Linux 3.16

Pull timer fixes from Thomas Gleixner:
 "Two fixes in the timer area:
   - a long-standing lock inversion due to a printk
   - suspend-related hrtimer corruption in sched_clock"

* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  timer: Fix lock inversion between hrtimer_bases.lock and scheduler locks
  sched_clock: Avoid corrupting hrtimer tree during suspend

.mailmap

@@ -62,6 +62,11 @@ Jeff Garzik <jgarzik@pretzel.yyz.us>
 Jens Axboe <axboe@suse.de>
 Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
 John Stultz <johnstul@us.ibm.com>
+<josh@joshtriplett.org> <josh@freedesktop.org>
+<josh@joshtriplett.org> <josh@kernel.org>
+<josh@joshtriplett.org> <josht@linux.vnet.ibm.com>
+<josh@joshtriplett.org> <josht@us.ibm.com>
+<josh@joshtriplett.org> <josht@vnet.ibm.com>
 Juha Yrjola <at solidboot.com>
 Juha Yrjola <juha.yrjola@nokia.com>
 Juha Yrjola <juha.yrjola@solidboot.com>

CREDITS

@@ -3511,10 +3511,11 @@ S: MacGregor A.C.T 2615
 S: Australia
 
 N: Josh Triplett
-E: josh@freedesktop.org
-P: 1024D/D0FE7AFB B24A 65C9 1D71 2AC2 DE87  CA26 189B 9946 D0FE 7AFB
-D: rcutorture maintainer
+E: josh@joshtriplett.org
+P: 4096R/8AFF873D 758E 5042 E397 4BA3 3A9C  1E67 0ED9 A3DF 8AFF 873D
+D: RCU and rcutorture
 D: lock annotations, finding and fixing lock bugs
+D: kernel tinification
 
 N: Winfried Trümper
 E: winni@xpilot.org

Documentation/input/event-codes.txt

@@ -281,6 +281,19 @@ gestures can normally be extracted from it.
 If INPUT_PROP_SEMI_MT is not set, the device is assumed to be a true MT
 device.
 
+INPUT_PROP_TOPBUTTONPAD:
+-----------------------
+Some laptops, most notably the Lenovo *40 series provide a trackstick
+device but do not have physical buttons associated with the trackstick
+device. Instead, the top area of the touchpad is marked to show
+visual/haptic areas for left, middle, right buttons intended to be used
+with the trackstick.
+
+If INPUT_PROP_TOPBUTTONPAD is set, userspace should emulate buttons
+accordingly. This property does not affect kernel behavior.
+The kernel does not provide button emulation for such devices but treats
+them as any other INPUT_PROP_BUTTONPAD device.
+
 Guidelines:
 ==========
 The guidelines below ensure proper single-touch and multi-finger functionality.

MAINTAINERS

@@ -6956,6 +6956,12 @@ L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	drivers/pinctrl/pinctrl-at91.c
 
+PIN CONTROLLER - RENESAS
+M:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
+L:	linux-sh@vger.kernel.org
+S:	Maintained
+F:	drivers/pinctrl/sh-pfc/
+
 PIN CONTROLLER - SAMSUNG
 M:	Tomasz Figa <t.figa@samsung.com>
 M:	Thomas Abraham <thomas.abraham@linaro.org>
@@ -7418,7 +7424,7 @@ S:	Orphan
 F:	drivers/net/wireless/ray*
 
 RCUTORTURE MODULE
-M:	Josh Triplett <josh@freedesktop.org>
+M:	Josh Triplett <josh@joshtriplett.org>
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
@@ -8019,6 +8025,16 @@ F:	drivers/ata/
 F:	include/linux/ata.h
 F:	include/linux/libata.h
 
+SERIAL ATA AHCI PLATFORM devices support
+M:	Hans de Goede <hdegoede@redhat.com>
+M:	Tejun Heo <tj@kernel.org>
+L:	linux-ide@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git
+S:	Supported
+F:	drivers/ata/ahci_platform.c
+F:	drivers/ata/libahci_platform.c
+F:	include/linux/ahci_platform.h
+
 SERVER ENGINES 10Gbps iSCSI - BladeEngine 2 DRIVER
 M:	Jayamohan Kallickal <jayamohan.kallickal@emulex.com>
 L:	linux-scsi@vger.kernel.org
@@ -8906,7 +8922,7 @@ M:	Stephen Warren <swarren@wwwdotorg.org>
 M:	Thierry Reding <thierry.reding@gmail.com>
 L:	linux-tegra@vger.kernel.org
 Q:	http://patchwork.ozlabs.org/project/linux-tegra/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/swarren/linux-tegra.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tegra/linux.git
 S:	Supported
 N:	[^a-z]tegra
 

Makefile

@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 16
 SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION =
 NAME = Shuffling Zombie Juror
 
 # *DOCUMENTATION*
@@ -688,6 +688,8 @@ KBUILD_CFLAGS	+= -fomit-frame-pointer
 endif
 endif
 
+KBUILD_CFLAGS   += $(call cc-option, -fno-var-tracking-assignments)
+
 ifdef CONFIG_DEBUG_INFO
 KBUILD_CFLAGS	+= -g
 KBUILD_AFLAGS	+= -Wa,-gdwarf-2

arch/arm/Kconfig

@@ -313,7 +313,7 @@ config ARCH_MULTIPLATFORM
 config ARCH_INTEGRATOR
 	bool "ARM Ltd. Integrator family"
 	select ARM_AMBA
-	select ARM_PATCH_PHYS_VIRT
+	select ARM_PATCH_PHYS_VIRT if MMU
 	select AUTO_ZRELADDR
 	select COMMON_CLK
 	select COMMON_CLK_VERSATILE
@@ -659,7 +659,7 @@ config ARCH_MSM
 config ARCH_SHMOBILE_LEGACY
 	bool "Renesas ARM SoCs (non-multiplatform)"
 	select ARCH_SHMOBILE
-	select ARM_PATCH_PHYS_VIRT
+	select ARM_PATCH_PHYS_VIRT if MMU
 	select CLKDEV_LOOKUP
 	select GENERIC_CLOCKEVENTS
 	select HAVE_ARM_SCU if SMP

arch/arm/boot/dts/hi3620.dtsi

@@ -73,7 +73,7 @@ amba {
 
 		L2: l2-cache {
 			compatible = "arm,pl310-cache";
-			reg = <0xfc10000 0x100000>;
+			reg = <0x100000 0x100000>;
 			interrupts = <0 15 4>;
 			cache-unified;
 			cache-level = <2>;

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

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

arch/arm/boot/dts/r8a7791.dtsi

@@ -540,9 +540,9 @@ sd1_clk: sd2_clk@e6150078 {
 			#clock-cells = <0>;
 			clock-output-names = "sd1";
 		};
-		sd2_clk: sd3_clk@e615007c {
+		sd2_clk: sd3_clk@e615026c {
 			compatible = "renesas,r8a7791-div6-clock", "renesas,cpg-div6-clock";
-			reg = <0 0xe615007c 0 4>;
+			reg = <0 0xe615026c 0 4>;
 			clocks = <&pll1_div2_clk>;
 			#clock-cells = <0>;
 			clock-output-names = "sd2";

arch/arm/boot/dts/ste-nomadik-s8815.dts

@@ -4,7 +4,7 @@
  */
 
 /dts-v1/;
-/include/ "ste-nomadik-stn8815.dtsi"
+#include "ste-nomadik-stn8815.dtsi"
 
 / {
 	model = "Calao Systems USB-S8815";

arch/arm/boot/dts/ste-nomadik-stn8815.dtsi

@@ -1,7 +1,9 @@
 /*
  * Device Tree for the ST-Ericsson Nomadik 8815 STn8815 SoC
  */
-/include/ "skeleton.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include "skeleton.dtsi"
 
 / {
 	#address-cells = <1>;
@@ -842,8 +844,7 @@ mmcsd: sdi@101f6000 {
 			bus-width = <4>;
 			cap-mmc-highspeed;
 			cap-sd-highspeed;
-			cd-gpios = <&gpio3 15 0x1>;
-			cd-inverted;
+			cd-gpios = <&gpio3 15 GPIO_ACTIVE_LOW>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&mmcsd_default_mux>, <&mmcsd_default_mode>;
 			vmmc-supply = <&vmmc_regulator>;

arch/arm/crypto/aesbs-glue.c

@@ -137,7 +137,7 @@ static int aesbs_cbc_encrypt(struct blkcipher_desc *desc,
 				dst += AES_BLOCK_SIZE;
 			} while (--blocks);
 		}
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	return err;
 }
@@ -158,7 +158,7 @@ static int aesbs_cbc_decrypt(struct blkcipher_desc *desc,
 		bsaes_cbc_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
 				  walk.nbytes, &ctx->dec, walk.iv);
 		kernel_neon_end();
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	while (walk.nbytes) {
 		u32 blocks = walk.nbytes / AES_BLOCK_SIZE;
@@ -182,7 +182,7 @@ static int aesbs_cbc_decrypt(struct blkcipher_desc *desc,
 			dst += AES_BLOCK_SIZE;
 			src += AES_BLOCK_SIZE;
 		} while (--blocks);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	return err;
 }
@@ -268,7 +268,7 @@ static int aesbs_xts_encrypt(struct blkcipher_desc *desc,
 		bsaes_xts_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
 				  walk.nbytes, &ctx->enc, walk.iv);
 		kernel_neon_end();
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	return err;
 }
@@ -292,7 +292,7 @@ static int aesbs_xts_decrypt(struct blkcipher_desc *desc,
 		bsaes_xts_decrypt(walk.src.virt.addr, walk.dst.virt.addr,
 				  walk.nbytes, &ctx->dec, walk.iv);
 		kernel_neon_end();
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	return err;
 }

arch/arm/include/asm/mach/arch.h

@@ -50,6 +50,7 @@ struct machine_desc {
 	struct smp_operations	*smp;		/* SMP operations	*/
 	bool			(*smp_init)(void);
 	void			(*fixup)(struct tag *, char **);
+	void			(*dt_fixup)(void);
 	void			(*init_meminfo)(void);
 	void			(*reserve)(void);/* reserve mem blocks	*/
 	void			(*map_io)(void);/* IO mapping function	*/

arch/arm/kernel/devtree.c

@@ -212,7 +212,7 @@ const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
 	mdesc_best = &__mach_desc_GENERIC_DT;
 #endif
 
-	if (!dt_phys || !early_init_dt_scan(phys_to_virt(dt_phys)))
+	if (!dt_phys || !early_init_dt_verify(phys_to_virt(dt_phys)))
 		return NULL;
 
 	mdesc = of_flat_dt_match_machine(mdesc_best, arch_get_next_mach);
@@ -237,6 +237,12 @@ const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
 		dump_machine_table(); /* does not return */
 	}
 
+	/* We really don't want to do this, but sometimes firmware provides buggy data */
+	if (mdesc->dt_fixup)
+		mdesc->dt_fixup();
+
+	early_init_dt_scan_nodes();
+
 	/* Change machine number to match the mdesc we're using */
 	__machine_arch_type = mdesc->nr;
 

arch/arm/kernel/iwmmxt.S

@@ -94,13 +94,19 @@ ENTRY(iwmmxt_task_enable)
 
 	mrc	p15, 0, r2, c2, c0, 0
 	mov	r2, r2				@ cpwait
+	bl	concan_save
 
-	teq	r1, #0				@ test for last ownership
-	mov	lr, r9				@ normal exit from exception
-	beq	concan_load			@ no owner, skip save
+#ifdef CONFIG_PREEMPT_COUNT
+	get_thread_info r10
+#endif
+4:	dec_preempt_count r10, r3
+	mov	pc, r9				@ normal exit from exception
 
 concan_save:
 
+	teq	r1, #0				@ test for last ownership
+	beq	concan_load			@ no owner, skip save
+
 	tmrc	r2, wCon
 
 	@ CUP? wCx
@@ -138,7 +144,7 @@ concan_dump:
 	wstrd	wR15, [r1, #MMX_WR15]
 
 2:	teq	r0, #0				@ anything to load?
-	beq	3f
+	moveq	pc, lr				@ if not, return
 
 concan_load:
 
@@ -171,14 +177,9 @@ concan_load:
 	@ clear CUP/MUP (only if r1 != 0)
 	teq	r1, #0
 	mov 	r2, #0
-	beq	3f
-	tmcr	wCon, r2
+	moveq	pc, lr
 
-3:
-#ifdef CONFIG_PREEMPT_COUNT
-	get_thread_info r10
-#endif
-4:	dec_preempt_count r10, r3
+	tmcr	wCon, r2
 	mov	pc, lr
 
