Merge branch 'x86/urgent' into x86/asm, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

171 files changed, 1238 insertions, 823 deletions

diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 76dde9db7934..0655495470ad 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -338,6 +338,19 @@ config ARC_PAGE_SIZE_4K
 
 endchoice
 
+choice
+	prompt "MMU Super Page Size"
+	depends on ISA_ARCV2 && TRANSPARENT_HUGEPAGE
+	default ARC_HUGEPAGE_2M
+
+config ARC_HUGEPAGE_2M
+	bool "2MB"
+
+config ARC_HUGEPAGE_16M
+	bool "16MB"
+
+endchoice
+
 if ISA_ARCOMPACT
 
 config ARC_COMPACT_IRQ_LEVELS
@@ -410,7 +423,7 @@ config ARC_HAS_RTC
 	default n
 	depends on !SMP
 
-config ARC_HAS_GRTC
+config ARC_HAS_GFRC
 	bool "SMP synchronized 64-bit cycle counter"
 	default y
 	depends on SMP
@@ -566,6 +579,12 @@ endmenu
 endmenu	 # "ARC Architecture Configuration"
 
 source "mm/Kconfig"
+
+config FORCE_MAX_ZONEORDER
+	int "Maximum zone order"
+	default "12" if ARC_HUGEPAGE_16M
+	default "11"
+
 source "net/Kconfig"
 source "drivers/Kconfig"
 source "fs/Kconfig"
diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig
index f36c047b33ca..735985974a31 100644
--- a/arch/arc/configs/vdk_hs38_smp_defconfig
+++ b/arch/arc/configs/vdk_hs38_smp_defconfig
@@ -16,7 +16,7 @@ CONFIG_ARC_PLAT_AXS10X=y
 CONFIG_AXS103=y
 CONFIG_ISA_ARCV2=y
 CONFIG_SMP=y
-# CONFIG_ARC_HAS_GRTC is not set
+# CONFIG_ARC_HAS_GFRC is not set
 CONFIG_ARC_UBOOT_SUPPORT=y
 CONFIG_ARC_BUILTIN_DTB_NAME="vdk_hs38_smp"
 CONFIG_PREEMPT=y
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index 7fac7d85ed6a..fdc5be5b1029 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -349,14 +349,13 @@ struct cpuinfo_arc {
 	struct cpuinfo_arc_bpu bpu;
 	struct bcr_identity core;
 	struct bcr_isa isa;
-	struct bcr_timer timers;
 	unsigned int vec_base;
 	struct cpuinfo_arc_ccm iccm, dccm;
 	struct {
 		unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, pad1:3,
 			     fpu_sp:1, fpu_dp:1, pad2:6,
 			     debug:1, ap:1, smart:1, rtt:1, pad3:4,
-			     pad4:8;
+			     timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4;
 	} extn;
 	struct bcr_mpy extn_mpy;
 	struct bcr_extn_xymem extn_xymem;
diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h
index 258b0e5ad332..1fc18ee06cf2 100644
--- a/arch/arc/include/asm/irqflags-arcv2.h
+++ b/arch/arc/include/asm/irqflags-arcv2.h
@@ -30,8 +30,11 @@
 /* Was Intr taken in User Mode */
 #define AUX_IRQ_ACT_BIT_U	31
 
-/* 0 is highest level, but taken by FIRQs, if present in design */
-#define ARCV2_IRQ_DEF_PRIO		0
+/*
+ * User space should be interruptable even by lowest prio interrupt
+ * Safe even if actual interrupt priorities is fewer or even one
+ */
+#define ARCV2_IRQ_DEF_PRIO	15
 
 /* seed value for status register */
 #define ISA_INIT_STATUS_BITS	(STATUS_IE_MASK | STATUS_AD_MASK | \
diff --git a/arch/arc/include/asm/mcip.h b/arch/arc/include/asm/mcip.h
index 46f4e5351b2a..847e3bbe387f 100644
--- a/arch/arc/include/asm/mcip.h
+++ b/arch/arc/include/asm/mcip.h
@@ -39,8 +39,8 @@ struct mcip_cmd {
 #define CMD_DEBUG_SET_MASK		0x34
 #define CMD_DEBUG_SET_SELECT		0x36
 
-#define CMD_GRTC_READ_LO		0x42
-#define CMD_GRTC_READ_HI		0x43
+#define CMD_GFRC_READ_LO		0x42
+#define CMD_GFRC_READ_HI		0x43
 
 #define CMD_IDU_ENABLE			0x71
 #define CMD_IDU_DISABLE			0x72
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 57af2f05ae84..d426d4215513 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -179,37 +179,44 @@
 #define __S111  PAGE_U_X_W_R
 
 /****************************************************************
- * Page Table Lookup split
+ * 2 tier (PGD:PTE) software page walker
  *
- * We implement 2 tier paging and since this is all software, we are free
- * to customize the span of a PGD / PTE entry to suit us
- *
- *			32 bit virtual address
+ * [31]		    32 bit virtual address              [0]
  * -------------------------------------------------------
- * | BITS_FOR_PGD    |  BITS_FOR_PTE    |  BITS_IN_PAGE  |
+ * |               | <------------ PGDIR_SHIFT ----------> |
+ * |		   |					 |
+ * | BITS_FOR_PGD  |  BITS_FOR_PTE  | <-- PAGE_SHIFT --> |
  * -------------------------------------------------------
  *       |                  |                |
  *       |                  |                --> off in page frame
- *       |		    |
  *       |                  ---> index into Page Table
- *       |
  *       ----> index into Page Directory
+ *
+ * In a single page size configuration, only PAGE_SHIFT is fixed
+ * So both PGD and PTE sizing can be tweaked
+ *  e.g. 8K page (PAGE_SHIFT 13) can have
+ *  - PGDIR_SHIFT 21  -> 11:8:13 address split
+ *  - PGDIR_SHIFT 24  -> 8:11:13 address split
+ *
+ * If Super Page is configured, PGDIR_SHIFT becomes fixed too,
+ * so the sizing flexibility is gone.
  */
 
-#define BITS_IN_PAGE	PAGE_SHIFT
-
-/* Optimal Sizing of Pg Tbl - based on MMU page size */
-#if defined(CONFIG_ARC_PAGE_SIZE_8K)
-#define BITS_FOR_PTE	8		/* 11:8:13 */
-#elif defined(CONFIG_ARC_PAGE_SIZE_16K)
-#define BITS_FOR_PTE	8		/* 10:8:14 */
-#elif defined(CONFIG_ARC_PAGE_SIZE_4K)
-#define BITS_FOR_PTE	9		/* 11:9:12 */
+#if defined(CONFIG_ARC_HUGEPAGE_16M)
+#define PGDIR_SHIFT	24
+#elif defined(CONFIG_ARC_HUGEPAGE_2M)
+#define PGDIR_SHIFT	21
+#else
+/*
+ * Only Normal page support so "hackable" (see comment above)
+ * Default value provides 11:8:13 (8K), 11:9:12 (4K)
+ */
+#define PGDIR_SHIFT	21
 #endif
 
-#define BITS_FOR_PGD	(32 - BITS_FOR_PTE - BITS_IN_PAGE)
+#define BITS_FOR_PTE	(PGDIR_SHIFT - PAGE_SHIFT)
+#define BITS_FOR_PGD	(32 - PGDIR_SHIFT)
 
-#define PGDIR_SHIFT	(32 - BITS_FOR_PGD)
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)	/* vaddr span, not PDG sz */
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S
index cbfec79137bf..b17830294706 100644
--- a/arch/arc/kernel/entry-arcv2.S
+++ b/arch/arc/kernel/entry-arcv2.S
@@ -211,7 +211,11 @@ debug_marker_syscall:
 ; (since IRQ NOT allowed in DS in ARCv2, this can only happen if orig
 ; entry was via Exception in DS which got preempted in kernel).
 ;
-; IRQ RTIE won't reliably restore DE bit and/or BTA, needs handling
+; IRQ RTIE won't reliably restore DE bit and/or BTA, needs workaround
+;
+; Solution is return from Intr w/o any delay slot quirks into a kernel trampoline
+; and from pure kernel mode return to delay slot which handles DS bit/BTA correctly
+
 .Lintr_ret_to_delay_slot:
 debug_marker_ds:
 
@@ -222,18 +226,23 @@ debug_marker_ds:
 	ld	r2, [sp, PT_ret]
 	ld	r3, [sp, PT_status32]
 
+	; STAT32 for Int return created from scratch
+	; (No delay dlot, disable Further intr in trampoline)
+
 	bic  	r0, r3, STATUS_U_MASK|STATUS_DE_MASK|STATUS_IE_MASK|STATUS_L_MASK
 	st	r0, [sp, PT_status32]
 
 	mov	r1, .Lintr_ret_to_delay_slot_2
 	st	r1, [sp, PT_ret]
 
+	; Orig exception PC/STAT32 safekept @orig_r0 and @event stack slots
 	st	r2, [sp, 0]
 	st	r3, [sp, 4]
 
 	b	.Lisr_ret_fast_path
 
 .Lintr_ret_to_delay_slot_2:
+	; Trampoline to restore orig exception PC/STAT32/BTA/AUX_USER_SP
 	sub	sp, sp, SZ_PT_REGS
 	st	r9, [sp, -4]
 
@@ -243,11 +252,19 @@ debug_marker_ds:
 	ld	r9, [sp, 4]
 	sr	r9, [erstatus]
 
+	; restore AUX_USER_SP if returning to U mode
+	bbit0	r9, STATUS_U_BIT, 1f
+	ld	r9, [sp, PT_sp]
+	sr	r9, [AUX_USER_SP]
+
+1:
 	ld	r9, [sp, 8]
 	sr	r9, [erbta]
 
 	ld	r9, [sp, -4]
 	add	sp, sp, SZ_PT_REGS
+
+	; return from pure kernel mode to delay slot
 	rtie
 
 END(ret_from_exception)
diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
index 0394f9f61b46..942526322ae7 100644
--- a/arch/arc/kernel/intc-arcv2.c
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -14,6 +14,8 @@
 #include <linux/irqchip.h>
 #include <asm/irq.h>
 
+static int irq_prio;
+
 /*
  * Early Hardware specific Interrupt setup
  * -Called very early (start_kernel -> setup_arch -> setup_processor)
@@ -24,6 +26,14 @@ void arc_init_IRQ(void)
 {
 	unsigned int tmp;
 
+	struct irq_build {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		unsigned int pad:3, firq:1, prio:4, exts:8, irqs:8, ver:8;
+#else
+		unsigned int ver:8, irqs:8, exts:8, prio:4, firq:1, pad:3;
+#endif
+	} irq_bcr;
+
 	struct aux_irq_ctrl {
 #ifdef CONFIG_CPU_BIG_ENDIAN
 		unsigned int res3:18, save_idx_regs:1, res2:1,
@@ -46,28 +56,25 @@ void arc_init_IRQ(void)
 
 	WRITE_AUX(AUX_IRQ_CTRL, ictrl);
 
-	/* setup status32, don't enable intr yet as kernel doesn't want */
-	tmp = read_aux_reg(0xa);
-	tmp |= ISA_INIT_STATUS_BITS;
-	tmp &= ~STATUS_IE_MASK;
-	asm volatile("flag %0	\n"::"r"(tmp));
-
 	/*
 	 * ARCv2 core intc provides multiple interrupt priorities (upto 16).
 	 * Typical builds though have only two levels (0-high, 1-low)
 	 * Linux by default uses lower prio 1 for most irqs, reserving 0 for
 	 * NMI style interrupts in future (say perf)
-	 *
-	 * Read the intc BCR to confirm that Linux default priority is avail
-	 * in h/w
-	 *
-	 * Note:
-	 *  IRQ_BCR[27..24] contains N-1 (for N priority levels) and prio level
-	 *  is 0 based.
 	 */
-	tmp = (read_aux_reg(ARC_REG_IRQ_BCR) >> 24 ) & 0xF;
-	if (ARCV2_IRQ_DEF_PRIO > tmp)
-		panic("Linux default irq prio incorrect\n");
+
+	READ_BCR(ARC_REG_IRQ_BCR, irq_bcr);
+
+	irq_prio = irq_bcr.prio;	/* Encoded as N-1 for N levels */
+	pr_info("archs-intc\t: %d priority levels (default %d)%s\n",
+		irq_prio + 1, irq_prio,
+		irq_bcr.firq ? " FIRQ (not used)":"");
+
+	/* setup status32, don't enable intr yet as kernel doesn't want */
+	tmp = read_aux_reg(0xa);
+	tmp |= STATUS_AD_MASK | (irq_prio << 1);
+	tmp &= ~STATUS_IE_MASK;
+	asm volatile("flag %0	\n"::"r"(tmp));
 }
 
 static void arcv2_irq_mask(struct irq_data *data)
@@ -86,7 +93,7 @@ void arcv2_irq_enable(struct irq_data *data)
 {
 	/* set default priority */
 	write_aux_reg(AUX_IRQ_SELECT, data->irq);
-	write_aux_reg(AUX_IRQ_PRIORITY, ARCV2_IRQ_DEF_PRIO);
+	write_aux_reg(AUX_IRQ_PRIORITY, irq_prio);
 
 	/*
 	 * hw auto enables (linux unmask) all by default
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index bd237acdf4f2..bc771f58fefb 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -96,13 +96,13 @@ static void mcip_probe_n_setup(void)
 #ifdef CONFIG_CPU_BIG_ENDIAN
 		unsigned int pad3:8,
 			     idu:1, llm:1, num_cores:6,
-			     iocoh:1,  grtc:1, dbg:1, pad2:1,
+			     iocoh:1,  gfrc:1, dbg:1, pad2:1,
 			     msg:1, sem:1, ipi:1, pad:1,
 			     ver:8;
 #else
 		unsigned int ver:8,
 			     pad:1, ipi:1, sem:1, msg:1,
-			     pad2:1, dbg:1, grtc:1, iocoh:1,
+			     pad2:1, dbg:1, gfrc:1, iocoh:1,
 			     num_cores:6, llm:1, idu:1,
 			     pad3:8;
 #endif
@@ -116,7 +116,7 @@ static void mcip_probe_n_setup(void)
 		IS_AVAIL1(mp.ipi, "IPI "),
 		IS_AVAIL1(mp.idu, "IDU "),
 		IS_AVAIL1(mp.dbg, "DEBUG "),
-		IS_AVAIL1(mp.grtc, "GRTC"));
+		IS_AVAIL1(mp.gfrc, "GFRC"));
 
 	idu_detected = mp.idu;
 
@@ -125,8 +125,8 @@ static void mcip_probe_n_setup(void)
 		__mcip_cmd_data(CMD_DEBUG_SET_MASK, 0xf, 0xf);
 	}
 
-	if (IS_ENABLED(CONFIG_ARC_HAS_GRTC) && !mp.grtc)
-		panic("kernel trying to use non-existent GRTC\n");
+	if (IS_ENABLED(CONFIG_ARC_HAS_GFRC) && !mp.gfrc)
+		panic("kernel trying to use non-existent GFRC\n");
 }
 
 struct plat_smp_ops plat_smp_ops = {
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index e1b87444ea9a..a7edceba5f84 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -45,6 +45,7 @@ struct cpuinfo_arc cpuinfo_arc700[NR_CPUS];
 static void read_arc_build_cfg_regs(void)
 {
 	struct bcr_perip uncached_space;
+	struct bcr_timer timer;
 	struct bcr_generic bcr;
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
 	unsigned long perip_space;
@@ -53,7 +54,11 @@ static void read_arc_build_cfg_regs(void)
 	READ_BCR(AUX_IDENTITY, cpu->core);
 	READ_BCR(ARC_REG_ISA_CFG_BCR, cpu->isa);
 
-	READ_BCR(ARC_REG_TIMERS_BCR, cpu->timers);
+	READ_BCR(ARC_REG_TIMERS_BCR, timer);
+	cpu->extn.timer0 = timer.t0;
+	cpu->extn.timer1 = timer.t1;
+	cpu->extn.rtc = timer.rtc;
+
 	cpu->vec_base = read_aux_reg(AUX_INTR_VEC_BASE);
 
 	READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space);
@@ -208,9 +213,9 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 		       (unsigned int)(arc_get_core_freq() / 10000) % 100);
 
 	n += scnprintf(buf + n, len - n, "Timers\t\t: %s%s%s%s\nISA Extn\t: ",
-		       IS_AVAIL1(cpu->timers.t0, "Timer0 "),
-		       IS_AVAIL1(cpu->timers.t1, "Timer1 "),
-		       IS_AVAIL2(cpu->timers.rtc, "64-bit RTC ",
+		       IS_AVAIL1(cpu->extn.timer0, "Timer0 "),
+		       IS_AVAIL1(cpu->extn.timer1, "Timer1 "),
+		       IS_AVAIL2(cpu->extn.rtc, "Local-64-bit-Ctr ",
 				 CONFIG_ARC_HAS_RTC));
 
 	n += i = scnprintf(buf + n, len - n, "%s%s%s%s%s",
@@ -293,13 +298,13 @@ static void arc_chk_core_config(void)
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
 	int fpu_enabled;
 
-	if (!cpu->timers.t0)
+	if (!cpu->extn.timer0)
 		panic("Timer0 is not present!\n");
 
-	if (!cpu->timers.t1)
+	if (!cpu->extn.timer1)
 		panic("Timer1 is not present!\n");
 
-	if (IS_ENABLED(CONFIG_ARC_HAS_RTC) && !cpu->timers.rtc)
+	if (IS_ENABLED(CONFIG_ARC_HAS_RTC) && !cpu->extn.rtc)
 		panic("RTC is not present\n");
 
 #ifdef CONFIG_ARC_HAS_DCCM
@@ -334,6 +339,7 @@ static void arc_chk_core_config(void)
 		panic("FPU non-existent, disable CONFIG_ARC_FPU_SAVE_RESTORE\n");
 
 	if (is_isa_arcv2() && IS_ENABLED(CONFIG_SMP) && cpu->isa.atomic &&
+	    IS_ENABLED(CONFIG_ARC_HAS_LLSC) &&
 	    !IS_ENABLED(CONFIG_ARC_STAR_9000923308))
 		panic("llock/scond livelock workaround missing\n");
 }
diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c
index dfad287f1db1..156d9833ff84 100644
--- a/arch/arc/kernel/time.c
+++ b/arch/arc/kernel/time.c
@@ -62,7 +62,7 @@
 
 /********** Clock Source Device *********/
 
-#ifdef CONFIG_ARC_HAS_GRTC
+#ifdef CONFIG_ARC_HAS_GFRC
 
 static int arc_counter_setup(void)
 {
@@ -83,10 +83,10 @@ static cycle_t arc_counter_read(struct clocksource *cs)
 
 	local_irq_save(flags);
 
-	__mcip_cmd(CMD_GRTC_READ_LO, 0);
+	__mcip_cmd(CMD_GFRC_READ_LO, 0);
 	stamp.l = read_aux_reg(ARC_REG_MCIP_READBACK);
 
-	__mcip_cmd(CMD_GRTC_READ_HI, 0);
+	__mcip_cmd(CMD_GFRC_READ_HI, 0);
 	stamp.h = read_aux_reg(ARC_REG_MCIP_READBACK);
 
 	local_irq_restore(flags);
@@ -95,7 +95,7 @@ static cycle_t arc_counter_read(struct clocksource *cs)
 }
 
 static struct clocksource arc_counter = {
-	.name   = "ARConnect GRTC",
+	.name   = "ARConnect GFRC",
 	.rating = 400,
 	.read   = arc_counter_read,
 	.mask   = CLOCKSOURCE_MASK(64),
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 4c23a68a0917..7a6a58ef8aaf 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -106,6 +106,15 @@ ORIG_CFLAGS := $(KBUILD_CFLAGS)
 KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS))
 endif
 
+# -fstack-protector-strong triggers protection checks in this code,
+# but it is being used too early to link to meaningful stack_chk logic.
+nossp_flags := $(call cc-option, -fno-stack-protector)
+CFLAGS_atags_to_fdt.o := $(nossp_flags)
+CFLAGS_fdt.o := $(nossp_flags)
+CFLAGS_fdt_ro.o := $(nossp_flags)
+CFLAGS_fdt_rw.o := $(nossp_flags)
+CFLAGS_fdt_wip.o := $(nossp_flags)
+
 ccflags-y := -fpic -mno-single-pic-base -fno-builtin -I$(obj)
 asflags-y := -DZIMAGE
 
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 04885f9f959e..1fafaad516ba 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -439,6 +439,7 @@
 			ti,mbox-num-users = <4>;
 			ti,mbox-num-fifos = <8>;
 			mbox_wkupm3: wkup_m3 {
+				ti,mbox-send-noirq;
 				ti,mbox-tx = <0 0 0>;
 				ti,mbox-rx = <0 0 3>;
 			};
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index df955ba4dc62..92068fbf8b57 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -73,7 +73,7 @@
 	global_timer: timer@48240200 {
 		compatible = "arm,cortex-a9-global-timer";
 		reg = <0x48240200 0x100>;
-		interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
 		interrupt-parent = <&gic>;
 		clocks = <&mpu_periphclk>;
 	};
@@ -81,7 +81,7 @@
 	local_timer: timer@48240600 {
 		compatible = "arm,cortex-a9-twd-timer";
 		reg = <0x48240600 0x100>;
-		interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <GIC_PPI 13 IRQ_TYPE_EDGE_RISING>;
 		interrupt-parent = <&gic>;
 		clocks = <&mpu_periphclk>;
 	};
@@ -290,6 +290,7 @@
 			ti,mbox-num-users = <4>;
 			ti,mbox-num-fifos = <8>;
 			mbox_wkupm3: wkup_m3 {
+				ti,mbox-send-noirq;
 				ti,mbox-tx = <0 0 0>;
 				ti,mbox-rx = <0 0 3>;
 			};
diff --git a/arch/arm/boot/dts/am437x-gp-evm.dts b/arch/arm/boot/dts/am437x-gp-evm.dts
index 64d43325bcbc..ecd09ab6d581 100644
--- a/arch/arm/boot/dts/am437x-gp-evm.dts
+++ b/arch/arm/boot/dts/am437x-gp-evm.dts
@@ -590,8 +590,6 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&pixcir_ts_pins>;
 		reg = <0x5c>;
-		interrupt-parent = <&gpio3>;
-		interrupts = <22 0>;
 
 		attb-gpio = <&gpio3 22 GPIO_ACTIVE_HIGH>;
 
@@ -599,7 +597,7 @@
 		 * 0x264 represents the offset of padconf register of
 		 * gpio3_22 from am43xx_pinmux base.
 		 */
-		interrupts-extended = <&gpio3 22 IRQ_TYPE_NONE>,
+		interrupts-extended = <&gpio3 22 IRQ_TYPE_EDGE_FALLING>,
 				      <&am43xx_pinmux 0x264>;
 		interrupt-names = "tsc", "wakeup";
 
diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts
index 746fd2b17958..d580e2b70f9a 100644
--- a/arch/arm/boot/dts/am43x-epos-evm.dts
+++ b/arch/arm/boot/dts/am43x-epos-evm.dts
@@ -491,7 +491,7 @@
 		pinctrl-0 = <&pixcir_ts_pins>;
 		reg = <0x5c>;
 		interrupt-parent = <&gpio1>;
-		interrupts = <17 0>;
+		interrupts = <17 IRQ_TYPE_EDGE_FALLING>;
 
 		attb-gpio = <&gpio1 17 GPIO_ACTIVE_HIGH>;
 
diff --git a/arch/arm/boot/dts/am57xx-cl-som-am57x.dts b/arch/arm/boot/dts/am57xx-cl-som-am57x.dts
index c53882643ae9..8d93882dc8d5 100644
--- a/arch/arm/boot/dts/am57xx-cl-som-am57x.dts
+++ b/arch/arm/boot/dts/am57xx-cl-som-am57x.dts
@@ -167,7 +167,7 @@
 			DRA7XX_CORE_IOPAD(0x35b8, PIN_INPUT_PULLDOWN | MUX_MODE3) /* vin2a_d20.rgmii1_rd3 */
 			DRA7XX_CORE_IOPAD(0x35bc, PIN_INPUT_PULLDOWN | MUX_MODE3) /* vin2a_d21.rgmii1_rd2 */
 			DRA7XX_CORE_IOPAD(0x35c0, PIN_INPUT_PULLDOWN | MUX_MODE3) /* vin2a_d22.rgmii1_rd1 */
-			DRA7XX_CORE_IOPAD(0x35c4, PIN_INPUT_PULLUP | MUX_MODE3)	/* vin2a_d23.rgmii1_rd0 */
+			DRA7XX_CORE_IOPAD(0x35c4, PIN_INPUT_PULLDOWN | MUX_MODE3) /* vin2a_d23.rgmii1_rd0 */
 		>;
 	};
 
@@ -492,14 +492,14 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&qspi1_pins>;
 
-	spi-max-frequency = <20000000>;
+	spi-max-frequency = <48000000>;
 
 	spi_flash: spi_flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
 		compatible = "spansion,m25p80", "jedec,spi-nor";
 		reg = <0>;				/* CS0 */
-		spi-max-frequency = <20000000>;
+		spi-max-frequency = <48000000>;
 
 		partition@0 {
 			label = "uboot";
@@ -559,13 +559,13 @@
 
 &cpsw_emac0 {
 	phy_id = <&davinci_mdio>, <0>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-txid";
 	dual_emac_res_vlan = <0>;
 };
 
 &cpsw_emac1 {
 	phy_id = <&davinci_mdio>, <1>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-txid";
 	dual_emac_res_vlan = <1>;
 };
 
@@ -588,7 +588,7 @@
 };
 
 &usb2 {
-	dr_mode = "peripheral";
+	dr_mode = "host";
 };
 
 &mcasp3 {
diff --git a/arch/arm/boot/dts/am57xx-sbc-am57x.dts b/arch/arm/boot/dts/am57xx-sbc-am57x.dts
index 77bb8e17401a..988e99632d49 100644
--- a/arch/arm/boot/dts/am57xx-sbc-am57x.dts
+++ b/arch/arm/boot/dts/am57xx-sbc-am57x.dts
@@ -25,8 +25,8 @@
 &dra7_pmx_core {
 	uart3_pins_default: uart3_pins_default {
 		pinctrl-single,pins = <
-			DRA7XX_CORE_IOPAD(0x37f8, PIN_INPUT_SLEW | MUX_MODE2)	/* uart2_ctsn.uart3_rxd */
-			DRA7XX_CORE_IOPAD(0x37fc, PIN_INPUT_SLEW | MUX_MODE1)	/* uart2_rtsn.uart3_txd */
+			DRA7XX_CORE_IOPAD(0x3648, PIN_INPUT_SLEW | MUX_MODE0)	/* uart3_rxd */
+			DRA7XX_CORE_IOPAD(0x364c, PIN_INPUT_SLEW | MUX_MODE0)	/* uart3_txd */
 		>;
 	};
 
@@ -108,9 +108,9 @@
 	pinctrl-0 = <&i2c5_pins_default>;
 	clock-frequency = <400000>;
 
-	eeprom_base: atmel@50 {
+	eeprom_base: atmel@54 {
 		compatible = "atmel,24c08";
-		reg = <0x50>;
+		reg = <0x54>;
 		pagesize = <16>;
 	};
 
diff --git a/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts b/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts
index 13cf69a8d0fb..fb9e1bbf2338 100644
--- a/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts
+++ b/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts
@@ -152,6 +152,7 @@
 				nand-on-flash-bbt;
 
 				partitions {
+					compatible = "fixed-partitions";
 					#address-cells = <1>;
 					#size-cells = <1>;
 
diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
index 77ddff036409..e683856c507c 100644
--- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
@@ -114,9 +114,15 @@
 
 			macb0: ethernet@f8008000 {
 				pinctrl-names = "default";
-				pinctrl-0 = <&pinctrl_macb0_default>;
+				pinctrl-0 = <&pinctrl_macb0_default &pinctrl_macb0_phy_irq>;
 				phy-mode = "rmii";
 				status = "okay";
+
+				ethernet-phy@1 {
+					reg = <0x1>;
+					interrupt-parent = <&pioA>;
+					interrupts = <73 IRQ_TYPE_LEVEL_LOW>;
+				};
 			};
 
 			pdmic@f8018000 {
@@ -300,6 +306,10 @@
 					bias-disable;
 				};
 
