adjust_rules(struct radeon_device *rdev,
 		}
 	}
 
+	/* limit clocks to max supported clocks based on voltage dependency tables */
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk,
+							&max_sclk_vddc);
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk,
+							&max_mclk_vddci);
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk,
+							&max_mclk_vddc);
+
+	for (i = 0; i < ps->performance_level_count; i++) {
+		if (max_sclk_vddc) {
+			if (ps->performance_levels[i].sclk > max_sclk_vddc)
+				ps->performance_levels[i].sclk = max_sclk_vddc;
+		}
+		if (max_mclk_vddci) {
+			if (ps->performance_levels[i].mclk > max_mclk_vddci)
+				ps->performance_levels[i].mclk = max_mclk_vddci;
+		}
+		if (max_mclk_vddc) {
+			if (ps->performance_levels[i].mclk > max_mclk_vddc)
+				ps->performance_levels[i].mclk = max_mclk_vddc;
+		}
+	}
+
 	/* XXX validate the min clocks required for display */
 
 	if (disable_mclk_switching) {
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index adbdb6503b05..d02fd1c045d5 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -2845,10 +2845,8 @@ static void cik_gpu_init(struct radeon_device *rdev)
 		rdev->config.cik.tile_config |= (3 << 0);
 		break;
 	}
-	if ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT)
-		rdev->config.cik.tile_config |= 1 << 4;
-	else
-		rdev->config.cik.tile_config |= 0 << 4;
+	rdev->config.cik.tile_config |=
+		((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT) << 4;
 	rdev->config.cik.tile_config |=
 		((gb_addr_config & PIPE_INTERLEAVE_SIZE_MASK) >> PIPE_INTERLEAVE_SIZE_SHIFT) << 8;
 	rdev->config.cik.tile_config |=
@@ -4456,8 +4454,8 @@ static int cik_mc_init(struct radeon_device *rdev)
 	rdev->mc.aper_base = pci_resource_start(rdev->pdev, 0);
 	rdev->mc.aper_size = pci_resource_len(rdev->pdev, 0);
 	/* size in MB on si */
-	rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE) * 1024 * 1024;
-	rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024 * 1024;
+	rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL;
+	rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL;
 	rdev->mc.visible_vram_size = rdev->mc.aper_size;
 	si_vram_gtt_location(rdev, &rdev->mc);
 	radeon_update_bandwidth_info(rdev);
@@ -4735,12 +4733,13 @@ static void cik_vm_decode_fault(struct radeon_device *rdev,
 	u32 mc_id = (status & MEMORY_CLIENT_ID_MASK) >> MEMORY_CLIENT_ID_SHIFT;
 	u32 vmid = (status & FAULT_VMID_MASK) >> FAULT_VMID_SHIFT;
 	u32 protections = (status & PROTECTIONS_MASK) >> PROTECTIONS_SHIFT;
-	char *block = (char *)&mc_client;
+	char block[5] = { mc_client >> 24, (mc_client >> 16) & 0xff,
+		(mc_client >> 8) & 0xff, mc_client & 0xff, 0 };
 
-	printk("VM fault (0x%02x, vmid %d) at page %u, %s from %s (%d)\n",
+	printk("VM fault (0x%02x, vmid %d) at page %u, %s from '%s' (0x%08x) (%d)\n",
 	       protections, vmid, addr,
 	       (status & MEMORY_CLIENT_RW_MASK) ? "write" : "read",
-	       block, mc_id);
+	       block, mc_client, mc_id);
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c
index 6c398a456d78..f26339028154 100644
--- a/drivers/gpu/drm/radeon/ni_dpm.c
+++ b/drivers/gpu/drm/radeon/ni_dpm.c
@@ -787,6 +787,7 @@ static void ni_apply_state_adjust_rules(struct radeon_device *rdev,
 	bool disable_mclk_switching;
 	u32 mclk, sclk;
 	u16 vddc, vddci;
+	u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc;
 	int i;
 
 	if ((rdev->pm.dpm.new_active_crtc_count > 1) ||
@@ -813,6 +814,29 @@ static void ni_apply_state_adjust_rules(struct radeon_device *rdev,
 		}
 	}
 
+	/* limit clocks to max supported clocks based on voltage dependency tables */
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk,
+							&max_sclk_vddc);
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk,
+							&max_mclk_vddci);
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk,
+							&max_mclk_vddc);
+
+	for (i = 0; i < ps->performance_level_count; i++) {
+		if (max_sclk_vddc) {
+			if (ps->performance_levels[i].sclk > max_sclk_vddc)
+				ps->performance_levels[i].sclk = max_sclk_vddc;
+		}
+		if (max_mclk_vddci) {
+			if (ps->performance_levels[i].mclk > max_mclk_vddci)
+				ps->performance_levels[i].mclk = max_mclk_vddci;
+		}
+		if (max_mclk_vddc) {
+			if (ps->performance_levels[i].mclk > max_mclk_vddc)
+				ps->performance_levels[i].mclk = max_mclk_vddc;
+		}
+	}
+
 	/* XXX validate the min clocks required for display */
 
 	if (disable_mclk_switching) {
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 24175717307b..d71333033b2b 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -2933,9 +2933,11 @@ static int r100_debugfs_cp_ring_info(struct seq_file *m, void *data)
 	seq_printf(m, "CP_RB_RPTR 0x%08x\n", rdp);
 	seq_printf(m, "%u free dwords in ring\n", ring->ring_free_dw);
 	seq_printf(m, "%u dwords in ring\n", count);
-	for (j = 0; j <= count; j++) {
-		i = (rdp + j) & ring->ptr_mask;
-		seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]);
+	if (ring->ready) {
+		for (j = 0; j <= count; j++) {
+			i = (rdp + j) & ring->ptr_mask;
+			seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]);
+		}
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/r600_dpm.c b/drivers/gpu/drm/radeon/r600_dpm.c
index e65f211a7be0..5513d8f06252 100644
--- a/drivers/gpu/drm/radeon/r600_dpm.c
+++ b/drivers/gpu/drm/radeon/r600_dpm.c
@@ -1084,7 +1084,7 @@ int r600_parse_extended_power_table(struct radeon_device *rdev)
 				rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries[i].dclk =
 					le16_to_cpu(uvd_clk->usDClkLow) | (uvd_clk->ucDClkHigh << 16);
 				rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries[i].v =
-					le16_to_cpu(limits->entries[i].usVoltage);
+					le16_to_cpu(entry->usVoltage);
 				entry = (ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record *)
 					((u8 *)entry + sizeof(ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record));
 			}
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index f443010ce90b..b0fa6002af3e 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -257,10 +257,7 @@ void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 	 * number (coefficient of two integer numbers.  DCCG_AUDIO_DTOx_PHASE
 	 * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator
 	 */
-	if (ASIC_IS_DCE3(rdev)) {
-		/* according to the reg specs, this should DCE3.2 only, but in
-		 * practice it seems to cover DCE3.0 as well.
-		 */
+	if (ASIC_IS_DCE32(rdev)) {
 		if (dig->dig_encoder == 0) {
 			dto_cntl = RREG32(DCCG_AUDIO_DTO0_CNTL) & ~DCCG_AUDIO_DTO_WALLCLOCK_RATIO_MASK;
 			dto_cntl |= DCCG_AUDIO_DTO_WALLCLOCK_RATIO(wallclock_ratio);
@@ -276,8 +273,21 @@ void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 			WREG32(DCCG_AUDIO_DTO1_MODULE, dto_modulo);
 			WREG32(DCCG_AUDIO_DTO_SELECT, 1); /* select DTO1 */
 		}
+	} else if (ASIC_IS_DCE3(rdev)) {
+		/* according to the reg specs, this should DCE3.2 only, but in
+		 * practice it seems to cover DCE3.0/3.1 as well.
+		 */
+		if (dig->dig_encoder == 0) {
+			WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100);
+			WREG32(DCCG_AUDIO_DTO0_MODULE, clock * 100);
+			WREG32(DCCG_AUDIO_DTO_SELECT, 0); /* select DTO0 */
+		} else {
+			WREG32(DCCG_AUDIO_DTO1_PHASE, base_rate * 100);
+			WREG32(DCCG_AUDIO_DTO1_MODULE, clock * 100);
+			WREG32(DCCG_AUDIO_DTO_SELECT, 1); /* select DTO1 */
+		}
 	} else {
-		/* according to the reg specs, this should be DCE2.0 and DCE3.0 */
+		/* according to the reg specs, this should be DCE2.0 and DCE3.0/3.1 */
 		WREG32(AUDIO_DTO, AUDIO_DTO_PHASE(base_rate / 10) |
 		       AUDIO_DTO_MODULE(clock / 10));
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index 5003385a7512..8f7e04538fd6 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -1004,6 +1004,8 @@ static struct radeon_asic rv6xx_asic = {
 		.wait_for_vblank = &avivo_wait_for_vblank,
 		.set_backlight_level = &atombios_set_backlight_level,
 		.get_backlight_level = &atombios_get_backlight_level,
+		.hdmi_enable = &r600_hdmi_enable,
+		.hdmi_setmode = &r600_hdmi_setmode,
 	},
 	.copy = {
 		.blit = &r600_copy_cpdma,
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index 404e25d285ba..f79ee184ffd5 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -1367,6 +1367,7 @@ bool radeon_atombios_get_ppll_ss_info(struct radeon_device *rdev,
 	int index = GetIndexIntoMasterTable(DATA, PPLL_SS_Info);
 	uint16_t data_offset, size;
 	struct _ATOM_SPREAD_SPECTRUM_INFO *ss_info;
+	struct _ATOM_SPREAD_SPECTRUM_ASSIGNMENT *ss_assign;
 	uint8_t frev, crev;
 	int i, num_indices;
 
@@ -1378,18 +1379,21 @@ bool radeon_atombios_get_ppll_ss_info(struct radeon_device *rdev,
 
 		num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) /
 			sizeof(ATOM_SPREAD_SPECTRUM_ASSIGNMENT);
-
+		ss_assign = (struct _ATOM_SPREAD_SPECTRUM_ASSIGNMENT*)
+			((u8 *)&ss_info->asSS_Info[0]);
 		for (i = 0; i < num_indices; i++) {
-			if (ss_info->asSS_Info[i].ucSS_Id == id) {
+			if (ss_assign->ucSS_Id == id) {
 				ss->percentage =
-					le16_to_cpu(ss_info->asSS_Info[i].usSpreadSpectrumPercentage);
-				ss->type = ss_info->asSS_Info[i].ucSpreadSpectrumType;
-				ss->step = ss_info->asSS_Info[i].ucSS_Step;
-				ss->delay = ss_info->asSS_Info[i].ucSS_Delay;
-				ss->range = ss_info->asSS_Info[i].ucSS_Range;
-				ss->refdiv = ss_info->asSS_Info[i].ucRecommendedRef_Div;
+					le16_to_cpu(ss_assign->usSpreadSpectrumPercentage);
+				ss->type = ss_assign->ucSpreadSpectrumType;
+				ss->step = ss_assign->ucSS_Step;
+				ss->delay = ss_assign->ucSS_Delay;
+				ss->range = ss_assign->ucSS_Range;
+				ss->refdiv = ss_assign->ucRecommendedRef_Div;
 				return true;
 			}
+			ss_assign = (struct _ATOM_SPREAD_SPECTRUM_ASSIGNMENT*)
+				((u8 *)ss_assign + sizeof(struct _ATOM_SPREAD_SPECTRUM_ASSIGNMENT));
 		}
 	}
 	return false;
@@ -1477,6 +1481,12 @@ union asic_ss_info {
 	struct _ATOM_ASIC_INTERNAL_SS_INFO_V3 info_3;
 };
 
+union asic_ss_assignment {
+	struct _ATOM_ASIC_SS_ASSIGNMENT v1;
+	struct _ATOM_ASIC_SS_ASSIGNMENT_V2 v2;
+	struct _ATOM_ASIC_SS_ASSIGNMENT_V3 v3;
+};
+
 bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev,
 				      struct radeon_atom_ss *ss,
 				      int id, u32 clock)
@@ -1485,6 +1495,7 @@ bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev,
 	int index = GetIndexIntoMasterTable(DATA, ASIC_InternalSS_Info);
 	uint16_t data_offset, size;
 	union asic_ss_info *ss_info;
+	union asic_ss_assignment *ss_assign;
 	uint8_t frev, crev;
 	int i, num_indices;
 
@@ -1509,45 +1520,52 @@ bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev,
 			num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) /
 				sizeof(ATOM_ASIC_SS_ASSIGNMENT);
 
+			ss_assign = (union asic_ss_assignment *)((u8 *)&ss_info->info.asSpreadSpectrum[0]);
 			for (i = 0; i < num_indices; i++) {
-				if ((ss_info->info.asSpreadSpectrum[i].ucClockIndication == id) &&
-				    (clock <= le32_to_cpu(ss_info->info.asSpreadSpectrum[i].ulTargetClockRange))) {
+				if ((ss_assign->v1.ucClockIndication == id) &&
+				    (clock <= le32_to_cpu(ss_assign->v1.ulTargetClockRange))) {
 					ss->percentage =
-						le16_to_cpu(ss_info->info.asSpreadSpectrum[i].usSpreadSpectrumPercentage);
-					ss->type = ss_info->info.asSpreadSpectrum[i].ucSpreadSpectrumMode;
-					ss->rate = le16_to_cpu(ss_info->info.asSpreadSpectrum[i].usSpreadRateInKhz);
+						le16_to_cpu(ss_assign->v1.usSpreadSpectrumPercentage);
+					ss->type = ss_assign->v1.ucSpreadSpectrumMode;
+					ss->rate = le16_to_cpu(ss_assign->v1.usSpreadRateInKhz);
 					return true;
 				}
+				ss_assign = (union asic_ss_assignment *)
+					((u8 *)ss_assign + sizeof(ATOM_ASIC_SS_ASSIGNMENT));
 			}
 			break;
 		case 2:
 			num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) /
 				sizeof(ATOM_ASIC_SS_ASSIGNMENT_V2);
+			ss_assign = (union asic_ss_assignment *)((u8 *)&ss_info->info_2.asSpreadSpectrum[0]);
 			for (i = 0; i < num_indices; i++) {
-				if ((ss_info->info_2.asSpreadSpectrum[i].ucClockIndication == id) &&
-				    (clock <= le32_to_cpu(ss_info->info_2.asSpreadSpectrum[i].ulTargetClockRange))) {
+				if ((ss_assign->v2.ucClockIndication == id) &&
+				    (clock <= le32_to_cpu(ss_assign->v2.ulTargetClockRange))) {
 					ss->percentage =
-						le16_to_cpu(ss_info->info_2.asSpreadSpectrum[i].usSpreadSpectrumPercentage);
-					ss->type = ss_info->info_2.asSpreadSpectrum[i].ucSpreadSpectrumMode;
-					ss->rate = le16_to_cpu(ss_info->info_2.asSpreadSpectrum[i].usSpreadRateIn10Hz);
+						le16_to_cpu(ss_assign->v2.usSpreadSpectrumPercentage);
+					ss->type = ss_assign->v2.ucSpreadSpectrumMode;
+					ss->rate = le16_to_cpu(ss_assign->v2.usSpreadRateIn10Hz);
 					if ((crev == 2) &&
 					    ((id == ASIC_INTERNAL_ENGINE_SS) ||
 					     (id == ASIC_INTERNAL_MEMORY_SS)))
 						ss->rate /= 100;
 					return true;
 				}
+				ss_assign = (union asic_ss_assignment *)
+					((u8 *)ss_assign + sizeof(ATOM_ASIC_SS_ASSIGNMENT_V2));
 			}
 			break;
 		case 3:
 			num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) /
 				sizeof(ATOM_ASIC_SS_ASSIGNMENT_V3);
+			ss_assign = (union asic_ss_assignment *)((u8 *)&ss_info->info_3.asSpreadSpectrum[0]);
 			for (i = 0; i < num_indices; i++) {
-				if ((ss_info->info_3.asSpreadSpectrum[i].ucClockIndication == id) &&
-				    (clock <= le32_to_cpu(ss_info->info_3.asSpreadSpectrum[i].ulTargetClockRange))) {
+				if ((ss_assign->v3.ucClockIndication == id) &&
+				    (clock <= le32_to_cpu(ss_assign->v3.ulTargetClockRange))) {
 					ss->percentage =
-						le16_to_cpu(ss_info->info_3.asSpreadSpectrum[i].usSpreadSpectrumPercentage);
-					ss->type = ss_info->info_3.asSpreadSpectrum[i].ucSpreadSpectrumMode;
-					ss->rate = le16_to_cpu(ss_info->info_3.asSpreadSpectrum[i].usSpreadRateIn10Hz);
+						le16_to_cpu(ss_assign->v3.usSpreadSpectrumPercentage);
+					ss->type = ss_assign->v3.ucSpreadSpectrumMode;
+					ss->rate = le16_to_cpu(ss_assign->v3.usSpreadRateIn10Hz);
 					if ((id == ASIC_INTERNAL_ENGINE_SS) ||
 					    (id == ASIC_INTERNAL_MEMORY_SS))
 						ss->rate /= 100;
@@ -1555,6 +1573,8 @@ bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev,
 						radeon_atombios_get_igp_ss_overrides(rdev, ss, id);
 					return true;
 				}
+				ss_assign = (union asic_ss_assignment *)
+					((u8 *)ss_assign + sizeof(ATOM_ASIC_SS_ASSIGNMENT_V3));
 			}
 			break;
 		default:
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index ac6ece61a476..66c222836631 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -85,8 +85,9 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 		   VRAM, also but everything into VRAM on AGP cards to avoid
 		   image corruptions */
 		if (p->ring == R600_RING_TYPE_UVD_INDEX &&
-		    (i == 0 || p->rdev->flags & RADEON_IS_AGP)) {
-			/* TODO: is this still needed for NI+ ? */
+		    p->rdev->family < CHIP_PALM &&
+		    (i == 0 || drm_pci_device_is_agp(p->rdev->ddev))) {
+
 			p->relocs[i].lobj.domain =
 				RADEON_GEM_DOMAIN_VRAM;
 
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index e29faa73b574..841d0e09be3e 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1320,13 +1320,22 @@ int radeon_device_init(struct radeon_device *rdev,
 			return r;
 	}
 	if ((radeon_testing & 1)) {
-		radeon_test_moves(rdev);
+		if (rdev->accel_working)
+			radeon_test_moves(rdev);
+		else
+			DRM_INFO("radeon: acceleration disabled, skipping move tests\n");
 	}
 	if ((radeon_testing & 2)) {
-		radeon_test_syncing(rdev);
+		if (rdev->accel_working)
+			radeon_test_syncing(rdev);
+		else
+			DRM_INFO("radeon: acceleration disabled, skipping sync tests\n");
 	}
 	if (radeon_benchmarking) {
-		radeon_benchmark(rdev, radeon_benchmarking);
+		if (rdev->accel_working)
+			radeon_benchmark(rdev, radeon_benchmarking);
+		else
+			DRM_INFO("radeon: acceleration disabled, skipping benchmarks\n");
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 87e1d69e8fdb..ac07ad1d4f8c 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -1002,7 +1002,7 @@ static void radeon_pm_resume_old(struct radeon_device *rdev)
 {
 	/* set up the default clocks if the MC ucode is loaded */
 	if ((rdev->family >= CHIP_BARTS) &&
-	    (rdev->family <= CHIP_HAINAN) &&
+	    (rdev->family <= CHIP_CAYMAN) &&
 	    rdev->mc_fw) {
 		if (rdev->pm.default_vddc)
 			radeon_atom_set_voltage(rdev, rdev->pm.default_vddc,
@@ -1046,7 +1046,7 @@ static void radeon_pm_resume_dpm(struct radeon_device *rdev)
 	if (ret) {
 		DRM_ERROR("radeon: dpm resume failed\n");
 		if ((rdev->family >= CHIP_BARTS) &&
-		    (rdev->family <= CHIP_HAINAN) &&
+		    (rdev->family <= CHIP_CAYMAN) &&
 		    rdev->mc_fw) {
 			if (rdev->pm.default_vddc)
 				radeon_atom_set_voltage(rdev, rdev->pm.default_vddc,
@@ -1097,7 +1097,7 @@ static int radeon_pm_init_old(struct radeon_device *rdev)
 		radeon_pm_init_profile(rdev);
 		/* set up the default clocks if the MC ucode is loaded */
 		if ((rdev->family >= CHIP_BARTS) &&
-		    (rdev->family <= CHIP_HAINAN) &&
+		    (rdev->family <= CHIP_CAYMAN) &&
 		    rdev->mc_fw) {
 			if (rdev->pm.default_vddc)
 				radeon_atom_set_voltage(rdev, rdev->pm.default_vddc,
@@ -1183,7 +1183,7 @@ static int radeon_pm_init_dpm(struct radeon_device *rdev)
 	if (ret) {
 		rdev->pm.dpm_enabled = false;
 		if ((rdev->family >= CHIP_BARTS) &&
-		    (rdev->family <= CHIP_HAINAN) &&
+		    (rdev->family <= CHIP_CAYMAN) &&
 		    rdev->mc_fw) {
 			if (rdev->pm.default_vddc)
 				radeon_atom_set_voltage(rdev, rdev->pm.default_vddc,
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 46a25f037b84..18254e1c3e71 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -839,9 +839,11 @@ static int radeon_debugfs_ring_info(struct seq_file *m, void *data)
 	 * packet that is the root issue
 	 */
 	i = (ring->rptr + ring->ptr_mask + 1 - 32) & ring->ptr_mask;
-	for (j = 0; j <= (count + 32); j++) {
-		seq_printf(m, "r[%5d]=0x%08x\n", i, ring->ring[i]);
-		i = (i + 1) & ring->ptr_mask;
+	if (ring->ready) {
+		for (j = 0; j <= (count + 32); j++) {
+			seq_printf(m, "r[%5d]=0x%08x\n", i, ring->ring[i]);
+			i = (i + 1) & ring->ptr_mask;
+		}
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 1a01bbff9bfa..a0f11856ddde 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -476,8 +476,7 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p,
 		return -EINVAL;
 	}
 
-	/* TODO: is this still necessary on NI+ ? */
-	if ((cmd == 0 || cmd == 0x3) &&
+	if (p->rdev->family < CHIP_PALM && (cmd == 0 || cmd == 0x3) &&
 	    (start >> 28) != (p->rdev->uvd.gpu_addr >> 28)) {
 		DRM_ERROR("msg/fb buffer %LX-%LX out of 256MB segment!\n",
 			  start, end);
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index cfe5d4d28915..9ace28702c76 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2910,6 +2910,7 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 	bool disable_sclk_switching = false;
 	u32 mclk, sclk;
 	u16 vddc, vddci;
+	u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc;
 	int i;
 
 	if ((rdev->pm.dpm.new_active_crtc_count > 1) ||
@@ -2943,6 +2944,29 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 		}
 	}
 
+	/* limit clocks to max supported clocks based on voltage dependency tables */
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk,
+							&max_sclk_vddc);
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk,
+							&max_mclk_vddci);
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk,
+							&max_mclk_vddc);
+
+	for (i = 0; i < ps->performance_level_count; i++) {
+		if (max_sclk_vddc) {
+			if (ps->performance_levels[i].sclk > max_sclk_vddc)
+				ps->performance_levels[i].sclk = max_sclk_vddc;
+		}
+		if (max_mclk_vddci) {
+			if (ps->performance_levels[i].mclk > max_mclk_vddci)
+				ps->performance_levels[i].mclk = max_mclk_vddci;
+		}
+		if (max_mclk_vddc) {
+			if (ps->performance_levels[i].mclk > max_mclk_vddc)
+				ps->performance_levels[i].mclk = max_mclk_vddc;
+		}
+	}
+
 	/* XXX validate the min clocks required for display */
 
 	if (disable_mclk_switching) {
diff --git a/drivers/gpu/drm/radeon/uvd_v1_0.c b/drivers/gpu/drm/radeon/uvd_v1_0.c
index 7266805d9786..3100fa9cb52f 100644
--- a/drivers/gpu/drm/radeon/uvd_v1_0.c
+++ b/drivers/gpu/drm/radeon/uvd_v1_0.c
@@ -212,8 +212,8 @@ int uvd_v1_0_start(struct radeon_device *rdev)
 	/* enable VCPU clock */
 	WREG32(UVD_VCPU_CNTL,  1 << 9);
 
-	/* enable UMC */
-	WREG32_P(UVD_LMI_CTRL2, 0, ~(1 << 8));
+	/* enable UMC and NC0 */
+	WREG32_P(UVD_LMI_CTRL2, 1 << 13, ~((1 << 8) | (1 << 13)));
 
 	/* boot up the VCPU */
 	WREG32(UVD_SOFT_RESET, 0);
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 4faea979975e..af6edf9b1936 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -194,7 +194,7 @@ int vmbus_connect(void)
 
 	do {
 		ret = vmbus_negotiate_version(msginfo, version);
-		if (ret)
+		if (ret == -ETIMEDOUT)
 			goto cleanup;
 
 		if (vmbus_connection.conn_state == CONNECTED)
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c
index 28b03325b872..09988b289622 100644
--- a/drivers/hv/hv_kvp.c
+++ b/drivers/hv/hv_kvp.c
@@ -32,13 +32,17 @@
 /*
  * Pre win8 version numbers used in ws2008 and ws 2008 r2 (win7)
  */
+#define WS2008_SRV_MAJOR	1
+#define WS2008_SRV_MINOR	0
+#define WS2008_SRV_VERSION     (WS2008_SRV_MAJOR << 16 | WS2008_SRV_MINOR)
+
 #define WIN7_SRV_MAJOR   3
 #define WIN7_SRV_MINOR   0
-#define WIN7_SRV_MAJOR_MINOR     (WIN7_SRV_MAJOR << 16 | WIN7_SRV_MINOR)
+#define WIN7_SRV_VERSION     (WIN7_SRV_MAJOR << 16 | WIN7_SRV_MINOR)
 
 #define WIN8_SRV_MAJOR   4
 #define WIN8_SRV_MINOR   0
-#define WIN8_SRV_MAJOR_MINOR     (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR)
+#define WIN8_SRV_VERSION     (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR)
 
 /*
  * Global state maintained for transaction that is being processed.
@@ -587,6 +591,8 @@ void hv_kvp_onchannelcallback(void *context)
 
 	struct icmsg_hdr *icmsghdrp;
 	struct icmsg_negotiate *negop = NULL;
+	int util_fw_version;
+	int kvp_srv_version;
 
 	if (kvp_transaction.active) {
 		/*
@@ -606,17 +612,26 @@ void hv_kvp_onchannelcallback(void *context)
 
 		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
 			/*
-			 * We start with win8 version and if the host cannot
-			 * support that we use the previous version.
+			 * Based on the host, select appropriate
+			 * framework and service versions we will
+			 * negotiate.
 			 */
-			if (vmbus_prep_negotiate_resp(icmsghdrp, negop,
-				 recv_buffer, UTIL_FW_MAJOR_MINOR,
-				 WIN8_SRV_MAJOR_MINOR))
-				goto done;
-
+			switch (vmbus_proto_version) {
+			case (VERSION_WS2008):
+				util_fw_version = UTIL_WS2K8_FW_VERSION;
+				kvp_srv_version = WS2008_SRV_VERSION;
+				break;
+			case (VERSION_WIN7):
+				util_fw_version = UTIL_FW_VERSION;
+				kvp_srv_version = WIN7_SRV_VERSION;
+				break;
+			default:
+				util_fw_version = UTIL_FW_VERSION;
+				kvp_srv_version = WIN8_SRV_VERSION;
+			}
 			vmbus_prep_negotiate_resp(icmsghdrp, negop,
-				 recv_buffer, UTIL_FW_MAJOR_MINOR,
-				 WIN7_SRV_MAJOR_MINOR);
+				 recv_buffer, util_fw_version,
+				 kvp_srv_version);
 
 		} else {
 			kvp_msg = (struct hv_kvp_msg *)&recv_buffer[
@@ -649,7 +664,6 @@ void hv_kvp_onchannelcallback(void *context)
 			return;
 
 		}
-done:
 
 		icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION
 			| ICMSGHDRFLAG_RESPONSE;
diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c
index e4572f3f2834..0c3546224376 100644
--- a/drivers/hv/hv_snapshot.c
+++ b/drivers/hv/hv_snapshot.c
@@ -26,7 +26,7 @@
 
 #define VSS_MAJOR  5
 #define VSS_MINOR  0
-#define VSS_MAJOR_MINOR    (VSS_MAJOR << 16 | VSS_MINOR)
+#define VSS_VERSION    (VSS_MAJOR << 16 | VSS_MINOR)
 
 
 
@@ -190,8 +190,8 @@ void hv_vss_onchannelcallback(void *context)
 
 		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
 			vmbus_prep_negotiate_resp(icmsghdrp, negop,
-				 recv_buffer, UTIL_FW_MAJOR_MINOR,
-				 VSS_MAJOR_MINOR);
+				 recv_buffer, UTIL_FW_VERSION,
+				 VSS_VERSION);
 		} else {
 			vss_msg = (struct hv_vss_msg *)&recv_buffer[
 				sizeof(struct vmbuspipe_hdr) +
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 9113850edb43..62dfd246b948 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -28,17 +28,32 @@
 #include <linux/reboot.h>
 #include <linux/hyperv.h>
 
-#define SHUTDOWN_MAJOR	3
-#define SHUTDOWN_MINOR  0
-#define SHUTDOWN_MAJOR_MINOR	(SHUTDOWN_MAJOR << 16 | SHUTDOWN_MINOR)
 
-#define TIMESYNCH_MAJOR	3
-#define TIMESYNCH_MINOR 0
-#define TIMESYNCH_MAJOR_MINOR	(TIMESYNCH_MAJOR << 16 | TIMESYNCH_MINOR)
+#define SD_MAJOR	3
+#define SD_MINOR	0
+#define SD_VERSION	(SD_MAJOR << 16 | SD_MINOR)
 
-#define HEARTBEAT_MAJOR	3
-#define HEARTBEAT_MINOR 0
-#define HEARTBEAT_MAJOR_MINOR	(HEARTBEAT_MAJOR << 16 | HEARTBEAT_MINOR)
+#define SD_WS2008_MAJOR		1
+#define SD_WS2008_VERSION	(SD_WS2008_MAJOR << 16 | SD_MINOR)
+
+#define TS_MAJOR	3
+#define TS_MINOR	0
+#define TS_VERSION	(TS_MAJOR << 16 | TS_MINOR)
+
+#define TS_WS2008_MAJOR		1
+#define TS_WS2008_VERSION	(TS_WS2008_MAJOR << 16 | TS_MINOR)
+
+#define HB_MAJOR	3
+#define HB_MINOR 0
+#define HB_VERSION	(HB_MAJOR << 16 | HB_MINOR)
+
+#define HB_WS2008_MAJOR	1
+#define HB_WS2008_VERSION	(HB_WS2008_MAJOR << 16 | HB_MINOR)
+
+static int sd_srv_version;
+static int ts_srv_version;
+static int hb_srv_version;
+static int util_fw_version;
 
 static void shutdown_onchannelcallback(void *context);
 static struct hv_util_service util_shutdown = {
@@ -99,8 +114,8 @@ static void shutdown_onchannelcallback(void *context)
 
