Merge tag 'driver-core-4.5-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core

Pull driver core fix from Greg KH:
 "Here is one driver core, well klist, fix for 4.5-rc4.

  It fixes a problem found in the scsi device list traversal that
  probably also could be triggered by other subsystems.

  The fix has been in linux-next for a while with no reported problems"

* tag 'driver-core-4.5-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core:
  klist: fix starting point removed bug in klist iterators
diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt
index e8d25e7..ff49cf9 100644
--- a/Documentation/cgroup-v2.txt
+++ b/Documentation/cgroup-v2.txt
@@ -7,7 +7,7 @@
 conventions of cgroup v2.  It describes all userland-visible aspects
 of cgroup including core and specific controller behaviors.  All
 future changes must be reflected in this document.  Documentation for
-v1 is available under Documentation/cgroup-legacy/.
+v1 is available under Documentation/cgroup-v1/.
 
 CONTENTS
 
diff --git a/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt b/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt
index 4e8b90e..07a7509 100644
--- a/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt
+++ b/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt
@@ -8,6 +8,7 @@
 Required properties:
 - compatible: "renesas,pci-r8a7790" for the R8A7790 SoC;
 	      "renesas,pci-r8a7791" for the R8A7791 SoC;
+	      "renesas,pci-r8a7793" for the R8A7793 SoC;
 	      "renesas,pci-r8a7794" for the R8A7794 SoC;
 	      "renesas,pci-rcar-gen2" for a generic R-Car Gen2 compatible device
 
diff --git a/Documentation/devicetree/bindings/pci/rcar-pci.txt b/Documentation/devicetree/bindings/pci/rcar-pci.txt
index 558fe52..6cf9969 100644
--- a/Documentation/devicetree/bindings/pci/rcar-pci.txt
+++ b/Documentation/devicetree/bindings/pci/rcar-pci.txt
@@ -4,6 +4,7 @@
 compatible: "renesas,pcie-r8a7779" for the R8A7779 SoC;
 	    "renesas,pcie-r8a7790" for the R8A7790 SoC;
 	    "renesas,pcie-r8a7791" for the R8A7791 SoC;
+	    "renesas,pcie-r8a7793" for the R8A7793 SoC;
 	    "renesas,pcie-r8a7795" for the R8A7795 SoC;
 	    "renesas,pcie-rcar-gen2" for a generic R-Car Gen2 compatible device.
 
diff --git a/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt b/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt
index ce55c0a..4da41bf 100644
--- a/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt
+++ b/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt
@@ -30,6 +30,8 @@
  "fsl,imx-audio-sgtl5000"
  (compatible with Documentation/devicetree/bindings/sound/imx-audio-sgtl5000.txt)
 
+ "fsl,imx-audio-wm8960"
+
 Required properties:
 
   - compatible		: Contains one of entries in the compatible list.
diff --git a/Documentation/devicetree/bindings/thermal/rcar-thermal.txt b/Documentation/devicetree/bindings/thermal/rcar-thermal.txt
index 332e625..e5ee3f1 100644
--- a/Documentation/devicetree/bindings/thermal/rcar-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/rcar-thermal.txt
@@ -1,8 +1,9 @@
 * Renesas R-Car Thermal
 
 Required properties:
-- compatible		: "renesas,thermal-<soctype>", "renesas,rcar-thermal"
-			  as fallback.
+- compatible		: "renesas,thermal-<soctype>",
+			   "renesas,rcar-gen2-thermal" (with thermal-zone) or
+			   "renesas,rcar-thermal" (without thermal-zone) as fallback.
 			  Examples with soctypes are:
 			    - "renesas,thermal-r8a73a4" (R-Mobile APE6)
 			    - "renesas,thermal-r8a7779" (R-Car H1)
@@ -36,3 +37,35 @@
 		0xe61f0300 0x38>;
 	interrupts = <0 69 IRQ_TYPE_LEVEL_HIGH>;
 };
+
+Example (with thermal-zone):
+
+thermal-zones {
+	cpu_thermal: cpu-thermal {
+		polling-delay-passive	= <1000>;
+		polling-delay		= <5000>;
+
+		thermal-sensors = <&thermal>;
+
+		trips {
+			cpu-crit {
+				temperature	= <115000>;
+				hysteresis	= <0>;
+				type		= "critical";
+			};
+		};
+		cooling-maps {
+		};
+	};
+};
+
+thermal: thermal@e61f0000 {
+	compatible =	"renesas,thermal-r8a7790",
+			"renesas,rcar-gen2-thermal",
+			"renesas,rcar-thermal";
+	reg = <0 0xe61f0000 0 0x14>, <0 0xe61f0100 0 0x38>;
+	interrupts = <0 69 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&mstp5_clks R8A7790_CLK_THERMAL>;
+	power-domains = <&cpg_clocks>;
+	#thermal-sensor-cells = <0>;
+};
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 551ecf0..9a53c92 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -4235,6 +4235,17 @@
 			The default value of this parameter is determined by
 			the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT.
 
+	workqueue.debug_force_rr_cpu
+			Workqueue used to implicitly guarantee that work
+			items queued without explicit CPU specified are put
+			on the local CPU.  This guarantee is no longer true
+			and while local CPU is still preferred work items
+			may be put on foreign CPUs.  This debug option
+			forces round-robin CPU selection to flush out
+			usages which depend on the now broken guarantee.
+			When enabled, memory and cache locality will be
+			impacted.
+
 	x2apic_phys	[X86-64,APIC] Use x2apic physical mode instead of
 			default x2apic cluster mode on platforms
 			supporting x2apic.
diff --git a/MAINTAINERS b/MAINTAINERS
index 7f1fa4f..cc2f753 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2362,14 +2362,6 @@
 S:	Maintained
 N:	bcm2835
 
-BROADCOM BCM33XX MIPS ARCHITECTURE
-M:	Kevin Cernekee <cernekee@gmail.com>
-L:	linux-mips@linux-mips.org
-S:	Maintained
-F:	arch/mips/bcm3384/*
-F:	arch/mips/include/asm/mach-bcm3384/*
-F:	arch/mips/kernel/*bmips*
-
 BROADCOM BCM47XX MIPS ARCHITECTURE
 M:	Hauke Mehrtens <hauke@hauke-m.de>
 M:	Rafał Miłecki <zajec5@gmail.com>
@@ -9787,10 +9779,11 @@
 F:	drivers/scsi/be2iscsi/
 
 Emulex 10Gbps NIC BE2, BE3-R, Lancer, Skyhawk-R DRIVER
-M:	Sathya Perla <sathya.perla@avagotech.com>
-M:	Ajit Khaparde <ajit.khaparde@avagotech.com>
-M:	Padmanabh Ratnakar <padmanabh.ratnakar@avagotech.com>
-M:	Sriharsha Basavapatna <sriharsha.basavapatna@avagotech.com>
+M:	Sathya Perla <sathya.perla@broadcom.com>
+M:	Ajit Khaparde <ajit.khaparde@broadcom.com>
+M:	Padmanabh Ratnakar <padmanabh.ratnakar@broadcom.com>
+M:	Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
+M:	Somnath Kotur <somnath.kotur@broadcom.com>
 L:	netdev@vger.kernel.org
 W:	http://www.emulex.com
 S:	Supported
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 76dde9d..0655495 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -338,6 +338,19 @@
 
 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 @@
 	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	 # "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 f36c047..7359859 100644
--- a/arch/arc/configs/vdk_hs38_smp_defconfig
+++ b/arch/arc/configs/vdk_hs38_smp_defconfig
@@ -16,7 +16,7 @@
 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 7fac7d8..fdc5be5 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -349,14 +349,13 @@
 	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 258b0e5..1fc18ee 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 46f4e53..847e3bb 100644
--- a/arch/arc/include/asm/mcip.h
+++ b/arch/arc/include/asm/mcip.h
@@ -39,8 +39,8 @@
 #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 57af2f0..d426d42 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 cbfec79..b178302 100644
--- a/arch/arc/kernel/entry-arcv2.S
+++ b/arch/arc/kernel/entry-arcv2.S
@@ -211,7 +211,11 @@
 ; (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 @@
 	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 @@
 	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 0394f9f..9425263 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 @@
 {
 	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 @@
 
 	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 @@
 {
 	/* 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 bd237ac..bc771f5 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -96,13 +96,13 @@
 #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 @@
 		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 @@
 		__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 e1b8744..a7edceb 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -45,6 +45,7 @@
 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 @@
 	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 @@
 		       (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 @@
 	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 @@
 		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 dfad287..156d983 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 @@
 
 	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 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/common/icst.c b/arch/arm/common/icst.c
index 2dc6da70..d7ed252 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 @@
 
 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 @@
 
 		if (f > p->vco_min && f <= p->vco_max)
 			break;
+		i++;
 	} while (i < 8);
 
 	if (i >= 8)
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index a715174..d18d6b4 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -292,24 +292,23 @@
 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
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 2731d3b..8ec88e5 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -103,6 +103,7 @@
 	u64 irqstat;
 
 	asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat));
+	dsb(sy);
 	return irqstat;
 }
 
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 738a95f..bef6e92 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 3066328..779a587 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -127,10 +127,14 @@
 
 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/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index ca8f5a5..f0e7bdf 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -36,7 +36,11 @@
 	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 @@
 	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 648112e..4d1ac81 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 @@
 		*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 @@
 	*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 @@
 	*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 eec3598b..2e90371 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1007,10 +1007,9 @@
 		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 @@
 }
 
 /**
- * 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 @@
 }
 
 /**
- * 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/mips/Kconfig b/arch/mips/Kconfig
index 57a945e..74a3db9 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2085,7 +2085,7 @@
 
 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/boot/dts/brcm/bcm6328.dtsi b/arch/mips/boot/dts/brcm/bcm6328.dtsi
index 459b9b2..d61b161 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 4fc7ece..1a7efa8 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 a3039bb..d4bf52c 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 4274ff4..8e25016 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 0dcc9163..7e5f760 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 2f3f9fc..c739ea7 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 bee221b..5f55d0a 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 571f30f..e24d41a 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 614ee21..8b9432c 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 cefb7a5..e090fc3 100644
--- a/arch/mips/include/asm/elf.h
+++ b/arch/mips/include/asm/elf.h
@@ -227,7 +227,7 @@
 	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 @@
 	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 @@
 
 #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 9cbf383..f06f97b 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -179,6 +179,10 @@
 		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/octeon/octeon-feature.h b/arch/mips/include/asm/octeon/octeon-feature.h
index 8ebd3f57..3ed10a8 100644
--- a/arch/mips/include/asm/octeon/octeon-feature.h
+++ b/arch/mips/include/asm/octeon/octeon-feature.h
@@ -128,7 +128,8 @@
 	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 3f832c3..041153f 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -45,7 +45,7 @@
  * 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 a71da57..eebf395 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 6499d93..47bc45a 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -101,10 +101,8 @@
 	/* 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 90f03a7..3129795 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 1188e00..1b992c6 100644
--- a/arch/mips/kernel/binfmt_elfn32.c
+++ b/arch/mips/kernel/binfmt_elfn32.c
@@ -35,7 +35,7 @@
 	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 9287678..abd3aff 100644
--- a/arch/mips/kernel/binfmt_elfo32.c
+++ b/arch/mips/kernel/binfmt_elfo32.c
@@ -47,7 +47,7 @@
 	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 f2975d4..eddd5fd 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -65,12 +65,10 @@
 	status = regs->cp0_status & ~(ST0_CU0|ST0_CU1|ST0_FR|KU_MASK);
 	status |= KU_USER;
 	regs->cp0_status = status;
-	clear_used_math();
-	clear_fpu_owner();
-	init_dsp();
-	clear_thread_flag(TIF_USEDMSA);
+	lose_fpu(0);
 	clear_thread_flag(TIF_MSA_CTX_LIVE);
-	disable_msa();
+	clear_used_math();
+	init_dsp();
 	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 2d23c83..a563174 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -595,3 +595,4 @@
 	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 deac633..2b2dc14 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -433,4 +433,5 @@
 	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 5a69eb4..2bf5c85 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -423,4 +423,5 @@
 	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 e4b6d7c..c5b759e 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -578,4 +578,5 @@
 	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 569a7d5..5fdaf8b 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -782,6 +782,7 @@
 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 bafcb7a..ae790c5 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -663,7 +663,7 @@
 	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 @@
 	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 @@
 		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 3bd0597..2496475 100644
--- a/arch/mips/mm/sc-mips.c
+++ b/arch/mips/mm/sc-mips.c
@@ -181,10 +181,6 @@
 	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 @@
 	/* 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 571148c..dc2c521 100644
--- a/arch/mips/mti-malta/malta-init.c
+++ b/arch/mips/mti-malta/malta-init.c
@@ -293,7 +293,6 @@
 	console_config();
 #endif
 	/* Early detection of CMP support */
-	mips_cm_probe();
 	mips_cpc_probe();
 
 	if (!register_cps_smp_ops())
@@ -304,10 +303,3 @@
 		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 a009ee4..1ae932c2 100644
--- a/arch/mips/pci/pci-mt7620.c
+++ b/arch/mips/pci/pci-mt7620.c
@@ -297,12 +297,12 @@
 		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/x86/Kconfig b/arch/x86/Kconfig
index 9af2e63..ab2ed53 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -475,6 +475,7 @@
 	depends on X86_64
 	depends on X86_EXTENDED_PLATFORM
 	depends on NUMA
+	depends on EFI
 	depends on X86_X2APIC
 	depends on PCI
 	---help---
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 2d5a50c..20c11d1 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -766,7 +766,7 @@
  * 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/mm/numa.c b/arch/x86/mm/numa.c
index c3b3f65..d04f809 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -469,7 +469,7 @@
 {
 	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/block/blk-core.c b/block/blk-core.c
index ab51685..b83d297 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2455,14 +2455,16 @@
 
 			rq = NULL;
 			break;
-		} else if (ret == BLKPREP_KILL) {
+		} else if (ret == BLKPREP_KILL || ret == BLKPREP_INVALID) {
+			int err = (ret == BLKPREP_INVALID) ? -EREMOTEIO : -EIO;
+
 			rq->cmd_flags |= REQ_QUIET;
 			/*
 			 * Mark this request as started so we don't trigger
 			 * any debug logic in the end I/O path.
 			 */
 			blk_start_request(rq);
-			__blk_end_request_all(rq, -EIO);
+			__blk_end_request_all(rq, err);
 		} else {
 			printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
 			break;
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 38c1aa8..28556fc 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -65,18 +65,10 @@
 	struct skcipher_async_rsgl first_sgl;
 	struct list_head list;
 	struct scatterlist *tsg;
-	char iv[];
+	atomic_t *inflight;
+	struct skcipher_request req;
 };
 
-#define GET_SREQ(areq, ctx) (struct skcipher_async_req *)((char *)areq + \
-	crypto_skcipher_reqsize(crypto_skcipher_reqtfm(&ctx->req)))
-
-#define GET_REQ_SIZE(ctx) \
-	crypto_skcipher_reqsize(crypto_skcipher_reqtfm(&ctx->req))
-
-#define GET_IV_SIZE(ctx) \
-	crypto_skcipher_ivsize(crypto_skcipher_reqtfm(&ctx->req))
-
 #define MAX_SGL_ENTS ((4096 - sizeof(struct skcipher_sg_list)) / \
 		      sizeof(struct scatterlist) - 1)
 
@@ -102,15 +94,12 @@
 
 static void skcipher_async_cb(struct crypto_async_request *req, int err)
 {
-	struct sock *sk = req->data;
-	struct alg_sock *ask = alg_sk(sk);
-	struct skcipher_ctx *ctx = ask->private;
-	struct skcipher_async_req *sreq = GET_SREQ(req, ctx);
+	struct skcipher_async_req *sreq = req->data;
 	struct kiocb *iocb = sreq->iocb;
 
-	atomic_dec(&ctx->inflight);
+	atomic_dec(sreq->inflight);
 	skcipher_free_async_sgls(sreq);
-	kfree(req);
+	kzfree(sreq);
 	iocb->ki_complete(iocb, err, err);
 }
 
@@ -306,8 +295,11 @@
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
+	struct sock *psk = ask->parent;
+	struct alg_sock *pask = alg_sk(psk);
 	struct skcipher_ctx *ctx = ask->private;
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(&ctx->req);
+	struct skcipher_tfm *skc = pask->private;
+	struct crypto_skcipher *tfm = skc->skcipher;
 	unsigned ivsize = crypto_skcipher_ivsize(tfm);
 	struct skcipher_sg_list *sgl;
 	struct af_alg_control con = {};
@@ -509,37 +501,43 @@
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
+	struct sock *psk = ask->parent;
+	struct alg_sock *pask = alg_sk(psk);
 	struct skcipher_ctx *ctx = ask->private;
+	struct skcipher_tfm *skc = pask->private;
+	struct crypto_skcipher *tfm = skc->skcipher;
 	struct skcipher_sg_list *sgl;
 	struct scatterlist *sg;
 	struct skcipher_async_req *sreq;
 	struct skcipher_request *req;
 	struct skcipher_async_rsgl *last_rsgl = NULL;
-	unsigned int txbufs = 0, len = 0, tx_nents = skcipher_all_sg_nents(ctx);
-	unsigned int reqlen = sizeof(struct skcipher_async_req) +
-				GET_REQ_SIZE(ctx) + GET_IV_SIZE(ctx);
+	unsigned int txbufs = 0, len = 0, tx_nents;
+	unsigned int reqsize = crypto_skcipher_reqsize(tfm);
+	unsigned int ivsize = crypto_skcipher_ivsize(tfm);
 	int err = -ENOMEM;
 	bool mark = false;
+	char *iv;
+
+	sreq = kzalloc(sizeof(*sreq) + reqsize + ivsize, GFP_KERNEL);
+	if (unlikely(!sreq))
+		goto out;
+
+	req = &sreq->req;
+	iv = (char *)(req + 1) + reqsize;
+	sreq->iocb = msg->msg_iocb;
+	INIT_LIST_HEAD(&sreq->list);
+	sreq->inflight = &ctx->inflight;
 
 	lock_sock(sk);
-	req = kmalloc(reqlen, GFP_KERNEL);
-	if (unlikely(!req))
-		goto unlock;
-
-	sreq = GET_SREQ(req, ctx);
-	sreq->iocb = msg->msg_iocb;
-	memset(&sreq->first_sgl, '\0', sizeof(struct skcipher_async_rsgl));
-	INIT_LIST_HEAD(&sreq->list);
+	tx_nents = skcipher_all_sg_nents(ctx);
 	sreq->tsg = kcalloc(tx_nents, sizeof(*sg), GFP_KERNEL);
-	if (unlikely(!sreq->tsg)) {
-		kfree(req);
+	if (unlikely(!sreq->tsg))
 		goto unlock;
-	}
 	sg_init_table(sreq->tsg, tx_nents);
-	memcpy(sreq->iv, ctx->iv, GET_IV_SIZE(ctx));
-	skcipher_request_set_tfm(req, crypto_skcipher_reqtfm(&ctx->req));
-	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
-				      skcipher_async_cb, sk);
+	memcpy(iv, ctx->iv, ivsize);
+	skcipher_request_set_tfm(req, tfm);
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP,
+				      skcipher_async_cb, sreq);
 
 	while (iov_iter_count(&msg->msg_iter)) {
 		struct skcipher_async_rsgl *rsgl;
@@ -615,20 +613,22 @@
 		sg_mark_end(sreq->tsg + txbufs - 1);
 
 	skcipher_request_set_crypt(req, sreq->tsg, sreq->first_sgl.sgl.sg,
-				   len, sreq->iv);
+				   len, iv);
 	err = ctx->enc ? crypto_skcipher_encrypt(req) :
 			 crypto_skcipher_decrypt(req);
 	if (err == -EINPROGRESS) {
 		atomic_inc(&ctx->inflight);
 		err = -EIOCBQUEUED;
+		sreq = NULL;
 		goto unlock;
 	}
 free:
 	skcipher_free_async_sgls(sreq);
-	kfree(req);
 unlock:
 	skcipher_wmem_wakeup(sk);
 	release_sock(sk);
+	kzfree(sreq);
+out:
 	return err;
 }
 
@@ -637,9 +637,12 @@
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
+	struct sock *psk = ask->parent;
+	struct alg_sock *pask = alg_sk(psk);
 	struct skcipher_ctx *ctx = ask->private;
-	unsigned bs = crypto_skcipher_blocksize(crypto_skcipher_reqtfm(
-		&ctx->req));
+	struct skcipher_tfm *skc = pask->private;
+	struct crypto_skcipher *tfm = skc->skcipher;
+	unsigned bs = crypto_skcipher_blocksize(tfm);
 	struct skcipher_sg_list *sgl;
 	struct scatterlist *sg;
 	int err = -EAGAIN;
@@ -947,7 +950,8 @@
 	ask->private = ctx;
 
 	skcipher_request_set_tfm(&ctx->req, skcipher);
-	skcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+	skcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_SLEEP |
+						 CRYPTO_TFM_REQ_MAY_BACKLOG,
 				      af_alg_complete, &ctx->completion);
 
 	sk->sk_destruct = skcipher_sock_destruct;
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index 237f379..43fe85f2 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -499,6 +499,7 @@
 		if (link->dump == NULL)
 			return -EINVAL;
 
+		down_read(&crypto_alg_sem);
 		list_for_each_entry(alg, &crypto_alg_list, cra_list)
 			dump_alloc += CRYPTO_REPORT_MAXSIZE;
 