 /*

arch/arm/kernel/kgdb.c

@@ -160,12 +160,16 @@ static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int instr)
 static struct undef_hook kgdb_brkpt_hook = {
 	.instr_mask		= 0xffffffff,
 	.instr_val		= KGDB_BREAKINST,
+	.cpsr_mask		= MODE_MASK,
+	.cpsr_val		= SVC_MODE,
 	.fn			= kgdb_brk_fn
 };
 
 static struct undef_hook kgdb_compiled_brkpt_hook = {
 	.instr_mask		= 0xffffffff,
 	.instr_val		= KGDB_COMPILED_BREAK,
+	.cpsr_mask		= MODE_MASK,
+	.cpsr_val		= SVC_MODE,
 	.fn			= kgdb_compiled_brk_fn
 };
 

arch/arm/mach-exynos/exynos.c

@@ -335,6 +335,15 @@ static void __init exynos_reserve(void)
 #endif
 }
 
+static void __init exynos_dt_fixup(void)
+{
+	/*
+	 * Some versions of uboot pass garbage entries in the memory node,
+	 * use the old CONFIG_ARM_NR_BANKS
+	 */
+	of_fdt_limit_memory(8);
+}
+
 DT_MACHINE_START(EXYNOS_DT, "SAMSUNG EXYNOS (Flattened Device Tree)")
 	/* Maintainer: Thomas Abraham <thomas.abraham@linaro.org> */
 	/* Maintainer: Kukjin Kim <kgene.kim@samsung.com> */
@@ -348,4 +357,5 @@ DT_MACHINE_START(EXYNOS_DT, "SAMSUNG EXYNOS (Flattened Device Tree)")
 	.dt_compat	= exynos_dt_compat,
 	.restart	= exynos_restart,
 	.reserve	= exynos_reserve,
+	.dt_fixup	= exynos_dt_fixup,
 MACHINE_END

arch/arm/mach-omap2/gpmc-nand.c

@@ -50,6 +50,16 @@ static bool gpmc_hwecc_bch_capable(enum omap_ecc ecc_opt)
 		 soc_is_omap54xx() || soc_is_dra7xx())
 		return 1;
 
+	if (ecc_opt == OMAP_ECC_BCH4_CODE_HW_DETECTION_SW ||
+		 ecc_opt == OMAP_ECC_BCH8_CODE_HW_DETECTION_SW) {
+		if (cpu_is_omap24xx())
+			return 0;
+		else if (cpu_is_omap3630() && (GET_OMAP_REVISION() == 0))
+			return 0;
+		else
+			return 1;
+	}
+
 	/* OMAP3xxx do not have ELM engine, so cannot support ECC schemes
 	 * which require H/W based ECC error detection */
 	if ((cpu_is_omap34xx() || cpu_is_omap3630()) &&
@@ -57,14 +67,6 @@ static bool gpmc_hwecc_bch_capable(enum omap_ecc ecc_opt)
 		 (ecc_opt == OMAP_ECC_BCH8_CODE_HW)))
 		return 0;
 
-	/*
-	 * For now, assume 4-bit mode is only supported on OMAP3630 ES1.x, x>=1
-	 * and AM33xx derivates. Other chips may be added if confirmed to work.
-	 */
-	if ((ecc_opt == OMAP_ECC_BCH4_CODE_HW_DETECTION_SW) &&
-	    (!cpu_is_omap3630() || (GET_OMAP_REVISION() == 0)))
-		return 0;
-
 	/* legacy platforms support only HAM1 (1-bit Hamming) ECC scheme */
 	if (ecc_opt == OMAP_ECC_HAM1_CODE_HW)
 		return 1;

arch/arm/mach-omap2/omap4-common.c

@@ -168,6 +168,10 @@ static void omap4_l2c310_write_sec(unsigned long val, unsigned reg)
 		smc_op = OMAP4_MON_L2X0_PREFETCH_INDEX;
 		break;
 
+	case L310_POWER_CTRL:
+		pr_info_once("OMAP L2C310: ROM does not support power control setting\n");
+		return;
+
 	default:
 		WARN_ONCE(1, "OMAP L2C310: ignoring write to reg 0x%x\n", reg);
 		return;

arch/arm/mm/dma-mapping.c

@@ -461,12 +461,21 @@ void __init dma_contiguous_remap(void)
 		map.type = MT_MEMORY_DMA_READY;
 
 		/*
-		 * Clear previous low-memory mapping
+		 * Clear previous low-memory mapping to ensure that the
+		 * TLB does not see any conflicting entries, then flush
+		 * the TLB of the old entries before creating new mappings.
+		 *
+		 * This ensures that any speculatively loaded TLB entries
+		 * (even though they may be rare) can not cause any problems,
+		 * and ensures that this code is architecturally compliant.
 		 */
 		for (addr = __phys_to_virt(start); addr < __phys_to_virt(end);
 		     addr += PMD_SIZE)
 			pmd_clear(pmd_off_k(addr));
 
+		flush_tlb_kernel_range(__phys_to_virt(start),
+				       __phys_to_virt(end));
+
 		iotable_init(&map, 1);
 	}
 }

arch/arm/mm/idmap.c

@@ -9,6 +9,11 @@
 #include <asm/sections.h>
 #include <asm/system_info.h>
 
+/*
+ * Note: accesses outside of the kernel image and the identity map area
+ * are not supported on any CPU using the idmap tables as its current
+ * page tables.
+ */
 pgd_t *idmap_pgd;
 phys_addr_t (*arch_virt_to_idmap) (unsigned long x);
 
@@ -25,6 +30,13 @@ static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 			pr_warning("Failed to allocate identity pmd.\n");
 			return;
 		}
+		/*
+		 * Copy the original PMD to ensure that the PMD entries for
+		 * the kernel image are preserved.
+		 */
+		if (!pud_none(*pud))
+			memcpy(pmd, pmd_offset(pud, 0),
+			       PTRS_PER_PMD * sizeof(pmd_t));
 		pud_populate(&init_mm, pud, pmd);
 		pmd += pmd_index(addr);
 	} else

arch/arm/mm/mmu.c

@@ -1406,8 +1406,8 @@ void __init early_paging_init(const struct machine_desc *mdesc,
 		return;
 
 	/* remap kernel code and data */
-	map_start = init_mm.start_code;
-	map_end   = init_mm.brk;
+	map_start = init_mm.start_code & PMD_MASK;
+	map_end   = ALIGN(init_mm.brk, PMD_SIZE);
 
 	/* get a handle on things... */
 	pgd0 = pgd_offset_k(0);
@@ -1442,7 +1442,7 @@ void __init early_paging_init(const struct machine_desc *mdesc,
 	}
 
 	/* remap pmds for kernel mapping */
-	phys = __pa(map_start) & PMD_MASK;
+	phys = __pa(map_start);
 	do {
 		*pmdk++ = __pmd(phys | pmdprot);
 		phys += PMD_SIZE;

arch/arm/xen/grant-table.c

@@ -51,3 +51,8 @@ int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes,
 {
 	return -ENOSYS;
 }
+
+int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status)
+{
+	return 0;
+}

arch/arm64/crypto/aes-glue.c

@@ -106,7 +106,7 @@ static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
 		aes_ecb_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key_enc, rounds, blocks, first);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	kernel_neon_end();
 	return err;
@@ -128,7 +128,7 @@ static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
 		aes_ecb_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key_dec, rounds, blocks, first);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	kernel_neon_end();
 	return err;
@@ -151,7 +151,7 @@ static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key_enc, rounds, blocks, walk.iv,
 				first);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	kernel_neon_end();
 	return err;
@@ -174,7 +174,7 @@ static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		aes_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key_dec, rounds, blocks, walk.iv,
 				first);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	kernel_neon_end();
 	return err;
@@ -243,7 +243,7 @@ static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key1.key_enc, rounds, blocks,
 				(u8 *)ctx->key2.key_enc, walk.iv, first);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	kernel_neon_end();
 
@@ -267,7 +267,7 @@ static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key1.key_dec, rounds, blocks,
 				(u8 *)ctx->key2.key_enc, walk.iv, first);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	kernel_neon_end();
 

arch/arm64/mm/init.c

@@ -60,6 +60,17 @@ static int __init early_initrd(char *p)
 early_param("initrd", early_initrd);
 #endif
 
+/*
+ * Return the maximum physical address for ZONE_DMA (DMA_BIT_MASK(32)). It
+ * currently assumes that for memory starting above 4G, 32-bit devices will
+ * use a DMA offset.
+ */
+static phys_addr_t max_zone_dma_phys(void)
+{
+	phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32);
+	return min(offset + (1ULL << 32), memblock_end_of_DRAM());
+}
+
 static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	struct memblock_region *reg;
@@ -70,9 +81,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 
 	/* 4GB maximum for 32-bit only capable devices */
 	if (IS_ENABLED(CONFIG_ZONE_DMA)) {
-		unsigned long max_dma_phys =
-			(unsigned long)(dma_to_phys(NULL, DMA_BIT_MASK(32)) + 1);
-		max_dma = max(min, min(max, max_dma_phys >> PAGE_SHIFT));
+		max_dma = PFN_DOWN(max_zone_dma_phys());
 		zone_size[ZONE_DMA] = max_dma - min;
 	}
 	zone_size[ZONE_NORMAL] = max - max_dma;
@@ -146,7 +155,7 @@ void __init arm64_memblock_init(void)
 
 	/* 4GB maximum for 32-bit only capable devices */
 	if (IS_ENABLED(CONFIG_ZONE_DMA))
-		dma_phys_limit = dma_to_phys(NULL, DMA_BIT_MASK(32)) + 1;
+		dma_phys_limit = max_zone_dma_phys();
 	dma_contiguous_reserve(dma_phys_limit);
 
 	memblock_allow_resize();

arch/blackfin/configs/BF609-EZKIT_defconfig

@@ -102,7 +102,7 @@ CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_BLACKFIN_TWI=y
 CONFIG_I2C_BLACKFIN_TWI_CLK_KHZ=100
 CONFIG_SPI=y
-CONFIG_SPI_BFIN_V3=y
+CONFIG_SPI_ADI_V3=y
 CONFIG_GPIOLIB=y
 CONFIG_GPIO_SYSFS=y
 # CONFIG_HWMON is not set

arch/blackfin/kernel/vmlinux.lds.S

@@ -145,7 +145,7 @@ SECTIONS
 
 	.text_l1 L1_CODE_START : AT(LOADADDR(.exit.data) + SIZEOF(.exit.data))
 #else
-	.init.data : AT(__data_lma + __data_len)
+	.init.data : AT(__data_lma + __data_len + 32)
 	{
 		__sinitdata = .;
 		INIT_DATA

arch/blackfin/mach-bf533/boards/blackstamp.c

@@ -20,6 +20,7 @@
 #include <linux/spi/spi.h>
 #include <linux/spi/flash.h>
 #include <linux/irq.h>
+#include <linux/gpio.h>
 #include <linux/i2c.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>

arch/blackfin/mach-bf537/boards/cm_bf537e.c

@@ -21,6 +21,7 @@
 #endif
 #include <linux/ata_platform.h>
 #include <linux/irq.h>
+#include <linux/gpio.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
 #include <asm/portmux.h>

arch/blackfin/mach-bf537/boards/cm_bf537u.c

@@ -21,6 +21,7 @@
 #endif
 #include <linux/ata_platform.h>
 #include <linux/irq.h>
+#include <linux/gpio.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
 #include <asm/portmux.h>

arch/blackfin/mach-bf537/boards/tcm_bf537.c

@@ -21,6 +21,7 @@
 #endif
 #include <linux/ata_platform.h>
 #include <linux/irq.h>
+#include <linux/gpio.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
 #include <asm/portmux.h>