 		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
 			vmbus_prep_negotiate_resp(icmsghdrp, negop,
-					shut_txf_buf, UTIL_FW_MAJOR_MINOR,
-					SHUTDOWN_MAJOR_MINOR);
+					shut_txf_buf, util_fw_version,
+					sd_srv_version);
 		} else {
 			shutdown_msg =
 				(struct shutdown_msg_data *)&shut_txf_buf[
@@ -216,6 +231,7 @@ static void timesync_onchannelcallback(void *context)
 	struct icmsg_hdr *icmsghdrp;
 	struct ictimesync_data *timedatap;
 	u8 *time_txf_buf = util_timesynch.recv_buffer;
+	struct icmsg_negotiate *negop = NULL;
 
 	vmbus_recvpacket(channel, time_txf_buf,
 			 PAGE_SIZE, &recvlen, &requestid);
@@ -225,9 +241,10 @@ static void timesync_onchannelcallback(void *context)
 				sizeof(struct vmbuspipe_hdr)];
 
 		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
-			vmbus_prep_negotiate_resp(icmsghdrp, NULL, time_txf_buf,
-						UTIL_FW_MAJOR_MINOR,
-						TIMESYNCH_MAJOR_MINOR);
+			vmbus_prep_negotiate_resp(icmsghdrp, negop,
+						time_txf_buf,
+						util_fw_version,
+						ts_srv_version);
 		} else {
 			timedatap = (struct ictimesync_data *)&time_txf_buf[
 				sizeof(struct vmbuspipe_hdr) +
@@ -257,6 +274,7 @@ static void heartbeat_onchannelcallback(void *context)
 	struct icmsg_hdr *icmsghdrp;
 	struct heartbeat_msg_data *heartbeat_msg;
 	u8 *hbeat_txf_buf = util_heartbeat.recv_buffer;
+	struct icmsg_negotiate *negop = NULL;
 
 	vmbus_recvpacket(channel, hbeat_txf_buf,
 			 PAGE_SIZE, &recvlen, &requestid);
@@ -266,9 +284,9 @@ static void heartbeat_onchannelcallback(void *context)
 				sizeof(struct vmbuspipe_hdr)];
 
 		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
-			vmbus_prep_negotiate_resp(icmsghdrp, NULL,
-				hbeat_txf_buf, UTIL_FW_MAJOR_MINOR,
-				HEARTBEAT_MAJOR_MINOR);
+			vmbus_prep_negotiate_resp(icmsghdrp, negop,
+				hbeat_txf_buf, util_fw_version,
+				hb_srv_version);
 		} else {
 			heartbeat_msg =
 				(struct heartbeat_msg_data *)&hbeat_txf_buf[
@@ -321,6 +339,25 @@ static int util_probe(struct hv_device *dev,
 		goto error;
 
 	hv_set_drvdata(dev, srv);
+	/*
+	 * Based on the host; initialize the framework and
+	 * service version numbers we will negotiate.
+	 */
+	switch (vmbus_proto_version) {
+	case (VERSION_WS2008):
+		util_fw_version = UTIL_WS2K8_FW_VERSION;
+		sd_srv_version = SD_WS2008_VERSION;
+		ts_srv_version = TS_WS2008_VERSION;
+		hb_srv_version = HB_WS2008_VERSION;
+		break;
+
+	default:
+		util_fw_version = UTIL_FW_VERSION;
+		sd_srv_version = SD_VERSION;
+		ts_srv_version = TS_VERSION;
+		hb_srv_version = HB_VERSION;
+	}
+
 	return 0;
 
 error:
diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c
index 62c2e32e25ef..98814d12a604 100644
--- a/drivers/hwmon/applesmc.c
+++ b/drivers/hwmon/applesmc.c
@@ -525,16 +525,25 @@ static int applesmc_init_smcreg_try(void)
 {
 	struct applesmc_registers *s = &smcreg;
 	bool left_light_sensor, right_light_sensor;
+	unsigned int count;
 	u8 tmp[1];
 	int ret;
 
 	if (s->init_complete)
 		return 0;
 
-	ret = read_register_count(&s->key_count);
+	ret = read_register_count(&count);
 	if (ret)
 		return ret;
 
+	if (s->cache && s->key_count != count) {
+		pr_warn("key count changed from %d to %d\n",
+			s->key_count, count);
+		kfree(s->cache);
+		s->cache = NULL;
+	}
+	s->key_count = count;
+
 	if (!s->cache)
 		s->cache = kcalloc(s->key_count, sizeof(*s->cache), GFP_KERNEL);
 	if (!s->cache)
diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c
index dbecf08399f8..5888feef1ac5 100644
--- a/drivers/i2c/busses/i2c-designware-core.c
+++ b/drivers/i2c/busses/i2c-designware-core.c
@@ -98,6 +98,8 @@
 
 #define DW_IC_ERR_TX_ABRT	0x1
 
+#define DW_IC_TAR_10BITADDR_MASTER BIT(12)
+
 /*
  * status codes
  */
@@ -388,22 +390,34 @@ static int i2c_dw_wait_bus_not_busy(struct dw_i2c_dev *dev)
 static void i2c_dw_xfer_init(struct dw_i2c_dev *dev)
 {
 	struct i2c_msg *msgs = dev->msgs;
-	u32 ic_con;
+	u32 ic_con, ic_tar = 0;
 
 	/* Disable the adapter */
 	__i2c_dw_enable(dev, false);
 
-	/* set the slave (target) address */
-	dw_writel(dev, msgs[dev->msg_write_idx].addr, DW_IC_TAR);
-
 	/* if the slave address is ten bit address, enable 10BITADDR */
 	ic_con = dw_readl(dev, DW_IC_CON);
-	if (msgs[dev->msg_write_idx].flags & I2C_M_TEN)
+	if (msgs[dev->msg_write_idx].flags & I2C_M_TEN) {
 		ic_con |= DW_IC_CON_10BITADDR_MASTER;
-	else
+		/*
+		 * If I2C_DYNAMIC_TAR_UPDATE is set, the 10-bit addressing
+		 * mode has to be enabled via bit 12 of IC_TAR register.
+		 * We set it always as I2C_DYNAMIC_TAR_UPDATE can't be
+		 * detected from registers.
+		 */
+		ic_tar = DW_IC_TAR_10BITADDR_MASTER;
+	} else {
 		ic_con &= ~DW_IC_CON_10BITADDR_MASTER;
+	}
+
 	dw_writel(dev, ic_con, DW_IC_CON);
 
+	/*
+	 * Set the slave (target) address and enable 10-bit addressing mode
+	 * if applicable.
+	 */
+	dw_writel(dev, msgs[dev->msg_write_idx].addr | ic_tar, DW_IC_TAR);
+
 	/* Enable the adapter */
 	__i2c_dw_enable(dev, true);
 
diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c
index 8ed79a086f85..1672effbcebb 100644
--- a/drivers/i2c/busses/i2c-ismt.c
+++ b/drivers/i2c/busses/i2c-ismt.c
@@ -393,6 +393,9 @@ static int ismt_access(struct i2c_adapter *adap, u16 addr,
 
 	desc = &priv->hw[priv->head];
 
+	/* Initialize the DMA buffer */
+	memset(priv->dma_buffer, 0, sizeof(priv->dma_buffer));
+
 	/* Initialize the descriptor */
 	memset(desc, 0, sizeof(struct ismt_desc));
 	desc->tgtaddr_rw = ISMT_DESC_ADDR_RW(addr, read_write);
diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c
index 7f3a47443494..d3e9cc3153a9 100644
--- a/drivers/i2c/busses/i2c-mv64xxx.c
+++ b/drivers/i2c/busses/i2c-mv64xxx.c
@@ -234,9 +234,9 @@ static int mv64xxx_i2c_offload_msg(struct mv64xxx_i2c_data *drv_data)
 		ctrl_reg |= MV64XXX_I2C_BRIDGE_CONTROL_WR |
 		    (msg->len - 1) << MV64XXX_I2C_BRIDGE_CONTROL_TX_SIZE_SHIFT;
 
-		writel_relaxed(data_reg_lo,
+		writel(data_reg_lo,
 			drv_data->reg_base + MV64XXX_I2C_REG_TX_DATA_LO);
-		writel_relaxed(data_reg_hi,
+		writel(data_reg_hi,
 			drv_data->reg_base + MV64XXX_I2C_REG_TX_DATA_HI);
 
 	} else {
@@ -697,6 +697,7 @@ static const struct of_device_id mv64xxx_i2c_of_match_table[] = {
 MODULE_DEVICE_TABLE(of, mv64xxx_i2c_of_match_table);
 
 #ifdef CONFIG_OF
+#ifdef CONFIG_HAVE_CLK
 static int
 mv64xxx_calc_freq(const int tclk, const int n, const int m)
 {
@@ -726,16 +727,12 @@ mv64xxx_find_baud_factors(const u32 req_freq, const u32 tclk, u32 *best_n,
 		return false;
 	return true;
 }
+#endif /* CONFIG_HAVE_CLK */
 
 static int
 mv64xxx_of_config(struct mv64xxx_i2c_data *drv_data,
 		  struct device *dev)
 {
-	const struct of_device_id *device;
-	struct device_node *np = dev->of_node;
-	u32 bus_freq, tclk;
-	int rc = 0;
-
 	/* CLK is mandatory when using DT to describe the i2c bus. We
 	 * need to know tclk in order to calculate bus clock
 	 * factors.
@@ -744,6 +741,11 @@ mv64xxx_of_config(struct mv64xxx_i2c_data *drv_data,
 	/* Have OF but no CLK */
 	return -ENODEV;
 #else
+	const struct of_device_id *device;
+	struct device_node *np = dev->of_node;
+	u32 bus_freq, tclk;
+	int rc = 0;
+
 	if (IS_ERR(drv_data->clk)) {
 		rc = -ENODEV;
 		goto out;
diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c
index 3535f3c0f7b4..3747b9bf67d6 100644
--- a/drivers/i2c/busses/i2c-s3c2410.c
+++ b/drivers/i2c/busses/i2c-s3c2410.c
@@ -1178,8 +1178,6 @@ static int s3c24xx_i2c_remove(struct platform_device *pdev)
 
 	i2c_del_adapter(&i2c->adap);
 
-	clk_disable_unprepare(i2c->clk);
-
 	if (pdev->dev.of_node && IS_ERR(i2c->pctrl))
 		s3c24xx_i2c_dt_gpio_free(i2c);
 
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index b39f6f0b45f2..0f12382aa35d 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -498,7 +498,7 @@ struct cached_dev {
 	 */
 	atomic_t		has_dirty;
 
-	struct ratelimit	writeback_rate;
+	struct bch_ratelimit	writeback_rate;
 	struct delayed_work	writeback_rate_update;
 
 	/*
@@ -507,10 +507,9 @@ struct cached_dev {
 	 */
 	sector_t		last_read;
 
-	/* Number of writeback bios in flight */
-	atomic_t		in_flight;
+	/* Limit number of writeback bios in flight */
+	struct semaphore	in_flight;
 	struct closure_with_timer writeback;
-	struct closure_waitlist	writeback_wait;
 
 	struct keybuf		writeback_keys;
 
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 8010eed06a51..22d1ae72c282 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -926,28 +926,45 @@ struct bkey *bch_next_recurse_key(struct btree *b, struct bkey *search)
 
 /* Mergesort */
 
+static void sort_key_next(struct btree_iter *iter,
+			  struct btree_iter_set *i)
+{
+	i->k = bkey_next(i->k);
+
+	if (i->k == i->end)
+		*i = iter->data[--iter->used];
+}
+
 static void btree_sort_fixup(struct btree_iter *iter)
 {
 	while (iter->used > 1) {
 		struct btree_iter_set *top = iter->data, *i = top + 1;
-		struct bkey *k;
 
 		if (iter->used > 2 &&
 		    btree_iter_cmp(i[0], i[1]))
 			i++;
 
-		for (k = i->k;
-		     k != i->end && bkey_cmp(top->k, &START_KEY(k)) > 0;
-		     k = bkey_next(k))
-			if (top->k > i->k)
-				__bch_cut_front(top->k, k);
-			else if (KEY_SIZE(k))
-				bch_cut_back(&START_KEY(k), top->k);
-
-		if (top->k < i->k || k == i->k)
+		if (bkey_cmp(top->k, &START_KEY(i->k)) <= 0)
 			break;
 
-		heap_sift(iter, i - top, btree_iter_cmp);
+		if (!KEY_SIZE(i->k)) {
+			sort_key_next(iter, i);
+			heap_sift(iter, i - top, btree_iter_cmp);
+			continue;
+		}
+
+		if (top->k > i->k) {
+			if (bkey_cmp(top->k, i->k) >= 0)
+				sort_key_next(iter, i);
+			else
+				bch_cut_front(top->k, i->k);
+
+			heap_sift(iter, i - top, btree_iter_cmp);
+		} else {
+			/* can't happen because of comparison func */
+			BUG_ON(!bkey_cmp(&START_KEY(top->k), &START_KEY(i->k)));
+			bch_cut_back(&START_KEY(i->k), top->k);
+		}
 	}
 }
 
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index f9764e61978b..f42fc7ed9cd6 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -255,7 +255,7 @@ void bch_btree_node_read(struct btree *b)
 
 	return;
 err:
-	bch_cache_set_error(b->c, "io error reading bucket %lu",
+	bch_cache_set_error(b->c, "io error reading bucket %zu",
 			    PTR_BUCKET_NR(b->c, &b->key, 0));
 }
 
@@ -612,7 +612,7 @@ static unsigned long bch_mca_scan(struct shrinker *shrink,
 		return SHRINK_STOP;
 
 	/* Return -1 if we can't do anything right now */
-	if (sc->gfp_mask & __GFP_WAIT)
+	if (sc->gfp_mask & __GFP_IO)
 		mutex_lock(&c->bucket_lock);
 	else if (!mutex_trylock(&c->bucket_lock))
 		return -1;
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index ba95ab84b2be..8435f81e5d85 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -153,7 +153,8 @@ int bch_journal_read(struct cache_set *c, struct list_head *list,
 		bitmap_zero(bitmap, SB_JOURNAL_BUCKETS);
 		pr_debug("%u journal buckets", ca->sb.njournal_buckets);
 
-		/* Read journal buckets ordered by golden ratio hash to quickly
+		/*
+		 * Read journal buckets ordered by golden ratio hash to quickly
 		 * find a sequence of buckets with valid journal entries
 		 */
 		for (i = 0; i < ca->sb.njournal_buckets; i++) {
@@ -166,18 +167,20 @@ int bch_journal_read(struct cache_set *c, struct list_head *list,
 				goto bsearch;
 		}
 
-		/* If that fails, check all the buckets we haven't checked
+		/*
+		 * If that fails, check all the buckets we haven't checked
 		 * already
 		 */
 		pr_debug("falling back to linear search");
 
-		for (l = 0; l < ca->sb.njournal_buckets; l++) {
-			if (test_bit(l, bitmap))
-				continue;
-
+		for (l = find_first_zero_bit(bitmap, ca->sb.njournal_buckets);
+		     l < ca->sb.njournal_buckets;
+		     l = find_next_zero_bit(bitmap, ca->sb.njournal_buckets, l + 1))
 			if (read_bucket(l))
 				goto bsearch;
-		}
+
+		if (list_empty(list))
+			continue;
 bsearch:
 		/* Binary search */
 		m = r = find_next_bit(bitmap, ca->sb.njournal_buckets, l + 1);
@@ -197,10 +200,12 @@ bsearch:
 				r = m;
 		}
 
-		/* Read buckets in reverse order until we stop finding more
+		/*
+		 * Read buckets in reverse order until we stop finding more
 		 * journal entries
 		 */
-		pr_debug("finishing up");
+		pr_debug("finishing up: m %u njournal_buckets %u",
+			 m, ca->sb.njournal_buckets);
 		l = m;
 
 		while (1) {
@@ -228,9 +233,10 @@ bsearch:
 			}
 	}
 
-	c->journal.seq = list_entry(list->prev,
-				    struct journal_replay,
-				    list)->j.seq;
+	if (!list_empty(list))
+		c->journal.seq = list_entry(list->prev,
+					    struct journal_replay,
+					    list)->j.seq;
 
 	return 0;
 #undef read_bucket
@@ -428,7 +434,7 @@ static void do_journal_discard(struct cache *ca)
 		return;
 	}
 
-	switch (atomic_read(&ja->discard_in_flight) == DISCARD_IN_FLIGHT) {
+	switch (atomic_read(&ja->discard_in_flight)) {
 	case DISCARD_IN_FLIGHT:
 		return;
 
@@ -689,6 +695,7 @@ void bch_journal_meta(struct cache_set *c, struct closure *cl)
 		if (cl)
 			BUG_ON(!closure_wait(&w->wait, cl));
 
+		closure_flush(&c->journal.io);
 		__journal_try_write(c, true);
 	}
 }
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 786a1a4f74d8..71eb233b9ace 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -997,14 +997,17 @@ static void request_write(struct cached_dev *dc, struct search *s)
 	} else {
 		bch_writeback_add(dc);
 
-		if (s->op.flush_journal) {
+		if (bio->bi_rw & REQ_FLUSH) {
 			/* Also need to send a flush to the backing device */
-			s->op.cache_bio = bio_clone_bioset(bio, GFP_NOIO,
-							   dc->disk.bio_split);
+			struct bio *flush = bio_alloc_bioset(0, GFP_NOIO,
+							     dc->disk.bio_split);
 
-			bio->bi_size = 0;
-			bio->bi_vcnt = 0;
-			closure_bio_submit(bio, cl, s->d);
+			flush->bi_rw	= WRITE_FLUSH;
+			flush->bi_bdev	= bio->bi_bdev;
+			flush->bi_end_io = request_endio;
+			flush->bi_private = cl;
+
+			closure_bio_submit(flush, cl, s->d);
 		} else {
 			s->op.cache_bio = bio;
 		}
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 4fe6ab2fbe2e..924dcfdae111 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -223,8 +223,13 @@ STORE(__cached_dev)
 	}
 
 	if (attr == &sysfs_label) {
-		/* note: endlines are preserved */
-		memcpy(dc->sb.label, buf, SB_LABEL_SIZE);
+		if (size > SB_LABEL_SIZE)
+			return -EINVAL;
+		memcpy(dc->sb.label, buf, size);
+		if (size < SB_LABEL_SIZE)
+			dc->sb.label[size] = '\0';
+		if (size && dc->sb.label[size - 1] == '\n')
+			dc->sb.label[size - 1] = '\0';
 		bch_write_bdev_super(dc, NULL);
 		if (dc->disk.c) {
 			memcpy(dc->disk.c->uuids[dc->disk.id].label,
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index 98eb81159a22..420dad545c7d 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -190,7 +190,16 @@ void bch_time_stats_update(struct time_stats *stats, uint64_t start_time)
 	stats->last = now ?: 1;
 }
 
-unsigned bch_next_delay(struct ratelimit *d, uint64_t done)
+/**
+ * bch_next_delay() - increment @d by the amount of work done, and return how
+ * long to delay until the next time to do some work.
+ *
+ * @d - the struct bch_ratelimit to update
+ * @done - the amount of work done, in arbitrary units
+ *
+ * Returns the amount of time to delay by, in jiffies
+ */
+uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done)
 {
 	uint64_t now = local_clock();
 
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index 1ae2a73ad85f..ea345c6896f4 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -450,17 +450,23 @@ read_attribute(name ## _last_ ## frequency_units)
 	(ewma) >> factor;						\
 })
 
-struct ratelimit {
+struct bch_ratelimit {
+	/* Next time we want to do some work, in nanoseconds */
 	uint64_t		next;
+
+	/*
+	 * Rate at which we want to do work, in units per nanosecond
+	 * The units here correspond to the units passed to bch_next_delay()
+	 */
 	unsigned		rate;
 };
 
-static inline void ratelimit_reset(struct ratelimit *d)
+static inline void bch_ratelimit_reset(struct bch_ratelimit *d)
 {
 	d->next = local_clock();
 }
 
-unsigned bch_next_delay(struct ratelimit *d, uint64_t done);
+uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done);
 
 #define __DIV_SAFE(n, d, zero)						\
 ({									\
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 22cbff551628..ba3ee48320f2 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -94,11 +94,15 @@ static void update_writeback_rate(struct work_struct *work)
 
 static unsigned writeback_delay(struct cached_dev *dc, unsigned sectors)
 {
+	uint64_t ret;
+
 	if (atomic_read(&dc->disk.detaching) ||
 	    !dc->writeback_percent)
 		return 0;
 
-	return bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL);
+	ret = bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL);
+
+	return min_t(uint64_t, ret, HZ);
 }
 
 /* Background writeback */
@@ -208,7 +212,7 @@ normal_refill:
 
 	up_write(&dc->writeback_lock);
 
-	ratelimit_reset(&dc->writeback_rate);
+	bch_ratelimit_reset(&dc->writeback_rate);
 
 	/* Punt to workqueue only so we don't recurse and blow the stack */
 	continue_at(cl, read_dirty, dirty_wq);
@@ -318,9 +322,7 @@ static void write_dirty_finish(struct closure *cl)
 	}
 
 	bch_keybuf_del(&dc->writeback_keys, w);
-	atomic_dec_bug(&dc->in_flight);
-
-	closure_wake_up(&dc->writeback_wait);
+	up(&dc->in_flight);
 
 	closure_return_with_destructor(cl, dirty_io_destructor);
 }
@@ -349,7 +351,7 @@ static void write_dirty(struct closure *cl)
 
 	closure_bio_submit(&io->bio, cl, &io->dc->disk);
 
-	continue_at(cl, write_dirty_finish, dirty_wq);
+	continue_at(cl, write_dirty_finish, system_wq);
 }
 
 static void read_dirty_endio(struct bio *bio, int error)
@@ -369,7 +371,7 @@ static void read_dirty_submit(struct closure *cl)
 
 	closure_bio_submit(&io->bio, cl, &io->dc->disk);
 
-	continue_at(cl, write_dirty, dirty_wq);
+	continue_at(cl, write_dirty, system_wq);
 }
 
 static void read_dirty(struct closure *cl)
@@ -394,12 +396,8 @@ static void read_dirty(struct closure *cl)
 
 		if (delay > 0 &&
 		    (KEY_START(&w->key) != dc->last_read ||
-		     jiffies_to_msecs(delay) > 50)) {
-			w->private = NULL;
-
-			closure_delay(&dc->writeback, delay);
-			continue_at(cl, read_dirty, dirty_wq);
-		}
+		     jiffies_to_msecs(delay) > 50))
+			delay = schedule_timeout_uninterruptible(delay);
 
 		dc->last_read	= KEY_OFFSET(&w->key);
 
@@ -424,15 +422,10 @@ static void read_dirty(struct closure *cl)
 
 		trace_bcache_writeback(&w->key);
 
-		closure_call(&io->cl, read_dirty_submit, NULL, &dc->disk.cl);
+		down(&dc->in_flight);
+		closure_call(&io->cl, read_dirty_submit, NULL, cl);
 
 		delay = writeback_delay(dc, KEY_SIZE(&w->key));
-
-		atomic_inc(&dc->in_flight);
-
-		if (!closure_wait_event(&dc->writeback_wait, cl,
-					atomic_read(&dc->in_flight) < 64))
-			continue_at(cl, read_dirty, dirty_wq);
 	}
 
 	if (0) {
@@ -442,7 +435,11 @@ err:
 		bch_keybuf_del(&dc->writeback_keys, w);
 	}
 
-	refill_dirty(cl);
+	/*
+	 * Wait for outstanding writeback IOs to finish (and keybuf slots to be
+	 * freed) before refilling again
+	 */
+	continue_at(cl, refill_dirty, dirty_wq);
 }
 
 /* Init */
@@ -484,6 +481,7 @@ void bch_sectors_dirty_init(struct cached_dev *dc)
 
 void bch_cached_dev_writeback_init(struct cached_dev *dc)
 {
+	sema_init(&dc->in_flight, 64);
 	closure_init_unlocked(&dc->writeback);
 	init_rwsem(&dc->writeback_lock);
 
@@ -513,7 +511,7 @@ void bch_writeback_exit(void)
 
 int __init bch_writeback_init(void)
 {
-	dirty_wq = create_singlethread_workqueue("bcache_writeback");
+	dirty_wq = create_workqueue("bcache_writeback");
 	if (!dirty_wq)
 		return -ENOMEM;
 
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index ea49834377c8..2a20986a2fec 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -19,8 +19,6 @@
 #define DM_MSG_PREFIX "io"
 
 #define DM_IO_MAX_REGIONS	BITS_PER_LONG
-#define MIN_IOS		16
-#define MIN_BIOS	16
 
 struct dm_io_client {
 	mempool_t *pool;
@@ -50,16 +48,17 @@ static struct kmem_cache *_dm_io_cache;
 struct dm_io_client *dm_io_client_create(void)
 {
 	struct dm_io_client *client;
+	unsigned min_ios = dm_get_reserved_bio_based_ios();
 
 	client = kmalloc(sizeof(*client), GFP_KERNEL);
 	if (!client)
 		return ERR_PTR(-ENOMEM);
 
-	client->pool = mempool_create_slab_pool(MIN_IOS, _dm_io_cache);
+	client->pool = mempool_create_slab_pool(min_ios, _dm_io_cache);
 	if (!client->pool)
 		goto bad;
 
-	client->bios = bioset_create(MIN_BIOS, 0);
+	client->bios = bioset_create(min_ios, 0);
 	if (!client->bios)
 		goto bad;
 
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index b759a127f9c3..de570a558764 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -7,6 +7,7 @@
 
 #include <linux/device-mapper.h>
 
+#include "dm.h"
 #include "dm-path-selector.h"
 #include "dm-uevent.h"
 
@@ -116,8 +117,6 @@ struct dm_mpath_io {
 
 typedef int (*action_fn) (struct pgpath *pgpath);
 
-#define MIN_IOS 256	/* Mempool size */
-
 static struct kmem_cache *_mpio_cache;
 
 static struct workqueue_struct *kmultipathd, *kmpath_handlerd;
@@ -190,6 +189,7 @@ static void free_priority_group(struct priority_group *pg,
 static struct multipath *alloc_multipath(struct dm_target *ti)
 {
 	struct multipath *m;
+	unsigned min_ios = dm_get_reserved_rq_based_ios();
 
 	m = kzalloc(sizeof(*m), GFP_KERNEL);
 	if (m) {
@@ -202,7 +202,7 @@ static struct multipath *alloc_multipath(struct dm_target *ti)
 		INIT_WORK(&m->trigger_event, trigger_event);
 		init_waitqueue_head(&m->pg_init_wait);
 		mutex_init(&m->work_mutex);
-		m->mpio_pool = mempool_create_slab_pool(MIN_IOS, _mpio_cache);
+		m->mpio_pool = mempool_create_slab_pool(min_ios, _mpio_cache);
 		if (!m->mpio_pool) {
 			kfree(m);
 			return NULL;
@@ -1268,6 +1268,7 @@ static int noretry_error(int error)
 	case -EREMOTEIO:
 	case -EILSEQ:
 	case -ENODATA:
+	case -ENOSPC:
 		return 1;
 	}
 
@@ -1298,8 +1299,17 @@ static int do_end_io(struct multipath *m, struct request *clone,
 	if (!error && !clone->errors)
 		return 0;	/* I/O complete */
 
-	if (noretry_error(error))
+	if (noretry_error(error)) {
+		if ((clone->cmd_flags & REQ_WRITE_SAME) &&
+		    !clone->q->limits.max_write_same_sectors) {
+			struct queue_limits *limits;
+
+			/* device doesn't really support WRITE SAME, disable it */
+			limits = dm_get_queue_limits(dm_table_get_md(m->ti->table));
+			limits->max_write_same_sectors = 0;
+		}
 		return error;
+	}
 
 	if (mpio->pgpath)
 		fail_path(mpio->pgpath);
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 3ac415675b6c..4caa8e6d59d7 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -256,7 +256,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw,
 	 */
 	INIT_WORK_ONSTACK(&req.work, do_metadata);
 	queue_work(ps->metadata_wq, &req.work);
-	flush_work(&req.work);
+	flush_workqueue(ps->metadata_wq);
 
 	return req.result;
 }
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index c434e5aab2df..aec57d76db5d 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -725,17 +725,16 @@ static int calc_max_buckets(void)
  */
 static int init_hash_tables(struct dm_snapshot *s)
 {
-	sector_t hash_size, cow_dev_size, origin_dev_size, max_buckets;
+	sector_t hash_size, cow_dev_size, max_buckets;
 
 	/*
 	 * Calculate based on the size of the original volume or
 	 * the COW volume...
 	 */
 	cow_dev_size = get_dev_size(s->cow->bdev);
-	origin_dev_size = get_dev_size(s->origin->bdev);
 	max_buckets = calc_max_buckets();
 
-	hash_size = min(origin_dev_size, cow_dev_size) >> s->store->chunk_shift;
+	hash_size = cow_dev_size >> s->store->chunk_shift;
 	hash_size = min(hash_size, max_buckets);
 
 	if (hash_size < 64)
diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
index 8ae31e8d3d64..3d404c1371ed 100644
--- a/drivers/md/dm-stats.c
+++ b/drivers/md/dm-stats.c
@@ -451,19 +451,26 @@ static void dm_stat_for_entry(struct dm_stat *s, size_t entry,
 	struct dm_stat_percpu *p;
 
 	/*
-	 * For strict correctness we should use local_irq_disable/enable
+	 * For strict correctness we should use local_irq_save/restore
 	 * instead of preempt_disable/enable.
 	 *
-	 * This is racy if the driver finishes bios from non-interrupt
-	 * context as well as from interrupt context or from more different
-	 * interrupts.
+	 * preempt_disable/enable is racy if the driver finishes bios
+	 * from non-interrupt context as well as from interrupt context
+	 * or from more different interrupts.
 	 *
-	 * However, the race only results in not counting some events,
-	 * so it is acceptable.
+	 * On 64-bit architectures the race only results in not counting some
+	 * events, so it is acceptable.  On 32-bit architectures the race could
+	 * cause the counter going off by 2^32, so we need to do proper locking
+	 * there.
 	 *
 	 * part_stat_lock()/part_stat_unlock() have this race too.
 	 */
+#if BITS_PER_LONG == 32
+	unsigned long flags;
+	local_irq_save(flags);
+#else
 	preempt_disable();
+#endif
 	p = &s->stat_percpu[smp_processor_id()][entry];
 
 	if (!end) {
@@ -478,7 +485,11 @@ static void dm_stat_for_entry(struct dm_stat *s, size_t entry,
 		p->ticks[idx] += duration;
 	}
 
+#if BITS_PER_LONG == 32
+	local_irq_restore(flags);
+#else
 	preempt_enable();
+#endif
 }
 
 static void __dm_stat_bio(struct dm_stat *s, unsigned long bi_rw,
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index ed063427d676..2c0cf511ec23 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -2095,6 +2095,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	 * them down to the data device.  The thin device's discard
 	 * processing will cause mappings to be removed from the btree.
 	 */
+	ti->discard_zeroes_data_unsupported = true;
 	if (pf.discard_enabled && pf.discard_passdown) {
 		ti->num_discard_bios = 1;
 