+				pinctrl_macb0_phy_irq: macb0_phy_irq {
+					pinmux = <PIN_PC9__GPIO>;
+				};
+
 				pinctrl_pdmic_default: pdmic_default {
 					pinmux = <PIN_PB26__PDMIC_DAT>,
 						<PIN_PB27__PDMIC_CLK>;
diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts
index 131614f28e75..569026e8f96c 100644
--- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts
@@ -86,10 +86,12 @@
 			macb0: ethernet@f8020000 {
 				phy-mode = "rmii";
 				status = "okay";
+				pinctrl-names = "default";
+				pinctrl-0 = <&pinctrl_macb0_rmii &pinctrl_macb0_phy_irq>;
 
 				phy0: ethernet-phy@1 {
 					interrupt-parent = <&pioE>;
-					interrupts = <1 IRQ_TYPE_EDGE_FALLING>;
+					interrupts = <1 IRQ_TYPE_LEVEL_LOW>;
 					reg = <1>;
 				};
 			};
@@ -152,6 +154,10 @@
 						atmel,pins =
 							<AT91_PIOE 8 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>;
 					};
+					pinctrl_macb0_phy_irq: macb0_phy_irq_0 {
+						atmel,pins =
+							<AT91_PIOE 1 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>;
+					};
 				};
 			};
 		};
diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts
index 2d4a33100af6..4e98cda97403 100644
--- a/arch/arm/boot/dts/at91-sama5d4ek.dts
+++ b/arch/arm/boot/dts/at91-sama5d4ek.dts
@@ -160,8 +160,15 @@
 			};
 
 			macb0: ethernet@f8020000 {
+				pinctrl-0 = <&pinctrl_macb0_rmii &pinctrl_macb0_phy_irq>;
 				phy-mode = "rmii";
 				status = "okay";
+
+				ethernet-phy@1 {
+					reg = <0x1>;
+					interrupt-parent = <&pioE>;
+					interrupts = <1 IRQ_TYPE_LEVEL_LOW>;
+				};
 			};
 
 			mmc1: mmc@fc000000 {
@@ -193,6 +200,10 @@
 
 			pinctrl@fc06a000 {
 				board {
+					pinctrl_macb0_phy_irq: macb0_phy_irq {
+						atmel,pins =
+							<AT91_PIOE 1 AT91_PERIPH_GPIO AT91_PINCTRL_NONE>;
+					};
 					pinctrl_mmc0_cd: mmc0_cd {
 						atmel,pins =
 							<AT91_PIOE 5 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>;
diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts
index ca4ddf86817a..626c67d66626 100644
--- a/arch/arm/boot/dts/at91sam9n12ek.dts
+++ b/arch/arm/boot/dts/at91sam9n12ek.dts
@@ -215,7 +215,7 @@
 	};
 
 	panel: panel {
-		compatible = "qd,qd43003c0-40", "simple-panel";
+		compatible = "qiaodian,qd43003c0-40", "simple-panel";
 		backlight = <&backlight>;
 		power-supply = <&panel_reg>;
 		#address-cells = <1>;
diff --git a/arch/arm/boot/dts/kirkwood-lswvl.dts b/arch/arm/boot/dts/kirkwood-lswvl.dts
index 09eed3cea0af..36eec7392ab4 100644
--- a/arch/arm/boot/dts/kirkwood-lswvl.dts
+++ b/arch/arm/boot/dts/kirkwood-lswvl.dts
@@ -1,7 +1,8 @@
 /*
  * Device Tree file for Buffalo Linkstation LS-WVL/VL
  *
- * Copyright (C) 2015, rogershimizu@gmail.com
+ * Copyright (C) 2015, 2016
+ * Roger Shimizu <rogershimizu@gmail.com>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -156,21 +157,21 @@
 		button@1 {
 			label = "Function Button";
 			linux,code = <KEY_OPTION>;
-			gpios = <&gpio0 45 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio1 13 GPIO_ACTIVE_LOW>;
 		};
 
 		button@2 {
 			label = "Power-on Switch";
 			linux,code = <KEY_RESERVED>;
 			linux,input-type = <5>;
-			gpios = <&gpio0 46 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio1 14 GPIO_ACTIVE_LOW>;
 		};
 
 		button@3 {
 			label = "Power-auto Switch";
 			linux,code = <KEY_ESC>;
 			linux,input-type = <5>;
-			gpios = <&gpio0 47 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio1 15 GPIO_ACTIVE_LOW>;
 		};
 	};
 
@@ -185,38 +186,38 @@
 
 		led@1 {
 			label = "lswvl:red:alarm";
-			gpios = <&gpio0 36 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio1 4 GPIO_ACTIVE_HIGH>;
 		};
 
 		led@2 {
 			label = "lswvl:red:func";
-			gpios = <&gpio0 37 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio1 5 GPIO_ACTIVE_HIGH>;
 		};
 
 		led@3 {
 			label = "lswvl:amber:info";
-			gpios = <&gpio0 38 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio1 6 GPIO_ACTIVE_HIGH>;
 		};
 
 		led@4 {
 			label = "lswvl:blue:func";
-			gpios = <&gpio0 39 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio1 7 GPIO_ACTIVE_HIGH>;
 		};
 
 		led@5 {
 			label = "lswvl:blue:power";
-			gpios = <&gpio0 40 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio1 8 GPIO_ACTIVE_LOW>;
 			default-state = "keep";
 		};
 
 		led@6 {
 			label = "lswvl:red:hdderr0";
-			gpios = <&gpio0 34 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>;
 		};
 
 		led@7 {
 			label = "lswvl:red:hdderr1";
-			gpios = <&gpio0 35 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio1 3 GPIO_ACTIVE_HIGH>;
 		};
 	};
 
@@ -233,7 +234,7 @@
 				3250 1
 				5000 0>;
 
-		alarm-gpios = <&gpio0 43 GPIO_ACTIVE_HIGH>;
+		alarm-gpios = <&gpio1 11 GPIO_ACTIVE_HIGH>;
 	};
 
 	restart_poweroff {
diff --git a/arch/arm/boot/dts/kirkwood-lswxl.dts b/arch/arm/boot/dts/kirkwood-lswxl.dts
index f5db16a08597..b13ec20a7088 100644
--- a/arch/arm/boot/dts/kirkwood-lswxl.dts
+++ b/arch/arm/boot/dts/kirkwood-lswxl.dts
@@ -1,7 +1,8 @@
 /*
  * Device Tree file for Buffalo Linkstation LS-WXL/WSXL
  *
- * Copyright (C) 2015, rogershimizu@gmail.com
+ * Copyright (C) 2015, 2016
+ * Roger Shimizu <rogershimizu@gmail.com>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -156,21 +157,21 @@
 		button@1 {
 			label = "Function Button";
 			linux,code = <KEY_OPTION>;
-			gpios = <&gpio1 41 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio1 9 GPIO_ACTIVE_LOW>;
 		};
 
 		button@2 {
 			label = "Power-on Switch";
 			linux,code = <KEY_RESERVED>;
 			linux,input-type = <5>;
-			gpios = <&gpio1 42 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio1 10 GPIO_ACTIVE_LOW>;
 		};
 
 		button@3 {
 			label = "Power-auto Switch";
 			linux,code = <KEY_ESC>;
 			linux,input-type = <5>;
-			gpios = <&gpio1 43 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio1 11 GPIO_ACTIVE_LOW>;
 		};
 	};
 
@@ -185,12 +186,12 @@
 
 		led@1 {
 			label = "lswxl:blue:func";
-			gpios = <&gpio1 36 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
 		};
 
 		led@2 {
 			label = "lswxl:red:alarm";
-			gpios = <&gpio1 49 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio1 17 GPIO_ACTIVE_LOW>;
 		};
 
 		led@3 {
@@ -200,23 +201,23 @@
 
 		led@4 {
 			label = "lswxl:blue:power";
-			gpios = <&gpio1 8 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio1 7 GPIO_ACTIVE_HIGH>;
+			default-state = "keep";
 		};
 
 		led@5 {
 			label = "lswxl:red:func";
-			gpios = <&gpio1 5 GPIO_ACTIVE_LOW>;
-			default-state = "keep";
+			gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>;
 		};
 
 		led@6 {
 			label = "lswxl:red:hdderr0";
-			gpios = <&gpio1 2 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio0 8 GPIO_ACTIVE_HIGH>;
 		};
 
 		led@7 {
 			label = "lswxl:red:hdderr1";
-			gpios = <&gpio1 3 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio1 14 GPIO_ACTIVE_HIGH>;
 		};
 	};
 
@@ -225,15 +226,15 @@
 		pinctrl-0 = <&pmx_fan_low &pmx_fan_high &pmx_fan_lock>;
 		pinctrl-names = "default";
 
-		gpios = <&gpio0 47 GPIO_ACTIVE_LOW
-			 &gpio0 48 GPIO_ACTIVE_LOW>;
+		gpios = <&gpio1 16 GPIO_ACTIVE_LOW
+			 &gpio1 15 GPIO_ACTIVE_LOW>;
 
 		gpio-fan,speed-map = <0 3
 				1500 2
 				3250 1
 				5000 0>;
 
-		alarm-gpios = <&gpio1 49 GPIO_ACTIVE_HIGH>;
+		alarm-gpios = <&gpio1 8 GPIO_ACTIVE_HIGH>;
 	};
 
 	restart_poweroff {
@@ -256,7 +257,7 @@
 			enable-active-high;
 			regulator-always-on;
 			regulator-boot-on;
-			gpio = <&gpio0 37 GPIO_ACTIVE_HIGH>;
+			gpio = <&gpio1 5 GPIO_ACTIVE_HIGH>;
 		};
 		hdd_power0: regulator@2 {
 			compatible = "regulator-fixed";
diff --git a/arch/arm/boot/dts/kirkwood-pogoplug-series-4.dts b/arch/arm/boot/dts/kirkwood-pogoplug-series-4.dts
index 1db6f2c506cc..8082d64266a3 100644
--- a/arch/arm/boot/dts/kirkwood-pogoplug-series-4.dts
+++ b/arch/arm/boot/dts/kirkwood-pogoplug-series-4.dts
@@ -131,6 +131,7 @@
 	chip-delay = <40>;
 	status = "okay";
 	partitions {
+		compatible = "fixed-partitions";
 		#address-cells = <1>;
 		#size-cells = <1>;
 
diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
index 7fed0bd4f3de..00805322367e 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
@@ -112,14 +112,6 @@
 	clock-frequency = <400000>;
 };
 
-&i2c2 {
-	clock-frequency = <400000>;
-};
-
-&i2c3 {
-	clock-frequency = <400000>;
-};
-
 /*
  * Only found on the wireless SOM. For the SOM without wireless, the pins for
  * MMC3 can be routed with jumpers to the second MMC slot on the devkit and
@@ -143,6 +135,7 @@
 		interrupt-parent = <&gpio5>;
 		interrupts = <24 IRQ_TYPE_LEVEL_HIGH>; /* gpio 152 */
 		ref-clock-frequency = <26000000>;
+		tcxo-clock-frequency = <26000000>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi
index 888412c63f97..902657d6713b 100644
--- a/arch/arm/boot/dts/omap5-board-common.dtsi
+++ b/arch/arm/boot/dts/omap5-board-common.dtsi
@@ -130,6 +130,16 @@
 	};
 };
 
+&gpio8 {
+	/* TI trees use GPIO instead of msecure, see also muxing */
+	p234 {
+		gpio-hog;
+		gpios = <10 GPIO_ACTIVE_HIGH>;
+		output-high;
+		line-name = "gpio8_234/msecure";
+	};
+};
+
 &omap5_pmx_core {
 	pinctrl-names = "default";
 	pinctrl-0 = <
@@ -213,6 +223,13 @@
 		>;
 	};
 
+	/* TI trees use GPIO mode; msecure mode does not work reliably? */
+	palmas_msecure_pins: palmas_msecure_pins {
+		pinctrl-single,pins = <
+			OMAP5_IOPAD(0x180, PIN_OUTPUT | MUX_MODE6) /* gpio8_234 */
+		>;
+	};
+
 	usbhost_pins: pinmux_usbhost_pins {
 		pinctrl-single,pins = <
 			OMAP5_IOPAD(0x0c4, PIN_INPUT | MUX_MODE0) /* usbb2_hsic_strobe */
@@ -278,6 +295,12 @@
 			&usbhost_wkup_pins
 	>;
 
+	palmas_sys_nirq_pins: pinmux_palmas_sys_nirq_pins {
+		pinctrl-single,pins = <
+			OMAP5_IOPAD(0x068, PIN_INPUT_PULLUP | MUX_MODE0) /* sys_nirq1 */
+		>;
+	};
+
 	usbhost_wkup_pins: pinmux_usbhost_wkup_pins {
 		pinctrl-single,pins = <
 			OMAP5_IOPAD(0x05a, PIN_OUTPUT | MUX_MODE0) /* fref_clk1_out, USB hub clk */
@@ -345,6 +368,8 @@
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		ti,system-power-controller;
+		pinctrl-names = "default";
+		pinctrl-0 = <&palmas_sys_nirq_pins &palmas_msecure_pins>;
 
 		extcon_usb3: palmas_usb {
 			compatible = "ti,palmas-usb-vid";
@@ -358,6 +383,14 @@
 			#clock-cells = <0>;
 		};
 
+		rtc {
+			compatible = "ti,palmas-rtc";
+			interrupt-parent = <&palmas>;
+			interrupts = <8 IRQ_TYPE_NONE>;
+			ti,backup-battery-chargeable;
+			ti,backup-battery-charge-high-current;
+		};
+
 		palmas_pmic {
 			compatible = "ti,palmas-pmic";
 			interrupt-parent = <&palmas>;
diff --git a/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts b/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts
index 3daec912b4bf..420788229e6f 100644
--- a/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts
+++ b/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts
@@ -1,7 +1,8 @@
 /*
  * Device Tree file for Buffalo Linkstation LS-WTGL
  *
- * Copyright (C) 2015, Roger Shimizu <rogershimizu@gmail.com>
+ * Copyright (C) 2015, 2016
+ * Roger Shimizu <rogershimizu@gmail.com>
  *
  * This file is dual-licensed: you can use it either under the terms
  * of the GPL or the X11 license, at your option. Note that this dual
@@ -69,8 +70,6 @@
 
 		internal-regs {
 			pinctrl: pinctrl@10000 {
-				pinctrl-0 = <&pmx_usb_power &pmx_power_hdd
-					&pmx_fan_low &pmx_fan_high &pmx_fan_lock>;
 				pinctrl-names = "default";
 
 				pmx_led_power: pmx-leds {
@@ -162,6 +161,7 @@
 		led@1 {
 			label = "lswtgl:blue:power";
 			gpios = <&gpio0 0 GPIO_ACTIVE_LOW>;
+			default-state = "keep";
 		};
 
 		led@2 {
@@ -188,7 +188,7 @@
 				3250 1
 				5000 0>;
 
-		alarm-gpios = <&gpio0 2 GPIO_ACTIVE_HIGH>;
+		alarm-gpios = <&gpio0 6 GPIO_ACTIVE_HIGH>;
 	};
 
 	restart_poweroff {
diff --git a/arch/arm/boot/dts/sama5d4.dtsi b/arch/arm/boot/dts/sama5d4.dtsi
index b8032bca4621..db1151c18466 100644
--- a/arch/arm/boot/dts/sama5d4.dtsi
+++ b/arch/arm/boot/dts/sama5d4.dtsi
@@ -1342,7 +1342,7 @@
 			dbgu: serial@fc069000 {
 				compatible = "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart";
 				reg = <0xfc069000 0x200>;
-				interrupts = <2 IRQ_TYPE_LEVEL_HIGH 7>;
+				interrupts = <45 IRQ_TYPE_LEVEL_HIGH 7>;
 				pinctrl-names = "default";
 				pinctrl-0 = <&pinctrl_dbgu>;
 				clocks = <&dbgu_clk>;
diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
index d0c743853318..27a333eb8987 100644
--- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
+++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
@@ -127,22 +127,14 @@
 			};
 			mmcsd_default_mode: mmcsd_default {
 				mmcsd_default_cfg1 {
-					/* MCCLK */
-					pins = "GPIO8_B10";
-					ste,output = <0>;
-				};
-				mmcsd_default_cfg2 {
-					/* MCCMDDIR, MCDAT0DIR, MCDAT31DIR, MCDATDIR2 */
-					pins = "GPIO10_C11", "GPIO15_A12",
-					"GPIO16_C13", "GPIO23_D15";
-					ste,output = <1>;
-				};
-				mmcsd_default_cfg3 {
-					/* MCCMD, MCDAT3-0, MCMSFBCLK */
-					pins = "GPIO9_A10", "GPIO11_B11",
-					"GPIO12_A11", "GPIO13_C12",
-					"GPIO14_B12", "GPIO24_C15";
-					ste,input = <1>;
+					/*
+					 * MCCLK, MCCMDDIR, MCDAT0DIR, MCDAT31DIR, MCDATDIR2
+					 * MCCMD, MCDAT3-0, MCMSFBCLK
+					 */
+					pins = "GPIO8_B10", "GPIO9_A10", "GPIO10_C11", "GPIO11_B11",
+					       "GPIO12_A11", "GPIO13_C12", "GPIO14_B12", "GPIO15_A12",
+					       "GPIO16_C13", "GPIO23_D15", "GPIO24_C15";
+					ste,output = <2>;
 				};
 			};
 		};
@@ -802,10 +794,21 @@
 			clock-names = "mclk", "apb_pclk";
 			interrupt-parent = <&vica>;
 			interrupts = <22>;
-			max-frequency = <48000000>;
+			max-frequency = <400000>;
 			bus-width = <4>;
 			cap-mmc-highspeed;
 			cap-sd-highspeed;
+			full-pwr-cycle;
+			/*
+			 * The STw4811 circuit used with the Nomadik strictly
+			 * requires that all of these signal direction pins be
+			 * routed and used for its 4-bit levelshifter.
+			 */
+			st,sig-dir-dat0;
+			st,sig-dir-dat2;
+			st,sig-dir-dat31;
+			st,sig-dir-cmd;
+			st,sig-pin-fbclk;
 			pinctrl-names = "default";
 			pinctrl-0 = <&mmcsd_default_mux>, <&mmcsd_default_mode>;
 			vmmc-supply = <&vmmc_regulator>;
diff --git a/arch/arm/common/icst.c b/arch/arm/common/icst.c
index 2dc6da70ae59..d7ed252708c5 100644
--- a/arch/arm/common/icst.c
+++ b/arch/arm/common/icst.c
@@ -16,7 +16,7 @@
  */
 #include <linux/module.h>
 #include <linux/kernel.h>
-
+#include <asm/div64.h>
 #include <asm/hardware/icst.h>
 
 /*
@@ -29,7 +29,11 @@ EXPORT_SYMBOL(icst525_s2div);
 
 unsigned long icst_hz(const struct icst_params *p, struct icst_vco vco)
 {
-	return p->ref * 2 * (vco.v + 8) / ((vco.r + 2) * p->s2div[vco.s]);
+	u64 dividend = p->ref * 2 * (u64)(vco.v + 8);
+	u32 divisor = (vco.r + 2) * p->s2div[vco.s];
+
+	do_div(dividend, divisor);
+	return (unsigned long)dividend;
 }
 
 EXPORT_SYMBOL(icst_hz);
@@ -58,6 +62,7 @@ icst_hz_to_vco(const struct icst_params *p, unsigned long freq)
 
 		if (f > p->vco_min && f <= p->vco_max)
 			break;
+		i++;
 	} while (i < 8);
 
 	if (i >= 8)
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 314f6be2dca2..8e8b2ace9b7c 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -426,6 +426,7 @@ CONFIG_SUNXI_WATCHDOG=y
 CONFIG_IMX2_WDT=y
 CONFIG_TEGRA_WATCHDOG=m
 CONFIG_MESON_WATCHDOG=y
+CONFIG_DW_WATCHDOG=y
 CONFIG_DIGICOLOR_WATCHDOG=y
 CONFIG_MFD_AS3711=y
 CONFIG_MFD_AS3722=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index c5e1943e5427..d18d6b42fcf5 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -50,6 +50,7 @@ CONFIG_SOC_AM33XX=y
 CONFIG_SOC_AM43XX=y
 CONFIG_SOC_DRA7XX=y
 CONFIG_ARM_THUMBEE=y
+CONFIG_ARM_KERNMEM_PERMS=y
 CONFIG_ARM_ERRATA_411920=y
 CONFIG_ARM_ERRATA_430973=y
 CONFIG_SMP=y
@@ -177,6 +178,7 @@ CONFIG_TI_CPTS=y
 CONFIG_AT803X_PHY=y
 CONFIG_SMSC_PHY=y
 CONFIG_USB_USBNET=m
+CONFIG_USB_NET_SMSC75XX=m
 CONFIG_USB_NET_SMSC95XX=m
 CONFIG_USB_ALI_M5632=y
 CONFIG_USB_AN2720=y
@@ -290,24 +292,23 @@ CONFIG_FB=y
 CONFIG_FIRMWARE_EDID=y
 CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_TILEBLITTING=y
-CONFIG_OMAP2_DSS=m
-CONFIG_OMAP5_DSS_HDMI=y
-CONFIG_OMAP2_DSS_SDI=y
-CONFIG_OMAP2_DSS_DSI=y
+CONFIG_FB_OMAP5_DSS_HDMI=y
+CONFIG_FB_OMAP2_DSS_SDI=y
+CONFIG_FB_OMAP2_DSS_DSI=y
 CONFIG_FB_OMAP2=m
-CONFIG_DISPLAY_ENCODER_TFP410=m
-CONFIG_DISPLAY_ENCODER_TPD12S015=m
-CONFIG_DISPLAY_CONNECTOR_DVI=m
-CONFIG_DISPLAY_CONNECTOR_HDMI=m
-CONFIG_DISPLAY_CONNECTOR_ANALOG_TV=m
-CONFIG_DISPLAY_PANEL_DPI=m
-CONFIG_DISPLAY_PANEL_DSI_CM=m
-CONFIG_DISPLAY_PANEL_SONY_ACX565AKM=m
-CONFIG_DISPLAY_PANEL_LGPHILIPS_LB035Q02=m
-CONFIG_DISPLAY_PANEL_SHARP_LS037V7DW01=m
-CONFIG_DISPLAY_PANEL_TPO_TD028TTEC1=m
-CONFIG_DISPLAY_PANEL_TPO_TD043MTEA1=m
-CONFIG_DISPLAY_PANEL_NEC_NL8048HL11=m
+CONFIG_FB_OMAP2_ENCODER_TFP410=m
+CONFIG_FB_OMAP2_ENCODER_TPD12S015=m
+CONFIG_FB_OMAP2_CONNECTOR_DVI=m
+CONFIG_FB_OMAP2_CONNECTOR_HDMI=m
+CONFIG_FB_OMAP2_CONNECTOR_ANALOG_TV=m
+CONFIG_FB_OMAP2_PANEL_DPI=m
+CONFIG_FB_OMAP2_PANEL_DSI_CM=m
+CONFIG_FB_OMAP2_PANEL_SONY_ACX565AKM=m
+CONFIG_FB_OMAP2_PANEL_LGPHILIPS_LB035Q02=m
+CONFIG_FB_OMAP2_PANEL_SHARP_LS037V7DW01=m
+CONFIG_FB_OMAP2_PANEL_TPO_TD028TTEC1=m
+CONFIG_FB_OMAP2_PANEL_TPO_TD043MTEA1=m
+CONFIG_FB_OMAP2_PANEL_NEC_NL8048HL11=m
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 CONFIG_LCD_CLASS_DEVICE=y
 CONFIG_LCD_PLATFORM=y
@@ -354,6 +355,11 @@ CONFIG_USB_MUSB_DSPS=m
 CONFIG_USB_INVENTRA_DMA=y
 CONFIG_USB_TI_CPPI41_DMA=y
 CONFIG_USB_DWC3=m
+CONFIG_USB_SERIAL=m
+CONFIG_USB_SERIAL_GENERIC=y
+CONFIG_USB_SERIAL_SIMPLE=m
+CONFIG_USB_SERIAL_FTDI_SIO=m
+CONFIG_USB_SERIAL_PL2303=m
 CONFIG_USB_TEST=m
 CONFIG_AM335X_PHY_USB=y
 CONFIG_USB_GADGET=m
@@ -387,6 +393,7 @@ CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=m
 CONFIG_LEDS_GPIO=m
 CONFIG_LEDS_PWM=m
+CONFIG_LEDS_PCA963X=m
 CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_TIMER=m
 CONFIG_LEDS_TRIGGER_ONESHOT=m
@@ -449,6 +456,8 @@ CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_INFO_SPLIT=y
+CONFIG_DEBUG_INFO_DWARF4=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_SCHEDSTATS=y
 CONFIG_TIMER_STATS=y
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index ede692ffa32e..5dd2528e9e45 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -417,6 +417,7 @@
 #define __NR_userfaultfd		(__NR_SYSCALL_BASE+388)
 #define __NR_membarrier			(__NR_SYSCALL_BASE+389)
 #define __NR_mlock2			(__NR_SYSCALL_BASE+390)
+#define __NR_copy_file_range		(__NR_SYSCALL_BASE+391)
 
 /*
  * The following SWIs are ARM private.
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index ac368bb068d1..dfc7cd6851ad 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -400,6 +400,7 @@
 		CALL(sys_userfaultfd)
 		CALL(sys_membarrier)
 		CALL(sys_mlock2)
+		CALL(sys_copy_file_range)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
diff --git a/arch/arm/mach-omap2/devices.c b/arch/arm/mach-omap2/devices.c
index 9cda974a3009..d7f1d69daf6d 100644
--- a/arch/arm/mach-omap2/devices.c
+++ b/arch/arm/mach-omap2/devices.c
@@ -18,7 +18,6 @@
 #include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/pinctrl/machine.h>
-#include <linux/platform_data/mailbox-omap.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/map.h>
@@ -66,32 +65,6 @@ static int __init omap3_l3_init(void)
 }
 omap_postcore_initcall(omap3_l3_init);
 
-#if defined(CONFIG_OMAP2PLUS_MBOX) || defined(CONFIG_OMAP2PLUS_MBOX_MODULE)
-static inline void __init omap_init_mbox(void)
-{
-	struct omap_hwmod *oh;
-	struct platform_device *pdev;
-	struct omap_mbox_pdata *pdata;
-
-	oh = omap_hwmod_lookup("mailbox");
-	if (!oh) {
-		pr_err("%s: unable to find hwmod\n", __func__);
-		return;
-	}
-	if (!oh->dev_attr) {
-		pr_err("%s: hwmod doesn't have valid attrs\n", __func__);
-		return;
-	}
-
-	pdata = (struct omap_mbox_pdata *)oh->dev_attr;
-	pdev = omap_device_build("omap-mailbox", -1, oh, pdata, sizeof(*pdata));
-	WARN(IS_ERR(pdev), "%s: could not build device, err %ld\n",
-						__func__, PTR_ERR(pdev));
-}
-#else
-static inline void omap_init_mbox(void) { }
-#endif /* CONFIG_OMAP2PLUS_MBOX */
-
 static inline void omap_init_sti(void) {}
 