arch/blackfin/mach-bf548/boards/ezkit.c

@@ -2118,7 +2118,7 @@ static struct pinctrl_map __initdata bfin_pinmux_map[] = {
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-rotary",  "pinctrl-adi2.0", NULL, "rotary"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin_can.0",  "pinctrl-adi2.0", NULL, "can0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin_can.1",  "pinctrl-adi2.0", NULL, "can1"),
-	PIN_MAP_MUX_GROUP_DEFAULT("bf54x-lq043",  "pinctrl-adi2.0", NULL, "ppi0_24b"),
+	PIN_MAP_MUX_GROUP_DEFAULT("bf54x-lq043",  "pinctrl-adi2.0", "ppi0_24bgrp", "ppi0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-i2s.0",  "pinctrl-adi2.0", NULL, "sport0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-tdm.0",  "pinctrl-adi2.0", NULL, "sport0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-ac97.0",  "pinctrl-adi2.0", NULL, "sport0"),
@@ -2140,7 +2140,9 @@ static struct pinctrl_map __initdata bfin_pinmux_map[] = {
 	PIN_MAP_MUX_GROUP_DEFAULT("pata-bf54x",  "pinctrl-adi2.0", NULL, "atapi_alter"),
 #endif
 	PIN_MAP_MUX_GROUP_DEFAULT("bf5xx-nand.0",  "pinctrl-adi2.0", NULL, "nfc0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("bf54x-keys",  "pinctrl-adi2.0", NULL, "keys_4x4"),
+	PIN_MAP_MUX_GROUP_DEFAULT("bf54x-keys",  "pinctrl-adi2.0", "keys_4x4grp", "keys"),
+	PIN_MAP_MUX_GROUP("bf54x-keys", "4bit",  "pinctrl-adi2.0", "keys_4x4grp", "keys"),
+	PIN_MAP_MUX_GROUP("bf54x-keys", "8bit",  "pinctrl-adi2.0", "keys_8x8grp", "keys"),
 };
 
 static int __init ezkit_init(void)

arch/blackfin/mach-bf561/boards/acvilon.c

@@ -44,6 +44,7 @@
 #include <linux/spi/flash.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
+#include <linux/gpio.h>
 #include <linux/jiffies.h>
 #include <linux/i2c-pca-platform.h>
 #include <linux/delay.h>

arch/blackfin/mach-bf561/boards/cm_bf561.c

@@ -18,6 +18,7 @@
 #endif
 #include <linux/ata_platform.h>
 #include <linux/irq.h>
+#include <linux/gpio.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
 #include <asm/portmux.h>

arch/blackfin/mach-bf561/boards/ezkit.c

@@ -14,6 +14,7 @@
 #include <linux/spi/spi.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
+#include <linux/gpio.h>
 #include <linux/delay.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>

arch/blackfin/mach-bf609/boards/ezkit.c

@@ -698,8 +698,6 @@ int bf609_nor_flash_init(struct platform_device *pdev)
 {
 #define CONFIG_SMC_GCTL_VAL     0x00000010
 
-	if (!devm_pinctrl_get_select_default(&pdev->dev))
-		return -EBUSY;
 	bfin_write32(SMC_GCTL, CONFIG_SMC_GCTL_VAL);
 	bfin_write32(SMC_B0CTL, 0x01002011);
 	bfin_write32(SMC_B0TIM, 0x08170977);
@@ -709,7 +707,6 @@ int bf609_nor_flash_init(struct platform_device *pdev)
 
 void bf609_nor_flash_exit(struct platform_device *pdev)
 {
-	devm_pinctrl_put(pdev->dev.pins->p);
 	bfin_write32(SMC_GCTL, 0);
 }
 
@@ -2058,15 +2055,14 @@ static struct pinctrl_map __initdata bfin_pinmux_map[] = {
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-rotary",  "pinctrl-adi2.0", NULL, "rotary"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin_can.0",  "pinctrl-adi2.0", NULL, "can0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("physmap-flash.0",  "pinctrl-adi2.0", NULL, "smc0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("bf609_nl8048.2",  "pinctrl-adi2.0", NULL, "ppi2_16b"),
-	PIN_MAP_MUX_GROUP_DEFAULT("bfin_display.0",  "pinctrl-adi2.0", NULL, "ppi0_16b"),
-#if IS_ENABLED(CONFIG_VIDEO_MT9M114)
-	PIN_MAP_MUX_GROUP_DEFAULT("bfin_capture.0",  "pinctrl-adi2.0", NULL, "ppi0_8b"),
-#elif IS_ENABLED(CONFIG_VIDEO_VS6624)
-	PIN_MAP_MUX_GROUP_DEFAULT("bfin_capture.0",  "pinctrl-adi2.0", NULL, "ppi0_16b"),
-#else
-	PIN_MAP_MUX_GROUP_DEFAULT("bfin_capture.0",  "pinctrl-adi2.0", NULL, "ppi0_24b"),
-#endif
+	PIN_MAP_MUX_GROUP_DEFAULT("bf609_nl8048.2",  "pinctrl-adi2.0", "ppi2_16bgrp", "ppi2"),
+	PIN_MAP_MUX_GROUP("bfin_display.0", "8bit",  "pinctrl-adi2.0", "ppi2_8bgrp", "ppi2"),
+	PIN_MAP_MUX_GROUP_DEFAULT("bfin_display.0",  "pinctrl-adi2.0", "ppi2_16bgrp", "ppi2"),
+	PIN_MAP_MUX_GROUP("bfin_display.0", "16bit",  "pinctrl-adi2.0", "ppi2_16bgrp", "ppi2"),
+	PIN_MAP_MUX_GROUP("bfin_capture.0", "8bit",  "pinctrl-adi2.0", "ppi0_8bgrp", "ppi0"),
+	PIN_MAP_MUX_GROUP_DEFAULT("bfin_capture.0",  "pinctrl-adi2.0", "ppi0_16bgrp", "ppi0"),
+	PIN_MAP_MUX_GROUP("bfin_capture.0", "16bit",  "pinctrl-adi2.0", "ppi0_16bgrp", "ppi0"),
+	PIN_MAP_MUX_GROUP("bfin_capture.0", "24bit",  "pinctrl-adi2.0", "ppi0_24bgrp", "ppi0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-i2s.0",  "pinctrl-adi2.0", NULL, "sport0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-tdm.0",  "pinctrl-adi2.0", NULL, "sport0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-i2s.1",  "pinctrl-adi2.0", NULL, "sport1"),

arch/blackfin/mach-bf609/include/mach/pm.h

@@ -10,6 +10,7 @@
 #define __MACH_BF609_PM_H__
 
 #include <linux/suspend.h>
+#include <linux/platform_device.h>
 
 extern int bfin609_pm_enter(suspend_state_t state);
 extern int bf609_pm_prepare(void);
@@ -19,6 +20,6 @@ void bf609_hibernate(void);
 void bfin_sec_raise_irq(unsigned int sid);
 void coreb_enable(void);
 
-int bf609_nor_flash_init(void);
-void bf609_nor_flash_exit(void);
+int bf609_nor_flash_init(struct platform_device *pdev);
+void bf609_nor_flash_exit(struct platform_device *pdev);
 #endif

arch/blackfin/mach-bf609/pm.c

@@ -291,13 +291,13 @@ static struct bfin_cpu_pm_fns bf609_cpu_pm = {
 #if defined(CONFIG_MTD_PHYSMAP) || defined(CONFIG_MTD_PHYSMAP_MODULE)
 static int smc_pm_syscore_suspend(void)
 {
-	bf609_nor_flash_exit();
+	bf609_nor_flash_exit(NULL);
 	return 0;
 }
 
 static void smc_pm_syscore_resume(void)
 {
-	bf609_nor_flash_init();
+	bf609_nor_flash_init(NULL);
 }
 
 static struct syscore_ops smc_pm_syscore_ops = {

arch/blackfin/mach-common/ints-priority.c

@@ -1208,8 +1208,6 @@ int __init init_arch_irq(void)
 
 	bfin_sec_set_priority(CONFIG_SEC_IRQ_PRIORITY_LEVELS, sec_int_priority);
 
-	bfin_sec_set_priority(CONFIG_SEC_IRQ_PRIORITY_LEVELS, sec_int_priority);
-
 	/* Enable interrupts IVG7-15 */
 	bfin_irq_flags |= IMASK_IVG15 |
 	    IMASK_IVG14 | IMASK_IVG13 | IMASK_IVG12 | IMASK_IVG11 |

arch/parisc/include/uapi/asm/signal.h

@@ -69,8 +69,6 @@
 #define SA_NOMASK	SA_NODEFER
 #define SA_ONESHOT	SA_RESETHAND
 
-#define SA_RESTORER	0x04000000 /* obsolete -- ignored */
-
 #define MINSIGSTKSZ	2048
 #define SIGSTKSZ	8192
 

arch/parisc/mm/init.c

@@ -728,7 +728,6 @@ static void __init pagetable_init(void)
 #endif
 
 	empty_zero_page = alloc_bootmem_pages(PAGE_SIZE);
-	memset(empty_zero_page, 0, PAGE_SIZE);
 }
 
 static void __init gateway_init(void)

arch/powerpc/include/asm/cputable.h

@@ -447,6 +447,7 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
 	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP)
 #define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG)
+#define CPU_FTRS_POWER8_DD1 (CPU_FTRS_POWER8 & ~CPU_FTR_DBELL)
 #define CPU_FTRS_CELL	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \

arch/powerpc/include/asm/kvm_book3s_64.h

@@ -198,8 +198,10 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
 	return rb;
 }
 
-static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
+static inline unsigned long __hpte_page_size(unsigned long h, unsigned long l,
+					     bool is_base_size)
 {
+
 	int size, a_psize;
 	/* Look at the 8 bit LP value */
 	unsigned int lp = (l >> LP_SHIFT) & ((1 << LP_BITS) - 1);
@@ -214,14 +216,27 @@ static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
 				continue;
 
 			a_psize = __hpte_actual_psize(lp, size);
-			if (a_psize != -1)
+			if (a_psize != -1) {
+				if (is_base_size)
+					return 1ul << mmu_psize_defs[size].shift;
 				return 1ul << mmu_psize_defs[a_psize].shift;
+			}
 		}
 
 	}
 	return 0;
 }
 
+static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
+{
+	return __hpte_page_size(h, l, 0);
+}
+
+static inline unsigned long hpte_base_page_size(unsigned long h, unsigned long l)
+{
+	return __hpte_page_size(h, l, 1);
+}
+
 static inline unsigned long hpte_rpn(unsigned long ptel, unsigned long psize)
 {
 	return ((ptel & HPTE_R_RPN) & ~(psize - 1)) >> PAGE_SHIFT;

arch/powerpc/include/asm/mmu-hash64.h

@@ -22,6 +22,7 @@
  */
 #include <asm/pgtable-ppc64.h>
 #include <asm/bug.h>
+#include <asm/processor.h>
 
 /*
  * Segment table
@@ -496,7 +497,7 @@ extern void slb_set_size(u16 size);
  */
 struct subpage_prot_table {
 	unsigned long maxaddr;	/* only addresses < this are protected */
-	unsigned int **protptrs[2];
+	unsigned int **protptrs[(TASK_SIZE_USER64 >> 43)];
 	unsigned int *low_prot[4];
 };
 

arch/powerpc/include/asm/ppc_asm.h

@@ -277,6 +277,8 @@ GLUE(.,name):
 	.globl n;	\
 n:
 
+#define _GLOBAL_TOC(name) _GLOBAL(name)
+
 #define _KPROBE(n)	\
 	.section ".kprobes.text","a";	\
 	.globl	n;	\

arch/powerpc/kernel/cputable.c

@@ -527,6 +527,26 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
+	{	/* Power8 DD1: Does not support doorbell IPIs */
+		.pvr_mask		= 0xffffff00,
+		.pvr_value		= 0x004d0100,
+		.cpu_name		= "POWER8 (raw)",
+		.cpu_features		= CPU_FTRS_POWER8_DD1,
+		.cpu_user_features	= COMMON_USER_POWER8,
+		.cpu_user_features2	= COMMON_USER2_POWER8,
+		.mmu_features		= MMU_FTRS_POWER8,
+		.icache_bsize		= 128,
+		.dcache_bsize		= 128,
+		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_IBM,
+		.oprofile_cpu_type	= "ppc64/power8",
+		.oprofile_type		= PPC_OPROFILE_INVALID,
+		.cpu_setup		= __setup_cpu_power8,
+		.cpu_restore		= __restore_cpu_power8,
+		.flush_tlb		= __flush_tlb_power8,
+		.machine_check_early	= __machine_check_early_realmode_p8,
+		.platform		= "power8",
+	},
 	{	/* Power8 */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x004d0000,

arch/powerpc/kernel/rtas_flash.c

@@ -611,17 +611,19 @@ static void rtas_flash_firmware(int reboot_type)
 	for (f = flist; f; f = next) {
 		/* Translate data addrs to absolute */
 		for (i = 0; i < f->num_blocks; i++) {
-			f->blocks[i].data = (char *)__pa(f->blocks[i].data);
+			f->blocks[i].data = (char *)cpu_to_be64(__pa(f->blocks[i].data));
 			image_size += f->blocks[i].length;
+			f->blocks[i].length = cpu_to_be64(f->blocks[i].length);
 		}
 		next = f->next;
 		/* Don't translate NULL pointer for last entry */
 		if (f->next)
-			f->next = (struct flash_block_list *)__pa(f->next);
+			f->next = (struct flash_block_list *)cpu_to_be64(__pa(f->next));
 		else
 			f->next = NULL;
 		/* make num_blocks into the version/length field */
 		f->num_blocks = (FLASH_BLOCK_LIST_VERSION << 56) | ((f->num_blocks+1)*16);
+		f->num_blocks = cpu_to_be64(f->num_blocks);
 	}
 
 	printk(KERN_ALERT "FLASH: flash image is %ld bytes\n", image_size);