@@ -2104,7 +2105,6 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		 * thin devices' discard limits consistent).
 		 */
 		ti->discards_supported = true;
-		ti->discard_zeroes_data_unsupported = true;
 	}
 	ti->private = pt;
 
@@ -2689,8 +2689,16 @@ static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits)
 	 * They get transferred to the live pool in bind_control_target()
 	 * called from pool_preresume().
 	 */
-	if (!pt->adjusted_pf.discard_enabled)
+	if (!pt->adjusted_pf.discard_enabled) {
+		/*
+		 * Must explicitly disallow stacking discard limits otherwise the
+		 * block layer will stack them if pool's data device has support.
+		 * QUEUE_FLAG_DISCARD wouldn't be set but there is no way for the
+		 * user to see that, so make sure to set all discard limits to 0.
+		 */
+		limits->discard_granularity = 0;
 		return;
+	}
 
 	disable_passdown_if_not_supported(pt);
 
@@ -2826,10 +2834,10 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	ti->per_bio_data_size = sizeof(struct dm_thin_endio_hook);
 
 	/* In case the pool supports discards, pass them on. */
+	ti->discard_zeroes_data_unsupported = true;
 	if (tc->pool->pf.discard_enabled) {
 		ti->discards_supported = true;
 		ti->num_discard_bios = 1;
-		ti->discard_zeroes_data_unsupported = true;
 		/* Discard bios must be split on a block boundary */
 		ti->split_discard_bios = true;
 	}
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 6a5e9ed2fcc3..b3e26c7d1417 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -211,10 +211,55 @@ struct dm_md_mempools {
 	struct bio_set *bs;
 };
 
-#define MIN_IOS 256
+#define RESERVED_BIO_BASED_IOS		16
+#define RESERVED_REQUEST_BASED_IOS	256
+#define RESERVED_MAX_IOS		1024
 static struct kmem_cache *_io_cache;
 static struct kmem_cache *_rq_tio_cache;
 
+/*
+ * Bio-based DM's mempools' reserved IOs set by the user.
+ */
+static unsigned reserved_bio_based_ios = RESERVED_BIO_BASED_IOS;
+
+/*
+ * Request-based DM's mempools' reserved IOs set by the user.
+ */
+static unsigned reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS;
+
+static unsigned __dm_get_reserved_ios(unsigned *reserved_ios,
+				      unsigned def, unsigned max)
+{
+	unsigned ios = ACCESS_ONCE(*reserved_ios);
+	unsigned modified_ios = 0;
+
+	if (!ios)
+		modified_ios = def;
+	else if (ios > max)
+		modified_ios = max;
+
+	if (modified_ios) {
+		(void)cmpxchg(reserved_ios, ios, modified_ios);
+		ios = modified_ios;
+	}
+
+	return ios;
+}
+
+unsigned dm_get_reserved_bio_based_ios(void)
+{
+	return __dm_get_reserved_ios(&reserved_bio_based_ios,
+				     RESERVED_BIO_BASED_IOS, RESERVED_MAX_IOS);
+}
+EXPORT_SYMBOL_GPL(dm_get_reserved_bio_based_ios);
+
+unsigned dm_get_reserved_rq_based_ios(void)
+{
+	return __dm_get_reserved_ios(&reserved_rq_based_ios,
+				     RESERVED_REQUEST_BASED_IOS, RESERVED_MAX_IOS);
+}
+EXPORT_SYMBOL_GPL(dm_get_reserved_rq_based_ios);
+
 static int __init local_init(void)
 {
 	int r = -ENOMEM;
@@ -2278,6 +2323,17 @@ struct target_type *dm_get_immutable_target_type(struct mapped_device *md)
 }
 
 /*
+ * The queue_limits are only valid as long as you have a reference
+ * count on 'md'.
+ */
+struct queue_limits *dm_get_queue_limits(struct mapped_device *md)
+{
+	BUG_ON(!atomic_read(&md->holders));
+	return &md->queue->limits;
+}
+EXPORT_SYMBOL_GPL(dm_get_queue_limits);
+
+/*
  * Fully initialize a request-based queue (->elevator, ->request_fn, etc).
  */
 static int dm_init_request_based_queue(struct mapped_device *md)
@@ -2862,18 +2918,18 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, u
 
 	if (type == DM_TYPE_BIO_BASED) {
 		cachep = _io_cache;
-		pool_size = 16;
+		pool_size = dm_get_reserved_bio_based_ios();
 		front_pad = roundup(per_bio_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
 	} else if (type == DM_TYPE_REQUEST_BASED) {
 		cachep = _rq_tio_cache;
-		pool_size = MIN_IOS;
+		pool_size = dm_get_reserved_rq_based_ios();
 		front_pad = offsetof(struct dm_rq_clone_bio_info, clone);
 		/* per_bio_data_size is not used. See __bind_mempools(). */
 		WARN_ON(per_bio_data_size != 0);
 	} else
 		goto out;
 
-	pools->io_pool = mempool_create_slab_pool(MIN_IOS, cachep);
+	pools->io_pool = mempool_create_slab_pool(pool_size, cachep);
 	if (!pools->io_pool)
 		goto out;
 
@@ -2924,6 +2980,13 @@ module_exit(dm_exit);
 
 module_param(major, uint, 0);
 MODULE_PARM_DESC(major, "The major number of the device mapper");
+
+module_param(reserved_bio_based_ios, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(reserved_bio_based_ios, "Reserved IOs in bio-based mempools");
+
+module_param(reserved_rq_based_ios, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(reserved_rq_based_ios, "Reserved IOs in request-based mempools");
+
 MODULE_DESCRIPTION(DM_NAME " driver");
 MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 5e604cc7b4aa..1d1ad7b7e527 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -184,6 +184,9 @@ void dm_free_md_mempools(struct dm_md_mempools *pools);
 /*
  * Helpers that are used by DM core
  */
+unsigned dm_get_reserved_bio_based_ios(void);
+unsigned dm_get_reserved_rq_based_ios(void);
+
 static inline bool dm_message_test_buffer_overflow(char *result, unsigned maxlen)
 {
 	return !maxlen || strlen(result) + 1 >= maxlen;
diff --git a/drivers/misc/mei/amthif.c b/drivers/misc/mei/amthif.c
index 04fd38567729..226c3f3cd3e8 100644
--- a/drivers/misc/mei/amthif.c
+++ b/drivers/misc/mei/amthif.c
@@ -57,6 +57,7 @@ void mei_amthif_reset_params(struct mei_device *dev)
 	dev->iamthif_ioctl = false;
 	dev->iamthif_state = MEI_IAMTHIF_IDLE;
 	dev->iamthif_timer = 0;
+	dev->iamthif_stall_timer = 0;
 }
 
 /**
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index 6d0282c08a06..cd2033cd7120 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -297,10 +297,13 @@ int __mei_cl_recv(struct mei_cl *cl, u8 *buf, size_t length)
 
 	if (cl->reading_state != MEI_READ_COMPLETE &&
 	    !waitqueue_active(&cl->rx_wait)) {
+
 		mutex_unlock(&dev->device_lock);
 
 		if (wait_event_interruptible(cl->rx_wait,
-				(MEI_READ_COMPLETE == cl->reading_state))) {
+				cl->reading_state == MEI_READ_COMPLETE  ||
+				mei_cl_is_transitioning(cl))) {
+
 			if (signal_pending(current))
 				return -EINTR;
 			return -ERESTARTSYS;
diff --git a/drivers/misc/mei/client.h b/drivers/misc/mei/client.h
index 6374ed99e233..c8396e582f1c 100644
--- a/drivers/misc/mei/client.h
+++ b/drivers/misc/mei/client.h
@@ -90,6 +90,12 @@ static inline bool mei_cl_is_connected(struct mei_cl *cl)
 		cl->dev->dev_state == MEI_DEV_ENABLED &&
 		cl->state == MEI_FILE_CONNECTED);
 }
+static inline bool mei_cl_is_transitioning(struct mei_cl *cl)
+{
+	return (MEI_FILE_INITIALIZING == cl->state ||
+		MEI_FILE_DISCONNECTED == cl->state ||
+		MEI_FILE_DISCONNECTING == cl->state);
+}
 
 bool mei_cl_is_other_connecting(struct mei_cl *cl);
 int mei_cl_disconnect(struct mei_cl *cl);
diff --git a/drivers/misc/mei/hbm.c b/drivers/misc/mei/hbm.c
index f1c974a0bc0d..9b3a0fb7f265 100644
--- a/drivers/misc/mei/hbm.c
+++ b/drivers/misc/mei/hbm.c
@@ -35,11 +35,15 @@ static void mei_hbm_me_cl_allocate(struct mei_device *dev)
 	struct mei_me_client *clients;
 	int b;
 
+	dev->me_clients_num = 0;
+	dev->me_client_presentation_num = 0;
+	dev->me_client_index = 0;
+
 	/* count how many ME clients we have */
 	for_each_set_bit(b, dev->me_clients_map, MEI_CLIENTS_MAX)
 		dev->me_clients_num++;
 
-	if (dev->me_clients_num <= 0)
+	if (dev->me_clients_num == 0)
 		return;
 
 	kfree(dev->me_clients);
@@ -221,7 +225,7 @@ static int mei_hbm_prop_req(struct mei_device *dev)
 	struct hbm_props_request *prop_req;
 	const size_t len = sizeof(struct hbm_props_request);
 	unsigned long next_client_index;
-	u8 client_num;
+	unsigned long client_num;
 
 
 	client_num = dev->me_client_presentation_num;
@@ -680,8 +684,6 @@ void mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr)
 		if (dev->dev_state == MEI_DEV_INIT_CLIENTS &&
 		    dev->hbm_state == MEI_HBM_ENUM_CLIENTS) {
 				dev->init_clients_timer = 0;
-				dev->me_client_presentation_num = 0;
-				dev->me_client_index = 0;
 				mei_hbm_me_cl_allocate(dev);
 				dev->hbm_state = MEI_HBM_CLIENT_PROPERTIES;
 
diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c
index 92c73118b13c..6197018e2f16 100644
--- a/drivers/misc/mei/init.c
+++ b/drivers/misc/mei/init.c
@@ -175,6 +175,9 @@ void mei_reset(struct mei_device *dev, int interrupts_enabled)
 		memset(&dev->wr_ext_msg, 0, sizeof(dev->wr_ext_msg));
 	}
 
+	/* we're already in reset, cancel the init timer */
+	dev->init_clients_timer = 0;
+
 	dev->me_clients_num = 0;
 	dev->rd_msg_hdr = 0;
 	dev->wd_pending = false;
diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c
index 9aa3b78067d3..c71420ef1e37 100644
--- a/drivers/misc/mei/main.c
+++ b/drivers/misc/mei/main.c
@@ -252,19 +252,16 @@ static ssize_t mei_read(struct file *file, char __user *ubuf,
 		mutex_unlock(&dev->device_lock);
 
 		if (wait_event_interruptible(cl->rx_wait,
-			(MEI_READ_COMPLETE == cl->reading_state ||
-			 MEI_FILE_INITIALIZING == cl->state ||
-			 MEI_FILE_DISCONNECTED == cl->state ||
-			 MEI_FILE_DISCONNECTING == cl->state))) {
+				MEI_READ_COMPLETE == cl->reading_state ||
+				mei_cl_is_transitioning(cl))) {
+
 			if (signal_pending(current))
 				return -EINTR;
 			return -ERESTARTSYS;
 		}
 
 		mutex_lock(&dev->device_lock);
-		if (MEI_FILE_INITIALIZING == cl->state ||
-		    MEI_FILE_DISCONNECTED == cl->state ||
-		    MEI_FILE_DISCONNECTING == cl->state) {
+		if (mei_cl_is_transitioning(cl)) {
 			rets = -EBUSY;
 			goto out;
 		}
diff --git a/drivers/misc/mei/mei_dev.h b/drivers/misc/mei/mei_dev.h
index 7b918b2fb894..456b322013e2 100644
--- a/drivers/misc/mei/mei_dev.h
+++ b/drivers/misc/mei/mei_dev.h
@@ -396,9 +396,9 @@ struct mei_device {
 	struct mei_me_client *me_clients; /* Note: memory has to be allocated */
 	DECLARE_BITMAP(me_clients_map, MEI_CLIENTS_MAX);
 	DECLARE_BITMAP(host_clients_map, MEI_CLIENTS_MAX);
-	u8 me_clients_num;
-	u8 me_client_presentation_num;
-	u8 me_client_index;
+	unsigned long me_clients_num;
+	unsigned long me_client_presentation_num;
+	unsigned long me_client_index;
 
 	struct mei_cl wd_cl;
 	enum mei_wd_states wd_state;
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index e8ccf6c0f08a..bdd64b1b4817 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1155,8 +1155,14 @@ static void pci_enable_bridge(struct pci_dev *dev)
 
 	pci_enable_bridge(dev->bus->self);
 
-	if (pci_is_enabled(dev))
+	if (pci_is_enabled(dev)) {
+		if (!dev->is_busmaster) {
+			dev_warn(&dev->dev, "driver skip pci_set_master, fix it!\n");
+			pci_set_master(dev);
+		}
 		return;
+	}
+
 	retval = pci_enable_device(dev);
 	if (retval)
 		dev_err(&dev->dev, "Error enabling bridge (%d), continuing\n",
diff --git a/drivers/staging/imx-drm/imx-drm-core.c b/drivers/staging/imx-drm/imx-drm-core.c
index 47c5888461ff..a2e52a0c53c9 100644
--- a/drivers/staging/imx-drm/imx-drm-core.c
+++ b/drivers/staging/imx-drm/imx-drm-core.c
@@ -41,7 +41,6 @@ struct imx_drm_device {
 	struct list_head			encoder_list;
 	struct list_head			connector_list;
 	struct mutex				mutex;
-	int					references;
 	int					pipes;
 	struct drm_fbdev_cma			*fbhelper;
 };
@@ -241,8 +240,6 @@ struct drm_device *imx_drm_device_get(void)
 		}
 	}
 
-	imxdrm->references++;
-
 	return imxdrm->drm;
 
 unwind_crtc:
@@ -280,8 +277,6 @@ void imx_drm_device_put(void)
 	list_for_each_entry(enc, &imxdrm->encoder_list, list)
 		module_put(enc->owner);
 
-	imxdrm->references--;
-
 	mutex_unlock(&imxdrm->mutex);
 }
 EXPORT_SYMBOL_GPL(imx_drm_device_put);
@@ -485,7 +480,7 @@ int imx_drm_add_crtc(struct drm_crtc *crtc,
 
 	mutex_lock(&imxdrm->mutex);
 
-	if (imxdrm->references) {
+	if (imxdrm->drm->open_count) {
 		ret = -EBUSY;
 		goto err_busy;
 	}
@@ -564,7 +559,7 @@ int imx_drm_add_encoder(struct drm_encoder *encoder,
 
 	mutex_lock(&imxdrm->mutex);
 
-	if (imxdrm->references) {
+	if (imxdrm->drm->open_count) {
 		ret = -EBUSY;
 		goto err_busy;
 	}
@@ -709,7 +704,7 @@ int imx_drm_add_connector(struct drm_connector *connector,
 
 	mutex_lock(&imxdrm->mutex);
 
-	if (imxdrm->references) {
+	if (imxdrm->drm->open_count) {
 		ret = -EBUSY;
 		goto err_busy;
 	}
diff --git a/drivers/staging/lustre/lustre/obdecho/echo_client.c b/drivers/staging/lustre/lustre/obdecho/echo_client.c
index 2644edf438c1..c8b43442dc74 100644
--- a/drivers/staging/lustre/lustre/obdecho/echo_client.c
+++ b/drivers/staging/lustre/lustre/obdecho/echo_client.c
@@ -1387,7 +1387,7 @@ echo_copyout_lsm (struct lov_stripe_md *lsm, void *_ulsm, int ulsm_nob)
 	if (nob > ulsm_nob)
 		return (-EINVAL);
 
-	if (copy_to_user (ulsm, lsm, sizeof(ulsm)))
+	if (copy_to_user (ulsm, lsm, sizeof(*ulsm)))
 		return (-EFAULT);
 
 	for (i = 0; i < lsm->lsm_stripe_count; i++) {
diff --git a/drivers/staging/octeon-usb/cvmx-usb.c b/drivers/staging/octeon-usb/cvmx-usb.c
index d7b3c82b5ead..45dfe94199ae 100644
--- a/drivers/staging/octeon-usb/cvmx-usb.c
+++ b/drivers/staging/octeon-usb/cvmx-usb.c
@@ -604,7 +604,7 @@ int cvmx_usb_initialize(struct cvmx_usb_state *state, int usb_port_number,
 			}
 	}
 
-	memset(usb, 0, sizeof(usb));
+	memset(usb, 0, sizeof(*usb));
 	usb->init_flags = flags;
 
 	/* Initialize the USB state structure */
diff --git a/drivers/staging/rtl8188eu/core/rtw_mp.c b/drivers/staging/rtl8188eu/core/rtw_mp.c
index c7ff2e4d1f23..9832dcbbd07f 100644
--- a/drivers/staging/rtl8188eu/core/rtw_mp.c
+++ b/drivers/staging/rtl8188eu/core/rtw_mp.c
@@ -907,7 +907,7 @@ u32 mp_query_psd(struct adapter *pAdapter, u8 *data)
 		sscanf(data, "pts =%d, start =%d, stop =%d", &psd_pts, &psd_start, &psd_stop);
 	}
 
-	_rtw_memset(data, '\0', sizeof(data));
+	_rtw_memset(data, '\0', sizeof(*data));
 
 	i = psd_start;
 	while (i < psd_stop) {
diff --git a/drivers/staging/rtl8188eu/hal/rtl8188e_dm.c b/drivers/staging/rtl8188eu/hal/rtl8188e_dm.c
index 9c2e7a20c09e..ec0028d4e61a 100644
--- a/drivers/staging/rtl8188eu/hal/rtl8188e_dm.c
+++ b/drivers/staging/rtl8188eu/hal/rtl8188e_dm.c
@@ -57,7 +57,7 @@ static void Init_ODM_ComInfo_88E(struct adapter *Adapter)
 	u8 cut_ver, fab_ver;
 
 	/*  Init Value */
-	_rtw_memset(dm_odm, 0, sizeof(dm_odm));
+	_rtw_memset(dm_odm, 0, sizeof(*dm_odm));
 
 	dm_odm->Adapter = Adapter;
 
diff --git a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c
index cd4100fb3645..95953ebc0279 100644
--- a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c
+++ b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c
@@ -6973,7 +6973,7 @@ static int rtw_mp_ctx(struct net_device *dev,
 	stop = strncmp(extra, "stop", 4);
 	sscanf(extra, "count =%d, pkt", &count);
 
-	_rtw_memset(extra, '\0', sizeof(extra));
+	_rtw_memset(extra, '\0', sizeof(*extra));
 
 	if (stop == 0) {
 		bStartTest = 0; /*  To set Stop */
diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
index d3078d200e50..9ca3180ebaa0 100644
--- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c
+++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
@@ -54,6 +54,7 @@ static struct usb_device_id rtw_usb_id_tbl[] = {
 	/*=== Customer ID ===*/
 	/****** 8188EUS ********/
 	{USB_DEVICE(0x8179, 0x07B8)}, /* Abocom - Abocom */
+	{USB_DEVICE(0x2001, 0x330F)}, /* DLink DWA-125 REV D1 */
 	{}	/* Terminating entry */
 };
 
diff --git a/drivers/staging/rtl8192u/r819xU_cmdpkt.c b/drivers/staging/rtl8192u/r819xU_cmdpkt.c
index 5bc361b16d4c..56144014b7c9 100644
--- a/drivers/staging/rtl8192u/r819xU_cmdpkt.c
+++ b/drivers/staging/rtl8192u/r819xU_cmdpkt.c
@@ -37,6 +37,8 @@ rt_status SendTxCommandPacket(struct net_device *dev, void *pData, u32 DataLen)
 	/* Get TCB and local buffer from common pool.
 	   (It is shared by CmdQ, MgntQ, and USB coalesce DataQ) */
 	skb  = dev_alloc_skb(USB_HWDESC_HEADER_LEN + DataLen + 4);
+	if (!skb)
+		return RT_STATUS_FAILURE;
 	memcpy((unsigned char *)(skb->cb), &dev, sizeof(dev));
 	tcb_desc = (cb_desc *)(skb->cb + MAX_DEV_ADDR_SIZE);
 	tcb_desc->queue_index = TXCMD_QUEUE;
diff --git a/drivers/staging/vt6656/iwctl.c b/drivers/staging/vt6656/iwctl.c
index d0cf7d8a20e5..8872e0f84f40 100644
--- a/drivers/staging/vt6656/iwctl.c
+++ b/drivers/staging/vt6656/iwctl.c
@@ -1634,6 +1634,9 @@ int iwctl_siwencodeext(struct net_device *dev, struct iw_request_info *info,
 	if (pMgmt == NULL)
 		return -EFAULT;
 
+	if (!(pDevice->flags & DEVICE_FLAGS_OPENED))
+		return -ENODEV;
+
 	buf = kzalloc(sizeof(struct viawget_wpa_param), GFP_KERNEL);
 	if (buf == NULL)
 		return -ENOMEM;
diff --git a/drivers/staging/vt6656/main_usb.c b/drivers/staging/vt6656/main_usb.c
index 536971786ae8..6f9d28182445 100644
--- a/drivers/staging/vt6656/main_usb.c
+++ b/drivers/staging/vt6656/main_usb.c
@@ -1098,6 +1098,8 @@ static int device_close(struct net_device *dev)
     memset(pMgmt->abyCurrBSSID, 0, 6);
     pMgmt->eCurrState = WMAC_STATE_IDLE;
 
+	pDevice->flags &= ~DEVICE_FLAGS_OPENED;
+
     device_free_tx_bufs(pDevice);
     device_free_rx_bufs(pDevice);
     device_free_int_bufs(pDevice);
@@ -1109,7 +1111,6 @@ static int device_close(struct net_device *dev)
     usb_free_urb(pDevice->pInterruptURB);
 
     BSSvClearNodeDBTable(pDevice, 0);
-    pDevice->flags &=(~DEVICE_FLAGS_OPENED);
 
     DBG_PRT(MSG_LEVEL_DEBUG, KERN_INFO "device_close2 \n");
 
diff --git a/drivers/staging/vt6656/rxtx.c b/drivers/staging/vt6656/rxtx.c
index fb743a8811bb..14f3e852215d 100644
--- a/drivers/staging/vt6656/rxtx.c
+++ b/drivers/staging/vt6656/rxtx.c
@@ -148,6 +148,8 @@ static void *s_vGetFreeContext(struct vnt_private *pDevice)
     DBG_PRT(MSG_LEVEL_DEBUG, KERN_INFO"GetFreeContext()\n");
 
     for (ii = 0; ii < pDevice->cbTD; ii++) {
+	if (!pDevice->apTD[ii])
+		return NULL;
         pContext = pDevice->apTD[ii];
         if (pContext->bBoolInUse == false) {
             pContext->bBoolInUse = true;
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index c9a9ddd1d0bc..01bf5eb4f238 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -1758,8 +1758,7 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
 		canon_change = (old->c_lflag ^ tty->termios.c_lflag) & ICANON;
 	if (canon_change) {
 		bitmap_zero(ldata->read_flags, N_TTY_BUF_SIZE);
-		ldata->line_start = 0;
-		ldata->canon_head = ldata->read_tail;
+		ldata->line_start = ldata->canon_head = ldata->read_tail;
 		ldata->erasing = 0;
 		ldata->lnext = 0;
 	}
diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c
index 52379e56a31e..44077c0b7670 100644
--- a/drivers/tty/serial/pch_uart.c
+++ b/drivers/tty/serial/pch_uart.c
@@ -667,30 +667,21 @@ static int pop_tx_x(struct eg20t_port *priv, unsigned char *buf)
 
 static int dma_push_rx(struct eg20t_port *priv, int size)
 {
-	struct tty_struct *tty;
 	int room;
 	struct uart_port *port = &priv->port;
 	struct tty_port *tport = &port->state->port;
 
-	port = &priv->port;
-	tty = tty_port_tty_get(tport);
-	if (!tty) {
-		dev_dbg(priv->port.dev, "%s:tty is busy now", __func__);
-		return 0;
-	}
-
 	room = tty_buffer_request_room(tport, size);
 
 	if (room < size)
 		dev_warn(port->dev, "Rx overrun: dropping %u bytes\n",
 			 size - room);
 	if (!room)
-		return room;
+		return 0;
 
 	tty_insert_flip_string(tport, sg_virt(&priv->sg_rx), size);
 
 	port->icount.rx += room;
-	tty_kref_put(tty);
 
 	return room;
 }
@@ -1098,6 +1089,8 @@ static void pch_uart_err_ir(struct eg20t_port *priv, unsigned int lsr)
 	if (tty == NULL) {
 		for (i = 0; error_msg[i] != NULL; i++)
 			dev_err(&priv->pdev->dev, error_msg[i]);
+	} else {
+		tty_kref_put(tty);
 	}
 }
 
diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c
index d0d972f7e43e..0489a2bdcdf9 100644
--- a/drivers/tty/serial/serial-tegra.c
+++ b/drivers/tty/serial/serial-tegra.c
@@ -732,7 +732,7 @@ static irqreturn_t tegra_uart_isr(int irq, void *data)
 static void tegra_uart_stop_rx(struct uart_port *u)
 {
 	struct tegra_uart_port *tup = to_tegra_uport(u);
-	struct tty_struct *tty = tty_port_tty_get(&tup->uport.state->port);
+	struct tty_struct *tty;
 	struct tty_port *port = &u->state->port;
 	struct dma_tx_state state;
 	unsigned long ier;
@@ -744,6 +744,8 @@ static void tegra_uart_stop_rx(struct uart_port *u)
 	if (!tup->rx_in_progress)
 		return;
 
+	tty = tty_port_tty_get(&tup->uport.state->port);
+
 	tegra_uart_wait_sym_time(tup, 1); /* wait a character interval */
 
 	ier = tup->ier_shadow;
diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c
index 03ba081c5772..6fd60fece6b4 100644
--- a/drivers/tty/tty_ioctl.c
+++ b/drivers/tty/tty_ioctl.c
@@ -1201,6 +1201,9 @@ int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file,
 		}
 		return 0;
 	case TCFLSH:
+		retval = tty_check_change(tty);
+		if (retval)
+			return retval;
 		return __tty_perform_flush(tty, arg);
 	default:
 		/* Try the mode commands */
diff --git a/drivers/usb/chipidea/Kconfig b/drivers/usb/chipidea/Kconfig
index 4a851e15e58c..77b47d82c9a6 100644
--- a/drivers/usb/chipidea/Kconfig
+++ b/drivers/usb/chipidea/Kconfig
@@ -1,6 +1,6 @@
 config USB_CHIPIDEA
 	tristate "ChipIdea Highspeed Dual Role Controller"
-	depends on (USB_EHCI_HCD && USB_GADGET) || (USB_EHCI_HCD && !USB_GADGET) || (!USB_EHCI_HCD && USB_GADGET)
+	depends on ((USB_EHCI_HCD && USB_GADGET) || (USB_EHCI_HCD && !USB_GADGET) || (!USB_EHCI_HCD && USB_GADGET)) && HAS_DMA
 	help
 	  Say Y here if your system has a dual role high speed USB
 	  controller based on ChipIdea silicon IP. Currently, only the
diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index 74d998d9b45b..be822a2c1776 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -131,7 +131,7 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 		if (ret) {
 			dev_err(&pdev->dev, "usbmisc init failed, ret=%d\n",
 					ret);
-			goto err_clk;
+			goto err_phy;
 		}
 	}
 
@@ -143,7 +143,7 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev,
 			"Can't register ci_hdrc platform device, err=%d\n",
 			ret);
-		goto err_clk;
+		goto err_phy;
 	}
 
 	if (data->usbmisc_data) {
@@ -164,6 +164,9 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 
 disable_device:
 	ci_hdrc_remove_device(data->ci_pdev);
+err_phy:
+	if (data->phy)
+		usb_phy_shutdown(data->phy);
 err_clk:
 	clk_disable_unprepare(data->clk);
 	return ret;
diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 94626409559a..23763dcec069 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -605,6 +605,7 @@ static int ci_hdrc_remove(struct platform_device *pdev)
 	dbg_remove_files(ci);
 	free_irq(ci->irq, ci);
 	ci_role_destroy(ci);
+	kfree(ci->hw_bank.regmap);
 
 	return 0;
 }
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index 6b4c2f2eb946..9333083dd111 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -1600,6 +1600,8 @@ static void destroy_eps(struct ci_hdrc *ci)
 	for (i = 0; i < ci->hw_ep_max; i++) {
 		struct ci_hw_ep *hwep = &ci->ci_hw_ep[i];
 
+		if (hwep->pending_td)
+			free_pending_td(hwep);
 		dma_pool_free(ci->qh_pool, hwep->qh.ptr, hwep->qh.dma);
 	}
 }
@@ -1667,13 +1669,13 @@ static int ci_udc_stop(struct usb_gadget *gadget,
 		if (ci->platdata->notify_event)
 			ci->platdata->notify_event(ci,
 			CI_HDRC_CONTROLLER_STOPPED_EVENT);
-		ci->driver = NULL;
 		spin_unlock_irqrestore(&ci->lock, flags);
 		_gadget_stop_activity(&ci->gadget);
 		spin_lock_irqsave(&ci->lock, flags);
 		pm_runtime_put(&ci->gadget.dev);
 	}
 
+	ci->driver = NULL;
 	spin_unlock_irqrestore(&ci->lock, flags);
 
 	return 0;
diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index 737e3c19967b..71dc5d768fa5 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -742,6 +742,22 @@ static int check_ctrlrecip(struct dev_state *ps, unsigned int requesttype,
 		if ((index & ~USB_DIR_IN) == 0)
 			return 0;
 		ret = findintfep(ps->dev, index);
+		if (ret < 0) {
+			/*
+			 * Some not fully compliant Win apps seem to get
+			 * index wrong and have the endpoint number here
+			 * rather than the endpoint address (with the
+			 * correct direction). Win does let this through,
+			 * so we'll not reject it here but leave it to
+			 * the device to not break KVM. But we warn.
+			 */
+			ret = findintfep(ps->dev, index ^ 0x80);
+			if (ret >= 0)
+				dev_info(&ps->dev->dev,
+					"%s: process %i (%s) requesting ep %02x but needs %02x\n",
+					__func__, task_pid_nr(current),
+					current->comm, index, index ^ 0x80);
+		}
 		if (ret >= 0)
 			ret = checkintf(ps, ret);
 		break;
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index dde4c83516a1..e6b682c6c236 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -3426,6 +3426,9 @@ static int usb_req_set_sel(struct usb_device *udev, enum usb3_link_state state)
 	unsigned long long u2_pel;
 	int ret;
 