 #if defined(CONFIG_SPI_OMAP24XX) || defined(CONFIG_SPI_OMAP24XX_MODULE)
@@ -229,7 +202,6 @@ static int __init omap2_init_devices(void)
 		 * please keep these calls, and their implementations above,
 		 * in alphabetical order so they're easier to sort through.
 		 */
-		omap_init_mbox();
 		omap_init_mcspi();
 		omap_init_sham();
 		omap_init_aes();
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index e781e4fae13a..a935d28443da 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -23,6 +23,8 @@
 #include <linux/platform_data/pinctrl-single.h>
 #include <linux/platform_data/iommu-omap.h>
 #include <linux/platform_data/wkup_m3.h>
+#include <linux/platform_data/pwm_omap_dmtimer.h>
+#include <plat/dmtimer.h>
 
 #include "common.h"
 #include "common-board-devices.h"
@@ -449,6 +451,24 @@ void omap_auxdata_legacy_init(struct device *dev)
 	dev->platform_data = &twl_gpio_auxdata;
 }
 
+/* Dual mode timer PWM callbacks platdata */
+#if IS_ENABLED(CONFIG_OMAP_DM_TIMER)
+struct pwm_omap_dmtimer_pdata pwm_dmtimer_pdata = {
+	.request_by_node = omap_dm_timer_request_by_node,
+	.free = omap_dm_timer_free,
+	.enable = omap_dm_timer_enable,
+	.disable = omap_dm_timer_disable,
+	.get_fclk = omap_dm_timer_get_fclk,
+	.start = omap_dm_timer_start,
+	.stop = omap_dm_timer_stop,
+	.set_load = omap_dm_timer_set_load,
+	.set_match = omap_dm_timer_set_match,
+	.set_pwm = omap_dm_timer_set_pwm,
+	.set_prescaler = omap_dm_timer_set_prescaler,
+	.write_counter = omap_dm_timer_write_counter,
+};
+#endif
+
 /*
  * Few boards still need auxdata populated before we populate
  * the dev entries in of_platform_populate().
@@ -502,6 +522,9 @@ static struct of_dev_auxdata omap_auxdata_lookup[] __initdata = {
 	OF_DEV_AUXDATA("ti,am4372-wkup-m3", 0x44d00000, "44d00000.wkup_m3",
 		       &wkup_m3_data),
 #endif
+#if IS_ENABLED(CONFIG_OMAP_DM_TIMER)
+	OF_DEV_AUXDATA("ti,omap-dmtimer-pwm", 0, NULL, &pwm_dmtimer_pdata),
+#endif
 #if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5)
 	OF_DEV_AUXDATA("ti,omap4-iommu", 0x4a066000, "4a066000.mmu",
 		       &omap4_iommu_pdata),
diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S
index eafd120b53f1..1b9f0520dea9 100644
--- a/arch/arm/mach-omap2/sleep34xx.S
+++ b/arch/arm/mach-omap2/sleep34xx.S
@@ -86,13 +86,18 @@ ENTRY(enable_omap3630_toggle_l2_on_restore)
 	stmfd	sp!, {lr}	@ save registers on stack
 	/* Setup so that we will disable and enable l2 */
 	mov	r1, #0x1
-	adrl	r2, l2dis_3630	@ may be too distant for plain adr
-	str	r1, [r2]
+	adrl	r3, l2dis_3630_offset	@ may be too distant for plain adr
+	ldr	r2, [r3]		@ value for offset
+	str	r1, [r2, r3]		@ write to l2dis_3630
 	ldmfd	sp!, {pc}	@ restore regs and return
 ENDPROC(enable_omap3630_toggle_l2_on_restore)
 
-	.text
-/* Function to call rom code to save secure ram context */
+/*
+ * Function to call rom code to save secure ram context. This gets
+ * relocated to SRAM, so it can be all in .data section. Otherwise
+ * we need to initialize api_params separately.
+ */
+	.data
 	.align	3
 ENTRY(save_secure_ram_context)
 	stmfd	sp!, {r4 - r11, lr}	@ save registers on stack
@@ -126,6 +131,8 @@ ENDPROC(save_secure_ram_context)
 ENTRY(save_secure_ram_context_sz)
 	.word	. - save_secure_ram_context
 
+	.text
+
 /*
  * ======================
  * == Idle entry point ==
@@ -289,12 +296,6 @@ wait_sdrc_ready:
 	bic	r5, r5, #0x40
 	str	r5, [r4]
 
-/*
- * PC-relative stores lead to undefined behaviour in Thumb-2: use a r7 as a
- * base instead.
- * Be careful not to clobber r7 when maintaing this code.
- */
-
 is_dll_in_lock_mode:
 	/* Is dll in lock mode? */
 	ldr	r4, sdrc_dlla_ctrl
@@ -302,11 +303,7 @@ is_dll_in_lock_mode:
 	tst	r5, #0x4
 	bne	exit_nonoff_modes	@ Return if locked
 	/* wait till dll locks */
-	adr	r7, kick_counter
 wait_dll_lock_timed:
-	ldr	r4, wait_dll_lock_counter
-	add	r4, r4, #1
-	str	r4, [r7, #wait_dll_lock_counter - kick_counter]
 	ldr	r4, sdrc_dlla_status
 	/* Wait 20uS for lock */
 	mov	r6, #8
@@ -330,9 +327,6 @@ kick_dll:
 	orr	r6, r6, #(1<<3)		@ enable dll
 	str	r6, [r4]
 	dsb
-	ldr	r4, kick_counter
-	add	r4, r4, #1
-	str	r4, [r7]		@ kick_counter
 	b	wait_dll_lock_timed
 
 exit_nonoff_modes:
@@ -360,15 +354,6 @@ sdrc_dlla_status:
 	.word	SDRC_DLLA_STATUS_V
 sdrc_dlla_ctrl:
 	.word	SDRC_DLLA_CTRL_V
-	/*
-	 * When exporting to userspace while the counters are in SRAM,
-	 * these 2 words need to be at the end to facilitate retrival!
-	 */
-kick_counter:
-	.word	0
-wait_dll_lock_counter:
-	.word	0
-
 ENTRY(omap3_do_wfi_sz)
 	.word	. - omap3_do_wfi
 
@@ -437,7 +422,9 @@ ENTRY(omap3_restore)
 	cmp	r2, #0x0	@ Check if target power state was OFF or RET
 	bne	logic_l1_restore
 
-	ldr	r0, l2dis_3630
+	adr	r1, l2dis_3630_offset	@ address for offset
+	ldr	r0, [r1]		@ value for offset
+	ldr	r0, [r1, r0]		@ value at l2dis_3630
 	cmp	r0, #0x1	@ should we disable L2 on 3630?
 	bne	skipl2dis
 	mrc	p15, 0, r0, c1, c0, 1
@@ -449,12 +436,14 @@ skipl2dis:
 	and	r1, #0x700
 	cmp	r1, #0x300
 	beq	l2_inv_gp
+	adr	r0, l2_inv_api_params_offset
+	ldr	r3, [r0]
+	add	r3, r3, r0		@ r3 points to dummy parameters
 	mov	r0, #40			@ set service ID for PPA
 	mov	r12, r0			@ copy secure Service ID in r12
 	mov	r1, #0			@ set task id for ROM code in r1
 	mov	r2, #4			@ set some flags in r2, r6
 	mov	r6, #0xff
-	adr	r3, l2_inv_api_params	@ r3 points to dummy parameters
 	dsb				@ data write barrier
 	dmb				@ data memory barrier
 	smc	#1			@ call SMI monitor (smi #1)
@@ -488,8 +477,8 @@ skipl2dis:
 	b	logic_l1_restore
 
 	.align
-l2_inv_api_params:
-	.word	0x1, 0x00
+l2_inv_api_params_offset:
+	.long	l2_inv_api_params - .
 l2_inv_gp:
 	/* Execute smi to invalidate L2 cache */
 	mov r12, #0x1			@ set up to invalidate L2
@@ -506,7 +495,9 @@ l2_inv_gp:
 	mov	r12, #0x2
 	smc	#0			@ Call SMI monitor (smieq)
 logic_l1_restore:
-	ldr	r1, l2dis_3630
+	adr	r0, l2dis_3630_offset	@ adress for offset
+	ldr	r1, [r0]		@ value for offset
+	ldr	r1, [r0, r1]		@ value at l2dis_3630
 	cmp	r1, #0x1		@ Test if L2 re-enable needed on 3630
 	bne	skipl2reen
 	mrc	p15, 0, r1, c1, c0, 1
@@ -535,9 +526,17 @@ control_stat:
 	.word	CONTROL_STAT
 control_mem_rta:
 	.word	CONTROL_MEM_RTA_CTRL
+l2dis_3630_offset:
+	.long	l2dis_3630 - .
+
+	.data
 l2dis_3630:
 	.word	0
 
+	.data
+l2_inv_api_params:
+	.word	0x1, 0x00
+
 /*
  * Internal functions
  */
diff --git a/arch/arm/mach-omap2/sleep44xx.S b/arch/arm/mach-omap2/sleep44xx.S
index 9b09d85d811a..c7a3b4aab4b5 100644
--- a/arch/arm/mach-omap2/sleep44xx.S
+++ b/arch/arm/mach-omap2/sleep44xx.S
@@ -29,12 +29,6 @@
 	dsb
 .endm
 
-ppa_zero_params:
-	.word		0x0
-
-ppa_por_params:
-	.word		1, 0
-
 #ifdef CONFIG_ARCH_OMAP4
 
 /*
@@ -266,7 +260,9 @@ ENTRY(omap4_cpu_resume)
 	beq	skip_ns_smp_enable
 ppa_actrl_retry:
 	mov     r0, #OMAP4_PPA_CPU_ACTRL_SMP_INDEX
-	adr	r3, ppa_zero_params		@ Pointer to parameters
+	adr	r1, ppa_zero_params_offset
+	ldr	r3, [r1]
+	add	r3, r3, r1			@ Pointer to ppa_zero_params
 	mov	r1, #0x0			@ Process ID
 	mov	r2, #0x4			@ Flag
 	mov	r6, #0xff
@@ -303,7 +299,9 @@ skip_ns_smp_enable:
 	ldr     r0, =OMAP4_PPA_L2_POR_INDEX
 	ldr     r1, =OMAP44XX_SAR_RAM_BASE
 	ldr     r4, [r1, #L2X0_PREFETCH_CTRL_OFFSET]
-	adr     r3, ppa_por_params
+	adr     r1, ppa_por_params_offset
+	ldr	r3, [r1]
+	add	r3, r3, r1			@ Pointer to ppa_por_params
 	str     r4, [r3, #0x04]
 	mov	r1, #0x0			@ Process ID
 	mov	r2, #0x4			@ Flag
@@ -328,6 +326,8 @@ skip_l2en:
 #endif
 
 	b	cpu_resume			@ Jump to generic resume
+ppa_por_params_offset:
+	.long	ppa_por_params - .
 ENDPROC(omap4_cpu_resume)
 #endif	/* CONFIG_ARCH_OMAP4 */
 
@@ -380,4 +380,13 @@ ENTRY(omap_do_wfi)
 	nop
 
 	ldmfd	sp!, {pc}
+ppa_zero_params_offset:
+	.long	ppa_zero_params - .
 ENDPROC(omap_do_wfi)
+
+	.data
+ppa_zero_params:
+	.word		0
+
+ppa_por_params:
+	.word		1, 0
diff --git a/arch/arm/mach-realview/Kconfig b/arch/arm/mach-realview/Kconfig
index def40a0dd60c..70ab4a25a5f8 100644
--- a/arch/arm/mach-realview/Kconfig
+++ b/arch/arm/mach-realview/Kconfig
@@ -1,5 +1,6 @@
 menuconfig ARCH_REALVIEW
-	bool "ARM Ltd. RealView family" if ARCH_MULTI_V5 || ARCH_MULTI_V6 || ARCH_MULTI_V7
+	bool "ARM Ltd. RealView family"
+	depends on ARCH_MULTI_V5 || ARCH_MULTI_V6 || ARCH_MULTI_V7
 	select ARM_AMBA
 	select ARM_TIMER_SP804
 	select COMMON_CLK_VERSATILE
diff --git a/arch/arm/mach-realview/platsmp-dt.c b/arch/arm/mach-realview/platsmp-dt.c
index 65585392655b..6964e8876061 100644
--- a/arch/arm/mach-realview/platsmp-dt.c
+++ b/arch/arm/mach-realview/platsmp-dt.c
@@ -80,7 +80,7 @@ static void __init realview_smp_prepare_cpus(unsigned int max_cpus)
 		     virt_to_phys(versatile_secondary_startup));
 }
 
-struct smp_operations realview_dt_smp_ops __initdata = {
+static const struct smp_operations realview_dt_smp_ops __initconst = {
 	.smp_prepare_cpus	= realview_smp_prepare_cpus,
 	.smp_secondary_init	= versatile_secondary_init,
 	.smp_boot_secondary	= versatile_boot_secondary,
diff --git a/arch/arm/mach-tango/Kconfig b/arch/arm/mach-tango/Kconfig
index d6a3714b096e..ebe15b93bbe8 100644
--- a/arch/arm/mach-tango/Kconfig
+++ b/arch/arm/mach-tango/Kconfig
@@ -1,5 +1,6 @@
 config ARCH_TANGO
-	bool "Sigma Designs Tango4 (SMP87xx)" if ARCH_MULTI_V7
+	bool "Sigma Designs Tango4 (SMP87xx)"
+	depends on ARCH_MULTI_V7
 	# Cortex-A9 MPCore r3p0, PL310 r3p2
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARM_ERRATA_754322
diff --git a/arch/arm/mach-tango/platsmp.c b/arch/arm/mach-tango/platsmp.c
index a18d5a34e2f5..a21f55e000d2 100644
--- a/arch/arm/mach-tango/platsmp.c
+++ b/arch/arm/mach-tango/platsmp.c
@@ -9,7 +9,7 @@ static int tango_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	return 0;
 }
 
-static struct smp_operations tango_smp_ops __initdata = {
+static const struct smp_operations tango_smp_ops __initconst = {
 	.smp_boot_secondary	= tango_boot_secondary,
 };
 
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index cd822d8454c0..307237cfe728 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -27,6 +27,8 @@ $(warning LSE atomics not supported by binutils)
 endif
 
 KBUILD_CFLAGS	+= -mgeneral-regs-only $(lseinstr)
+KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables
+KBUILD_CFLAGS	+= $(call cc-option, -mpc-relative-literal-loads)
 KBUILD_AFLAGS	+= $(lseinstr)
 
 ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi
index dd5158eb5872..e5b59ca9debb 100644
--- a/arch/arm64/boot/dts/arm/juno-base.dtsi
+++ b/arch/arm64/boot/dts/arm/juno-base.dtsi
@@ -115,6 +115,7 @@
 			     <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 90 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 91 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 92 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi b/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi
index da7b6e613257..933cba359918 100644
--- a/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi
+++ b/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi
@@ -23,9 +23,8 @@ soc0: soc@000000000 {
 		};
 	};
 
-	dsa: dsa@c7000000 {
+	dsaf0: dsa@c7000000 {
 		compatible = "hisilicon,hns-dsaf-v1";
-		dsa_name = "dsaf0";
 		mode = "6port-16rss";
 		interrupt-parent = <&mbigen_dsa>;
 
@@ -127,7 +126,7 @@ soc0: soc@000000000 {
 
 	eth0: ethernet@0{
 		compatible = "hisilicon,hns-nic-v1";
-		ae-name = "dsaf0";
+		ae-handle = <&dsaf0>;
 		port-id = <0>;
 		local-mac-address = [00 00 00 01 00 58];
 		status = "disabled";
@@ -135,14 +134,14 @@ soc0: soc@000000000 {
 	};
 	eth1: ethernet@1{
 		compatible = "hisilicon,hns-nic-v1";
-		ae-name = "dsaf0";
+		ae-handle = <&dsaf0>;
 		port-id = <1>;
 		status = "disabled";
 		dma-coherent;
 	};
 	eth2: ethernet@2{
 		compatible = "hisilicon,hns-nic-v1";
-		ae-name = "dsaf0";
+		ae-handle = <&dsaf0>;
 		port-id = <2>;
 		local-mac-address = [00 00 00 01 00 5a];
 		status = "disabled";
@@ -150,7 +149,7 @@ soc0: soc@000000000 {
 	};
 	eth3: ethernet@3{
 		compatible = "hisilicon,hns-nic-v1";
-		ae-name = "dsaf0";
+		ae-handle = <&dsaf0>;
 		port-id = <3>;
 		local-mac-address = [00 00 00 01 00 5b];
 		status = "disabled";
@@ -158,7 +157,7 @@ soc0: soc@000000000 {
 	};
 	eth4: ethernet@4{
 		compatible = "hisilicon,hns-nic-v1";
-		ae-name = "dsaf0";
+		ae-handle = <&dsaf0>;
 		port-id = <4>;
 		local-mac-address = [00 00 00 01 00 5c];
 		status = "disabled";
@@ -166,7 +165,7 @@ soc0: soc@000000000 {
 	};
 	eth5: ethernet@5{
 		compatible = "hisilicon,hns-nic-v1";
-		ae-name = "dsaf0";
+		ae-handle = <&dsaf0>;
 		port-id = <5>;
 		local-mac-address = [00 00 00 01 00 5d];
 		status = "disabled";
@@ -174,7 +173,7 @@ soc0: soc@000000000 {
 	};
 	eth6: ethernet@6{
 		compatible = "hisilicon,hns-nic-v1";
-		ae-name = "dsaf0";
+		ae-handle = <&dsaf0>;
 		port-id = <6>;
 		local-mac-address = [00 00 00 01 00 5e];
 		status = "disabled";
@@ -182,7 +181,7 @@ soc0: soc@000000000 {
 	};
 	eth7: ethernet@7{
 		compatible = "hisilicon,hns-nic-v1";
-		ae-name = "dsaf0";
+		ae-handle = <&dsaf0>;
 		port-id = <7>;
 		local-mac-address = [00 00 00 01 00 5f];
 		status = "disabled";
diff --git a/arch/arm64/boot/dts/nvidia/tegra132-norrin.dts b/arch/arm64/boot/dts/nvidia/tegra132-norrin.dts
index 7dfe1c085966..62f33fc84e3e 100644
--- a/arch/arm64/boot/dts/nvidia/tegra132-norrin.dts
+++ b/arch/arm64/boot/dts/nvidia/tegra132-norrin.dts
@@ -12,6 +12,8 @@
 		rtc1 = "/rtc@0,7000e000";
 	};
 
+	chosen { };
+
 	memory {
 		device_type = "memory";
 		reg = <0x0 0x80000000 0x0 0x80000000>;
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 18ca9fb9e65f..86581f793e39 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -16,7 +16,6 @@ CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_MEMCG=y
 CONFIG_MEMCG_SWAP=y
-CONFIG_MEMCG_KMEM=y
 CONFIG_CGROUP_HUGETLB=y
 # CONFIG_UTS_NS is not set
 # CONFIG_IPC_NS is not set
@@ -37,15 +36,13 @@ CONFIG_ARCH_EXYNOS7=y
 CONFIG_ARCH_LAYERSCAPE=y
 CONFIG_ARCH_HISI=y
 CONFIG_ARCH_MEDIATEK=y
+CONFIG_ARCH_QCOM=y
 CONFIG_ARCH_ROCKCHIP=y
 CONFIG_ARCH_SEATTLE=y
 CONFIG_ARCH_RENESAS=y
 CONFIG_ARCH_R8A7795=y
 CONFIG_ARCH_STRATIX10=y
 CONFIG_ARCH_TEGRA=y
-CONFIG_ARCH_TEGRA_132_SOC=y
-CONFIG_ARCH_TEGRA_210_SOC=y
-CONFIG_ARCH_QCOM=y
 CONFIG_ARCH_SPRD=y
 CONFIG_ARCH_THUNDER=y
 CONFIG_ARCH_UNIPHIER=y
@@ -54,14 +51,19 @@ CONFIG_ARCH_XGENE=y
 CONFIG_ARCH_ZYNQMP=y
 CONFIG_PCI=y
 CONFIG_PCI_MSI=y
+CONFIG_PCI_IOV=y
+CONFIG_PCI_RCAR_GEN2_PCIE=y
 CONFIG_PCI_HOST_GENERIC=y
 CONFIG_PCI_XGENE=y
-CONFIG_SMP=y
+CONFIG_PCI_LAYERSCAPE=y
+CONFIG_PCI_HISI=y
+CONFIG_PCIE_QCOM=y
 CONFIG_SCHED_MC=y
 CONFIG_PREEMPT=y
 CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CMA=y
+CONFIG_XEN=y
 CONFIG_CMDLINE="console=ttyAMA0"
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_COMPAT=y
@@ -100,7 +102,11 @@ CONFIG_PATA_OF_PLATFORM=y
 CONFIG_NETDEVICES=y
 CONFIG_TUN=y
 CONFIG_VIRTIO_NET=y
+CONFIG_AMD_XGBE=y
 CONFIG_NET_XGENE=y
+CONFIG_E1000E=y
+CONFIG_IGB=y
+CONFIG_IGBVF=y
 CONFIG_SKY2=y
 CONFIG_RAVB=y
 CONFIG_SMC91X=y
@@ -117,25 +123,23 @@ CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_DW=y
 CONFIG_SERIAL_8250_MT6577=y
 CONFIG_SERIAL_8250_UNIPHIER=y
+CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_AMBA_PL011=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
 CONFIG_SERIAL_SAMSUNG=y
-CONFIG_SERIAL_SAMSUNG_UARTS_4=y
-CONFIG_SERIAL_SAMSUNG_UARTS=4
 CONFIG_SERIAL_SAMSUNG_CONSOLE=y
+CONFIG_SERIAL_TEGRA=y
 CONFIG_SERIAL_SH_SCI=y
 CONFIG_SERIAL_SH_SCI_NR_UARTS=11
 CONFIG_SERIAL_SH_SCI_CONSOLE=y
-CONFIG_SERIAL_TEGRA=y
 CONFIG_SERIAL_MSM=y
 CONFIG_SERIAL_MSM_CONSOLE=y
-CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_XILINX_PS_UART=y
 CONFIG_SERIAL_XILINX_PS_UART_CONSOLE=y
 CONFIG_VIRTIO_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
 CONFIG_I2C_QUP=y
+CONFIG_I2C_UNIPHIER_F=y
 CONFIG_I2C_RCAR=y
 CONFIG_SPI=y
 CONFIG_SPI_PL022=y
@@ -176,8 +180,6 @@ CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_SDHCI_TEGRA=y
 CONFIG_MMC_SPI=y
 CONFIG_MMC_DW=y
-CONFIG_MMC_DW_IDMAC=y
-CONFIG_MMC_DW_PLTFM=y
 CONFIG_MMC_DW_EXYNOS=y
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
@@ -187,28 +189,33 @@ CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 CONFIG_LEDS_TRIGGER_CPU=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_EFI=y
+CONFIG_RTC_DRV_PL031=y
 CONFIG_RTC_DRV_XGENE=y
 CONFIG_DMADEVICES=y
-CONFIG_RCAR_DMAC=y
 CONFIG_QCOM_BAM_DMA=y
 CONFIG_TEGRA20_APB_DMA=y
+CONFIG_RCAR_DMAC=y
+CONFIG_VFIO=y
+CONFIG_VFIO_PCI=y
 CONFIG_VIRTIO_PCI=y
 CONFIG_VIRTIO_BALLOON=y
 CONFIG_VIRTIO_MMIO=y
+CONFIG_XEN_GNTDEV=y
+CONFIG_XEN_GRANT_DEV_ALLOC=y
 CONFIG_COMMON_CLK_CS2000_CP=y
 CONFIG_COMMON_CLK_QCOM=y
 CONFIG_MSM_GCC_8916=y
 CONFIG_HWSPINLOCK_QCOM=y
-# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_ARM_SMMU=y
 CONFIG_QCOM_SMEM=y
 CONFIG_QCOM_SMD=y
 CONFIG_QCOM_SMD_RPM=y
+CONFIG_ARCH_TEGRA_132_SOC=y
+CONFIG_ARCH_TEGRA_210_SOC=y
+CONFIG_HISILICON_IRQ_MBIGEN=y
 CONFIG_PHY_XGENE=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
 CONFIG_FANOTIFY=y
 CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
 CONFIG_QUOTA=y
@@ -239,6 +246,7 @@ CONFIG_LOCKUP_DETECTOR=y
 # CONFIG_FTRACE is not set
 CONFIG_MEMTEST=y
 CONFIG_SECURITY=y
+CONFIG_CRYPTO_ECHAINIV=y
 CONFIG_CRYPTO_ANSI_CPRNG=y
 CONFIG_ARM64_CRYPTO=y
 CONFIG_CRYPTO_SHA1_ARM64_CE=y
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 2731d3b25ed2..8ec88e5b290f 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -103,6 +103,7 @@ static inline u64 gic_read_iar_common(void)
 	u64 irqstat;
 
 	asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat));
+	dsb(sy);
 	return irqstat;
 }
 
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index 007a69fc4f40..5f3ab8c1db55 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -121,6 +121,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		return -EFAULT;
 
 	asm volatile("// futex_atomic_cmpxchg_inatomic\n"
+ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
 "	prfm	pstl1strm, %2\n"
 "1:	ldxr	%w1, %2\n"
 "	sub	%w3, %w1, %w4\n"
@@ -137,6 +138,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 "	.align	3\n"
 "	.quad	1b, 4b, 2b, 4b\n"
 "	.popsection\n"
+ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
 	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp)
 	: "r" (oldval), "r" (newval), "Ir" (-EFAULT)
 	: "memory");
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 738a95f93e49..bef6e9243c63 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -182,6 +182,7 @@
 #define CPTR_EL2_TCPAC	(1 << 31)
 #define CPTR_EL2_TTA	(1 << 20)
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
+#define CPTR_EL2_DEFAULT	0x000033ff
 
 /* Hyp Debug Configuration Register bits */
 #define MDCR_EL2_TDRA		(1 << 11)
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 3066328cd86b..779a5872a2c5 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -127,10 +127,14 @@ static inline unsigned long *vcpu_spsr(const struct kvm_vcpu *vcpu)
 
 static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu)
 {
-	u32 mode = *vcpu_cpsr(vcpu) & PSR_MODE_MASK;
+	u32 mode;
 
-	if (vcpu_mode_is_32bit(vcpu))
+	if (vcpu_mode_is_32bit(vcpu)) {
+		mode = *vcpu_cpsr(vcpu) & COMPAT_PSR_MODE_MASK;
 		return mode > COMPAT_PSR_MODE_USR;
+	}
+
+	mode = *vcpu_cpsr(vcpu) & PSR_MODE_MASK;
 
 	return mode != PSR_MODE_EL0t;
 }
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 9b2f5a9d019d..ae615b9d9a55 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -39,6 +39,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/personality.h> /* for READ_IMPLIES_EXEC */
 #include <asm/pgtable-types.h>
 
 extern void __cpu_clear_user_page(void *p, unsigned long user);
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 2d545d7aa80b..bf464de33f52 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -67,11 +67,11 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 #define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
 #define PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
 
-#define PROT_DEVICE_nGnRnE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
-#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
-#define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_NC))
-#define PROT_NORMAL_WT		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_WT))
-#define PROT_NORMAL		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL))
+#define PROT_DEVICE_nGnRnE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
+#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE))
+#define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC))
+#define PROT_NORMAL_WT		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT))
+#define PROT_NORMAL		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL))
 
 #define PROT_SECT_DEVICE_nGnRE	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE))
 #define PROT_SECT_NORMAL	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
@@ -81,7 +81,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 
 #define PAGE_KERNEL		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_RO		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
-#define PAGE_KERNEL_ROX	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
+#define PAGE_KERNEL_ROX		__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
 #define PAGE_KERNEL_EXEC	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_EXEC_CONT	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
 
@@ -153,6 +153,7 @@ extern struct page *empty_zero_page;
 #define pte_write(pte)		(!!(pte_val(pte) & PTE_WRITE))
 #define pte_exec(pte)		(!(pte_val(pte) & PTE_UXN))
 #define pte_cont(pte)		(!!(pte_val(pte) & PTE_CONT))
+#define pte_user(pte)		(!!(pte_val(pte) & PTE_USER))
 