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -1562,7 +1562,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 				goto out;
 			}
 			if (!rma_setup && is_vrma_hpte(v)) {
-				unsigned long psize = hpte_page_size(v, r);
+				unsigned long psize = hpte_base_page_size(v, r);
 				unsigned long senc = slb_pgsize_encoding(psize);
 				unsigned long lpcr;
 

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -814,13 +814,10 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
 			r = hpte[i+1];
 
 			/*
-			 * Check the HPTE again, including large page size
-			 * Since we don't currently allow any MPSS (mixed
-			 * page-size segment) page sizes, it is sufficient
-			 * to check against the actual page size.
+			 * Check the HPTE again, including base page size
 			 */
 			if ((v & valid) && (v & mask) == val &&
-			    hpte_page_size(v, r) == (1ul << pshift))
+			    hpte_base_page_size(v, r) == (1ul << pshift))
 				/* Return with the HPTE still locked */
 				return (hash << 3) + (i >> 1);
 

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -48,7 +48,7 @@
  *
  * LR = return address to continue at after eventually re-enabling MMU
  */
-_GLOBAL(kvmppc_hv_entry_trampoline)
+_GLOBAL_TOC(kvmppc_hv_entry_trampoline)
 	mflr	r0
 	std	r0, PPC_LR_STKOFF(r1)
 	stdu	r1, -112(r1)

arch/powerpc/kvm/book3s_interrupts.S

@@ -25,7 +25,11 @@
 #include <asm/exception-64s.h>
 
 #if defined(CONFIG_PPC_BOOK3S_64)
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define FUNC(name) 		name
+#else
 #define FUNC(name) 		GLUE(.,name)
+#endif
 #define GET_SHADOW_VCPU(reg)    addi	reg, r13, PACA_SVCPU
 
 #elif defined(CONFIG_PPC_BOOK3S_32)

arch/powerpc/kvm/book3s_rmhandlers.S

@@ -36,7 +36,11 @@
 
 #if defined(CONFIG_PPC_BOOK3S_64)
 
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define FUNC(name) 		name
+#else
 #define FUNC(name) 		GLUE(.,name)
+#endif
 
 #elif defined(CONFIG_PPC_BOOK3S_32)
 
@@ -146,7 +150,7 @@ kvmppc_handler_skip_ins:
  * On entry, r4 contains the guest shadow MSR
  * MSR.EE has to be 0 when calling this function
  */
-_GLOBAL(kvmppc_entry_trampoline)
+_GLOBAL_TOC(kvmppc_entry_trampoline)
 	mfmsr	r5
 	LOAD_REG_ADDR(r7, kvmppc_handler_trampoline_enter)
 	toreal(r7)

arch/powerpc/kvm/book3s_rtas.c

@@ -23,20 +23,20 @@ static void kvm_rtas_set_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
 	u32 irq, server, priority;
 	int rc;
 
-	if (args->nargs != 3 || args->nret != 1) {
+	if (be32_to_cpu(args->nargs) != 3 || be32_to_cpu(args->nret) != 1) {
 		rc = -3;
 		goto out;
 	}
 
-	irq = args->args[0];
-	server = args->args[1];
-	priority = args->args[2];
+	irq = be32_to_cpu(args->args[0]);
+	server = be32_to_cpu(args->args[1]);
+	priority = be32_to_cpu(args->args[2]);
 
 	rc = kvmppc_xics_set_xive(vcpu->kvm, irq, server, priority);
 	if (rc)
 		rc = -3;
 out:
-	args->rets[0] = rc;
+	args->rets[0] = cpu_to_be32(rc);
 }
 
 static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
@@ -44,12 +44,12 @@ static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
 	u32 irq, server, priority;
 	int rc;
 
-	if (args->nargs != 1 || args->nret != 3) {
+	if (be32_to_cpu(args->nargs) != 1 || be32_to_cpu(args->nret) != 3) {
 		rc = -3;
 		goto out;
 	}
 
-	irq = args->args[0];
+	irq = be32_to_cpu(args->args[0]);
 
 	server = priority = 0;
 	rc = kvmppc_xics_get_xive(vcpu->kvm, irq, &server, &priority);
@@ -58,10 +58,10 @@ static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
 		goto out;
 	}
 
-	args->rets[1] = server;
-	args->rets[2] = priority;
+	args->rets[1] = cpu_to_be32(server);
+	args->rets[2] = cpu_to_be32(priority);
 out:
-	args->rets[0] = rc;
+	args->rets[0] = cpu_to_be32(rc);
 }
 
 static void kvm_rtas_int_off(struct kvm_vcpu *vcpu, struct rtas_args *args)
@@ -69,18 +69,18 @@ static void kvm_rtas_int_off(struct kvm_vcpu *vcpu, struct rtas_args *args)
 	u32 irq;
 	int rc;
 
-	if (args->nargs != 1 || args->nret != 1) {
+	if (be32_to_cpu(args->nargs) != 1 || be32_to_cpu(args->nret) != 1) {
 		rc = -3;
 		goto out;
 	}
 
-	irq = args->args[0];
+	irq = be32_to_cpu(args->args[0]);
 
 	rc = kvmppc_xics_int_off(vcpu->kvm, irq);
 	if (rc)
 		rc = -3;
 out:
-	args->rets[0] = rc;
+	args->rets[0] = cpu_to_be32(rc);
 }
 
 static void kvm_rtas_int_on(struct kvm_vcpu *vcpu, struct rtas_args *args)
@@ -88,18 +88,18 @@ static void kvm_rtas_int_on(struct kvm_vcpu *vcpu, struct rtas_args *args)
 	u32 irq;
 	int rc;
 
-	if (args->nargs != 1 || args->nret != 1) {
+	if (be32_to_cpu(args->nargs) != 1 || be32_to_cpu(args->nret) != 1) {
 		rc = -3;
 		goto out;
 	}
 
-	irq = args->args[0];
+	irq = be32_to_cpu(args->args[0]);
 
 	rc = kvmppc_xics_int_on(vcpu->kvm, irq);
 	if (rc)
 		rc = -3;
 out:
-	args->rets[0] = rc;
+	args->rets[0] = cpu_to_be32(rc);
 }
 #endif /* CONFIG_KVM_XICS */
 
@@ -205,32 +205,6 @@ int kvm_vm_ioctl_rtas_define_token(struct kvm *kvm, void __user *argp)
 	return rc;
 }
 
-static void kvmppc_rtas_swap_endian_in(struct rtas_args *args)
-{
-#ifdef __LITTLE_ENDIAN__
-	int i;
-
-	args->token = be32_to_cpu(args->token);
-	args->nargs = be32_to_cpu(args->nargs);
-	args->nret = be32_to_cpu(args->nret);
-	for (i = 0; i < args->nargs; i++)
-		args->args[i] = be32_to_cpu(args->args[i]);
-#endif
-}
-
-static void kvmppc_rtas_swap_endian_out(struct rtas_args *args)
-{
-#ifdef __LITTLE_ENDIAN__
-	int i;
-
-	for (i = 0; i < args->nret; i++)
-		args->args[i] = cpu_to_be32(args->args[i]);
-	args->token = cpu_to_be32(args->token);
-	args->nargs = cpu_to_be32(args->nargs);
-	args->nret = cpu_to_be32(args->nret);
-#endif
-}
-
 int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 {
 	struct rtas_token_definition *d;
@@ -249,8 +223,6 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 	if (rc)
 		goto fail;
 
-	kvmppc_rtas_swap_endian_in(&args);
-
 	/*
 	 * args->rets is a pointer into args->args. Now that we've
 	 * copied args we need to fix it up to point into our copy,
@@ -258,13 +230,13 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 	 * value so we can restore it on the way out.
 	 */
 	orig_rets = args.rets;
-	args.rets = &args.args[args.nargs];
+	args.rets = &args.args[be32_to_cpu(args.nargs)];
 
 	mutex_lock(&vcpu->kvm->lock);
 
 	rc = -ENOENT;
 	list_for_each_entry(d, &vcpu->kvm->arch.rtas_tokens, list) {
-		if (d->token == args.token) {
+		if (d->token == be32_to_cpu(args.token)) {
 			d->handler->handler(vcpu, &args);
 			rc = 0;
 			break;
@@ -275,7 +247,6 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 
 	if (rc == 0) {
 		args.rets = orig_rets;
-		kvmppc_rtas_swap_endian_out(&args);
 		rc = kvm_write_guest(vcpu->kvm, args_phys, &args, sizeof(args));
 		if (rc)
 			goto fail;

arch/powerpc/kvm/e500_mmu_host.c

@@ -473,7 +473,8 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 		if (printk_ratelimit())
 			pr_err("%s: pte not present: gfn %lx, pfn %lx\n",
 				__func__, (long)gfn, pfn);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 	kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg);
 

arch/powerpc/lib/mem_64.S

@@ -77,7 +77,7 @@ _GLOBAL(memset)
 	stb	r4,0(r6)
 	blr
 
-_GLOBAL(memmove)
+_GLOBAL_TOC(memmove)
 	cmplw	0,r3,r4
 	bgt	backwards_memcpy
 	b	memcpy

arch/powerpc/lib/sstep.c

@@ -1198,7 +1198,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 			sh = regs->gpr[rb] & 0x3f;
 			ival = (signed int) regs->gpr[rd];
 			regs->gpr[ra] = ival >> (sh < 32 ? sh : 31);
-			if (ival < 0 && (sh >= 32 || (ival & ((1 << sh) - 1)) != 0))
+			if (ival < 0 && (sh >= 32 || (ival & ((1ul << sh) - 1)) != 0))
 				regs->xer |= XER_CA;
 			else
 				regs->xer &= ~XER_CA;
@@ -1208,7 +1208,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 			sh = rb;
 			ival = (signed int) regs->gpr[rd];
 			regs->gpr[ra] = ival >> sh;
-			if (ival < 0 && (ival & ((1 << sh) - 1)) != 0)
+			if (ival < 0 && (ival & ((1ul << sh) - 1)) != 0)
 				regs->xer |= XER_CA;
 			else
 				regs->xer &= ~XER_CA;
@@ -1216,7 +1216,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 
 #ifdef __powerpc64__
 		case 27:	/* sld */
-			sh = regs->gpr[rd] & 0x7f;
+			sh = regs->gpr[rb] & 0x7f;
 			if (sh < 64)
 				regs->gpr[ra] = regs->gpr[rd] << sh;
 			else
@@ -1235,7 +1235,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 			sh = regs->gpr[rb] & 0x7f;
 			ival = (signed long int) regs->gpr[rd];
 			regs->gpr[ra] = ival >> (sh < 64 ? sh : 63);
-			if (ival < 0 && (sh >= 64 || (ival & ((1 << sh) - 1)) != 0))
+			if (ival < 0 && (sh >= 64 || (ival & ((1ul << sh) - 1)) != 0))
 				regs->xer |= XER_CA;
 			else
 				regs->xer &= ~XER_CA;
@@ -1246,7 +1246,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 			sh = rb | ((instr & 2) << 4);
 			ival = (signed long int) regs->gpr[rd];
 			regs->gpr[ra] = ival >> sh;
-			if (ival < 0 && (ival & ((1 << sh) - 1)) != 0)
+			if (ival < 0 && (ival & ((1ul << sh) - 1)) != 0)
 				regs->xer |= XER_CA;
 			else
 				regs->xer &= ~XER_CA;

arch/powerpc/perf/core-book3s.c

@@ -1307,6 +1307,9 @@ static void power_pmu_enable(struct pmu *pmu)
  out_enable:
 	pmao_restore_workaround(ebb);
 
+	if (ppmu->flags & PPMU_ARCH_207S)
+		mtspr(SPRN_MMCR2, 0);
+
 	mmcr0 = ebb_switch_in(ebb, cpuhw->mmcr[0]);
 
 	mb();
@@ -1315,9 +1318,6 @@ static void power_pmu_enable(struct pmu *pmu)
 
 	write_mmcr0(cpuhw, mmcr0);
 