@@ -508,8 +509,11 @@
 				.done = link->done,
 				.min_dump_alloc = dump_alloc,
 			};
-			return netlink_dump_start(crypto_nlsk, skb, nlh, &c);
+			err = netlink_dump_start(crypto_nlsk, skb, nlh, &c);
 		}
+		up_read(&crypto_alg_sem);
+
+		return err;
 	}
 
 	err = nlmsg_parse(nlh, crypto_msg_min[type], attrs, CRYPTOCFGA_MAX,
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 594fcab..546a369 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -264,6 +264,26 @@
 	{ PCI_VDEVICE(INTEL, 0x3b2b), board_ahci }, /* PCH RAID */
 	{ PCI_VDEVICE(INTEL, 0x3b2c), board_ahci }, /* PCH RAID */
 	{ PCI_VDEVICE(INTEL, 0x3b2f), board_ahci }, /* PCH AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b0), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b1), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b2), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b3), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b4), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b5), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b6), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b7), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19bE), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19bF), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c0), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c1), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c2), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c3), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c4), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c5), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c6), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c7), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19cE), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19cF), board_ahci }, /* DNV AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1c02), board_ahci }, /* CPT AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1c03), board_ahci }, /* CPT AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1c04), board_ahci }, /* CPT RAID */
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index a4faa43..a44c75d 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -250,6 +250,7 @@
 	AHCI_HFLAG_MULTI_MSI		= 0,
 	AHCI_HFLAG_MULTI_MSIX		= 0,
 #endif
+	AHCI_HFLAG_WAKE_BEFORE_STOP	= (1 << 22), /* wake before DMA stop */
 
 	/* ap->flags bits */
 
diff --git a/drivers/ata/ahci_brcmstb.c b/drivers/ata/ahci_brcmstb.c
index b36cae2..e87bcec 100644
--- a/drivers/ata/ahci_brcmstb.c
+++ b/drivers/ata/ahci_brcmstb.c
@@ -317,6 +317,7 @@
 	if (IS_ERR(hpriv))
 		return PTR_ERR(hpriv);
 	hpriv->plat_data = priv;
+	hpriv->flags = AHCI_HFLAG_WAKE_BEFORE_STOP;
 
 	brcm_sata_alpm_init(hpriv);
 
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index d61740e..4029679 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -496,8 +496,8 @@
 		}
 	}
 
-	/* fabricate port_map from cap.nr_ports */
-	if (!port_map) {
+	/* fabricate port_map from cap.nr_ports for < AHCI 1.3 */
+	if (!port_map && vers < 0x10300) {
 		port_map = (1 << ahci_nr_ports(cap)) - 1;
 		dev_warn(dev, "forcing PORTS_IMPL to 0x%x\n", port_map);
 
@@ -593,8 +593,22 @@
 int ahci_stop_engine(struct ata_port *ap)
 {
 	void __iomem *port_mmio = ahci_port_base(ap);
+	struct ahci_host_priv *hpriv = ap->host->private_data;
 	u32 tmp;
 
+	/*
+	 * On some controllers, stopping a port's DMA engine while the port
+	 * is in ALPM state (partial or slumber) results in failures on
+	 * subsequent DMA engine starts.  For those controllers, put the
+	 * port back in active state before stopping its DMA engine.
+	 */
+	if ((hpriv->flags & AHCI_HFLAG_WAKE_BEFORE_STOP) &&
+	    (ap->link.lpm_policy > ATA_LPM_MAX_POWER) &&
+	    ahci_set_lpm(&ap->link, ATA_LPM_MAX_POWER, ATA_LPM_WAKE_ONLY)) {
+		dev_err(ap->host->dev, "Failed to wake up port before engine stop\n");
+		return -EIO;
+	}
+
 	tmp = readl(port_mmio + PORT_CMD);
 
 	/* check if the HBA is idle */
@@ -689,6 +703,9 @@
 	void __iomem *port_mmio = ahci_port_base(ap);
 
 	if (policy != ATA_LPM_MAX_POWER) {
+		/* wakeup flag only applies to the max power policy */
+		hints &= ~ATA_LPM_WAKE_ONLY;
+
 		/*
 		 * Disable interrupts on Phy Ready. This keeps us from
 		 * getting woken up due to spurious phy ready
@@ -704,7 +721,8 @@
 		u32 cmd = readl(port_mmio + PORT_CMD);
 
 		if (policy == ATA_LPM_MAX_POWER || !(hints & ATA_LPM_HIPM)) {
-			cmd &= ~(PORT_CMD_ASP | PORT_CMD_ALPE);
+			if (!(hints & ATA_LPM_WAKE_ONLY))
+				cmd &= ~(PORT_CMD_ASP | PORT_CMD_ALPE);
 			cmd |= PORT_CMD_ICC_ACTIVE;
 
 			writel(cmd, port_mmio + PORT_CMD);
@@ -712,6 +730,9 @@
 
 			/* wait 10ms to be sure we've come out of LPM state */
 			ata_msleep(ap, 10);
+
+			if (hints & ATA_LPM_WAKE_ONLY)
+				return 0;
 		} else {
 			cmd |= PORT_CMD_ALPE;
 			if (policy == ATA_LPM_MIN_POWER)
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index cbb7471..55e257c 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4125,6 +4125,7 @@
 	{ "SAMSUNG CD-ROM SN-124", "N001",	ATA_HORKAGE_NODMA },
 	{ "Seagate STT20000A", NULL,		ATA_HORKAGE_NODMA },
 	{ " 2GB ATA Flash Disk", "ADMA428M",	ATA_HORKAGE_NODMA },
+	{ "VRFDFC22048UCHC-TE*", NULL,		ATA_HORKAGE_NODMA },
 	/* Odd clown on sil3726/4726 PMPs */
 	{ "Config  Disk",	NULL,		ATA_HORKAGE_DISABLE },
 
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index cdf6215..051b615 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -997,12 +997,9 @@
 static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq)
 {
 	struct ata_port *ap = qc->ap;
-	unsigned long flags;
 
 	if (ap->ops->error_handler) {
 		if (in_wq) {
-			spin_lock_irqsave(ap->lock, flags);
-
 			/* EH might have kicked in while host lock is
 			 * released.
 			 */
@@ -1014,8 +1011,6 @@
 				} else
 					ata_port_freeze(ap);
 			}
-
-			spin_unlock_irqrestore(ap->lock, flags);
 		} else {
 			if (likely(!(qc->err_mask & AC_ERR_HSM)))
 				ata_qc_complete(qc);
@@ -1024,10 +1019,8 @@
 		}
 	} else {
 		if (in_wq) {
-			spin_lock_irqsave(ap->lock, flags);
 			ata_sff_irq_on(ap);
 			ata_qc_complete(qc);
-			spin_unlock_irqrestore(ap->lock, flags);
 		} else
 			ata_qc_complete(qc);
 	}
@@ -1048,9 +1041,10 @@
 {
 	struct ata_link *link = qc->dev->link;
 	struct ata_eh_info *ehi = &link->eh_info;
-	unsigned long flags = 0;
 	int poll_next;
 
+	lockdep_assert_held(ap->lock);
+
 	WARN_ON_ONCE((qc->flags & ATA_QCFLAG_ACTIVE) == 0);
 
 	/* Make sure ata_sff_qc_issue() does not throw things
@@ -1112,14 +1106,6 @@
 			}
 		}
 
-		/* Send the CDB (atapi) or the first data block (ata pio out).
-		 * During the state transition, interrupt handler shouldn't
-		 * be invoked before the data transfer is complete and
-		 * hsm_task_state is changed. Hence, the following locking.
-		 */
-		if (in_wq)
-			spin_lock_irqsave(ap->lock, flags);
-
 		if (qc->tf.protocol == ATA_PROT_PIO) {
 			/* PIO data out protocol.
 			 * send first data block.
@@ -1135,9 +1121,6 @@
 			/* send CDB */
 			atapi_send_cdb(ap, qc);
 
-		if (in_wq)
-			spin_unlock_irqrestore(ap->lock, flags);
-
 		/* if polling, ata_sff_pio_task() handles the rest.
 		 * otherwise, interrupt handler takes over from here.
 		 */
@@ -1296,7 +1279,8 @@
 		break;
 	default:
 		poll_next = 0;
-		BUG();
+		WARN(true, "ata%d: SFF host state machine in invalid state %d",
+		     ap->print_id, ap->hsm_task_state);
 	}
 
 	return poll_next;
@@ -1361,12 +1345,14 @@
 	u8 status;
 	int poll_next;
 
+	spin_lock_irq(ap->lock);
+
 	BUG_ON(ap->sff_pio_task_link == NULL);
 	/* qc can be NULL if timeout occurred */
 	qc = ata_qc_from_tag(ap, link->active_tag);
 	if (!qc) {
 		ap->sff_pio_task_link = NULL;
-		return;
+		goto out_unlock;
 	}
 
 fsm_start:
@@ -1381,11 +1367,14 @@
 	 */
 	status = ata_sff_busy_wait(ap, ATA_BUSY, 5);
 	if (status & ATA_BUSY) {
+		spin_unlock_irq(ap->lock);
 		ata_msleep(ap, 2);
+		spin_lock_irq(ap->lock);
+
 		status = ata_sff_busy_wait(ap, ATA_BUSY, 10);
 		if (status & ATA_BUSY) {
 			ata_sff_queue_pio_task(link, ATA_SHORT_PAUSE);
-			return;
+			goto out_unlock;
 		}
 	}
 
@@ -1402,6 +1391,8 @@
 	 */
 	if (poll_next)
 		goto fsm_start;
+out_unlock:
+	spin_unlock_irq(ap->lock);
 }
 
 /**
diff --git a/drivers/base/component.c b/drivers/base/component.c
index 89f5cf68..04a1582 100644
--- a/drivers/base/component.c
+++ b/drivers/base/component.c
@@ -206,6 +206,8 @@
 		if (mc->release)
 			mc->release(master, mc->data);
 	}
+
+	kfree(match->compare);
 }
 
 static void devm_component_match_release(struct device *dev, void *res)
@@ -221,14 +223,14 @@
 	if (match->alloc == num)
 		return 0;
 
-	new = devm_kmalloc_array(dev, num, sizeof(*new), GFP_KERNEL);
+	new = kmalloc_array(num, sizeof(*new), GFP_KERNEL);
 	if (!new)
 		return -ENOMEM;
 
 	if (match->compare) {
 		memcpy(new, match->compare, sizeof(*new) *
 					    min(match->num, num));
-		devm_kfree(dev, match->compare);
+		kfree(match->compare);
 	}
 	match->compare = new;
 	match->alloc = num;
@@ -283,6 +285,24 @@
 }
 EXPORT_SYMBOL(component_match_add_release);
 
+static void free_master(struct master *master)
+{
+	struct component_match *match = master->match;
+	int i;
+
+	list_del(&master->node);
+
+	if (match) {
+		for (i = 0; i < match->num; i++) {
+			struct component *c = match->compare[i].component;
+			if (c)
+				c->master = NULL;
+		}
+	}
+
+	kfree(master);
+}
+
 int component_master_add_with_match(struct device *dev,
 	const struct component_master_ops *ops,
 	struct component_match *match)
@@ -309,11 +329,9 @@
 
 	ret = try_to_bring_up_master(master, NULL);
 
-	if (ret < 0) {
-		/* Delete off the list if we weren't successful */
-		list_del(&master->node);
-		kfree(master);
-	}
+	if (ret < 0)
+		free_master(master);
+
 	mutex_unlock(&component_mutex);
 
 	return ret < 0 ? ret : 0;
@@ -324,25 +342,12 @@
 	const struct component_master_ops *ops)
 {
 	struct master *master;
-	int i;
 
 	mutex_lock(&component_mutex);
 	master = __master_find(dev, ops);
 	if (master) {
-		struct component_match *match = master->match;
-
 		take_down_master(master);
-
-		list_del(&master->node);
-
-		if (match) {
-			for (i = 0; i < match->num; i++) {
-				struct component *c = match->compare[i].component;
-				if (c)
-					c->master = NULL;
-			}
-		}
-		kfree(master);
+		free_master(master);
 	}
 	mutex_unlock(&component_mutex);
 }
@@ -486,6 +491,8 @@
 
 	ret = try_to_bring_up_masters(component);
 	if (ret < 0) {
+		if (component->master)
+			remove_component(component->master, component);
 		list_del(&component->node);
 
 		kfree(component);
diff --git a/drivers/base/regmap/regmap-mmio.c b/drivers/base/regmap/regmap-mmio.c
index 8812bfb..eea5156 100644
--- a/drivers/base/regmap/regmap-mmio.c
+++ b/drivers/base/regmap/regmap-mmio.c
@@ -133,17 +133,17 @@
 	while (val_size) {
 		switch (ctx->val_bytes) {
 		case 1:
-			__raw_writeb(*(u8 *)val, ctx->regs + offset);
+			writeb(*(u8 *)val, ctx->regs + offset);
 			break;
 		case 2:
-			__raw_writew(*(u16 *)val, ctx->regs + offset);
+			writew(*(u16 *)val, ctx->regs + offset);
 			break;
 		case 4:
-			__raw_writel(*(u32 *)val, ctx->regs + offset);
+			writel(*(u32 *)val, ctx->regs + offset);
 			break;
 #ifdef CONFIG_64BIT
 		case 8:
-			__raw_writeq(*(u64 *)val, ctx->regs + offset);
+			writeq(*(u64 *)val, ctx->regs + offset);
 			break;
 #endif
 		default:
@@ -193,17 +193,17 @@
 	while (val_size) {
 		switch (ctx->val_bytes) {
 		case 1:
-			*(u8 *)val = __raw_readb(ctx->regs + offset);
+			*(u8 *)val = readb(ctx->regs + offset);
 			break;
 		case 2:
-			*(u16 *)val = __raw_readw(ctx->regs + offset);
+			*(u16 *)val = readw(ctx->regs + offset);
 			break;
 		case 4:
-			*(u32 *)val = __raw_readl(ctx->regs + offset);
+			*(u32 *)val = readl(ctx->regs + offset);
 			break;
 #ifdef CONFIG_64BIT
 		case 8:
-			*(u64 *)val = __raw_readq(ctx->regs + offset);
+			*(u64 *)val = readq(ctx->regs + offset);
 			break;
 #endif
 		default:
diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c
index 20de861..8bf9914 100644
--- a/drivers/crypto/atmel-sha.c
+++ b/drivers/crypto/atmel-sha.c
@@ -782,7 +782,7 @@
 	dd->flags &= ~(SHA_FLAGS_BUSY | SHA_FLAGS_FINAL | SHA_FLAGS_CPU |
 			SHA_FLAGS_DMA_READY | SHA_FLAGS_OUTPUT_READY);
 
-	clk_disable_unprepare(dd->iclk);
+	clk_disable(dd->iclk);
 
 	if (req->base.complete)
 		req->base.complete(&req->base, err);
@@ -795,7 +795,7 @@
 {
 	int err;
 
-	err = clk_prepare_enable(dd->iclk);
+	err = clk_enable(dd->iclk);
 	if (err)
 		return err;
 
@@ -822,7 +822,7 @@
 	dev_info(dd->dev,
 			"version: 0x%x\n", dd->hw_version);
 
-	clk_disable_unprepare(dd->iclk);
+	clk_disable(dd->iclk);
 }
 
 static int atmel_sha_handle_queue(struct atmel_sha_dev *dd,
@@ -1410,6 +1410,10 @@
 		goto res_err;
 	}
 
+	err = clk_prepare(sha_dd->iclk);
+	if (err)
+		goto res_err;
+
 	atmel_sha_hw_version_init(sha_dd);
 
 	atmel_sha_get_cap(sha_dd);
@@ -1421,12 +1425,12 @@
 			if (IS_ERR(pdata)) {
 				dev_err(&pdev->dev, "platform data not available\n");
 				err = PTR_ERR(pdata);
-				goto res_err;
+				goto iclk_unprepare;
 			}
 		}
 		if (!pdata->dma_slave) {
 			err = -ENXIO;
-			goto res_err;
+			goto iclk_unprepare;
 		}
 		err = atmel_sha_dma_init(sha_dd, pdata);
 		if (err)
@@ -1457,6 +1461,8 @@
 	if (sha_dd->caps.has_dma)
 		atmel_sha_dma_cleanup(sha_dd);
 err_sha_dma:
+iclk_unprepare:
+	clk_unprepare(sha_dd->iclk);
 res_err:
 	tasklet_kill(&sha_dd->done_task);
 sha_dd_err:
@@ -1483,12 +1489,7 @@
 	if (sha_dd->caps.has_dma)
 		atmel_sha_dma_cleanup(sha_dd);
 
-	iounmap(sha_dd->io_base);
-
-	clk_put(sha_dd->iclk);
-
-	if (sha_dd->irq >= 0)
-		free_irq(sha_dd->irq, sha_dd);
+	clk_unprepare(sha_dd->iclk);
 
 	return 0;
 }
diff --git a/drivers/crypto/marvell/cesa.c b/drivers/crypto/marvell/cesa.c
index 0643e33..c0656e7 100644
--- a/drivers/crypto/marvell/cesa.c
+++ b/drivers/crypto/marvell/cesa.c
@@ -306,7 +306,7 @@
 		return -ENOMEM;
 
 	dma->padding_pool = dmam_pool_create("cesa_padding", dev, 72, 1, 0);
-	if (!dma->cache_pool)
+	if (!dma->padding_pool)
 		return -ENOMEM;
 
 	cesa->dma = dma;
diff --git a/drivers/gpio/gpio-altera.c b/drivers/gpio/gpio-altera.c
index 2aeaebd..3f87a03 100644
--- a/drivers/gpio/gpio-altera.c
+++ b/drivers/gpio/gpio-altera.c
@@ -312,8 +312,8 @@
 		handle_simple_irq, IRQ_TYPE_NONE);
 
 	if (ret) {
-		dev_info(&pdev->dev, "could not add irqchip\n");
-		return ret;
+		dev_err(&pdev->dev, "could not add irqchip\n");
+		goto teardown;
 	}
 
 	gpiochip_set_chained_irqchip(&altera_gc->mmchip.gc,
@@ -326,6 +326,7 @@
 skip_irq:
 	return 0;
 teardown:
+	of_mm_gpiochip_remove(&altera_gc->mmchip);
 	pr_err("%s: registration failed with status %d\n",
 		node->full_name, ret);
 
diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c
index ec58f42..cd007a6 100644
--- a/drivers/gpio/gpio-davinci.c
+++ b/drivers/gpio/gpio-davinci.c
@@ -195,7 +195,7 @@
 static int davinci_gpio_probe(struct platform_device *pdev)
 {
 	int i, base;
-	unsigned ngpio;
+	unsigned ngpio, nbank;
 	struct davinci_gpio_controller *chips;
 	struct davinci_gpio_platform_data *pdata;
 	struct davinci_gpio_regs __iomem *regs;
@@ -224,8 +224,9 @@
 	if (WARN_ON(ARCH_NR_GPIOS < ngpio))
 		ngpio = ARCH_NR_GPIOS;
 
+	nbank = DIV_ROUND_UP(ngpio, 32);
 	chips = devm_kzalloc(dev,
-			     ngpio * sizeof(struct davinci_gpio_controller),
+			     nbank * sizeof(struct davinci_gpio_controller),
 			     GFP_KERNEL);
 	if (!chips)
 		return -ENOMEM;
@@ -511,7 +512,7 @@
 			return irq;
 		}
 
-		irq_domain = irq_domain_add_legacy(NULL, ngpio, irq, 0,
+		irq_domain = irq_domain_add_legacy(dev->of_node, ngpio, irq, 0,
 							&davinci_gpio_irq_ops,
 							chips);
 		if (!irq_domain) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 82edf95..5e7770f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -87,6 +87,8 @@
 extern int amdgpu_sched_hw_submission;
 extern int amdgpu_enable_semaphores;
 extern int amdgpu_powerplay;
+extern unsigned amdgpu_pcie_gen_cap;
+extern unsigned amdgpu_pcie_lane_cap;
 
 #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS	        3000
 #define AMDGPU_MAX_USEC_TIMEOUT			100000	/* 100 ms */
@@ -132,47 +134,6 @@
 #define AMDGPU_RESET_VCE			(1 << 13)
 #define AMDGPU_RESET_VCE1			(1 << 14)
 
-/* CG block flags */
-#define AMDGPU_CG_BLOCK_GFX			(1 << 0)
-#define AMDGPU_CG_BLOCK_MC			(1 << 1)
-#define AMDGPU_CG_BLOCK_SDMA			(1 << 2)
-#define AMDGPU_CG_BLOCK_UVD			(1 << 3)
-#define AMDGPU_CG_BLOCK_VCE			(1 << 4)
-#define AMDGPU_CG_BLOCK_HDP			(1 << 5)
-#define AMDGPU_CG_BLOCK_BIF			(1 << 6)
-
-/* CG flags */
-#define AMDGPU_CG_SUPPORT_GFX_MGCG		(1 << 0)
-#define AMDGPU_CG_SUPPORT_GFX_MGLS		(1 << 1)
-#define AMDGPU_CG_SUPPORT_GFX_CGCG		(1 << 2)
-#define AMDGPU_CG_SUPPORT_GFX_CGLS		(1 << 3)
-#define AMDGPU_CG_SUPPORT_GFX_CGTS		(1 << 4)
-#define AMDGPU_CG_SUPPORT_GFX_CGTS_LS		(1 << 5)
-#define AMDGPU_CG_SUPPORT_GFX_CP_LS		(1 << 6)
-#define AMDGPU_CG_SUPPORT_GFX_RLC_LS		(1 << 7)
-#define AMDGPU_CG_SUPPORT_MC_LS			(1 << 8)
-#define AMDGPU_CG_SUPPORT_MC_MGCG		(1 << 9)
-#define AMDGPU_CG_SUPPORT_SDMA_LS		(1 << 10)
-#define AMDGPU_CG_SUPPORT_SDMA_MGCG		(1 << 11)
-#define AMDGPU_CG_SUPPORT_BIF_LS		(1 << 12)
-#define AMDGPU_CG_SUPPORT_UVD_MGCG		(1 << 13)
-#define AMDGPU_CG_SUPPORT_VCE_MGCG		(1 << 14)
-#define AMDGPU_CG_SUPPORT_HDP_LS		(1 << 15)
-#define AMDGPU_CG_SUPPORT_HDP_MGCG		(1 << 16)
-
-/* PG flags */
-#define AMDGPU_PG_SUPPORT_GFX_PG		(1 << 0)
-#define AMDGPU_PG_SUPPORT_GFX_SMG		(1 << 1)
-#define AMDGPU_PG_SUPPORT_GFX_DMG		(1 << 2)
-#define AMDGPU_PG_SUPPORT_UVD			(1 << 3)
-#define AMDGPU_PG_SUPPORT_VCE			(1 << 4)
-#define AMDGPU_PG_SUPPORT_CP			(1 << 5)
-#define AMDGPU_PG_SUPPORT_GDS			(1 << 6)
-#define AMDGPU_PG_SUPPORT_RLC_SMU_HS		(1 << 7)
-#define AMDGPU_PG_SUPPORT_SDMA			(1 << 8)
-#define AMDGPU_PG_SUPPORT_ACP			(1 << 9)
-#define AMDGPU_PG_SUPPORT_SAMU			(1 << 10)
-
 /* GFX current status */
 #define AMDGPU_GFX_NORMAL_MODE			0x00000000L
 #define AMDGPU_GFX_SAFE_MODE			0x00000001L
@@ -606,8 +567,6 @@
 	uint32_t		align;
 };
 