+	if (udev->state != USB_STATE_CONFIGURED)
+		return 0;
+
 	/* Convert SEL and PEL stored in ns to us */
 	u1_sel = DIV_ROUND_UP(udev->u1_params.sel, 1000);
 	u1_pel = DIV_ROUND_UP(udev->u1_params.pel, 1000);
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 997ebe420bc9..2e252aae51ca 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -29,6 +29,7 @@
 #define PCI_VENDOR_ID_SYNOPSYS		0x16c3
 #define PCI_DEVICE_ID_SYNOPSYS_HAPSUSB3	0xabcd
 #define PCI_DEVICE_ID_INTEL_BYT		0x0f37
+#define PCI_DEVICE_ID_INTEL_MRFLD	0x119e
 
 struct dwc3_pci {
 	struct device		*dev;
@@ -189,6 +190,7 @@ static DEFINE_PCI_DEVICE_TABLE(dwc3_pci_id_table) = {
 				PCI_DEVICE_ID_SYNOPSYS_HAPSUSB3),
 	},
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BYT), },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MRFLD), },
 	{  }	/* Terminating Entry */
 };
 MODULE_DEVICE_TABLE(pci, dwc3_pci_id_table);
diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c
index 1a66c5baa0d1..0658908d8968 100644
--- a/drivers/usb/gadget/f_fs.c
+++ b/drivers/usb/gadget/f_fs.c
@@ -1034,37 +1034,19 @@ struct ffs_sb_fill_data {
 	struct ffs_file_perms perms;
 	umode_t root_mode;
 	const char *dev_name;
-	union {
-		/* set by ffs_fs_mount(), read by ffs_sb_fill() */
-		void *private_data;
-		/* set by ffs_sb_fill(), read by ffs_fs_mount */
-		struct ffs_data *ffs_data;
-	};
+	struct ffs_data *ffs_data;
 };
 
 static int ffs_sb_fill(struct super_block *sb, void *_data, int silent)
 {
 	struct ffs_sb_fill_data *data = _data;
 	struct inode	*inode;
-	struct ffs_data	*ffs;
+	struct ffs_data	*ffs = data->ffs_data;
 
 	ENTER();
 
-	/* Initialise data */
-	ffs = ffs_data_new();
-	if (unlikely(!ffs))
-		goto Enomem;
-
 	ffs->sb              = sb;
-	ffs->dev_name        = kstrdup(data->dev_name, GFP_KERNEL);
-	if (unlikely(!ffs->dev_name))
-		goto Enomem;
-	ffs->file_perms      = data->perms;
-	ffs->private_data    = data->private_data;
-
-	/* used by the caller of this function */
-	data->ffs_data       = ffs;
-
+	data->ffs_data       = NULL;
 	sb->s_fs_info        = ffs;
 	sb->s_blocksize      = PAGE_CACHE_SIZE;
 	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
@@ -1080,17 +1062,14 @@ static int ffs_sb_fill(struct super_block *sb, void *_data, int silent)
 				  &data->perms);
 	sb->s_root = d_make_root(inode);
 	if (unlikely(!sb->s_root))
-		goto Enomem;
+		return -ENOMEM;
 
 	/* EP0 file */
 	if (unlikely(!ffs_sb_create_file(sb, "ep0", ffs,
 					 &ffs_ep0_operations, NULL)))
-		goto Enomem;
+		return -ENOMEM;
 
 	return 0;
-
-Enomem:
-	return -ENOMEM;
 }
 
 static int ffs_fs_parse_opts(struct ffs_sb_fill_data *data, char *opts)
@@ -1193,6 +1172,7 @@ ffs_fs_mount(struct file_system_type *t, int flags,
 	struct dentry *rv;
 	int ret;
 	void *ffs_dev;
+	struct ffs_data	*ffs;
 
 	ENTER();
 
@@ -1200,18 +1180,30 @@ ffs_fs_mount(struct file_system_type *t, int flags,
 	if (unlikely(ret < 0))
 		return ERR_PTR(ret);
 
+	ffs = ffs_data_new();
+	if (unlikely(!ffs))
+		return ERR_PTR(-ENOMEM);
+	ffs->file_perms = data.perms;
+
+	ffs->dev_name = kstrdup(dev_name, GFP_KERNEL);
+	if (unlikely(!ffs->dev_name)) {
+		ffs_data_put(ffs);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	ffs_dev = functionfs_acquire_dev_callback(dev_name);
-	if (IS_ERR(ffs_dev))
-		return ffs_dev;
+	if (IS_ERR(ffs_dev)) {
+		ffs_data_put(ffs);
+		return ERR_CAST(ffs_dev);
+	}
+	ffs->private_data = ffs_dev;
+	data.ffs_data = ffs;
 
-	data.dev_name = dev_name;
-	data.private_data = ffs_dev;
 	rv = mount_nodev(t, flags, &data, ffs_sb_fill);
-
-	/* data.ffs_data is set by ffs_sb_fill */
-	if (IS_ERR(rv))
+	if (IS_ERR(rv) && data.ffs_data) {
 		functionfs_release_dev_callback(data.ffs_data);
-
+		ffs_data_put(data.ffs_data);
+	}
 	return rv;
 }
 
diff --git a/drivers/usb/host/ehci-fsl.c b/drivers/usb/host/ehci-fsl.c
index 4449f565d6c6..f2407b2e8a99 100644
--- a/drivers/usb/host/ehci-fsl.c
+++ b/drivers/usb/host/ehci-fsl.c
@@ -130,7 +130,7 @@ static int usb_hcd_fsl_probe(const struct hc_driver *driver,
 	}
 
 	/* Enable USB controller, 83xx or 8536 */
-	if (pdata->have_sysif_regs)
+	if (pdata->have_sysif_regs && pdata->controller_ver < FSL_USB_VER_1_6)
 		setbits32(hcd->regs + FSL_SOC_USB_CTRL, 0x4);
 
 	/* Don't need to set host mode here. It will be done by tdi_reset() */
@@ -232,15 +232,9 @@ static int ehci_fsl_setup_phy(struct usb_hcd *hcd,
 	case FSL_USB2_PHY_ULPI:
 		if (pdata->have_sysif_regs && pdata->controller_ver) {
 			/* controller version 1.6 or above */
+			clrbits32(non_ehci + FSL_SOC_USB_CTRL, UTMI_PHY_EN);
 			setbits32(non_ehci + FSL_SOC_USB_CTRL,
-					ULPI_PHY_CLK_SEL);
-			/*
-			 * Due to controller issue of PHY_CLK_VALID in ULPI
-			 * mode, we set USB_CTRL_USB_EN before checking
-			 * PHY_CLK_VALID, otherwise PHY_CLK_VALID doesn't work.
-			 */
-			clrsetbits_be32(non_ehci + FSL_SOC_USB_CTRL,
-					UTMI_PHY_EN, USB_CTRL_USB_EN);
+				ULPI_PHY_CLK_SEL | USB_CTRL_USB_EN);
 		}
 		portsc |= PORT_PTS_ULPI;
 		break;
@@ -270,8 +264,9 @@ static int ehci_fsl_setup_phy(struct usb_hcd *hcd,
 	if (pdata->have_sysif_regs && pdata->controller_ver &&
 	    (phy_mode == FSL_USB2_PHY_ULPI)) {
 		/* check PHY_CLK_VALID to get phy clk valid */
-		if (!spin_event_timeout(in_be32(non_ehci + FSL_SOC_USB_CTRL) &
-				PHY_CLK_VALID, FSL_USB_PHY_CLK_TIMEOUT, 0)) {
+		if (!(spin_event_timeout(in_be32(non_ehci + FSL_SOC_USB_CTRL) &
+				PHY_CLK_VALID, FSL_USB_PHY_CLK_TIMEOUT, 0) ||
+				in_be32(non_ehci + FSL_SOC_USB_PRICTRL))) {
 			printk(KERN_WARNING "fsl-ehci: USB PHY clock invalid\n");
 			return -EINVAL;
 		}
diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c
index 6bd299e61f58..854c2ec7b699 100644
--- a/drivers/usb/host/ehci-pci.c
+++ b/drivers/usb/host/ehci-pci.c
@@ -361,7 +361,7 @@ static struct pci_driver ehci_pci_driver = {
 	.remove =	usb_hcd_pci_remove,
 	.shutdown = 	usb_hcd_pci_shutdown,
 
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_PM
 	.driver =	{
 		.pm =	&usb_hcd_pci_pm_ops
 	},
diff --git a/drivers/usb/host/imx21-hcd.c b/drivers/usb/host/imx21-hcd.c
index 60a5de505ca1..adb01d950a16 100644
--- a/drivers/usb/host/imx21-hcd.c
+++ b/drivers/usb/host/imx21-hcd.c
@@ -824,13 +824,13 @@ static int imx21_hc_urb_enqueue_isoc(struct usb_hcd *hcd,
 			i = DIV_ROUND_UP(wrap_frame(
 					cur_frame - urb->start_frame),
 					urb->interval);
-			if (urb->transfer_flags & URB_ISO_ASAP) {
+
+			/* Treat underruns as if URB_ISO_ASAP was set */
+			if ((urb->transfer_flags & URB_ISO_ASAP) ||
+					i >= urb->number_of_packets) {
 				urb->start_frame = wrap_frame(urb->start_frame
 						+ i * urb->interval);
 				i = 0;
-			} else if (i >= urb->number_of_packets) {
-				ret = -EXDEV;
-				goto alloc_dmem_failed;
 			}
 		}
 	}
diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c
index 8f6b695af6a4..604cad1bcf9c 100644
--- a/drivers/usb/host/ohci-hcd.c
+++ b/drivers/usb/host/ohci-hcd.c
@@ -216,31 +216,26 @@ static int ohci_urb_enqueue (
 			frame &= ~(ed->interval - 1);
 			frame |= ed->branch;
 			urb->start_frame = frame;
+			ed->last_iso = frame + ed->interval * (size - 1);
 		}
 	} else if (ed->type == PIPE_ISOCHRONOUS) {
 		u16	next = ohci_frame_no(ohci) + 1;
 		u16	frame = ed->last_iso + ed->interval;
+		u16	length = ed->interval * (size - 1);
 
 		/* Behind the scheduling threshold? */
 		if (unlikely(tick_before(frame, next))) {
 
-			/* USB_ISO_ASAP: Round up to the first available slot */
+			/* URB_ISO_ASAP: Round up to the first available slot */
 			if (urb->transfer_flags & URB_ISO_ASAP) {
 				frame += (next - frame + ed->interval - 1) &
 						-ed->interval;
 
 			/*
-			 * Not ASAP: Use the next slot in the stream.  If
-			 * the entire URB falls before the threshold, fail.
+			 * Not ASAP: Use the next slot in the stream,
+			 * no matter what.
 			 */
 			} else {
-				if (tick_before(frame + ed->interval *
-					(urb->number_of_packets - 1), next)) {
-					retval = -EXDEV;
-					usb_hcd_unlink_urb_from_ep(hcd, urb);
-					goto fail;
-				}
-
 				/*
 				 * Some OHCI hardware doesn't handle late TDs
 				 * correctly.  After retiring them it proceeds
@@ -251,9 +246,16 @@ static int ohci_urb_enqueue (
 				urb_priv->td_cnt = DIV_ROUND_UP(
 						(u16) (next - frame),
 						ed->interval);
+				if (urb_priv->td_cnt >= urb_priv->length) {
+					++urb_priv->td_cnt;	/* Mark it */
+					ohci_dbg(ohci, "iso underrun %p (%u+%u < %u)\n",
+							urb, frame, length,
+							next);
+				}
 			}
 		}
 		urb->start_frame = frame;
+		ed->last_iso = frame + length;
 	}
 
 	/* fill the TDs and link them to the ed; and
diff --git a/drivers/usb/host/ohci-q.c b/drivers/usb/host/ohci-q.c
index df4a6707322d..e7f577e63624 100644
--- a/drivers/usb/host/ohci-q.c
+++ b/drivers/usb/host/ohci-q.c
@@ -41,9 +41,13 @@ finish_urb(struct ohci_hcd *ohci, struct urb *urb, int status)
 __releases(ohci->lock)
 __acquires(ohci->lock)
 {
-	 struct device *dev = ohci_to_hcd(ohci)->self.controller;
+	struct device *dev = ohci_to_hcd(ohci)->self.controller;
+	struct usb_host_endpoint *ep = urb->ep;
+	struct urb_priv *urb_priv;
+
 	// ASSERT (urb->hcpriv != 0);
 
+ restart:
 	urb_free_priv (ohci, urb->hcpriv);
 	urb->hcpriv = NULL;
 	if (likely(status == -EINPROGRESS))
@@ -80,6 +84,21 @@ __acquires(ohci->lock)
 		ohci->hc_control &= ~(OHCI_CTRL_PLE|OHCI_CTRL_IE);
 		ohci_writel (ohci, ohci->hc_control, &ohci->regs->control);
 	}
+
+	/*
+	 * An isochronous URB that is sumitted too late won't have any TDs
+	 * (marked by the fact that the td_cnt value is larger than the
+	 * actual number of TDs).  If the next URB on this endpoint is like
+	 * that, give it back now.
+	 */
+	if (!list_empty(&ep->urb_list)) {
+		urb = list_first_entry(&ep->urb_list, struct urb, urb_list);
+		urb_priv = urb->hcpriv;
+		if (urb_priv->td_cnt > urb_priv->length) {
+			status = 0;
+			goto restart;
+		}
+	}
 }
 
 
@@ -546,7 +565,6 @@ td_fill (struct ohci_hcd *ohci, u32 info,
 		td->hwCBP = cpu_to_hc32 (ohci, data & 0xFFFFF000);
 		*ohci_hwPSWp(ohci, td, 0) = cpu_to_hc16 (ohci,
 						(data & 0x0FFF) | 0xE000);
-		td->ed->last_iso = info & 0xffff;
 	} else {
 		td->hwCBP = cpu_to_hc32 (ohci, data);
 	}
@@ -996,7 +1014,7 @@ rescan_this:
 			urb_priv->td_cnt++;
 
 			/* if URB is done, clean up */
-			if (urb_priv->td_cnt == urb_priv->length) {
+			if (urb_priv->td_cnt >= urb_priv->length) {
 				modified = completed = 1;
 				finish_urb(ohci, urb, 0);
 			}
@@ -1086,7 +1104,7 @@ static void takeback_td(struct ohci_hcd *ohci, struct td *td)
 	urb_priv->td_cnt++;
 
 	/* If all this urb's TDs are done, call complete() */
-	if (urb_priv->td_cnt == urb_priv->length)
+	if (urb_priv->td_cnt >= urb_priv->length)
 		finish_urb(ohci, urb, status);
 
 	/* clean schedule:  unlink EDs that are no longer busy */
diff --git a/drivers/usb/host/uhci-pci.c b/drivers/usb/host/uhci-pci.c
index c300bd2f7d1c..0f228c46eeda 100644
--- a/drivers/usb/host/uhci-pci.c
+++ b/drivers/usb/host/uhci-pci.c
@@ -293,7 +293,7 @@ static struct pci_driver uhci_pci_driver = {
 	.remove =	usb_hcd_pci_remove,
 	.shutdown =	uhci_shutdown,
 
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_PM
 	.driver =	{
 		.pm =	&usb_hcd_pci_pm_ops
 	},
diff --git a/drivers/usb/host/uhci-q.c b/drivers/usb/host/uhci-q.c
index 041c6ddb695c..da6f56d996ce 100644
--- a/drivers/usb/host/uhci-q.c
+++ b/drivers/usb/host/uhci-q.c
@@ -1303,7 +1303,7 @@ static int uhci_submit_isochronous(struct uhci_hcd *uhci, struct urb *urb,
 		}
 
 		/* Fell behind? */
-		if (uhci_frame_before_eq(frame, next)) {
+		if (!uhci_frame_before_eq(next, frame)) {
 
 			/* USB_ISO_ASAP: Round up to the first available slot */
 			if (urb->transfer_flags & URB_ISO_ASAP)
@@ -1311,13 +1311,17 @@ static int uhci_submit_isochronous(struct uhci_hcd *uhci, struct urb *urb,
 						-qh->period;
 
 			/*
-			 * Not ASAP: Use the next slot in the stream.  If
-			 * the entire URB falls before the threshold, fail.
+			 * Not ASAP: Use the next slot in the stream,
+			 * no matter what.
 			 */
 			else if (!uhci_frame_before_eq(next,
 					frame + (urb->number_of_packets - 1) *
 						qh->period))
-				return -EXDEV;
+				dev_dbg(uhci_dev(uhci), "iso underrun %p (%u+%u < %u)\n",
+						urb, frame,
+						(urb->number_of_packets - 1) *
+							qh->period,
+						next);
 		}
 	}
 
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index fae697ed0b70..773a6b28c4f1 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -287,7 +287,7 @@ static int xhci_stop_device(struct xhci_hcd *xhci, int slot_id, int suspend)
 		if (virt_dev->eps[i].ring && virt_dev->eps[i].ring->dequeue)
 			xhci_queue_stop_endpoint(xhci, slot_id, i, suspend);
 	}
-	cmd->command_trb = xhci->cmd_ring->enqueue;
+	cmd->command_trb = xhci_find_next_enqueue(xhci->cmd_ring);
 	list_add_tail(&cmd->cmd_list, &virt_dev->cmd_list);
 	xhci_queue_stop_endpoint(xhci, slot_id, 0, suspend);
 	xhci_ring_cmd_db(xhci);
@@ -552,11 +552,15 @@ void xhci_del_comp_mod_timer(struct xhci_hcd *xhci, u32 status, u16 wIndex)
  *  - Mark a port as being done with device resume,
  *    and ring the endpoint doorbells.
  *  - Stop the Synopsys redriver Compliance Mode polling.
+ *  - Drop and reacquire the xHCI lock, in order to wait for port resume.
  */
 static u32 xhci_get_port_status(struct usb_hcd *hcd,
 		struct xhci_bus_state *bus_state,
 		__le32 __iomem **port_array,
-		u16 wIndex, u32 raw_port_status)
+		u16 wIndex, u32 raw_port_status,
+		unsigned long flags)
+	__releases(&xhci->lock)
+	__acquires(&xhci->lock)
 {
 	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
 	u32 status = 0;
@@ -591,21 +595,42 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd,
 			return 0xffffffff;
 		if (time_after_eq(jiffies,
 					bus_state->resume_done[wIndex])) {
+			int time_left;
+
 			xhci_dbg(xhci, "Resume USB2 port %d\n",
 					wIndex + 1);
 			bus_state->resume_done[wIndex] = 0;
 			clear_bit(wIndex, &bus_state->resuming_ports);
+
+			set_bit(wIndex, &bus_state->rexit_ports);
 			xhci_set_link_state(xhci, port_array, wIndex,
 					XDEV_U0);
-			xhci_dbg(xhci, "set port %d resume\n",
-					wIndex + 1);
-			slot_id = xhci_find_slot_id_by_port(hcd, xhci,
-					wIndex + 1);
-			if (!slot_id) {
-				xhci_dbg(xhci, "slot_id is zero\n");
-				return 0xffffffff;
+
+			spin_unlock_irqrestore(&xhci->lock, flags);
+			time_left = wait_for_completion_timeout(
+					&bus_state->rexit_done[wIndex],
+					msecs_to_jiffies(
+						XHCI_MAX_REXIT_TIMEOUT));
+			spin_lock_irqsave(&xhci->lock, flags);
+
+			if (time_left) {
+				slot_id = xhci_find_slot_id_by_port(hcd,
+						xhci, wIndex + 1);
+				if (!slot_id) {
+					xhci_dbg(xhci, "slot_id is zero\n");
+					return 0xffffffff;
+				}
+				xhci_ring_device(xhci, slot_id);
+			} else {
+				int port_status = xhci_readl(xhci,
+						port_array[wIndex]);
+				xhci_warn(xhci, "Port resume took longer than %i msec, port status = 0x%x\n",
+						XHCI_MAX_REXIT_TIMEOUT,
+						port_status);
+				status |= USB_PORT_STAT_SUSPEND;
+				clear_bit(wIndex, &bus_state->rexit_ports);
 			}
-			xhci_ring_device(xhci, slot_id);
+
 			bus_state->port_c_suspend |= 1 << wIndex;
 			bus_state->suspended_ports &= ~(1 << wIndex);
 		} else {
@@ -728,7 +753,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 			break;
 		}
 		status = xhci_get_port_status(hcd, bus_state, port_array,
-				wIndex, temp);
+				wIndex, temp, flags);
 		if (status == 0xffffffff)
 			goto error;
 
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 53b972c2a09f..83bcd13622c3 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -2428,6 +2428,8 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 	for (i = 0; i < USB_MAXCHILDREN; ++i) {
 		xhci->bus_state[0].resume_done[i] = 0;
 		xhci->bus_state[1].resume_done[i] = 0;
+		/* Only the USB 2.0 completions will ever be used. */
+		init_completion(&xhci->bus_state[1].rexit_done[i]);
 	}
 
 	if (scratchpad_alloc(xhci, flags))
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index c2d495057eb5..236c3aabe940 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -351,7 +351,7 @@ static struct pci_driver xhci_pci_driver = {
 	/* suspend and resume implemented later */
 
 	.shutdown = 	usb_hcd_pci_shutdown,
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_PM
 	.driver = {
 		.pm = &usb_hcd_pci_pm_ops
 	},
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 411da1fc7ae8..6bfbd80ec2b9 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -123,6 +123,16 @@ static int enqueue_is_link_trb(struct xhci_ring *ring)
 	return TRB_TYPE_LINK_LE32(link->control);
 }
 
+union xhci_trb *xhci_find_next_enqueue(struct xhci_ring *ring)
+{
+	/* Enqueue pointer can be left pointing to the link TRB,
+	 * we must handle that
+	 */
+	if (TRB_TYPE_LINK_LE32(ring->enqueue->link.control))
+		return ring->enq_seg->next->trbs;
+	return ring->enqueue;
+}
+
 /* Updates trb to point to the next TRB in the ring, and updates seg if the next
  * TRB is in a new segment.  This does not skip over link TRBs, and it does not
  * effect the ring dequeue or enqueue pointers.
@@ -859,8 +869,12 @@ remove_finished_td:
 		/* Otherwise ring the doorbell(s) to restart queued transfers */
 		ring_doorbell_for_active_rings(xhci, slot_id, ep_index);
 	}
-	ep->stopped_td = NULL;
-	ep->stopped_trb = NULL;
+
+	/* Clear stopped_td and stopped_trb if endpoint is not halted */
+	if (!(ep->ep_state & EP_HALTED)) {
+		ep->stopped_td = NULL;
+		ep->stopped_trb = NULL;
+	}
 
 	/*
 	 * Drop the lock and complete the URBs in the cancelled TD list.
@@ -1414,6 +1428,12 @@ static void handle_cmd_completion(struct xhci_hcd *xhci,
 			inc_deq(xhci, xhci->cmd_ring);
 			return;
 		}
+		/* There is no command to handle if we get a stop event when the
+		 * command ring is empty, event->cmd_trb points to the next
+		 * unset command
+		 */
+		if (xhci->cmd_ring->dequeue == xhci->cmd_ring->enqueue)
+			return;
 	}
 
 	switch (le32_to_cpu(xhci->cmd_ring->dequeue->generic.field[3])
@@ -1743,6 +1763,19 @@ static void handle_port_status(struct xhci_hcd *xhci,
 		}
 	}
 
+	/*
+	 * Check to see if xhci-hub.c is waiting on RExit to U0 transition (or
+	 * RExit to a disconnect state).  If so, let the the driver know it's
+	 * out of the RExit state.
+	 */
+	if (!DEV_SUPERSPEED(temp) &&
+			test_and_clear_bit(faked_port_index,
+				&bus_state->rexit_ports)) {
+		complete(&bus_state->rexit_done[faked_port_index]);
+		bogus_port_status = true;
+		goto cleanup;
+	}
+
 	if (hcd->speed != HCD_USB3)
 		xhci_test_and_clear_bit(xhci, port_array, faked_port_index,
 					PORT_PLC);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 49b6edb84a79..1e36dbb48366 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -2598,15 +2598,7 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci,
 	if (command) {
 		cmd_completion = command->completion;
 		cmd_status = &command->status;
-		command->command_trb = xhci->cmd_ring->enqueue;
-
-		/* Enqueue pointer can be left pointing to the link TRB,
-		 * we must handle that
-		 */
-		if (TRB_TYPE_LINK_LE32(command->command_trb->link.control))
-			command->command_trb =
-				xhci->cmd_ring->enq_seg->next->trbs;
-
+		command->command_trb = xhci_find_next_enqueue(xhci->cmd_ring);
 		list_add_tail(&command->cmd_list, &virt_dev->cmd_list);
 	} else {
 		cmd_completion = &virt_dev->cmd_completion;
@@ -2614,7 +2606,7 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci,
 	}
 	init_completion(cmd_completion);
 
-	cmd_trb = xhci->cmd_ring->dequeue;
+	cmd_trb = xhci_find_next_enqueue(xhci->cmd_ring);
 	if (!ctx_change)
 		ret = xhci_queue_configure_endpoint(xhci, in_ctx->dma,
 				udev->slot_id, must_succeed);
@@ -3439,14 +3431,7 @@ int xhci_discover_or_reset_device(struct usb_hcd *hcd, struct usb_device *udev)
 
 	/* Attempt to submit the Reset Device command to the command ring */
 	spin_lock_irqsave(&xhci->lock, flags);
-	reset_device_cmd->command_trb = xhci->cmd_ring->enqueue;
-
-	/* Enqueue pointer can be left pointing to the link TRB,
-	 * we must handle that
-	 */
-	if (TRB_TYPE_LINK_LE32(reset_device_cmd->command_trb->link.control))
-		reset_device_cmd->command_trb =
-			xhci->cmd_ring->enq_seg->next->trbs;
+	reset_device_cmd->command_trb = xhci_find_next_enqueue(xhci->cmd_ring);
 
 	list_add_tail(&reset_device_cmd->cmd_list, &virt_dev->cmd_list);
 	ret = xhci_queue_reset_device(xhci, slot_id);
@@ -3650,7 +3635,7 @@ int xhci_alloc_dev(struct usb_hcd *hcd, struct usb_device *udev)
 	union xhci_trb *cmd_trb;
 
 	spin_lock_irqsave(&xhci->lock, flags);
-	cmd_trb = xhci->cmd_ring->dequeue;
+	cmd_trb = xhci_find_next_enqueue(xhci->cmd_ring);
 	ret = xhci_queue_slot_control(xhci, TRB_ENABLE_SLOT, 0);
 	if (ret) {
 		spin_unlock_irqrestore(&xhci->lock, flags);
@@ -3785,7 +3770,7 @@ int xhci_address_device(struct usb_hcd *hcd, struct usb_device *udev)
 				slot_ctx->dev_info >> 27);
 
 	spin_lock_irqsave(&xhci->lock, flags);
-	cmd_trb = xhci->cmd_ring->dequeue;
+	cmd_trb = xhci_find_next_enqueue(xhci->cmd_ring);
 	ret = xhci_queue_address_device(xhci, virt_dev->in_ctx->dma,
 					udev->slot_id);
 	if (ret) {
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 46aa14894148..289fbfbae746 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1412,8 +1412,18 @@ struct xhci_bus_state {
 	unsigned long		resume_done[USB_MAXCHILDREN];
 	/* which ports have started to resume */
 	unsigned long		resuming_ports;
+	/* Which ports are waiting on RExit to U0 transition. */
+	unsigned long		rexit_ports;
+	struct completion	rexit_done[USB_MAXCHILDREN];
 };
 
+
+/*
+ * It can take up to 20 ms to transition from RExit to U0 on the
+ * Intel Lynx Point LP xHCI host.
+ */
+#define	XHCI_MAX_REXIT_TIMEOUT	(20 * 1000)
+
 static inline unsigned int hcd_index(struct usb_hcd *hcd)
 {
 	if (hcd->speed == HCD_USB3)
@@ -1840,6 +1850,7 @@ int xhci_cancel_cmd(struct xhci_hcd *xhci, struct xhci_command *command,
 		union xhci_trb *cmd_trb);
 void xhci_ring_ep_doorbell(struct xhci_hcd *xhci, unsigned int slot_id,
 		unsigned int ep_index, unsigned int stream_id);
+union xhci_trb *xhci_find_next_enqueue(struct xhci_ring *ring);
 
 /* xHCI roothub code */
 void xhci_set_link_state(struct xhci_hcd *xhci, __le32 __iomem **port_array,
diff --git a/drivers/video/mmp/hw/mmp_ctrl.c b/drivers/video/mmp/hw/mmp_ctrl.c
index 75dca19bf214..6ac755270ab4 100644
--- a/drivers/video/mmp/hw/mmp_ctrl.c
+++ b/drivers/video/mmp/hw/mmp_ctrl.c
@@ -514,7 +514,7 @@ static int mmphw_probe(struct platform_device *pdev)
 	if (IS_ERR(ctrl->clk)) {
 		dev_err(ctrl->dev, "unable to get clk %s\n", mi->clk_name);
 		ret = -ENOENT;
-		goto failed_get_clk;
+		goto failed;
 	}
 	clk_prepare_enable(ctrl->clk);
 
@@ -551,21 +551,8 @@ failed_path_init:
 		path_deinit(path_plat);
 	}
 
-	if (ctrl->clk) {
-		devm_clk_put(ctrl->dev, ctrl->clk);
-		clk_disable_unprepare(ctrl->clk);
-	}
-failed_get_clk:
-	devm_free_irq(ctrl->dev, ctrl->irq, ctrl);
+	clk_disable_unprepare(ctrl->clk);
 failed:
-	if (ctrl) {
-		if (ctrl->reg_base)
-			devm_iounmap(ctrl->dev, ctrl->reg_base);
-		devm_release_mem_region(ctrl->dev, res->start,
-				resource_size(res));
-		devm_kfree(ctrl->dev, ctrl);
-	}
-
 	dev_err(&pdev->dev, "device init failed\n");
 
 	return ret;
diff --git a/drivers/video/mxsfb.c b/drivers/video/mxsfb.c
index d250ed0f806d..27197a8048c0 100644
--- a/drivers/video/mxsfb.c
+++ b/drivers/video/mxsfb.c
@@ -620,6 +620,7 @@ static int mxsfb_restore_mode(struct mxsfb_info *host)
 		break;
 	case 3:
 		bits_per_pixel = 32;
+		break;
 	case 1:
 	default:
 		return -EINVAL;
diff --git a/drivers/video/neofb.c b/drivers/video/neofb.c
index 7ef079c146e7..c172a5281f9e 100644
--- a/drivers/video/neofb.c
+++ b/drivers/video/neofb.c
@@ -2075,6 +2075,7 @@ static int neofb_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	if (!fb_find_mode(&info->var, info, mode_option, NULL, 0,
 			info->monspecs.modedb, 16)) {
 		printk(KERN_ERR "neofb: Unable to find usable video mode.\n");
+		err = -EINVAL;
 		goto err_map_video;
 	}
 