-	if (ppmu->flags & PPMU_ARCH_207S)
-		mtspr(SPRN_MMCR2, 0);
-
 	/*
 	 * Enable instruction sampling if necessary
 	 */

arch/powerpc/platforms/powernv/opal-elog.c

@@ -249,7 +249,7 @@ static void elog_work_fn(struct work_struct *work)
 
 	rc = opal_get_elog_size(&id, &size, &type);
 	if (rc != OPAL_SUCCESS) {
-		pr_err("ELOG: Opal log read failed\n");
+		pr_err("ELOG: OPAL log info read failed\n");
 		return;
 	}
 
@@ -257,7 +257,7 @@ static void elog_work_fn(struct work_struct *work)
 	log_id = be64_to_cpu(id);
 	elog_type = be64_to_cpu(type);
 
-	BUG_ON(elog_size > OPAL_MAX_ERRLOG_SIZE);
+	WARN_ON(elog_size > OPAL_MAX_ERRLOG_SIZE);
 
 	if (elog_size >= OPAL_MAX_ERRLOG_SIZE)
 		elog_size  =  OPAL_MAX_ERRLOG_SIZE;

arch/powerpc/platforms/pseries/dlpar.c

@@ -86,6 +86,7 @@ static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa,
 	}
 
 	of_node_set_flag(dn, OF_DYNAMIC);
+	of_node_init(dn);
 
 	return dn;
 }

arch/powerpc/platforms/pseries/reconfig.c

@@ -69,6 +69,7 @@ static int pSeries_reconfig_add_node(const char *path, struct property *proplist
 
 	np->properties = proplist;
 	of_node_set_flag(np, OF_DYNAMIC);
+	of_node_init(np);
 
 	np->parent = derive_parent(path);
 	if (IS_ERR(np->parent)) {

arch/s390/include/asm/switch_to.h

@@ -51,8 +51,8 @@ static inline int restore_fp_ctl(u32 *fpc)
 		return 0;
 
 	asm volatile(
-		"0:	lfpc    %1\n"
-		"	la	%0,0\n"
+		"	lfpc    %1\n"
+		"0:	la	%0,0\n"
 		"1:\n"
 		EX_TABLE(0b,1b)
 		: "=d" (rc) : "Q" (*fpc), "0" (-EINVAL));

arch/s390/kernel/head.S

@@ -437,11 +437,11 @@ ENTRY(startup_kdump)
 
 #if defined(CONFIG_64BIT)
 #if defined(CONFIG_MARCH_ZEC12)
-	.long 3, 0xc100efea, 0xf46ce800, 0x00400000
+	.long 3, 0xc100eff2, 0xf46ce800, 0x00400000
 #elif defined(CONFIG_MARCH_Z196)
-	.long 2, 0xc100efea, 0xf46c0000
+	.long 2, 0xc100eff2, 0xf46c0000
 #elif defined(CONFIG_MARCH_Z10)
-	.long 2, 0xc100efea, 0xf0680000
+	.long 2, 0xc100eff2, 0xf0680000
 #elif defined(CONFIG_MARCH_Z9_109)
 	.long 1, 0xc100efc2
 #elif defined(CONFIG_MARCH_Z990)

arch/s390/kernel/ptrace.c

@@ -334,9 +334,14 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 			unsigned long mask = PSW_MASK_USER;
 
 			mask |= is_ri_task(child) ? PSW_MASK_RI : 0;
-			if ((data & ~mask) != PSW_USER_BITS)
+			if ((data ^ PSW_USER_BITS) & ~mask)
+				/* Invalid psw mask. */
+				return -EINVAL;
+			if ((data & PSW_MASK_ASC) == PSW_ASC_HOME)
+				/* Invalid address-space-control bits */
 				return -EINVAL;
 			if ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA))
+				/* Invalid addressing mode bits */
 				return -EINVAL;
 		}
 		*(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data;
@@ -672,9 +677,12 @@ static int __poke_user_compat(struct task_struct *child,
 
 			mask |= is_ri_task(child) ? PSW32_MASK_RI : 0;
 			/* Build a 64 bit psw mask from 31 bit mask. */
-			if ((tmp & ~mask) != PSW32_USER_BITS)
+			if ((tmp ^ PSW32_USER_BITS) & ~mask)
 				/* Invalid psw mask. */
 				return -EINVAL;
+			if ((data & PSW32_MASK_ASC) == PSW32_ASC_HOME)
+				/* Invalid address-space-control bits */
+				return -EINVAL;
 			regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) |
 				(regs->psw.mask & PSW_MASK_BA) |
 				(__u64)(tmp & mask) << 32;

arch/s390/pci/pci.c

@@ -48,13 +48,10 @@
 static LIST_HEAD(zpci_list);
 static DEFINE_SPINLOCK(zpci_list_lock);
 
-static void zpci_enable_irq(struct irq_data *data);
-static void zpci_disable_irq(struct irq_data *data);
-
 static struct irq_chip zpci_irq_chip = {
 	.name = "zPCI",
-	.irq_unmask = zpci_enable_irq,
-	.irq_mask = zpci_disable_irq,
+	.irq_unmask = unmask_msi_irq,
+	.irq_mask = mask_msi_irq,
 };
 
 static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES);
@@ -244,43 +241,6 @@ static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len)
 	return rc;
 }
 
-static int zpci_msi_set_mask_bits(struct msi_desc *msi, u32 mask, u32 flag)
-{
-	int offset, pos;
-	u32 mask_bits;
-
-	if (msi->msi_attrib.is_msix) {
-		offset = msi->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
-			PCI_MSIX_ENTRY_VECTOR_CTRL;
-		msi->masked = readl(msi->mask_base + offset);
-		writel(flag, msi->mask_base + offset);
-	} else if (msi->msi_attrib.maskbit) {
-		pos = (long) msi->mask_base;
-		pci_read_config_dword(msi->dev, pos, &mask_bits);
-		mask_bits &= ~(mask);
-		mask_bits |= flag & mask;
-		pci_write_config_dword(msi->dev, pos, mask_bits);
-	} else
-		return 0;
-
-	msi->msi_attrib.maskbit = !!flag;
-	return 1;
-}
-
-static void zpci_enable_irq(struct irq_data *data)
-{
-	struct msi_desc *msi = irq_get_msi_desc(data->irq);
-
-	zpci_msi_set_mask_bits(msi, 1, 0);
-}
-
-static void zpci_disable_irq(struct irq_data *data)
-{
-	struct msi_desc *msi = irq_get_msi_desc(data->irq);
-
-	zpci_msi_set_mask_bits(msi, 1, 1);
-}
-
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
 }
@@ -487,7 +447,10 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev)
 
 	/* Release MSI interrupts */
 	list_for_each_entry(msi, &pdev->msi_list, list) {
-		zpci_msi_set_mask_bits(msi, 1, 1);
+		if (msi->msi_attrib.is_msix)
+			default_msix_mask_irq(msi, 1);
+		else
+			default_msi_mask_irq(msi, 1, 1);
 		irq_set_msi_desc(msi->irq, NULL);
 		irq_free_desc(msi->irq);
 		msi->msg.address_lo = 0;

arch/sh/Makefile

@@ -32,7 +32,8 @@ endif
 
 cflags-$(CONFIG_CPU_SH2)		:= $(call cc-option,-m2,)
 cflags-$(CONFIG_CPU_SH2A)		+= $(call cc-option,-m2a,) \
-					   $(call cc-option,-m2a-nofpu,)
+					   $(call cc-option,-m2a-nofpu,) \
+					   $(call cc-option,-m4-nofpu,)
 cflags-$(CONFIG_CPU_SH3)		:= $(call cc-option,-m3,)
 cflags-$(CONFIG_CPU_SH4)		:= $(call cc-option,-m4,) \
 	$(call cc-option,-mno-implicit-fp,-m4-nofpu)

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

@@ -410,8 +410,9 @@
 #define __NR_finit_module	342
 #define __NR_sched_setattr	343
 #define __NR_sched_getattr	344
+#define __NR_renameat2		345
 
-#define NR_syscalls		345
+#define NR_syscalls		346
 
 /* Bitmask values returned from kern_features system call.  */
 #define KERN_FEATURE_MIXED_MODE_STACK	0x00000001

arch/sparc/kernel/sys32.S

@@ -48,6 +48,7 @@ SIGN1(sys32_futex, compat_sys_futex, %o1)
 SIGN1(sys32_recvfrom, compat_sys_recvfrom, %o0)
 SIGN1(sys32_recvmsg, compat_sys_recvmsg, %o0)
 SIGN1(sys32_sendmsg, compat_sys_sendmsg, %o0)
+SIGN2(sys32_renameat2, sys_renameat2, %o0, %o2)
 
 	.globl		sys32_mmap2
 sys32_mmap2:

arch/sparc/kernel/systbls_32.S

@@ -86,3 +86,4 @@ sys_call_table:
 /*330*/	.long sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, sys_open_by_handle_at, sys_clock_adjtime
 /*335*/	.long sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev
 /*340*/	.long sys_ni_syscall, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
+/*345*/	.long sys_renameat2

arch/sparc/kernel/systbls_64.S

@@ -87,6 +87,7 @@ sys_call_table32:
 /*330*/	.word compat_sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, compat_sys_open_by_handle_at, compat_sys_clock_adjtime
 	.word sys_syncfs, compat_sys_sendmmsg, sys_setns, compat_sys_process_vm_readv, compat_sys_process_vm_writev
 /*340*/	.word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
+	.word sys32_renameat2
 
 #endif /* CONFIG_COMPAT */
 
@@ -165,3 +166,4 @@ sys_call_table:
 /*330*/	.word sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, sys_open_by_handle_at, sys_clock_adjtime
 	.word sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev
 /*340*/	.word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
+	.word sys_renameat2

arch/x86/include/asm/irqflags.h

@@ -129,7 +129,7 @@ static inline notrace unsigned long arch_local_irq_save(void)
 
 #define PARAVIRT_ADJUST_EXCEPTION_FRAME	/*  */
 
-#define INTERRUPT_RETURN	iretq
+#define INTERRUPT_RETURN	jmp native_iret
 #define USERGS_SYSRET64				\
 	swapgs;					\
 	sysretq;

arch/x86/kernel/cpu/intel.c

@@ -370,6 +370,17 @@ static void init_intel(struct cpuinfo_x86 *c)
 	 */
 	detect_extended_topology(c);
 
+	if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
+		/*
+		 * let's use the legacy cpuid vector 0x1 and 0x4 for topology
+		 * detection.
+		 */
+		c->x86_max_cores = intel_num_cpu_cores(c);
+#ifdef CONFIG_X86_32
+		detect_ht(c);
+#endif
+	}
+
 	l2 = init_intel_cacheinfo(c);
 	if (c->cpuid_level > 9) {
 		unsigned eax = cpuid_eax(10);
@@ -438,17 +449,6 @@ static void init_intel(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_P3);
 #endif
 
-	if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
-		/*
-		 * let's use the legacy cpuid vector 0x1 and 0x4 for topology
-		 * detection.
-		 */
-		c->x86_max_cores = intel_num_cpu_cores(c);
-#ifdef CONFIG_X86_32
-		detect_ht(c);
-#endif
-	}
-
 	/* Work around errata */
 	srat_detect_node(c);
 

arch/x86/kernel/cpu/intel_cacheinfo.c

@@ -730,6 +730,18 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
 #endif
 	}
 
+#ifdef CONFIG_X86_HT
+	/*
+	 * If cpu_llc_id is not yet set, this means cpuid_level < 4 which in
+	 * turns means that the only possibility is SMT (as indicated in
+	 * cpuid1). Since cpuid2 doesn't specify shared caches, and we know
+	 * that SMT shares all caches, we can unconditionally set cpu_llc_id to
+	 * c->phys_proc_id.
+	 */
+	if (per_cpu(cpu_llc_id, cpu) == BAD_APICID)
+		per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
+#endif
+
 	c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d));
 
 	return l2;

arch/x86/kernel/cpu/mcheck/mce.c

@@ -2451,6 +2451,12 @@ static __init int mcheck_init_device(void)
 	for_each_online_cpu(i) {
 		err = mce_device_create(i);
 		if (err) {
+			/*
+			 * Register notifier anyway (and do not unreg it) so
+			 * that we don't leave undeleted timers, see notifier
+			 * callback above.
+			 */
+			__register_hotcpu_notifier(&mce_cpu_notifier);
 			cpu_notifier_register_done();
 			goto err_device_create;
 		}
@@ -2471,10 +2477,6 @@ static __init int mcheck_init_device(void)
 err_register:
 	unregister_syscore_ops(&mce_syscore_ops);
 