 #ifdef CONFIG_ARM64_HW_AFDBM
 #define pte_hw_dirty(pte)	(pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
@@ -163,8 +164,6 @@ extern struct page *empty_zero_page;
 #define pte_dirty(pte)		(pte_sw_dirty(pte) || pte_hw_dirty(pte))
 
 #define pte_valid(pte)		(!!(pte_val(pte) & PTE_VALID))
-#define pte_valid_user(pte) \
-	((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
 #define pte_valid_not_user(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
 #define pte_valid_young(pte) \
@@ -278,13 +277,13 @@ extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pte)
 {
-	if (pte_valid_user(pte)) {
-		if (!pte_special(pte) && pte_exec(pte))
-			__sync_icache_dcache(pte, addr);
+	if (pte_valid(pte)) {
 		if (pte_sw_dirty(pte) && pte_write(pte))
 			pte_val(pte) &= ~PTE_RDONLY;
 		else
 			pte_val(pte) |= PTE_RDONLY;
+		if (pte_user(pte) && pte_exec(pte) && !pte_special(pte))
+			__sync_icache_dcache(pte, addr);
 	}
 
 	/*
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index ffe9c2b6431b..917d98108b3f 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -514,9 +514,14 @@ CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
 #endif
 
 	/* EL2 debug */
+	mrs	x0, id_aa64dfr0_el1		// Check ID_AA64DFR0_EL1 PMUVer
+	sbfx	x0, x0, #8, #4
+	cmp	x0, #1
+	b.lt	4f				// Skip if no PMU present
 	mrs	x0, pmcr_el0			// Disable debug access traps
 	ubfx	x0, x0, #11, #5			// to EL2 and allow access to
 	msr	mdcr_el2, x0			// all PMU counters from EL1
+4:
 
 	/* Stage-2 translation */
 	msr	vttbr_el2, xzr
diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h
index bc2abb8b1599..999633bd7294 100644
--- a/arch/arm64/kernel/image.h
+++ b/arch/arm64/kernel/image.h
@@ -65,6 +65,16 @@
 #ifdef CONFIG_EFI
 
 /*
+ * Prevent the symbol aliases below from being emitted into the kallsyms
+ * table, by forcing them to be absolute symbols (which are conveniently
+ * ignored by scripts/kallsyms) rather than section relative symbols.
+ * The distinction is only relevant for partial linking, and only for symbols
+ * that are defined within a section declaration (which is not the case for
+ * the definitions below) so the resulting values will be identical.
+ */
+#define KALLSYMS_HIDE(sym)	ABSOLUTE(sym)
+
+/*
  * The EFI stub has its own symbol namespace prefixed by __efistub_, to
  * isolate it from the kernel proper. The following symbols are legally
  * accessed by the stub, so provide some aliases to make them accessible.
@@ -73,25 +83,25 @@
  * linked at. The routines below are all implemented in assembler in a
  * position independent manner
  */
-__efistub_memcmp		= __pi_memcmp;
-__efistub_memchr		= __pi_memchr;
-__efistub_memcpy		= __pi_memcpy;
-__efistub_memmove		= __pi_memmove;
-__efistub_memset		= __pi_memset;
-__efistub_strlen		= __pi_strlen;
-__efistub_strcmp		= __pi_strcmp;
-__efistub_strncmp		= __pi_strncmp;
-__efistub___flush_dcache_area	= __pi___flush_dcache_area;
+__efistub_memcmp		= KALLSYMS_HIDE(__pi_memcmp);
+__efistub_memchr		= KALLSYMS_HIDE(__pi_memchr);
+__efistub_memcpy		= KALLSYMS_HIDE(__pi_memcpy);
+__efistub_memmove		= KALLSYMS_HIDE(__pi_memmove);
+__efistub_memset		= KALLSYMS_HIDE(__pi_memset);
+__efistub_strlen		= KALLSYMS_HIDE(__pi_strlen);
+__efistub_strcmp		= KALLSYMS_HIDE(__pi_strcmp);
+__efistub_strncmp		= KALLSYMS_HIDE(__pi_strncmp);
+__efistub___flush_dcache_area	= KALLSYMS_HIDE(__pi___flush_dcache_area);
 
 #ifdef CONFIG_KASAN
-__efistub___memcpy		= __pi_memcpy;
-__efistub___memmove		= __pi_memmove;
-__efistub___memset		= __pi_memset;
+__efistub___memcpy		= KALLSYMS_HIDE(__pi_memcpy);
+__efistub___memmove		= KALLSYMS_HIDE(__pi_memmove);
+__efistub___memset		= KALLSYMS_HIDE(__pi_memset);
 #endif
 
-__efistub__text			= _text;
-__efistub__end			= _end;
-__efistub__edata		= _edata;
+__efistub__text			= KALLSYMS_HIDE(_text);
+__efistub__end			= KALLSYMS_HIDE(_end);
+__efistub__edata		= KALLSYMS_HIDE(_edata);
 
 #endif
 
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index ca8f5a5e2f96..f0e7bdfae134 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -36,7 +36,11 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 	write_sysreg(val, hcr_el2);
 	/* Trap on AArch32 cp15 c15 accesses (EL1 or EL0) */
 	write_sysreg(1 << 15, hstr_el2);
-	write_sysreg(CPTR_EL2_TTA | CPTR_EL2_TFP, cptr_el2);
+
+	val = CPTR_EL2_DEFAULT;
+	val |= CPTR_EL2_TTA | CPTR_EL2_TFP;
+	write_sysreg(val, cptr_el2);
+
 	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
 }
 
@@ -45,7 +49,7 @@ static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
 	write_sysreg(HCR_RW, hcr_el2);
 	write_sysreg(0, hstr_el2);
 	write_sysreg(read_sysreg(mdcr_el2) & MDCR_EL2_HPMN_MASK, mdcr_el2);
-	write_sysreg(0, cptr_el2);
+	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
 }
 
 static void __hyp_text __activate_vm(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index 648112e90ed5..4d1ac81870d2 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -27,7 +27,11 @@
 
 #define PSTATE_FAULT_BITS_64 	(PSR_MODE_EL1h | PSR_A_BIT | PSR_F_BIT | \
 				 PSR_I_BIT | PSR_D_BIT)
-#define EL1_EXCEPT_SYNC_OFFSET	0x200
+
+#define CURRENT_EL_SP_EL0_VECTOR	0x0
+#define CURRENT_EL_SP_ELx_VECTOR	0x200
+#define LOWER_EL_AArch64_VECTOR		0x400
+#define LOWER_EL_AArch32_VECTOR		0x600
 
 static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
 {
@@ -97,6 +101,34 @@ static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt,
 		*fsr = 0x14;
 }
 
+enum exception_type {
+	except_type_sync	= 0,
+	except_type_irq		= 0x80,
+	except_type_fiq		= 0x100,
+	except_type_serror	= 0x180,
+};
+
+static u64 get_except_vector(struct kvm_vcpu *vcpu, enum exception_type type)
+{
+	u64 exc_offset;
+
+	switch (*vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT)) {
+	case PSR_MODE_EL1t:
+		exc_offset = CURRENT_EL_SP_EL0_VECTOR;
+		break;
+	case PSR_MODE_EL1h:
+		exc_offset = CURRENT_EL_SP_ELx_VECTOR;
+		break;
+	case PSR_MODE_EL0t:
+		exc_offset = LOWER_EL_AArch64_VECTOR;
+		break;
+	default:
+		exc_offset = LOWER_EL_AArch32_VECTOR;
+	}
+
+	return vcpu_sys_reg(vcpu, VBAR_EL1) + exc_offset + type;
+}
+
 static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr)
 {
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
@@ -108,8 +140,8 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr
 	*vcpu_spsr(vcpu) = cpsr;
 	*vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu);
 
+	*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
 	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
-	*vcpu_pc(vcpu) = vcpu_sys_reg(vcpu, VBAR_EL1) + EL1_EXCEPT_SYNC_OFFSET;
 
 	vcpu_sys_reg(vcpu, FAR_EL1) = addr;
 
@@ -143,8 +175,8 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 	*vcpu_spsr(vcpu) = cpsr;
 	*vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu);
 
+	*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
 	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
-	*vcpu_pc(vcpu) = vcpu_sys_reg(vcpu, VBAR_EL1) + EL1_EXCEPT_SYNC_OFFSET;
 
 	/*
 	 * Build an unknown exception, depending on the instruction
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index eec3598b4184..2e90371cfb37 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1007,10 +1007,9 @@ static int emulate_cp(struct kvm_vcpu *vcpu,
 		if (likely(r->access(vcpu, params, r))) {
 			/* Skip instruction, since it was emulated */
 			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+			/* Handled */
+			return 0;
 		}
-
-		/* Handled */
-		return 0;
 	}
 
 	/* Not handled */
@@ -1043,7 +1042,7 @@ static void unhandled_cp_access(struct kvm_vcpu *vcpu,
 }
 
 /**
- * kvm_handle_cp_64 -- handles a mrrc/mcrr trap on a guest CP15 access
+ * kvm_handle_cp_64 -- handles a mrrc/mcrr trap on a guest CP14/CP15 access
  * @vcpu: The VCPU pointer
  * @run:  The kvm_run struct
  */
@@ -1095,7 +1094,7 @@ out:
 }
 
 /**
- * kvm_handle_cp15_32 -- handles a mrc/mcr trap on a guest CP15 access
+ * kvm_handle_cp_32 -- handles a mrc/mcr trap on a guest CP14/CP15 access
  * @vcpu: The VCPU pointer
  * @run:  The kvm_run struct
  */
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index 5a22a119a74c..0adbebbc2803 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -46,7 +46,7 @@ enum address_markers_idx {
 	PCI_START_NR,
 	PCI_END_NR,
 	MODULES_START_NR,
-	MODUELS_END_NR,
+	MODULES_END_NR,
 	KERNEL_SPACE_NR,
 };
 
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index cf038c7d9fa9..cab7a5be40aa 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -120,6 +120,7 @@ static void __init cpu_set_ttbr1(unsigned long ttbr1)
 void __init kasan_init(void)
 {
 	struct memblock_region *reg;
+	int i;
 
 	/*
 	 * We are going to perform proper setup of shadow memory.
@@ -155,6 +156,14 @@ void __init kasan_init(void)
 				pfn_to_nid(virt_to_pfn(start)));
 	}
 
+	/*
+	 * KAsan may reuse the contents of kasan_zero_pte directly, so we
+	 * should make sure that it maps the zero page read-only.
+	 */
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		set_pte(&kasan_zero_pte[i],
+			pfn_pte(virt_to_pfn(kasan_zero_page), PAGE_KERNEL_RO));
+
 	memset(kasan_zero_page, 0, PAGE_SIZE);
 	cpu_set_ttbr1(__pa(swapper_pg_dir));
 	flush_tlb_all();
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index 3571c7309c5e..0795c3a36d8f 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -14,6 +14,7 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/vmalloc.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -44,6 +45,7 @@ static int change_memory_common(unsigned long addr, int numpages,
 	unsigned long end = start + size;
 	int ret;
 	struct page_change_data data;
+	struct vm_struct *area;
 
 	if (!PAGE_ALIGNED(addr)) {
 		start &= PAGE_MASK;
@@ -51,11 +53,27 @@ static int change_memory_common(unsigned long addr, int numpages,
 		WARN_ON_ONCE(1);
 	}
 
-	if (start < MODULES_VADDR || start >= MODULES_END)
+	/*
+	 * Kernel VA mappings are always live, and splitting live section
+	 * mappings into page mappings may cause TLB conflicts. This means
+	 * we have to ensure that changing the permission bits of the range
+	 * we are operating on does not result in such splitting.
+	 *
+	 * Let's restrict ourselves to mappings created by vmalloc (or vmap).
+	 * Those are guaranteed to consist entirely of page mappings, and
+	 * splitting is never needed.
+	 *
+	 * So check whether the [addr, addr + size) interval is entirely
+	 * covered by precisely one VM area that has the VM_ALLOC flag set.
+	 */
+	area = find_vm_area((void *)addr);
+	if (!area ||
+	    end > (unsigned long)area->addr + area->size ||
+	    !(area->flags & VM_ALLOC))
 		return -EINVAL;
 
-	if (end < MODULES_VADDR || end >= MODULES_END)
-		return -EINVAL;
+	if (!numpages)
+		return 0;
 
 	data.set_mask = set_mask;
 	data.clear_mask = clear_mask;
diff --git a/arch/arm64/mm/proc-macros.S b/arch/arm64/mm/proc-macros.S
index 146bd99a7532..e6a30e1268a8 100644
--- a/arch/arm64/mm/proc-macros.S
+++ b/arch/arm64/mm/proc-macros.S
@@ -84,3 +84,15 @@
 	b.lo	9998b
 	dsb	\domain
 	.endm
+
+/*
+ * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present
+ */
+	.macro	reset_pmuserenr_el0, tmpreg
+	mrs	\tmpreg, id_aa64dfr0_el1	// Check ID_AA64DFR0_EL1 PMUVer
+	sbfx	\tmpreg, \tmpreg, #8, #4
+	cmp	\tmpreg, #1			// Skip if no PMU present
+	b.lt	9000f
+	msr	pmuserenr_el0, xzr		// Disable PMU access from EL0
+9000:
+	.endm
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index a3d867e723b4..c164d2cb35c0 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -117,7 +117,7 @@ ENTRY(cpu_do_resume)
 	 */
 	ubfx	x11, x11, #1, #1
 	msr	oslar_el1, x11
-	msr	pmuserenr_el0, xzr		// Disable PMU access from EL0
+	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
 	mov	x0, x12
 	dsb	nsh		// Make sure local tlb invalidation completed
 	isb
@@ -154,7 +154,7 @@ ENTRY(__cpu_setup)
 	msr	cpacr_el1, x0			// Enable FP/ASIMD
 	mov	x0, #1 << 12			// Reset mdscr_el1 and disable
 	msr	mdscr_el1, x0			// access to the DCC from EL0
-	msr	pmuserenr_el0, xzr		// Disable PMU access from EL0
+	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
 	/*
 	 * Memory region attributes for LPAE:
 	 *
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index 836ac5a963c8..2841c0a3fd3b 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -276,6 +276,7 @@ source "kernel/Kconfig.preempt"
 
 config SMP
 	bool "Symmetric multi-processing support"
+	depends on MMU
 	---help---
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, say N. If you have a system with more
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 57a945e832f4..74a3db92da1b 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2085,7 +2085,7 @@ config PAGE_SIZE_32KB
 
 config PAGE_SIZE_64KB
 	bool "64kB"
-	depends on !CPU_R3000 && !CPU_TX39XX
+	depends on !CPU_R3000 && !CPU_TX39XX && !CPU_R6000
 	help
 	  Using 64kB page size will result in higher performance kernel at
 	  the price of higher memory consumption.  This option is available on
diff --git a/arch/mips/bcm63xx/nvram.c b/arch/mips/bcm63xx/nvram.c
index 5f2bc1e10eae..05757aed016c 100644
--- a/arch/mips/bcm63xx/nvram.c
+++ b/arch/mips/bcm63xx/nvram.c
@@ -19,6 +19,8 @@
 
 #include <bcm63xx_nvram.h>
 
+#define BCM63XX_DEFAULT_PSI_SIZE	64
+
 static struct bcm963xx_nvram nvram;
 static int mac_addr_used;
 
@@ -85,3 +87,12 @@ int bcm63xx_nvram_get_mac_address(u8 *mac)
 	return 0;
 }
 EXPORT_SYMBOL(bcm63xx_nvram_get_mac_address);
+
+int bcm63xx_nvram_get_psi_size(void)
+{
+	if (nvram.psi_size > 0)
+		return nvram.psi_size;
+
+	return BCM63XX_DEFAULT_PSI_SIZE;
+}
+EXPORT_SYMBOL(bcm63xx_nvram_get_psi_size);
diff --git a/arch/mips/boot/dts/brcm/bcm6328.dtsi b/arch/mips/boot/dts/brcm/bcm6328.dtsi
index 459b9b252c3b..d61b1616b604 100644
--- a/arch/mips/boot/dts/brcm/bcm6328.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm6328.dtsi
@@ -74,6 +74,7 @@
 		timer: timer@10000040 {
 			compatible = "syscon";
 			reg = <0x10000040 0x2c>;
+			little-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7125.dtsi b/arch/mips/boot/dts/brcm/bcm7125.dtsi
index 4fc7ecee273c..1a7efa883c5e 100644
--- a/arch/mips/boot/dts/brcm/bcm7125.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7125.dtsi
@@ -98,6 +98,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7125-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x60c>;
+			little-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7346.dtsi b/arch/mips/boot/dts/brcm/bcm7346.dtsi
index a3039bb53477..d4bf52cfcf17 100644
--- a/arch/mips/boot/dts/brcm/bcm7346.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7346.dtsi
@@ -118,6 +118,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7346-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
+			little-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7358.dtsi b/arch/mips/boot/dts/brcm/bcm7358.dtsi
index 4274ff41ec21..8e2501694d03 100644
--- a/arch/mips/boot/dts/brcm/bcm7358.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7358.dtsi
@@ -112,6 +112,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7358-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
+			little-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7360.dtsi b/arch/mips/boot/dts/brcm/bcm7360.dtsi
index 0dcc9163c27b..7e5f76040fb8 100644
--- a/arch/mips/boot/dts/brcm/bcm7360.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7360.dtsi
@@ -112,6 +112,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7360-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
+			little-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7362.dtsi b/arch/mips/boot/dts/brcm/bcm7362.dtsi
index 2f3f9fc2c478..c739ea77acb0 100644
--- a/arch/mips/boot/dts/brcm/bcm7362.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7362.dtsi
@@ -118,6 +118,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7362-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
+			little-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7420.dtsi b/arch/mips/boot/dts/brcm/bcm7420.dtsi
index bee221b3b568..5f55d0a50a28 100644
--- a/arch/mips/boot/dts/brcm/bcm7420.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7420.dtsi
@@ -99,6 +99,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7420-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x60c>;
+			little-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7425.dtsi b/arch/mips/boot/dts/brcm/bcm7425.dtsi
index 571f30f52e3f..e24d41ab4e30 100644
--- a/arch/mips/boot/dts/brcm/bcm7425.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7425.dtsi
@@ -100,6 +100,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7425-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
+			little-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7435.dtsi b/arch/mips/boot/dts/brcm/bcm7435.dtsi
index 614ee211f71a..8b9432cc062b 100644
--- a/arch/mips/boot/dts/brcm/bcm7435.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7435.dtsi
@@ -114,6 +114,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7425-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
+			little-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/include/asm/elf.h b/arch/mips/include/asm/elf.h
index cefb7a596878..e090fc388e02 100644
--- a/arch/mips/include/asm/elf.h
+++ b/arch/mips/include/asm/elf.h
@@ -227,7 +227,7 @@ struct mips_elf_abiflags_v0 {
 	int __res = 1;							\
 	struct elfhdr *__h = (hdr);					\
 									\
-	if (__h->e_machine != EM_MIPS)					\
+	if (!mips_elf_check_machine(__h))				\
 		__res = 0;						\
 	if (__h->e_ident[EI_CLASS] != ELFCLASS32)			\
 		__res = 0;						\
@@ -258,7 +258,7 @@ struct mips_elf_abiflags_v0 {
 	int __res = 1;							\
 	struct elfhdr *__h = (hdr);					\
 									\
-	if (__h->e_machine != EM_MIPS)					\
+	if (!mips_elf_check_machine(__h))				\
 		__res = 0;						\
 	if (__h->e_ident[EI_CLASS] != ELFCLASS64)			\
 		__res = 0;						\
@@ -285,6 +285,11 @@ struct mips_elf_abiflags_v0 {
 
 #endif /* !defined(ELF_ARCH) */
 
+#define mips_elf_check_machine(x) ((x)->e_machine == EM_MIPS)
+
+#define vmcore_elf32_check_arch mips_elf_check_machine
+#define vmcore_elf64_check_arch mips_elf_check_machine
+
 struct mips_abi;
 
 extern struct mips_abi mips_abi;
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index 9cbf383b8834..f06f97bd62df 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -179,6 +179,10 @@ static inline void lose_fpu_inatomic(int save, struct task_struct *tsk)
 		if (save)
 			_save_fp(tsk);
 		__disable_fpu();
+	} else {
+		/* FPU should not have been left enabled with no owner */
+		WARN(read_c0_status() & ST0_CU1,
+		     "Orphaned FPU left enabled");
 	}
 	KSTK_STATUS(tsk) &= ~ST0_CU1;
 	clear_tsk_thread_flag(tsk, TIF_USEDFPU);
diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h
index 4e0b6bc1165e..348df49dcc9f 100644
--- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h
+++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h
@@ -30,4 +30,6 @@ u8 *bcm63xx_nvram_get_name(void);
  */
 int bcm63xx_nvram_get_mac_address(u8 *mac);
 
+int bcm63xx_nvram_get_psi_size(void);
+
 #endif /* BCM63XX_NVRAM_H */
diff --git a/arch/mips/include/asm/octeon/octeon-feature.h b/arch/mips/include/asm/octeon/octeon-feature.h
index 8ebd3f579b84..3ed10a8d7865 100644
--- a/arch/mips/include/asm/octeon/octeon-feature.h
+++ b/arch/mips/include/asm/octeon/octeon-feature.h
@@ -128,7 +128,8 @@ static inline int octeon_has_feature(enum octeon_feature feature)
 	case OCTEON_FEATURE_PCIE:
 		return OCTEON_IS_MODEL(OCTEON_CN56XX)
 			|| OCTEON_IS_MODEL(OCTEON_CN52XX)
-			|| OCTEON_IS_MODEL(OCTEON_CN6XXX);
+			|| OCTEON_IS_MODEL(OCTEON_CN6XXX)
+			|| OCTEON_IS_MODEL(OCTEON_CN7XXX);
 
 	case OCTEON_FEATURE_SRIO:
 		return OCTEON_IS_MODEL(OCTEON_CN63XX)
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index 3f832c3dd8f5..041153f5cf93 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -45,7 +45,7 @@ extern unsigned int vced_count, vcei_count;
  * User space process size: 2GB. This is hardcoded into a few places,
  * so don't change it unless you know what you are doing.
  */
-#define TASK_SIZE	0x7fff8000UL
+#define TASK_SIZE	0x80000000UL
 #endif
 
 #define STACK_TOP_MAX	TASK_SIZE
diff --git a/arch/mips/include/asm/stackframe.h b/arch/mips/include/asm/stackframe.h
index a71da576883c..eebf39549606 100644
--- a/arch/mips/include/asm/stackframe.h
+++ b/arch/mips/include/asm/stackframe.h
@@ -289,7 +289,7 @@
 		.set	reorder
 		.set	noat
 		mfc0	a0, CP0_STATUS
-		li	v1, 0xff00
+		li	v1, ST0_CU1 | ST0_IM
 		ori	a0, STATMASK
 		xori	a0, STATMASK
 		mtc0	a0, CP0_STATUS
@@ -330,7 +330,7 @@
 		ori	a0, STATMASK
 		xori	a0, STATMASK
 		mtc0	a0, CP0_STATUS
-		li	v1, 0xff00
+		li	v1, ST0_CU1 | ST0_FR | ST0_IM
 		and	a0, v1
 		LONG_L	v0, PT_STATUS(sp)
 		nor	v1, $0, v1
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
index 6499d93ae68d..47bc45a67e9b 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -101,10 +101,8 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	/* O32 ABI syscall() - Either 64-bit with O32 or 32-bit */
 	if ((config_enabled(CONFIG_32BIT) ||
 	    test_tsk_thread_flag(task, TIF_32BIT_REGS)) &&
-	    (regs->regs[2] == __NR_syscall)) {
+	    (regs->regs[2] == __NR_syscall))
 		i++;
-		n++;
-	}
 
 	while (n--)
 		ret |= mips_get_syscall_arg(args++, task, regs, i++);
diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h
index 90f03a7da665..3129795de940 100644
--- a/arch/mips/include/uapi/asm/unistd.h
+++ b/arch/mips/include/uapi/asm/unistd.h
@@ -380,16 +380,17 @@
 #define __NR_userfaultfd		(__NR_Linux + 357)
 #define __NR_membarrier			(__NR_Linux + 358)
 #define __NR_mlock2			(__NR_Linux + 359)
+#define __NR_copy_file_range		(__NR_Linux + 360)
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		359
+#define __NR_Linux_syscalls		360
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		359
+#define __NR_O32_Linux_syscalls		360
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -717,16 +718,17 @@
 #define __NR_userfaultfd		(__NR_Linux + 317)
 #define __NR_membarrier			(__NR_Linux + 318)
 #define __NR_mlock2			(__NR_Linux + 319)
+#define __NR_copy_file_range		(__NR_Linux + 320)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		319
+#define __NR_Linux_syscalls		320
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		319
+#define __NR_64_Linux_syscalls		320
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -1058,15 +1060,16 @@
 #define __NR_userfaultfd		(__NR_Linux + 321)
 #define __NR_membarrier			(__NR_Linux + 322)
 #define __NR_mlock2			(__NR_Linux + 323)
+#define __NR_copy_file_range		(__NR_Linux + 324)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		323
+#define __NR_Linux_syscalls		324
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		323
+#define __NR_N32_Linux_syscalls		324
 
 #endif /* _UAPI_ASM_UNISTD_H */
diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c
index 1188e00bb120..1b992c6e3d8e 100644
--- a/arch/mips/kernel/binfmt_elfn32.c
+++ b/arch/mips/kernel/binfmt_elfn32.c
@@ -35,7 +35,7 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
 	int __res = 1;							\
 	struct elfhdr *__h = (hdr);					\
 									\
-	if (__h->e_machine != EM_MIPS)					\
+	if (!mips_elf_check_machine(__h))				\
 		__res = 0;						\
 	if (__h->e_ident[EI_CLASS] != ELFCLASS32)			\
 		__res = 0;						\
diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c
index 928767858b86..abd3affe5fb3 100644
--- a/arch/mips/kernel/binfmt_elfo32.c
+++ b/arch/mips/kernel/binfmt_elfo32.c
@@ -47,7 +47,7 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
 	int __res = 1;							\
 	struct elfhdr *__h = (hdr);					\
 									\
-	if (__h->e_machine != EM_MIPS)					\
+	if (!mips_elf_check_machine(__h))				\
 		__res = 0;						\
 	if (__h->e_ident[EI_CLASS] != ELFCLASS32)			\
 		__res = 0;						\
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index f2975d4d1e44..eddd5fd6fdfa 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -65,12 +65,10 @@ void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp)
 	status = regs->cp0_status & ~(ST0_CU0|ST0_CU1|ST0_FR|KU_MASK);
 	status |= KU_USER;
 	regs->cp0_status = status;
+	lose_fpu(0);
+	clear_thread_flag(TIF_MSA_CTX_LIVE);
 	clear_used_math();
-	clear_fpu_owner();
 	init_dsp();
-	clear_thread_flag(TIF_USEDMSA);
-	clear_thread_flag(TIF_MSA_CTX_LIVE);
-	disable_msa();
 	regs->cp0_epc = pc;
 	regs->regs[29] = sp;
 }
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 2d23c834ba96..a56317444bda 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -595,3 +595,4 @@ EXPORT(sys_call_table)
 	PTR	sys_userfaultfd
 	PTR	sys_membarrier
 	PTR	sys_mlock2
+	PTR	sys_copy_file_range		/* 4360 */
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index deac63315d0e..2b2dc14610d0 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -433,4 +433,5 @@ EXPORT(sys_call_table)
 	PTR	sys_userfaultfd
 	PTR	sys_membarrier
 	PTR	sys_mlock2
+	PTR	sys_copy_file_range		/* 5320 */
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 5a69eb48d0a8..2bf5c8593d91 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -423,4 +423,5 @@ EXPORT(sysn32_call_table)
 	PTR	sys_userfaultfd
 	PTR	sys_membarrier
 	PTR	sys_mlock2
+	PTR	sys_copy_file_range
 	.size	sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index e4b6d7c97822..c5b759e584c7 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -578,4 +578,5 @@ EXPORT(sys32_call_table)
 	PTR	sys_userfaultfd
 	PTR	sys_membarrier
 	PTR	sys_mlock2
+	PTR	sys_copy_file_range		/* 4360 */
 	.size	sys32_call_table,.-sys32_call_table
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 569a7d5242dd..5fdaf8bdcd2e 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -782,6 +782,7 @@ static inline void prefill_possible_map(void) {}
 void __init setup_arch(char **cmdline_p)
 {
 	cpu_probe();
+	mips_cm_probe();
 	prom_init();
 
 	setup_early_fdc_console();
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index bafcb7ad5c85..ae790c575d4f 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -663,7 +663,7 @@ static int simulate_rdhwr_normal(struct pt_regs *regs, unsigned int opcode)
 	return -1;
 }
 