@@ -2097,7 +2098,8 @@ static int neofb_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	       info->fix.smem_len >> 10, info->var.xres,
 	       info->var.yres, h_sync / 1000, h_sync % 1000, v_sync);
 
-	if (fb_alloc_cmap(&info->cmap, 256, 0) < 0)
+	err = fb_alloc_cmap(&info->cmap, 256, 0);
+	if (err < 0)
 		goto err_map_video;
 
 	err = register_framebuffer(info);
diff --git a/drivers/video/of_display_timing.c b/drivers/video/of_display_timing.c
index 171821ddd78d..ba5b40f581f6 100644
--- a/drivers/video/of_display_timing.c
+++ b/drivers/video/of_display_timing.c
@@ -120,7 +120,7 @@ int of_get_display_timing(struct device_node *np, const char *name,
 		return -EINVAL;
 	}
 
-	timing_np = of_find_node_by_name(np, name);
+	timing_np = of_get_child_by_name(np, name);
 	if (!timing_np) {
 		pr_err("%s: could not find node '%s'\n",
 			of_node_full_name(np), name);
@@ -143,11 +143,11 @@ struct display_timings *of_get_display_timings(struct device_node *np)
 	struct display_timings *disp;
 
 	if (!np) {
-		pr_err("%s: no devicenode given\n", of_node_full_name(np));
+		pr_err("%s: no device node given\n", of_node_full_name(np));
 		return NULL;
 	}
 
-	timings_np = of_find_node_by_name(np, "display-timings");
+	timings_np = of_get_child_by_name(np, "display-timings");
 	if (!timings_np) {
 		pr_err("%s: could not find display-timings node\n",
 			of_node_full_name(np));
diff --git a/drivers/video/omap2/displays-new/Kconfig b/drivers/video/omap2/displays-new/Kconfig
index 6c90885b0940..10b25e7cd878 100644
--- a/drivers/video/omap2/displays-new/Kconfig
+++ b/drivers/video/omap2/displays-new/Kconfig
@@ -35,6 +35,7 @@ config DISPLAY_PANEL_DPI
 
 config DISPLAY_PANEL_DSI_CM
 	tristate "Generic DSI Command Mode Panel"
+	depends on BACKLIGHT_CLASS_DEVICE
 	help
 	  Driver for generic DSI command mode panels.
 
diff --git a/drivers/video/omap2/displays-new/connector-analog-tv.c b/drivers/video/omap2/displays-new/connector-analog-tv.c
index 1b60698f141e..ccd9073f706f 100644
--- a/drivers/video/omap2/displays-new/connector-analog-tv.c
+++ b/drivers/video/omap2/displays-new/connector-analog-tv.c
@@ -191,7 +191,7 @@ static int tvc_probe_pdata(struct platform_device *pdev)
 	in = omap_dss_find_output(pdata->source);
 	if (in == NULL) {
 		dev_err(&pdev->dev, "Failed to find video source\n");
-		return -ENODEV;
+		return -EPROBE_DEFER;
 	}
 
 	ddata->in = in;
diff --git a/drivers/video/omap2/displays-new/connector-dvi.c b/drivers/video/omap2/displays-new/connector-dvi.c
index bc5f8ceda371..63d88ee6dfe4 100644
--- a/drivers/video/omap2/displays-new/connector-dvi.c
+++ b/drivers/video/omap2/displays-new/connector-dvi.c
@@ -263,7 +263,7 @@ static int dvic_probe_pdata(struct platform_device *pdev)
 	in = omap_dss_find_output(pdata->source);
 	if (in == NULL) {
 		dev_err(&pdev->dev, "Failed to find video source\n");
-		return -ENODEV;
+		return -EPROBE_DEFER;
 	}
 
 	ddata->in = in;
diff --git a/drivers/video/omap2/displays-new/connector-hdmi.c b/drivers/video/omap2/displays-new/connector-hdmi.c
index c5826716d6ab..9abe2c039ae9 100644
--- a/drivers/video/omap2/displays-new/connector-hdmi.c
+++ b/drivers/video/omap2/displays-new/connector-hdmi.c
@@ -290,7 +290,7 @@ static int hdmic_probe_pdata(struct platform_device *pdev)
 	in = omap_dss_find_output(pdata->source);
 	if (in == NULL) {
 		dev_err(&pdev->dev, "Failed to find video source\n");
-		return -ENODEV;
+		return -EPROBE_DEFER;
 	}
 
 	ddata->in = in;
diff --git a/drivers/video/omap2/dss/dispc.c b/drivers/video/omap2/dss/dispc.c
index 02a7340111df..477975009eee 100644
--- a/drivers/video/omap2/dss/dispc.c
+++ b/drivers/video/omap2/dss/dispc.c
@@ -3691,6 +3691,7 @@ static int __init omap_dispchw_probe(struct platform_device *pdev)
 	}
 
 	pm_runtime_enable(&pdev->dev);
+	pm_runtime_irq_safe(&pdev->dev);
 
 	r = dispc_runtime_get();
 	if (r)
diff --git a/drivers/video/s3fb.c b/drivers/video/s3fb.c
index 47ca86c5c6c0..d838ba829459 100644
--- a/drivers/video/s3fb.c
+++ b/drivers/video/s3fb.c
@@ -1336,14 +1336,7 @@ static int s3_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 			(info->var.bits_per_pixel * info->var.xres_virtual);
 	if (info->var.yres_virtual < info->var.yres) {
 		dev_err(info->device, "virtual vertical size smaller than real\n");
-		goto err_find_mode;
-	}
-
-	/* maximize virtual vertical size for fast scrolling */
-	info->var.yres_virtual = info->fix.smem_len * 8 /
-			(info->var.bits_per_pixel * info->var.xres_virtual);
-	if (info->var.yres_virtual < info->var.yres) {
-		dev_err(info->device, "virtual vertical size smaller than real\n");
+		rc = -EINVAL;
 		goto err_find_mode;
 	}
 
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index a50c6e3a7cc4..b232908a6192 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -398,8 +398,6 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 	if (nr_pages > ARRAY_SIZE(frame_list))
 		nr_pages = ARRAY_SIZE(frame_list);
 
-	scratch_page = get_balloon_scratch_page();
-
 	for (i = 0; i < nr_pages; i++) {
 		page = alloc_page(gfp);
 		if (page == NULL) {
@@ -413,6 +411,12 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 
 		scrub_page(page);
 
+		/*
+		 * Ballooned out frames are effectively replaced with
+		 * a scratch frame.  Ensure direct mappings and the
+		 * p2m are consistent.
+		 */
+		scratch_page = get_balloon_scratch_page();
 #ifdef CONFIG_XEN_HAVE_PVMMU
 		if (xen_pv_domain() && !PageHighMem(page)) {
 			ret = HYPERVISOR_update_va_mapping(
@@ -422,24 +426,19 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 			BUG_ON(ret);
 		}
 #endif
-	}
-
-	/* Ensure that ballooned highmem pages don't have kmaps. */
-	kmap_flush_unused();
-	flush_tlb_all();
-
-	/* No more mappings: invalidate P2M and add to balloon. */
-	for (i = 0; i < nr_pages; i++) {
-		pfn = mfn_to_pfn(frame_list[i]);
 		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
 			unsigned long p;
 			p = page_to_pfn(scratch_page);
 			__set_phys_to_machine(pfn, pfn_to_mfn(p));
 		}
+		put_balloon_scratch_page();
+
 		balloon_append(pfn_to_page(pfn));
 	}
 
-	put_balloon_scratch_page();
+	/* Ensure that ballooned highmem pages don't have kmaps. */
+	kmap_flush_unused();
+	flush_tlb_all();
 
 	set_xen_guest_handle(reservation.extent_start, frame_list);
 	reservation.nr_extents   = nr_pages;
diff --git a/fs/bio.c b/fs/bio.c
index b3b20ed9510e..ea5035da4d9a 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -917,8 +917,8 @@ void bio_copy_data(struct bio *dst, struct bio *src)
 		src_p = kmap_atomic(src_bv->bv_page);
 		dst_p = kmap_atomic(dst_bv->bv_page);
 
-		memcpy(dst_p + dst_bv->bv_offset,
-		       src_p + src_bv->bv_offset,
+		memcpy(dst_p + dst_offset,
+		       src_p + src_offset,
 		       bytes);
 
 		kunmap_atomic(dst_p);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 121da2dc3be8..d4e81e4a9b04 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1924,7 +1924,7 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 {
 	int tmp, hangup_needed = 0;
 	struct ocfs2_super *osb = NULL;
-	char nodestr[8];
+	char nodestr[12];
 
 	trace_ocfs2_dismount_volume(sb);
 
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 73feacc49b2e..fd777032c2ba 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -1163,21 +1163,6 @@ static struct reiserfs_journal_list *find_newer_jl_for_cn(struct
 	return NULL;
 }
 
-static int newer_jl_done(struct reiserfs_journal_cnode *cn)
-{
-	struct super_block *sb = cn->sb;
-	b_blocknr_t blocknr = cn->blocknr;
-
-	cn = cn->hprev;
-	while (cn) {
-		if (cn->sb == sb && cn->blocknr == blocknr && cn->jlist &&
-		    atomic_read(&cn->jlist->j_commit_left) != 0)
-				    return 0;
-		cn = cn->hprev;
-	}
-	return 1;
-}
-
 static void remove_journal_hash(struct super_block *,
 				struct reiserfs_journal_cnode **,
 				struct reiserfs_journal_list *, unsigned long,
@@ -1353,7 +1338,6 @@ static int flush_journal_list(struct super_block *s,
 		reiserfs_warning(s, "clm-2048", "called with wcount %d",
 				 atomic_read(&journal->j_wcount));
 	}
-	BUG_ON(jl->j_trans_id == 0);
 
 	/* if flushall == 0, the lock is already held */
 	if (flushall) {
@@ -1593,31 +1577,6 @@ static int flush_journal_list(struct super_block *s,
 	return err;
 }
 
-static int test_transaction(struct super_block *s,
-                            struct reiserfs_journal_list *jl)
-{
-	struct reiserfs_journal_cnode *cn;
-
-	if (jl->j_len == 0 || atomic_read(&jl->j_nonzerolen) == 0)
-		return 1;
-
-	cn = jl->j_realblock;
-	while (cn) {
-		/* if the blocknr == 0, this has been cleared from the hash,
-		 ** skip it
-		 */
-		if (cn->blocknr == 0) {
-			goto next;
-		}
-		if (cn->bh && !newer_jl_done(cn))
-			return 0;
-	      next:
-		cn = cn->next;
-		cond_resched();
-	}
-	return 0;
-}
-
 static int write_one_transaction(struct super_block *s,
 				 struct reiserfs_journal_list *jl,
 				 struct buffer_chunk *chunk)
@@ -1805,6 +1764,8 @@ static int flush_used_journal_lists(struct super_block *s,
 			break;
 		tjl = JOURNAL_LIST_ENTRY(tjl->j_list.next);
 	}
+	get_journal_list(jl);
+	get_journal_list(flush_jl);
 	/* try to find a group of blocks we can flush across all the
 	 ** transactions, but only bother if we've actually spanned
 	 ** across multiple lists
@@ -1813,6 +1774,8 @@ static int flush_used_journal_lists(struct super_block *s,
 		ret = kupdate_transactions(s, jl, &tjl, &trans_id, len, i);
 	}
 	flush_journal_list(s, flush_jl, 1);
+	put_journal_list(s, flush_jl);
+	put_journal_list(s, jl);
 	return 0;
 }
 
@@ -3868,27 +3831,6 @@ int reiserfs_prepare_for_journal(struct super_block *sb,
 	return 1;
 }
 
-static void flush_old_journal_lists(struct super_block *s)
-{
-	struct reiserfs_journal *journal = SB_JOURNAL(s);
-	struct reiserfs_journal_list *jl;
-	struct list_head *entry;
-	time_t now = get_seconds();
-
-	while (!list_empty(&journal->j_journal_list)) {
-		entry = journal->j_journal_list.next;
-		jl = JOURNAL_LIST_ENTRY(entry);
-		/* this check should always be run, to send old lists to disk */
-		if (jl->j_timestamp < (now - (JOURNAL_MAX_TRANS_AGE * 4)) &&
-		    atomic_read(&jl->j_commit_left) == 0 &&
-		    test_transaction(s, jl)) {
-			flush_used_journal_lists(s, jl);
-		} else {
-			break;
-		}
-	}
-}
-
 /*
 ** long and ugly.  If flush, will not return until all commit
 ** blocks and all real buffers in the trans are on disk.
@@ -4232,7 +4174,6 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 			}
 		}
 	}
-	flush_old_journal_lists(sb);
 
 	journal->j_current_jl->j_list_bitmap =
 	    get_list_bitmap(sb, journal->j_current_jl);
diff --git a/fs/udf/ialloc.c b/fs/udf/ialloc.c
index 7e5aae4bf46f..6eaf5edf1ea1 100644
--- a/fs/udf/ialloc.c
+++ b/fs/udf/ialloc.c
@@ -30,18 +30,17 @@ void udf_free_inode(struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;
 	struct udf_sb_info *sbi = UDF_SB(sb);
+	struct logicalVolIntegrityDescImpUse *lvidiu = udf_sb_lvidiu(sb);
 
-	mutex_lock(&sbi->s_alloc_mutex);
-	if (sbi->s_lvid_bh) {
-		struct logicalVolIntegrityDescImpUse *lvidiu =
-							udf_sb_lvidiu(sbi);
+	if (lvidiu) {
+		mutex_lock(&sbi->s_alloc_mutex);
 		if (S_ISDIR(inode->i_mode))
 			le32_add_cpu(&lvidiu->numDirs, -1);
 		else
 			le32_add_cpu(&lvidiu->numFiles, -1);
 		udf_updated_lvid(sb);
+		mutex_unlock(&sbi->s_alloc_mutex);
 	}
-	mutex_unlock(&sbi->s_alloc_mutex);
 
 	udf_free_blocks(sb, NULL, &UDF_I(inode)->i_location, 0, 1);
 }
@@ -55,6 +54,7 @@ struct inode *udf_new_inode(struct inode *dir, umode_t mode, int *err)
 	uint32_t start = UDF_I(dir)->i_location.logicalBlockNum;
 	struct udf_inode_info *iinfo;
 	struct udf_inode_info *dinfo = UDF_I(dir);
+	struct logicalVolIntegrityDescImpUse *lvidiu;
 
 	inode = new_inode(sb);
 
@@ -92,12 +92,10 @@ struct inode *udf_new_inode(struct inode *dir, umode_t mode, int *err)
 		return NULL;
 	}
 
-	if (sbi->s_lvid_bh) {
-		struct logicalVolIntegrityDescImpUse *lvidiu;
-
+	lvidiu = udf_sb_lvidiu(sb);
+	if (lvidiu) {
 		iinfo->i_unique = lvid_get_unique_id(sb);
 		mutex_lock(&sbi->s_alloc_mutex);
-		lvidiu = udf_sb_lvidiu(sbi);
 		if (S_ISDIR(mode))
 			le32_add_cpu(&lvidiu->numDirs, 1);
 		else
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 839a2bad7f45..91219385691d 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -94,13 +94,25 @@ static unsigned int udf_count_free(struct super_block *);
 static int udf_statfs(struct dentry *, struct kstatfs *);
 static int udf_show_options(struct seq_file *, struct dentry *);
 
-struct logicalVolIntegrityDescImpUse *udf_sb_lvidiu(struct udf_sb_info *sbi)
+struct logicalVolIntegrityDescImpUse *udf_sb_lvidiu(struct super_block *sb)
 {
-	struct logicalVolIntegrityDesc *lvid =
-		(struct logicalVolIntegrityDesc *)sbi->s_lvid_bh->b_data;
-	__u32 number_of_partitions = le32_to_cpu(lvid->numOfPartitions);
-	__u32 offset = number_of_partitions * 2 *
-				sizeof(uint32_t)/sizeof(uint8_t);
+	struct logicalVolIntegrityDesc *lvid;
+	unsigned int partnum;
+	unsigned int offset;
+
+	if (!UDF_SB(sb)->s_lvid_bh)
+		return NULL;
+	lvid = (struct logicalVolIntegrityDesc *)UDF_SB(sb)->s_lvid_bh->b_data;
+	partnum = le32_to_cpu(lvid->numOfPartitions);
+	if ((sb->s_blocksize - sizeof(struct logicalVolIntegrityDescImpUse) -
+	     offsetof(struct logicalVolIntegrityDesc, impUse)) /
+	     (2 * sizeof(uint32_t)) < partnum) {
+		udf_err(sb, "Logical volume integrity descriptor corrupted "
+			"(numOfPartitions = %u)!\n", partnum);
+		return NULL;
+	}
+	/* The offset is to skip freeSpaceTable and sizeTable arrays */
+	offset = partnum * 2 * sizeof(uint32_t);
 	return (struct logicalVolIntegrityDescImpUse *)&(lvid->impUse[offset]);
 }
 
@@ -629,9 +641,10 @@ static int udf_remount_fs(struct super_block *sb, int *flags, char *options)
 	struct udf_options uopt;
 	struct udf_sb_info *sbi = UDF_SB(sb);
 	int error = 0;
+	struct logicalVolIntegrityDescImpUse *lvidiu = udf_sb_lvidiu(sb);
 
-	if (sbi->s_lvid_bh) {
-		int write_rev = le16_to_cpu(udf_sb_lvidiu(sbi)->minUDFWriteRev);
+	if (lvidiu) {
+		int write_rev = le16_to_cpu(lvidiu->minUDFWriteRev);
 		if (write_rev > UDF_MAX_WRITE_VERSION && !(*flags & MS_RDONLY))
 			return -EACCES;
 	}
@@ -1905,11 +1918,12 @@ static void udf_open_lvid(struct super_block *sb)
 
 	if (!bh)
 		return;
-
-	mutex_lock(&sbi->s_alloc_mutex);
 	lvid = (struct logicalVolIntegrityDesc *)bh->b_data;
-	lvidiu = udf_sb_lvidiu(sbi);
+	lvidiu = udf_sb_lvidiu(sb);
+	if (!lvidiu)
+		return;
 
+	mutex_lock(&sbi->s_alloc_mutex);
 	lvidiu->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX;
 	lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX;
 	udf_time_to_disk_stamp(&lvid->recordingDateAndTime,
@@ -1937,10 +1951,12 @@ static void udf_close_lvid(struct super_block *sb)
 
 	if (!bh)
 		return;
+	lvid = (struct logicalVolIntegrityDesc *)bh->b_data;
+	lvidiu = udf_sb_lvidiu(sb);
+	if (!lvidiu)
+		return;
 
 	mutex_lock(&sbi->s_alloc_mutex);
-	lvid = (struct logicalVolIntegrityDesc *)bh->b_data;
-	lvidiu = udf_sb_lvidiu(sbi);
 	lvidiu->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX;
 	lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX;
 	udf_time_to_disk_stamp(&lvid->recordingDateAndTime, CURRENT_TIME);
@@ -2093,15 +2109,19 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
 
 	if (sbi->s_lvid_bh) {
 		struct logicalVolIntegrityDescImpUse *lvidiu =
-							udf_sb_lvidiu(sbi);
-		uint16_t minUDFReadRev = le16_to_cpu(lvidiu->minUDFReadRev);
-		uint16_t minUDFWriteRev = le16_to_cpu(lvidiu->minUDFWriteRev);
-		/* uint16_t maxUDFWriteRev =
-				le16_to_cpu(lvidiu->maxUDFWriteRev); */
+							udf_sb_lvidiu(sb);
+		uint16_t minUDFReadRev;
+		uint16_t minUDFWriteRev;
 
+		if (!lvidiu) {
+			ret = -EINVAL;
+			goto error_out;
+		}
+		minUDFReadRev = le16_to_cpu(lvidiu->minUDFReadRev);
+		minUDFWriteRev = le16_to_cpu(lvidiu->minUDFWriteRev);
 		if (minUDFReadRev > UDF_MAX_READ_VERSION) {
 			udf_err(sb, "minUDFReadRev=%x (max is %x)\n",
-				le16_to_cpu(lvidiu->minUDFReadRev),
+				minUDFReadRev,
 				UDF_MAX_READ_VERSION);
 			ret = -EINVAL;
 			goto error_out;
@@ -2265,11 +2285,7 @@ static int udf_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct logicalVolIntegrityDescImpUse *lvidiu;
 	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
-	if (sbi->s_lvid_bh != NULL)
-		lvidiu = udf_sb_lvidiu(sbi);
-	else
-		lvidiu = NULL;
-
+	lvidiu = udf_sb_lvidiu(sb);
 	buf->f_type = UDF_SUPER_MAGIC;
 	buf->f_bsize = sb->s_blocksize;
 	buf->f_blocks = sbi->s_partmaps[sbi->s_partition].s_partition_len;
diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h
index ed401e94aa8c..1f32c7bd9f57 100644
--- a/fs/udf/udf_sb.h
+++ b/fs/udf/udf_sb.h
@@ -162,7 +162,7 @@ static inline struct udf_sb_info *UDF_SB(struct super_block *sb)
 	return sb->s_fs_info;
 }
 
-struct logicalVolIntegrityDescImpUse *udf_sb_lvidiu(struct udf_sb_info *sbi);
+struct logicalVolIntegrityDescImpUse *udf_sb_lvidiu(struct super_block *sb);
 
 int udf_compute_nr_groups(struct super_block *sb, u32 partition);
 
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 88c5ea75ebf6..f1d85cfc0a54 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -628,6 +628,7 @@ xfs_buf_item_unlock(
 		else if (aborted) {
 			ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp));
 			if (lip->li_flags & XFS_LI_IN_AIL) {
+				spin_lock(&lip->li_ailp->xa_lock);
 				xfs_trans_ail_delete(lip->li_ailp, lip,
 						     SHUTDOWN_LOG_IO_ERROR);
 			}
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 069537c845e5..20bf8e8002d6 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -1224,6 +1224,7 @@ xfs_da3_node_toosmall(
 	/* start with smaller blk num */
 	forward = nodehdr.forw < nodehdr.back;
 	for (i = 0; i < 2; forward = !forward, i++) {
+		struct xfs_da3_icnode_hdr thdr;
 		if (forward)
 			blkno = nodehdr.forw;
 		else
@@ -1236,10 +1237,10 @@ xfs_da3_node_toosmall(
 			return(error);
 
 		node = bp->b_addr;
-		xfs_da3_node_hdr_from_disk(&nodehdr, node);
+		xfs_da3_node_hdr_from_disk(&thdr, node);
 		xfs_trans_brelse(state->args->trans, bp);
 
-		if (count - nodehdr.count >= 0)
+		if (count - thdr.count >= 0)
 			break;	/* fits with at least 25% to spare */
 	}
 	if (i >= 2) {
diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/xfs_fs.h
index 1edb5cc3e5f4..18272c766a50 100644
--- a/fs/xfs/xfs_fs.h
+++ b/fs/xfs/xfs_fs.h
@@ -515,7 +515,7 @@ typedef struct xfs_swapext
 /*	XFS_IOC_GETBIOSIZE ---- deprecated 47	   */
 #define XFS_IOC_GETBMAPX	_IOWR('X', 56, struct getbmap)
 #define XFS_IOC_ZERO_RANGE	_IOW ('X', 57, struct xfs_flock64)
-#define XFS_IOC_FREE_EOFBLOCKS	_IOR ('X', 58, struct xfs_eofblocks)
+#define XFS_IOC_FREE_EOFBLOCKS	_IOR ('X', 58, struct xfs_fs_eofblocks)
 
 /*
  * ioctl commands that replace IRIX syssgi()'s
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 193206ba4358..474807a401c8 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -119,11 +119,6 @@ xfs_inode_free(
 		ip->i_itemp = NULL;
 	}
 
-	/* asserts to verify all state is correct here */
-	ASSERT(atomic_read(&ip->i_pincount) == 0);
-	ASSERT(!spin_is_locked(&ip->i_flags_lock));
-	ASSERT(!xfs_isiflocked(ip));
-
 	/*
 	 * Because we use RCU freeing we need to ensure the inode always
 	 * appears to be reclaimed with an invalid inode number when in the
@@ -135,6 +130,10 @@ xfs_inode_free(
 	ip->i_ino = 0;
 	spin_unlock(&ip->i_flags_lock);
 
+	/* asserts to verify all state is correct here */
+	ASSERT(atomic_read(&ip->i_pincount) == 0);
+	ASSERT(!xfs_isiflocked(ip));
+
 	call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
 }
 
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index dabda9521b4b..cc179878fe41 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1970,6 +1970,13 @@ xlog_recover_do_inode_buffer(
  * magic number.  If we don't recognise the magic number in the buffer, then
  * return a LSN of -1 so that the caller knows it was an unrecognised block and
  * so can recover the buffer.
+ *
+ * Note: we cannot rely solely on magic number matches to determine that the
+ * buffer has a valid LSN - we also need to verify that it belongs to this
+ * filesystem, so we need to extract the object's LSN and compare it to that
+ * which we read from the superblock. If the UUIDs don't match, then we've got a
+ * stale metadata block from an old filesystem instance that we need to recover
+ * over the top of.
  */
 static xfs_lsn_t
 xlog_recover_get_buf_lsn(
@@ -1980,6 +1987,8 @@ xlog_recover_get_buf_lsn(
 	__uint16_t		magic16;
 	__uint16_t		magicda;
 	void			*blk = bp->b_addr;
+	uuid_t			*uuid;
+	xfs_lsn_t		lsn = -1;
 
 	/* v4 filesystems always recover immediately */
 	if (!xfs_sb_version_hascrc(&mp->m_sb))
@@ -1992,43 +2001,79 @@ xlog_recover_get_buf_lsn(
 	case XFS_ABTB_MAGIC:
 	case XFS_ABTC_MAGIC:
 	case XFS_IBT_CRC_MAGIC:
-	case XFS_IBT_MAGIC:
-		return be64_to_cpu(
-				((struct xfs_btree_block *)blk)->bb_u.s.bb_lsn);
+	case XFS_IBT_MAGIC: {
+		struct xfs_btree_block *btb = blk;
+
+		lsn = be64_to_cpu(btb->bb_u.s.bb_lsn);
+		uuid = &btb->bb_u.s.bb_uuid;
+		break;
+	}
 	case XFS_BMAP_CRC_MAGIC:
-	case XFS_BMAP_MAGIC:
-		return be64_to_cpu(
-				((struct xfs_btree_block *)blk)->bb_u.l.bb_lsn);
+	case XFS_BMAP_MAGIC: {
+		struct xfs_btree_block *btb = blk;
+
+		lsn = be64_to_cpu(btb->bb_u.l.bb_lsn);
+		uuid = &btb->bb_u.l.bb_uuid;
+		break;
+	}
 	case XFS_AGF_MAGIC:
-		return be64_to_cpu(((struct xfs_agf *)blk)->agf_lsn);
+		lsn = be64_to_cpu(((struct xfs_agf *)blk)->agf_lsn);
+		uuid = &((struct xfs_agf *)blk)->agf_uuid;
+		break;
 	case XFS_AGFL_MAGIC:
-		return be64_to_cpu(((struct xfs_agfl *)blk)->agfl_lsn);
+		lsn = be64_to_cpu(((struct xfs_agfl *)blk)->agfl_lsn);
+		uuid = &((struct xfs_agfl *)blk)->agfl_uuid;
+		break;
 	case XFS_AGI_MAGIC:
-		return be64_to_cpu(((struct xfs_agi *)blk)->agi_lsn);
+		lsn = be64_to_cpu(((struct xfs_agi *)blk)->agi_lsn);
+		uuid = &((struct xfs_agi *)blk)->agi_uuid;
+		break;
 	case XFS_SYMLINK_MAGIC:
-		return be64_to_cpu(((struct xfs_dsymlink_hdr *)blk)->sl_lsn);
+		lsn = be64_to_cpu(((struct xfs_dsymlink_hdr *)blk)->sl_lsn);
+		uuid = &((struct xfs_dsymlink_hdr *)blk)->sl_uuid;
+		break;
 	case XFS_DIR3_BLOCK_MAGIC:
 	case XFS_DIR3_DATA_MAGIC:
 	case XFS_DIR3_FREE_MAGIC:
-		return be64_to_cpu(((struct xfs_dir3_blk_hdr *)blk)->lsn);
+		lsn = be64_to_cpu(((struct xfs_dir3_blk_hdr *)blk)->lsn);
+		uuid = &((struct xfs_dir3_blk_hdr *)blk)->uuid;
+		break;
 	case XFS_ATTR3_RMT_MAGIC:
-		return be64_to_cpu(((struct xfs_attr3_rmt_hdr *)blk)->rm_lsn);
+		lsn = be64_to_cpu(((struct xfs_attr3_rmt_hdr *)blk)->rm_lsn);
+		uuid = &((struct xfs_attr3_rmt_hdr *)blk)->rm_uuid;
+		break;
 	case XFS_SB_MAGIC:
-		return be64_to_cpu(((struct xfs_dsb *)blk)->sb_lsn);
+		lsn = be64_to_cpu(((struct xfs_dsb *)blk)->sb_lsn);
+		uuid = &((struct xfs_dsb *)blk)->sb_uuid;
+		break;
 	default:
 		break;
 	}
 
+	if (lsn != (xfs_lsn_t)-1) {
+		if (!uuid_equal(&mp->m_sb.sb_uuid, uuid))
+			goto recover_immediately;
+		return lsn;
+	}
+
 	magicda = be16_to_cpu(((struct xfs_da_blkinfo *)blk)->magic);
 	switch (magicda) {
 	case XFS_DIR3_LEAF1_MAGIC:
 	case XFS_DIR3_LEAFN_MAGIC:
 	case XFS_DA3_NODE_MAGIC:
-		return be64_to_cpu(((struct xfs_da3_blkinfo *)blk)->lsn);
+		lsn = be64_to_cpu(((struct xfs_da3_blkinfo *)blk)->lsn);
+		uuid = &((struct xfs_da3_blkinfo *)blk)->uuid;
+		break;
 	default:
 		break;
 	}
 
+	if (lsn != (xfs_lsn_t)-1) {
+		if (!uuid_equal(&mp->m_sb.sb_uuid, uuid))
+			goto recover_immediately;
+		return lsn;
+	}
+
 	/*
 	 * We do individual object checks on dquot and inode buffers as they
 	 * have their own individual LSN records. Also, we could have a stale
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 653073de09e3..ed419c62dde1 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -406,13 +406,14 @@ int dm_noflush_suspending(struct dm_target *ti);
 union map_info *dm_get_mapinfo(struct bio *bio);
 union map_info *dm_get_rq_mapinfo(struct request *rq);
 
+struct queue_limits *dm_get_queue_limits(struct mapped_device *md);
+
 /*
  * Geometry functions.
  */
 int dm_get_geometry(struct mapped_device *md, struct hd_geometry *geo);
 int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo);
 
-
 /*-----------------------------------------------------------------
  * Functions for manipulating device-mapper tables.
  *---------------------------------------------------------------*/
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index c68ecfe29441..15da677478dd 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -30,10 +30,13 @@
 /*
  * Framework version for util services.
  */
+#define UTIL_FW_MINOR  0
+
+#define UTIL_WS2K8_FW_MAJOR  1
+#define UTIL_WS2K8_FW_VERSION     (UTIL_WS2K8_FW_MAJOR << 16 | UTIL_FW_MINOR)
 