-struct amdgpu_sa_bo;
-
 /* sub-allocation buffer */
 struct amdgpu_sa_bo {
 	struct list_head		olist;
@@ -2360,6 +2319,8 @@
 int amdgpu_ttm_tt_set_userptr(struct ttm_tt *ttm, uint64_t addr,
 				     uint32_t flags);
 bool amdgpu_ttm_tt_has_userptr(struct ttm_tt *ttm);
+bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
+				  unsigned long end);
 bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm);
 uint32_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm,
 				 struct ttm_mem_reg *mem);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index a081dda..7a4b101 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -795,6 +795,12 @@
 	case CGS_SYSTEM_INFO_PCIE_MLW:
 		sys_info->value = adev->pm.pcie_mlw_mask;
 		break;
+	case CGS_SYSTEM_INFO_CG_FLAGS:
+		sys_info->value = adev->cg_flags;
+		break;
+	case CGS_SYSTEM_INFO_PG_FLAGS:
+		sys_info->value = adev->pg_flags;
+		break;
 	default:
 		return -ENODEV;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6553146..51bfc11 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1795,15 +1795,20 @@
 	}
 
 	/* post card */
-	amdgpu_atom_asic_init(adev->mode_info.atom_context);
+	if (!amdgpu_card_posted(adev))
+		amdgpu_atom_asic_init(adev->mode_info.atom_context);
 
 	r = amdgpu_resume(adev);
+	if (r)
+		DRM_ERROR("amdgpu_resume failed (%d).\n", r);
 
 	amdgpu_fence_driver_resume(adev);
 
-	r = amdgpu_ib_ring_tests(adev);
-	if (r)
-		DRM_ERROR("ib ring test failed (%d).\n", r);
+	if (resume) {
+		r = amdgpu_ib_ring_tests(adev);
+		if (r)
+			DRM_ERROR("ib ring test failed (%d).\n", r);
+	}
 
 	r = amdgpu_late_init(adev);
 	if (r)
@@ -1933,80 +1938,97 @@
 	return r;
 }
 
+#define AMDGPU_DEFAULT_PCIE_GEN_MASK 0x30007  /* gen: chipset 1/2, asic 1/2/3 */
+#define AMDGPU_DEFAULT_PCIE_MLW_MASK 0x2f0000 /* 1/2/4/8/16 lanes */
+
 void amdgpu_get_pcie_info(struct amdgpu_device *adev)
 {
 	u32 mask;
 	int ret;
 
-	if (pci_is_root_bus(adev->pdev->bus))
+	if (amdgpu_pcie_gen_cap)
+		adev->pm.pcie_gen_mask = amdgpu_pcie_gen_cap;
+
+	if (amdgpu_pcie_lane_cap)
+		adev->pm.pcie_mlw_mask = amdgpu_pcie_lane_cap;
+
+	/* covers APUs as well */
+	if (pci_is_root_bus(adev->pdev->bus)) {
+		if (adev->pm.pcie_gen_mask == 0)
+			adev->pm.pcie_gen_mask = AMDGPU_DEFAULT_PCIE_GEN_MASK;
+		if (adev->pm.pcie_mlw_mask == 0)
+			adev->pm.pcie_mlw_mask = AMDGPU_DEFAULT_PCIE_MLW_MASK;
 		return;
-
-	if (amdgpu_pcie_gen2 == 0)
-		return;
-
-	if (adev->flags & AMD_IS_APU)
-		return;
-
-	ret = drm_pcie_get_speed_cap_mask(adev->ddev, &mask);
-	if (!ret) {
-		adev->pm.pcie_gen_mask = (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
-					  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 |
-					  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3);
-
-		if (mask & DRM_PCIE_SPEED_25)
-			adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1;
-		if (mask & DRM_PCIE_SPEED_50)
-			adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2;
-		if (mask & DRM_PCIE_SPEED_80)
-			adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3;
 	}
-	ret = drm_pcie_get_max_link_width(adev->ddev, &mask);
-	if (!ret) {
-		switch (mask) {
-		case 32:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 16:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 12:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 8:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 4:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 2:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 1:
-			adev->pm.pcie_mlw_mask = CAIL_PCIE_LINK_WIDTH_SUPPORT_X1;
-			break;
-		default:
-			break;
+
+	if (adev->pm.pcie_gen_mask == 0) {
+		ret = drm_pcie_get_speed_cap_mask(adev->ddev, &mask);
+		if (!ret) {
+			adev->pm.pcie_gen_mask = (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+						  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 |
+						  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3);
+
+			if (mask & DRM_PCIE_SPEED_25)
+				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1;
+			if (mask & DRM_PCIE_SPEED_50)
+				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2;
+			if (mask & DRM_PCIE_SPEED_80)
+				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3;
+		} else {
+			adev->pm.pcie_gen_mask = AMDGPU_DEFAULT_PCIE_GEN_MASK;
+		}
+	}
+	if (adev->pm.pcie_mlw_mask == 0) {
+		ret = drm_pcie_get_max_link_width(adev->ddev, &mask);
+		if (!ret) {
+			switch (mask) {
+			case 32:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 16:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 12:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 8:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 4:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 2:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 1:
+				adev->pm.pcie_mlw_mask = CAIL_PCIE_LINK_WIDTH_SUPPORT_X1;
+				break;
+			default:
+				break;
+			}
+		} else {
+			adev->pm.pcie_mlw_mask = AMDGPU_DEFAULT_PCIE_MLW_MASK;
 		}
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 9c1af89..9ef1db8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -83,6 +83,8 @@
 int amdgpu_sched_hw_submission = 2;
 int amdgpu_enable_semaphores = 0;
 int amdgpu_powerplay = -1;
+unsigned amdgpu_pcie_gen_cap = 0;
+unsigned amdgpu_pcie_lane_cap = 0;
 
 MODULE_PARM_DESC(vramlimit, "Restrict VRAM for testing, in megabytes");
 module_param_named(vramlimit, amdgpu_vram_limit, int, 0600);
@@ -170,6 +172,12 @@
 module_param_named(powerplay, amdgpu_powerplay, int, 0444);
 #endif
 
+MODULE_PARM_DESC(pcie_gen_cap, "PCIE Gen Caps (0: autodetect (default))");
+module_param_named(pcie_gen_cap, amdgpu_pcie_gen_cap, uint, 0444);
+
+MODULE_PARM_DESC(pcie_lane_cap, "PCIE Lane Caps (0: autodetect (default))");
+module_param_named(pcie_lane_cap, amdgpu_pcie_lane_cap, uint, 0444);
+
 static struct pci_device_id pciidlist[] = {
 #ifdef CONFIG_DRM_AMDGPU_CIK
 	/* Kaveri */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index b1969f2..d4e2780 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -142,7 +142,8 @@
 
 		list_for_each_entry(bo, &node->bos, mn_list) {
 
-			if (!bo->tbo.ttm || bo->tbo.ttm->state != tt_bound)
+			if (!amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm, start,
+							  end))
 				continue;
 
 			r = amdgpu_bo_reserve(bo, true);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
index 8b88edb..ca72a2e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
@@ -354,12 +354,15 @@
 
 		for (i = 0, count = 0; i < AMDGPU_MAX_RINGS; ++i)
 			if (fences[i])
-				fences[count++] = fences[i];
+				fences[count++] = fence_get(fences[i]);
 
 		if (count) {
 			spin_unlock(&sa_manager->wq.lock);
 			t = fence_wait_any_timeout(fences, count, false,
 						   MAX_SCHEDULE_TIMEOUT);
+			for (i = 0; i < count; ++i)
+				fence_put(fences[i]);
+
 			r = (t > 0) ? 0 : t;
 			spin_lock(&sa_manager->wq.lock);
 		} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 55cf05e..6442a06 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -783,6 +783,25 @@
 	return !!gtt->userptr;
 }
 
+bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
+				  unsigned long end)
+{
+	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	unsigned long size;
+
+	if (gtt == NULL)
+		return false;
+
+	if (gtt->ttm.ttm.state != tt_bound || !gtt->userptr)
+		return false;
+
+	size = (unsigned long)gtt->ttm.ttm.num_pages * PAGE_SIZE;
+	if (gtt->userptr > end || gtt->userptr + size <= start)
+		return false;
+
+	return true;
+}
+
 bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm)
 {
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index 8b4731d..474ca02 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -31,6 +31,7 @@
 #include "ci_dpm.h"
 #include "gfx_v7_0.h"
 #include "atom.h"
+#include "amd_pcie.h"
 #include <linux/seq_file.h>
 
 #include "smu/smu_7_0_1_d.h"
@@ -5835,18 +5836,16 @@
 	u8 frev, crev;
 	struct ci_power_info *pi;
 	int ret;
-	u32 mask;
 
 	pi = kzalloc(sizeof(struct ci_power_info), GFP_KERNEL);
 	if (pi == NULL)
 		return -ENOMEM;
 	adev->pm.dpm.priv = pi;
 
-	ret = drm_pcie_get_speed_cap_mask(adev->ddev, &mask);
-	if (ret)
-		pi->sys_pcie_mask = 0;
-	else
-		pi->sys_pcie_mask = mask;
+	pi->sys_pcie_mask =
+		(adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_MASK) >>
+		CAIL_PCIE_LINK_SPEED_SUPPORT_SHIFT;
+
 	pi->force_pcie_gen = AMDGPU_PCIE_GEN_INVALID;
 
 	pi->pcie_gen_performance.max = AMDGPU_PCIE_GEN1;
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index fd9c958..155965e 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1762,6 +1762,9 @@
 	if (amdgpu_aspm == 0)
 		return;
 
+	if (pci_is_root_bus(adev->pdev->bus))
+		return;
+
 	/* XXX double check APUs */
 	if (adev->flags & AMD_IS_APU)
 		return;
@@ -2332,72 +2335,72 @@
 	switch (adev->asic_type) {
 	case CHIP_BONAIRE:
 		adev->cg_flags =
-			AMDGPU_CG_SUPPORT_GFX_MGCG |
-			AMDGPU_CG_SUPPORT_GFX_MGLS |
-			/*AMDGPU_CG_SUPPORT_GFX_CGCG |*/
-			AMDGPU_CG_SUPPORT_GFX_CGLS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS_LS |
-			AMDGPU_CG_SUPPORT_GFX_CP_LS |
-			AMDGPU_CG_SUPPORT_MC_LS |
-			AMDGPU_CG_SUPPORT_MC_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_LS |
-			AMDGPU_CG_SUPPORT_BIF_LS |
-			AMDGPU_CG_SUPPORT_VCE_MGCG |
-			AMDGPU_CG_SUPPORT_UVD_MGCG |
-			AMDGPU_CG_SUPPORT_HDP_LS |
-			AMDGPU_CG_SUPPORT_HDP_MGCG;
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_MGLS |
+			/*AMD_CG_SUPPORT_GFX_CGCG |*/
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_CGTS |
+			AMD_CG_SUPPORT_GFX_CGTS_LS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_MC_LS |
+			AMD_CG_SUPPORT_MC_MGCG |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_VCE_MGCG |
+			AMD_CG_SUPPORT_UVD_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags = 0;
 		adev->external_rev_id = adev->rev_id + 0x14;
 		break;
 	case CHIP_HAWAII:
 		adev->cg_flags =
-			AMDGPU_CG_SUPPORT_GFX_MGCG |
-			AMDGPU_CG_SUPPORT_GFX_MGLS |
-			/*AMDGPU_CG_SUPPORT_GFX_CGCG |*/
-			AMDGPU_CG_SUPPORT_GFX_CGLS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS |
-			AMDGPU_CG_SUPPORT_GFX_CP_LS |
-			AMDGPU_CG_SUPPORT_MC_LS |
-			AMDGPU_CG_SUPPORT_MC_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_LS |
-			AMDGPU_CG_SUPPORT_BIF_LS |
-			AMDGPU_CG_SUPPORT_VCE_MGCG |
-			AMDGPU_CG_SUPPORT_UVD_MGCG |
-			AMDGPU_CG_SUPPORT_HDP_LS |
-			AMDGPU_CG_SUPPORT_HDP_MGCG;
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_MGLS |
+			/*AMD_CG_SUPPORT_GFX_CGCG |*/
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_CGTS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_MC_LS |
+			AMD_CG_SUPPORT_MC_MGCG |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_VCE_MGCG |
+			AMD_CG_SUPPORT_UVD_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags = 0;
 		adev->external_rev_id = 0x28;
 		break;
 	case CHIP_KAVERI:
 		adev->cg_flags =
-			AMDGPU_CG_SUPPORT_GFX_MGCG |
-			AMDGPU_CG_SUPPORT_GFX_MGLS |
-			/*AMDGPU_CG_SUPPORT_GFX_CGCG |*/
-			AMDGPU_CG_SUPPORT_GFX_CGLS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS_LS |
-			AMDGPU_CG_SUPPORT_GFX_CP_LS |
-			AMDGPU_CG_SUPPORT_SDMA_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_LS |
-			AMDGPU_CG_SUPPORT_BIF_LS |
-			AMDGPU_CG_SUPPORT_VCE_MGCG |
-			AMDGPU_CG_SUPPORT_UVD_MGCG |
-			AMDGPU_CG_SUPPORT_HDP_LS |
-			AMDGPU_CG_SUPPORT_HDP_MGCG;
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_MGLS |
+			/*AMD_CG_SUPPORT_GFX_CGCG |*/
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_CGTS |
+			AMD_CG_SUPPORT_GFX_CGTS_LS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_VCE_MGCG |
+			AMD_CG_SUPPORT_UVD_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags =
-			/*AMDGPU_PG_SUPPORT_GFX_PG |
-			  AMDGPU_PG_SUPPORT_GFX_SMG |
-			  AMDGPU_PG_SUPPORT_GFX_DMG |*/
-			AMDGPU_PG_SUPPORT_UVD |
-			/*AMDGPU_PG_SUPPORT_VCE |
-			  AMDGPU_PG_SUPPORT_CP |
-			  AMDGPU_PG_SUPPORT_GDS |
-			  AMDGPU_PG_SUPPORT_RLC_SMU_HS |
-			  AMDGPU_PG_SUPPORT_ACP |
-			  AMDGPU_PG_SUPPORT_SAMU |*/
+			/*AMD_PG_SUPPORT_GFX_PG |
+			  AMD_PG_SUPPORT_GFX_SMG |
+			  AMD_PG_SUPPORT_GFX_DMG |*/
+			AMD_PG_SUPPORT_UVD |
+			/*AMD_PG_SUPPORT_VCE |
+			  AMD_PG_SUPPORT_CP |
+			  AMD_PG_SUPPORT_GDS |
+			  AMD_PG_SUPPORT_RLC_SMU_HS |
+			  AMD_PG_SUPPORT_ACP |
+			  AMD_PG_SUPPORT_SAMU |*/
 			0;
 		if (adev->pdev->device == 0x1312 ||
 			adev->pdev->device == 0x1316 ||
@@ -2409,29 +2412,29 @@
 	case CHIP_KABINI:
 	case CHIP_MULLINS:
 		adev->cg_flags =
-			AMDGPU_CG_SUPPORT_GFX_MGCG |
-			AMDGPU_CG_SUPPORT_GFX_MGLS |
-			/*AMDGPU_CG_SUPPORT_GFX_CGCG |*/
-			AMDGPU_CG_SUPPORT_GFX_CGLS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS_LS |
-			AMDGPU_CG_SUPPORT_GFX_CP_LS |
-			AMDGPU_CG_SUPPORT_SDMA_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_LS |
-			AMDGPU_CG_SUPPORT_BIF_LS |
-			AMDGPU_CG_SUPPORT_VCE_MGCG |
-			AMDGPU_CG_SUPPORT_UVD_MGCG |
-			AMDGPU_CG_SUPPORT_HDP_LS |
-			AMDGPU_CG_SUPPORT_HDP_MGCG;
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_MGLS |
+			/*AMD_CG_SUPPORT_GFX_CGCG |*/
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_CGTS |
+			AMD_CG_SUPPORT_GFX_CGTS_LS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_VCE_MGCG |
+			AMD_CG_SUPPORT_UVD_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags =
-			/*AMDGPU_PG_SUPPORT_GFX_PG |
-			  AMDGPU_PG_SUPPORT_GFX_SMG | */
-			AMDGPU_PG_SUPPORT_UVD |
-			/*AMDGPU_PG_SUPPORT_VCE |
-			  AMDGPU_PG_SUPPORT_CP |
-			  AMDGPU_PG_SUPPORT_GDS |
-			  AMDGPU_PG_SUPPORT_RLC_SMU_HS |
-			  AMDGPU_PG_SUPPORT_SAMU |*/
+			/*AMD_PG_SUPPORT_GFX_PG |
+			  AMD_PG_SUPPORT_GFX_SMG | */
+			AMD_PG_SUPPORT_UVD |
+			/*AMD_PG_SUPPORT_VCE |
+			  AMD_PG_SUPPORT_CP |
+			  AMD_PG_SUPPORT_GDS |
+			  AMD_PG_SUPPORT_RLC_SMU_HS |
+			  AMD_PG_SUPPORT_SAMU |*/
 			0;
 		if (adev->asic_type == CHIP_KABINI) {
 			if (adev->rev_id == 0)
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index 5f712ce..c55ecf0 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -885,7 +885,7 @@
 {
 	u32 orig, data;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_SDMA_MGCG)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_SDMA_MGCG)) {
 		WREG32(mmSDMA0_CLK_CTRL + SDMA0_REGISTER_OFFSET, 0x00000100);
 		WREG32(mmSDMA0_CLK_CTRL + SDMA1_REGISTER_OFFSET, 0x00000100);
 	} else {
@@ -906,7 +906,7 @@
 {
 	u32 orig, data;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_SDMA_LS)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_SDMA_LS)) {
 		orig = data = RREG32(mmSDMA0_POWER_CNTL + SDMA0_REGISTER_OFFSET);
 		data |= 0x100;
 		if (orig != data)
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
index 4dd17f2..9056355 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
@@ -445,13 +445,13 @@
 	pi->gfx_pg_threshold = 500;
 	pi->caps_fps = true;
 	/* uvd */
-	pi->caps_uvd_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_UVD) ? true : false;
+	pi->caps_uvd_pg = (adev->pg_flags & AMD_PG_SUPPORT_UVD) ? true : false;
 	pi->caps_uvd_dpm = true;
 	/* vce */
-	pi->caps_vce_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_VCE) ? true : false;
+	pi->caps_vce_pg = (adev->pg_flags & AMD_PG_SUPPORT_VCE) ? true : false;
 	pi->caps_vce_dpm = true;
 	/* acp */
-	pi->caps_acp_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_ACP) ? true : false;
+	pi->caps_acp_pg = (adev->pg_flags & AMD_PG_SUPPORT_ACP) ? true : false;
 	pi->caps_acp_dpm = true;
 
 	pi->caps_stable_power_state = false;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 6c76139..7732059 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -4109,7 +4109,7 @@
 
 	orig = data = RREG32(mmRLC_CGCG_CGLS_CTRL);
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_CGCG)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG)) {
 		gfx_v7_0_enable_gui_idle_interrupt(adev, true);
 
 		tmp = gfx_v7_0_halt_rlc(adev);
@@ -4147,9 +4147,9 @@
 {
 	u32 data, orig, tmp = 0;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_MGCG)) {
-		if (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_MGLS) {
-			if (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_CP_LS) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) {
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGLS) {
+			if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CP_LS) {
 				orig = data = RREG32(mmCP_MEM_SLP_CNTL);
 				data |= CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK;
 				if (orig != data)
@@ -4176,14 +4176,14 @@
 
 		gfx_v7_0_update_rlc(adev, tmp);
 
-		if (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_CGTS) {
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGTS) {
 			orig = data = RREG32(mmCGTS_SM_CTRL_REG);
 			data &= ~CGTS_SM_CTRL_REG__SM_MODE_MASK;
 			data |= (0x2 << CGTS_SM_CTRL_REG__SM_MODE__SHIFT);
 			data |= CGTS_SM_CTRL_REG__SM_MODE_ENABLE_MASK;
 			data &= ~CGTS_SM_CTRL_REG__OVERRIDE_MASK;
-			if ((adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_MGLS) &&
-			    (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_CGTS_LS))
+			if ((adev->cg_flags & AMD_CG_SUPPORT_GFX_MGLS) &&
+			    (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGTS_LS))
 				data &= ~CGTS_SM_CTRL_REG__LS_OVERRIDE_MASK;
 			data &= ~CGTS_SM_CTRL_REG__ON_MONITOR_ADD_MASK;
 			data |= CGTS_SM_CTRL_REG__ON_MONITOR_ADD_EN_MASK;
@@ -4249,7 +4249,7 @@
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_RLC_SMU_HS))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS))
 		data |= RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PU_ENABLE_MASK;
 	else
 		data &= ~RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PU_ENABLE_MASK;
@@ -4263,7 +4263,7 @@
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_RLC_SMU_HS))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS))
 		data |= RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PD_ENABLE_MASK;
 	else
 		data &= ~RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PD_ENABLE_MASK;
@@ -4276,7 +4276,7 @@
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_CP))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_CP))
 		data &= ~0x8000;
 	else
 		data |= 0x8000;
@@ -4289,7 +4289,7 @@
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_GDS))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GDS))
 		data &= ~0x2000;
 	else
 		data |= 0x2000;
@@ -4370,7 +4370,7 @@
 {
 	u32 data, orig;
 