-static int simulate_rdhwr_mm(struct pt_regs *regs, unsigned short opcode)
+static int simulate_rdhwr_mm(struct pt_regs *regs, unsigned int opcode)
 {
 	if ((opcode & MM_POOL32A_FUNC) == MM_RDHWR) {
 		int rd = (opcode & MM_RS) >> 16;
@@ -1119,11 +1119,12 @@ no_r2_instr:
 	if (get_isa16_mode(regs->cp0_epc)) {
 		unsigned short mmop[2] = { 0 };
 
-		if (unlikely(get_user(mmop[0], epc) < 0))
+		if (unlikely(get_user(mmop[0], (u16 __user *)epc + 0) < 0))
 			status = SIGSEGV;
-		if (unlikely(get_user(mmop[1], epc) < 0))
+		if (unlikely(get_user(mmop[1], (u16 __user *)epc + 1) < 0))
 			status = SIGSEGV;
-		opcode = (mmop[0] << 16) | mmop[1];
+		opcode = mmop[0];
+		opcode = (opcode << 16) | mmop[1];
 
 		if (status < 0)
 			status = simulate_rdhwr_mm(regs, opcode);
@@ -1369,26 +1370,12 @@ asmlinkage void do_cpu(struct pt_regs *regs)
 		if (unlikely(compute_return_epc(regs) < 0))
 			break;
 
-		if (get_isa16_mode(regs->cp0_epc)) {
-			unsigned short mmop[2] = { 0 };
-
-			if (unlikely(get_user(mmop[0], epc) < 0))
-				status = SIGSEGV;
-			if (unlikely(get_user(mmop[1], epc) < 0))
-				status = SIGSEGV;
-			opcode = (mmop[0] << 16) | mmop[1];
-
-			if (status < 0)
-				status = simulate_rdhwr_mm(regs, opcode);
-		} else {
+		if (!get_isa16_mode(regs->cp0_epc)) {
 			if (unlikely(get_user(opcode, epc) < 0))
 				status = SIGSEGV;
 
 			if (!cpu_has_llsc && status < 0)
 				status = simulate_llsc(regs, opcode);
-
-			if (status < 0)
-				status = simulate_rdhwr_normal(regs, opcode);
 		}
 
 		if (status < 0)
diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c
index 3bd0597d9c3d..249647578e58 100644
--- a/arch/mips/mm/sc-mips.c
+++ b/arch/mips/mm/sc-mips.c
@@ -181,10 +181,6 @@ static int __init mips_sc_probe_cm3(void)
 	return 1;
 }
 
-void __weak platform_early_l2_init(void)
-{
-}
-
 static inline int __init mips_sc_probe(void)
 {
 	struct cpuinfo_mips *c = &current_cpu_data;
@@ -194,12 +190,6 @@ static inline int __init mips_sc_probe(void)
 	/* Mark as not present until probe completed */
 	c->scache.flags |= MIPS_CACHE_NOT_PRESENT;
 
-	/*
-	 * Do we need some platform specific probing before
-	 * we configure L2?
-	 */
-	platform_early_l2_init();
-
 	if (mips_cm_revision() >= CM_REV_CM3)
 		return mips_sc_probe_cm3();
 
diff --git a/arch/mips/mti-malta/malta-init.c b/arch/mips/mti-malta/malta-init.c
index 571148c5fd0b..dc2c5214809d 100644
--- a/arch/mips/mti-malta/malta-init.c
+++ b/arch/mips/mti-malta/malta-init.c
@@ -293,7 +293,6 @@ mips_pci_controller:
 	console_config();
 #endif
 	/* Early detection of CMP support */
-	mips_cm_probe();
 	mips_cpc_probe();
 
 	if (!register_cps_smp_ops())
@@ -304,10 +303,3 @@ mips_pci_controller:
 		return;
 	register_up_smp_ops();
 }
-
-void platform_early_l2_init(void)
-{
-	/* L2 configuration lives in the CM3 */
-	if (mips_cm_revision() >= CM_REV_CM3)
-		mips_cm_probe();
-}
diff --git a/arch/mips/pci/pci-mt7620.c b/arch/mips/pci/pci-mt7620.c
index a009ee458934..1ae932c2d78b 100644
--- a/arch/mips/pci/pci-mt7620.c
+++ b/arch/mips/pci/pci-mt7620.c
@@ -297,12 +297,12 @@ static int mt7620_pci_probe(struct platform_device *pdev)
 		return PTR_ERR(rstpcie0);
 
 	bridge_base = devm_ioremap_resource(&pdev->dev, bridge_res);
-	if (!bridge_base)
-		return -ENOMEM;
+	if (IS_ERR(bridge_base))
+		return PTR_ERR(bridge_base);
 
 	pcie_base = devm_ioremap_resource(&pdev->dev, pcie_res);
-	if (!pcie_base)
-		return -ENOMEM;
+	if (IS_ERR(pcie_base))
+		return PTR_ERR(pcie_base);
 
 	iomem_resource.start = 0;
 	iomem_resource.end = ~0;
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 06f17e778c27..8d1c8162f0c1 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -50,7 +50,9 @@
  * set of bits not changed in pmd_modify.
  */
 #define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \
-			 _PAGE_ACCESSED | _PAGE_THP_HUGE)
+			 _PAGE_ACCESSED | _PAGE_THP_HUGE | _PAGE_PTE | \
+			 _PAGE_SOFT_DIRTY)
+
 
 #ifdef CONFIG_PPC_64K_PAGES
 #include <asm/book3s/64/hash-64k.h>
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 8204b0c393aa..8d1c41d28318 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -223,7 +223,6 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd)
 #define pmd_pfn(pmd)		pte_pfn(pmd_pte(pmd))
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
-#define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
 #define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 271fefbbe521..9d08d8cbed1a 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -38,8 +38,7 @@
 
 #define KVM_MAX_VCPUS		NR_CPUS
 #define KVM_MAX_VCORES		NR_CPUS
-#define KVM_USER_MEM_SLOTS 32
-#define KVM_MEM_SLOTS_NUM KVM_USER_MEM_SLOTS
+#define KVM_USER_MEM_SLOTS	512
 
 #ifdef CONFIG_KVM_MMIO
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 5654ece02c0d..3fa9df70aa20 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -383,3 +383,4 @@ SYSCALL(ni_syscall)
 SYSCALL(ni_syscall)
 SYSCALL(ni_syscall)
 SYSCALL(mlock2)
+SYSCALL(copy_file_range)
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index 6a5ace5fa0c8..1f2594d45605 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -12,7 +12,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define NR_syscalls		379
+#define NR_syscalls		380
 
 #define __NR__exit __NR_exit
 
diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h
index 12a05652377a..940290d45b08 100644
--- a/arch/powerpc/include/uapi/asm/unistd.h
+++ b/arch/powerpc/include/uapi/asm/unistd.h
@@ -389,5 +389,6 @@
 #define __NR_userfaultfd	364
 #define __NR_membarrier		365
 #define __NR_mlock2		378
+#define __NR_copy_file_range	379
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 8654cb166c19..ca9e5371930e 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -883,32 +883,29 @@ void eeh_pe_restore_bars(struct eeh_pe *pe)
 const char *eeh_pe_loc_get(struct eeh_pe *pe)
 {
 	struct pci_bus *bus = eeh_pe_bus_get(pe);
-	struct device_node *dn = pci_bus_to_OF_node(bus);
+	struct device_node *dn;
 	const char *loc = NULL;
 
-	if (!dn)
-		goto out;
+	while (bus) {
+		dn = pci_bus_to_OF_node(bus);
+		if (!dn) {
+			bus = bus->parent;
+			continue;
+		}
 
-	/* PHB PE or root PE ? */
-	if (pci_is_root_bus(bus)) {
-		loc = of_get_property(dn, "ibm,loc-code", NULL);
-		if (!loc)
+		if (pci_is_root_bus(bus))
 			loc = of_get_property(dn, "ibm,io-base-loc-code", NULL);
+		else
+			loc = of_get_property(dn, "ibm,slot-location-code",
+					      NULL);
+
 		if (loc)
-			goto out;
+			return loc;
 
-		/* Check the root port */
-		dn = dn->child;
-		if (!dn)
-			goto out;
+		bus = bus->parent;
 	}
 
-	loc = of_get_property(dn, "ibm,loc-code", NULL);
-	if (!loc)
-		loc = of_get_property(dn, "ibm,slot-location-code", NULL);
-
-out:
-	return loc ? loc : "N/A";
+	return "N/A";
 }
 
 /**
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index db475d41b57a..f28754c497e5 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -701,31 +701,3 @@ _GLOBAL(kexec_sequence)
 	li	r5,0
 	blr	/* image->start(physid, image->start, 0); */
 #endif /* CONFIG_KEXEC */
-
-#ifdef CONFIG_MODULES
-#if defined(_CALL_ELF) && _CALL_ELF == 2
-
-#ifdef CONFIG_MODVERSIONS
-.weak __crc_TOC.
-.section "___kcrctab+TOC.","a"
-.globl __kcrctab_TOC.
-__kcrctab_TOC.:
-	.llong	__crc_TOC.
-#endif
-
-/*
- * Export a fake .TOC. since both modpost and depmod will complain otherwise.
- * Both modpost and depmod strip the leading . so we do the same here.
- */
-.section "__ksymtab_strings","a"
-__kstrtab_TOC.:
-	.asciz "TOC."
-
-.section "___ksymtab+TOC.","a"
-/* This symbol name is important: it's used by modpost to find exported syms */
-.globl __ksymtab_TOC.
-__ksymtab_TOC.:
-	.llong 0 /* .value */
-	.llong __kstrtab_TOC.
-#endif /* ELFv2 */
-#endif /* MODULES */
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 59663af9315f..ac64ffdb52c8 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -326,7 +326,10 @@ static void dedotify_versions(struct modversion_info *vers,
 		}
 }
 
-/* Undefined symbols which refer to .funcname, hack to funcname (or .TOC.) */
+/*
+ * Undefined symbols which refer to .funcname, hack to funcname. Make .TOC.
+ * seem to be defined (value set later).
+ */
 static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab)
 {
 	unsigned int i;
@@ -334,8 +337,11 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab)
 	for (i = 1; i < numsyms; i++) {
 		if (syms[i].st_shndx == SHN_UNDEF) {
 			char *name = strtab + syms[i].st_name;
-			if (name[0] == '.')
+			if (name[0] == '.') {
+				if (strcmp(name+1, "TOC.") == 0)
+					syms[i].st_shndx = SHN_ABS;
 				memmove(name, name+1, strlen(name));
+			}
 		}
 	}
 }
@@ -351,7 +357,7 @@ static Elf64_Sym *find_dot_toc(Elf64_Shdr *sechdrs,
 	numsyms = sechdrs[symindex].sh_size / sizeof(Elf64_Sym);
 
 	for (i = 1; i < numsyms; i++) {
-		if (syms[i].st_shndx == SHN_UNDEF
+		if (syms[i].st_shndx == SHN_ABS
 		    && strcmp(strtab + syms[i].st_name, "TOC.") == 0)
 			return &syms[i];
 	}
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index 774a253ca4e1..9bf7031a67ff 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -377,15 +377,12 @@ no_seg_found:
 
 static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb)
 {
-	struct kvmppc_vcpu_book3s *vcpu_book3s;
 	u64 esid, esid_1t;
 	int slb_nr;
 	struct kvmppc_slb *slbe;
 
 	dprintk("KVM MMU: slbmte(0x%llx, 0x%llx)\n", rs, rb);
 
-	vcpu_book3s = to_book3s(vcpu);
-
 	esid = GET_ESID(rb);
 	esid_1t = GET_ESID_1T(rb);
 	slb_nr = rb & 0xfff;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index cff207b72c46..baeddb06811d 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -833,6 +833,24 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	vcpu->stat.sum_exits++;
 
+	/*
+	 * This can happen if an interrupt occurs in the last stages
+	 * of guest entry or the first stages of guest exit (i.e. after
+	 * setting paca->kvm_hstate.in_guest to KVM_GUEST_MODE_GUEST_HV
+	 * and before setting it to KVM_GUEST_MODE_HOST_HV).
+	 * That can happen due to a bug, or due to a machine check
+	 * occurring at just the wrong time.
+	 */
+	if (vcpu->arch.shregs.msr & MSR_HV) {
+		printk(KERN_EMERG "KVM trap in HV mode!\n");
+		printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n",
+			vcpu->arch.trap, kvmppc_get_pc(vcpu),
+			vcpu->arch.shregs.msr);
+		kvmppc_dump_regs(vcpu);
+		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		run->hw.hardware_exit_reason = vcpu->arch.trap;
+		return RESUME_HOST;
+	}
 	run->exit_reason = KVM_EXIT_UNKNOWN;
 	run->ready_for_interrupt_injection = 1;
 	switch (vcpu->arch.trap) {
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 3c6badcd53ef..6ee26de9a1de 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -2153,7 +2153,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
 	/* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */
 2:	rlwimi	r5, r4, 5, DAWRX_DR | DAWRX_DW
-	rlwimi	r5, r4, 1, DAWRX_WT
+	rlwimi	r5, r4, 2, DAWRX_WT
 	clrrdi	r4, r4, 3
 	std	r4, VCPU_DAWR(r3)
 	std	r5, VCPU_DAWRX(r3)
@@ -2404,6 +2404,8 @@ machine_check_realmode:
 	 * guest as machine check causing guest to crash.
 	 */
 	ld	r11, VCPU_MSR(r9)
+	rldicl.	r0, r11, 64-MSR_HV_LG, 63 /* check if it happened in HV mode */
+	bne	mc_cont			/* if so, exit to host */
 	andi.	r10, r11, MSR_RI	/* check for unrecoverable exception */
 	beq	1f			/* Deliver a machine check to guest */
 	ld	r10, VCPU_PC(r9)
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 6fd2405c7f4a..a3b182dcb823 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -919,21 +919,17 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 				r = -ENXIO;
 				break;
 			}
-			vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval;
+			val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0];
 			break;
 		case KVM_REG_PPC_VSCR:
 			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
 				r = -ENXIO;
 				break;
 			}
-			vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val);
+			val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]);
 			break;
 		case KVM_REG_PPC_VRSAVE:
-			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
-				r = -ENXIO;
-				break;
-			}
-			vcpu->arch.vrsave = set_reg_val(reg->id, val);
+			val = get_reg_val(reg->id, vcpu->arch.vrsave);
 			break;
 #endif /* CONFIG_ALTIVEC */
 		default:
@@ -974,17 +970,21 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 				r = -ENXIO;
 				break;
 			}
-			val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0];
+			vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval;
 			break;
 		case KVM_REG_PPC_VSCR:
 			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
 				r = -ENXIO;
 				break;
 			}
-			val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]);
+			vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val);
 			break;
 		case KVM_REG_PPC_VRSAVE:
-			val = get_reg_val(reg->id, vcpu->arch.vrsave);
+			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
+				r = -ENXIO;
+				break;
+			}
+			vcpu->arch.vrsave = set_reg_val(reg->id, val);
 			break;
 #endif /* CONFIG_ALTIVEC */
 		default:
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 22d94c3e6fc4..d0f0a514b04e 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -560,12 +560,12 @@ subsys_initcall(add_system_ram_resources);
  */
 int devmem_is_allowed(unsigned long pfn)
 {
+	if (page_is_rtas_user_buf(pfn))
+		return 1;
 	if (iomem_is_exclusive(PFN_PHYS(pfn)))
 		return 0;
 	if (!page_is_ram(pfn))
 		return 1;
-	if (page_is_rtas_user_buf(pfn))
-		return 1;
 	return 0;
 }
 #endif /* CONFIG_STRICT_DEVMEM */
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index 7d5e295255b7..9958ba8bf0d2 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -816,7 +816,7 @@ static struct power_pmu power8_pmu = {
 	.get_constraint		= power8_get_constraint,
 	.get_alternatives	= power8_get_alternatives,
 	.disable_pmc		= power8_disable_pmc,
-	.flags			= PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_ARCH_207S,
+	.flags			= PPMU_HAS_SIER | PPMU_ARCH_207S,
 	.n_generic		= ARRAY_SIZE(power8_generic_events),
 	.generic_events		= power8_generic_events,
 	.cache_events		= &power8_cache_events,
diff --git a/arch/s390/include/asm/irqflags.h b/arch/s390/include/asm/irqflags.h
index 16aa0c779e07..595a275c36f8 100644
--- a/arch/s390/include/asm/irqflags.h
+++ b/arch/s390/include/asm/irqflags.h
@@ -8,6 +8,8 @@
 
 #include <linux/types.h>
 
+#define ARCH_IRQ_ENABLED	(3UL << (BITS_PER_LONG - 8))
+
 /* store then OR system mask. */
 #define __arch_local_irq_stosm(__or)					\
 ({									\
@@ -54,14 +56,17 @@ static inline notrace void arch_local_irq_enable(void)
 	__arch_local_irq_stosm(0x03);
 }
 
+/* This only restores external and I/O interrupt state */
 static inline notrace void arch_local_irq_restore(unsigned long flags)
 {
-	__arch_local_irq_ssm(flags);
+	/* only disabled->disabled and disabled->enabled is valid */
+	if (flags & ARCH_IRQ_ENABLED)
+		arch_local_irq_enable();
 }
 
 static inline notrace bool arch_irqs_disabled_flags(unsigned long flags)
 {
-	return !(flags & (3UL << (BITS_PER_LONG - 8)));
+	return !(flags & ARCH_IRQ_ENABLED);
 }
 
 static inline notrace bool arch_irqs_disabled(void)
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 6742414dbd6f..8959ebb6d2c9 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -546,7 +546,6 @@ struct kvm_vcpu_arch {
 	struct kvm_s390_sie_block *sie_block;
 	unsigned int      host_acrs[NUM_ACRS];
 	struct fpu	  host_fpregs;
-	struct fpu	  guest_fpregs;
 	struct kvm_s390_local_interrupt local_int;
 	struct hrtimer    ckc_timer;
 	struct kvm_s390_pgm_info pgm;
diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
index 1a9a98de5bde..69aa18be61af 100644
--- a/arch/s390/include/asm/pci_io.h
+++ b/arch/s390/include/asm/pci_io.h
@@ -8,10 +8,13 @@
 #include <asm/pci_insn.h>
 
 /* I/O Map */
-#define ZPCI_IOMAP_MAX_ENTRIES		0x7fff
-#define ZPCI_IOMAP_ADDR_BASE		0x8000000000000000ULL
-#define ZPCI_IOMAP_ADDR_IDX_MASK	0x7fff000000000000ULL
-#define ZPCI_IOMAP_ADDR_OFF_MASK	0x0000ffffffffffffULL
+#define ZPCI_IOMAP_SHIFT		48
+#define ZPCI_IOMAP_ADDR_BASE		0x8000000000000000UL
+#define ZPCI_IOMAP_ADDR_OFF_MASK	((1UL << ZPCI_IOMAP_SHIFT) - 1)
+#define ZPCI_IOMAP_MAX_ENTRIES							\
+	((ULONG_MAX - ZPCI_IOMAP_ADDR_BASE + 1) / (1UL << ZPCI_IOMAP_SHIFT))
+#define ZPCI_IOMAP_ADDR_IDX_MASK						\
+	(~ZPCI_IOMAP_ADDR_OFF_MASK - ZPCI_IOMAP_ADDR_BASE)
 
 struct zpci_iomap_entry {
 	u32 fh;
@@ -21,8 +24,9 @@ struct zpci_iomap_entry {
 
 extern struct zpci_iomap_entry *zpci_iomap_start;
 
+#define ZPCI_ADDR(idx) (ZPCI_IOMAP_ADDR_BASE | ((u64) idx << ZPCI_IOMAP_SHIFT))
 #define ZPCI_IDX(addr)								\
-	(((__force u64) addr & ZPCI_IOMAP_ADDR_IDX_MASK) >> 48)
+	(((__force u64) addr & ZPCI_IOMAP_ADDR_IDX_MASK) >> ZPCI_IOMAP_SHIFT)
 #define ZPCI_OFFSET(addr)							\
 	((__force u64) addr & ZPCI_IOMAP_ADDR_OFF_MASK)
 
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index f16debf6a612..1c4fe129486d 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -166,14 +166,14 @@ extern __vector128 init_task_fpu_regs[__NUM_VXRS];
  */
 #define start_thread(regs, new_psw, new_stackp) do {			\
 	regs->psw.mask	= PSW_USER_BITS | PSW_MASK_EA | PSW_MASK_BA;	\
-	regs->psw.addr	= new_psw | PSW_ADDR_AMODE;			\
+	regs->psw.addr	= new_psw;					\
 	regs->gprs[15]	= new_stackp;					\
 	execve_tail();							\
 } while (0)
 
 #define start_thread31(regs, new_psw, new_stackp) do {			\
 	regs->psw.mask	= PSW_USER_BITS | PSW_MASK_BA;			\
-	regs->psw.addr	= new_psw | PSW_ADDR_AMODE;			\
+	regs->psw.addr	= new_psw;					\
 	regs->gprs[15]	= new_stackp;					\
 	crst_table_downgrade(current->mm, 1UL << 31);			\
 	execve_tail();							\
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index f00cd35c8ac4..99bc456cc26a 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -149,7 +149,7 @@ static inline int test_pt_regs_flag(struct pt_regs *regs, int flag)
 #define arch_has_block_step()	(1)
 
 #define user_mode(regs) (((regs)->psw.mask & PSW_MASK_PSTATE) != 0)
-#define instruction_pointer(regs) ((regs)->psw.addr & PSW_ADDR_INSN)
+#define instruction_pointer(regs) ((regs)->psw.addr)
 #define user_stack_pointer(regs)((regs)->gprs[15])
 #define profile_pc(regs) instruction_pointer(regs)
 
@@ -161,7 +161,7 @@ static inline long regs_return_value(struct pt_regs *regs)
 static inline void instruction_pointer_set(struct pt_regs *regs,
 					   unsigned long val)
 {
-	regs->psw.addr = val | PSW_ADDR_AMODE;
+	regs->psw.addr = val;
 }
 
 int regs_query_register_offset(const char *name);
@@ -171,7 +171,7 @@ unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n);
 
 static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
 {
-	return regs->gprs[15] & PSW_ADDR_INSN;
+	return regs->gprs[15];
 }
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h
index 34ec202472c6..ab3aa6875a59 100644
--- a/arch/s390/include/uapi/asm/unistd.h
+++ b/arch/s390/include/uapi/asm/unistd.h
@@ -310,7 +310,8 @@
 #define __NR_recvmsg		372
 #define __NR_shutdown		373
 #define __NR_mlock2		374
-#define NR_syscalls 375
+#define __NR_copy_file_range	375
+#define NR_syscalls 376
 
 /* 
  * There are some system calls that are not present on 64 bit, some
diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c
index fac4eeddef91..ae2cda5eee5a 100644
--- a/arch/s390/kernel/compat_wrapper.c
+++ b/arch/s390/kernel/compat_wrapper.c
@@ -177,3 +177,4 @@ COMPAT_SYSCALL_WRAP3(getsockname, int, fd, struct sockaddr __user *, usockaddr,
 COMPAT_SYSCALL_WRAP3(getpeername, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len);
 COMPAT_SYSCALL_WRAP6(sendto, int, fd, void __user *, buff, size_t, len, unsigned int, flags, struct sockaddr __user *, addr, int, addr_len);
 COMPAT_SYSCALL_WRAP3(mlock2, unsigned long, start, size_t, len, int, flags);
+COMPAT_SYSCALL_WRAP6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags);
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index a92b39fd0e63..3986c9f62191 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -59,8 +59,6 @@ struct save_area * __init save_area_alloc(bool is_boot_cpu)
 	struct save_area *sa;
 
 	sa = (void *) memblock_alloc(sizeof(*sa), 8);
-	if (!sa)
-		return NULL;
 	if (is_boot_cpu)
 		list_add(&sa->list, &dump_save_areas);
 	else
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 6fca0e46464e..c890a5589e59 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -1470,7 +1470,7 @@ debug_dflt_header_fn(debug_info_t * id, struct debug_view *view,
 		except_str = "*";
 	else
 		except_str = "-";
-	caller = ((unsigned long) entry->caller) & PSW_ADDR_INSN;
+	caller = (unsigned long) entry->caller;
 	rc += sprintf(out_buf, "%02i %011lld:%06lu %1u %1s %02i %p  ",
 		      area, (long long)time_spec.tv_sec,
 		      time_spec.tv_nsec / 1000, level, except_str,
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index dc8e20473484..02bd02ff648b 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -34,22 +34,21 @@ __show_trace(unsigned long sp, unsigned long low, unsigned long high)
 	unsigned long addr;
 
 	while (1) {
-		sp = sp & PSW_ADDR_INSN;
 		if (sp < low || sp > high - sizeof(*sf))
 			return sp;
 		sf = (struct stack_frame *) sp;
-		addr = sf->gprs[8] & PSW_ADDR_INSN;
+		addr = sf->gprs[8];
 		printk("([<%016lx>] %pSR)\n", addr, (void *)addr);
 		/* Follow the backchain. */
 		while (1) {
 			low = sp;
-			sp = sf->back_chain & PSW_ADDR_INSN;
+			sp = sf->back_chain;
 			if (!sp)
 				break;
 			if (sp <= low || sp > high - sizeof(*sf))
 				return sp;
 			sf = (struct stack_frame *) sp;
-			addr = sf->gprs[8] & PSW_ADDR_INSN;
+			addr = sf->gprs[8];
 			printk(" [<%016lx>] %pSR\n", addr, (void *)addr);
 		}
 		/* Zero backchain detected, check for interrupt frame. */
@@ -57,7 +56,7 @@ __show_trace(unsigned long sp, unsigned long low, unsigned long high)
 		if (sp <= low || sp > high - sizeof(*regs))
 			return sp;
 		regs = (struct pt_regs *) sp;
-		addr = regs->psw.addr & PSW_ADDR_INSN;
+		addr = regs->psw.addr;
 		printk(" [<%016lx>] %pSR\n", addr, (void *)addr);
 		low = sp;
 		sp = regs->gprs[15];
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 20a5caf6d981..c55576bbaa1f 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -252,14 +252,14 @@ static void early_pgm_check_handler(void)
 	unsigned long addr;
 
 	addr = S390_lowcore.program_old_psw.addr;
-	fixup = search_exception_tables(addr & PSW_ADDR_INSN);
+	fixup = search_exception_tables(addr);
 	if (!fixup)
 		disabled_wait(0);
 	/* Disable low address protection before storing into lowcore. */
 	__ctl_store(cr0, 0, 0);
 	cr0_new = cr0 & ~(1UL << 28);
 	__ctl_load(cr0_new, 0, 0);
-	S390_lowcore.program_old_psw.addr = extable_fixup(fixup)|PSW_ADDR_AMODE;
+	S390_lowcore.program_old_psw.addr = extable_fixup(fixup);
 	__ctl_load(cr0, 0, 0);
 }
 