 #define UTIL_FW_MAJOR  3
-#define UTIL_FW_MINOR  0
-#define UTIL_FW_MAJOR_MINOR     (UTIL_FW_MAJOR << 16 | UTIL_FW_MINOR)
+#define UTIL_FW_VERSION     (UTIL_FW_MAJOR << 16 | UTIL_FW_MINOR)
 
 
 /*
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 60e95872da29..ecc82b37c4cc 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -53,23 +53,6 @@ struct mem_cgroup_reclaim_cookie {
 	unsigned int generation;
 };
 
-enum mem_cgroup_filter_t {
-	VISIT,		/* visit current node */
-	SKIP,		/* skip the current node and continue traversal */
-	SKIP_TREE,	/* skip the whole subtree and continue traversal */
-};
-
-/*
- * mem_cgroup_filter_t predicate might instruct mem_cgroup_iter_cond how to
- * iterate through the hierarchy tree. Each tree element is checked by the
- * predicate before it is returned by the iterator. If a filter returns
- * SKIP or SKIP_TREE then the iterator code continues traversal (with the
- * next node down the hierarchy or the next node that doesn't belong under the
- * memcg's subtree).
- */
-typedef enum mem_cgroup_filter_t
-(*mem_cgroup_iter_filter)(struct mem_cgroup *memcg, struct mem_cgroup *root);
-
 #ifdef CONFIG_MEMCG
 /*
  * All "charge" functions with gfp_mask should use GFP_KERNEL or
@@ -137,18 +120,9 @@ mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
 extern void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 	struct page *oldpage, struct page *newpage, bool migration_ok);
 
-struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root,
-				   struct mem_cgroup *prev,
-				   struct mem_cgroup_reclaim_cookie *reclaim,
-				   mem_cgroup_iter_filter cond);
-
-static inline struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
-				   struct mem_cgroup *prev,
-				   struct mem_cgroup_reclaim_cookie *reclaim)
-{
-	return mem_cgroup_iter_cond(root, prev, reclaim, NULL);
-}
-
+struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
+				   struct mem_cgroup *,
+				   struct mem_cgroup_reclaim_cookie *);
 void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
 
 /*
@@ -260,9 +234,9 @@ static inline void mem_cgroup_dec_page_stat(struct page *page,
 	mem_cgroup_update_page_stat(page, idx, -1);
 }
 
-enum mem_cgroup_filter_t
-mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg,
-		struct mem_cgroup *root);
+unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+						gfp_t gfp_mask,
+						unsigned long *total_scanned);
 
 void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx);
 static inline void mem_cgroup_count_vm_event(struct mm_struct *mm,
@@ -376,15 +350,6 @@ static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 		struct page *oldpage, struct page *newpage, bool migration_ok)
 {
 }
-static inline struct mem_cgroup *
-mem_cgroup_iter_cond(struct mem_cgroup *root,
-		struct mem_cgroup *prev,
-		struct mem_cgroup_reclaim_cookie *reclaim,
-		mem_cgroup_iter_filter cond)
-{
-	/* first call must return non-NULL, second return NULL */
-	return (struct mem_cgroup *)(unsigned long)!prev;
-}
 
 static inline struct mem_cgroup *
 mem_cgroup_iter(struct mem_cgroup *root,
@@ -471,11 +436,11 @@ static inline void mem_cgroup_dec_page_stat(struct page *page,
 }
 
 static inline
-enum mem_cgroup_filter_t
-mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg,
-		struct mem_cgroup *root)
+unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+					    gfp_t gfp_mask,
+					    unsigned long *total_scanned)
 {
-	return VISIT;
+	return 0;
 }
 
 static inline void mem_cgroup_split_huge_fixup(struct page *head)
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index ccd4260834c5..bab49da8a0f0 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -15,8 +15,8 @@
 #include <linux/spinlock_types.h>
 #include <linux/linkage.h>
 #include <linux/lockdep.h>
-
 #include <linux/atomic.h>
+#include <asm/processor.h>
 
 /*
  * Simple, straightforward mutexes with strict semantics:
@@ -175,8 +175,8 @@ extern void mutex_unlock(struct mutex *lock);
 
 extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
 
-#ifndef CONFIG_HAVE_ARCH_MUTEX_CPU_RELAX
-#define arch_mutex_cpu_relax()	cpu_relax()
+#ifndef arch_mutex_cpu_relax
+# define arch_mutex_cpu_relax() cpu_relax()
 #endif
 
 #endif
diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h
index 535cecf1e02f..fcd63baee5f2 100644
--- a/include/linux/of_irq.h
+++ b/include/linux/of_irq.h
@@ -1,8 +1,6 @@
 #ifndef __OF_IRQ_H
 #define __OF_IRQ_H
 
-#if defined(CONFIG_OF)
-struct of_irq;
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/irq.h>
@@ -10,14 +8,6 @@ struct of_irq;
 #include <linux/ioport.h>
 #include <linux/of.h>
 
-/*
- * irq_of_parse_and_map() is used by all OF enabled platforms; but SPARC
- * implements it differently.  However, the prototype is the same for all,
- * so declare it here regardless of the CONFIG_OF_IRQ setting.
- */
-extern unsigned int irq_of_parse_and_map(struct device_node *node, int index);
-
-#if defined(CONFIG_OF_IRQ)
 /**
  * of_irq - container for device_node/irq_specifier pair for an irq controller
  * @controller: pointer to interrupt controller device tree node
@@ -71,11 +61,17 @@ extern int of_irq_to_resource(struct device_node *dev, int index,
 extern int of_irq_count(struct device_node *dev);
 extern int of_irq_to_resource_table(struct device_node *dev,
 		struct resource *res, int nr_irqs);
-extern struct device_node *of_irq_find_parent(struct device_node *child);
 
 extern void of_irq_init(const struct of_device_id *matches);
 
-#endif /* CONFIG_OF_IRQ */
+#if defined(CONFIG_OF)
+/*
+ * irq_of_parse_and_map() is used by all OF enabled platforms; but SPARC
+ * implements it differently.  However, the prototype is the same for all,
+ * so declare it here regardless of the CONFIG_OF_IRQ setting.
+ */
+extern unsigned int irq_of_parse_and_map(struct device_node *node, int index);
+extern struct device_node *of_irq_find_parent(struct device_node *child);
 
 #else /* !CONFIG_OF */
 static inline unsigned int irq_of_parse_and_map(struct device_node *dev,
diff --git a/include/linux/smp.h b/include/linux/smp.h
index cfb7ca094b38..731f5237d5f4 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -155,6 +155,12 @@ smp_call_function_any(const struct cpumask *mask, smp_call_func_t func,
 
 static inline void kick_all_cpus_sync(void) {  }
 
+static inline void __smp_call_function_single(int cpuid,
+		struct call_single_data *data, int wait)
+{
+	on_each_cpu(data->func, data->info, wait);
+}
+
 #endif /* !SMP */
 
 /*
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index fa8b3adf9ffb..46d41e8b0dcc 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -1007,4 +1007,6 @@ struct drm_radeon_info {
 #define SI_TILE_MODE_DEPTH_STENCIL_2D_4AA	3
 #define SI_TILE_MODE_DEPTH_STENCIL_2D_8AA	2
 
+#define CIK_TILE_MODE_DEPTH_STENCIL_1D		5
+
 #endif
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 40a1fb807396..009a655a5d35 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -380,10 +380,13 @@ struct perf_event_mmap_page {
 	union {
 		__u64	capabilities;
 		struct {
-			__u64	cap_usr_time		: 1,
-				cap_usr_rdpmc		: 1,
-				cap_usr_time_zero	: 1,
-				cap_____res		: 61;
+			__u64	cap_bit0		: 1, /* Always 0, deprecated, see commit 860f085b74e9 */
+				cap_bit0_is_deprecated	: 1, /* Always 1, signals that bit 0 is zero */
+
+				cap_user_rdpmc		: 1, /* The RDPMC instruction can be used to read counts */
+				cap_user_time		: 1, /* The time_* fields are used */
+				cap_user_time_zero	: 1, /* The time_zero field is used */
+				cap_____res		: 59;
 		};
 	};
 
@@ -442,12 +445,13 @@ struct perf_event_mmap_page {
 	 *               ((rem * time_mult) >> time_shift);
 	 */
 	__u64	time_zero;
+	__u32	size;			/* Header size up to __reserved[] fields. */
 
 		/*
 		 * Hole for extension of the self monitor capabilities
 		 */
 
-	__u64	__reserved[119];	/* align to 1k */
+	__u8	__reserved[118*8+4];	/* align to 1k. */
 
 	/*
 	 * Control data for the mmap() data buffer.
@@ -528,6 +532,7 @@ enum perf_event_type {
 	 *	u64				len;
 	 *	u64				pgoff;
 	 *	char				filename[];
+	 * 	struct sample_id		sample_id;
 	 * };
 	 */
 	PERF_RECORD_MMAP			= 1,
diff --git a/ipc/msg.c b/ipc/msg.c
index b0d541d42677..9e4310c546ae 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -165,6 +165,15 @@ static inline void msg_rmid(struct ipc_namespace *ns, struct msg_queue *s)
 	ipc_rmid(&msg_ids(ns), &s->q_perm);
 }
 
+static void msg_rcu_free(struct rcu_head *head)
+{
+	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+	struct msg_queue *msq = ipc_rcu_to_struct(p);
+
+	security_msg_queue_free(msq);
+	ipc_rcu_free(head);
+}
+
 /**
  * newque - Create a new msg queue
  * @ns: namespace
@@ -189,15 +198,14 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params)
 	msq->q_perm.security = NULL;
 	retval = security_msg_queue_alloc(msq);
 	if (retval) {
-		ipc_rcu_putref(msq);
+		ipc_rcu_putref(msq, ipc_rcu_free);
 		return retval;
 	}
 
 	/* ipc_addid() locks msq upon success. */
 	id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
 	if (id < 0) {
-		security_msg_queue_free(msq);
-		ipc_rcu_putref(msq);
+		ipc_rcu_putref(msq, msg_rcu_free);
 		return id;
 	}
 
@@ -276,8 +284,7 @@ static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 		free_msg(msg);
 	}
 	atomic_sub(msq->q_cbytes, &ns->msg_bytes);
-	security_msg_queue_free(msq);
-	ipc_rcu_putref(msq);
+	ipc_rcu_putref(msq, msg_rcu_free);
 }
 
 /*
@@ -717,7 +724,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
 		rcu_read_lock();
 		ipc_lock_object(&msq->q_perm);
 
-		ipc_rcu_putref(msq);
+		ipc_rcu_putref(msq, ipc_rcu_free);
 		if (msq->q_perm.deleted) {
 			err = -EIDRM;
 			goto out_unlock0;
diff --git a/ipc/sem.c b/ipc/sem.c
index 69b6a21f3844..19c8b980d1fe 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -243,6 +243,15 @@ static void merge_queues(struct sem_array *sma)
 	}
 }
 
+static void sem_rcu_free(struct rcu_head *head)
+{
+	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+	struct sem_array *sma = ipc_rcu_to_struct(p);
+
+	security_sem_free(sma);
+	ipc_rcu_free(head);
+}
+
 /*
  * If the request contains only one semaphore operation, and there are
  * no complex transactions pending, lock only the semaphore involved.
@@ -374,12 +383,7 @@ static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns
 static inline void sem_lock_and_putref(struct sem_array *sma)
 {
 	sem_lock(sma, NULL, -1);
-	ipc_rcu_putref(sma);
-}
-
-static inline void sem_putref(struct sem_array *sma)
-{
-	ipc_rcu_putref(sma);
+	ipc_rcu_putref(sma, ipc_rcu_free);
 }
 
 static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
@@ -458,14 +462,13 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params)
 	sma->sem_perm.security = NULL;
 	retval = security_sem_alloc(sma);
 	if (retval) {
-		ipc_rcu_putref(sma);
+		ipc_rcu_putref(sma, ipc_rcu_free);
 		return retval;
 	}
 
 	id = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni);
 	if (id < 0) {
-		security_sem_free(sma);
-		ipc_rcu_putref(sma);
+		ipc_rcu_putref(sma, sem_rcu_free);
 		return id;
 	}
 	ns->used_sems += nsems;
@@ -1047,8 +1050,7 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 
 	wake_up_sem_queue_do(&tasks);
 	ns->used_sems -= sma->sem_nsems;
-	security_sem_free(sma);
-	ipc_rcu_putref(sma);
+	ipc_rcu_putref(sma, sem_rcu_free);
 }
 
 static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, int version)
@@ -1292,7 +1294,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 			rcu_read_unlock();
 			sem_io = ipc_alloc(sizeof(ushort)*nsems);
 			if(sem_io == NULL) {
-				sem_putref(sma);
+				ipc_rcu_putref(sma, ipc_rcu_free);
 				return -ENOMEM;
 			}
 
@@ -1328,20 +1330,20 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		if(nsems > SEMMSL_FAST) {
 			sem_io = ipc_alloc(sizeof(ushort)*nsems);
 			if(sem_io == NULL) {
-				sem_putref(sma);
+				ipc_rcu_putref(sma, ipc_rcu_free);
 				return -ENOMEM;
 			}
 		}
 
 		if (copy_from_user (sem_io, p, nsems*sizeof(ushort))) {
-			sem_putref(sma);
+			ipc_rcu_putref(sma, ipc_rcu_free);
 			err = -EFAULT;
 			goto out_free;
 		}
 
 		for (i = 0; i < nsems; i++) {
 			if (sem_io[i] > SEMVMX) {
-				sem_putref(sma);
+				ipc_rcu_putref(sma, ipc_rcu_free);
 				err = -ERANGE;
 				goto out_free;
 			}
@@ -1629,7 +1631,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid)
 	/* step 2: allocate new undo structure */
 	new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL);
 	if (!new) {
-		sem_putref(sma);
+		ipc_rcu_putref(sma, ipc_rcu_free);
 		return ERR_PTR(-ENOMEM);
 	}
 
diff --git a/ipc/shm.c b/ipc/shm.c
index 2821cdf93adb..d69739610fd4 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -167,6 +167,15 @@ static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp)
 	ipc_lock_object(&ipcp->shm_perm);
 }
 
+static void shm_rcu_free(struct rcu_head *head)
+{
+	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+	struct shmid_kernel *shp = ipc_rcu_to_struct(p);
+
+	security_shm_free(shp);
+	ipc_rcu_free(head);
+}
+
 static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
 {
 	ipc_rmid(&shm_ids(ns), &s->shm_perm);
@@ -208,8 +217,7 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
 		user_shm_unlock(file_inode(shp->shm_file)->i_size,
 						shp->mlock_user);
 	fput (shp->shm_file);
-	security_shm_free(shp);
-	ipc_rcu_putref(shp);
+	ipc_rcu_putref(shp, shm_rcu_free);
 }
 
 /*
@@ -497,7 +505,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	shp->shm_perm.security = NULL;
 	error = security_shm_alloc(shp);
 	if (error) {
-		ipc_rcu_putref(shp);
+		ipc_rcu_putref(shp, ipc_rcu_free);
 		return error;
 	}
 
@@ -566,8 +574,7 @@ no_id:
 		user_shm_unlock(size, shp->mlock_user);
 	fput(file);
 no_file:
-	security_shm_free(shp);
-	ipc_rcu_putref(shp);
+	ipc_rcu_putref(shp, shm_rcu_free);
 	return error;
 }
 
diff --git a/ipc/util.c b/ipc/util.c
index e829da9ed01f..fdb8ae740775 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -474,11 +474,6 @@ void ipc_free(void* ptr, int size)
 		kfree(ptr);
 }
 
-struct ipc_rcu {
-	struct rcu_head rcu;
-	atomic_t refcount;
-} ____cacheline_aligned_in_smp;
-
 /**
  *	ipc_rcu_alloc	-	allocate ipc and rcu space 
  *	@size: size desired
@@ -505,27 +500,24 @@ int ipc_rcu_getref(void *ptr)
 	return atomic_inc_not_zero(&p->refcount);
 }
 
-/**
- * ipc_schedule_free - free ipc + rcu space
- * @head: RCU callback structure for queued work
- */
-static void ipc_schedule_free(struct rcu_head *head)
-{
-	vfree(container_of(head, struct ipc_rcu, rcu));
-}
-
-void ipc_rcu_putref(void *ptr)
+void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head))
 {
 	struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1;
 
 	if (!atomic_dec_and_test(&p->refcount))
 		return;
 
-	if (is_vmalloc_addr(ptr)) {
-		call_rcu(&p->rcu, ipc_schedule_free);
-	} else {
-		kfree_rcu(p, rcu);
-	}
+	call_rcu(&p->rcu, func);
+}
+
+void ipc_rcu_free(struct rcu_head *head)
+{
+	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+
+	if (is_vmalloc_addr(p))
+		vfree(p);
+	else
+		kfree(p);
 }
 
 /**
diff --git a/ipc/util.h b/ipc/util.h
index c5f3338ba1fa..f2f5036f2eed 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -47,6 +47,13 @@ static inline void msg_exit_ns(struct ipc_namespace *ns) { }
 static inline void shm_exit_ns(struct ipc_namespace *ns) { }
 #endif
 
+struct ipc_rcu {
+	struct rcu_head rcu;
+	atomic_t refcount;
+} ____cacheline_aligned_in_smp;
+
+#define ipc_rcu_to_struct(p)  ((void *)(p+1))
+
 /*
  * Structure that holds the parameters needed by the ipc operations
  * (see after)
@@ -120,7 +127,8 @@ void ipc_free(void* ptr, int size);
  */
 void* ipc_rcu_alloc(int size);
 int ipc_rcu_getref(void *ptr);
-void ipc_rcu_putref(void *ptr);
+void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head));
+void ipc_rcu_free(struct rcu_head *head);
 
 struct kern_ipc_perm *ipc_lock(struct ipc_ids *, int);
 struct kern_ipc_perm *ipc_obtain_object(struct ipc_ids *ids, int id);
diff --git a/kernel/audit.c b/kernel/audit.c
index 91e53d04b6a9..7b0e23a740ce 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1117,9 +1117,10 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 
 			sleep_time = timeout_start + audit_backlog_wait_time -
 					jiffies;
-			if ((long)sleep_time > 0)
+			if ((long)sleep_time > 0) {
 				wait_for_auditd(sleep_time);
-			continue;
+				continue;
+			}
 		}
 		if (audit_rate_check() && printk_ratelimit())
 			printk(KERN_WARNING
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 247091bf0587..859c8dfd78a1 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -51,6 +51,15 @@ void context_tracking_user_enter(void)
 	unsigned long flags;
 
 	/*
+	 * Repeat the user_enter() check here because some archs may be calling
+	 * this from asm and if no CPU needs context tracking, they shouldn't
+	 * go further. Repeat the check here until they support the static key
+	 * check.
+	 */
+	if (!static_key_false(&context_tracking_enabled))
+		return;
+
+	/*
 	 * Some contexts may involve an exception occuring in an irq,
 	 * leading to that nesting:
 	 * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit()
@@ -151,6 +160,9 @@ void context_tracking_user_exit(void)
 {
 	unsigned long flags;
 
+	if (!static_key_false(&context_tracking_enabled))
+		return;
+
 	if (in_interrupt())
 		return;
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index dd236b66ca3a..cb4238e85b38 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3660,6 +3660,26 @@ static void calc_timer_values(struct perf_event *event,
 	*running = ctx_time - event->tstamp_running;
 }
 
+static void perf_event_init_userpage(struct perf_event *event)
+{
+	struct perf_event_mmap_page *userpg;
+	struct ring_buffer *rb;
+
+	rcu_read_lock();
+	rb = rcu_dereference(event->rb);
+	if (!rb)
+		goto unlock;
+
+	userpg = rb->user_page;
+
+	/* Allow new userspace to detect that bit 0 is deprecated */
+	userpg->cap_bit0_is_deprecated = 1;
+	userpg->size = offsetof(struct perf_event_mmap_page, __reserved);
+
+unlock:
+	rcu_read_unlock();
+}
+
 void __weak arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 {
 }
@@ -4044,6 +4064,7 @@ again:
 	ring_buffer_attach(event, rb);
 	rcu_assign_pointer(event->rb, rb);
 
+	perf_event_init_userpage(event);
 	perf_event_update_userpage(event);
 
 unlock:
diff --git a/kernel/params.c b/kernel/params.c
index 81c4e78c8f4c..c00d5b502aa4 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -254,11 +254,11 @@ int parse_args(const char *doing,
 
 
 STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(short, short, "%hi", long, kstrtoul);
+STANDARD_PARAM_DEF(short, short, "%hi", long, kstrtol);
 STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(int, int, "%i", long, kstrtoul);
+STANDARD_PARAM_DEF(int, int, "%i", long, kstrtol);
 STANDARD_PARAM_DEF(uint, unsigned int, "%u", unsigned long, kstrtoul);
-STANDARD_PARAM_DEF(long, long, "%li", long, kstrtoul);
+STANDARD_PARAM_DEF(long, long, "%li", long, kstrtol);
 STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", unsigned long, kstrtoul);
 
 int param_set_charp(const char *val, const struct kernel_param *kp)
diff --git a/kernel/reboot.c b/kernel/reboot.c
index 269ed9384cc4..f813b3474646 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -32,7 +32,14 @@ EXPORT_SYMBOL(cad_pid);
 #endif
 enum reboot_mode reboot_mode DEFAULT_REBOOT_MODE;
 
-int reboot_default;
+/*
+ * This variable is used privately to keep track of whether or not
+ * reboot_type is still set to its default value (i.e., reboot= hasn't
+ * been set on the command line).  This is needed so that we can
+ * suppress DMI scanning for reboot quirks.  Without it, it's
+ * impossible to override a faulty reboot quirk without recompiling.
+ */
+int reboot_default = 1;
 int reboot_cpu;
 enum reboot_type reboot_type = BOOT_ACPI;
 int reboot_force;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 11cd13667359..7c70201fbc61 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4242,7 +4242,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
 	}
 
 	if (!se) {
-		cfs_rq->h_load = rq->avg.load_avg_contrib;
+		cfs_rq->h_load = cfs_rq->runnable_load_avg;
 		cfs_rq->last_h_load_update = now;
 	}
 
@@ -4823,8 +4823,8 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
 		(busiest->load_per_task * SCHED_POWER_SCALE) /
 		busiest->group_power;
 
-	if (busiest->avg_load - local->avg_load + scaled_busy_load_per_task >=
-	    (scaled_busy_load_per_task * imbn)) {
+	if (busiest->avg_load + scaled_busy_load_per_task >=
+	    local->avg_load + (scaled_busy_load_per_task * imbn)) {
 		env->imbalance = busiest->load_per_task;
 		return;
 	}
@@ -4896,7 +4896,8 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 	 * max load less than avg load(as we skip the groups at or below
 	 * its cpu_power, while calculating max_load..)
 	 */
-	if (busiest->avg_load < sds->avg_load) {
+	if (busiest->avg_load <= sds->avg_load ||
+	    local->avg_load >= sds->avg_load) {
 		env->imbalance = 0;
 		return fix_small_imbalance(env, sds);
 	}
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 51c4f34d258e..4431610f049a 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -486,7 +486,52 @@ static struct smp_hotplug_thread watchdog_threads = {
 	.unpark			= watchdog_enable,
 };
 
-static int watchdog_enable_all_cpus(void)
+static void restart_watchdog_hrtimer(void *info)
+{
+	struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
+	int ret;
+
+	/*
+	 * No need to cancel and restart hrtimer if it is currently executing
+	 * because it will reprogram itself with the new period now.
+	 * We should never see it unqueued here because we are running per-cpu
+	 * with interrupts disabled.
+	 */
+	ret = hrtimer_try_to_cancel(hrtimer);
+	if (ret == 1)
+		hrtimer_start(hrtimer, ns_to_ktime(sample_period),
+				HRTIMER_MODE_REL_PINNED);
+}
+
+static void update_timers(int cpu)
+{
+	struct call_single_data data = {.func = restart_watchdog_hrtimer};
+	/*
+	 * Make sure that perf event counter will adopt to a new
+	 * sampling period. Updating the sampling period directly would
+	 * be much nicer but we do not have an API for that now so
+	 * let's use a big hammer.
+	 * Hrtimer will adopt the new period on the next tick but this
+	 * might be late already so we have to restart the timer as well.
+	 */
+	watchdog_nmi_disable(cpu);
+	__smp_call_function_single(cpu, &data, 1);
+	watchdog_nmi_enable(cpu);
+}
+
+static void update_timers_all_cpus(void)
+{
+	int cpu;
+
+	get_online_cpus();
+	preempt_disable();
+	for_each_online_cpu(cpu)
+		update_timers(cpu);
+	preempt_enable();
+	put_online_cpus();
+}
+
+static int watchdog_enable_all_cpus(bool sample_period_changed)
 {
 	int err = 0;
 
@@ -496,6 +541,8 @@ static int watchdog_enable_all_cpus(void)
 			pr_err("Failed to create watchdog threads, disabled\n");
 		else
 			watchdog_running = 1;
+	} else if (sample_period_changed) {
+		update_timers_all_cpus();
 	}
 
 	return err;
@@ -520,13 +567,15 @@ int proc_dowatchdog(struct ctl_table *table, int write,
 		    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	int err, old_thresh, old_enabled;
+	static DEFINE_MUTEX(watchdog_proc_mutex);
 
+	mutex_lock(&watchdog_proc_mutex);
 	old_thresh = ACCESS_ONCE(watchdog_thresh);
 	old_enabled = ACCESS_ONCE(watchdog_user_enabled);
 
 	err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (err || !write)
-		return err;
+		goto out;
 
 	set_sample_period();
 	/*
@@ -535,7 +584,7 @@ int proc_dowatchdog(struct ctl_table *table, int write,
 	 * watchdog_*_all_cpus() function takes care of this.
 	 */
 	if (watchdog_user_enabled && watchdog_thresh)
-		err = watchdog_enable_all_cpus();
+		err = watchdog_enable_all_cpus(old_thresh != watchdog_thresh);
 	else
 		watchdog_disable_all_cpus();
 
@@ -544,7 +593,8 @@ int proc_dowatchdog(struct ctl_table *table, int write,
 		watchdog_thresh = old_thresh;
 		watchdog_user_enabled = old_enabled;
 	}
-
+out:
+	mutex_unlock(&watchdog_proc_mutex);
 	return err;
 }
 #endif /* CONFIG_SYSCTL */
@@ -554,5 +604,5 @@ void __init lockup_detector_init(void)
 	set_sample_period();
 
 	if (watchdog_user_enabled)
-		watchdog_enable_all_cpus();
+		watchdog_enable_all_cpus(false);
 }
diff --git a/lib/kobject.c b/lib/kobject.c
index 962175134702..669bf190d4fb 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -933,10 +933,7 @@ const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj)
 
 bool kobj_ns_current_may_mount(enum kobj_ns_type type)
 {
-	bool may_mount = false;
-
-	if (type == KOBJ_NS_TYPE_NONE)
-		return true;
+	bool may_mount = true;
 
 	spin_lock(&kobj_ns_type_lock);
 	if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) &&
diff --git a/lib/lockref.c b/lib/lockref.c
index 677d036cf3c7..6f9d434c1521 100644
--- a/lib/lockref.c
+++ b/lib/lockref.c
@@ -4,6 +4,22 @@
 #ifdef CONFIG_CMPXCHG_LOCKREF
 
 /*
+ * Allow weakly-ordered memory architectures to provide barrier-less
+ * cmpxchg semantics for lockref updates.
+ */
+#ifndef cmpxchg64_relaxed
+# define cmpxchg64_relaxed cmpxchg64
+#endif
+
+/*
+ * Allow architectures to override the default cpu_relax() within CMPXCHG_LOOP.
+ * This is useful for architectures with an expensive cpu_relax().
+ */
+#ifndef arch_mutex_cpu_relax
+# define arch_mutex_cpu_relax() cpu_relax()
+#endif
+
+/*
  * Note that the "cmpxchg()" reloads the "old" value for the
  * failure case.
  */
@@ -14,12 +30,13 @@
 	while (likely(arch_spin_value_unlocked(old.lock.rlock.raw_lock))) {  	\
 		struct lockref new = old, prev = old;				\
 		CODE								\
-		old.lock_count = cmpxchg64(&lockref->lock_count,		\
-					   old.lock_count, new.lock_count);	\
+		old.lock_count = cmpxchg64_relaxed(&lockref->lock_count,	\
+						   old.lock_count,		\
+						   new.lock_count);		\
 		if (likely(old.lock_count == prev.lock_count)) {		\
 			SUCCESS;						\
 		}								\
-		cpu_relax();							\
+		arch_mutex_cpu_relax();						\
 	}									\
 } while (0)
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d5ff3ce13029..1c52ddbc839b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -39,6 +39,7 @@
 #include <linux/limits.h>
 #include <linux/export.h>
 #include <linux/mutex.h>
+#include <linux/rbtree.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
@@ -160,6 +161,10 @@ struct mem_cgroup_per_zone {
 
 	struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1];
 
+	struct rb_node		tree_node;	/* RB tree node */
+	unsigned long long	usage_in_excess;/* Set to the value by which */
+						/* the soft limit is exceeded*/
+	bool			on_tree;
 	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
 						/* use container_of	   */
 };
@@ -168,6 +173,26 @@ struct mem_cgroup_per_node {
 	struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
 };
 
+/*
+ * Cgroups above their limits are maintained in a RB-Tree, independent of
+ * their hierarchy representation
+ */
+
+struct mem_cgroup_tree_per_zone {
+	struct rb_root rb_root;
+	spinlock_t lock;
+};
+
+struct mem_cgroup_tree_per_node {
+	struct mem_cgroup_tree_per_zone rb_tree_per_zone[MAX_NR_ZONES];
+};
+
+struct mem_cgroup_tree {
+	struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES];
+};
+
+static struct mem_cgroup_tree soft_limit_tree __read_mostly;
+
 struct mem_cgroup_threshold {
 	struct eventfd_ctx *eventfd;
 	u64 threshold;
@@ -303,22 +328,6 @@ struct mem_cgroup {
 	atomic_t	numainfo_events;
 	atomic_t	numainfo_updating;
 #endif
-	/*
-	 * Protects soft_contributed transitions.
-	 * See mem_cgroup_update_soft_limit
-	 */
-	spinlock_t soft_lock;
-
-	/*
-	 * If true then this group has increased parents' children_in_excess
-	 * when it got over the soft limit.
-	 * When a group falls bellow the soft limit, parents' children_in_excess
-	 * is decreased and soft_contributed changed to false.
-	 */
-	bool soft_contributed;
-
-	/* Number of children that are in soft limit excess */
-	atomic_t children_in_excess;
 
 	struct mem_cgroup_per_node *nodeinfo[0];
 	/* WARNING: nodeinfo must be the last member here */
@@ -422,6 +431,7 @@ static bool move_file(void)
  * limit reclaim to prevent infinite loops, if they ever occur.
  */
 #define	MEM_CGROUP_MAX_RECLAIM_LOOPS		100
+#define	MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS	2
 
 enum charge_type {
 	MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
@@ -648,6 +658,164 @@ page_cgroup_zoneinfo(struct mem_cgroup *memcg, struct page *page)
 	return mem_cgroup_zoneinfo(memcg, nid, zid);
 }
 