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_PG)) {
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)) {
 		orig = data = RREG32(mmRLC_PG_CNTL);
 		data |= RLC_PG_CNTL__GFX_POWER_GATING_ENABLE_MASK;
 		if (orig != data)
@@ -4442,7 +4442,7 @@
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_SMG))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_SMG))
 		data |= RLC_PG_CNTL__STATIC_PER_CU_PG_ENABLE_MASK;
 	else
 		data &= ~RLC_PG_CNTL__STATIC_PER_CU_PG_ENABLE_MASK;
@@ -4456,7 +4456,7 @@
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_DMG))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_DMG))
 		data |= RLC_PG_CNTL__DYN_PER_CU_PG_ENABLE_MASK;
 	else
 		data &= ~RLC_PG_CNTL__DYN_PER_CU_PG_ENABLE_MASK;
@@ -4623,15 +4623,15 @@
 
 static void gfx_v7_0_init_pg(struct amdgpu_device *adev)
 {
-	if (adev->pg_flags & (AMDGPU_PG_SUPPORT_GFX_PG |
-			      AMDGPU_PG_SUPPORT_GFX_SMG |
-			      AMDGPU_PG_SUPPORT_GFX_DMG |
-			      AMDGPU_PG_SUPPORT_CP |
-			      AMDGPU_PG_SUPPORT_GDS |
-			      AMDGPU_PG_SUPPORT_RLC_SMU_HS)) {
+	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
+			      AMD_PG_SUPPORT_GFX_SMG |
+			      AMD_PG_SUPPORT_GFX_DMG |
+			      AMD_PG_SUPPORT_CP |
+			      AMD_PG_SUPPORT_GDS |
+			      AMD_PG_SUPPORT_RLC_SMU_HS)) {
 		gfx_v7_0_enable_sclk_slowdown_on_pu(adev, true);
 		gfx_v7_0_enable_sclk_slowdown_on_pd(adev, true);
-		if (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_PG) {
+		if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG) {
 			gfx_v7_0_init_gfx_cgpg(adev);
 			gfx_v7_0_enable_cp_pg(adev, true);
 			gfx_v7_0_enable_gds_pg(adev, true);
@@ -4643,14 +4643,14 @@
 
 static void gfx_v7_0_fini_pg(struct amdgpu_device *adev)
 {
-	if (adev->pg_flags & (AMDGPU_PG_SUPPORT_GFX_PG |
-			      AMDGPU_PG_SUPPORT_GFX_SMG |
-			      AMDGPU_PG_SUPPORT_GFX_DMG |
-			      AMDGPU_PG_SUPPORT_CP |
-			      AMDGPU_PG_SUPPORT_GDS |
-			      AMDGPU_PG_SUPPORT_RLC_SMU_HS)) {
+	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
+			      AMD_PG_SUPPORT_GFX_SMG |
+			      AMD_PG_SUPPORT_GFX_DMG |
+			      AMD_PG_SUPPORT_CP |
+			      AMD_PG_SUPPORT_GDS |
+			      AMD_PG_SUPPORT_RLC_SMU_HS)) {
 		gfx_v7_0_update_gfx_pg(adev, false);
-		if (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_PG) {
+		if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG) {
 			gfx_v7_0_enable_cp_pg(adev, false);
 			gfx_v7_0_enable_gds_pg(adev, false);
 		}
@@ -5527,14 +5527,14 @@
 	if (state == AMD_PG_STATE_GATE)
 		gate = true;
 
-	if (adev->pg_flags & (AMDGPU_PG_SUPPORT_GFX_PG |
-			      AMDGPU_PG_SUPPORT_GFX_SMG |
-			      AMDGPU_PG_SUPPORT_GFX_DMG |
-			      AMDGPU_PG_SUPPORT_CP |
-			      AMDGPU_PG_SUPPORT_GDS |
-			      AMDGPU_PG_SUPPORT_RLC_SMU_HS)) {
+	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
+			      AMD_PG_SUPPORT_GFX_SMG |
+			      AMD_PG_SUPPORT_GFX_DMG |
+			      AMD_PG_SUPPORT_CP |
+			      AMD_PG_SUPPORT_GDS |
+			      AMD_PG_SUPPORT_RLC_SMU_HS)) {
 		gfx_v7_0_update_gfx_pg(adev, gate);
-		if (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_PG) {
+		if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG) {
 			gfx_v7_0_enable_cp_pg(adev, gate);
 			gfx_v7_0_enable_gds_pg(adev, gate);
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 8aa2991..b806079 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -792,7 +792,7 @@
 
 	for (i = 0; i < ARRAY_SIZE(mc_cg_registers); i++) {
 		orig = data = RREG32(mc_cg_registers[i]);
-		if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_MC_LS))
+		if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_LS))
 			data |= mc_cg_ls_en[i];
 		else
 			data &= ~mc_cg_ls_en[i];
@@ -809,7 +809,7 @@
 
 	for (i = 0; i < ARRAY_SIZE(mc_cg_registers); i++) {
 		orig = data = RREG32(mc_cg_registers[i]);
-		if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_MC_MGCG))
+		if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG))
 			data |= mc_cg_en[i];
 		else
 			data &= ~mc_cg_en[i];
@@ -825,7 +825,7 @@
 
 	orig = data = RREG32_PCIE(ixPCIE_CNTL2);
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_BIF_LS)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_BIF_LS)) {
 		data = REG_SET_FIELD(data, PCIE_CNTL2, SLV_MEM_LS_EN, 1);
 		data = REG_SET_FIELD(data, PCIE_CNTL2, MST_MEM_LS_EN, 1);
 		data = REG_SET_FIELD(data, PCIE_CNTL2, REPLAY_MEM_LS_EN, 1);
@@ -848,7 +848,7 @@
 
 	orig = data = RREG32(mmHDP_HOST_PATH_CNTL);
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_HDP_MGCG))
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_HDP_MGCG))
 		data = REG_SET_FIELD(data, HDP_HOST_PATH_CNTL, CLOCK_GATING_DIS, 0);
 	else
 		data = REG_SET_FIELD(data, HDP_HOST_PATH_CNTL, CLOCK_GATING_DIS, 1);
@@ -864,7 +864,7 @@
 
 	orig = data = RREG32(mmHDP_MEM_POWER_LS);
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_HDP_LS))
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS))
 		data = REG_SET_FIELD(data, HDP_MEM_POWER_LS, LS_ENABLE, 1);
 	else
 		data = REG_SET_FIELD(data, HDP_MEM_POWER_LS, LS_ENABLE, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
index 7e9154c..654d767 100644
--- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
@@ -2859,11 +2859,11 @@
 	pi->voltage_drop_t = 0;
 	pi->caps_sclk_throttle_low_notification = false;
 	pi->caps_fps = false; /* true? */
-	pi->caps_uvd_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_UVD) ? true : false;
+	pi->caps_uvd_pg = (adev->pg_flags & AMD_PG_SUPPORT_UVD) ? true : false;
 	pi->caps_uvd_dpm = true;
-	pi->caps_vce_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_VCE) ? true : false;
-	pi->caps_samu_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_SAMU) ? true : false;
-	pi->caps_acp_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_ACP) ? true : false;
+	pi->caps_vce_pg = (adev->pg_flags & AMD_PG_SUPPORT_VCE) ? true : false;
+	pi->caps_samu_pg = (adev->pg_flags & AMD_PG_SUPPORT_SAMU) ? true : false;
+	pi->caps_acp_pg = (adev->pg_flags & AMD_PG_SUPPORT_ACP) ? true : false;
 	pi->caps_stable_p_state = false;
 
 	ret = kv_parse_sys_info_table(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
index 5e9f73a..fbd3767 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -611,7 +611,7 @@
 {
 	u32 orig, data;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_UVD_MGCG)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG)) {
 		data = RREG32_UVD_CTX(ixUVD_CGC_MEM_CTRL);
 		data = 0xfff;
 		WREG32_UVD_CTX(ixUVD_CGC_MEM_CTRL, data);
@@ -830,6 +830,9 @@
 	bool gate = false;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG))
+		return 0;
+
 	if (state == AMD_CG_STATE_GATE)
 		gate = true;
 
@@ -848,7 +851,10 @@
 	 * revisit this when there is a cleaner line between
 	 * the smc and the hw blocks
 	 */
-	 struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_UVD))
+		return 0;
 
 	if (state == AMD_PG_STATE_GATE) {
 		uvd_v4_2_stop(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index 38864f56..57f1c5b 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
@@ -774,6 +774,11 @@
 static int uvd_v5_0_set_clockgating_state(void *handle,
 					  enum amd_clockgating_state state)
 {
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG))
+		return 0;
+
 	return 0;
 }
 
@@ -789,6 +794,9 @@
 	 */
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_UVD))
+		return 0;
+
 	if (state == AMD_PG_STATE_GATE) {
 		uvd_v5_0_stop(adev);
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 3d59139..0b365b7 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -532,7 +532,7 @@
 	uvd_v6_0_mc_resume(adev);
 
 	/* Set dynamic clock gating in S/W control mode */
-	if (adev->cg_flags & AMDGPU_CG_SUPPORT_UVD_MGCG) {
+	if (adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG) {
 		if (adev->flags & AMD_IS_APU)
 			cz_set_uvd_clock_gating_branches(adev, false);
 		else
@@ -1000,7 +1000,7 @@
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
 
-	if (!(adev->cg_flags & AMDGPU_CG_SUPPORT_UVD_MGCG))
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG))
 		return 0;
 
 	if (enable) {
@@ -1030,6 +1030,9 @@
 	 */
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_UVD))
+		return 0;
+
 	if (state == AMD_PG_STATE_GATE) {
 		uvd_v6_0_stop(adev);
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
index 52ac7a8..a822eda 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
@@ -373,7 +373,7 @@
 {
 	bool sw_cg = false;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_VCE_MGCG)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG)) {
 		if (sw_cg)
 			vce_v2_0_set_sw_cg(adev, true);
 		else
@@ -608,6 +608,9 @@
 	 */
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_VCE))
+		return 0;
+
 	if (state == AMD_PG_STATE_GATE)
 		/* XXX do we need a vce_v2_0_stop()? */
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index e99af81..d662fa9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -277,7 +277,7 @@
 		WREG32_P(mmVCE_STATUS, 0, ~1);
 
 		/* Set Clock-Gating off */
-		if (adev->cg_flags & AMDGPU_CG_SUPPORT_VCE_MGCG)
+		if (adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG)
 			vce_v3_0_set_vce_sw_clock_gating(adev, false);
 
 		if (r) {
@@ -676,7 +676,7 @@
 	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
 	int i;
 
-	if (!(adev->cg_flags & AMDGPU_CG_SUPPORT_VCE_MGCG))
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG))
 		return 0;
 
 	mutex_lock(&adev->grbm_idx_mutex);
@@ -728,6 +728,9 @@
 	 */
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_VCE))
+		return 0;
+
 	if (state == AMD_PG_STATE_GATE)
 		/* XXX do we need a vce_v3_0_stop()? */
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 89f5a1f..0d14d10 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1457,8 +1457,7 @@
 	case CHIP_STONEY:
 		adev->has_uvd = true;
 		adev->cg_flags = 0;
-		/* Disable UVD pg */
-		adev->pg_flags = /* AMDGPU_PG_SUPPORT_UVD | */AMDGPU_PG_SUPPORT_VCE;
+		adev->pg_flags = 0;
 		adev->external_rev_id = adev->rev_id + 0x1;
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index 1195d06f..dbf7e64 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -85,6 +85,38 @@
 	AMD_PG_STATE_UNGATE,
 };
 
+/* CG flags */
+#define AMD_CG_SUPPORT_GFX_MGCG			(1 << 0)
+#define AMD_CG_SUPPORT_GFX_MGLS			(1 << 1)
+#define AMD_CG_SUPPORT_GFX_CGCG			(1 << 2)
+#define AMD_CG_SUPPORT_GFX_CGLS			(1 << 3)
+#define AMD_CG_SUPPORT_GFX_CGTS			(1 << 4)
+#define AMD_CG_SUPPORT_GFX_CGTS_LS		(1 << 5)
+#define AMD_CG_SUPPORT_GFX_CP_LS		(1 << 6)
+#define AMD_CG_SUPPORT_GFX_RLC_LS		(1 << 7)
+#define AMD_CG_SUPPORT_MC_LS			(1 << 8)
+#define AMD_CG_SUPPORT_MC_MGCG			(1 << 9)
+#define AMD_CG_SUPPORT_SDMA_LS			(1 << 10)
+#define AMD_CG_SUPPORT_SDMA_MGCG		(1 << 11)
+#define AMD_CG_SUPPORT_BIF_LS			(1 << 12)
+#define AMD_CG_SUPPORT_UVD_MGCG			(1 << 13)
+#define AMD_CG_SUPPORT_VCE_MGCG			(1 << 14)
+#define AMD_CG_SUPPORT_HDP_LS			(1 << 15)
+#define AMD_CG_SUPPORT_HDP_MGCG			(1 << 16)
+
+/* PG flags */
+#define AMD_PG_SUPPORT_GFX_PG			(1 << 0)
+#define AMD_PG_SUPPORT_GFX_SMG			(1 << 1)
+#define AMD_PG_SUPPORT_GFX_DMG			(1 << 2)
+#define AMD_PG_SUPPORT_UVD			(1 << 3)
+#define AMD_PG_SUPPORT_VCE			(1 << 4)
+#define AMD_PG_SUPPORT_CP			(1 << 5)
+#define AMD_PG_SUPPORT_GDS			(1 << 6)
+#define AMD_PG_SUPPORT_RLC_SMU_HS		(1 << 7)
+#define AMD_PG_SUPPORT_SDMA			(1 << 8)
+#define AMD_PG_SUPPORT_ACP			(1 << 9)
+#define AMD_PG_SUPPORT_SAMU			(1 << 10)
+
 enum amd_pm_state_type {
 	/* not used for dpm */
 	POWER_STATE_TYPE_DEFAULT,
diff --git a/drivers/gpu/drm/amd/include/cgs_common.h b/drivers/gpu/drm/amd/include/cgs_common.h
index 713aec9..aec38fc 100644
--- a/drivers/gpu/drm/amd/include/cgs_common.h
+++ b/drivers/gpu/drm/amd/include/cgs_common.h
@@ -109,6 +109,8 @@
 	CGS_SYSTEM_INFO_ADAPTER_BDF_ID = 1,
 	CGS_SYSTEM_INFO_PCIE_GEN_INFO,
 	CGS_SYSTEM_INFO_PCIE_MLW,
+	CGS_SYSTEM_INFO_CG_FLAGS,
+	CGS_SYSTEM_INFO_PG_FLAGS,
 	CGS_SYSTEM_INFO_ID_MAXIMUM,
 };
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
index 0874ab4..cf01177 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
@@ -174,6 +174,8 @@
 {
 	struct cz_hwmgr *cz_hwmgr = (struct cz_hwmgr *)(hwmgr->backend);
 	uint32_t i;
+	struct cgs_system_info sys_info = {0};
+	int result;
 
 	cz_hwmgr->gfx_ramp_step = 256*25/100;
 
@@ -247,6 +249,22 @@
 	phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 				   PHM_PlatformCaps_DisableVoltageIsland);
 
+	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+		      PHM_PlatformCaps_UVDPowerGating);
+	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+		      PHM_PlatformCaps_VCEPowerGating);
+	sys_info.size = sizeof(struct cgs_system_info);
+	sys_info.info_id = CGS_SYSTEM_INFO_PG_FLAGS;
+	result = cgs_query_system_info(hwmgr->device, &sys_info);
+	if (!result) {
+		if (sys_info.value & AMD_PG_SUPPORT_UVD)
+			phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+				      PHM_PlatformCaps_UVDPowerGating);
+		if (sys_info.value & AMD_PG_SUPPORT_VCE)
+			phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+				      PHM_PlatformCaps_VCEPowerGating);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
index 44a9250..980d3bf 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
@@ -4451,6 +4451,7 @@
 	pp_atomctrl_gpio_pin_assignment gpio_pin_assignment;
 	struct phm_ppt_v1_information *pptable_info = (struct phm_ppt_v1_information *)(hwmgr->pptable);
 	phw_tonga_ulv_parm *ulv;
+	struct cgs_system_info sys_info = {0};
 
 	PP_ASSERT_WITH_CODE((NULL != hwmgr),
 		"Invalid Parameter!", return -1;);
@@ -4615,9 +4616,23 @@
 
 	data->vddc_phase_shed_control = 0;
 
-	if (0 == result) {
-		struct cgs_system_info sys_info = {0};
+	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+		      PHM_PlatformCaps_UVDPowerGating);
+	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+		      PHM_PlatformCaps_VCEPowerGating);
+	sys_info.size = sizeof(struct cgs_system_info);
+	sys_info.info_id = CGS_SYSTEM_INFO_PG_FLAGS;
+	result = cgs_query_system_info(hwmgr->device, &sys_info);
+	if (!result) {
+		if (sys_info.value & AMD_PG_SUPPORT_UVD)
+			phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+				      PHM_PlatformCaps_UVDPowerGating);
+		if (sys_info.value & AMD_PG_SUPPORT_VCE)
+			phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+				      PHM_PlatformCaps_VCEPowerGating);
+	}
 
+	if (0 == result) {
 		data->is_tlu_enabled = 0;
 		hwmgr->platform_descriptor.hardwareActivityPerformanceLevels =
 			TONGA_MAX_HARDWARE_POWERLEVELS;
diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c
index c507896..197b157 100644
--- a/drivers/gpu/drm/radeon/radeon_sa.c
+++ b/drivers/gpu/drm/radeon/radeon_sa.c
@@ -349,8 +349,13 @@
 			/* see if we can skip over some allocations */
 		} while (radeon_sa_bo_next_hole(sa_manager, fences, tries));
 
+		for (i = 0; i < RADEON_NUM_RINGS; ++i)
+			radeon_fence_ref(fences[i]);
+
 		spin_unlock(&sa_manager->wq.lock);
 		r = radeon_fence_wait_any(rdev, fences, false);
+		for (i = 0; i < RADEON_NUM_RINGS; ++i)
+			radeon_fence_unref(&fences[i]);
 		spin_lock(&sa_manager->wq.lock);
 		/* if we have nothing to wait for block */
 		if (r == -ENOENT) {
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index 3de9351..14606af 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -336,7 +336,6 @@
 	union ib_gid gid;
 	struct ib_gid_attr gid_attr = {};
 	ssize_t ret;
-	va_list args;
 
 	ret = ib_query_gid(p->ibdev, p->port_num, tab_attr->index, &gid,
 			   &gid_attr);
@@ -348,7 +347,6 @@
 err:
 	if (gid_attr.ndev)
 		dev_put(gid_attr.ndev);
-	va_end(args);
 	return ret;
 }
 
@@ -722,12 +720,11 @@
 
 	if (get_perf_mad(dev, port_num, IB_PMA_CLASS_PORT_INFO,
 				&cpi, 40, sizeof(cpi)) >= 0) {
-
-		if (cpi.capability_mask && IB_PMA_CLASS_CAP_EXT_WIDTH)
+		if (cpi.capability_mask & IB_PMA_CLASS_CAP_EXT_WIDTH)
 			/* We have extended counters */
 			return &pma_group_ext;
 
-		if (cpi.capability_mask && IB_PMA_CLASS_CAP_EXT_WIDTH_NOIETF)
+		if (cpi.capability_mask & IB_PMA_CLASS_CAP_EXT_WIDTH_NOIETF)
 			/* But not the IETF ones */
 			return &pma_group_noietf;
 	}
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 9116bc3..34cb8e8 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -270,8 +270,10 @@
 		/* fall through */
 	case IB_QPT_RC:
 		size += sizeof(struct mlx5_wqe_ctrl_seg) +
-			sizeof(struct mlx5_wqe_atomic_seg) +
-			sizeof(struct mlx5_wqe_raddr_seg);
+			max(sizeof(struct mlx5_wqe_atomic_seg) +
+			    sizeof(struct mlx5_wqe_raddr_seg),
+			    sizeof(struct mlx5_wqe_umr_ctrl_seg) +
+			    sizeof(struct mlx5_mkey_seg));
 		break;
 
 	case IB_QPT_XRC_TGT:
@@ -279,9 +281,9 @@
 
 	case IB_QPT_UC:
 		size += sizeof(struct mlx5_wqe_ctrl_seg) +
-			sizeof(struct mlx5_wqe_raddr_seg) +
-			sizeof(struct mlx5_wqe_umr_ctrl_seg) +
-			sizeof(struct mlx5_mkey_seg);
+			max(sizeof(struct mlx5_wqe_raddr_seg),
+			    sizeof(struct mlx5_wqe_umr_ctrl_seg) +
+			    sizeof(struct mlx5_mkey_seg));
 		break;
 
 	case IB_QPT_UD:
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index 5738493..f387430 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -228,6 +228,11 @@
 
 	ocrdma_alloc_pd_pool(dev);
 
+	if (!ocrdma_alloc_stats_resources(dev)) {
+		pr_err("%s: stats resource allocation failed\n", __func__);
+		goto alloc_err;
+	}
+
 	spin_lock_init(&dev->av_tbl.lock);
 	spin_lock_init(&dev->flush_q_lock);
 	return 0;
@@ -238,6 +243,7 @@
 
 static void ocrdma_free_resources(struct ocrdma_dev *dev)
 {
+	ocrdma_release_stats_resources(dev);
 	kfree(dev->stag_arr);
 	kfree(dev->qp_tbl);
 	kfree(dev->cq_tbl);
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
index 86c303a..255f774 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
@@ -64,10 +64,11 @@
 	return cpy_len;
 }
 
-static bool ocrdma_alloc_stats_mem(struct ocrdma_dev *dev)
+bool ocrdma_alloc_stats_resources(struct ocrdma_dev *dev)
 {
 	struct stats_mem *mem = &dev->stats_mem;
 
+	mutex_init(&dev->stats_lock);
 	/* Alloc mbox command mem*/
 	mem->size = max_t(u32, sizeof(struct ocrdma_rdma_stats_req),
 			sizeof(struct ocrdma_rdma_stats_resp));
@@ -91,13 +92,14 @@
 	return true;
 }
 