@@ -268,9 +268,9 @@ static noinline __init void setup_lowcore_early(void)
 	psw_t psw;
 
 	psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA;
-	psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_ext_handler;
+	psw.addr = (unsigned long) s390_base_ext_handler;
 	S390_lowcore.external_new_psw = psw;
-	psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler;
+	psw.addr = (unsigned long) s390_base_pgm_handler;
 	S390_lowcore.program_new_psw = psw;
 	s390_base_pgm_handler_fn = early_pgm_check_handler;
 }
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index e0eaf11134b4..0f7bfeba6da6 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -203,7 +203,7 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip)
 		goto out;
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		goto out;
-	ip = (ip & PSW_ADDR_INSN) - MCOUNT_INSN_SIZE;
+	ip -= MCOUNT_INSN_SIZE;
 	trace.func = ip;
 	trace.depth = current->curr_ret_stack + 1;
 	/* Only trace if the calling function expects to. */
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 0a5a6b661b93..f20abdb5630a 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -2057,12 +2057,12 @@ void s390_reset_system(void)
 	/* Set new machine check handler */
 	S390_lowcore.mcck_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT;
 	S390_lowcore.mcck_new_psw.addr =
-		PSW_ADDR_AMODE | (unsigned long) s390_base_mcck_handler;
+		(unsigned long) s390_base_mcck_handler;
 
 	/* Set new program check handler */
 	S390_lowcore.program_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT;
 	S390_lowcore.program_new_psw.addr =
-		PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler;
+		(unsigned long) s390_base_pgm_handler;
 
 	/*
 	 * Clear subchannel ID and number to signal new kernel that no CCW or
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 389db56a2208..250f5972536a 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -226,7 +226,7 @@ static void enable_singlestep(struct kprobe_ctlblk *kcb,
 	__ctl_load(per_kprobe, 9, 11);
 	regs->psw.mask |= PSW_MASK_PER;
 	regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT);
-	regs->psw.addr = ip | PSW_ADDR_AMODE;
+	regs->psw.addr = ip;
 }
 NOKPROBE_SYMBOL(enable_singlestep);
 
@@ -238,7 +238,7 @@ static void disable_singlestep(struct kprobe_ctlblk *kcb,
 	__ctl_load(kcb->kprobe_saved_ctl, 9, 11);
 	regs->psw.mask &= ~PSW_MASK_PER;
 	regs->psw.mask |= kcb->kprobe_saved_imask;
-	regs->psw.addr = ip | PSW_ADDR_AMODE;
+	regs->psw.addr = ip;
 }
 NOKPROBE_SYMBOL(disable_singlestep);
 
@@ -310,7 +310,7 @@ static int kprobe_handler(struct pt_regs *regs)
 	 */
 	preempt_disable();
 	kcb = get_kprobe_ctlblk();
-	p = get_kprobe((void *)((regs->psw.addr & PSW_ADDR_INSN) - 2));
+	p = get_kprobe((void *)(regs->psw.addr - 2));
 
 	if (p) {
 		if (kprobe_running()) {
@@ -460,7 +460,7 @@ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 			break;
 	}
 
-	regs->psw.addr = orig_ret_address | PSW_ADDR_AMODE;
+	regs->psw.addr = orig_ret_address;
 
 	pop_kprobe(get_kprobe_ctlblk());
 	kretprobe_hash_unlock(current, &flags);
@@ -490,7 +490,7 @@ NOKPROBE_SYMBOL(trampoline_probe_handler);
 static void resume_execution(struct kprobe *p, struct pt_regs *regs)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long ip = regs->psw.addr & PSW_ADDR_INSN;
+	unsigned long ip = regs->psw.addr;
 	int fixup = probe_get_fixup_type(p->ainsn.insn);
 
 	/* Check if the kprobes location is an enabled ftrace caller */
@@ -605,9 +605,9 @@ static int kprobe_trap_handler(struct pt_regs *regs, int trapnr)
 		 * In case the user-specified fault handler returned
 		 * zero, try to fix up.
 		 */
-		entry = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN);
+		entry = search_exception_tables(regs->psw.addr);
 		if (entry) {
-			regs->psw.addr = extable_fixup(entry) | PSW_ADDR_AMODE;
+			regs->psw.addr = extable_fixup(entry);
 			return 1;
 		}
 
@@ -683,7 +683,7 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs));
 
 	/* setup return addr to the jprobe handler routine */
-	regs->psw.addr = (unsigned long) jp->entry | PSW_ADDR_AMODE;
+	regs->psw.addr = (unsigned long) jp->entry;
 	regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT);
 
 	/* r15 is the stack pointer */
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 61595c1f0a0f..cfcba2dd9bb5 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -74,7 +74,7 @@ static unsigned long guest_is_user_mode(struct pt_regs *regs)
 
 static unsigned long instruction_pointer_guest(struct pt_regs *regs)
 {
-	return sie_block(regs)->gpsw.addr & PSW_ADDR_INSN;
+	return sie_block(regs)->gpsw.addr;
 }
 
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
@@ -231,29 +231,27 @@ static unsigned long __store_trace(struct perf_callchain_entry *entry,
 	struct pt_regs *regs;
 
 	while (1) {
-		sp = sp & PSW_ADDR_INSN;
 		if (sp < low || sp > high - sizeof(*sf))
 			return sp;
 		sf = (struct stack_frame *) sp;
-		perf_callchain_store(entry, sf->gprs[8] & PSW_ADDR_INSN);
+		perf_callchain_store(entry, sf->gprs[8]);
 		/* Follow the backchain. */
 		while (1) {
 			low = sp;
-			sp = sf->back_chain & PSW_ADDR_INSN;
+			sp = sf->back_chain;
 			if (!sp)
 				break;
 			if (sp <= low || sp > high - sizeof(*sf))
 				return sp;
 			sf = (struct stack_frame *) sp;
-			perf_callchain_store(entry,
-					     sf->gprs[8] & PSW_ADDR_INSN);
+			perf_callchain_store(entry, sf->gprs[8]);
 		}
 		/* Zero backchain detected, check for interrupt frame. */
 		sp = (unsigned long) (sf + 1);
 		if (sp <= low || sp > high - sizeof(*regs))
 			return sp;
 		regs = (struct pt_regs *) sp;
-		perf_callchain_store(entry, sf->gprs[8] & PSW_ADDR_INSN);
+		perf_callchain_store(entry, sf->gprs[8]);
 		low = sp;
 		sp = regs->gprs[15];
 	}
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 114ee8b96f17..2bba7df4ac51 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -56,10 +56,10 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
 		return 0;
 	low = task_stack_page(tsk);
 	high = (struct stack_frame *) task_pt_regs(tsk);
-	sf = (struct stack_frame *) (tsk->thread.ksp & PSW_ADDR_INSN);
+	sf = (struct stack_frame *) tsk->thread.ksp;
 	if (sf <= low || sf > high)
 		return 0;
-	sf = (struct stack_frame *) (sf->back_chain & PSW_ADDR_INSN);
+	sf = (struct stack_frame *) sf->back_chain;
 	if (sf <= low || sf > high)
 		return 0;
 	return sf->gprs[8];
@@ -154,7 +154,7 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
 		memset(&frame->childregs, 0, sizeof(struct pt_regs));
 		frame->childregs.psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT |
 				PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
-		frame->childregs.psw.addr = PSW_ADDR_AMODE |
+		frame->childregs.psw.addr =
 				(unsigned long) kernel_thread_starter;
 		frame->childregs.gprs[9] = new_stackp; /* function */
 		frame->childregs.gprs[10] = arg;
@@ -220,14 +220,14 @@ unsigned long get_wchan(struct task_struct *p)
 		return 0;
 	low = task_stack_page(p);
 	high = (struct stack_frame *) task_pt_regs(p);
-	sf = (struct stack_frame *) (p->thread.ksp & PSW_ADDR_INSN);
+	sf = (struct stack_frame *) p->thread.ksp;
 	if (sf <= low || sf > high)
 		return 0;
 	for (count = 0; count < 16; count++) {
-		sf = (struct stack_frame *) (sf->back_chain & PSW_ADDR_INSN);
+		sf = (struct stack_frame *) sf->back_chain;
 		if (sf <= low || sf > high)
 			return 0;
-		return_address = sf->gprs[8] & PSW_ADDR_INSN;
+		return_address = sf->gprs[8];
 		if (!in_sched_functions(return_address))
 			return return_address;
 	}
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 01c37b36caf9..49b1c13bf6c9 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -84,7 +84,7 @@ void update_cr_regs(struct task_struct *task)
 		if (test_tsk_thread_flag(task, TIF_UPROBE_SINGLESTEP))
 			new.control |= PER_EVENT_IFETCH;
 		new.start = 0;
-		new.end = PSW_ADDR_INSN;
+		new.end = -1UL;
 	}
 
 	/* Take care of the PER enablement bit in the PSW. */
@@ -148,7 +148,7 @@ static inline unsigned long __peek_user_per(struct task_struct *child,
 	else if (addr == (addr_t) &dummy->cr11)
 		/* End address of the active per set. */
 		return test_thread_flag(TIF_SINGLE_STEP) ?
-			PSW_ADDR_INSN : child->thread.per_user.end;
+			-1UL : child->thread.per_user.end;
 	else if (addr == (addr_t) &dummy->bits)
 		/* Single-step bit. */
 		return test_thread_flag(TIF_SINGLE_STEP) ?
@@ -495,8 +495,6 @@ long arch_ptrace(struct task_struct *child, long request,
 		}
 		return 0;
 	default:
-		/* Removing high order bit from addr (only for 31 bit). */
-		addr &= PSW_ADDR_INSN;
 		return ptrace_request(child, request, addr, data);
 	}
 }
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index c6878fbbcf13..9220db5c996a 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -301,25 +301,21 @@ static void __init setup_lowcore(void)
 	BUILD_BUG_ON(sizeof(struct lowcore) != LC_PAGES * 4096);
 	lc = __alloc_bootmem_low(LC_PAGES * PAGE_SIZE, LC_PAGES * PAGE_SIZE, 0);
 	lc->restart_psw.mask = PSW_KERNEL_BITS;
-	lc->restart_psw.addr =
-		PSW_ADDR_AMODE | (unsigned long) restart_int_handler;
+	lc->restart_psw.addr = (unsigned long) restart_int_handler;
 	lc->external_new_psw.mask = PSW_KERNEL_BITS |
 		PSW_MASK_DAT | PSW_MASK_MCHECK;
-	lc->external_new_psw.addr =
-		PSW_ADDR_AMODE | (unsigned long) ext_int_handler;
+	lc->external_new_psw.addr = (unsigned long) ext_int_handler;
 	lc->svc_new_psw.mask = PSW_KERNEL_BITS |
 		PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
-	lc->svc_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) system_call;
+	lc->svc_new_psw.addr = (unsigned long) system_call;
 	lc->program_new_psw.mask = PSW_KERNEL_BITS |
 		PSW_MASK_DAT | PSW_MASK_MCHECK;
-	lc->program_new_psw.addr =
-		PSW_ADDR_AMODE | (unsigned long) pgm_check_handler;
+	lc->program_new_psw.addr = (unsigned long) pgm_check_handler;
 	lc->mcck_new_psw.mask = PSW_KERNEL_BITS;
-	lc->mcck_new_psw.addr =
-		PSW_ADDR_AMODE | (unsigned long) mcck_int_handler;
+	lc->mcck_new_psw.addr = (unsigned long) mcck_int_handler;
 	lc->io_new_psw.mask = PSW_KERNEL_BITS |
 		PSW_MASK_DAT | PSW_MASK_MCHECK;
-	lc->io_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) io_int_handler;
+	lc->io_new_psw.addr = (unsigned long) io_int_handler;
 	lc->clock_comparator = -1ULL;
 	lc->kernel_stack = ((unsigned long) &init_thread_union)
 		+ THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index 028cc46cb82a..d82562cf0a0e 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -331,13 +331,13 @@ static int setup_frame(int sig, struct k_sigaction *ka,
 	/* Set up to return from userspace.  If provided, use a stub
 	   already in userspace.  */
 	if (ka->sa.sa_flags & SA_RESTORER) {
-		restorer = (unsigned long) ka->sa.sa_restorer | PSW_ADDR_AMODE;
+		restorer = (unsigned long) ka->sa.sa_restorer;
 	} else {
 		/* Signal frame without vector registers are short ! */
 		__u16 __user *svc = (void __user *) frame + frame_size - 2;
 		if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, svc))
 			return -EFAULT;
-		restorer = (unsigned long) svc | PSW_ADDR_AMODE;
+		restorer = (unsigned long) svc;
 	}
 
 	/* Set up registers for signal handler */
@@ -347,7 +347,7 @@ static int setup_frame(int sig, struct k_sigaction *ka,
 	regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA |
 		(PSW_USER_BITS & PSW_MASK_ASC) |
 		(regs->psw.mask & ~PSW_MASK_ASC);
-	regs->psw.addr = (unsigned long) ka->sa.sa_handler | PSW_ADDR_AMODE;
+	regs->psw.addr = (unsigned long) ka->sa.sa_handler;
 
 	regs->gprs[2] = sig;
 	regs->gprs[3] = (unsigned long) &frame->sc;
@@ -394,13 +394,12 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 	/* Set up to return from userspace.  If provided, use a stub
 	   already in userspace.  */
 	if (ksig->ka.sa.sa_flags & SA_RESTORER) {
-		restorer = (unsigned long)
-			ksig->ka.sa.sa_restorer | PSW_ADDR_AMODE;
+		restorer = (unsigned long) ksig->ka.sa.sa_restorer;
 	} else {
 		__u16 __user *svc = &frame->svc_insn;
 		if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, svc))
 			return -EFAULT;
-		restorer = (unsigned long) svc | PSW_ADDR_AMODE;
+		restorer = (unsigned long) svc;
 	}
 
 	/* Create siginfo on the signal stack */
@@ -426,7 +425,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 	regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA |
 		(PSW_USER_BITS & PSW_MASK_ASC) |
 		(regs->psw.mask & ~PSW_MASK_ASC);
-	regs->psw.addr = (unsigned long) ksig->ka.sa.sa_handler | PSW_ADDR_AMODE;
+	regs->psw.addr = (unsigned long) ksig->ka.sa.sa_handler;
 
 	regs->gprs[2] = ksig->sig;
 	regs->gprs[3] = (unsigned long) &frame->info;
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index a13468b9a913..3c65a8eae34d 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -623,8 +623,6 @@ void __init smp_save_dump_cpus(void)
 		return;
 	/* Allocate a page as dumping area for the store status sigps */
 	page = memblock_alloc_base(PAGE_SIZE, PAGE_SIZE, 1UL << 31);
-	if (!page)
-		panic("could not allocate memory for save area\n");
 	/* Set multi-threading state to the previous system. */
 	pcpu_set_smt(sclp.mtid_prev);
 	boot_cpu_addr = stap();
diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
index 1785cd82253c..5acba3cb7220 100644
--- a/arch/s390/kernel/stacktrace.c
+++ b/arch/s390/kernel/stacktrace.c
@@ -21,12 +21,11 @@ static unsigned long save_context_stack(struct stack_trace *trace,
 	unsigned long addr;
 
 	while(1) {
-		sp &= PSW_ADDR_INSN;
 		if (sp < low || sp > high)
 			return sp;
 		sf = (struct stack_frame *)sp;
 		while(1) {
-			addr = sf->gprs[8] & PSW_ADDR_INSN;
+			addr = sf->gprs[8];
 			if (!trace->skip)
 				trace->entries[trace->nr_entries++] = addr;
 			else
@@ -34,7 +33,7 @@ static unsigned long save_context_stack(struct stack_trace *trace,
 			if (trace->nr_entries >= trace->max_entries)
 				return sp;
 			low = sp;
-			sp = sf->back_chain & PSW_ADDR_INSN;
+			sp = sf->back_chain;
 			if (!sp)
 				break;
 			if (sp <= low || sp > high - sizeof(*sf))
@@ -46,7 +45,7 @@ static unsigned long save_context_stack(struct stack_trace *trace,
 		if (sp <= low || sp > high - sizeof(*regs))
 			return sp;
 		regs = (struct pt_regs *)sp;
-		addr = regs->psw.addr & PSW_ADDR_INSN;
+		addr = regs->psw.addr;
 		if (savesched || !in_sched_functions(addr)) {
 			if (!trace->skip)
 				trace->entries[trace->nr_entries++] = addr;
@@ -65,7 +64,7 @@ void save_stack_trace(struct stack_trace *trace)
 	register unsigned long sp asm ("15");
 	unsigned long orig_sp, new_sp;
 
-	orig_sp = sp & PSW_ADDR_INSN;
+	orig_sp = sp;
 	new_sp = save_context_stack(trace, orig_sp,
 				    S390_lowcore.panic_stack - PAGE_SIZE,
 				    S390_lowcore.panic_stack, 1);
@@ -86,7 +85,7 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
 	unsigned long sp, low, high;
 
-	sp = tsk->thread.ksp & PSW_ADDR_INSN;
+	sp = tsk->thread.ksp;
 	low = (unsigned long) task_stack_page(tsk);
 	high = (unsigned long) task_pt_regs(tsk);
 	save_context_stack(trace, sp, low, high, 0);
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index 5378c3ea1b98..293d8b98fd52 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -383,3 +383,4 @@ SYSCALL(sys_recvfrom,compat_sys_recvfrom)
 SYSCALL(sys_recvmsg,compat_sys_recvmsg)
 SYSCALL(sys_shutdown,sys_shutdown)
 SYSCALL(sys_mlock2,compat_sys_mlock2)
+SYSCALL(sys_copy_file_range,compat_sys_copy_file_range) /* 375 */
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index d69d648759c9..017eb03daee2 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -32,8 +32,7 @@ static inline void __user *get_trap_ip(struct pt_regs *regs)
 		address = *(unsigned long *)(current->thread.trap_tdb + 24);
 	else
 		address = regs->psw.addr;
-	return (void __user *)
-		((address - (regs->int_code >> 16)) & PSW_ADDR_INSN);
+	return (void __user *) (address - (regs->int_code >> 16));
 }
 
 static inline void report_user_fault(struct pt_regs *regs, int signr)
@@ -46,7 +45,7 @@ static inline void report_user_fault(struct pt_regs *regs, int signr)
 		return;
 	printk("User process fault: interruption code %04x ilc:%d ",
 	       regs->int_code & 0xffff, regs->int_code >> 17);
-	print_vma_addr("in ", regs->psw.addr & PSW_ADDR_INSN);
+	print_vma_addr("in ", regs->psw.addr);
 	printk("\n");
 	show_regs(regs);
 }
@@ -69,13 +68,13 @@ void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str)
 		report_user_fault(regs, si_signo);
         } else {
                 const struct exception_table_entry *fixup;
-                fixup = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN);
+		fixup = search_exception_tables(regs->psw.addr);
                 if (fixup)
-			regs->psw.addr = extable_fixup(fixup) | PSW_ADDR_AMODE;
+			regs->psw.addr = extable_fixup(fixup);
 		else {
 			enum bug_trap_type btt;
 
-			btt = report_bug(regs->psw.addr & PSW_ADDR_INSN, regs);
+			btt = report_bug(regs->psw.addr, regs);
 			if (btt == BUG_TRAP_TYPE_WARN)
 				return;
 			die(regs, str);
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 5fce52cf0e57..5ea5af3c7db7 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -29,6 +29,7 @@ config KVM
 	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
 	select SRCU
+	select KVM_VFIO
 	---help---
 	  Support hosting paravirtualized guest machines using the SIE
 	  virtualization capability on the mainframe. This should work
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index b3b553469650..d42fa38c2429 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -7,7 +7,7 @@
 # as published by the Free Software Foundation.
 
 KVM := ../../../virt/kvm
-common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o  $(KVM)/async_pf.o $(KVM)/irqchip.o
+common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o  $(KVM)/async_pf.o $(KVM)/irqchip.o $(KVM)/vfio.o
 
 ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
 
diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c
index 47518a324d75..d697312ce9ee 100644
--- a/arch/s390/kvm/guestdbg.c
+++ b/arch/s390/kvm/guestdbg.c
@@ -116,7 +116,7 @@ static void enable_all_hw_wp(struct kvm_vcpu *vcpu)
 	if (*cr9 & PER_EVENT_STORE && *cr9 & PER_CONTROL_ALTERATION) {
 		*cr9 &= ~PER_CONTROL_ALTERATION;
 		*cr10 = 0;
-		*cr11 = PSW_ADDR_INSN;
+		*cr11 = -1UL;
 	} else {
 		*cr9 &= ~PER_CONTROL_ALTERATION;
 		*cr9 |= PER_EVENT_STORE;
@@ -159,7 +159,7 @@ void kvm_s390_patch_guest_per_regs(struct kvm_vcpu *vcpu)
 		vcpu->arch.sie_block->gcr[0] &= ~0x800ul;
 		vcpu->arch.sie_block->gcr[9] |= PER_EVENT_IFETCH;
 		vcpu->arch.sie_block->gcr[10] = 0;
-		vcpu->arch.sie_block->gcr[11] = PSW_ADDR_INSN;
+		vcpu->arch.sie_block->gcr[11] = -1UL;
 	}
 
 	if (guestdbg_hw_bp_enabled(vcpu)) {
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 835d60bedb54..4af21c771f9b 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1423,44 +1423,18 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-/*
- * Backs up the current FP/VX register save area on a particular
- * destination.  Used to switch between different register save
- * areas.
- */
-static inline void save_fpu_to(struct fpu *dst)
-{
-	dst->fpc = current->thread.fpu.fpc;
-	dst->regs = current->thread.fpu.regs;
-}
-
-/*
- * Switches the FP/VX register save area from which to lazy
- * restore register contents.
- */
-static inline void load_fpu_from(struct fpu *from)
-{
-	current->thread.fpu.fpc = from->fpc;
-	current->thread.fpu.regs = from->regs;
-}
-
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	/* Save host register state */
 	save_fpu_regs();
-	save_fpu_to(&vcpu->arch.host_fpregs);
-
-	if (test_kvm_facility(vcpu->kvm, 129)) {
-		current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
-		/*
-		 * Use the register save area in the SIE-control block
-		 * for register restore and save in kvm_arch_vcpu_put()
-		 */
-		current->thread.fpu.vxrs =
-			(__vector128 *)&vcpu->run->s.regs.vrs;
-	} else
-		load_fpu_from(&vcpu->arch.guest_fpregs);
+	vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc;
+	vcpu->arch.host_fpregs.regs = current->thread.fpu.regs;
 
+	/* Depending on MACHINE_HAS_VX, data stored to vrs either
+	 * has vector register or floating point register format.
+	 */
+	current->thread.fpu.regs = vcpu->run->s.regs.vrs;
+	current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
 	if (test_fp_ctl(current->thread.fpu.fpc))
 		/* User space provided an invalid FPC, let's clear it */
 		current->thread.fpu.fpc = 0;
@@ -1476,19 +1450,13 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 	gmap_disable(vcpu->arch.gmap);
 
+	/* Save guest register state */
 	save_fpu_regs();
+	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
 
-	if (test_kvm_facility(vcpu->kvm, 129))
-		/*
-		 * kvm_arch_vcpu_load() set up the register save area to
-		 * the &vcpu->run->s.regs.vrs and, thus, the vector registers
-		 * are already saved.  Only the floating-point control must be
-		 * copied.
-		 */
-		vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
-	else
-		save_fpu_to(&vcpu->arch.guest_fpregs);
-	load_fpu_from(&vcpu->arch.host_fpregs);
+	/* Restore host register state */
+	current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc;
+	current->thread.fpu.regs = vcpu->arch.host_fpregs.regs;
 
 	save_access_regs(vcpu->run->s.regs.acrs);
 	restore_access_regs(vcpu->arch.host_acrs);
@@ -1506,8 +1474,9 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
 	vcpu->arch.sie_block->gcr[0]  = 0xE0UL;
 	vcpu->arch.sie_block->gcr[14] = 0xC2000000UL;
-	vcpu->arch.guest_fpregs.fpc = 0;
-	asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc));
+	/* make sure the new fpc will be lazily loaded */
+	save_fpu_regs();
+	current->thread.fpu.fpc = 0;
 	vcpu->arch.sie_block->gbea = 1;
 	vcpu->arch.sie_block->pp = 0;
 	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
@@ -1648,17 +1617,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	vcpu->arch.local_int.wq = &vcpu->wq;
 	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
 
-	/*
-	 * Allocate a save area for floating-point registers.  If the vector
-	 * extension is available, register contents are saved in the SIE
-	 * control block.  The allocated save area is still required in
-	 * particular places, for example, in kvm_s390_vcpu_store_status().
-	 */
-	vcpu->arch.guest_fpregs.fprs = kzalloc(sizeof(freg_t) * __NUM_FPRS,
-					       GFP_KERNEL);
-	if (!vcpu->arch.guest_fpregs.fprs)
-		goto out_free_sie_block;
-
 	rc = kvm_vcpu_init(vcpu, kvm, id);
 	if (rc)
 		goto out_free_sie_block;
@@ -1879,19 +1837,27 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 
 int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
+	/* make sure the new values will be lazily loaded */
+	save_fpu_regs();
 	if (test_fp_ctl(fpu->fpc))
 		return -EINVAL;
-	memcpy(vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
-	vcpu->arch.guest_fpregs.fpc = fpu->fpc;
-	save_fpu_regs();
-	load_fpu_from(&vcpu->arch.guest_fpregs);
+	current->thread.fpu.fpc = fpu->fpc;
+	if (MACHINE_HAS_VX)
+		convert_fp_to_vx(current->thread.fpu.vxrs, (freg_t *)fpu->fprs);
+	else
+		memcpy(current->thread.fpu.fprs, &fpu->fprs, sizeof(fpu->fprs));
 	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	memcpy(&fpu->fprs, vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs));
-	fpu->fpc = vcpu->arch.guest_fpregs.fpc;
+	/* make sure we have the latest values */
+	save_fpu_regs();
+	if (MACHINE_HAS_VX)
+		convert_vx_to_fp((freg_t *)fpu->fprs, current->thread.fpu.vxrs);
+	else
+		memcpy(fpu->fprs, current->thread.fpu.fprs, sizeof(fpu->fprs));
+	fpu->fpc = current->thread.fpu.fpc;
 	return 0;
 }
 