+static struct mem_cgroup_tree_per_zone *
+soft_limit_tree_node_zone(int nid, int zid)
+{
+	return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
+}
+
+static struct mem_cgroup_tree_per_zone *
+soft_limit_tree_from_page(struct page *page)
+{
+	int nid = page_to_nid(page);
+	int zid = page_zonenum(page);
+
+	return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
+}
+
+static void
+__mem_cgroup_insert_exceeded(struct mem_cgroup *memcg,
+				struct mem_cgroup_per_zone *mz,
+				struct mem_cgroup_tree_per_zone *mctz,
+				unsigned long long new_usage_in_excess)
+{
+	struct rb_node **p = &mctz->rb_root.rb_node;
+	struct rb_node *parent = NULL;
+	struct mem_cgroup_per_zone *mz_node;
+
+	if (mz->on_tree)
+		return;
+
+	mz->usage_in_excess = new_usage_in_excess;
+	if (!mz->usage_in_excess)
+		return;
+	while (*p) {
+		parent = *p;
+		mz_node = rb_entry(parent, struct mem_cgroup_per_zone,
+					tree_node);
+		if (mz->usage_in_excess < mz_node->usage_in_excess)
+			p = &(*p)->rb_left;
+		/*
+		 * We can't avoid mem cgroups that are over their soft
+		 * limit by the same amount
+		 */
+		else if (mz->usage_in_excess >= mz_node->usage_in_excess)
+			p = &(*p)->rb_right;
+	}
+	rb_link_node(&mz->tree_node, parent, p);
+	rb_insert_color(&mz->tree_node, &mctz->rb_root);
+	mz->on_tree = true;
+}
+
+static void
+__mem_cgroup_remove_exceeded(struct mem_cgroup *memcg,
+				struct mem_cgroup_per_zone *mz,
+				struct mem_cgroup_tree_per_zone *mctz)
+{
+	if (!mz->on_tree)
+		return;
+	rb_erase(&mz->tree_node, &mctz->rb_root);
+	mz->on_tree = false;
+}
+
+static void
+mem_cgroup_remove_exceeded(struct mem_cgroup *memcg,
+				struct mem_cgroup_per_zone *mz,
+				struct mem_cgroup_tree_per_zone *mctz)
+{
+	spin_lock(&mctz->lock);
+	__mem_cgroup_remove_exceeded(memcg, mz, mctz);
+	spin_unlock(&mctz->lock);
+}
+
+
+static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
+{
+	unsigned long long excess;
+	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup_tree_per_zone *mctz;
+	int nid = page_to_nid(page);
+	int zid = page_zonenum(page);
+	mctz = soft_limit_tree_from_page(page);
+
+	/*
+	 * Necessary to update all ancestors when hierarchy is used.
+	 * because their event counter is not touched.
+	 */
+	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
+		mz = mem_cgroup_zoneinfo(memcg, nid, zid);
+		excess = res_counter_soft_limit_excess(&memcg->res);
+		/*
+		 * We have to update the tree if mz is on RB-tree or
+		 * mem is over its softlimit.
+		 */
+		if (excess || mz->on_tree) {
+			spin_lock(&mctz->lock);
+			/* if on-tree, remove it */
+			if (mz->on_tree)
+				__mem_cgroup_remove_exceeded(memcg, mz, mctz);
+			/*
+			 * Insert again. mz->usage_in_excess will be updated.
+			 * If excess is 0, no tree ops.
+			 */
+			__mem_cgroup_insert_exceeded(memcg, mz, mctz, excess);
+			spin_unlock(&mctz->lock);
+		}
+	}
+}
+
+static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
+{
+	int node, zone;
+	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup_tree_per_zone *mctz;
+
+	for_each_node(node) {
+		for (zone = 0; zone < MAX_NR_ZONES; zone++) {
+			mz = mem_cgroup_zoneinfo(memcg, node, zone);
+			mctz = soft_limit_tree_node_zone(node, zone);
+			mem_cgroup_remove_exceeded(memcg, mz, mctz);
+		}
+	}
+}
+
+static struct mem_cgroup_per_zone *
+__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
+{
+	struct rb_node *rightmost = NULL;
+	struct mem_cgroup_per_zone *mz;
+
+retry:
+	mz = NULL;
+	rightmost = rb_last(&mctz->rb_root);
+	if (!rightmost)
+		goto done;		/* Nothing to reclaim from */
+
+	mz = rb_entry(rightmost, struct mem_cgroup_per_zone, tree_node);
+	/*
+	 * Remove the node now but someone else can add it back,
+	 * we will to add it back at the end of reclaim to its correct
+	 * position in the tree.
+	 */
+	__mem_cgroup_remove_exceeded(mz->memcg, mz, mctz);
+	if (!res_counter_soft_limit_excess(&mz->memcg->res) ||
+		!css_tryget(&mz->memcg->css))
+		goto retry;
+done:
+	return mz;
+}
+
+static struct mem_cgroup_per_zone *
+mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
+{
+	struct mem_cgroup_per_zone *mz;
+
+	spin_lock(&mctz->lock);
+	mz = __mem_cgroup_largest_soft_limit_node(mctz);
+	spin_unlock(&mctz->lock);
+	return mz;
+}
+
 /*
  * Implementation Note: reading percpu statistics for memcg.
  *
@@ -822,48 +990,6 @@ static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg,
 }
 
 /*
- * Called from rate-limited memcg_check_events when enough
- * MEM_CGROUP_TARGET_SOFTLIMIT events are accumulated and it makes sure
- * that all the parents up the hierarchy will be notified that this group
- * is in excess or that it is not in excess anymore. mmecg->soft_contributed
- * makes the transition a single action whenever the state flips from one to
- * the other.
- */
-static void mem_cgroup_update_soft_limit(struct mem_cgroup *memcg)
-{
-	unsigned long long excess = res_counter_soft_limit_excess(&memcg->res);
-	struct mem_cgroup *parent = memcg;
-	int delta = 0;
-
-	spin_lock(&memcg->soft_lock);
-	if (excess) {
-		if (!memcg->soft_contributed) {
-			delta = 1;
-			memcg->soft_contributed = true;
-		}
-	} else {
-		if (memcg->soft_contributed) {
-			delta = -1;
-			memcg->soft_contributed = false;
-		}
-	}
-
-	/*
-	 * Necessary to update all ancestors when hierarchy is used
-	 * because their event counter is not touched.
-	 * We track children even outside the hierarchy for the root
-	 * cgroup because tree walk starting at root should visit
-	 * all cgroups and we want to prevent from pointless tree
-	 * walk if no children is below the limit.
-	 */
-	while (delta && (parent = parent_mem_cgroup(parent)))
-		atomic_add(delta, &parent->children_in_excess);
-	if (memcg != root_mem_cgroup && !root_mem_cgroup->use_hierarchy)
-		atomic_add(delta, &root_mem_cgroup->children_in_excess);
-	spin_unlock(&memcg->soft_lock);
-}
-
-/*
  * Check events in order.
  *
  */
@@ -886,7 +1012,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
 
 		mem_cgroup_threshold(memcg);
 		if (unlikely(do_softlimit))
-			mem_cgroup_update_soft_limit(memcg);
+			mem_cgroup_update_tree(memcg, page);
 #if MAX_NUMNODES > 1
 		if (unlikely(do_numainfo))
 			atomic_inc(&memcg->numainfo_events);
@@ -929,15 +1055,6 @@ struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
 	return memcg;
 }
 
-static enum mem_cgroup_filter_t
-mem_cgroup_filter(struct mem_cgroup *memcg, struct mem_cgroup *root,
-		mem_cgroup_iter_filter cond)
-{
-	if (!cond)
-		return VISIT;
-	return cond(memcg, root);
-}
-
 /*
  * Returns a next (in a pre-order walk) alive memcg (with elevated css
  * ref. count) or NULL if the whole root's subtree has been visited.
@@ -945,7 +1062,7 @@ mem_cgroup_filter(struct mem_cgroup *memcg, struct mem_cgroup *root,
  * helper function to be used by mem_cgroup_iter
  */
 static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root,
-		struct mem_cgroup *last_visited, mem_cgroup_iter_filter cond)
+		struct mem_cgroup *last_visited)
 {
 	struct cgroup_subsys_state *prev_css, *next_css;
 
@@ -963,31 +1080,11 @@ skip_node:
 	if (next_css) {
 		struct mem_cgroup *mem = mem_cgroup_from_css(next_css);
 
-		switch (mem_cgroup_filter(mem, root, cond)) {
-		case SKIP:
+		if (css_tryget(&mem->css))
+			return mem;
+		else {
 			prev_css = next_css;
 			goto skip_node;
-		case SKIP_TREE:
-			if (mem == root)
-				return NULL;
-			/*
-			 * css_rightmost_descendant is not an optimal way to
-			 * skip through a subtree (especially for imbalanced
-			 * trees leaning to right) but that's what we have right
-			 * now. More effective solution would be traversing
-			 * right-up for first non-NULL without calling
-			 * css_next_descendant_pre afterwards.
-			 */
-			prev_css = css_rightmost_descendant(next_css);
-			goto skip_node;
-		case VISIT:
-			if (css_tryget(&mem->css))
-				return mem;
-			else {
-				prev_css = next_css;
-				goto skip_node;
-			}
-			break;
 		}
 	}
 
@@ -1051,7 +1148,6 @@ static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter,
  * @root: hierarchy root
  * @prev: previously returned memcg, NULL on first invocation
  * @reclaim: cookie for shared reclaim walks, NULL for full walks
- * @cond: filter for visited nodes, NULL for no filter
  *
  * Returns references to children of the hierarchy below @root, or
  * @root itself, or %NULL after a full round-trip.
@@ -1064,18 +1160,15 @@ static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter,
  * divide up the memcgs in the hierarchy among all concurrent
  * reclaimers operating on the same zone and priority.
  */
-struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root,
+struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 				   struct mem_cgroup *prev,
-				   struct mem_cgroup_reclaim_cookie *reclaim,
-				   mem_cgroup_iter_filter cond)
+				   struct mem_cgroup_reclaim_cookie *reclaim)
 {
 	struct mem_cgroup *memcg = NULL;
 	struct mem_cgroup *last_visited = NULL;
 
-	if (mem_cgroup_disabled()) {
-		/* first call must return non-NULL, second return NULL */
-		return (struct mem_cgroup *)(unsigned long)!prev;
-	}
+	if (mem_cgroup_disabled())
+		return NULL;
 
 	if (!root)
 		root = root_mem_cgroup;
@@ -1086,9 +1179,7 @@ struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root,
 	if (!root->use_hierarchy && root != root_mem_cgroup) {
 		if (prev)
 			goto out_css_put;
-		if (mem_cgroup_filter(root, root, cond) == VISIT)
-			return root;
-		return NULL;
+		return root;
 	}
 
 	rcu_read_lock();
@@ -1111,7 +1202,7 @@ struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root,
 			last_visited = mem_cgroup_iter_load(iter, root, &seq);
 		}
 
-		memcg = __mem_cgroup_iter_next(root, last_visited, cond);
+		memcg = __mem_cgroup_iter_next(root, last_visited);
 
 		if (reclaim) {
 			mem_cgroup_iter_update(iter, last_visited, memcg, seq);
@@ -1122,11 +1213,7 @@ struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root,
 				reclaim->generation = iter->generation;
 		}
 
-		/*
-		 * We have finished the whole tree walk or no group has been
-		 * visited because filter told us to skip the root node.
-		 */
-		if (!memcg && (prev || (cond && !last_visited)))
+		if (prev && !memcg)
 			goto out_unlock;
 	}
 out_unlock:
@@ -1767,7 +1854,6 @@ static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg,
 	return total;
 }
 
-#if MAX_NUMNODES > 1
 /**
  * test_mem_cgroup_node_reclaimable
  * @memcg: the target memcg
@@ -1790,6 +1876,7 @@ static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *memcg,
 	return false;
 
 }
+#if MAX_NUMNODES > 1
 
 /*
  * Always updating the nodemask is not very good - even if we have an empty
@@ -1857,50 +1944,104 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
 	return node;
 }
 
+/*
+ * Check all nodes whether it contains reclaimable pages or not.
+ * For quick scan, we make use of scan_nodes. This will allow us to skip
+ * unused nodes. But scan_nodes is lazily updated and may not cotain
+ * enough new information. We need to do double check.
+ */
+static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap)
+{
+	int nid;
+
+	/*
+	 * quick check...making use of scan_node.
+	 * We can skip unused nodes.
+	 */
+	if (!nodes_empty(memcg->scan_nodes)) {
+		for (nid = first_node(memcg->scan_nodes);
+		     nid < MAX_NUMNODES;
+		     nid = next_node(nid, memcg->scan_nodes)) {
+
+			if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap))
+				return true;
+		}
+	}
+	/*
+	 * Check rest of nodes.
+	 */
+	for_each_node_state(nid, N_MEMORY) {
+		if (node_isset(nid, memcg->scan_nodes))
+			continue;
+		if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap))
+			return true;
+	}
+	return false;
+}
+
 #else
 int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
 {
 	return 0;
 }
 
-#endif
-
-/*
- * A group is eligible for the soft limit reclaim under the given root
- * hierarchy if
- *	a) it is over its soft limit
- *	b) any parent up the hierarchy is over its soft limit
- *
- * If the given group doesn't have any children over the limit then it
- * doesn't make any sense to iterate its subtree.
- */
-enum mem_cgroup_filter_t
-mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg,
-		struct mem_cgroup *root)
+static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap)
 {
-	struct mem_cgroup *parent;
-
-	if (!memcg)
-		memcg = root_mem_cgroup;
-	parent = memcg;
-
-	if (res_counter_soft_limit_excess(&memcg->res))
-		return VISIT;
+	return test_mem_cgroup_node_reclaimable(memcg, 0, noswap);
+}
+#endif
 
-	/*
-	 * If any parent up to the root in the hierarchy is over its soft limit
-	 * then we have to obey and reclaim from this group as well.
-	 */
-	while ((parent = parent_mem_cgroup(parent))) {
-		if (res_counter_soft_limit_excess(&parent->res))
-			return VISIT;
-		if (parent == root)
+static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
+				   struct zone *zone,
+				   gfp_t gfp_mask,
+				   unsigned long *total_scanned)
+{
+	struct mem_cgroup *victim = NULL;
+	int total = 0;
+	int loop = 0;
+	unsigned long excess;
+	unsigned long nr_scanned;
+	struct mem_cgroup_reclaim_cookie reclaim = {
+		.zone = zone,
+		.priority = 0,
+	};
+
+	excess = res_counter_soft_limit_excess(&root_memcg->res) >> PAGE_SHIFT;
+
+	while (1) {
+		victim = mem_cgroup_iter(root_memcg, victim, &reclaim);
+		if (!victim) {
+			loop++;
+			if (loop >= 2) {
+				/*
+				 * If we have not been able to reclaim
+				 * anything, it might because there are
+				 * no reclaimable pages under this hierarchy
+				 */
+				if (!total)
+					break;
+				/*
+				 * We want to do more targeted reclaim.
+				 * excess >> 2 is not to excessive so as to
+				 * reclaim too much, nor too less that we keep
+				 * coming back to reclaim from this cgroup
+				 */
+				if (total >= (excess >> 2) ||
+					(loop > MEM_CGROUP_MAX_RECLAIM_LOOPS))
+					break;
+			}
+			continue;
+		}
+		if (!mem_cgroup_reclaimable(victim, false))
+			continue;
+		total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false,
+						     zone, &nr_scanned);
+		*total_scanned += nr_scanned;
+		if (!res_counter_soft_limit_excess(&root_memcg->res))
 			break;
 	}
-
-	if (!atomic_read(&memcg->children_in_excess))
-		return SKIP_TREE;
-	return SKIP;
+	mem_cgroup_iter_break(root_memcg, victim);
+	return total;
 }
 
 static DEFINE_SPINLOCK(memcg_oom_lock);
@@ -2812,7 +2953,9 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 	unlock_page_cgroup(pc);
 
 	/*
-	 * "charge_statistics" updated event counter.
+	 * "charge_statistics" updated event counter. Then, check it.
+	 * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree.
+	 * if they exceeds softlimit.
 	 */
 	memcg_check_events(memcg, page);
 }
@@ -4647,6 +4790,98 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
 	return ret;
 }
 
+unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+					    gfp_t gfp_mask,
+					    unsigned long *total_scanned)
+{
+	unsigned long nr_reclaimed = 0;
+	struct mem_cgroup_per_zone *mz, *next_mz = NULL;
+	unsigned long reclaimed;
+	int loop = 0;
+	struct mem_cgroup_tree_per_zone *mctz;
+	unsigned long long excess;
+	unsigned long nr_scanned;
+
+	if (order > 0)
+		return 0;
+
+	mctz = soft_limit_tree_node_zone(zone_to_nid(zone), zone_idx(zone));
+	/*
+	 * This loop can run a while, specially if mem_cgroup's continuously
+	 * keep exceeding their soft limit and putting the system under
+	 * pressure
+	 */
+	do {
+		if (next_mz)
+			mz = next_mz;
+		else
+			mz = mem_cgroup_largest_soft_limit_node(mctz);
+		if (!mz)
+			break;
+
+		nr_scanned = 0;
+		reclaimed = mem_cgroup_soft_reclaim(mz->memcg, zone,
+						    gfp_mask, &nr_scanned);
+		nr_reclaimed += reclaimed;
+		*total_scanned += nr_scanned;
+		spin_lock(&mctz->lock);
+
+		/*
+		 * If we failed to reclaim anything from this memory cgroup
+		 * it is time to move on to the next cgroup
+		 */
+		next_mz = NULL;
+		if (!reclaimed) {
+			do {
+				/*
+				 * Loop until we find yet another one.
+				 *
+				 * By the time we get the soft_limit lock
+				 * again, someone might have aded the
+				 * group back on the RB tree. Iterate to
+				 * make sure we get a different mem.
+				 * mem_cgroup_largest_soft_limit_node returns
+				 * NULL if no other cgroup is present on
+				 * the tree
+				 */
+				next_mz =
+				__mem_cgroup_largest_soft_limit_node(mctz);
+				if (next_mz == mz)
+					css_put(&next_mz->memcg->css);
+				else /* next_mz == NULL or other memcg */
+					break;
+			} while (1);
+		}
+		__mem_cgroup_remove_exceeded(mz->memcg, mz, mctz);
+		excess = res_counter_soft_limit_excess(&mz->memcg->res);
+		/*
+		 * One school of thought says that we should not add
+		 * back the node to the tree if reclaim returns 0.
+		 * But our reclaim could return 0, simply because due
+		 * to priority we are exposing a smaller subset of
+		 * memory to reclaim from. Consider this as a longer
+		 * term TODO.
+		 */
+		/* If excess == 0, no tree ops */
+		__mem_cgroup_insert_exceeded(mz->memcg, mz, mctz, excess);
+		spin_unlock(&mctz->lock);
+		css_put(&mz->memcg->css);
+		loop++;
+		/*
+		 * Could not reclaim anything and there are no more
+		 * mem cgroups to try or we seem to be looping without
+		 * reclaiming anything.
+		 */
+		if (!nr_reclaimed &&
+			(next_mz == NULL ||
+			loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS))
+			break;
+	} while (!nr_reclaimed);
+	if (next_mz)
+		css_put(&next_mz->memcg->css);
+	return nr_reclaimed;
+}
+
 /**
  * mem_cgroup_force_empty_list - clears LRU of a group
  * @memcg: group to clear
@@ -5911,6 +6146,8 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 	for (zone = 0; zone < MAX_NR_ZONES; zone++) {
 		mz = &pn->zoneinfo[zone];
 		lruvec_init(&mz->lruvec);
+		mz->usage_in_excess = 0;
+		mz->on_tree = false;
 		mz->memcg = memcg;
 	}
 	memcg->nodeinfo[node] = pn;
@@ -5966,6 +6203,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 	int node;
 	size_t size = memcg_size();
 
+	mem_cgroup_remove_from_trees(memcg);
 	free_css_id(&mem_cgroup_subsys, &memcg->css);
 
 	for_each_node(node)
@@ -6002,6 +6240,29 @@ struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 }
 EXPORT_SYMBOL(parent_mem_cgroup);
 
+static void __init mem_cgroup_soft_limit_tree_init(void)
+{
+	struct mem_cgroup_tree_per_node *rtpn;
+	struct mem_cgroup_tree_per_zone *rtpz;
+	int tmp, node, zone;
+
+	for_each_node(node) {
+		tmp = node;
+		if (!node_state(node, N_NORMAL_MEMORY))
+			tmp = -1;
+		rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp);
+		BUG_ON(!rtpn);
+
+		soft_limit_tree.rb_tree_per_node[node] = rtpn;
+
+		for (zone = 0; zone < MAX_NR_ZONES; zone++) {
+			rtpz = &rtpn->rb_tree_per_zone[zone];
+			rtpz->rb_root = RB_ROOT;
+			spin_lock_init(&rtpz->lock);
+		}
+	}
+}
+
 static struct cgroup_subsys_state * __ref
 mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 {
@@ -6031,7 +6292,6 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	mutex_init(&memcg->thresholds_lock);
 	spin_lock_init(&memcg->move_lock);
 	vmpressure_init(&memcg->vmpressure);
-	spin_lock_init(&memcg->soft_lock);
 
 	return &memcg->css;
 
@@ -6109,13 +6369,6 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 
 	mem_cgroup_invalidate_reclaim_iterators(memcg);
 	mem_cgroup_reparent_charges(memcg);
-	if (memcg->soft_contributed) {
-		while ((memcg = parent_mem_cgroup(memcg)))
-			atomic_dec(&memcg->children_in_excess);
-
-		if (memcg != root_mem_cgroup && !root_mem_cgroup->use_hierarchy)
-			atomic_dec(&root_mem_cgroup->children_in_excess);
-	}
 	mem_cgroup_destroy_all_caches(memcg);
 	vmpressure_cleanup(&memcg->vmpressure);
 }
@@ -6790,6 +7043,7 @@ static int __init mem_cgroup_init(void)
 {
 	hotcpu_notifier(memcg_cpu_hotplug_callback, 0);
 	enable_swap_cgroup();
+	mem_cgroup_soft_limit_tree_init();
 	memcg_stock_init();
 	return 0;
 }
diff --git a/mm/mlock.c b/mm/mlock.c
index d63802663242..67ba6da7d0e3 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -736,6 +736,7 @@ static int do_mlockall(int flags)
 
 		/* Ignore errors */
 		mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
+		cond_resched();
 	}
 out:
 	return 0;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8ed1b775bdc9..beb35778c69f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -139,23 +139,11 @@ static bool global_reclaim(struct scan_control *sc)
 {
 	return !sc->target_mem_cgroup;
 }
-
-static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc)
-{
-	struct mem_cgroup *root = sc->target_mem_cgroup;
-	return !mem_cgroup_disabled() &&
-		mem_cgroup_soft_reclaim_eligible(root, root) != SKIP_TREE;
-}
 #else
 static bool global_reclaim(struct scan_control *sc)
 {
 	return true;
 }
-
-static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc)
-{
-	return false;
-}
 #endif
 
 unsigned long zone_reclaimable_pages(struct zone *zone)
@@ -2176,11 +2164,9 @@ static inline bool should_continue_reclaim(struct zone *zone,
 	}
 }
 
-static int
-__shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
+static void shrink_zone(struct zone *zone, struct scan_control *sc)
 {
 	unsigned long nr_reclaimed, nr_scanned;
-	int groups_scanned = 0;
 
 	do {
 		struct mem_cgroup *root = sc->target_mem_cgroup;
@@ -2188,17 +2174,15 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
 			.zone = zone,
 			.priority = sc->priority,
 		};
-		struct mem_cgroup *memcg = NULL;
-		mem_cgroup_iter_filter filter = (soft_reclaim) ?
-			mem_cgroup_soft_reclaim_eligible : NULL;
+		struct mem_cgroup *memcg;
 
 		nr_reclaimed = sc->nr_reclaimed;
 		nr_scanned = sc->nr_scanned;
 
-		while ((memcg = mem_cgroup_iter_cond(root, memcg, &reclaim, filter))) {
+		memcg = mem_cgroup_iter(root, NULL, &reclaim);
+		do {
 			struct lruvec *lruvec;
 
-			groups_scanned++;
 			lruvec = mem_cgroup_zone_lruvec(zone, memcg);
 
 			shrink_lruvec(lruvec, sc);
@@ -2218,7 +2202,8 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
 				mem_cgroup_iter_break(root, memcg);
 				break;
 			}
-		}
+			memcg = mem_cgroup_iter(root, memcg, &reclaim);
+		} while (memcg);
 
 		vmpressure(sc->gfp_mask, sc->target_mem_cgroup,
 			   sc->nr_scanned - nr_scanned,
@@ -2226,37 +2211,6 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
 
 	} while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed,
 					 sc->nr_scanned - nr_scanned, sc));
-
-	return groups_scanned;
-}
-
-
-static void shrink_zone(struct zone *zone, struct scan_control *sc)
-{
-	bool do_soft_reclaim = mem_cgroup_should_soft_reclaim(sc);
-	unsigned long nr_scanned = sc->nr_scanned;
-	int scanned_groups;
-
-	scanned_groups = __shrink_zone(zone, sc, do_soft_reclaim);
-	/*
-	 * memcg iterator might race with other reclaimer or start from
-	 * a incomplete tree walk so the tree walk in __shrink_zone
-	 * might have missed groups that are above the soft limit. Try
-	 * another loop to catch up with others. Do it just once to
-	 * prevent from reclaim latencies when other reclaimers always
-	 * preempt this one.
-	 */
-	if (do_soft_reclaim && !scanned_groups)
-		__shrink_zone(zone, sc, do_soft_reclaim);
-
-	/*
-	 * No group is over the soft limit or those that are do not have
-	 * pages in the zone we are reclaiming so we have to reclaim everybody
-	 */
-	if (do_soft_reclaim && (sc->nr_scanned == nr_scanned)) {
-		__shrink_zone(zone, sc, false);
-		return;
-	}
 }
 
 /* Returns true if compaction should go ahead for a high-order request */
@@ -2320,6 +2274,8 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 {
 	struct zoneref *z;
 	struct zone *zone;
+	unsigned long nr_soft_reclaimed;
+	unsigned long nr_soft_scanned;
 	bool aborted_reclaim = false;
 
 	/*
@@ -2359,6 +2315,18 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 					continue;
 				}
 			}
+			/*
+			 * This steals pages from memory cgroups over softlimit
+			 * and returns the number of reclaimed pages and
+			 * scanned pages. This works for global memory pressure
+			 * and balancing, not for a memcg's limit.
+			 */
+			nr_soft_scanned = 0;
+			nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
+						sc->order, sc->gfp_mask,
+						&nr_soft_scanned);
+			sc->nr_reclaimed += nr_soft_reclaimed;
+			sc->nr_scanned += nr_soft_scanned;
 			/* need some check for avoid more shrink_zone() */
 		}
 
@@ -2952,6 +2920,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 {
 	int i;
 	int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
+	unsigned long nr_soft_reclaimed;
+	unsigned long nr_soft_scanned;
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
 		.priority = DEF_PRIORITY,
@@ -3066,6 +3036,15 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 
 			sc.nr_scanned = 0;
 
+			nr_soft_scanned = 0;
+			/*
+			 * Call soft limit reclaim before calling shrink_zone.
+			 */
+			nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
+							order, sc.gfp_mask,
+							&nr_soft_scanned);
+			sc.nr_reclaimed += nr_soft_reclaimed;
+
 			/*
 			 * There should be no need to raise the scanning
 			 * priority if enough pages are already being scanned
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 47016c304c84..66cad506b8a2 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -3975,8 +3975,8 @@ sub string_find_replace {
 # check for new externs in .h files.
 		if ($realfile =~ /\.h$/ &&
 		    $line =~ /^\+\s*(extern\s+)$Type\s*$Ident\s*\(/s) {
-			if (WARN("AVOID_EXTERNS",
-				 "extern prototypes should be avoided in .h files\n" . $herecurr) &&
+			if (CHK("AVOID_EXTERNS",
+				"extern prototypes should be avoided in .h files\n" . $herecurr) &&
 			    $fix) {
 				$fixed[$linenr - 1] =~ s/(.*)\bextern\b\s*(.*)/$1$2/;
 			}
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index 98969541cbcc..bea523a5d852 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -139,6 +139,18 @@ static int snd_compr_open(struct inode *inode, struct file *f)
 static int snd_compr_free(struct inode *inode, struct file *f)
 {
 	struct snd_compr_file *data = f->private_data;
+	struct snd_compr_runtime *runtime = data->stream.runtime;
+
+	switch (runtime->state) {
+	case SNDRV_PCM_STATE_RUNNING:
+	case SNDRV_PCM_STATE_DRAINING:
+	case SNDRV_PCM_STATE_PAUSED:
+		data->stream.ops->trigger(&data->stream, SNDRV_PCM_TRIGGER_STOP);
+		break;
+	default:
+		break;
+	}
+
 	data->stream.ops->free(&data->stream);
 	kfree(data->stream.runtime->buffer);
 	kfree(data->stream.runtime);
@@ -837,7 +849,8 @@ static int snd_compress_dev_disconnect(struct snd_device *device)
 	struct snd_compr *compr;
 
 	compr = device->device_data;
-	snd_unregister_device(compr->direction, compr->card, compr->device);
+	snd_unregister_device(SNDRV_DEVICE_TYPE_COMPRESS, compr->card,
+		compr->device);
 	return 0;
 }
 
diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c
index b524f89a1f13..18d972501585 100644
--- a/sound/pci/hda/patch_cirrus.c
+++ b/sound/pci/hda/patch_cirrus.c
@@ -111,6 +111,9 @@ enum {
 /* 0x0009 - 0x0014 -> 12 test regs */
 /* 0x0015 - visibility reg */
 
+/* Cirrus Logic CS4208 */
+#define CS4208_VENDOR_NID	0x24
+
 /*
  * Cirrus Logic CS4210
  *
@@ -223,6 +226,16 @@ static const struct hda_verb cs_coef_init_verbs[] = {
 	{} /* terminator */
 };
 