-static void ocrdma_release_stats_mem(struct ocrdma_dev *dev)
+void ocrdma_release_stats_resources(struct ocrdma_dev *dev)
 {
 	struct stats_mem *mem = &dev->stats_mem;
 
 	if (mem->va)
 		dma_free_coherent(&dev->nic_info.pdev->dev, mem->size,
 				  mem->va, mem->pa);
+	mem->va = NULL;
 	kfree(mem->debugfs_mem);
 }
 
@@ -838,15 +840,9 @@
 				&dev->reset_stats, &ocrdma_dbg_ops))
 		goto err;
 
-	/* Now create dma_mem for stats mbx command */
-	if (!ocrdma_alloc_stats_mem(dev))
-		goto err;
-
-	mutex_init(&dev->stats_lock);
 
 	return;
 err:
-	ocrdma_release_stats_mem(dev);
 	debugfs_remove_recursive(dev->dir);
 	dev->dir = NULL;
 }
@@ -855,9 +851,7 @@
 {
 	if (!dev->dir)
 		return;
-	debugfs_remove(dev->dir);
-	mutex_destroy(&dev->stats_lock);
-	ocrdma_release_stats_mem(dev);
+	debugfs_remove_recursive(dev->dir);
 }
 
 void ocrdma_init_debugfs(void)
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.h b/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
index c9e58d0..bba1fec 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
@@ -65,6 +65,8 @@
 
 void ocrdma_rem_debugfs(void);
 void ocrdma_init_debugfs(void);
+bool ocrdma_alloc_stats_resources(struct ocrdma_dev *dev);
+void ocrdma_release_stats_resources(struct ocrdma_dev *dev);
 void ocrdma_rem_port_stats(struct ocrdma_dev *dev);
 void ocrdma_add_port_stats(struct ocrdma_dev *dev);
 int ocrdma_pma_counters(struct ocrdma_dev *dev,
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index d4c687b..37620b4 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -125,8 +125,8 @@
 					IB_DEVICE_SYS_IMAGE_GUID |
 					IB_DEVICE_LOCAL_DMA_LKEY |
 					IB_DEVICE_MEM_MGT_EXTENSIONS;
-	attr->max_sge = min(dev->attr.max_send_sge, dev->attr.max_srq_sge);
-	attr->max_sge_rd = 0;
+	attr->max_sge = dev->attr.max_send_sge;
+	attr->max_sge_rd = attr->max_sge;
 	attr->max_cq = dev->attr.max_cq;
 	attr->max_cqe = dev->attr.max_cqe;
 	attr->max_mr = dev->attr.max_mr;
@@ -2726,8 +2726,7 @@
 		OCRDMA_CQE_UD_STATUS_MASK) >> OCRDMA_CQE_UD_STATUS_SHIFT;
 	ibwc->src_qp = le32_to_cpu(cqe->flags_status_srcqpn) &
 						OCRDMA_CQE_SRCQP_MASK;
-	ibwc->pkey_index = le32_to_cpu(cqe->ud.rxlen_pkey) &
-						OCRDMA_CQE_PKEY_MASK;
+	ibwc->pkey_index = 0;
 	ibwc->wc_flags = IB_WC_GRH;
 	ibwc->byte_len = (le32_to_cpu(cqe->ud.rxlen_pkey) >>
 					OCRDMA_CQE_UD_XFER_LEN_SHIFT);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 5ea0c14..fa9c42f 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -245,8 +245,6 @@
 	skb_reset_mac_header(skb);
 	skb_pull(skb, IPOIB_ENCAP_LEN);
 
-	skb->truesize = SKB_TRUESIZE(skb->len);
-
 	++dev->stats.rx_packets;
 	dev->stats.rx_bytes += skb->len;
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 050dfa1..2588931 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -456,7 +456,10 @@
 	return status;
 }
 
-static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
+/*
+ * Caller must hold 'priv->lock'
+ */
+static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ib_sa_multicast *multicast;
@@ -466,6 +469,10 @@
 	ib_sa_comp_mask comp_mask;
 	int ret = 0;
 
+	if (!priv->broadcast ||
+	    !test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
+		return -EINVAL;
+
 	ipoib_dbg_mcast(priv, "joining MGID %pI6\n", mcast->mcmember.mgid.raw);
 
 	rec.mgid     = mcast->mcmember.mgid;
@@ -525,20 +532,23 @@
 			rec.join_state = 4;
 #endif
 	}
+	spin_unlock_irq(&priv->lock);
 
 	multicast = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port,
 					 &rec, comp_mask, GFP_KERNEL,
 					 ipoib_mcast_join_complete, mcast);
+	spin_lock_irq(&priv->lock);
 	if (IS_ERR(multicast)) {
 		ret = PTR_ERR(multicast);
 		ipoib_warn(priv, "ib_sa_join_multicast failed, status %d\n", ret);
-		spin_lock_irq(&priv->lock);
 		/* Requeue this join task with a backoff delay */
 		__ipoib_mcast_schedule_join_thread(priv, mcast, 1);
 		clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
 		spin_unlock_irq(&priv->lock);
 		complete(&mcast->done);
+		spin_lock_irq(&priv->lock);
 	}
+	return 0;
 }
 
 void ipoib_mcast_join_task(struct work_struct *work)
@@ -620,9 +630,10 @@
 				/* Found the next unjoined group */
 				init_completion(&mcast->done);
 				set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
-				spin_unlock_irq(&priv->lock);
-				ipoib_mcast_join(dev, mcast);
-				spin_lock_irq(&priv->lock);
+				if (ipoib_mcast_join(dev, mcast)) {
+					spin_unlock_irq(&priv->lock);
+					return;
+				}
 			} else if (!delay_until ||
 				 time_before(mcast->delay_until, delay_until))
 				delay_until = mcast->delay_until;
@@ -641,10 +652,9 @@
 	if (mcast) {
 		init_completion(&mcast->done);
 		set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
+		ipoib_mcast_join(dev, mcast);
 	}
 	spin_unlock_irq(&priv->lock);
-	if (mcast)
-		ipoib_mcast_join(dev, mcast);
 }
 
 int ipoib_mcast_start_thread(struct net_device *dev)
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 6727954..e8a84d1 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -1207,7 +1207,6 @@
 #else
 static int xpad_led_probe(struct usb_xpad *xpad) { return 0; }
 static void xpad_led_disconnect(struct usb_xpad *xpad) { }
-static void xpad_identify_controller(struct usb_xpad *xpad) { }
 #endif
 
 static int xpad_start_input(struct usb_xpad *xpad)
diff --git a/drivers/input/keyboard/adp5589-keys.c b/drivers/input/keyboard/adp5589-keys.c
index 4d446d5..c01a1d6 100644
--- a/drivers/input/keyboard/adp5589-keys.c
+++ b/drivers/input/keyboard/adp5589-keys.c
@@ -235,7 +235,7 @@
 	unsigned short gpimapsize;
 	unsigned extend_cfg;
 	bool is_adp5585;
-	bool adp5585_support_row5;
+	bool support_row5;
 #ifdef CONFIG_GPIOLIB
 	unsigned char gpiomap[ADP5589_MAXGPIO];
 	bool export_gpio;
@@ -485,7 +485,7 @@
 	if (kpad->extend_cfg & C4_EXTEND_CFG)
 		pin_used[kpad->var->c4_extend_cfg] = true;
 
-	if (!kpad->adp5585_support_row5)
+	if (!kpad->support_row5)
 		pin_used[5] = true;
 
 	for (i = 0; i < kpad->var->maxgpio; i++)
@@ -884,12 +884,13 @@
 
 	switch (id->driver_data) {
 	case ADP5585_02:
-		kpad->adp5585_support_row5 = true;
+		kpad->support_row5 = true;
 	case ADP5585_01:
 		kpad->is_adp5585 = true;
 		kpad->var = &const_adp5585;
 		break;
 	case ADP5589:
+		kpad->support_row5 = true;
 		kpad->var = &const_adp5589;
 		break;
 	}
diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c
index 378db10..4401be2 100644
--- a/drivers/input/keyboard/cap11xx.c
+++ b/drivers/input/keyboard/cap11xx.c
@@ -304,8 +304,10 @@
 		led->cdev.brightness = LED_OFF;
 
 		error = of_property_read_u32(child, "reg", &reg);
-		if (error != 0 || reg >= num_leds)
+		if (error != 0 || reg >= num_leds) {
+			of_node_put(child);
 			return -EINVAL;
+		}
 
 		led->reg = reg;
 		led->priv = priv;
@@ -313,8 +315,10 @@
 		INIT_WORK(&led->work, cap11xx_led_work);
 
 		error = devm_led_classdev_register(dev, &led->cdev);
-		if (error)
+		if (error) {
+			of_node_put(child);
 			return error;
+		}
 
 		priv->num_leds++;
 		led++;
diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig
index d6d16fa..1f2337a 100644
--- a/drivers/input/misc/Kconfig
+++ b/drivers/input/misc/Kconfig
@@ -733,7 +733,7 @@
 	  module will be called xen-kbdfront.
 
 config INPUT_SIRFSOC_ONKEY
-	bool "CSR SiRFSoC power on/off/suspend key support"
+	tristate "CSR SiRFSoC power on/off/suspend key support"
 	depends on ARCH_SIRF && OF
 	default y
 	help
diff --git a/drivers/input/misc/sirfsoc-onkey.c b/drivers/input/misc/sirfsoc-onkey.c
index 9d5b89b..ed7237f 100644
--- a/drivers/input/misc/sirfsoc-onkey.c
+++ b/drivers/input/misc/sirfsoc-onkey.c
@@ -101,7 +101,7 @@
 static const struct of_device_id sirfsoc_pwrc_of_match[] = {
 	{ .compatible = "sirf,prima2-pwrc" },
 	{},
-}
+};
 MODULE_DEVICE_TABLE(of, sirfsoc_pwrc_of_match);
 
 static int sirfsoc_pwrc_probe(struct platform_device *pdev)
diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c
index e272f06..a3f0f5a 100644
--- a/drivers/input/mouse/vmmouse.c
+++ b/drivers/input/mouse/vmmouse.c
@@ -458,8 +458,6 @@
 	priv->abs_dev = abs_dev;
 	psmouse->private = priv;
 
-	input_set_capability(rel_dev, EV_REL, REL_WHEEL);
-
 	/* Set up and register absolute device */
 	snprintf(priv->phys, sizeof(priv->phys), "%s/input1",
 		 psmouse->ps2dev.serio->phys);
@@ -475,10 +473,6 @@
 	abs_dev->id.version = psmouse->model;
 	abs_dev->dev.parent = &psmouse->ps2dev.serio->dev;
 
-	error = input_register_device(priv->abs_dev);
-	if (error)
-		goto init_fail;
-
 	/* Set absolute device capabilities */
 	input_set_capability(abs_dev, EV_KEY, BTN_LEFT);
 	input_set_capability(abs_dev, EV_KEY, BTN_RIGHT);
@@ -488,6 +482,13 @@
 	input_set_abs_params(abs_dev, ABS_X, 0, VMMOUSE_MAX_X, 0, 0);
 	input_set_abs_params(abs_dev, ABS_Y, 0, VMMOUSE_MAX_Y, 0, 0);
 
+	error = input_register_device(priv->abs_dev);
+	if (error)
+		goto init_fail;
+
+	/* Add wheel capability to the relative device */
+	input_set_capability(rel_dev, EV_REL, REL_WHEEL);
+
 	psmouse->protocol_handler = vmmouse_process_byte;
 	psmouse->disconnect = vmmouse_disconnect;
 	psmouse->reconnect = vmmouse_reconnect;
diff --git a/drivers/input/serio/serio.c b/drivers/input/serio/serio.c
index 8f82897..1ca7f55 100644
--- a/drivers/input/serio/serio.c
+++ b/drivers/input/serio/serio.c
@@ -134,7 +134,7 @@
 	int error;
 
 	error = device_attach(&serio->dev);
-	if (error < 0)
+	if (error < 0 && error != -EPROBE_DEFER)
 		dev_warn(&serio->dev,
 			 "device_attach() failed for %s (%s), error: %d\n",
 			 serio->phys, serio->name, error);
diff --git a/drivers/input/touchscreen/colibri-vf50-ts.c b/drivers/input/touchscreen/colibri-vf50-ts.c
index 5d4903a..69828d0 100644
--- a/drivers/input/touchscreen/colibri-vf50-ts.c
+++ b/drivers/input/touchscreen/colibri-vf50-ts.c
@@ -21,6 +21,7 @@
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c
index 0b0f8c1..23fbe38 100644
--- a/drivers/input/touchscreen/edt-ft5x06.c
+++ b/drivers/input/touchscreen/edt-ft5x06.c
@@ -822,16 +822,22 @@
 	int error;
 
 	error = device_property_read_u32(dev, "threshold", &val);
-	if (!error)
-		reg_addr->reg_threshold = val;
+	if (!error) {
+		edt_ft5x06_register_write(tsdata, reg_addr->reg_threshold, val);
+		tsdata->threshold = val;
+	}
 
 	error = device_property_read_u32(dev, "gain", &val);
-	if (!error)
-		reg_addr->reg_gain = val;
+	if (!error) {
+		edt_ft5x06_register_write(tsdata, reg_addr->reg_gain, val);
+		tsdata->gain = val;
+	}
 
 	error = device_property_read_u32(dev, "offset", &val);
-	if (!error)
-		reg_addr->reg_offset = val;
+	if (!error) {
+		edt_ft5x06_register_write(tsdata, reg_addr->reg_offset, val);
+		tsdata->offset = val;
+	}
 }
 
 static void
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 3447549..0a73632 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -66,7 +66,10 @@
 	unsigned long		phys_base;
 	struct its_cmd_block	*cmd_base;
 	struct its_cmd_block	*cmd_write;
-	void			*tables[GITS_BASER_NR_REGS];
+	struct {
+		void		*base;
+		u32		order;
+	} tables[GITS_BASER_NR_REGS];
 	struct its_collection	*collections;
 	struct list_head	its_device_list;
 	u64			flags;
@@ -807,9 +810,10 @@
 	int i;
 
 	for (i = 0; i < GITS_BASER_NR_REGS; i++) {
-		if (its->tables[i]) {
-			free_page((unsigned long)its->tables[i]);
-			its->tables[i] = NULL;
+		if (its->tables[i].base) {
+			free_pages((unsigned long)its->tables[i].base,
+				   its->tables[i].order);
+			its->tables[i].base = NULL;
 		}
 	}
 }
@@ -890,7 +894,8 @@
 			goto out_free;
 		}
 
-		its->tables[i] = base;
+		its->tables[i].base = base;
+		its->tables[i].order = order;
 
 retry_baser:
 		val = (virt_to_phys(base) 				 |
@@ -940,7 +945,7 @@
 			 * something is horribly wrong...
 			 */
 			free_pages((unsigned long)base, order);
-			its->tables[i] = NULL;
+			its->tables[i].base = NULL;
 
 			switch (psz) {
 			case SZ_16K:
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 911758c..8f9ebf7 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -384,9 +384,6 @@
 	.irq_unmask		= gic_unmask_irq,
 	.irq_eoi		= gic_eoi_irq,
 	.irq_set_type		= gic_set_type,
-#ifdef CONFIG_SMP
-	.irq_set_affinity	= gic_set_affinity,
-#endif
 	.irq_get_irqchip_state	= gic_irq_get_irqchip_state,
 	.irq_set_irqchip_state	= gic_irq_set_irqchip_state,
 	.flags			= IRQCHIP_SET_TYPE_MASKED |
@@ -400,9 +397,6 @@
 	.irq_unmask		= gic_unmask_irq,
 	.irq_eoi		= gic_eoimode1_eoi_irq,
 	.irq_set_type		= gic_set_type,
-#ifdef CONFIG_SMP
-	.irq_set_affinity	= gic_set_affinity,
-#endif
 	.irq_get_irqchip_state	= gic_irq_get_irqchip_state,
 	.irq_set_irqchip_state	= gic_irq_set_irqchip_state,
 	.irq_set_vcpu_affinity	= gic_irq_set_vcpu_affinity,
@@ -443,7 +437,7 @@
 	u32 bypass = 0;
 	u32 mode = 0;
 
-	if (static_key_true(&supports_deactivate))
+	if (gic == &gic_data[0] && static_key_true(&supports_deactivate))
 		mode = GIC_CPU_CTRL_EOImodeNS;
 
 	/*
@@ -1039,6 +1033,11 @@
 		gic->chip.name = kasprintf(GFP_KERNEL, "GIC-%d", gic_nr);
 	}
 
+#ifdef CONFIG_SMP
+	if (gic_nr == 0)
+		gic->chip.irq_set_affinity = gic_set_affinity;
+#endif
+
 #ifdef CONFIG_GIC_NON_BANKED
 	if (percpu_offset) { /* Frankein-GIC without banked registers... */
 		unsigned int cpu;
diff --git a/drivers/irqchip/irq-sun4i.c b/drivers/irqchip/irq-sun4i.c
index 0704362..376b280 100644
--- a/drivers/irqchip/irq-sun4i.c
+++ b/drivers/irqchip/irq-sun4i.c
@@ -22,7 +22,6 @@
 #include <linux/of_irq.h>
 
 #include <asm/exception.h>
-#include <asm/mach/irq.h>
 
 #define SUN4I_IRQ_VECTOR_REG		0x00
 #define SUN4I_IRQ_PROTECTION_REG	0x08
diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c
index e6e4bac..12099b0 100644
--- a/drivers/mfd/db8500-prcmu.c
+++ b/drivers/mfd/db8500-prcmu.c
@@ -2048,6 +2048,7 @@
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(db8500_prcmu_config_hotmon);
 
 static int config_hot_period(u16 val)
 {
@@ -2074,11 +2075,13 @@
 
 	return config_hot_period(cycles32k);
 }
+EXPORT_SYMBOL_GPL(db8500_prcmu_start_temp_sense);
 
 int db8500_prcmu_stop_temp_sense(void)
 {
 	return config_hot_period(0xFFFF);
 }
+EXPORT_SYMBOL_GPL(db8500_prcmu_stop_temp_sense);
 
 static int prcmu_a9wdog(u8 cmd, u8 d0, u8 d1, u8 d2, u8 d3)
 {
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 5914263..fe207e5 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -47,13 +47,10 @@
 #include "queue.h"
 
 MODULE_ALIAS("mmc:block");
-
-#ifdef KERNEL
 #ifdef MODULE_PARAM_PREFIX
 #undef MODULE_PARAM_PREFIX
 #endif
 #define MODULE_PARAM_PREFIX "mmcblk."
-#endif
 
 #define INAND_CMD38_ARG_EXT_CSD  113
 #define INAND_CMD38_ARG_ERASE    0x00
@@ -655,8 +652,10 @@
 	}
 
 	md = mmc_blk_get(bdev->bd_disk);
-	if (!md)
+	if (!md) {
+		err = -EINVAL;
 		goto cmd_err;
+	}
 
 	card = md->queue.card;
 	if (IS_ERR(card)) {
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index 1c1b45e..3446097 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -925,6 +925,10 @@
 
 			dma_addr = dma_map_page(dma_dev, sg_page(sg), 0,
 						PAGE_SIZE, dir);
+			if (dma_mapping_error(dma_dev, dma_addr)) {
+				data->error = -EFAULT;
+				break;
+			}
 			if (direction == DMA_TO_DEVICE)
 				t->tx_dma = dma_addr + sg->offset;
 			else
@@ -1393,10 +1397,12 @@
 		host->dma_dev = dev;
 		host->ones_dma = dma_map_single(dev, ones,
 				MMC_SPI_BLOCKSIZE, DMA_TO_DEVICE);
+		if (dma_mapping_error(dev, host->ones_dma))
+			goto fail_ones_dma;
 		host->data_dma = dma_map_single(dev, host->data,
 				sizeof(*host->data), DMA_BIDIRECTIONAL);
-
-		/* REVISIT in theory those map operations can fail... */
+		if (dma_mapping_error(dev, host->data_dma))
+			goto fail_data_dma;
 
 		dma_sync_single_for_cpu(host->dma_dev,
 				host->data_dma, sizeof(*host->data),
@@ -1462,6 +1468,11 @@
 	if (host->dma_dev)
 		dma_unmap_single(host->dma_dev, host->data_dma,
 				sizeof(*host->data), DMA_BIDIRECTIONAL);
+fail_data_dma:
+	if (host->dma_dev)
+		dma_unmap_single(host->dma_dev, host->ones_dma,
+				MMC_SPI_BLOCKSIZE, DMA_TO_DEVICE);
+fail_ones_dma:
 	kfree(host->data);
 
 fail_nobuf1:
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index ce08896..da82477 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -86,7 +86,7 @@
 static inline void pxamci_init_ocr(struct pxamci_host *host)
 {
 #ifdef CONFIG_REGULATOR
-	host->vcc = regulator_get_optional(mmc_dev(host->mmc), "vmmc");
+	host->vcc = devm_regulator_get_optional(mmc_dev(host->mmc), "vmmc");
 
 	if (IS_ERR(host->vcc))
 		host->vcc = NULL;
@@ -654,12 +654,8 @@
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	irq = platform_get_irq(pdev, 0);
-	if (!r || irq < 0)
-		return -ENXIO;
-
-	r = request_mem_region(r->start, SZ_4K, DRIVER_NAME);
-	if (!r)
-		return -EBUSY;
+	if (irq < 0)
+		return irq;
 
 	mmc = mmc_alloc_host(sizeof(struct pxamci_host), &pdev->dev);
 	if (!mmc) {
@@ -695,7 +691,7 @@
 	host->pdata = pdev->dev.platform_data;
 	host->clkrt = CLKRT_OFF;
 
-	host->clk = clk_get(&pdev->dev, NULL);
+	host->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(host->clk)) {
 		ret = PTR_ERR(host->clk);
 		host->clk = NULL;
@@ -727,9 +723,9 @@
 	host->irq = irq;
 	host->imask = MMC_I_MASK_ALL;
 
-	host->base = ioremap(r->start, SZ_4K);
-	if (!host->base) {
-		ret = -ENOMEM;
+	host->base = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(host->base)) {
+		ret = PTR_ERR(host->base);
 		goto out;
 	}
 