@@ -2396,6 +2362,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
 {
 	unsigned char archmode = 1;
+	freg_t fprs[NUM_FPRS];
 	unsigned int px;
 	u64 clkcomp;
 	int rc;
@@ -2411,8 +2378,16 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
 		gpa = px;
 	} else
 		gpa -= __LC_FPREGS_SAVE_AREA;
-	rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
-			     vcpu->arch.guest_fpregs.fprs, 128);
+
+	/* manually convert vector registers if necessary */
+	if (MACHINE_HAS_VX) {
+		convert_vx_to_fp(fprs, current->thread.fpu.vxrs);
+		rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
+				     fprs, 128);
+	} else {
+		rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
+				     vcpu->run->s.regs.vrs, 128);
+	}
 	rc |= write_guest_abs(vcpu, gpa + __LC_GPREGS_SAVE_AREA,
 			      vcpu->run->s.regs.gprs, 128);
 	rc |= write_guest_abs(vcpu, gpa + __LC_PSW_SAVE_AREA,
@@ -2420,7 +2395,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
 	rc |= write_guest_abs(vcpu, gpa + __LC_PREFIX_SAVE_AREA,
 			      &px, 4);
 	rc |= write_guest_abs(vcpu, gpa + __LC_FP_CREG_SAVE_AREA,
-			      &vcpu->arch.guest_fpregs.fpc, 4);
+			      &vcpu->run->s.regs.fpc, 4);
 	rc |= write_guest_abs(vcpu, gpa + __LC_TOD_PROGREG_SAVE_AREA,
 			      &vcpu->arch.sie_block->todpr, 4);
 	rc |= write_guest_abs(vcpu, gpa + __LC_CPU_TIMER_SAVE_AREA,
@@ -2443,19 +2418,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 	 * it into the save area
 	 */
 	save_fpu_regs();
-	if (test_kvm_facility(vcpu->kvm, 129)) {
-		/*
-		 * If the vector extension is available, the vector registers
-		 * which overlaps with floating-point registers are saved in
-		 * the SIE-control block.  Hence, extract the floating-point
-		 * registers and the FPC value and store them in the
-		 * guest_fpregs structure.
-		 */
-		vcpu->arch.guest_fpregs.fpc = current->thread.fpu.fpc;
-		convert_vx_to_fp(vcpu->arch.guest_fpregs.fprs,
-				 current->thread.fpu.vxrs);
-	} else
-		save_fpu_to(&vcpu->arch.guest_fpregs);
+	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
 	save_access_regs(vcpu->run->s.regs.acrs);
 
 	return kvm_s390_store_status_unloaded(vcpu, addr);
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 1b903f6ad54a..791a4146052c 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -228,7 +228,7 @@ static inline void report_user_fault(struct pt_regs *regs, long signr)
 		return;
 	printk(KERN_ALERT "User process fault: interruption code %04x ilc:%d ",
 	       regs->int_code & 0xffff, regs->int_code >> 17);
-	print_vma_addr(KERN_CONT "in ", regs->psw.addr & PSW_ADDR_INSN);
+	print_vma_addr(KERN_CONT "in ", regs->psw.addr);
 	printk(KERN_CONT "\n");
 	printk(KERN_ALERT "failing address: %016lx TEID: %016lx\n",
 	       regs->int_parm_long & __FAIL_ADDR_MASK, regs->int_parm_long);
@@ -256,9 +256,9 @@ static noinline void do_no_context(struct pt_regs *regs)
 	const struct exception_table_entry *fixup;
 
 	/* Are we prepared to handle this kernel fault?  */
-	fixup = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN);
+	fixup = search_exception_tables(regs->psw.addr);
 	if (fixup) {
-		regs->psw.addr = extable_fixup(fixup) | PSW_ADDR_AMODE;
+		regs->psw.addr = extable_fixup(fixup);
 		return;
 	}
 
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index c722400c7697..73e290337092 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -98,7 +98,7 @@ void __init paging_init(void)
 	__ctl_load(S390_lowcore.kernel_asce, 1, 1);
 	__ctl_load(S390_lowcore.kernel_asce, 7, 7);
 	__ctl_load(S390_lowcore.kernel_asce, 13, 13);
-	arch_local_irq_restore(4UL << (BITS_PER_LONG - 8));
+	__arch_local_irq_stosm(0x04);
 
 	sparse_memory_present_with_active_regions(MAX_NUMNODES);
 	sparse_init();
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index ea01477b4aa6..45c4daa49930 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -169,12 +169,12 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 
 int s390_mmap_check(unsigned long addr, unsigned long len, unsigned long flags)
 {
-	if (is_compat_task() || (TASK_SIZE >= (1UL << 53)))
+	if (is_compat_task() || TASK_SIZE >= TASK_MAX_SIZE)
 		return 0;
 	if (!(flags & MAP_FIXED))
 		addr = 0;
 	if ((addr + len) >= TASK_SIZE)
-		return crst_table_upgrade(current->mm, 1UL << 53);
+		return crst_table_upgrade(current->mm, TASK_MAX_SIZE);
 	return 0;
 }
 
@@ -189,9 +189,9 @@ s390_get_unmapped_area(struct file *filp, unsigned long addr,
 	area = arch_get_unmapped_area(filp, addr, len, pgoff, flags);
 	if (!(area & ~PAGE_MASK))
 		return area;
-	if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) {
+	if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < TASK_MAX_SIZE) {
 		/* Upgrade the page table to 4 levels and retry. */
-		rc = crst_table_upgrade(mm, 1UL << 53);
+		rc = crst_table_upgrade(mm, TASK_MAX_SIZE);
 		if (rc)
 			return (unsigned long) rc;
 		area = arch_get_unmapped_area(filp, addr, len, pgoff, flags);
@@ -211,9 +211,9 @@ s390_get_unmapped_area_topdown(struct file *filp, const unsigned long addr,
 	area = arch_get_unmapped_area_topdown(filp, addr, len, pgoff, flags);
 	if (!(area & ~PAGE_MASK))
 		return area;
-	if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) {
+	if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < TASK_MAX_SIZE) {
 		/* Upgrade the page table to 4 levels and retry. */
-		rc = crst_table_upgrade(mm, 1UL << 53);
+		rc = crst_table_upgrade(mm, TASK_MAX_SIZE);
 		if (rc)
 			return (unsigned long) rc;
 		area = arch_get_unmapped_area_topdown(filp, addr, len,
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index a809fa8e6f8b..5109827883ac 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -55,7 +55,7 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long limit)
 	unsigned long entry;
 	int flush;
 
-	BUG_ON(limit > (1UL << 53));
+	BUG_ON(limit > TASK_MAX_SIZE);
 	flush = 0;
 repeat:
 	table = crst_table_alloc(mm);
diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c
index 43f32ce60aa3..2794845061c6 100644
--- a/arch/s390/numa/numa.c
+++ b/arch/s390/numa/numa.c
@@ -57,9 +57,7 @@ static __init pg_data_t *alloc_node_data(void)
 {
 	pg_data_t *res;
 
-	res = (pg_data_t *) memblock_alloc(sizeof(pg_data_t), 1);
-	if (!res)
-		panic("Could not allocate memory for node data!\n");
+	res = (pg_data_t *) memblock_alloc(sizeof(pg_data_t), 8);
 	memset(res, 0, sizeof(pg_data_t));
 	return res;
 }
@@ -162,7 +160,7 @@ static int __init numa_init_late(void)
 		register_one_node(nid);
 	return 0;
 }
-device_initcall(numa_init_late);
+arch_initcall(numa_init_late);
 
 static int __init parse_debug(char *parm)
 {
diff --git a/arch/s390/oprofile/backtrace.c b/arch/s390/oprofile/backtrace.c
index 8a6811b2cdb9..fe0bfe370c45 100644
--- a/arch/s390/oprofile/backtrace.c
+++ b/arch/s390/oprofile/backtrace.c
@@ -16,24 +16,23 @@ __show_trace(unsigned int *depth, unsigned long sp,
 	struct pt_regs *regs;
 
 	while (*depth) {
-		sp = sp & PSW_ADDR_INSN;
 		if (sp < low || sp > high - sizeof(*sf))
 			return sp;
 		sf = (struct stack_frame *) sp;
 		(*depth)--;
-		oprofile_add_trace(sf->gprs[8] & PSW_ADDR_INSN);
+		oprofile_add_trace(sf->gprs[8]);
 
 		/* Follow the backchain.  */
 		while (*depth) {
 			low = sp;
-			sp = sf->back_chain & PSW_ADDR_INSN;
+			sp = sf->back_chain;
 			if (!sp)
 				break;
 			if (sp <= low || sp > high - sizeof(*sf))
 				return sp;
 			sf = (struct stack_frame *) sp;
 			(*depth)--;
-			oprofile_add_trace(sf->gprs[8] & PSW_ADDR_INSN);
+			oprofile_add_trace(sf->gprs[8]);
 
 		}
 
@@ -46,7 +45,7 @@ __show_trace(unsigned int *depth, unsigned long sp,
 			return sp;
 		regs = (struct pt_regs *) sp;
 		(*depth)--;
-		oprofile_add_trace(sf->gprs[8] & PSW_ADDR_INSN);
+		oprofile_add_trace(sf->gprs[8]);
 		low = sp;
 		sp = regs->gprs[15];
 	}
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 11d4f277e9f6..8f19c8f9d660 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -68,9 +68,12 @@ static struct airq_struct zpci_airq = {
 	.isc = PCI_ISC,
 };
 
-/* I/O Map */
+#define ZPCI_IOMAP_ENTRIES						\
+	min(((unsigned long) CONFIG_PCI_NR_FUNCTIONS * PCI_BAR_COUNT),	\
+	    ZPCI_IOMAP_MAX_ENTRIES)
+
 static DEFINE_SPINLOCK(zpci_iomap_lock);
-static DECLARE_BITMAP(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES);
+static unsigned long *zpci_iomap_bitmap;
 struct zpci_iomap_entry *zpci_iomap_start;
 EXPORT_SYMBOL_GPL(zpci_iomap_start);
 
@@ -265,27 +268,20 @@ void __iomem *pci_iomap_range(struct pci_dev *pdev,
 			      unsigned long max)
 {
 	struct zpci_dev *zdev =	to_zpci(pdev);
-	u64 addr;
 	int idx;
 
-	if ((bar & 7) != bar)
+	if (!pci_resource_len(pdev, bar))
 		return NULL;
 
 	idx = zdev->bars[bar].map_idx;
 	spin_lock(&zpci_iomap_lock);
-	if (zpci_iomap_start[idx].count++) {
-		BUG_ON(zpci_iomap_start[idx].fh != zdev->fh ||
-		       zpci_iomap_start[idx].bar != bar);
-	} else {
-		zpci_iomap_start[idx].fh = zdev->fh;
-		zpci_iomap_start[idx].bar = bar;
-	}
 	/* Detect overrun */
-	BUG_ON(!zpci_iomap_start[idx].count);
+	WARN_ON(!++zpci_iomap_start[idx].count);
+	zpci_iomap_start[idx].fh = zdev->fh;
+	zpci_iomap_start[idx].bar = bar;
 	spin_unlock(&zpci_iomap_lock);
 
-	addr = ZPCI_IOMAP_ADDR_BASE | ((u64) idx << 48);
-	return (void __iomem *) addr + offset;
+	return (void __iomem *) ZPCI_ADDR(idx) + offset;
 }
 EXPORT_SYMBOL(pci_iomap_range);
 
@@ -297,12 +293,11 @@ EXPORT_SYMBOL(pci_iomap);
 
 void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
 {
-	unsigned int idx;
+	unsigned int idx = ZPCI_IDX(addr);
 
-	idx = (((__force u64) addr) & ~ZPCI_IOMAP_ADDR_BASE) >> 48;
 	spin_lock(&zpci_iomap_lock);
 	/* Detect underrun */
-	BUG_ON(!zpci_iomap_start[idx].count);
+	WARN_ON(!zpci_iomap_start[idx].count);
 	if (!--zpci_iomap_start[idx].count) {
 		zpci_iomap_start[idx].fh = 0;
 		zpci_iomap_start[idx].bar = 0;
@@ -544,15 +539,15 @@ static void zpci_irq_exit(void)
 
 static int zpci_alloc_iomap(struct zpci_dev *zdev)
 {
-	int entry;
+	unsigned long entry;
 
 	spin_lock(&zpci_iomap_lock);
-	entry = find_first_zero_bit(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES);
-	if (entry == ZPCI_IOMAP_MAX_ENTRIES) {
+	entry = find_first_zero_bit(zpci_iomap_bitmap, ZPCI_IOMAP_ENTRIES);
+	if (entry == ZPCI_IOMAP_ENTRIES) {
 		spin_unlock(&zpci_iomap_lock);
 		return -ENOSPC;
 	}
-	set_bit(entry, zpci_iomap);
+	set_bit(entry, zpci_iomap_bitmap);
 	spin_unlock(&zpci_iomap_lock);
 	return entry;
 }
@@ -561,7 +556,7 @@ static void zpci_free_iomap(struct zpci_dev *zdev, int entry)
 {
 	spin_lock(&zpci_iomap_lock);
 	memset(&zpci_iomap_start[entry], 0, sizeof(struct zpci_iomap_entry));
-	clear_bit(entry, zpci_iomap);
+	clear_bit(entry, zpci_iomap_bitmap);
 	spin_unlock(&zpci_iomap_lock);
 }
 
@@ -611,8 +606,7 @@ static int zpci_setup_bus_resources(struct zpci_dev *zdev,
 		if (zdev->bars[i].val & 4)
 			flags |= IORESOURCE_MEM_64;
 
-		addr = ZPCI_IOMAP_ADDR_BASE + ((u64) entry << 48);
-
+		addr = ZPCI_ADDR(entry);
 		size = 1UL << zdev->bars[i].size;
 
 		res = __alloc_res(zdev, addr, size, flags);
@@ -873,23 +867,30 @@ static int zpci_mem_init(void)
 	zdev_fmb_cache = kmem_cache_create("PCI_FMB_cache", sizeof(struct zpci_fmb),
 				16, 0, NULL);
 	if (!zdev_fmb_cache)
-		goto error_zdev;
+		goto error_fmb;
 
-	/* TODO: use realloc */
-	zpci_iomap_start = kzalloc(ZPCI_IOMAP_MAX_ENTRIES * sizeof(*zpci_iomap_start),
-				   GFP_KERNEL);
+	zpci_iomap_start = kcalloc(ZPCI_IOMAP_ENTRIES,
+				   sizeof(*zpci_iomap_start), GFP_KERNEL);
 	if (!zpci_iomap_start)
 		goto error_iomap;
-	return 0;
 
+	zpci_iomap_bitmap = kcalloc(BITS_TO_LONGS(ZPCI_IOMAP_ENTRIES),
+				    sizeof(*zpci_iomap_bitmap), GFP_KERNEL);
+	if (!zpci_iomap_bitmap)
+		goto error_iomap_bitmap;
+
+	return 0;
+error_iomap_bitmap:
+	kfree(zpci_iomap_start);
 error_iomap:
 	kmem_cache_destroy(zdev_fmb_cache);
-error_zdev:
+error_fmb:
 	return -ENOMEM;
 }
 
 static void zpci_mem_exit(void)
 {
+	kfree(zpci_iomap_bitmap);
 	kfree(zpci_iomap_start);
 	kmem_cache_destroy(zdev_fmb_cache);
 }
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 369a3e05d468..b0e04751c5d5 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -53,6 +53,11 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 
 	pr_err("%s: Event 0x%x reports an error for PCI function 0x%x\n",
 	       pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid);
+
+	if (!pdev)
+		return;
+
+	pdev->error_state = pci_channel_io_perm_failure;
 }
 
 void zpci_event_error(void *data)
diff --git a/arch/sh/include/asm/barrier.h b/arch/sh/include/asm/barrier.h
index f887c6465a82..8a84e05adb2e 100644
--- a/arch/sh/include/asm/barrier.h
+++ b/arch/sh/include/asm/barrier.h
@@ -33,7 +33,6 @@
 #endif
 
 #define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
-#define smp_store_mb(var, value) __smp_store_mb(var, value)
 
 #include <asm-generic/barrier.h>
 
diff --git a/arch/um/include/asm/page.h b/arch/um/include/asm/page.h
index e13d41c392ae..f878bec23576 100644
--- a/arch/um/include/asm/page.h
+++ b/arch/um/include/asm/page.h
@@ -34,21 +34,18 @@ struct page;
 
 #if defined(CONFIG_3_LEVEL_PGTABLES) && !defined(CONFIG_64BIT)
 
-typedef struct { unsigned long pte_low, pte_high; } pte_t;
+typedef struct { unsigned long pte; } pte_t;
 typedef struct { unsigned long pmd; } pmd_t;
 typedef struct { unsigned long pgd; } pgd_t;
-#define pte_val(x) ((x).pte_low | ((unsigned long long) (x).pte_high << 32))
-
-#define pte_get_bits(pte, bits) ((pte).pte_low & (bits))
-#define pte_set_bits(pte, bits) ((pte).pte_low |= (bits))
-#define pte_clear_bits(pte, bits) ((pte).pte_low &= ~(bits))
-#define pte_copy(to, from) ({ (to).pte_high = (from).pte_high; \
-			      smp_wmb(); \
-			      (to).pte_low = (from).pte_low; })
-#define pte_is_zero(pte) (!((pte).pte_low & ~_PAGE_NEWPAGE) && !(pte).pte_high)
-#define pte_set_val(pte, phys, prot) \
-	({ (pte).pte_high = (phys) >> 32; \
-	   (pte).pte_low = (phys) | pgprot_val(prot); })
+#define pte_val(p) ((p).pte)
+
+#define pte_get_bits(p, bits) ((p).pte & (bits))
+#define pte_set_bits(p, bits) ((p).pte |= (bits))
+#define pte_clear_bits(p, bits) ((p).pte &= ~(bits))
+#define pte_copy(to, from) ({ (to).pte = (from).pte; })
+#define pte_is_zero(p) (!((p).pte & ~_PAGE_NEWPAGE))
+#define pte_set_val(p, phys, prot) \
+	({ (p).pte = (phys) | pgprot_val(prot); })
 
 #define pmd_val(x)	((x).pmd)
 #define __pmd(x) ((pmd_t) { (x) } )
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 330e738ccfc1..c46662f64c39 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -475,6 +475,7 @@ config X86_UV
 	depends on X86_64
 	depends on X86_EXTENDED_PLATFORM
 	depends on NUMA
+	depends on EFI
 	depends on X86_X2APIC
 	depends on PCI
 	---help---
@@ -509,11 +510,10 @@ config X86_INTEL_CE
 
 config X86_INTEL_MID
 	bool "Intel MID platform support"
-	depends on X86_32
 	depends on X86_EXTENDED_PLATFORM
 	depends on X86_PLATFORM_DEVICES
 	depends on PCI
-	depends on PCI_GOANY
+	depends on X86_64 || (PCI_GOANY && X86_32)
 	depends on X86_IO_APIC
 	select SFI
 	select I2C
@@ -778,8 +778,8 @@ config HPET_TIMER
 	  HPET is the next generation timer replacing legacy 8254s.
 	  The HPET provides a stable time base on SMP
 	  systems, unlike the TSC, but it is more expensive to access,
-	  as it is off-chip.  You can find the HPET spec at
-	  <http://www.intel.com/hardwaredesign/hpetspec_1.pdf>.
+	  as it is off-chip.  The interface used is documented
+	  in the HPET spec, revision 1.
 
 	  You can safely choose Y here.  However, HPET will only be
 	  activated if the platform and the BIOS support this feature.
diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha20-ssse3-x86_64.S
index 712b13047b41..3a33124e9112 100644
--- a/arch/x86/crypto/chacha20-ssse3-x86_64.S
+++ b/arch/x86/crypto/chacha20-ssse3-x86_64.S
@@ -157,7 +157,9 @@ ENTRY(chacha20_4block_xor_ssse3)
 	# done with the slightly better performing SSSE3 byte shuffling,
 	# 7/12-bit word rotation uses traditional shift+OR.
 
-	sub		$0x40,%rsp
+	mov		%rsp,%r11
+	sub		$0x80,%rsp
+	and		$~63,%rsp
 
 	# x0..15[0-3] = s0..3[0..3]
 	movq		0x00(%rdi),%xmm1
@@ -620,6 +622,6 @@ ENTRY(chacha20_4block_xor_ssse3)
 	pxor		%xmm1,%xmm15
 	movdqu		%xmm15,0xf0(%rsi)
 
-	add		$0x40,%rsp
+	mov		%r11,%rsp
 	ret
 ENDPROC(chacha20_4block_xor_ssse3)
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 881b4768644a..e7de5c9a4fbd 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -23,11 +23,13 @@ extern void irq_ctx_init(int cpu);
 
 #define __ARCH_HAS_DO_SOFTIRQ
 
+struct irq_desc;
+
 #ifdef CONFIG_HOTPLUG_CPU
 #include <linux/cpumask.h>
 extern int check_irq_vectors_for_cpu_disable(void);
 extern void fixup_irqs(void);
-extern void irq_force_complete_move(int);
+extern void irq_force_complete_move(struct irq_desc *desc);
 #endif
 
 #ifdef CONFIG_HAVE_KVM
@@ -37,7 +39,6 @@ extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void));
 extern void (*x86_platform_ipi_callback)(void);
 extern void native_init_IRQ(void);
 
-struct irq_desc;
 extern bool handle_irq(struct irq_desc *desc, struct pt_regs *regs);
 
 extern __visible unsigned int do_IRQ(struct pt_regs *regs);
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 04c27a013165..4432ab7f407c 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -366,20 +366,18 @@ static inline enum page_cache_mode pgprot2cachemode(pgprot_t pgprot)
 }
 static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot)
 {
+	pgprotval_t val = pgprot_val(pgprot);
 	pgprot_t new;
-	unsigned long val;
 
-	val = pgprot_val(pgprot);
 	pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) |
 		((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT));
 	return new;
 }
 static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot)
 {
+	pgprotval_t val = pgprot_val(pgprot);
 	pgprot_t new;
-	unsigned long val;
 
-	val = pgprot_val(pgprot);
 	pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) |
 			  ((val & _PAGE_PAT_LARGE) >>
 			   (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT));
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 491a3d9dbb15..ecb410310e70 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -765,7 +765,7 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
  * Return saved PC of a blocked thread.
  * What is this good for? it will be always the scheduler or ret_from_fork.
  */
-#define thread_saved_pc(t)	(*(unsigned long *)((t)->thread.sp - 8))
+#define thread_saved_pc(t)	READ_ONCE_NOCHECK(*(unsigned long *)((t)->thread.sp - 8))
 
 #define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
 extern unsigned long KSTK_ESP(struct task_struct *task);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index f25321894ad2..fdb0fbfb1197 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2521,6 +2521,7 @@ void __init setup_ioapic_dest(void)
 {
 	int pin, ioapic, irq, irq_entry;
 	const struct cpumask *mask;
+	struct irq_desc *desc;
 	struct irq_data *idata;
 	struct irq_chip *chip;
 
@@ -2536,7 +2537,9 @@ void __init setup_ioapic_dest(void)
 		if (irq < 0 || !mp_init_irq_at_boot(ioapic, irq))
 			continue;
 
-		idata = irq_get_irq_data(irq);
+		desc = irq_to_desc(irq);
+		raw_spin_lock_irq(&desc->lock);
+		idata = irq_desc_get_irq_data(desc);
 
 		/*
 		 * Honour affinities which have been set in early boot
@@ -2550,6 +2553,7 @@ void __init setup_ioapic_dest(void)
 		/* Might be lapic_chip for irq 0 */
 		if (chip->irq_set_affinity)
 			chip->irq_set_affinity(idata, mask, false);
+		raw_spin_unlock_irq(&desc->lock);
 	}
 }
 #endif
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 908cb37da171..3b670df4ba7b 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -31,7 +31,7 @@ struct apic_chip_data {
 struct irq_domain *x86_vector_domain;
 EXPORT_SYMBOL_GPL(x86_vector_domain);
 static DEFINE_RAW_SPINLOCK(vector_lock);
-static cpumask_var_t vector_cpumask;
+static cpumask_var_t vector_cpumask, vector_searchmask, searched_cpumask;
 static struct irq_chip lapic_controller;
 #ifdef	CONFIG_X86_IO_APIC
 static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY];
@@ -118,35 +118,47 @@ static int __assign_irq_vector(int irq, struct apic_chip_data *d,
 	 */
 	static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START;
 	static int current_offset = VECTOR_OFFSET_START % 16;
-	int cpu, err;
+	int cpu, vector;
 
-	if (d->move_in_progress)
+	/*
+	 * If there is still a move in progress or the previous move has not
+	 * been cleaned up completely, tell the caller to come back later.
+	 */
+	if (d->move_in_progress ||
+	    cpumask_intersects(d->old_domain, cpu_online_mask))
 		return -EBUSY;
 
 	/* Only try and allocate irqs on cpus that are present */
-	err = -ENOSPC;
 	cpumask_clear(d->old_domain);
+	cpumask_clear(searched_cpumask);
 	cpu = cpumask_first_and(mask, cpu_online_mask);
 	while (cpu < nr_cpu_ids) {
-		int new_cpu, vector, offset;
+		int new_cpu, offset;
 
+		/* Get the possible target cpus for @mask/@cpu from the apic */
 		apic->vector_allocation_domain(cpu, vector_cpumask, mask);
 
+		/*
+		 * Clear the offline cpus from @vector_cpumask for searching
+		 * and verify whether the result overlaps with @mask. If true,
+		 * then the call to apic->cpu_mask_to_apicid_and() will
+		 * succeed as well. If not, no point in trying to find a
+		 * vector in this mask.
+		 */
+		cpumask_and(vector_searchmask, vector_cpumask, cpu_online_mask);
+		if (!cpumask_intersects(vector_searchmask, mask))
+			goto next_cpu;
+
 		if (cpumask_subset(vector_cpumask, d->domain)) {
-			err = 0;
 			if (cpumask_equal(vector_cpumask, d->domain))
-				break;
+				goto success;
 			/*
-			 * New cpumask using the vector is a proper subset of
-			 * the current in use mask. So cleanup the vector
-			 * allocation for the members that are not used anymore.
+			 * Mark the cpus which are not longer in the mask for
+			 * cleanup.
 			 */
-			cpumask_andnot(d->old_domain, d->domain,
-				       vector_cpumask);
-			d->move_in_progress =
-			   cpumask_intersects(d->old_domain, cpu_online_mask);
-			cpumask_and(d->domain, d->domain, vector_cpumask);
-			break;
+			cpumask_andnot(d->old_domain, d->domain, vector_cpumask);
+			vector = d->cfg.vector;
+			goto update;
 		}
 
 		vector = current_vector;
@@ -158,45 +170,60 @@ next:
 			vector = FIRST_EXTERNAL_VECTOR + offset;
 		}
 
-		if (unlikely(current_vector == vector)) {
-			cpumask_or(d->old_domain, d->old_domain,
-				   vector_cpumask);
-			cpumask_andnot(vector_cpumask, mask, d->old_domain);
-			cpu = cpumask_first_and(vector_cpumask,
-						cpu_online_mask);
-			continue;
-		}
+		/* If the search wrapped around, try the next cpu */
+		if (unlikely(current_vector == vector))
+			goto next_cpu;
 
 		if (test_bit(vector, used_vectors))
 			goto next;
 
-		for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) {
+		for_each_cpu(new_cpu, vector_searchmask) {
 			if (!IS_ERR_OR_NULL(per_cpu(vector_irq, new_cpu)[vector]))
 				goto next;
 		}
 		/* Found one! */
 		current_vector = vector;
 		current_offset = offset;
-		if (d->cfg.vector) {
+		/* Schedule the old vector for cleanup on all cpus */
+		if (d->cfg.vector)
 			cpumask_copy(d->old_domain, d->domain);
-			d->move_in_progress =
-			   cpumask_intersects(d->old_domain, cpu_online_mask);
-		}
-		for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask)
+		for_each_cpu(new_cpu, vector_searchmask)
 			per_cpu(vector_irq, new_cpu)[vector] = irq_to_desc(irq);
-		d->cfg.vector = vector;
-		cpumask_copy(d->domain, vector_cpumask);
-		err = 0;
-		break;
-	}
+		goto update;
 
-	if (!err) {
-		/* cache destination APIC IDs into cfg->dest_apicid */
-		err = apic->cpu_mask_to_apicid_and(mask, d->domain,
-						   &d->cfg.dest_apicid);
+next_cpu:
+		/*
+		 * We exclude the current @vector_cpumask from the requested
+		 * @mask and try again with the next online cpu in the
+		 * result. We cannot modify @mask, so we use @vector_cpumask
+		 * as a temporary buffer here as it will be reassigned when
+		 * calling apic->vector_allocation_domain() above.
+		 */
+		cpumask_or(searched_cpumask, searched_cpumask, vector_cpumask);
+		cpumask_andnot(vector_cpumask, mask, searched_cpumask);
+		cpu = cpumask_first_and(vector_cpumask, cpu_online_mask);
+		continue;
 	}
+	return -ENOSPC;
 