+static const struct hda_verb cs4208_coef_init_verbs[] = {
+	{0x01, AC_VERB_SET_POWER_STATE, 0x00}, /* AFG: D0 */
+	{0x24, AC_VERB_SET_PROC_STATE, 0x01},  /* VPW: processing on */
+	{0x24, AC_VERB_SET_COEF_INDEX, 0x0033},
+	{0x24, AC_VERB_SET_PROC_COEF, 0x0001}, /* A1 ICS */
+	{0x24, AC_VERB_SET_COEF_INDEX, 0x0034},
+	{0x24, AC_VERB_SET_PROC_COEF, 0x1C01}, /* A1 Enable, A Thresh = 300mV */
+	{} /* terminator */
+};
+
 /* Errata: CS4207 rev C0/C1/C2 Silicon
  *
  * http://www.cirrus.com/en/pubs/errata/ER880C3.pdf
@@ -295,6 +308,8 @@ static int cs_init(struct hda_codec *codec)
 		/* init_verb sequence for C0/C1/C2 errata*/
 		snd_hda_sequence_write(codec, cs_errata_init_verbs);
 		snd_hda_sequence_write(codec, cs_coef_init_verbs);
+	} else if (spec->vendor_nid == CS4208_VENDOR_NID) {
+		snd_hda_sequence_write(codec, cs4208_coef_init_verbs);
 	}
 
 	snd_hda_gen_init(codec);
@@ -434,6 +449,29 @@ static const struct hda_pintbl mba42_pincfgs[] = {
 	{} /* terminator */
 };
 
+static const struct hda_pintbl mba6_pincfgs[] = {
+	{ 0x10, 0x032120f0 }, /* HP */
+	{ 0x11, 0x500000f0 },
+	{ 0x12, 0x90100010 }, /* Speaker */
+	{ 0x13, 0x500000f0 },
+	{ 0x14, 0x500000f0 },
+	{ 0x15, 0x770000f0 },
+	{ 0x16, 0x770000f0 },
+	{ 0x17, 0x430000f0 },
+	{ 0x18, 0x43ab9030 }, /* Mic */
+	{ 0x19, 0x770000f0 },
+	{ 0x1a, 0x770000f0 },
+	{ 0x1b, 0x770000f0 },
+	{ 0x1c, 0x90a00090 },
+	{ 0x1d, 0x500000f0 },
+	{ 0x1e, 0x500000f0 },
+	{ 0x1f, 0x500000f0 },
+	{ 0x20, 0x500000f0 },
+	{ 0x21, 0x430000f0 },
+	{ 0x22, 0x430000f0 },
+	{} /* terminator */
+};
+
 static void cs420x_fixup_gpio_13(struct hda_codec *codec,
 				 const struct hda_fixup *fix, int action)
 {
@@ -556,22 +594,23 @@ static int patch_cs420x(struct hda_codec *codec)
 
 /*
  * CS4208 support:
- * Its layout is no longer compatible with CS4206/CS4207, and the generic
- * parser seems working fairly well, except for trivial fixups.
+ * Its layout is no longer compatible with CS4206/CS4207
  */
 enum {
+	CS4208_MBA6,
 	CS4208_GPIO0,
 };
 
 static const struct hda_model_fixup cs4208_models[] = {
 	{ .id = CS4208_GPIO0, .name = "gpio0" },
+	{ .id = CS4208_MBA6, .name = "mba6" },
 	{}
 };
 
 static const struct snd_pci_quirk cs4208_fixup_tbl[] = {
 	/* codec SSID */
-	SND_PCI_QUIRK(0x106b, 0x7100, "MacBookPro 6,1", CS4208_GPIO0),
-	SND_PCI_QUIRK(0x106b, 0x7200, "MacBookPro 6,2", CS4208_GPIO0),
+	SND_PCI_QUIRK(0x106b, 0x7100, "MacBookAir 6,1", CS4208_MBA6),
+	SND_PCI_QUIRK(0x106b, 0x7200, "MacBookAir 6,2", CS4208_MBA6),
 	{} /* terminator */
 };
 
@@ -588,18 +627,35 @@ static void cs4208_fixup_gpio0(struct hda_codec *codec,
 }
 
 static const struct hda_fixup cs4208_fixups[] = {
+	[CS4208_MBA6] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = mba6_pincfgs,
+		.chained = true,
+		.chain_id = CS4208_GPIO0,
+	},
 	[CS4208_GPIO0] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = cs4208_fixup_gpio0,
 	},
 };
 
+/* correct the 0dB offset of input pins */
+static void cs4208_fix_amp_caps(struct hda_codec *codec, hda_nid_t adc)
+{
+	unsigned int caps;
+
+	caps = query_amp_caps(codec, adc, HDA_INPUT);
+	caps &= ~(AC_AMPCAP_OFFSET);
+	caps |= 0x02;
+	snd_hda_override_amp_caps(codec, adc, HDA_INPUT, caps);
+}
+
 static int patch_cs4208(struct hda_codec *codec)
 {
 	struct cs_spec *spec;
 	int err;
 
-	spec = cs_alloc_spec(codec, 0); /* no specific w/a */
+	spec = cs_alloc_spec(codec, CS4208_VENDOR_NID);
 	if (!spec)
 		return -ENOMEM;
 
@@ -609,6 +665,12 @@ static int patch_cs4208(struct hda_codec *codec)
 			   cs4208_fixups);
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE);
 
+	snd_hda_override_wcaps(codec, 0x18,
+			       get_wcaps(codec, 0x18) | AC_WCAP_STEREO);
+	cs4208_fix_amp_caps(codec, 0x18);
+	cs4208_fix_amp_caps(codec, 0x1b);
+	cs4208_fix_amp_caps(codec, 0x1c);
+
 	err = cs_parse_auto_config(codec);
 	if (err < 0)
 		goto error;
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 3d8cd04455a6..7ea0245fc6bd 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -1149,32 +1149,43 @@ static int hdmi_choose_cvt(struct hda_codec *codec,
 }
 
 static void haswell_config_cvts(struct hda_codec *codec,
-			int pin_id, int mux_id)
+			hda_nid_t pin_nid, int mux_idx)
 {
 	struct hdmi_spec *spec = codec->spec;
-	struct hdmi_spec_per_pin *per_pin;
-	int pin_idx, mux_idx;
-	int curr;
-	int err;
+	hda_nid_t nid, end_nid;
+	int cvt_idx, curr;
+	struct hdmi_spec_per_cvt *per_cvt;
 
-	for (pin_idx = 0; pin_idx < spec->num_pins; pin_idx++) {
-		per_pin = get_pin(spec, pin_idx);
+	/* configure all pins, including "no physical connection" ones */
+	end_nid = codec->start_nid + codec->num_nodes;
+	for (nid = codec->start_nid; nid < end_nid; nid++) {
+		unsigned int wid_caps = get_wcaps(codec, nid);
+		unsigned int wid_type = get_wcaps_type(wid_caps);
 
-		if (pin_idx == pin_id)
+		if (wid_type != AC_WID_PIN)
 			continue;
 
-		curr = snd_hda_codec_read(codec, per_pin->pin_nid, 0,
+		if (nid == pin_nid)
+			continue;
+
+		curr = snd_hda_codec_read(codec, nid, 0,
 					  AC_VERB_GET_CONNECT_SEL, 0);
+		if (curr != mux_idx)
+			continue;
 
-		/* Choose another unused converter */
-		if (curr == mux_id) {
-			err = hdmi_choose_cvt(codec, pin_idx, NULL, &mux_idx);
-			if (err < 0)
-				return;
-			snd_printdd("HDMI: choose converter %d for pin %d\n", mux_idx, pin_idx);
-			snd_hda_codec_write_cache(codec, per_pin->pin_nid, 0,
+		/* choose an unassigned converter. The conveters in the
+		 * connection list are in the same order as in the codec.
+		 */
+		for (cvt_idx = 0; cvt_idx < spec->num_cvts; cvt_idx++) {
+			per_cvt = get_cvt(spec, cvt_idx);
+			if (!per_cvt->assigned) {
+				snd_printdd("choose cvt %d for pin nid %d\n",
+					cvt_idx, nid);
+				snd_hda_codec_write_cache(codec, nid, 0,
 					    AC_VERB_SET_CONNECT_SEL,
-					    mux_idx);
+					    cvt_idx);
+				break;
+			}
 		}
 	}
 }
@@ -1216,7 +1227,7 @@ static int hdmi_pcm_open(struct hda_pcm_stream *hinfo,
 
 	/* configure unused pins to choose other converters */
 	if (is_haswell(codec))
-		haswell_config_cvts(codec, pin_idx, mux_idx);
+		haswell_config_cvts(codec, per_pin->pin_nid, mux_idx);
 
 	snd_hda_spdif_ctls_assign(codec, pin_idx, per_cvt->cvt_nid);
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index bc07d369fac4..0e303b99a47c 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -3439,6 +3439,9 @@ static void alc283_fixup_chromebook(struct hda_codec *codec,
 		/* Set to manual mode */
 		val = alc_read_coef_idx(codec, 0x06);
 		alc_write_coef_idx(codec, 0x06, val & ~0x000c);
+		/* Enable Line1 input control by verb */
+		val = alc_read_coef_idx(codec, 0x1a);
+		alc_write_coef_idx(codec, 0x1a, val | (1 << 4));
 		break;
 	}
 }
@@ -3531,6 +3534,7 @@ enum {
 	ALC269VB_FIXUP_ORDISSIMO_EVE2,
 	ALC283_FIXUP_CHROME_BOOK,
 	ALC282_FIXUP_ASUS_TX300,
+	ALC283_FIXUP_INT_MIC,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -3790,6 +3794,16 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc282_fixup_asus_tx300,
 	},
+	[ALC283_FIXUP_INT_MIC] = {
+		.type = HDA_FIXUP_VERBS,
+		.v.verbs = (const struct hda_verb[]) {
+			{0x20, AC_VERB_SET_COEF_INDEX, 0x1a},
+			{0x20, AC_VERB_SET_PROC_COEF, 0x0011},
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_LIMIT_INT_MIC_BOOST
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -3874,7 +3888,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x2214, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x2215, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
-	SND_PCI_QUIRK(0x17aa, 0x501a, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x17aa, 0x501a, "Thinkpad", ALC283_FIXUP_INT_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x5026, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K),
diff --git a/tools/lib/lk/debugfs.c b/tools/lib/lk/debugfs.c
index 099e7cd022e4..7c4347962353 100644
--- a/tools/lib/lk/debugfs.c
+++ b/tools/lib/lk/debugfs.c
@@ -5,7 +5,6 @@
 #include <stdbool.h>
 #include <sys/vfs.h>
 #include <sys/mount.h>
-#include <linux/magic.h>
 #include <linux/kernel.h>
 
 #include "debugfs.h"
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index 9570c2b0f83c..b2519e49424f 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -32,7 +32,7 @@ u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
 int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
 			     struct perf_tsc_conversion *tc)
 {
-	bool cap_usr_time_zero;
+	bool cap_user_time_zero;
 	u32 seq;
 	int i = 0;
 
@@ -42,7 +42,7 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
 		tc->time_mult = pc->time_mult;
 		tc->time_shift = pc->time_shift;
 		tc->time_zero = pc->time_zero;
-		cap_usr_time_zero = pc->cap_usr_time_zero;
+		cap_user_time_zero = pc->cap_user_time_zero;
 		rmb();
 		if (pc->lock == seq && !(seq & 1))
 			break;
@@ -52,7 +52,7 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
 		}
 	}
 
-	if (!cap_usr_time_zero)
+	if (!cap_user_time_zero)
 		return -EOPNOTSUPP;
 
 	return 0;
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 423875c999b2..afe377b2884f 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -321,8 +321,6 @@ found:
 	return perf_event__repipe(tool, event_sw, &sample_sw, machine);
 }
 
-extern volatile int session_done;
-
 static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index c2dff9cb1f2c..9b5f077fee5b 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -101,7 +101,7 @@ static int setup_cpunode_map(void)
 
 	dir1 = opendir(PATH_SYS_NODE);
 	if (!dir1)
-		return -1;
+		return 0;
 
 	while ((dent1 = readdir(dir1)) != NULL) {
 		if (dent1->d_type != DT_DIR ||
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8e50d8d77419..72eae7498c09 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -401,8 +401,6 @@ static int perf_report__setup_sample_type(struct perf_report *rep)
 	return 0;
 }
 
-extern volatile int session_done;
-
 static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
@@ -568,6 +566,9 @@ static int __cmd_report(struct perf_report *rep)
 		}
 	}
 
+	if (session_done())
+		return 0;
+
 	if (nr_samples == 0) {
 		ui__error("The %s file has no samples!\n", session->filename);
 		return 0;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 7f31a3ded1b6..9c333ff3dfeb 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -553,8 +553,6 @@ static struct perf_tool perf_script = {
 	.ordering_requires_timestamps = true,
 };
 
-extern volatile int session_done;
-
 static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index f5aa6375e3e9..71aa3e35406b 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -16,6 +16,23 @@
 #include <sys/mman.h>
 #include <linux/futex.h>
 
+/* For older distros: */
+#ifndef MAP_STACK
+# define MAP_STACK		0x20000
+#endif
+
+#ifndef MADV_HWPOISON
+# define MADV_HWPOISON		100
+#endif
+
+#ifndef MADV_MERGEABLE
+# define MADV_MERGEABLE		12
+#endif
+
+#ifndef MADV_UNMERGEABLE
+# define MADV_UNMERGEABLE	13
+#endif
+
 static size_t syscall_arg__scnprintf_hex(char *bf, size_t size,
 					 unsigned long arg,
 					 u8 arg_idx __maybe_unused,
@@ -1038,6 +1055,7 @@ static int trace__replay(struct trace *trace)
 
 	trace->tool.sample	  = trace__process_sample;
 	trace->tool.mmap	  = perf_event__process_mmap;
+	trace->tool.mmap2	  = perf_event__process_mmap2;
 	trace->tool.comm	  = perf_event__process_comm;
 	trace->tool.exit	  = perf_event__process_exit;
 	trace->tool.fork	  = perf_event__process_fork;
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 214e17e97e5c..5f6f9b3271bb 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -87,7 +87,7 @@ CFLAGS += -Wall
 CFLAGS += -Wextra
 CFLAGS += -std=gnu99
 
-EXTLIBS = -lelf -lpthread -lrt -lm
+EXTLIBS = -lelf -lpthread -lrt -lm -ldl
 
 ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -fstack-protector-all,-fstack-protector-all),y)
   CFLAGS += -fstack-protector-all
@@ -180,6 +180,9 @@ FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS)
 ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y)
   CFLAGS += -DLIBELF_MMAP
 endif
+ifeq ($(call try-cc,$(SOURCE_ELF_GETPHDRNUM),$(FLAGS_LIBELF),-DHAVE_ELF_GETPHDRNUM),y)
+  CFLAGS += -DHAVE_ELF_GETPHDRNUM
+endif
 
 # include ARCH specific config
 -include $(src-perf)/arch/$(ARCH)/Makefile
diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak
index 708fb8e9822a..d5a8dd44945f 100644
--- a/tools/perf/config/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -61,6 +61,15 @@ int main(void)
 }
 endef
 
+define SOURCE_ELF_GETPHDRNUM
+#include <libelf.h>
+int main(void)
+{
+	size_t dst;
+	return elf_getphdrnum(0, &dst);
+}
+endef
+
 ifndef NO_SLANG
 define SOURCE_SLANG
 #include <slang.h>
@@ -210,6 +219,7 @@ define SOURCE_LIBAUDIT
 
 int main(void)
 {
+	printf(\"error message: %s\n\", audit_errno_to_name(0));
 	return audit_open();
 }
 endef
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index bfc5a27597d6..7eae5488ecea 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -809,7 +809,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 		    end = map__rip_2objdump(map, sym->end);
 
 		offset = line_ip - start;
-		if (offset < 0 || (u64)line_ip > end)
+		if ((u64)line_ip < start || (u64)line_ip > end)
 			offset = -1;
 		else
 			parsed_line = tmp2 + 1;
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 3e5f5430a28a..e23bde19d590 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -263,6 +263,21 @@ bool die_is_signed_type(Dwarf_Die *tp_die)
 }
 
 /**
+ * die_is_func_def - Ensure that this DIE is a subprogram and definition
+ * @dw_die: a DIE
+ *
+ * Ensure that this DIE is a subprogram and NOT a declaration. This
+ * returns true if @dw_die is a function definition.
+ **/
+bool die_is_func_def(Dwarf_Die *dw_die)
+{
+	Dwarf_Attribute attr;
+
+	return (dwarf_tag(dw_die) == DW_TAG_subprogram &&
+		dwarf_attr(dw_die, DW_AT_declaration, &attr) == NULL);
+}
+
+/**
  * die_get_data_member_location - Get the data-member offset
  * @mb_die: a DIE of a member of a data structure
  * @offs: The offset of the member in the data structure
@@ -392,6 +407,10 @@ static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
 {
 	struct __addr_die_search_param *ad = data;
 
+	/*
+	 * Since a declaration entry doesn't has given pc, this always returns
+	 * function definition entry.
+	 */
 	if (dwarf_tag(fn_die) == DW_TAG_subprogram &&
 	    dwarf_haspc(fn_die, ad->addr)) {
 		memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die));
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index 6ce1717784b7..8658d41697d2 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -38,6 +38,9 @@ extern int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr,
 extern int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr,
 			int (*callback)(Dwarf_Die *, void *), void *data);
 
+/* Ensure that this DIE is a subprogram and definition (not declaration) */
+extern bool die_is_func_def(Dwarf_Die *dw_die);
+
 /* Compare diename and tname */
 extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname);
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 26441d0e571b..ce69901176d8 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -199,9 +199,11 @@ static int write_buildid(char *name, size_t name_len, u8 *build_id,
 	return write_padded(fd, name, name_len + 1, len);
 }
 
-static int __dsos__write_buildid_table(struct list_head *head, pid_t pid,
-				u16 misc, int fd)
+static int __dsos__write_buildid_table(struct list_head *head,
+				       struct machine *machine,
+				       pid_t pid, u16 misc, int fd)
 {
+	char nm[PATH_MAX];
 	struct dso *pos;
 
 	dsos__for_each_with_build_id(pos, head) {
@@ -215,6 +217,10 @@ static int __dsos__write_buildid_table(struct list_head *head, pid_t pid,
 		if (is_vdso_map(pos->short_name)) {
 			name = (char *) VDSO__MAP_NAME;
 			name_len = sizeof(VDSO__MAP_NAME) + 1;
+		} else if (dso__is_kcore(pos)) {
+			machine__mmap_name(machine, nm, sizeof(nm));
+			name = nm;
+			name_len = strlen(nm) + 1;
 		} else {
 			name = pos->long_name;
 			name_len = pos->long_name_len + 1;
@@ -240,10 +246,10 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
 		umisc = PERF_RECORD_MISC_GUEST_USER;
 	}
 
-	err = __dsos__write_buildid_table(&machine->kernel_dsos, machine->pid,
-					  kmisc, fd);
+	err = __dsos__write_buildid_table(&machine->kernel_dsos, machine,
+					  machine->pid, kmisc, fd);
 	if (err == 0)
-		err = __dsos__write_buildid_table(&machine->user_dsos,
+		err = __dsos__write_buildid_table(&machine->user_dsos, machine,
 						  machine->pid, umisc, fd);
 	return err;
 }
@@ -375,23 +381,31 @@ out_free:
 	return err;
 }
 
-static int dso__cache_build_id(struct dso *dso, const char *debugdir)
+static int dso__cache_build_id(struct dso *dso, struct machine *machine,
+			       const char *debugdir)
 {
 	bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
 	bool is_vdso = is_vdso_map(dso->short_name);
+	char *name = dso->long_name;
+	char nm[PATH_MAX];
 
-	return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id),
-				     dso->long_name, debugdir,
-				     is_kallsyms, is_vdso);
+	if (dso__is_kcore(dso)) {
+		is_kallsyms = true;
+		machine__mmap_name(machine, nm, sizeof(nm));
+		name = nm;
+	}
+	return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name,
+				     debugdir, is_kallsyms, is_vdso);
 }
 
-static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
+static int __dsos__cache_build_ids(struct list_head *head,
+				   struct machine *machine, const char *debugdir)
 {
 	struct dso *pos;
 	int err = 0;
 
 	dsos__for_each_with_build_id(pos, head)
-		if (dso__cache_build_id(pos, debugdir))
+		if (dso__cache_build_id(pos, machine, debugdir))
 			err = -1;
 
 	return err;
@@ -399,8 +413,9 @@ static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
 
 static int machine__cache_build_ids(struct machine *machine, const char *debugdir)
 {
-	int ret = __dsos__cache_build_ids(&machine->kernel_dsos, debugdir);
-	ret |= __dsos__cache_build_ids(&machine->user_dsos, debugdir);
+	int ret = __dsos__cache_build_ids(&machine->kernel_dsos, machine,
+					  debugdir);
+	ret |= __dsos__cache_build_ids(&machine->user_dsos, machine, debugdir);
 	return ret;
 }
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 46a0d35a05e1..9ff6cf3e9a99 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -611,6 +611,8 @@ void hists__collapse_resort(struct hists *hists)
 	next = rb_first(root);
 
 	while (next) {
+		if (session_done())
+			break;
 		n = rb_entry(next, struct hist_entry, rb_node_in);
 		next = rb_next(&n->rb_node_in);
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 933d14f287ca..6188d2876a71 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -792,7 +792,7 @@ static int machine__create_modules(struct machine *machine)
 		modules = path;
 	}
 
-	if (symbol__restricted_filename(path, "/proc/modules"))
+	if (symbol__restricted_filename(modules, "/proc/modules"))
 		return -1;
 
 	file = fopen(modules, "r");
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index be0329394d56..371476cb8ddc 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -118,7 +118,6 @@ static const Dwfl_Callbacks offline_callbacks = {
 static int debuginfo__init_offline_dwarf(struct debuginfo *self,
 					 const char *path)
 {
-	Dwfl_Module *mod;
 	int fd;
 
 	fd = open(path, O_RDONLY);
@@ -129,11 +128,11 @@ static int debuginfo__init_offline_dwarf(struct debuginfo *self,
 	if (!self->dwfl)
 		goto error;
 
-	mod = dwfl_report_offline(self->dwfl, "", "", fd);
-	if (!mod)
+	self->mod = dwfl_report_offline(self->dwfl, "", "", fd);
+	if (!self->mod)
 		goto error;
 
-	self->dbg = dwfl_module_getdwarf(mod, &self->bias);
+	self->dbg = dwfl_module_getdwarf(self->mod, &self->bias);
 	if (!self->dbg)
 		goto error;
 
@@ -676,37 +675,42 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
 }
 
 /* Convert subprogram DIE to trace point */
-static int convert_to_trace_point(Dwarf_Die *sp_die, Dwarf_Addr paddr,
-				  bool retprobe, struct probe_trace_point *tp)
+static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
+				  Dwarf_Addr paddr, bool retprobe,
+				  struct probe_trace_point *tp)
 {
 	Dwarf_Addr eaddr, highaddr;
-	const char *name;
-
-	/* Copy the name of probe point */
-	name = dwarf_diename(sp_die);
-	if (name) {
-		if (dwarf_entrypc(sp_die, &eaddr) != 0) {
-			pr_warning("Failed to get entry address of %s\n",
-				   dwarf_diename(sp_die));
-			return -ENOENT;
-		}
-		if (dwarf_highpc(sp_die, &highaddr) != 0) {
-			pr_warning("Failed to get end address of %s\n",
-				   dwarf_diename(sp_die));
-			return -ENOENT;
-		}
-		if (paddr > highaddr) {
-			pr_warning("Offset specified is greater than size of %s\n",
-				   dwarf_diename(sp_die));
-			return -EINVAL;
-		}
-		tp->symbol = strdup(name);
-		if (tp->symbol == NULL)
-			return -ENOMEM;
-		tp->offset = (unsigned long)(paddr - eaddr);
-	} else
-		/* This function has no name. */
-		tp->offset = (unsigned long)paddr;
+	GElf_Sym sym;
+	const char *symbol;
+
+	/* Verify the address is correct */
+	if (dwarf_entrypc(sp_die, &eaddr) != 0) {
+		pr_warning("Failed to get entry address of %s\n",
+			   dwarf_diename(sp_die));
+		return -ENOENT;
+	}
+	if (dwarf_highpc(sp_die, &highaddr) != 0) {
+		pr_warning("Failed to get end address of %s\n",
+			   dwarf_diename(sp_die));
+		return -ENOENT;
+	}
+	if (paddr > highaddr) {
+		pr_warning("Offset specified is greater than size of %s\n",
+			   dwarf_diename(sp_die));
+		return -EINVAL;
+	}
+
+	/* Get an appropriate symbol from symtab */
+	symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
+	if (!symbol) {
+		pr_warning("Failed to find symbol at 0x%lx\n",
+			   (unsigned long)paddr);
+		return -ENOENT;
+	}
+	tp->offset = (unsigned long)(paddr - sym.st_value);
+	tp->symbol = strdup(symbol);
+	if (!tp->symbol)
+		return -ENOMEM;
 
 	/* Return probe must be on the head of a subprogram */
 	if (retprobe) {
@@ -734,7 +738,7 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 	}
 
 	/* If not a real subprogram, find a real one */
-	if (dwarf_tag(sc_die) != DW_TAG_subprogram) {
+	if (!die_is_func_def(sc_die)) {
 		if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
 			pr_warning("Failed to find probe point in any "
 				   "functions.\n");
@@ -980,12 +984,10 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 	struct dwarf_callback_param *param = data;
 	struct probe_finder *pf = param->data;
 	struct perf_probe_point *pp = &pf->pev->point;
-	Dwarf_Attribute attr;
 
 	/* Check tag and diename */
-	if (dwarf_tag(sp_die) != DW_TAG_subprogram ||
-	    !die_compare_name(sp_die, pp->function) ||
-	    dwarf_attr(sp_die, DW_AT_declaration, &attr))
+	if (!die_is_func_def(sp_die) ||
+	    !die_compare_name(sp_die, pp->function))
 		return DWARF_CB_OK;
 
 	/* Check declared file */
@@ -1151,7 +1153,7 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf)
 	tev = &tf->tevs[tf->ntevs++];
 
 	/* Trace point should be converted from subprogram DIE */
-	ret = convert_to_trace_point(&pf->sp_die, pf->addr,
+	ret = convert_to_trace_point(&pf->sp_die, tf->mod, pf->addr,
 				     pf->pev->point.retprobe, &tev->point);
 	if (ret < 0)
 		return ret;
@@ -1183,7 +1185,7 @@ int debuginfo__find_trace_events(struct debuginfo *self,
 {
 	struct trace_event_finder tf = {
 			.pf = {.pev = pev, .callback = add_probe_trace_event},
-			.max_tevs = max_tevs};
+			.mod = self->mod, .max_tevs = max_tevs};
 	int ret;
 
 	/* Allocate result tevs array */
@@ -1252,7 +1254,7 @@ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf)
 	vl = &af->vls[af->nvls++];
 
 	/* Trace point should be converted from subprogram DIE */
-	ret = convert_to_trace_point(&pf->sp_die, pf->addr,
+	ret = convert_to_trace_point(&pf->sp_die, af->mod, pf->addr,
 				     pf->pev->point.retprobe, &vl->point);
 	if (ret < 0)
 		return ret;
@@ -1291,6 +1293,7 @@ int debuginfo__find_available_vars_at(struct debuginfo *self,
 {
 	struct available_var_finder af = {
 			.pf = {.pev = pev, .callback = add_available_vars},
+			.mod = self->mod,
 			.max_vls = max_vls, .externs = externs};
 	int ret;
 
@@ -1474,7 +1477,7 @@ static int line_range_inline_cb(Dwarf_Die *in_die, void *data)
 	return 0;
 }
 
-/* Search function from function name */
+/* Search function definition from function name */
 static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 {
 	struct dwarf_callback_param *param = data;
@@ -1485,7 +1488,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 	if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die)))
 		return DWARF_CB_OK;
 
-	if (dwarf_tag(sp_die) == DW_TAG_subprogram &&
+	if (die_is_func_def(sp_die) &&
 	    die_compare_name(sp_die, lr->function)) {
 		lf->fname = dwarf_decl_file(sp_die);
 		dwarf_decl_line(sp_die, &lr->offset);
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 17e94d0c36f9..3b7d63018960 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -23,6 +23,7 @@ static inline int is_c_varname(const char *name)
 /* debug information structure */
 struct debuginfo {
 	Dwarf		*dbg;
+	Dwfl_Module	*mod;
 	Dwfl		*dwfl;
 	Dwarf_Addr	bias;
 };
@@ -77,6 +78,7 @@ struct probe_finder {
 
 struct trace_event_finder {
 	struct probe_finder	pf;
+	Dwfl_Module		*mod;		/* For solving symbols */
 	struct probe_trace_event *tevs;		/* Found trace events */
 	int			ntevs;		/* Number of trace events */
 	int			max_tevs;	/* Max number of trace events */
@@ -84,6 +86,7 @@ struct trace_event_finder {
 
 struct available_var_finder {
 	struct probe_finder	pf;
+	Dwfl_Module		*mod;		/* For solving symbols */
 	struct variable_list	*vls;		/* Found variable lists */
 	int			nvls;		/* Number of variable lists */
 	int			max_vls;	/* Max no. of variable lists */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 51f5edf2a6d0..70ffa41518f3 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -531,6 +531,9 @@ static int flush_sample_queue(struct perf_session *s,
 		return 0;
 
 	list_for_each_entry_safe(iter, tmp, head, list) {
+		if (session_done())
+			return 0;
+
 		if (iter->timestamp > limit)
 			break;
 
@@ -1160,7 +1163,6 @@ static void perf_session__warn_about_errors(const struct perf_session *session,
 	}
 }
 
-#define session_done()	(*(volatile int *)(&session_done))
 volatile int session_done;
 
 static int __perf_session__process_pipe_events(struct perf_session *self,
@@ -1372,10 +1374,13 @@ more:
 				    "Processing events...");
 	}
 
+	err = 0;
+	if (session_done())
+		goto out_err;
+
 	if (file_pos < file_size)
 		goto more;
 
-	err = 0;
 	/* do the final flush for ordered samples */
 	session->ordered_samples.next_flush = ULLONG_MAX;
 	err = flush_sample_queue(session, tool);
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 3aa75fb2225f..04bf7373a7e5 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -124,4 +124,8 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
 
 #define perf_session__set_tracepoints_handlers(session, array) \
 	__perf_session__set_tracepoints_handlers(session, array, ARRAY_SIZE(array))
+
+extern volatile int session_done;
+
+#define session_done()	(*(volatile int *)(&session_done))
 #endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index a7b9ab557380..a9c829be5216 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -8,6 +8,22 @@
 #include "symbol.h"
 #include "debug.h"
 
+#ifndef HAVE_ELF_GETPHDRNUM
+static int elf_getphdrnum(Elf *elf, size_t *dst)
+{
+	GElf_Ehdr gehdr;
+	GElf_Ehdr *ehdr;
+
+	ehdr = gelf_getehdr(elf, &gehdr);
+	if (!ehdr)
+		return -1;
+
+	*dst = ehdr->e_phnum;
+
+	return 0;
+}
+#endif
+
 #ifndef NT_GNU_BUILD_ID
 #define NT_GNU_BUILD_ID 3
 #endif
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index fe7a27d67d2b..e9e1c03f927d 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -186,7 +186,7 @@ void parse_proc_kallsyms(struct pevent *pevent,
 	char *next = NULL;
 	char *addr_str;
 	char *mod;
-	char *fmt;
+	char *fmt = NULL;
 
 	line = strtok_r(file, "\n", &next);
 	while (line) {