-	cpu_notifier_register_begin();
-	__unregister_hotcpu_notifier(&mce_cpu_notifier);
-	cpu_notifier_register_done();
-
 err_device_create:
 	/*
 	 * We didn't keep track of which devices were created above, but

arch/x86/kernel/cpu/perf_event.c

@@ -118,6 +118,9 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event)
 			continue;
 		if (event->attr.config1 & ~er->valid_mask)
 			return -EINVAL;
+		/* Check if the extra msrs can be safely accessed*/
+		if (!er->extra_msr_access)
+			return -ENXIO;
 
 		reg->idx = er->idx;
 		reg->config = event->attr.config1;

arch/x86/kernel/cpu/perf_event.h

@@ -295,14 +295,16 @@ struct extra_reg {
 	u64			config_mask;
 	u64			valid_mask;
 	int			idx;  /* per_xxx->regs[] reg index */
+	bool			extra_msr_access;
 };
 
 #define EVENT_EXTRA_REG(e, ms, m, vm, i) {	\
-	.event = (e),		\
-	.msr = (ms),		\
-	.config_mask = (m),	\
-	.valid_mask = (vm),	\
-	.idx = EXTRA_REG_##i,	\
+	.event = (e),			\
+	.msr = (ms),			\
+	.config_mask = (m),		\
+	.valid_mask = (vm),		\
+	.idx = EXTRA_REG_##i,		\
+	.extra_msr_access = true,	\
 	}
 
 #define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx)	\

arch/x86/kernel/cpu/perf_event_intel.c

@@ -2182,6 +2182,41 @@ static void intel_snb_check_microcode(void)
 	}
 }
 
+/*
+ * Under certain circumstances, access certain MSR may cause #GP.
+ * The function tests if the input MSR can be safely accessed.
+ */
+static bool check_msr(unsigned long msr, u64 mask)
+{
+	u64 val_old, val_new, val_tmp;
+
+	/*
+	 * Read the current value, change it and read it back to see if it
+	 * matches, this is needed to detect certain hardware emulators
+	 * (qemu/kvm) that don't trap on the MSR access and always return 0s.
+	 */
+	if (rdmsrl_safe(msr, &val_old))
+		return false;
+
+	/*
+	 * Only change the bits which can be updated by wrmsrl.
+	 */
+	val_tmp = val_old ^ mask;
+	if (wrmsrl_safe(msr, val_tmp) ||
+	    rdmsrl_safe(msr, &val_new))
+		return false;
+
+	if (val_new != val_tmp)
+		return false;
+
+	/* Here it's sure that the MSR can be safely accessed.
+	 * Restore the old value and return.
+	 */
+	wrmsrl(msr, val_old);
+
+	return true;
+}
+
 static __init void intel_sandybridge_quirk(void)
 {
 	x86_pmu.check_microcode = intel_snb_check_microcode;
@@ -2271,7 +2306,8 @@ __init int intel_pmu_init(void)
 	union cpuid10_ebx ebx;
 	struct event_constraint *c;
 	unsigned int unused;
-	int version;
+	struct extra_reg *er;
+	int version, i;
 
 	if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
 		switch (boot_cpu_data.x86) {
@@ -2474,6 +2510,9 @@ __init int intel_pmu_init(void)
 	case 62: /* IvyBridge EP */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
+		/* dTLB-load-misses on IVB is different than SNB */
+		hw_cache_event_ids[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = 0x8108; /* DTLB_LOAD_MISSES.DEMAND_LD_MISS_CAUSES_A_WALK */
+
 		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
 		       sizeof(hw_cache_extra_regs));
 
@@ -2574,6 +2613,34 @@ __init int intel_pmu_init(void)
 		}
 	}
 
+	/*
+	 * Access LBR MSR may cause #GP under certain circumstances.
+	 * E.g. KVM doesn't support LBR MSR
+	 * Check all LBT MSR here.
+	 * Disable LBR access if any LBR MSRs can not be accessed.
+	 */
+	if (x86_pmu.lbr_nr && !check_msr(x86_pmu.lbr_tos, 0x3UL))
+		x86_pmu.lbr_nr = 0;
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		if (!(check_msr(x86_pmu.lbr_from + i, 0xffffUL) &&
+		      check_msr(x86_pmu.lbr_to + i, 0xffffUL)))
+			x86_pmu.lbr_nr = 0;
+	}
+
+	/*
+	 * Access extra MSR may cause #GP under certain circumstances.
+	 * E.g. KVM doesn't support offcore event
+	 * Check all extra_regs here.
+	 */
+	if (x86_pmu.extra_regs) {
+		for (er = x86_pmu.extra_regs; er->msr; er++) {
+			er->extra_msr_access = check_msr(er->msr, 0x1ffUL);
+			/* Disable LBR select mapping */
+			if ((er->idx == EXTRA_REG_LBR) && !er->extra_msr_access)
+				x86_pmu.lbr_sel_map = NULL;
+		}
+	}
+
 	/* Support full width counters using alternative MSR range */
 	if (x86_pmu.intel_cap.full_width_write) {
 		x86_pmu.max_period = x86_pmu.cntval_mask;

arch/x86/kernel/cpu/perf_event_intel_ds.c

@@ -311,9 +311,11 @@ static int alloc_bts_buffer(int cpu)
 	if (!x86_pmu.bts)
 		return 0;
 
-	buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL, node);
-	if (unlikely(!buffer))
+	buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
+	if (unlikely(!buffer)) {
+		WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__);
 		return -ENOMEM;
+	}
 
 	max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
 	thresh = max / 16;

arch/x86/kernel/cpu/perf_event_intel_uncore.c

@@ -550,16 +550,16 @@ static struct extra_reg snbep_uncore_cbox_extra_regs[] = {
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xc),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xa),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xa),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xc),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xa),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xa),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2),
@@ -1222,6 +1222,7 @@ static struct extra_reg ivt_uncore_cbox_extra_regs[] = {
 	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
 				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2),
+
 	SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc),
@@ -1245,7 +1246,7 @@ static struct extra_reg ivt_uncore_cbox_extra_regs[] = {
 	SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18),

arch/x86/kernel/entry_32.S

@@ -425,8 +425,8 @@ sysenter_do_call:
 	cmpl $(NR_syscalls), %eax
 	jae sysenter_badsys
 	call *sys_call_table(,%eax,4)
-	movl %eax,PT_EAX(%esp)
 sysenter_after_call:
+	movl %eax,PT_EAX(%esp)
 	LOCKDEP_SYS_EXIT
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
@@ -502,6 +502,7 @@ ENTRY(system_call)
 	jae syscall_badsys
 syscall_call:
 	call *sys_call_table(,%eax,4)
+syscall_after_call:
 	movl %eax,PT_EAX(%esp)		# store the return value
 syscall_exit:
 	LOCKDEP_SYS_EXIT
@@ -675,12 +676,12 @@ syscall_fault:
 END(syscall_fault)
 
 syscall_badsys:
-	movl $-ENOSYS,PT_EAX(%esp)
-	jmp syscall_exit
+	movl $-ENOSYS,%eax
+	jmp syscall_after_call
 END(syscall_badsys)
 
 sysenter_badsys:
-	movl $-ENOSYS,PT_EAX(%esp)
+	movl $-ENOSYS,%eax
 	jmp sysenter_after_call
 END(syscall_badsys)
 	CFI_ENDPROC

arch/x86/kernel/entry_64.S

@@ -830,27 +830,24 @@ restore_args:
 	RESTORE_ARGS 1,8,1
 
 irq_return:
+	INTERRUPT_RETURN
+
+ENTRY(native_iret)
 	/*
 	 * Are we returning to a stack segment from the LDT?  Note: in
 	 * 64-bit mode SS:RSP on the exception stack is always valid.
 	 */
 #ifdef CONFIG_X86_ESPFIX64
 	testb $4,(SS-RIP)(%rsp)
-	jnz irq_return_ldt
+	jnz native_irq_return_ldt
 #endif
 
-irq_return_iret:
-	INTERRUPT_RETURN
-	_ASM_EXTABLE(irq_return_iret, bad_iret)
-
-#ifdef CONFIG_PARAVIRT
-ENTRY(native_iret)
+native_irq_return_iret:
 	iretq
-	_ASM_EXTABLE(native_iret, bad_iret)
-#endif
+	_ASM_EXTABLE(native_irq_return_iret, bad_iret)
 
 #ifdef CONFIG_X86_ESPFIX64
-irq_return_ldt:
+native_irq_return_ldt:
 	pushq_cfi %rax
 	pushq_cfi %rdi
 	SWAPGS
@@ -872,7 +869,7 @@ irq_return_ldt:
 	SWAPGS
 	movq %rax,%rsp
 	popq_cfi %rax
-	jmp irq_return_iret
+	jmp native_irq_return_iret
 #endif
 
 	.section .fixup,"ax"
@@ -956,13 +953,8 @@ __do_double_fault:
 	cmpl $__KERNEL_CS,CS(%rdi)
 	jne do_double_fault
 	movq RIP(%rdi),%rax
-	cmpq $irq_return_iret,%rax
-#ifdef CONFIG_PARAVIRT
-	je 1f
-	cmpq $native_iret,%rax
-#endif
+	cmpq $native_irq_return_iret,%rax
 	jne do_double_fault		/* This shouldn't happen... */
-1:
 	movq PER_CPU_VAR(kernel_stack),%rax
 	subq $(6*8-KERNEL_STACK_OFFSET),%rax	/* Reset to original stack */
 	movq %rax,RSP(%rdi)
@@ -1428,7 +1420,7 @@ error_sti:
  */
 error_kernelspace:
 	incl %ebx
-	leaq irq_return_iret(%rip),%rcx
+	leaq native_irq_return_iret(%rip),%rcx
 	cmpq %rcx,RIP+8(%rsp)
 	je error_swapgs
 	movl %ecx,%eax	/* zero extend */

arch/x86/kernel/kprobes/core.c

@@ -574,6 +574,9 @@ int kprobe_int3_handler(struct pt_regs *regs)
 	struct kprobe *p;
 	struct kprobe_ctlblk *kcb;
 
+	if (user_mode_vm(regs))
+		return 0;
+
 	addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t));
 	/*
 	 * We don't want to be preempted for the entire

arch/x86/kernel/paravirt_patch_64.c

@@ -6,7 +6,6 @@ DEF_NATIVE(pv_irq_ops, irq_disable, "cli");
 DEF_NATIVE(pv_irq_ops, irq_enable, "sti");
 DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq");
 DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax");
-DEF_NATIVE(pv_cpu_ops, iret, "iretq");
 DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
 DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
 DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
@@ -50,7 +49,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_irq_ops, save_fl);
 		PATCH_SITE(pv_irq_ops, irq_enable);
 		PATCH_SITE(pv_irq_ops, irq_disable);
-		PATCH_SITE(pv_cpu_ops, iret);
 		PATCH_SITE(pv_cpu_ops, irq_enable_sysexit);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret32);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret64);

arch/x86/kvm/x86.c

@@ -5887,6 +5887,18 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 			kvm_x86_ops->set_nmi(vcpu);
 		}
 	} else if (kvm_cpu_has_injectable_intr(vcpu)) {
+		/*
+		 * Because interrupts can be injected asynchronously, we are
+		 * calling check_nested_events again here to avoid a race condition.
+		 * See https://lkml.org/lkml/2014/7/2/60 for discussion about this
+		 * proposal and current concerns.  Perhaps we should be setting
+		 * KVM_REQ_EVENT only on certain events and not unconditionally?
+		 */
+		if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
+			r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
+			if (r != 0)
+				return r;
+		}
 		if (kvm_x86_ops->interrupt_allowed(vcpu)) {
 			kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu),
 					    false);

arch/x86/xen/grant-table.c

@@ -36,99 +36,133 @@
 
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/slab.h>
 #include <linux/vmalloc.h>
 
 #include <xen/interface/xen.h>
 #include <xen/page.h>
 #include <xen/grant_table.h>
+#include <xen/xen.h>
 
 #include <asm/pgtable.h>
 
-static int map_pte_fn(pte_t *pte, struct page *pmd_page,
-		      unsigned long addr, void *data)
-{
-	unsigned long **frames = (unsigned long **)data;
-
-	set_pte_at(&init_mm, addr, pte, mfn_pte((*frames)[0], PAGE_KERNEL));
-	(*frames)++;
-	return 0;
-}
-
-/*
- * This function is used to map shared frames to store grant status. It is
- * different from map_pte_fn above, the frames type here is uint64_t.
- */
-static int map_pte_fn_status(pte_t *pte, struct page *pmd_page,
-			     unsigned long addr, void *data)
-{
-	uint64_t **frames = (uint64_t **)data;
-
-	set_pte_at(&init_mm, addr, pte, mfn_pte((*frames)[0], PAGE_KERNEL));
-	(*frames)++;
-	return 0;
-}
-
-static int unmap_pte_fn(pte_t *pte, struct page *pmd_page,
-			unsigned long addr, void *data)
-{
-
-	set_pte_at(&init_mm, addr, pte, __pte(0));
-	return 0;
-}
+static struct gnttab_vm_area {
+	struct vm_struct *area;
+	pte_t **ptes;
+} gnttab_shared_vm_area, gnttab_status_vm_area;
 
 int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
 			   unsigned long max_nr_gframes,
 			   void **__shared)
 {
-	int rc;
 	void *shared = *__shared;
+	unsigned long addr;
+	unsigned long i;
 