-	return err;
+update:
+	/*
+	 * Exclude offline cpus from the cleanup mask and set the
+	 * move_in_progress flag when the result is not empty.
+	 */
+	cpumask_and(d->old_domain, d->old_domain, cpu_online_mask);
+	d->move_in_progress = !cpumask_empty(d->old_domain);
+	d->cfg.vector = vector;
+	cpumask_copy(d->domain, vector_cpumask);
+success:
+	/*
+	 * Cache destination APIC IDs into cfg->dest_apicid. This cannot fail
+	 * as we already established, that mask & d->domain & cpu_online_mask
+	 * is not empty.
+	 */
+	BUG_ON(apic->cpu_mask_to_apicid_and(mask, d->domain,
+					    &d->cfg.dest_apicid));
+	return 0;
 }
 
 static int assign_irq_vector(int irq, struct apic_chip_data *data,
@@ -226,10 +253,8 @@ static int assign_irq_vector_policy(int irq, int node,
 static void clear_irq_vector(int irq, struct apic_chip_data *data)
 {
 	struct irq_desc *desc;
-	unsigned long flags;
 	int cpu, vector;
 
-	raw_spin_lock_irqsave(&vector_lock, flags);
 	BUG_ON(!data->cfg.vector);
 
 	vector = data->cfg.vector;
@@ -239,10 +264,13 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data)
 	data->cfg.vector = 0;
 	cpumask_clear(data->domain);
 
-	if (likely(!data->move_in_progress)) {
-		raw_spin_unlock_irqrestore(&vector_lock, flags);
+	/*
+	 * If move is in progress or the old_domain mask is not empty,
+	 * i.e. the cleanup IPI has not been processed yet, we need to remove
+	 * the old references to desc from all cpus vector tables.
+	 */
+	if (!data->move_in_progress && cpumask_empty(data->old_domain))
 		return;
-	}
 
 	desc = irq_to_desc(irq);
 	for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) {
@@ -255,7 +283,6 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data)
 		}
 	}
 	data->move_in_progress = 0;
-	raw_spin_unlock_irqrestore(&vector_lock, flags);
 }
 
 void init_irq_alloc_info(struct irq_alloc_info *info,
@@ -276,19 +303,24 @@ void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src)
 static void x86_vector_free_irqs(struct irq_domain *domain,
 				 unsigned int virq, unsigned int nr_irqs)
 {
+	struct apic_chip_data *apic_data;
 	struct irq_data *irq_data;
+	unsigned long flags;
 	int i;
 
 	for (i = 0; i < nr_irqs; i++) {
 		irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i);
 		if (irq_data && irq_data->chip_data) {
+			raw_spin_lock_irqsave(&vector_lock, flags);
 			clear_irq_vector(virq + i, irq_data->chip_data);
-			free_apic_chip_data(irq_data->chip_data);
+			apic_data = irq_data->chip_data;
+			irq_domain_reset_irq_data(irq_data);
+			raw_spin_unlock_irqrestore(&vector_lock, flags);
+			free_apic_chip_data(apic_data);
 #ifdef	CONFIG_X86_IO_APIC
 			if (virq + i < nr_legacy_irqs())
 				legacy_irq_data[virq + i] = NULL;
 #endif
-			irq_domain_reset_irq_data(irq_data);
 		}
 	}
 }
@@ -406,6 +438,8 @@ int __init arch_early_irq_init(void)
 	arch_init_htirq_domain(x86_vector_domain);
 
 	BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL));
+	BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL));
+	BUG_ON(!alloc_cpumask_var(&searched_cpumask, GFP_KERNEL));
 
 	return arch_early_ioapic_init();
 }
@@ -494,14 +528,7 @@ static int apic_set_affinity(struct irq_data *irq_data,
 		return -EINVAL;
 
 	err = assign_irq_vector(irq, data, dest);
-	if (err) {
-		if (assign_irq_vector(irq, data,
-				      irq_data_get_affinity_mask(irq_data)))
-			pr_err("Failed to recover vector for irq %d\n", irq);
-		return err;
-	}
-
-	return IRQ_SET_MASK_OK;
+	return err ? err : IRQ_SET_MASK_OK;
 }
 
 static struct irq_chip lapic_controller = {
@@ -513,20 +540,12 @@ static struct irq_chip lapic_controller = {
 #ifdef CONFIG_SMP
 static void __send_cleanup_vector(struct apic_chip_data *data)
 {
-	cpumask_var_t cleanup_mask;
-
-	if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
-		unsigned int i;
-
-		for_each_cpu_and(i, data->old_domain, cpu_online_mask)
-			apic->send_IPI_mask(cpumask_of(i),
-					    IRQ_MOVE_CLEANUP_VECTOR);
-	} else {
-		cpumask_and(cleanup_mask, data->old_domain, cpu_online_mask);
-		apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
-		free_cpumask_var(cleanup_mask);
-	}
+	raw_spin_lock(&vector_lock);
+	cpumask_and(data->old_domain, data->old_domain, cpu_online_mask);
 	data->move_in_progress = 0;
+	if (!cpumask_empty(data->old_domain))
+		apic->send_IPI_mask(data->old_domain, IRQ_MOVE_CLEANUP_VECTOR);
+	raw_spin_unlock(&vector_lock);
 }
 
 void send_cleanup_vector(struct irq_cfg *cfg)
@@ -570,12 +589,25 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 			goto unlock;
 
 		/*
-		 * Check if the irq migration is in progress. If so, we
-		 * haven't received the cleanup request yet for this irq.
+		 * Nothing to cleanup if irq migration is in progress
+		 * or this cpu is not set in the cleanup mask.
 		 */
-		if (data->move_in_progress)
+		if (data->move_in_progress ||
+		    !cpumask_test_cpu(me, data->old_domain))
 			goto unlock;
 
+		/*
+		 * We have two cases to handle here:
+		 * 1) vector is unchanged but the target mask got reduced
+		 * 2) vector and the target mask has changed
+		 *
+		 * #1 is obvious, but in #2 we have two vectors with the same
+		 * irq descriptor: the old and the new vector. So we need to
+		 * make sure that we only cleanup the old vector. The new
+		 * vector has the current @vector number in the config and
+		 * this cpu is part of the target mask. We better leave that
+		 * one alone.
+		 */
 		if (vector == data->cfg.vector &&
 		    cpumask_test_cpu(me, data->domain))
 			goto unlock;
@@ -593,6 +625,7 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 			goto unlock;
 		}
 		__this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
+		cpumask_clear_cpu(me, data->old_domain);
 unlock:
 		raw_spin_unlock(&desc->lock);
 	}
@@ -621,12 +654,48 @@ void irq_complete_move(struct irq_cfg *cfg)
 	__irq_complete_move(cfg, ~get_irq_regs()->orig_ax);
 }
 
-void irq_force_complete_move(int irq)
+/*
+ * Called with @desc->lock held and interrupts disabled.
+ */
+void irq_force_complete_move(struct irq_desc *desc)
 {
-	struct irq_cfg *cfg = irq_cfg(irq);
+	struct irq_data *irqdata = irq_desc_get_irq_data(desc);
+	struct apic_chip_data *data = apic_chip_data(irqdata);
+	struct irq_cfg *cfg = data ? &data->cfg : NULL;
 
-	if (cfg)
-		__irq_complete_move(cfg, cfg->vector);
+	if (!cfg)
+		return;
+
+	__irq_complete_move(cfg, cfg->vector);
+
+	/*
+	 * This is tricky. If the cleanup of @data->old_domain has not been
+	 * done yet, then the following setaffinity call will fail with
+	 * -EBUSY. This can leave the interrupt in a stale state.
+	 *
+	 * The cleanup cannot make progress because we hold @desc->lock. So in
+	 * case @data->old_domain is not yet cleaned up, we need to drop the
+	 * lock and acquire it again. @desc cannot go away, because the
+	 * hotplug code holds the sparse irq lock.
+	 */
+	raw_spin_lock(&vector_lock);
+	/* Clean out all offline cpus (including ourself) first. */
+	cpumask_and(data->old_domain, data->old_domain, cpu_online_mask);
+	while (!cpumask_empty(data->old_domain)) {
+		raw_spin_unlock(&vector_lock);
+		raw_spin_unlock(&desc->lock);
+		cpu_relax();
+		raw_spin_lock(&desc->lock);
+		/*
+		 * Reevaluate apic_chip_data. It might have been cleared after
+		 * we dropped @desc->lock.
+		 */
+		data = apic_chip_data(irqdata);
+		if (!data)
+			return;
+		raw_spin_lock(&vector_lock);
+	}
+	raw_spin_unlock(&vector_lock);
 }
 #endif
 
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index d760c6bb37b5..624db00583f4 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -889,7 +889,10 @@ void __init uv_system_init(void)
 		return;
 	}
 	pr_info("UV: Found %s hub\n", hub);
-	map_low_mmrs();
+
+	/* We now only need to map the MMRs on UV1 */
+	if (is_uv1_hub())
+		map_low_mmrs();
 
 	m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR );
 	m_val = m_n_config.s.m_skt;
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index a667078a5180..fed2ab1f1065 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1960,7 +1960,8 @@ intel_bts_constraints(struct perf_event *event)
 
 static int intel_alt_er(int idx, u64 config)
 {
-	int alt_idx;
+	int alt_idx = idx;
+
 	if (!(x86_pmu.flags & PMU_FL_HAS_RSP_1))
 		return idx;
 
@@ -2897,14 +2898,12 @@ static void intel_pmu_cpu_starting(int cpu)
 		return;
 
 	if (!(x86_pmu.flags & PMU_FL_NO_HT_SHARING)) {
-		void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED];
-
 		for_each_cpu(i, topology_sibling_cpumask(cpu)) {
 			struct intel_shared_regs *pc;
 
 			pc = per_cpu(cpu_hw_events, i).shared_regs;
 			if (pc && pc->core_id == core_id) {
-				*onln = cpuc->shared_regs;
+				cpuc->kfree_on_online[0] = cpuc->shared_regs;
 				cpuc->shared_regs = pc;
 				break;
 			}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index f97f8075bf04..3bf41d413775 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -995,6 +995,9 @@ static int __init uncore_pci_init(void)
 	case 87: /* Knights Landing */
 		ret = knl_uncore_pci_init();
 		break;
+	case 94: /* SkyLake */
+		ret = skl_uncore_pci_init();
+		break;
 	default:
 		return 0;
 	}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 07aa2d6bd710..a7086b862156 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -336,6 +336,7 @@ int snb_uncore_pci_init(void);
 int ivb_uncore_pci_init(void);
 int hsw_uncore_pci_init(void);
 int bdw_uncore_pci_init(void);
+int skl_uncore_pci_init(void);
 void snb_uncore_cpu_init(void);
 void nhm_uncore_cpu_init(void);
 int snb_pci2phy_map_init(int devid);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
index 0b934820fafd..2bd030ddd0db 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -8,6 +8,7 @@
 #define PCI_DEVICE_ID_INTEL_HSW_IMC	0x0c00
 #define PCI_DEVICE_ID_INTEL_HSW_U_IMC	0x0a04
 #define PCI_DEVICE_ID_INTEL_BDW_IMC	0x1604
+#define PCI_DEVICE_ID_INTEL_SKL_IMC	0x191f
 
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
@@ -524,6 +525,14 @@ static const struct pci_device_id bdw_uncore_pci_ids[] = {
 	{ /* end: all zeroes */ },
 };
 
+static const struct pci_device_id skl_uncore_pci_ids[] = {
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* end: all zeroes */ },
+};
+
 static struct pci_driver snb_uncore_pci_driver = {
 	.name		= "snb_uncore",
 	.id_table	= snb_uncore_pci_ids,
@@ -544,6 +553,11 @@ static struct pci_driver bdw_uncore_pci_driver = {
 	.id_table	= bdw_uncore_pci_ids,
 };
 
+static struct pci_driver skl_uncore_pci_driver = {
+	.name		= "skl_uncore",
+	.id_table	= skl_uncore_pci_ids,
+};
+
 struct imc_uncore_pci_dev {
 	__u32 pci_id;
 	struct pci_driver *driver;
@@ -558,6 +572,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver),    /* 4th Gen Core Processor */
 	IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver),  /* 4th Gen Core ULT Mobile Processor */
 	IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver),    /* 5th Gen Core U */
+	IMC_DEV(SKL_IMC, &skl_uncore_pci_driver),    /* 6th Gen Core */
 	{  /* end marker */ }
 };
 
@@ -610,6 +625,11 @@ int bdw_uncore_pci_init(void)
 	return imc_uncore_pci_init();
 }
 
+int skl_uncore_pci_init(void)
+{
+	return imc_uncore_pci_init();
+}
+
 /* end of Sandy Bridge uncore support */
 
 /* Nehalem uncore support */
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index f129a9af6357..2c0f3407bd1f 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -192,5 +192,13 @@ void __init x86_64_start_reservations(char *real_mode_data)
 
 	reserve_ebda_region();
 
+	switch (boot_params.hdr.hardware_subarch) {
+	case X86_SUBARCH_INTEL_MID:
+		x86_intel_mid_early_setup();
+		break;
+	default:
+		break;
+	}
+
 	start_kernel();
 }
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index f8062aaf5df9..61521dc19c10 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -462,7 +462,7 @@ void fixup_irqs(void)
 		 * non intr-remapping case, we can't wait till this interrupt
 		 * arrives at this cpu before completing the irq move.
 		 */
-		irq_force_complete_move(irq);
+		irq_force_complete_move(desc);
 
 		if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
 			break_affinity = 1;
@@ -470,6 +470,15 @@ void fixup_irqs(void)
 		}
 
 		chip = irq_data_get_irq_chip(data);
+		/*
+		 * The interrupt descriptor might have been cleaned up
+		 * already, but it is not yet removed from the radix tree
+		 */
+		if (!chip) {
+			raw_spin_unlock(&desc->lock);
+			continue;
+		}
+
 		if (!irqd_can_move_in_process_context(data) && chip->irq_mask)
 			chip->irq_mask(data);
 
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index fba343062055..2b0ef26da0bd 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -232,17 +232,31 @@ ENDPROC(copy_user_enhanced_fast_string)
 
 /*
  * copy_user_nocache - Uncached memory copy with exception handling
- * This will force destination/source out of cache for more performance.
+ * This will force destination out of cache for more performance.
+ *
+ * Note: Cached memory copy is used when destination or size is not
+ * naturally aligned. That is:
+ *  - Require 8-byte alignment when size is 8 bytes or larger.
+ *  - Require 4-byte alignment when size is 4 bytes.
  */
 ENTRY(__copy_user_nocache)
 	ASM_STAC
+
+	/* If size is less than 8 bytes, go to 4-byte copy */
 	cmpl $8,%edx
-	jb 20f		/* less then 8 bytes, go to byte copy loop */
+	jb .L_4b_nocache_copy_entry
+
+	/* If destination is not 8-byte aligned, "cache" copy to align it */
 	ALIGN_DESTINATION
+
+	/* Set 4x8-byte copy count and remainder */
 	movl %edx,%ecx
 	andl $63,%edx
 	shrl $6,%ecx
-	jz 17f
+	jz .L_8b_nocache_copy_entry	/* jump if count is 0 */
+
+	/* Perform 4x8-byte nocache loop-copy */
+.L_4x8b_nocache_copy_loop:
 1:	movq (%rsi),%r8
 2:	movq 1*8(%rsi),%r9
 3:	movq 2*8(%rsi),%r10
@@ -262,60 +276,106 @@ ENTRY(__copy_user_nocache)
 	leaq 64(%rsi),%rsi
 	leaq 64(%rdi),%rdi
 	decl %ecx
-	jnz 1b
-17:	movl %edx,%ecx
+	jnz .L_4x8b_nocache_copy_loop
+
+	/* Set 8-byte copy count and remainder */
+.L_8b_nocache_copy_entry:
+	movl %edx,%ecx
 	andl $7,%edx
 	shrl $3,%ecx
-	jz 20f
-18:	movq (%rsi),%r8
-19:	movnti %r8,(%rdi)
+	jz .L_4b_nocache_copy_entry	/* jump if count is 0 */
+
+	/* Perform 8-byte nocache loop-copy */
+.L_8b_nocache_copy_loop:
+20:	movq (%rsi),%r8
+21:	movnti %r8,(%rdi)
 	leaq 8(%rsi),%rsi
 	leaq 8(%rdi),%rdi
 	decl %ecx
-	jnz 18b
-20:	andl %edx,%edx
-	jz 23f
+	jnz .L_8b_nocache_copy_loop
+
+	/* If no byte left, we're done */
+.L_4b_nocache_copy_entry:
+	andl %edx,%edx
+	jz .L_finish_copy
+
+	/* If destination is not 4-byte aligned, go to byte copy: */
+	movl %edi,%ecx
+	andl $3,%ecx
+	jnz .L_1b_cache_copy_entry
+
+	/* Set 4-byte copy count (1 or 0) and remainder */
 	movl %edx,%ecx
-21:	movb (%rsi),%al
-22:	movb %al,(%rdi)
+	andl $3,%edx
+	shrl $2,%ecx
+	jz .L_1b_cache_copy_entry	/* jump if count is 0 */
+
+	/* Perform 4-byte nocache copy: */
+30:	movl (%rsi),%r8d
+31:	movnti %r8d,(%rdi)
+	leaq 4(%rsi),%rsi
+	leaq 4(%rdi),%rdi
+
+	/* If no bytes left, we're done: */
+	andl %edx,%edx
+	jz .L_finish_copy
+
+	/* Perform byte "cache" loop-copy for the remainder */
+.L_1b_cache_copy_entry:
+	movl %edx,%ecx
+.L_1b_cache_copy_loop:
+40:	movb (%rsi),%al
+41:	movb %al,(%rdi)
 	incq %rsi
 	incq %rdi
 	decl %ecx
-	jnz 21b
-23:	xorl %eax,%eax
+	jnz .L_1b_cache_copy_loop
+
+	/* Finished copying; fence the prior stores */
+.L_finish_copy:
+	xorl %eax,%eax
 	ASM_CLAC
 	sfence
 	ret
 
 	.section .fixup,"ax"
-30:	shll $6,%ecx
+.L_fixup_4x8b_copy:
+	shll $6,%ecx
 	addl %ecx,%edx
-	jmp 60f
-40:	lea (%rdx,%rcx,8),%rdx
-	jmp 60f
-50:	movl %ecx,%edx
-60:	sfence
+	jmp .L_fixup_handle_tail
+.L_fixup_8b_copy:
+	lea (%rdx,%rcx,8),%rdx
+	jmp .L_fixup_handle_tail
+.L_fixup_4b_copy:
+	lea (%rdx,%rcx,4),%rdx
+	jmp .L_fixup_handle_tail
+.L_fixup_1b_copy:
+	movl %ecx,%edx
+.L_fixup_handle_tail:
+	sfence
 	jmp copy_user_handle_tail
 	.previous
 
-	_ASM_EXTABLE(1b,30b)
-	_ASM_EXTABLE(2b,30b)
-	_ASM_EXTABLE(3b,30b)
-	_ASM_EXTABLE(4b,30b)
-	_ASM_EXTABLE(5b,30b)
-	_ASM_EXTABLE(6b,30b)
-	_ASM_EXTABLE(7b,30b)
-	_ASM_EXTABLE(8b,30b)
-	_ASM_EXTABLE(9b,30b)
-	_ASM_EXTABLE(10b,30b)
-	_ASM_EXTABLE(11b,30b)
-	_ASM_EXTABLE(12b,30b)
-	_ASM_EXTABLE(13b,30b)
-	_ASM_EXTABLE(14b,30b)
-	_ASM_EXTABLE(15b,30b)
-	_ASM_EXTABLE(16b,30b)
-	_ASM_EXTABLE(18b,40b)
-	_ASM_EXTABLE(19b,40b)
-	_ASM_EXTABLE(21b,50b)
-	_ASM_EXTABLE(22b,50b)
+	_ASM_EXTABLE(1b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(2b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(3b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(4b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(5b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(6b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(7b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(8b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(9b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(10b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(11b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(12b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(13b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(14b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(15b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(16b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(20b,.L_fixup_8b_copy)
+	_ASM_EXTABLE(21b,.L_fixup_8b_copy)
+	_ASM_EXTABLE(30b,.L_fixup_4b_copy)
+	_ASM_EXTABLE(31b,.L_fixup_4b_copy)
+	_ASM_EXTABLE(40b,.L_fixup_1b_copy)
+	_ASM_EXTABLE(41b,.L_fixup_1b_copy)
 ENDPROC(__copy_user_nocache)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index eef44d9a3f77..e830c71a1323 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -287,6 +287,9 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (!pmd_k)
 		return -1;
 
+	if (pmd_huge(*pmd_k))
+		return 0;
+
 	pte_k = pte_offset_kernel(pmd_k, address);
 	if (!pte_present(*pte_k))
 		return -1;
@@ -360,8 +363,6 @@ void vmalloc_sync_all(void)
  * 64-bit:
  *
  *   Handle a fault on the vmalloc area
- *
- * This assumes no large pages in there.
  */
 static noinline int vmalloc_fault(unsigned long address)
 {
@@ -403,17 +404,23 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (pud_none(*pud_ref))
 		return -1;
 
-	if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref))
+	if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref))
 		BUG();
 
+	if (pud_huge(*pud))
+		return 0;
+
 	pmd = pmd_offset(pud, address);
 	pmd_ref = pmd_offset(pud_ref, address);
 	if (pmd_none(*pmd_ref))
 		return -1;
 
-	if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref))
+	if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref))
 		BUG();
 
+	if (pmd_huge(*pmd))
+		return 0;
+
 	pte_ref = pte_offset_kernel(pmd_ref, address);
 	if (!pte_present(*pte_ref))
 		return -1;
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 42982b26e32b..740d7ac03a55 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -173,10 +173,10 @@ static __init int setup_hugepagesz(char *opt)
 }
 __setup("hugepagesz=", setup_hugepagesz);
 
-#ifdef CONFIG_CMA
+#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
 static __init int gigantic_pages_init(void)
 {
-	/* With CMA we can allocate gigantic pages at runtime */
+	/* With compaction or CMA we can allocate gigantic pages at runtime */
 	if (cpu_has_gbpages && !size_to_hstate(1UL << PUD_SHIFT))
 		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
 	return 0;
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index c3b3f653ed0c..d04f8094bc23 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -469,7 +469,7 @@ static void __init numa_clear_kernel_node_hotplug(void)
 {
 	int i, nid;
 	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
-	unsigned long start, end;
+	phys_addr_t start, end;
 	struct memblock_region *r;
 
 	/*
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index fc6a4c8f6e2a..2440814b0069 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -33,7 +33,7 @@ struct cpa_data {
 	pgd_t		*pgd;
 	pgprot_t	mask_set;
 	pgprot_t	mask_clr;
-	int		numpages;
+	unsigned long	numpages;
 	int		flags;
 	unsigned long	pfn;
 	unsigned	force_split : 1;
@@ -1350,7 +1350,7 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
 		 * CPA operation. Either a large page has been
 		 * preserved or a single page update happened.
 		 */
-		BUG_ON(cpa->numpages > numpages);
+		BUG_ON(cpa->numpages > numpages || !cpa->numpages);
 		numpages -= cpa->numpages;
 		if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY))
 			cpa->curpage++;
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 1c7380da65ff..2d66db8f80f9 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -8,6 +8,7 @@
 #include <linux/memblock.h>
 #include <linux/bootmem.h>
 #include <linux/acpi.h>
+#include <linux/dmi.h>
 #include <asm/efi.h>
 #include <asm/uv/uv.h>
 
@@ -248,6 +249,16 @@ out:
 	return ret;
 }
 
+static const struct dmi_system_id sgi_uv1_dmi[] = {
+	{ NULL, "SGI UV1",
+		{	DMI_MATCH(DMI_PRODUCT_NAME,	"Stoutland Platform"),
+			DMI_MATCH(DMI_PRODUCT_VERSION,	"1.0"),
+			DMI_MATCH(DMI_BIOS_VENDOR,	"SGI.COM"),
+		}
+	},
+	{ } /* NULL entry stops DMI scanning */
+};
+
 void __init efi_apply_memmap_quirks(void)
 {
 	/*
@@ -260,10 +271,8 @@ void __init efi_apply_memmap_quirks(void)
 		efi_unmap_memmap();
 	}
 
-	/*
-	 * UV doesn't support the new EFI pagetable mapping yet.
-	 */
-	if (is_uv_system())
+	/* UV2+ BIOS has a fix for this issue.  UV1 still needs the quirk. */
+	if (dmi_check_system(sgi_uv1_dmi))
 		set_bit(EFI_OLD_MEMMAP, &efi.flags);
 }
 
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 1bbc21e2e4ae..90bb997ed0a2 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -138,7 +138,7 @@ static void intel_mid_arch_setup(void)
 		intel_mid_ops = get_intel_mid_ops[__intel_mid_cpu_chip]();
 	else {
 		intel_mid_ops = get_intel_mid_ops[INTEL_MID_CPU_CHIP_PENWELL]();
-		pr_info("ARCH: Unknown SoC, assuming PENWELL!\n");
+		pr_info("ARCH: Unknown SoC, assuming Penwell!\n");
 	}
 
 out:
@@ -214,12 +214,10 @@ static inline int __init setup_x86_intel_mid_timer(char *arg)
 	else if (strcmp("lapic_and_apbt", arg) == 0)
 		intel_mid_timer_options = INTEL_MID_TIMER_LAPIC_APBT;
 	else {
-		pr_warn("X86 INTEL_MID timer option %s not recognised"
-			   " use x86_intel_mid_timer=apbt_only or lapic_and_apbt\n",
-			   arg);
+		pr_warn("X86 INTEL_MID timer option %s not recognised use x86_intel_mid_timer=apbt_only or lapic_and_apbt\n",
+			arg);
 		return -EINVAL;
 	}
 	return 0;
 }
 __setup("x86_intel_mid_timer=", setup_x86_intel_mid_timer);
-
diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c
index c1bdafaac3ca..c61b6c332e97 100644
--- a/arch/x86/platform/intel-quark/imr.c
+++ b/arch/x86/platform/intel-quark/imr.c
@@ -220,11 +220,12 @@ static int imr_dbgfs_state_show(struct seq_file *s, void *unused)
 		if (imr_is_enabled(&imr)) {
 			base = imr_to_phys(imr.addr_lo);
 			end = imr_to_phys(imr.addr_hi) + IMR_MASK;
+			size = end - base + 1;
 		} else {
 			base = 0;
 			end = 0;
+			size = 0;
 		}
-		size = end - base;
 		seq_printf(s, "imr%02i: base=%pa, end=%pa, size=0x%08zx "
 			   "rmask=0x%08x, wmask=0x%08x, %s, %s\n", i,
 			   &base, &end, size, imr.rmask, imr.wmask,
@@ -579,6 +580,7 @@ static void __init imr_fixup_memmap(struct imr_device *idev)
 {
 	phys_addr_t base = virt_to_phys(&_text);
 	size_t size = virt_to_phys(&__end_rodata) - base;
+	unsigned long start, end;
 	int i;
 	int ret;
 
@@ -586,18 +588,24 @@ static void __init imr_fixup_memmap(struct imr_device *idev)
 	for (i = 0; i < idev->max_imr; i++)
 		imr_clear(i);
 
+	start = (unsigned long)_text;
+	end = (unsigned long)__end_rodata - 1;
+
 	/*
 	 * Setup a locked IMR around the physical extent of the kernel
 	 * from the beginning of the .text secton to the end of the
 	 * .rodata section as one physically contiguous block.
+	 *
+	 * We don't round up @size since it is already PAGE_SIZE aligned.
+	 * See vmlinux.lds.S for details.
 	 */
 	ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, true);
 	if (ret < 0) {
-		pr_err("unable to setup IMR for kernel: (%p - %p)\n",
-			&_text, &__end_rodata);
+		pr_err("unable to setup IMR for kernel: %zu KiB (%lx - %lx)\n",
+			size / 1024, start, end);
 	} else {
-		pr_info("protecting kernel .text - .rodata: %zu KiB (%p - %p)\n",
-			size / 1024, &_text, &__end_rodata);
+		pr_info("protecting kernel .text - .rodata: %zu KiB (%lx - %lx)\n",
+			size / 1024, start, end);
 	}
 
 }