@@ -742,7 +738,8 @@
 	writel(64, host->base + MMC_RESTO);
 	writel(host->imask, host->base + MMC_I_MASK);
 
-	ret = request_irq(host->irq, pxamci_irq, 0, DRIVER_NAME, host);
+	ret = devm_request_irq(&pdev->dev, host->irq, pxamci_irq, 0,
+			       DRIVER_NAME, host);
 	if (ret)
 		goto out;
 
@@ -804,7 +801,7 @@
 		dev_err(&pdev->dev, "Failed requesting gpio_ro %d\n", gpio_ro);
 		goto out;
 	} else {
-		mmc->caps |= host->pdata->gpio_card_ro_invert ?
+		mmc->caps2 |= host->pdata->gpio_card_ro_invert ?
 			0 : MMC_CAP2_RO_ACTIVE_HIGH;
 	}
 
@@ -833,14 +830,9 @@
 			dma_release_channel(host->dma_chan_rx);
 		if (host->dma_chan_tx)
 			dma_release_channel(host->dma_chan_tx);
-		if (host->base)
-			iounmap(host->base);
-		if (host->clk)
-			clk_put(host->clk);
 	}
 	if (mmc)
 		mmc_free_host(mmc);
-	release_resource(r);
 	return ret;
 }
 
@@ -859,9 +851,6 @@
 			gpio_ro = host->pdata->gpio_card_ro;
 			gpio_power = host->pdata->gpio_power;
 		}
-		if (host->vcc)
-			regulator_put(host->vcc);
-
 		if (host->pdata && host->pdata->exit)
 			host->pdata->exit(&pdev->dev, mmc);
 
@@ -870,16 +859,10 @@
 		       END_CMD_RES|PRG_DONE|DATA_TRAN_DONE,
 		       host->base + MMC_I_MASK);
 
-		free_irq(host->irq, host);
 		dmaengine_terminate_all(host->dma_chan_rx);
 		dmaengine_terminate_all(host->dma_chan_tx);
 		dma_release_channel(host->dma_chan_rx);
 		dma_release_channel(host->dma_chan_tx);
-		iounmap(host->base);
-
-		clk_put(host->clk);
-
-		release_resource(host->res);
 
 		mmc_free_host(mmc);
 	}
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index f6047fc..a5cda92 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -146,6 +146,33 @@
 	.ops = &sdhci_acpi_ops_int,
 };
 
+static int bxt_get_cd(struct mmc_host *mmc)
+{
+	int gpio_cd = mmc_gpio_get_cd(mmc);
+	struct sdhci_host *host = mmc_priv(mmc);
+	unsigned long flags;
+	int ret = 0;
+
+	if (!gpio_cd)
+		return 0;
+
+	pm_runtime_get_sync(mmc->parent);
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	if (host->flags & SDHCI_DEVICE_DEAD)
+		goto out;
+
+	ret = !!(sdhci_readl(host, SDHCI_PRESENT_STATE) & SDHCI_CARD_PRESENT);
+out:
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	pm_runtime_mark_last_busy(mmc->parent);
+	pm_runtime_put_autosuspend(mmc->parent);
+
+	return ret;
+}
+
 static int sdhci_acpi_emmc_probe_slot(struct platform_device *pdev,
 				      const char *hid, const char *uid)
 {
@@ -196,6 +223,9 @@
 
 	/* Platform specific code during sd probe slot goes here */
 
+	if (hid && !strcmp(hid, "80865ACA"))
+		host->mmc_host_ops.get_cd = bxt_get_cd;
+
 	return 0;
 }
 
diff --git a/drivers/mmc/host/sdhci-of-at91.c b/drivers/mmc/host/sdhci-of-at91.c
index 7e7d8f0..9cb86fb 100644
--- a/drivers/mmc/host/sdhci-of-at91.c
+++ b/drivers/mmc/host/sdhci-of-at91.c
@@ -217,6 +217,7 @@
 pm_runtime_disable:
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_set_suspended(&pdev->dev);
+	pm_runtime_put_noidle(&pdev->dev);
 clocks_disable_unprepare:
 	clk_disable_unprepare(priv->gck);
 	clk_disable_unprepare(priv->mainck);
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index cc851b0..df3b8ec 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -330,6 +330,33 @@
 	sdhci_pci_spt_drive_strength = 0x10 | ((val >> 12) & 0xf);
 }
 
+static int bxt_get_cd(struct mmc_host *mmc)
+{
+	int gpio_cd = mmc_gpio_get_cd(mmc);
+	struct sdhci_host *host = mmc_priv(mmc);
+	unsigned long flags;
+	int ret = 0;
+
+	if (!gpio_cd)
+		return 0;
+
+	pm_runtime_get_sync(mmc->parent);
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	if (host->flags & SDHCI_DEVICE_DEAD)
+		goto out;
+
+	ret = !!(sdhci_readl(host, SDHCI_PRESENT_STATE) & SDHCI_CARD_PRESENT);
+out:
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	pm_runtime_mark_last_busy(mmc->parent);
+	pm_runtime_put_autosuspend(mmc->parent);
+
+	return ret;
+}
+
 static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
 {
 	slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE |
@@ -362,6 +389,10 @@
 	slot->cd_con_id = NULL;
 	slot->cd_idx = 0;
 	slot->cd_override_level = true;
+	if (slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_BXT_SD ||
+	    slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_APL_SD)
+		slot->host->mmc_host_ops.get_cd = bxt_get_cd;
+
 	return 0;
 }
 
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index d622435..add9fdf 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1360,7 +1360,7 @@
 	sdhci_runtime_pm_get(host);
 
 	/* Firstly check card presence */
-	present = sdhci_do_get_cd(host);
+	present = mmc->ops->get_cd(mmc);
 
 	spin_lock_irqsave(&host->lock, flags);
 
@@ -2849,6 +2849,8 @@
 
 	host = mmc_priv(mmc);
 	host->mmc = mmc;
+	host->mmc_host_ops = sdhci_ops;
+	mmc->ops = &host->mmc_host_ops;
 
 	return host;
 }
@@ -3037,7 +3039,6 @@
 	/*
 	 * Set host parameters.
 	 */
-	mmc->ops = &sdhci_ops;
 	max_clk = host->max_clk;
 
 	if (host->ops->get_min_clock)
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 7654ae5..0115e99 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -430,6 +430,7 @@
 
 	/* Internal data */
 	struct mmc_host *mmc;	/* MMC structure */
+	struct mmc_host_ops mmc_host_ops;	/* MMC host ops */
 	u64 dma_mask;		/* custom DMA mask */
 
 #if defined(CONFIG_LEDS_CLASS) || defined(CONFIG_LEDS_CLASS_MODULE)
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index 1ca8a13..6234eab3 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -445,7 +445,7 @@
 							pdata->slave_id_rx);
 	} else {
 		host->chan_tx = dma_request_slave_channel(dev, "tx");
-		host->chan_tx = dma_request_slave_channel(dev, "rx");
+		host->chan_rx = dma_request_slave_channel(dev, "rx");
 	}
 	dev_dbg(dev, "%s: got channel TX %p RX %p\n", __func__, host->chan_tx,
 		host->chan_rx);
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 49eea89..3010080 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -7831,6 +7831,14 @@
 	return ret;
 }
 
+static bool tg3_tso_bug_gso_check(struct tg3_napi *tnapi, struct sk_buff *skb)
+{
+	/* Check if we will never have enough descriptors,
+	 * as gso_segs can be more than current ring size
+	 */
+	return skb_shinfo(skb)->gso_segs < tnapi->tx_pending / 3;
+}
+
 static netdev_tx_t tg3_start_xmit(struct sk_buff *, struct net_device *);
 
 /* Use GSO to workaround all TSO packets that meet HW bug conditions
@@ -7934,14 +7942,19 @@
 		 * vlan encapsulated.
 		 */
 		if (skb->protocol == htons(ETH_P_8021Q) ||
-		    skb->protocol == htons(ETH_P_8021AD))
-			return tg3_tso_bug(tp, tnapi, txq, skb);
+		    skb->protocol == htons(ETH_P_8021AD)) {
+			if (tg3_tso_bug_gso_check(tnapi, skb))
+				return tg3_tso_bug(tp, tnapi, txq, skb);
+			goto drop;
+		}
 
 		if (!skb_is_gso_v6(skb)) {
 			if (unlikely((ETH_HLEN + hdr_len) > 80) &&
-			    tg3_flag(tp, TSO_BUG))
-				return tg3_tso_bug(tp, tnapi, txq, skb);
-
+			    tg3_flag(tp, TSO_BUG)) {
+				if (tg3_tso_bug_gso_check(tnapi, skb))
+					return tg3_tso_bug(tp, tnapi, txq, skb);
+				goto drop;
+			}
 			ip_csum = iph->check;
 			ip_tot_len = iph->tot_len;
 			iph->check = 0;
@@ -8073,7 +8086,7 @@
 	if (would_hit_hwbug) {
 		tg3_tx_skb_unmap(tnapi, tnapi->tx_prod, i);
 
-		if (mss) {
+		if (mss && tg3_tso_bug_gso_check(tnapi, skb)) {
 			/* If it's a TSO packet, do GSO instead of
 			 * allocating and copying to a large linear SKB
 			 */
diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h
index 1671fa3..7ba6d53 100644
--- a/drivers/net/ethernet/cisco/enic/enic.h
+++ b/drivers/net/ethernet/cisco/enic/enic.h
@@ -33,7 +33,7 @@
 
 #define DRV_NAME		"enic"
 #define DRV_DESCRIPTION		"Cisco VIC Ethernet NIC Driver"
-#define DRV_VERSION		"2.3.0.12"
+#define DRV_VERSION		"2.3.0.20"
 #define DRV_COPYRIGHT		"Copyright 2008-2013 Cisco Systems, Inc"
 
 #define ENIC_BARS_MAX		6
diff --git a/drivers/net/ethernet/cisco/enic/vnic_dev.c b/drivers/net/ethernet/cisco/enic/vnic_dev.c
index 1ffd105..1fdf5fe 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_dev.c
+++ b/drivers/net/ethernet/cisco/enic/vnic_dev.c
@@ -298,7 +298,8 @@
 			  int wait)
 {
 	struct devcmd2_controller *dc2c = vdev->devcmd2;
-	struct devcmd2_result *result = dc2c->result + dc2c->next_result;
+	struct devcmd2_result *result;
+	u8 color;
 	unsigned int i;
 	int delay, err;
 	u32 fetch_index, new_posted;
@@ -336,13 +337,17 @@
 	if (dc2c->cmd_ring[posted].flags & DEVCMD2_FNORESULT)
 		return 0;
 
+	result = dc2c->result + dc2c->next_result;
+	color = dc2c->color;
+
+	dc2c->next_result++;
+	if (dc2c->next_result == dc2c->result_size) {
+		dc2c->next_result = 0;
+		dc2c->color = dc2c->color ? 0 : 1;
+	}
+
 	for (delay = 0; delay < wait; delay++) {
-		if (result->color == dc2c->color) {
-			dc2c->next_result++;
-			if (dc2c->next_result == dc2c->result_size) {
-				dc2c->next_result = 0;
-				dc2c->color = dc2c->color ? 0 : 1;
-			}
+		if (result->color == color) {
 			if (result->error) {
 				err = result->error;
 				if (err != ERR_ECMDUNKNOWN ||
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index d48d579..e94ca1c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2429,7 +2429,7 @@
 	flush_workqueue(priv->mfunc.master.comm_wq);
 	destroy_workqueue(priv->mfunc.master.comm_wq);
 err_slaves:
-	while (--i) {
+	while (i--) {
 		for (port = 1; port <= MLX4_MAX_PORTS; port++)
 			kfree(priv->mfunc.master.slave_state[i].vlan_filter[port]);
 	}
diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
index 70814b7..fc8bbff 100644
--- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c
+++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
@@ -1880,9 +1880,9 @@
 	}
 	netdev_reset_queue(ndev);
 
+	dwceqos_init_hw(lp);
 	napi_enable(&lp->napi);
 	phy_start(lp->phy_dev);
-	dwceqos_init_hw(lp);
 
 	netif_start_queue(ndev);
 	tasklet_enable(&lp->tx_bdreclaim_tasklet);
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 0b14ac3..028e387 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1039,6 +1039,17 @@
 	return geneve_xmit_skb(skb, dev, info);
 }
 
+static int geneve_change_mtu(struct net_device *dev, int new_mtu)
+{
+	/* GENEVE overhead is not fixed, so we can't enforce a more
+	 * precise max MTU.
+	 */
+	if (new_mtu < 68 || new_mtu > IP_MAX_MTU)
+		return -EINVAL;
+	dev->mtu = new_mtu;
+	return 0;
+}
+
 static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 {
 	struct ip_tunnel_info *info = skb_tunnel_info(skb);
@@ -1083,7 +1094,7 @@
 	.ndo_stop		= geneve_stop,
 	.ndo_start_xmit		= geneve_xmit,
 	.ndo_get_stats64	= ip_tunnel_get_stats64,
-	.ndo_change_mtu		= eth_change_mtu,
+	.ndo_change_mtu		= geneve_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_fill_metadata_dst	= geneve_fill_metadata_dst,
@@ -1442,11 +1453,21 @@
 
 	err = geneve_configure(net, dev, &geneve_remote_unspec,
 			       0, 0, 0, htons(dst_port), true, 0);
-	if (err) {
-		free_netdev(dev);
-		return ERR_PTR(err);
-	}
+	if (err)
+		goto err;
+
+	/* openvswitch users expect packet sizes to be unrestricted,
+	 * so set the largest MTU we can.
+	 */
+	err = geneve_change_mtu(dev, IP_MAX_MTU);
+	if (err)
+		goto err;
+
 	return dev;
+
+ err:
+	free_netdev(dev);
+	return ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(geneve_dev_create_fb);
 
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 6543918..a31cd95 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2367,27 +2367,41 @@
 {
 }
 
+static int __vxlan_change_mtu(struct net_device *dev,
+			      struct net_device *lowerdev,
+			      struct vxlan_rdst *dst, int new_mtu, bool strict)
+{
+	int max_mtu = IP_MAX_MTU;
+
+	if (lowerdev)
+		max_mtu = lowerdev->mtu;
+
+	if (dst->remote_ip.sa.sa_family == AF_INET6)
+		max_mtu -= VXLAN6_HEADROOM;
+	else
+		max_mtu -= VXLAN_HEADROOM;
+
+	if (new_mtu < 68)
+		return -EINVAL;
+
+	if (new_mtu > max_mtu) {
+		if (strict)
+			return -EINVAL;
+
+		new_mtu = max_mtu;
+	}
+
+	dev->mtu = new_mtu;
+	return 0;
+}
+
 static int vxlan_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_rdst *dst = &vxlan->default_dst;
-	struct net_device *lowerdev;
-	int max_mtu;
-
-	lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex);
-	if (lowerdev == NULL)
-		return eth_change_mtu(dev, new_mtu);
-
-	if (dst->remote_ip.sa.sa_family == AF_INET6)
-		max_mtu = lowerdev->mtu - VXLAN6_HEADROOM;
-	else
-		max_mtu = lowerdev->mtu - VXLAN_HEADROOM;
-
-	if (new_mtu < 68 || new_mtu > max_mtu)
-		return -EINVAL;
-
-	dev->mtu = new_mtu;
-	return 0;
+	struct net_device *lowerdev = __dev_get_by_index(vxlan->net,
+							 dst->remote_ifindex);
+	return __vxlan_change_mtu(dev, lowerdev, dst, new_mtu, true);
 }
 
 static int egress_ipv4_tun_info(struct net_device *dev, struct sk_buff *skb,
@@ -2765,6 +2779,7 @@
 	int err;
 	bool use_ipv6 = false;
 	__be16 default_port = vxlan->cfg.dst_port;
+	struct net_device *lowerdev = NULL;
 
 	vxlan->net = src_net;
 
@@ -2785,9 +2800,7 @@
 	}
 
 	if (conf->remote_ifindex) {
-		struct net_device *lowerdev
-			 = __dev_get_by_index(src_net, conf->remote_ifindex);
-
+		lowerdev = __dev_get_by_index(src_net, conf->remote_ifindex);
 		dst->remote_ifindex = conf->remote_ifindex;
 
 		if (!lowerdev) {
@@ -2811,6 +2824,12 @@
 		needed_headroom = lowerdev->hard_header_len;
 	}
 
+	if (conf->mtu) {
+		err = __vxlan_change_mtu(dev, lowerdev, dst, conf->mtu, false);
+		if (err)
+			return err;
+	}
+
 	if (use_ipv6 || conf->flags & VXLAN_F_COLLECT_METADATA)
 		needed_headroom += VXLAN6_HEADROOM;
 	else
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index 5648317..39c4be4 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -154,6 +154,7 @@
 	{ .compatible = "marvell,88E1111", },
 	{ .compatible = "marvell,88e1116", },
 	{ .compatible = "marvell,88e1118", },
+	{ .compatible = "marvell,88e1145", },
 	{ .compatible = "marvell,88e1149r", },
 	{ .compatible = "marvell,88e1310", },
 	{ .compatible = "marvell,88E1510", },
diff --git a/drivers/pci/host/pcie-iproc.c b/drivers/pci/host/pcie-iproc.c
index 5816bce..a576aee 100644
--- a/drivers/pci/host/pcie-iproc.c
+++ b/drivers/pci/host/pcie-iproc.c
@@ -64,7 +64,6 @@
 #define OARR_SIZE_CFG                BIT(OARR_SIZE_CFG_SHIFT)
 
 #define MAX_NUM_OB_WINDOWS           2
-#define MAX_NUM_PAXC_PF              4
 
 #define IPROC_PCIE_REG_INVALID 0xffff
 
@@ -170,20 +169,6 @@
 	writel(val, pcie->base + offset + (window * 8));
 }
 
-static inline bool iproc_pcie_device_is_valid(struct iproc_pcie *pcie,
-					      unsigned int slot,
-					      unsigned int fn)
-{
-	if (slot > 0)
-		return false;
-
-	/* PAXC can only support limited number of functions */
-	if (pcie->type == IPROC_PCIE_PAXC && fn >= MAX_NUM_PAXC_PF)
-		return false;
-
-	return true;
-}
-
 /**
  * Note access to the configuration registers are protected at the higher layer
  * by 'pci_lock' in drivers/pci/access.c
@@ -199,11 +184,11 @@
 	u32 val;
 	u16 offset;
 
-	if (!iproc_pcie_device_is_valid(pcie, slot, fn))
-		return NULL;
-
 	/* root complex access */
 	if (busno == 0) {
+		if (slot > 0 || fn > 0)
+			return NULL;
+
 		iproc_pcie_write_reg(pcie, IPROC_PCIE_CFG_IND_ADDR,
 				     where & CFG_IND_ADDR_MASK);
 		offset = iproc_pcie_reg_offset(pcie, IPROC_PCIE_CFG_IND_DATA);
@@ -213,6 +198,14 @@
 			return (pcie->base + offset);
 	}
 
+	/*
+	 * PAXC is connected to an internally emulated EP within the SoC.  It
+	 * allows only one device.
+	 */
+	if (pcie->type == IPROC_PCIE_PAXC)
+		if (slot > 0)
+			return NULL;
+
 	/* EP device access */
 	val = (busno << CFG_ADDR_BUS_NUM_SHIFT) |
 		(slot << CFG_ADDR_DEV_NUM_SHIFT) |
diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c
index 0bf82a2..48d21e0 100644
--- a/drivers/pci/pcie/aer/aerdrv.c
+++ b/drivers/pci/pcie/aer/aerdrv.c
@@ -262,7 +262,6 @@
 	rpc->rpd = dev;
 	INIT_WORK(&rpc->dpc_handler, aer_isr);
 	mutex_init(&rpc->rpc_mutex);
-	init_waitqueue_head(&rpc->wait_release);
 
 	/* Use PCIe bus function to store rpc into PCIe device */
 	set_service_data(dev, rpc);
@@ -285,8 +284,7 @@
 		if (rpc->isr)
 			free_irq(dev->irq, dev);
 
-		wait_event(rpc->wait_release, rpc->prod_idx == rpc->cons_idx);
-
+		flush_work(&rpc->dpc_handler);
 		aer_disable_rootport(rpc);
 		kfree(rpc);
 		set_service_data(dev, NULL);
diff --git a/drivers/pci/pcie/aer/aerdrv.h b/drivers/pci/pcie/aer/aerdrv.h
index 84420b7..945c939 100644
--- a/drivers/pci/pcie/aer/aerdrv.h
+++ b/drivers/pci/pcie/aer/aerdrv.h
@@ -72,7 +72,6 @@
 					 * recovery on the same
 					 * root port hierarchy
 					 */
-	wait_queue_head_t wait_release;
 };
 
 struct aer_broadcast_data {
diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
index 7123925..521e39c 100644
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -811,8 +811,6 @@
 	while (get_e_source(rpc, &e_src))
 		aer_isr_one_error(p_device, &e_src);
 	mutex_unlock(&rpc->rpc_mutex);
-
-	wake_up(&rpc->wait_release);
 }
 
 /**
diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index e7e117d..0124d17 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -224,6 +224,7 @@
 
 config PHY_HI6220_USB
 	tristate "hi6220 USB PHY support"
+	depends on (ARCH_HISI && ARM64) || COMPILE_TEST
 	select GENERIC_PHY
 	select MFD_SYSCON
 	help
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index 8c7f27d..e7e574d 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -275,20 +275,21 @@
 
 int phy_power_on(struct phy *phy)
 {
-	int ret;
+	int ret = 0;
 
 	if (!phy)
-		return 0;
+		goto out;
 
 	if (phy->pwr) {
 		ret = regulator_enable(phy->pwr);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	ret = phy_pm_runtime_get_sync(phy);
 	if (ret < 0 && ret != -ENOTSUPP)
-		return ret;
+		goto err_pm_sync;
+
 	ret = 0; /* Override possible ret == -ENOTSUPP */
 
 	mutex_lock(&phy->mutex);
@@ -296,19 +297,20 @@
 		ret = phy->ops->power_on(phy);
 		if (ret < 0) {
 			dev_err(&phy->dev, "phy poweron failed --> %d\n", ret);
-			goto out;
+			goto err_pwr_on;
 		}
 	}
 	++phy->power_count;
 	mutex_unlock(&phy->mutex);
 	return 0;
 