-	if (shared == NULL) {
-		struct vm_struct *area =
-			alloc_vm_area(PAGE_SIZE * max_nr_gframes, NULL);
-		BUG_ON(area == NULL);
-		shared = area->addr;
-		*__shared = shared;
+	if (shared == NULL)
+		*__shared = shared = gnttab_shared_vm_area.area->addr;
+
+	addr = (unsigned long)shared;
+
+	for (i = 0; i < nr_gframes; i++) {
+		set_pte_at(&init_mm, addr, gnttab_shared_vm_area.ptes[i],
+			   mfn_pte(frames[i], PAGE_KERNEL));
+		addr += PAGE_SIZE;
 	}
 
-	rc = apply_to_page_range(&init_mm, (unsigned long)shared,
-				 PAGE_SIZE * nr_gframes,
-				 map_pte_fn, &frames);
-	return rc;
+	return 0;
 }
 
 int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes,
 			   unsigned long max_nr_gframes,
 			   grant_status_t **__shared)
 {
-	int rc;
 	grant_status_t *shared = *__shared;
+	unsigned long addr;
+	unsigned long i;
 
-	if (shared == NULL) {
-		/* No need to pass in PTE as we are going to do it
-		 * in apply_to_page_range anyhow. */
-		struct vm_struct *area =
-			alloc_vm_area(PAGE_SIZE * max_nr_gframes, NULL);
-		BUG_ON(area == NULL);
-		shared = area->addr;
-		*__shared = shared;
+	if (shared == NULL)
+		*__shared = shared = gnttab_status_vm_area.area->addr;
+
+	addr = (unsigned long)shared;
+
+	for (i = 0; i < nr_gframes; i++) {
+		set_pte_at(&init_mm, addr, gnttab_status_vm_area.ptes[i],
+			   mfn_pte(frames[i], PAGE_KERNEL));
+		addr += PAGE_SIZE;
 	}
 
-	rc = apply_to_page_range(&init_mm, (unsigned long)shared,
-				 PAGE_SIZE * nr_gframes,
-				 map_pte_fn_status, &frames);
-	return rc;
+	return 0;
 }
 
 void arch_gnttab_unmap(void *shared, unsigned long nr_gframes)
 {
-	apply_to_page_range(&init_mm, (unsigned long)shared,
-			    PAGE_SIZE * nr_gframes, unmap_pte_fn, NULL);
+	pte_t **ptes;
+	unsigned long addr;
+	unsigned long i;
+
+	if (shared == gnttab_status_vm_area.area->addr)
+		ptes = gnttab_status_vm_area.ptes;
+	else
+		ptes = gnttab_shared_vm_area.ptes;
+
+	addr = (unsigned long)shared;
+
+	for (i = 0; i < nr_gframes; i++) {
+		set_pte_at(&init_mm, addr, ptes[i], __pte(0));
+		addr += PAGE_SIZE;
+	}
 }
+
+static int arch_gnttab_valloc(struct gnttab_vm_area *area, unsigned nr_frames)
+{
+	area->ptes = kmalloc(sizeof(pte_t *) * nr_frames, GFP_KERNEL);
+	if (area->ptes == NULL)
+		return -ENOMEM;
+
+	area->area = alloc_vm_area(PAGE_SIZE * nr_frames, area->ptes);
+	if (area->area == NULL) {
+		kfree(area->ptes);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void arch_gnttab_vfree(struct gnttab_vm_area *area)
+{
+	free_vm_area(area->area);
+	kfree(area->ptes);
+}
+
+int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status)
+{
+	int ret;
+
+	if (!xen_pv_domain())
+		return 0;
+
+	ret = arch_gnttab_valloc(&gnttab_shared_vm_area, nr_shared);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Always allocate the space for the status frames in case
+	 * we're migrated to a host with V2 support.
+	 */
+	ret = arch_gnttab_valloc(&gnttab_status_vm_area, nr_status);
+	if (ret < 0)
+		goto err;
+
+	return 0;
+  err:
+	arch_gnttab_vfree(&gnttab_shared_vm_area);
+	return -ENOMEM;
+}
+
 #ifdef CONFIG_XEN_PVH
 #include <xen/balloon.h>
 #include <xen/events.h>
-#include <xen/xen.h>
 #include <linux/slab.h>
 static int __init xlated_setup_gnttab_pages(void)
 {

arch/xtensa/kernel/vectors.S

@@ -376,38 +376,42 @@ _DoubleExceptionVector_WindowOverflow:
 	beqz	a2, 1f		# if at start of vector, don't restore
 
 	addi	a0, a0, -128
-	bbsi	a0, 8, 1f	# don't restore except for overflow 8 and 12
-	bbsi	a0, 7, 2f
+	bbsi.l	a0, 8, 1f	# don't restore except for overflow 8 and 12
+
+	/*
+	 * This fixup handler is for the extremely unlikely case where the
+	 * overflow handler's reference thru a0 gets a hardware TLB refill
+	 * that bumps out the (distinct, aliasing) TLB entry that mapped its
+	 * prior references thru a9/a13, and where our reference now thru
+	 * a9/a13 gets a 2nd-level miss exception (not hardware TLB refill).
+	 */
+	movi	a2, window_overflow_restore_a0_fixup
+	s32i	a2, a3, EXC_TABLE_FIXUP
+	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	xsr	a3, excsave1
+
+	bbsi.l	a0, 7, 2f
 
 	/*
 	 * Restore a0 as saved by _WindowOverflow8().
-	 *
-	 * FIXME:  we really need a fixup handler for this L32E,
-	 * for the extremely unlikely case where the overflow handler's
-	 * reference thru a0 gets a hardware TLB refill that bumps out
-	 * the (distinct, aliasing) TLB entry that mapped its prior
-	 * references thru a9, and where our reference now thru a9
-	 * gets a 2nd-level miss exception (not hardware TLB refill).
 	 */
 
-	l32e	a2, a9, -16
-	wsr	a2, depc	# replace the saved a0
-	j	1f
+	l32e	a0, a9, -16
+	wsr	a0, depc	# replace the saved a0
+	j	3f
 
 2:
 	/*
 	 * Restore a0 as saved by _WindowOverflow12().
-	 *
-	 * FIXME:  we really need a fixup handler for this L32E,
-	 * for the extremely unlikely case where the overflow handler's
-	 * reference thru a0 gets a hardware TLB refill that bumps out
-	 * the (distinct, aliasing) TLB entry that mapped its prior
-	 * references thru a13, and where our reference now thru a13
-	 * gets a 2nd-level miss exception (not hardware TLB refill).
 	 */
 
-	l32e	a2, a13, -16
-	wsr	a2, depc	# replace the saved a0
+	l32e	a0, a13, -16
+	wsr	a0, depc	# replace the saved a0
+3:
+	xsr	a3, excsave1
+	movi	a0, 0
+	s32i	a0, a3, EXC_TABLE_FIXUP
+	s32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
 1:
 	/*
 	 * Restore WindowBase while leaving all address registers restored.
@@ -449,6 +453,7 @@ _DoubleExceptionVector_WindowOverflow:
 
 	s32i	a0, a2, PT_DEPC
 
+_DoubleExceptionVector_handle_exception:
 	addx4	a0, a0, a3
 	l32i	a0, a0, EXC_TABLE_FAST_USER
 	xsr	a3, excsave1
@@ -464,10 +469,119 @@ _DoubleExceptionVector_WindowOverflow:
 	rotw	-3
 	j	1b
 
-	.end literal_prefix
 
 ENDPROC(_DoubleExceptionVector)
 
+/*
+ * Fixup handler for TLB miss in double exception handler for window owerflow.
+ * We get here with windowbase set to the window that was being spilled and
+ * a0 trashed. a0 bit 7 determines if this is a call8 (bit clear) or call12
+ * (bit set) window.
+ *
+ * We do the following here:
+ * - go to the original window retaining a0 value;
+ * - set up exception stack to return back to appropriate a0 restore code
+ *   (we'll need to rotate window back and there's no place to save this
+ *    information, use different return address for that);
+ * - handle the exception;
+ * - go to the window that was being spilled;
+ * - set up window_overflow_restore_a0_fixup as a fixup routine;
+ * - reload a0;
+ * - restore the original window;
+ * - reset the default fixup routine;
+ * - return to user. By the time we get to this fixup handler all information
+ *   about the conditions of the original double exception that happened in
+ *   the window overflow handler is lost, so we just return to userspace to
+ *   retry overflow from start.
+ *
+ * a0: value of depc, original value in depc
+ * a2: trashed, original value in EXC_TABLE_DOUBLE_SAVE
+ * a3: exctable, original value in excsave1
+ */
+
+ENTRY(window_overflow_restore_a0_fixup)
+
+	rsr	a0, ps
+	extui	a0, a0, PS_OWB_SHIFT, PS_OWB_WIDTH
+	rsr	a2, windowbase
+	sub	a0, a2, a0
+	extui	a0, a0, 0, 3
+	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	xsr	a3, excsave1
+
+	_beqi	a0, 1, .Lhandle_1
+	_beqi	a0, 3, .Lhandle_3
+
+	.macro	overflow_fixup_handle_exception_pane n
+
+	rsr	a0, depc
+	rotw	-\n
+
+	xsr	a3, excsave1
+	wsr	a2, depc
+	l32i	a2, a3, EXC_TABLE_KSTK
+	s32i	a0, a2, PT_AREG0
+
+	movi	a0, .Lrestore_\n
+	s32i	a0, a2, PT_DEPC
+	rsr	a0, exccause
+	j	_DoubleExceptionVector_handle_exception
+
+	.endm
+
+	overflow_fixup_handle_exception_pane 2
+.Lhandle_1:
+	overflow_fixup_handle_exception_pane 1
+.Lhandle_3:
+	overflow_fixup_handle_exception_pane 3
+
+	.macro	overflow_fixup_restore_a0_pane n
+
+	rotw	\n
+	/* Need to preserve a0 value here to be able to handle exception
+	 * that may occur on a0 reload from stack. It may occur because
+	 * TLB miss handler may not be atomic and pointer to page table
+	 * may be lost before we get here. There are no free registers,
+	 * so we need to use EXC_TABLE_DOUBLE_SAVE area.
+	 */
+	xsr	a3, excsave1
+	s32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	movi	a2, window_overflow_restore_a0_fixup
+	s32i	a2, a3, EXC_TABLE_FIXUP
+	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	xsr	a3, excsave1
+	bbsi.l	a0, 7, 1f
+	l32e	a0, a9, -16
+	j	2f
+1:
+	l32e	a0, a13, -16
+2:
+	rotw	-\n
+
+	.endm
+
+.Lrestore_2:
+	overflow_fixup_restore_a0_pane 2
+
+.Lset_default_fixup:
+	xsr	a3, excsave1
+	s32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	movi	a2, 0
+	s32i	a2, a3, EXC_TABLE_FIXUP
+	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	xsr	a3, excsave1
+	rfe
+
+.Lrestore_1:
+	overflow_fixup_restore_a0_pane 1
+	j	.Lset_default_fixup
+.Lrestore_3:
+	overflow_fixup_restore_a0_pane 3
+	j	.Lset_default_fixup
+
+ENDPROC(window_overflow_restore_a0_fixup)
+
+	.end literal_prefix
 /*
  * Debug interrupt vector
  *

arch/xtensa/kernel/vmlinux.lds.S

@@ -269,13 +269,13 @@ SECTIONS
 		  .UserExceptionVector.literal)
   SECTION_VECTOR (_DoubleExceptionVector_literal,
 		  .DoubleExceptionVector.literal,
-		  DOUBLEEXC_VECTOR_VADDR - 16,
+		  DOUBLEEXC_VECTOR_VADDR - 40,
 		  SIZEOF(.UserExceptionVector.text),
 		  .UserExceptionVector.text)
   SECTION_VECTOR (_DoubleExceptionVector_text,
 		  .DoubleExceptionVector.text,
 		  DOUBLEEXC_VECTOR_VADDR,
-		  32,
+		  40,
 		  .DoubleExceptionVector.literal)
 
   . = (LOADADDR( .DoubleExceptionVector.text ) + SIZEOF( .DoubleExceptionVector.text ) + 3) & ~ 3;

arch/xtensa/mm/init.c

@@ -191,7 +191,7 @@ int __init mem_reserve(unsigned long start, unsigned long end, int must_exist)
 		return -EINVAL;
 	}
 
-	if (it && start - it->start < bank_sz) {
+	if (it && start - it->start <= bank_sz) {
 		if (start == it->start) {
 			if (end - it->start < bank_sz) {
 				it->start = end;

block/blk-cgroup.c

@@ -872,6 +872,13 @@ void blkcg_drain_queue(struct request_queue *q)
 {
 	lockdep_assert_held(q->queue_lock);
 
+	/*
+	 * @q could be exiting and already have destroyed all blkgs as
+	 * indicated by NULL root_blkg.  If so, don't confuse policies.
+	 */
+	if (!q->root_blkg)
+		return;
+
 	blk_throtl_drain(q);
 }
 

block/blk-tag.c

@@ -27,18 +27,15 @@ struct request *blk_queue_find_tag(struct request_queue *q, int tag)
 EXPORT_SYMBOL(blk_queue_find_tag);
 
 /**
- * __blk_free_tags - release a given set of tag maintenance info
+ * blk_free_tags - release a given set of tag maintenance info
  * @bqt:	the tag map to free
  *
- * Tries to free the specified @bqt.  Returns true if it was
- * actually freed and false if there are still references using it
+ * Drop the reference count on @bqt and frees it when the last reference
+ * is dropped.
  */
-static int __blk_free_tags(struct blk_queue_tag *bqt)
+void blk_free_tags(struct blk_queue_tag *bqt)
 {
-	int retval;
-
-	retval = atomic_dec_and_test(&bqt->refcnt);
-	if (retval) {
+	if (atomic_dec_and_test(&bqt->refcnt)) {
 		BUG_ON(find_first_bit(bqt->tag_map, bqt->max_depth) <
 							bqt->max_depth);
 
@@ -50,9 +47,8 @@ static int __blk_free_tags(struct blk_queue_tag *bqt)
 
 		kfree(bqt);
 	}
-
-	return retval;
 }
+EXPORT_SYMBOL(blk_free_tags);
 
 /**
  * __blk_queue_free_tags - release tag maintenance info
@@ -69,27 +65,12 @@ void __blk_queue_free_tags(struct request_queue *q)
 	if (!bqt)
 		return;
 
-	__blk_free_tags(bqt);
+	blk_free_tags(bqt);
 
 	q->queue_tags = NULL;
 	queue_flag_clear_unlocked(QUEUE_FLAG_QUEUED, q);
 }
 
-/**
- * blk_free_tags - release a given set of tag maintenance info
- * @bqt:	the tag map to free
- *
- * For externally managed @bqt frees the map.  Callers of this
- * function must guarantee to have released all the queues that
- * might have been using this tag map.
- */
-void blk_free_tags(struct blk_queue_tag *bqt)
-{
-	if (unlikely(!__blk_free_tags(bqt)))
-		BUG();
-}
-EXPORT_SYMBOL(blk_free_tags);
-
 /**
  * blk_queue_free_tags - release tag maintenance info
  * @q:  the request queue for the device

block/compat_ioctl.c

@@ -690,6 +690,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKROSET:
 	case BLKDISCARD:
 	case BLKSECDISCARD:
+	case BLKZEROOUT:
 	/*
 	 * the ones below are implemented in blkdev_locked_ioctl,
 	 * but we call blkdev_ioctl, which gets the lock for us

crypto/af_alg.c

@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/net.h>
 #include <linux/rwsem.h>
+#include <linux/security.h>
 
 struct alg_type_list {
 	const struct af_alg_type *type;
@@ -243,6 +244,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock)
 
 	sock_init_data(newsock, sk2);
 	sock_graft(sk2, newsock);
+	security_sk_clone(sk, sk2);
 
 	err = type->accept(ask->private, sk2);
 	if (err) {

drivers/ata/ahci.c

@@ -456,6 +456,7 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 
 	/* Promise */
 	{ PCI_VDEVICE(PROMISE, 0x3f20), board_ahci },	/* PDC42819 */
+	{ PCI_VDEVICE(PROMISE, 0x3781), board_ahci },   /* FastTrak TX8660 ahci-mode */
 
 	/* Asmedia */
 	{ PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci },	/* ASM1060 */

drivers/ata/libata-core.c

@@ -4787,6 +4787,10 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words)
  *	ata_qc_new - Request an available ATA command, for queueing
  *	@ap: target port
  *
+ *	Some ATA host controllers may implement a queue depth which is less
+ *	than ATA_MAX_QUEUE. So we shouldn't allocate a tag which is beyond
+ *	the hardware limitation.
+ *
  *	LOCKING:
  *	None.
  */
@@ -4794,14 +4798,15 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words)
 static struct ata_queued_cmd *ata_qc_new(struct ata_port *ap)
 {
 	struct ata_queued_cmd *qc = NULL;
+	unsigned int max_queue = ap->host->n_tags;
 	unsigned int i, tag;
 
 	/* no command while frozen */
 	if (unlikely(ap->pflags & ATA_PFLAG_FROZEN))
 		return NULL;
 
-	for (i = 0; i < ATA_MAX_QUEUE; i++) {
-		tag = (i + ap->last_tag + 1) % ATA_MAX_QUEUE;
+	for (i = 0, tag = ap->last_tag + 1; i < max_queue; i++, tag++) {
+		tag = tag < max_queue ? tag : 0;
 
 		/* the last tag is reserved for internal command. */
 		if (tag == ATA_TAG_INTERNAL)
@@ -6088,6 +6093,7 @@ void ata_host_init(struct ata_host *host, struct device *dev,
 {
 	spin_lock_init(&host->lock);
 	mutex_init(&host->eh_mutex);
+	host->n_tags = ATA_MAX_QUEUE - 1;
 	host->dev = dev;
 	host->ops = ops;
 }
@@ -6169,6 +6175,8 @@ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht)
 {
 	int i, rc;
 
+	host->n_tags = clamp(sht->can_queue, 1, ATA_MAX_QUEUE - 1);
+
 	/* host must have been started */
 	if (!(host->flags & ATA_HOST_STARTED)) {
 		dev_err(host->dev, "BUG: trying to register unstarted host\n");

drivers/ata/libata-eh.c

@@ -1811,7 +1811,7 @@ static unsigned int ata_eh_analyze_tf(struct ata_queued_cmd *qc,
 	case ATA_DEV_ATA:
 		if (err & ATA_ICRC)
 			qc->err_mask |= AC_ERR_ATA_BUS;
-		if (err & ATA_UNC)
+		if (err & (ATA_UNC | ATA_AMNF))
 			qc->err_mask |= AC_ERR_MEDIA;
 		if (err & ATA_IDNF)
 			qc->err_mask |= AC_ERR_INVALID;
@@ -2556,11 +2556,12 @@ static void ata_eh_link_report(struct ata_link *link)
 		}
 
 		if (cmd->command != ATA_CMD_PACKET &&
-		    (res->feature & (ATA_ICRC | ATA_UNC | ATA_IDNF |
-				     ATA_ABORTED)))
-			ata_dev_err(qc->dev, "error: { %s%s%s%s}\n",
+		    (res->feature & (ATA_ICRC | ATA_UNC | ATA_AMNF |
+				     ATA_IDNF | ATA_ABORTED)))
+			ata_dev_err(qc->dev, "error: { %s%s%s%s%s}\n",
 			  res->feature & ATA_ICRC ? "ICRC " : "",
 			  res->feature & ATA_UNC ? "UNC " : "",
+			  res->feature & ATA_AMNF ? "AMNF " : "",
 			  res->feature & ATA_IDNF ? "IDNF " : "",
 			  res->feature & ATA_ABORTED ? "ABRT " : "");
 #endif

drivers/ata/pata_ep93xx.c

@@ -915,7 +915,7 @@ static int ep93xx_pata_probe(struct platform_device *pdev)
 	struct ep93xx_pata_data *drv_data;
 	struct ata_host *host;
 	struct ata_port *ap;
-	unsigned int irq;
+	int irq;
 	struct resource *mem_res;
 	void __iomem *ide_base;
 	int err;

drivers/block/drbd/drbd_nl.c

@@ -544,6 +544,12 @@ void conn_try_outdate_peer_async(struct drbd_connection *connection)
 	struct task_struct *opa;
 
 	kref_get(&connection->kref);
+	/* We may just have force_sig()'ed this thread
+	 * to get it out of some blocking network function.
+	 * Clear signals; otherwise kthread_run(), which internally uses
+	 * wait_on_completion_killable(), will mistake our pending signal
+	 * for a new fatal signal and fail. */
+	flush_signals(current);
 	opa = kthread_run(_try_outdate_peer_async, connection, "drbd_async_h");
 	if (IS_ERR(opa)) {
 		drbd_err(connection, "out of mem, failed to invoke fence-peer helper\n");

drivers/block/zram/zram_drv.c

@@ -622,11 +622,18 @@ static void zram_reset_device(struct zram *zram, bool reset_capacity)
 	memset(&zram->stats, 0, sizeof(zram->stats));
 
 	zram->disksize = 0;
-	if (reset_capacity) {
+	if (reset_capacity)
 		set_capacity(zram->disk, 0);
-		revalidate_disk(zram->disk);
-	}
+
 	up_write(&zram->init_lock);
+
+	/*
+	 * Revalidate disk out of the init_lock to avoid lockdep splat.
+	 * It's okay because disk's capacity is protected by init_lock
+	 * so that revalidate_disk always sees up-to-date capacity.
+	 */
+	if (reset_capacity)
+		revalidate_disk(zram->disk);
 }
 
 static ssize_t disksize_store(struct device *dev,
@@ -666,8 +673,15 @@ static ssize_t disksize_store(struct device *dev,
 	zram->comp = comp;
 	zram->disksize = disksize;
 	set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);
-	revalidate_disk(zram->disk);
 	up_write(&zram->init_lock);
+
+	/*
+	 * Revalidate disk out of the init_lock to avoid lockdep splat.
+	 * It's okay because disk's capacity is protected by init_lock
+	 * so that revalidate_disk always sees up-to-date capacity.
+	 */
+	revalidate_disk(zram->disk);
+
 	return len;
 
 out_destroy_comp:

drivers/clk/ti/clk-7xx.c

@@ -16,7 +16,7 @@
 #include <linux/clkdev.h>
 #include <linux/clk/ti.h>
 
-#define DRA7_DPLL_ABE_DEFFREQ				361267200
+#define DRA7_DPLL_ABE_DEFFREQ				180633600
 #define DRA7_DPLL_GMAC_DEFFREQ				1000000000
 
 
@@ -322,6 +322,11 @@ int __init dra7xx_dt_clk_init(void)
 	if (rc)
 		pr_err("%s: failed to configure ABE DPLL!\n", __func__);
 
+	dpll_ck = clk_get_sys(NULL, "dpll_abe_m2x2_ck");
+	rc = clk_set_rate(dpll_ck, DRA7_DPLL_ABE_DEFFREQ * 2);
+	if (rc)
+		pr_err("%s: failed to configure ABE DPLL m2x2!\n", __func__);
+
 	dpll_ck = clk_get_sys(NULL, "dpll_gmac_ck");
 	rc = clk_set_rate(dpll_ck, DRA7_DPLL_GMAC_DEFFREQ);
 	if (rc)

drivers/firewire/ohci.c

@@ -336,10 +336,10 @@ static const struct {
 		QUIRK_CYCLE_TIMER | QUIRK_IR_WAKE},
 
 	{PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_VT6315, 0,
-		QUIRK_CYCLE_TIMER | QUIRK_NO_MSI},
+		QUIRK_CYCLE_TIMER /* FIXME: necessary? */ | QUIRK_NO_MSI},
 
 	{PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_VT6315, PCI_ANY_ID,
-		0},
+		QUIRK_NO_MSI},
 
 	{PCI_VENDOR_ID_VIA, PCI_ANY_ID, PCI_ANY_ID,
 		QUIRK_CYCLE_TIMER | QUIRK_NO_MSI},

drivers/gpio/gpio-rcar.c

@@ -284,6 +284,7 @@ static int gpio_rcar_irq_domain_map(struct irq_domain *h, unsigned int irq,
 
 static struct irq_domain_ops gpio_rcar_irq_domain_ops = {
 	.map	= gpio_rcar_irq_domain_map,
+	.xlate	= irq_domain_xlate_twocell,
 };
 
 struct gpio_rcar_info {