-out:
+err_pwr_on:
 	mutex_unlock(&phy->mutex);
 	phy_pm_runtime_put_sync(phy);
+err_pm_sync:
 	if (phy->pwr)
 		regulator_disable(phy->pwr);
-
+out:
 	return ret;
 }
 EXPORT_SYMBOL_GPL(phy_power_on);
diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c
index 4a3fc6e..840f3ea 100644
--- a/drivers/phy/phy-twl4030-usb.c
+++ b/drivers/phy/phy-twl4030-usb.c
@@ -715,6 +715,7 @@
 	pm_runtime_use_autosuspend(&pdev->dev);
 	pm_runtime_set_autosuspend_delay(&pdev->dev, 2000);
 	pm_runtime_enable(&pdev->dev);
+	pm_runtime_get_sync(&pdev->dev);
 
 	/* Our job is to use irqs and status from the power module
 	 * to keep the transceiver disabled when nothing's connected.
@@ -750,6 +751,7 @@
 	struct twl4030_usb *twl = platform_get_drvdata(pdev);
 	int val;
 
+	usb_remove_phy(&twl->phy);
 	pm_runtime_get_sync(twl->dev);
 	cancel_delayed_work(&twl->id_workaround_work);
 	device_remove_file(twl->dev, &dev_attr_vbus);
@@ -757,6 +759,13 @@
 	/* set transceiver mode to power on defaults */
 	twl4030_usb_set_mode(twl, -1);
 
+	/* idle ulpi before powering off */
+	if (cable_present(twl->linkstat))
+		pm_runtime_put_noidle(twl->dev);
+	pm_runtime_mark_last_busy(twl->dev);
+	pm_runtime_put_sync_suspend(twl->dev);
+	pm_runtime_disable(twl->dev);
+
 	/* autogate 60MHz ULPI clock,
 	 * clear dpll clock request for i2c access,
 	 * disable 32KHz
@@ -771,11 +780,6 @@
 	/* disable complete OTG block */
 	twl4030_usb_clear_bits(twl, POWER_CTRL, POWER_CTRL_OTG_ENAB);
 
-	if (cable_present(twl->linkstat))
-		pm_runtime_put_noidle(twl->dev);
-	pm_runtime_mark_last_busy(twl->dev);
-	pm_runtime_put(twl->dev);
-
 	return 0;
 }
 
diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c
index 20f0ad9..e20f23e 100644
--- a/drivers/platform/x86/intel-hid.c
+++ b/drivers/platform/x86/intel-hid.c
@@ -41,8 +41,7 @@
 	{ KE_KEY, 4, { KEY_HOME } },
 	{ KE_KEY, 5, { KEY_END } },
 	{ KE_KEY, 6, { KEY_PAGEUP } },
-	{ KE_KEY, 4, { KEY_PAGEDOWN } },
-	{ KE_KEY, 4, { KEY_HOME } },
+	{ KE_KEY, 7, { KEY_PAGEDOWN } },
 	{ KE_KEY, 8, { KEY_RFKILL } },
 	{ KE_KEY, 9, { KEY_POWER } },
 	{ KE_KEY, 11, { KEY_SLEEP } },
diff --git a/drivers/platform/x86/intel_scu_ipcutil.c b/drivers/platform/x86/intel_scu_ipcutil.c
index 02bc5a6..aa45424 100644
--- a/drivers/platform/x86/intel_scu_ipcutil.c
+++ b/drivers/platform/x86/intel_scu_ipcutil.c
@@ -49,7 +49,7 @@
 
 static int scu_reg_access(u32 cmd, struct scu_ipc_data  *data)
 {
-	int count = data->count;
+	unsigned int count = data->count;
 
 	if (count == 0 || count == 3 || count > 4)
 		return -EINVAL;
diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c
index 3613581..93880ed 100644
--- a/drivers/scsi/device_handler/scsi_dh_rdac.c
+++ b/drivers/scsi/device_handler/scsi_dh_rdac.c
@@ -562,7 +562,7 @@
 			/*
 			 * Command Lock contention
 			 */
-			err = SCSI_DH_RETRY;
+			err = SCSI_DH_IMM_RETRY;
 		break;
 	default:
 		break;
@@ -612,6 +612,8 @@
 		err = mode_select_handle_sense(sdev, h->sense);
 		if (err == SCSI_DH_RETRY && retry_cnt--)
 			goto retry;
+		if (err == SCSI_DH_IMM_RETRY)
+			goto retry;
 	}
 	if (err == SCSI_DH_OK) {
 		h->state = RDAC_STATE_ACTIVE;
diff --git a/drivers/scsi/hisi_sas/Kconfig b/drivers/scsi/hisi_sas/Kconfig
index b676618..d1dd161 100644
--- a/drivers/scsi/hisi_sas/Kconfig
+++ b/drivers/scsi/hisi_sas/Kconfig
@@ -1,6 +1,6 @@
 config SCSI_HISI_SAS
 	tristate "HiSilicon SAS"
-	depends on HAS_DMA
+	depends on HAS_DMA && HAS_IOMEM
 	depends on ARM64 || COMPILE_TEST
 	select SCSI_SAS_LIBSAS
 	select BLK_DEV_INTEGRITY
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
index 057fdeb..eea24d7 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
@@ -1289,13 +1289,10 @@
 		goto out;
 	}
 
-	if (cmplt_hdr_data & CMPLT_HDR_ERR_RCRD_XFRD_MSK) {
-		if (!(cmplt_hdr_data & CMPLT_HDR_CMD_CMPLT_MSK) ||
-		    !(cmplt_hdr_data & CMPLT_HDR_RSPNS_XFRD_MSK))
-			ts->stat = SAS_DATA_OVERRUN;
-		else
-			slot_err_v1_hw(hisi_hba, task, slot);
+	if (cmplt_hdr_data & CMPLT_HDR_ERR_RCRD_XFRD_MSK &&
+		!(cmplt_hdr_data & CMPLT_HDR_RSPNS_XFRD_MSK)) {
 
+		slot_err_v1_hw(hisi_hba, task, slot);
 		goto out;
 	}
 
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 52a8765..692a757 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -2204,7 +2204,7 @@
 	/* Clear outstanding commands array. */
 	for (que = 0; que < ha->max_req_queues; que++) {
 		req = ha->req_q_map[que];
-		if (!req)
+		if (!req || !test_bit(que, ha->req_qid_map))
 			continue;
 		req->out_ptr = (void *)(req->ring + req->length);
 		*req->out_ptr = 0;
@@ -2221,7 +2221,7 @@
 
 	for (que = 0; que < ha->max_rsp_queues; que++) {
 		rsp = ha->rsp_q_map[que];
-		if (!rsp)
+		if (!rsp || !test_bit(que, ha->rsp_qid_map))
 			continue;
 		rsp->in_ptr = (void *)(rsp->ring + rsp->length);
 		*rsp->in_ptr = 0;
@@ -4981,7 +4981,7 @@
 
 	for (i = 1; i < ha->max_rsp_queues; i++) {
 		rsp = ha->rsp_q_map[i];
-		if (rsp) {
+		if (rsp && test_bit(i, ha->rsp_qid_map)) {
 			rsp->options &= ~BIT_0;
 			ret = qla25xx_init_rsp_que(base_vha, rsp);
 			if (ret != QLA_SUCCESS)
@@ -4996,8 +4996,8 @@
 	}
 	for (i = 1; i < ha->max_req_queues; i++) {
 		req = ha->req_q_map[i];
-		if (req) {
-		/* Clear outstanding commands array. */
+		if (req && test_bit(i, ha->req_qid_map)) {
+			/* Clear outstanding commands array. */
 			req->options &= ~BIT_0;
 			ret = qla25xx_init_req_que(base_vha, req);
 			if (ret != QLA_SUCCESS)
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index d4d65eb..4af9547 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -3063,9 +3063,9 @@
 		    "MSI-X: Failed to enable support "
 		    "-- %d/%d\n Retry with %d vectors.\n",
 		    ha->msix_count, ret, ret);
+		ha->msix_count = ret;
+		ha->max_rsp_queues = ha->msix_count - 1;
 	}
-	ha->msix_count = ret;
-	ha->max_rsp_queues = ha->msix_count - 1;
 	ha->msix_entries = kzalloc(sizeof(struct qla_msix_entry) *
 				ha->msix_count, GFP_KERNEL);
 	if (!ha->msix_entries) {
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index c5dd594..cf7ba52 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -600,7 +600,7 @@
 	/* Delete request queues */
 	for (cnt = 1; cnt < ha->max_req_queues; cnt++) {
 		req = ha->req_q_map[cnt];
-		if (req) {
+		if (req && test_bit(cnt, ha->req_qid_map)) {
 			ret = qla25xx_delete_req_que(vha, req);
 			if (ret != QLA_SUCCESS) {
 				ql_log(ql_log_warn, vha, 0x00ea,
@@ -614,7 +614,7 @@
 	/* Delete response queues */
 	for (cnt = 1; cnt < ha->max_rsp_queues; cnt++) {
 		rsp = ha->rsp_q_map[cnt];
-		if (rsp) {
+		if (rsp && test_bit(cnt, ha->rsp_qid_map)) {
 			ret = qla25xx_delete_rsp_que(vha, rsp);
 			if (ret != QLA_SUCCESS) {
 				ql_log(ql_log_warn, vha, 0x00eb,
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index f1788db..f6c7ce3 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -409,6 +409,9 @@
 	int cnt;
 
 	for (cnt = 0; cnt < ha->max_req_queues; cnt++) {
+		if (!test_bit(cnt, ha->req_qid_map))
+			continue;
+
 		req = ha->req_q_map[cnt];
 		qla2x00_free_req_que(ha, req);
 	}
@@ -416,6 +419,9 @@
 	ha->req_q_map = NULL;
 
 	for (cnt = 0; cnt < ha->max_rsp_queues; cnt++) {
+		if (!test_bit(cnt, ha->rsp_qid_map))
+			continue;
+
 		rsp = ha->rsp_q_map[cnt];
 		qla2x00_free_rsp_que(ha, rsp);
 	}
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 8075a4c..ee967be 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -105,7 +105,7 @@
 static int qlt_issue_task_mgmt(struct qla_tgt_sess *sess, uint32_t lun,
 	int fn, void *iocb, int flags);
 static void qlt_send_term_exchange(struct scsi_qla_host *ha, struct qla_tgt_cmd
-	*cmd, struct atio_from_isp *atio, int ha_locked);
+	*cmd, struct atio_from_isp *atio, int ha_locked, int ul_abort);
 static void qlt_reject_free_srr_imm(struct scsi_qla_host *ha,
 	struct qla_tgt_srr_imm *imm, int ha_lock);
 static void qlt_abort_cmd_on_host_reset(struct scsi_qla_host *vha,
@@ -1756,7 +1756,7 @@
 		qlt_send_notify_ack(vha, &mcmd->orig_iocb.imm_ntfy,
 		    0, 0, 0, 0, 0, 0);
 	else {
-		if (mcmd->se_cmd.se_tmr_req->function == TMR_ABORT_TASK)
+		if (mcmd->orig_iocb.atio.u.raw.entry_type == ABTS_RECV_24XX)
 			qlt_24xx_send_abts_resp(vha, &mcmd->orig_iocb.abts,
 			    mcmd->fc_tm_rsp, false);
 		else
@@ -2665,7 +2665,7 @@
 			/* no need to terminate. FW already freed exchange. */
 			qlt_abort_cmd_on_host_reset(cmd->vha, cmd);
 		else
-			qlt_send_term_exchange(vha, cmd, &cmd->atio, 1);
+			qlt_send_term_exchange(vha, cmd, &cmd->atio, 1, 0);
 		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 		return 0;
 	}
@@ -3173,7 +3173,8 @@
 }
 
 static void qlt_send_term_exchange(struct scsi_qla_host *vha,
-	struct qla_tgt_cmd *cmd, struct atio_from_isp *atio, int ha_locked)
+	struct qla_tgt_cmd *cmd, struct atio_from_isp *atio, int ha_locked,
+	int ul_abort)
 {
 	unsigned long flags = 0;
 	int rc;
@@ -3193,8 +3194,7 @@
 		qlt_alloc_qfull_cmd(vha, atio, 0, 0);
 
 done:
-	if (cmd && (!cmd->aborted ||
-	    !cmd->cmd_sent_to_fw)) {
+	if (cmd && !ul_abort && !cmd->aborted) {
 		if (cmd->sg_mapped)
 			qlt_unmap_sg(vha, cmd);
 		vha->hw->tgt.tgt_ops->free_cmd(cmd);
@@ -3253,21 +3253,38 @@
 
 }
 
-void qlt_abort_cmd(struct qla_tgt_cmd *cmd)
+int qlt_abort_cmd(struct qla_tgt_cmd *cmd)
 {
 	struct qla_tgt *tgt = cmd->tgt;
 	struct scsi_qla_host *vha = tgt->vha;
 	struct se_cmd *se_cmd = &cmd->se_cmd;
+	unsigned long flags;
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf014,
 	    "qla_target(%d): terminating exchange for aborted cmd=%p "
 	    "(se_cmd=%p, tag=%llu)", vha->vp_idx, cmd, &cmd->se_cmd,
 	    se_cmd->tag);
 
+	spin_lock_irqsave(&cmd->cmd_lock, flags);
+	if (cmd->aborted) {
+		spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+		/*
+		 * It's normal to see 2 calls in this path:
+		 *  1) XFER Rdy completion + CMD_T_ABORT
+		 *  2) TCM TMR - drain_state_list
+		 */
+	        ql_dbg(ql_dbg_tgt_mgt, vha, 0xffff,
+			"multiple abort. %p transport_state %x, t_state %x,"
+			" se_cmd_flags %x \n", cmd, cmd->se_cmd.transport_state,
+			cmd->se_cmd.t_state,cmd->se_cmd.se_cmd_flags);
+		return EIO;
+	}
 	cmd->aborted = 1;
 	cmd->cmd_flags |= BIT_6;
+	spin_unlock_irqrestore(&cmd->cmd_lock, flags);
 
-	qlt_send_term_exchange(vha, cmd, &cmd->atio, 0);
+	qlt_send_term_exchange(vha, cmd, &cmd->atio, 0, 1);
+	return 0;
 }
 EXPORT_SYMBOL(qlt_abort_cmd);
 
@@ -3282,6 +3299,9 @@
 
 	BUG_ON(cmd->cmd_in_wq);
 
+	if (cmd->sg_mapped)
+		qlt_unmap_sg(cmd->vha, cmd);
+
 	if (!cmd->q_full)
 		qlt_decr_num_pend_cmds(cmd->vha);
 
@@ -3399,7 +3419,7 @@
 		term = 1;
 
 	if (term)
-		qlt_send_term_exchange(vha, cmd, &cmd->atio, 1);
+		qlt_send_term_exchange(vha, cmd, &cmd->atio, 1, 0);
 
 	return term;
 }
@@ -3580,12 +3600,13 @@
 		case CTIO_PORT_LOGGED_OUT:
 		case CTIO_PORT_UNAVAILABLE:
 		{
-			int logged_out = (status & 0xFFFF);
+			int logged_out =
+				(status & 0xFFFF) == CTIO_PORT_LOGGED_OUT;
+
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf059,
 			    "qla_target(%d): CTIO with %s status %x "
 			    "received (state %x, se_cmd %p)\n", vha->vp_idx,
-			    (logged_out == CTIO_PORT_LOGGED_OUT) ?
-			    "PORT LOGGED OUT" : "PORT UNAVAILABLE",
+			    logged_out ? "PORT LOGGED OUT" : "PORT UNAVAILABLE",
 			    status, cmd->state, se_cmd);
 
 			if (logged_out && cmd->sess) {
@@ -3754,6 +3775,7 @@
 		goto out_term;
 	}
 
+	spin_lock_init(&cmd->cmd_lock);
 	cdb = &atio->u.isp24.fcp_cmnd.cdb[0];
 	cmd->se_cmd.tag = atio->u.isp24.exchange_addr;
 	cmd->unpacked_lun = scsilun_to_int(
@@ -3796,7 +3818,7 @@
 	 */
 	cmd->cmd_flags |= BIT_2;
 	spin_lock_irqsave(&ha->hardware_lock, flags);
-	qlt_send_term_exchange(vha, NULL, &cmd->atio, 1);
+	qlt_send_term_exchange(vha, NULL, &cmd->atio, 1, 0);
 
 	qlt_decr_num_pend_cmds(vha);
 	percpu_ida_free(&sess->se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
@@ -3918,7 +3940,7 @@
 
 out_term:
 	spin_lock_irqsave(&ha->hardware_lock, flags);
-	qlt_send_term_exchange(vha, NULL, &op->atio, 1);
+	qlt_send_term_exchange(vha, NULL, &op->atio, 1, 0);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 	kfree(op);
 
@@ -3982,7 +4004,8 @@
 
 	cmd->cmd_in_wq = 1;
 	cmd->cmd_flags |= BIT_0;
-	cmd->se_cmd.cpuid = -1;
+	cmd->se_cmd.cpuid = ha->msix_count ?
+		ha->tgt.rspq_vector_cpuid : WORK_CPU_UNBOUND;
 
 	spin_lock(&vha->cmd_list_lock);
 	list_add_tail(&cmd->cmd_list, &vha->qla_cmd_list);
@@ -3990,7 +4013,6 @@
 
 	INIT_WORK(&cmd->work, qlt_do_work);
 	if (ha->msix_count) {
-		cmd->se_cmd.cpuid = ha->tgt.rspq_vector_cpuid;
 		if (cmd->atio.u.isp24.fcp_cmnd.rddata)
 			queue_work_on(smp_processor_id(), qla_tgt_wq,
 			    &cmd->work);
@@ -4771,7 +4793,7 @@
 		dump_stack();
 	} else {
 		cmd->cmd_flags |= BIT_9;
-		qlt_send_term_exchange(vha, cmd, &cmd->atio, 1);
+		qlt_send_term_exchange(vha, cmd, &cmd->atio, 1, 0);
 	}
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 }
@@ -4950,7 +4972,7 @@
 				    sctio, sctio->srr_id);
 				list_del(&sctio->srr_list_entry);
 				qlt_send_term_exchange(vha, sctio->cmd,
-				    &sctio->cmd->atio, 1);
+				    &sctio->cmd->atio, 1, 0);
 				kfree(sctio);
 			}
 		}
@@ -5123,7 +5145,7 @@
 	    atio->u.isp24.fcp_hdr.s_id);
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 	if (!sess) {
-		qlt_send_term_exchange(vha, NULL, atio, 1);
+		qlt_send_term_exchange(vha, NULL, atio, 1, 0);
 		return 0;
 	}
 	/* Sending marker isn't necessary, since we called from ISR */
@@ -5406,7 +5428,7 @@
 #if 1 /* With TERM EXCHANGE some FC cards refuse to boot */
 				qlt_send_busy(vha, atio, SAM_STAT_BUSY);
 #else
-				qlt_send_term_exchange(vha, NULL, atio, 1);
+				qlt_send_term_exchange(vha, NULL, atio, 1, 0);
 #endif
 
 				if (!ha_locked)
@@ -5523,7 +5545,7 @@
 #if 1 /* With TERM EXCHANGE some FC cards refuse to boot */
 				qlt_send_busy(vha, atio, 0);
 #else
-				qlt_send_term_exchange(vha, NULL, atio, 1);
+				qlt_send_term_exchange(vha, NULL, atio, 1, 0);
 #endif
 			} else {
 				if (tgt->tgt_stop) {
@@ -5532,7 +5554,7 @@
 					    "command to target, sending TERM "
 					    "EXCHANGE for rsp\n");
 					qlt_send_term_exchange(vha, NULL,
-					    atio, 1);
+					    atio, 1, 0);
 				} else {
 					ql_dbg(ql_dbg_tgt, vha, 0xe060,
 					    "qla_target(%d): Unable to send "
@@ -5960,7 +5982,7 @@
 	return;
 
 out_term:
-	qlt_send_term_exchange(vha, NULL, &prm->tm_iocb2, 0);
+	qlt_send_term_exchange(vha, NULL, &prm->tm_iocb2, 1, 0);
 	if (sess)
 		ha->tgt.tgt_ops->put_sess(sess);
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index 71b2865..22a6a76 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -943,6 +943,36 @@
 	qlt_plogi_ack_t *plogi_link[QLT_PLOGI_LINK_MAX];
 };
 
+typedef enum {
+	/*
+	 * BIT_0 - Atio Arrival / schedule to work
+	 * BIT_1 - qlt_do_work
+	 * BIT_2 - qlt_do work failed
+	 * BIT_3 - xfer rdy/tcm_qla2xxx_write_pending
+	 * BIT_4 - read respond/tcm_qla2xx_queue_data_in
+	 * BIT_5 - status respond / tcm_qla2xx_queue_status
+	 * BIT_6 - tcm request to abort/Term exchange.
+	 *	pre_xmit_response->qlt_send_term_exchange
+	 * BIT_7 - SRR received (qlt_handle_srr->qlt_xmit_response)
+	 * BIT_8 - SRR received (qlt_handle_srr->qlt_rdy_to_xfer)
+	 * BIT_9 - SRR received (qla_handle_srr->qlt_send_term_exchange)
+	 * BIT_10 - Data in - hanlde_data->tcm_qla2xxx_handle_data
+
+	 * BIT_12 - good completion - qlt_ctio_do_completion -->free_cmd
+	 * BIT_13 - Bad completion -
+	 *	qlt_ctio_do_completion --> qlt_term_ctio_exchange
+	 * BIT_14 - Back end data received/sent.
+	 * BIT_15 - SRR prepare ctio
+	 * BIT_16 - complete free
+	 * BIT_17 - flush - qlt_abort_cmd_on_host_reset
+	 * BIT_18 - completion w/abort status
+	 * BIT_19 - completion w/unknown status
+	 * BIT_20 - tcm_qla2xxx_free_cmd
+	 */
+	CMD_FLAG_DATA_WORK = BIT_11,
+	CMD_FLAG_DATA_WORK_FREE = BIT_21,
+} cmd_flags_t;
+
 struct qla_tgt_cmd {
 	struct se_cmd se_cmd;
 	struct qla_tgt_sess *sess;
@@ -952,6 +982,7 @@
 	/* Sense buffer that will be mapped into outgoing status */
 	unsigned char sense_buffer[TRANSPORT_SENSE_BUFFER];
 
+	spinlock_t cmd_lock;
 	/* to save extra sess dereferences */
 	unsigned int conf_compl_supported:1;
 	unsigned int sg_mapped:1;
@@ -986,30 +1017,8 @@
 
 	uint64_t jiffies_at_alloc;
 	uint64_t jiffies_at_free;
-	/* BIT_0 - Atio Arrival / schedule to work
-	 * BIT_1 - qlt_do_work
-	 * BIT_2 - qlt_do work failed
-	 * BIT_3 - xfer rdy/tcm_qla2xxx_write_pending
-	 * BIT_4 - read respond/tcm_qla2xx_queue_data_in
-	 * BIT_5 - status respond / tcm_qla2xx_queue_status
-	 * BIT_6 - tcm request to abort/Term exchange.
-	 *	pre_xmit_response->qlt_send_term_exchange
-	 * BIT_7 - SRR received (qlt_handle_srr->qlt_xmit_response)
-	 * BIT_8 - SRR received (qlt_handle_srr->qlt_rdy_to_xfer)
-	 * BIT_9 - SRR received (qla_handle_srr->qlt_send_term_exchange)
-	 * BIT_10 - Data in - hanlde_data->tcm_qla2xxx_handle_data
-	 * BIT_11 - Data actually going to TCM : tcm_qla2xx_handle_data_work
-	 * BIT_12 - good completion - qlt_ctio_do_completion -->free_cmd
-	 * BIT_13 - Bad completion -
-	 *	qlt_ctio_do_completion --> qlt_term_ctio_exchange
-	 * BIT_14 - Back end data received/sent.
-	 * BIT_15 - SRR prepare ctio
-	 * BIT_16 - complete free
-	 * BIT_17 - flush - qlt_abort_cmd_on_host_reset
-	 * BIT_18 - completion w/abort status
-	 * BIT_19 - completion w/unknown status
-	 */
-	uint32_t cmd_flags;
+
+	cmd_flags_t cmd_flags;
 };
 
 struct qla_tgt_sess_work_param {
@@ -1148,7 +1157,7 @@
 extern void qlt_response_pkt_all_vps(struct scsi_qla_host *, response_t *);
 extern int qlt_rdy_to_xfer(struct qla_tgt_cmd *);
 extern int qlt_xmit_response(struct qla_tgt_cmd *, int, uint8_t);
-extern void qlt_abort_cmd(struct qla_tgt_cmd *);
+extern int qlt_abort_cmd(struct qla_tgt_cmd *);
 extern void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *);
 extern void qlt_free_mcmd(struct qla_tgt_mgmt_cmd *);
 extern void qlt_free_cmd(struct qla_tgt_cmd *cmd);
diff --git a/drivers/scsi/qla2xxx/qla_tmpl.c b/drivers/scsi/qla2xxx/qla_tmpl.c
index ddbe2e7..c3e6225 100644
--- a/drivers/scsi/qla2xxx/qla_tmpl.c
+++ b/drivers/scsi/qla2xxx/qla_tmpl.c
@@ -395,6 +395,10 @@
 	if (ent->t263.queue_type == T263_QUEUE_TYPE_REQ) {
 		for (i = 0; i < vha->hw->max_req_queues; i++) {
 			struct req_que *req = vha->hw->req_q_map[i];
+
+			if (!test_bit(i, vha->hw->req_qid_map))
+				continue;
+
 			if (req || !buf) {
 				length = req ?
 				    req->length : REQUEST_ENTRY_CNT_24XX;
@@ -408,6 +412,10 @@
 	} else if (ent->t263.queue_type == T263_QUEUE_TYPE_RSP) {
 		for (i = 0; i < vha->hw->max_rsp_queues; i++) {
 			struct rsp_que *rsp = vha->hw->rsp_q_map[i];
+
+			if (!test_bit(i, vha->hw->rsp_qid_map))
+				continue;
+
 			if (rsp || !buf) {
 				length = rsp ?
 				    rsp->length : RESPONSE_ENTRY_CNT_MQ;
@@ -634,6 +642,10 @@
 	if (ent->t274.queue_type == T274_QUEUE_TYPE_REQ_SHAD) {
 		for (i = 0; i < vha->hw->max_req_queues; i++) {
 			struct req_que *req = vha->hw->req_q_map[i];
+
+			if (!test_bit(i, vha->hw->req_qid_map))
+				continue;
+
 			if (req || !buf) {
 				qla27xx_insert16(i, buf, len);
 				qla27xx_insert16(1, buf, len);
@@ -645,6 +657,10 @@
 	} else if (ent->t274.queue_type == T274_QUEUE_TYPE_RSP_SHAD) {
 		for (i = 0; i < vha->hw->max_rsp_queues; i++) {
 			struct rsp_que *rsp = vha->hw->rsp_q_map[i];
+
+			if (!test_bit(i, vha->hw->rsp_qid_map))
+				continue;
+
 			if (rsp || !buf) {
 				qla27xx_insert16(i, buf, len);
 				qla27xx_insert16(1, buf, len);
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index faf0a12..1808a01 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -298,6 +298,10 @@
 {
 	cmd->vha->tgt_counters.core_qla_free_cmd++;
 	cmd->cmd_in_wq = 1;
+
+	BUG_ON(cmd->cmd_flags & BIT_20);
+	cmd->cmd_flags |= BIT_20;
+
 	INIT_WORK(&cmd->work, tcm_qla2xxx_complete_free);
 	queue_work_on(smp_processor_id(), tcm_qla2xxx_free_wq, &cmd->work);
 }
@@ -374,6 +378,20 @@
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
+
+	if (cmd->aborted) {
+		/* Cmd can loop during Q-full.  tcm_qla2xxx_aborted_task
+		 * can get ahead of this cmd. tcm_qla2xxx_aborted_task
+		 * already kick start the free.
+		 */
+		pr_debug("write_pending aborted cmd[%p] refcount %d "
+			"transport_state %x, t_state %x, se_cmd_flags %x\n",
+			cmd,cmd->se_cmd.cmd_kref.refcount.counter,
+			cmd->se_cmd.transport_state,
+			cmd->se_cmd.t_state,
+			cmd->se_cmd.se_cmd_flags);
+		return 0;
+	}
 	cmd->cmd_flags |= BIT_3;
 	cmd->bufflen = se_cmd->data_length;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
@@ -405,7 +423,7 @@
 	    se_cmd->t_state == TRANSPORT_COMPLETE_QF_WP) {
 		spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
 		wait_for_completion_timeout(&se_cmd->t_transport_stop_comp,
-					    3 * HZ);
+						50);
 		return 0;
 	}
 	spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
@@ -444,6 +462,9 @@
 	if (bidi)
 		flags |= TARGET_SCF_BIDI_OP;
 
+	if (se_cmd->cpuid != WORK_CPU_UNBOUND)
+		flags |= TARGET_SCF_USE_CPUID;
+
 	sess = cmd->sess;
 	if (!sess) {
 		pr_err("Unable to locate struct qla_tgt_sess from qla_tgt_cmd\n");
@@ -465,13 +486,25 @@
 static void tcm_qla2xxx_handle_data_work(struct work_struct *work)
 {
 	struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work);
+	unsigned long flags;
 
 	/*
 	 * Ensure that the complete FCP WRITE payload has been received.
 	 * Otherwise return an exception via CHECK_CONDITION status.
 	 */
 	cmd->cmd_in_wq = 0;
-	cmd->cmd_flags |= BIT_11;
+
+	spin_lock_irqsave(&cmd->cmd_lock, flags);
+	cmd->cmd_flags |= CMD_FLAG_DATA_WORK;
+	if (cmd->aborted) {
+		cmd->cmd_flags |= CMD_FLAG_DATA_WORK_FREE;
+		spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+
+		tcm_qla2xxx_free_cmd(cmd);
+		return;
+	}
+	spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+
 	cmd->vha->tgt_counters.qla_core_ret_ctio++;
 	if (!cmd->write_data_transferred) {
 		/*
@@ -546,6 +579,20 @@
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
 
+	if (cmd->aborted) {
+		/* Cmd can loop during Q-full.  tcm_qla2xxx_aborted_task
+		 * can get ahead of this cmd. tcm_qla2xxx_aborted_task
+		 * already kick start the free.
+		 */
+		pr_debug("queue_data_in aborted cmd[%p] refcount %d "
+			"transport_state %x, t_state %x, se_cmd_flags %x\n",
+			cmd,cmd->se_cmd.cmd_kref.refcount.counter,
+			cmd->se_cmd.transport_state,
+			cmd->se_cmd.t_state,
+			cmd->se_cmd.se_cmd_flags);
+		return 0;
+	}
+
 	cmd->cmd_flags |= BIT_4;
 	cmd->bufflen = se_cmd->data_length;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
@@ -637,11 +684,34 @@
 	qlt_xmit_tm_rsp(mcmd);
 }
 
+
+#define DATA_WORK_NOT_FREE(_flags) \
+	(( _flags & (CMD_FLAG_DATA_WORK|CMD_FLAG_DATA_WORK_FREE)) == \
+	 CMD_FLAG_DATA_WORK)
 static void tcm_qla2xxx_aborted_task(struct se_cmd *se_cmd)
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
-	qlt_abort_cmd(cmd);
+	unsigned long flags;
+
+	if (qlt_abort_cmd(cmd))
+		return;
+
+	spin_lock_irqsave(&cmd->cmd_lock, flags);
+	if ((cmd->state == QLA_TGT_STATE_NEW)||
+		((cmd->state == QLA_TGT_STATE_DATA_IN) &&
+		 DATA_WORK_NOT_FREE(cmd->cmd_flags)) ) {
+
+		cmd->cmd_flags |= CMD_FLAG_DATA_WORK_FREE;
+		spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+		/* Cmd have not reached firmware.
+		 * Use this trigger to free it. */
+		tcm_qla2xxx_free_cmd(cmd);
+		return;
+	}
+	spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+	return;
+
 }
 
 static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *,
diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c
index 47b9d13..da2e068 100644
--- a/drivers/scsi/scsi_devinfo.c
+++ b/drivers/scsi/scsi_devinfo.c
@@ -205,6 +205,7 @@
 	{"Intel", "Multi-Flex", NULL, BLIST_NO_RSOC},
 	{"iRiver", "iFP Mass Driver", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36},
 	{"LASOUND", "CDX7405", "3.10", BLIST_MAX5LUN | BLIST_SINGLELUN},
+	{"Marvell", "Console", NULL, BLIST_SKIP_VPD_PAGES},
 	{"MATSHITA", "PD-1", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
 	{"MATSHITA", "DMC-LC5", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36},
 	{"MATSHITA", "DMC-LC40", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36},
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index bb669d3..d749da7 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -761,7 +761,7 @@
 		break;
 
 	default:
-		ret = BLKPREP_KILL;
+		ret = BLKPREP_INVALID;
 		goto out;
 	}
 
@@ -839,7 +839,7 @@
 	int ret;
 
 	if (sdkp->device->no_write_same)
-		return BLKPREP_KILL;
+		return BLKPREP_INVALID;
 
 	BUG_ON(bio_offset(bio) || bio_iovec(bio).bv_len != sdp->sector_size);
 
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 55627d0..292c04e 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -42,6 +42,7 @@
 #include <scsi/scsi_devinfo.h>
 #include <scsi/scsi_dbg.h>
 #include <scsi/scsi_transport_fc.h>
+#include <scsi/scsi_transport.h>
 
 /*
  * All wire protocol details (storage protocol between the guest and the host)
@@ -477,19 +478,18 @@
 struct storvsc_scan_work {
 	struct work_struct work;
 	struct Scsi_Host *host;
-	uint lun;
+	u8 lun;
+	u8 tgt_id;
 };
 
 static void storvsc_device_scan(struct work_struct *work)
 {
 	struct storvsc_scan_work *wrk;
-	uint lun;
 	struct scsi_device *sdev;
 
 	wrk = container_of(work, struct storvsc_scan_work, work);
-	lun = wrk->lun;
 
-	sdev = scsi_device_lookup(wrk->host, 0, 0, lun);
+	sdev = scsi_device_lookup(wrk->host, 0, wrk->tgt_id, wrk->lun);
 	if (!sdev)
 		goto done;
 	scsi_rescan_device(&sdev->sdev_gendev);
@@ -540,7 +540,7 @@
 	if (!scsi_host_get(wrk->host))
 		goto done;
 
-	sdev = scsi_device_lookup(wrk->host, 0, 0, wrk->lun);
+	sdev = scsi_device_lookup(wrk->host, 0, wrk->tgt_id, wrk->lun);
 
 	if (sdev) {
 		scsi_remove_device(sdev);
@@ -940,6 +940,7 @@
 
 	wrk->host = host;
 	wrk->lun = vm_srb->lun;
+	wrk->tgt_id = vm_srb->target_id;
 	INIT_WORK(&wrk->work, process_err_fn);
 	schedule_work(&wrk->work);
 }
@@ -1770,6 +1771,11 @@
 	fc_transport_template = fc_attach_transport(&fc_transport_functions);
 	if (!fc_transport_template)
 		return -ENODEV;
+
+	/*
+	 * Install Hyper-V specific timeout handler.
+	 */
+	fc_transport_template->eh_timed_out = storvsc_eh_timed_out;
 #endif
 
 	ret = vmbus_driver_register(&storvsc_drv);
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 3327c49..713c63d9 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -898,7 +898,7 @@
 	da->unmap_zeroes_data = flag;
 	pr_debug("dev[%p]: SE Device Thin Provisioning LBPRZ bit: %d\n",
 		 da->da_dev, flag);
-	return 0;
+	return count;
 }
 
 /*
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index cacd97a..da457e2 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -828,6 +828,50 @@
 	return dev;
 }
 
+/*
+ * Check if the underlying struct block_device request_queue supports
+ * the QUEUE_FLAG_DISCARD bit for UNMAP/WRITE_SAME in SCSI + TRIM
+ * in ATA and we need to set TPE=1
+ */
+bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib,
+				       struct request_queue *q, int block_size)
+{
+	if (!blk_queue_discard(q))
+		return false;
+
+	attrib->max_unmap_lba_count = (q->limits.max_discard_sectors << 9) /
+								block_size;
+	/*
+	 * Currently hardcoded to 1 in Linux/SCSI code..
+	 */
+	attrib->max_unmap_block_desc_count = 1;
+	attrib->unmap_granularity = q->limits.discard_granularity / block_size;
+	attrib->unmap_granularity_alignment = q->limits.discard_alignment /
+								block_size;
+	attrib->unmap_zeroes_data = q->limits.discard_zeroes_data;
+	return true;
+}
+EXPORT_SYMBOL(target_configure_unmap_from_queue);
+
+/*
+ * Convert from blocksize advertised to the initiator to the 512 byte
+ * units unconditionally used by the Linux block layer.
+ */
+sector_t target_to_linux_sector(struct se_device *dev, sector_t lb)
+{
+	switch (dev->dev_attrib.block_size) {
+	case 4096:
+		return lb << 3;
+	case 2048:
+		return lb << 2;
+	case 1024:
+		return lb << 1;
+	default:
+		return lb;
+	}
+}
+EXPORT_SYMBOL(target_to_linux_sector);
+
 int target_configure_device(struct se_device *dev)
 {
 	struct se_hba *hba = dev->se_hba;
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index e319570..75f0f08 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -160,25 +160,11 @@
 			" block_device blocks: %llu logical_block_size: %d\n",
 			dev_size, div_u64(dev_size, fd_dev->fd_block_size),
 			fd_dev->fd_block_size);
-		/*
-		 * Check if the underlying struct block_device request_queue supports
-		 * the QUEUE_FLAG_DISCARD bit for UNMAP/WRITE_SAME in SCSI + TRIM
-		 * in ATA and we need to set TPE=1
-		 */
-		if (blk_queue_discard(q)) {
-			dev->dev_attrib.max_unmap_lba_count =
-				q->limits.max_discard_sectors;
-			/*
-			 * Currently hardcoded to 1 in Linux/SCSI code..
-			 */
-			dev->dev_attrib.max_unmap_block_desc_count = 1;
-			dev->dev_attrib.unmap_granularity =
-				q->limits.discard_granularity >> 9;
-			dev->dev_attrib.unmap_granularity_alignment =
-				q->limits.discard_alignment;
+
+		if (target_configure_unmap_from_queue(&dev->dev_attrib, q,
+						      fd_dev->fd_block_size))
 			pr_debug("IFILE: BLOCK Discard support available,"
-					" disabled by default\n");
-		}
+				 " disabled by default\n");
 		/*
 		 * Enable write same emulation for IBLOCK and use 0xFFFF as
 		 * the smaller WRITE_SAME(10) only has a two-byte block count.
@@ -490,9 +476,12 @@
 	if (S_ISBLK(inode->i_mode)) {
 		/* The backend is block device, use discard */
 		struct block_device *bdev = inode->i_bdev;
+		struct se_device *dev = cmd->se_dev;
 
-		ret = blkdev_issue_discard(bdev, lba,
-				nolb, GFP_KERNEL, 0);
+		ret = blkdev_issue_discard(bdev,
+					   target_to_linux_sector(dev, lba),
+					   target_to_linux_sector(dev,  nolb),
+					   GFP_KERNEL, 0);
 		if (ret < 0) {
 			pr_warn("FILEIO: blkdev_issue_discard() failed: %d\n",
 				ret);
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 5a2899f..abe4eb9 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -121,29 +121,11 @@
 	dev->dev_attrib.hw_max_sectors = queue_max_hw_sectors(q);
 	dev->dev_attrib.hw_queue_depth = q->nr_requests;
 
-	/*
-	 * Check if the underlying struct block_device request_queue supports
-	 * the QUEUE_FLAG_DISCARD bit for UNMAP/WRITE_SAME in SCSI + TRIM
-	 * in ATA and we need to set TPE=1
-	 */
-	if (blk_queue_discard(q)) {
-		dev->dev_attrib.max_unmap_lba_count =
-				q->limits.max_discard_sectors;
-
-		/*
-		 * Currently hardcoded to 1 in Linux/SCSI code..
-		 */
-		dev->dev_attrib.max_unmap_block_desc_count = 1;
-		dev->dev_attrib.unmap_granularity =
-				q->limits.discard_granularity >> 9;
-		dev->dev_attrib.unmap_granularity_alignment =
-				q->limits.discard_alignment;
-		dev->dev_attrib.unmap_zeroes_data =
-				q->limits.discard_zeroes_data;
-
+	if (target_configure_unmap_from_queue(&dev->dev_attrib, q,
+					      dev->dev_attrib.hw_block_size))
 		pr_debug("IBLOCK: BLOCK Discard support available,"
-				" disabled by default\n");
-	}
+			 " disabled by default\n");
+
 	/*
 	 * Enable write same emulation for IBLOCK and use 0xFFFF as
 	 * the smaller WRITE_SAME(10) only has a two-byte block count.
@@ -415,9 +397,13 @@
 iblock_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb)
 {
 	struct block_device *bdev = IBLOCK_DEV(cmd->se_dev)->ibd_bd;
+	struct se_device *dev = cmd->se_dev;
 	int ret;
 
-	ret = blkdev_issue_discard(bdev, lba, nolb, GFP_KERNEL, 0);
+	ret = blkdev_issue_discard(bdev,
+				   target_to_linux_sector(dev, lba),
+				   target_to_linux_sector(dev,  nolb),
+				   GFP_KERNEL, 0);
 	if (ret < 0) {
 		pr_err("blkdev_issue_discard() failed: %d\n", ret);
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
@@ -433,8 +419,10 @@
 	struct scatterlist *sg;
 	struct bio *bio;
 	struct bio_list list;
-	sector_t block_lba = cmd->t_task_lba;
-	sector_t sectors = sbc_get_write_same_sectors(cmd);
+	struct se_device *dev = cmd->se_dev;
+	sector_t block_lba = target_to_linux_sector(dev, cmd->t_task_lba);
+	sector_t sectors = target_to_linux_sector(dev,
+					sbc_get_write_same_sectors(cmd));
 
 	if (cmd->prot_op) {
 		pr_err("WRITE_SAME: Protection information with IBLOCK"
@@ -648,12 +636,12 @@
 		  enum dma_data_direction data_direction)
 {
 	struct se_device *dev = cmd->se_dev;
+	sector_t block_lba = target_to_linux_sector(dev, cmd->t_task_lba);
 	struct iblock_req *ibr;
 	struct bio *bio, *bio_start;
 	struct bio_list list;
 	struct scatterlist *sg;
 	u32 sg_num = sgl_nents;
-	sector_t block_lba;
 	unsigned bio_cnt;
 	int rw = 0;
 	int i;
@@ -679,24 +667,6 @@
 		rw = READ;
 	}
 
-	/*
-	 * Convert the blocksize advertised to the initiator to the 512 byte
-	 * units unconditionally used by the Linux block layer.
-	 */
-	if (dev->dev_attrib.block_size == 4096)
-		block_lba = (cmd->t_task_lba << 3);
-	else if (dev->dev_attrib.block_size == 2048)
-		block_lba = (cmd->t_task_lba << 2);
-	else if (dev->dev_attrib.block_size == 1024)
-		block_lba = (cmd->t_task_lba << 1);
-	else if (dev->dev_attrib.block_size == 512)
-		block_lba = cmd->t_task_lba;
-	else {
-		pr_err("Unsupported SCSI -> BLOCK LBA conversion:"
-				" %u\n", dev->dev_attrib.block_size);
-		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-	}
-
 	ibr = kzalloc(sizeof(struct iblock_req), GFP_KERNEL);
 	if (!ibr)
 		goto fail;
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index dae0750c..db4412f 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -141,7 +141,6 @@
 int	transport_dump_vpd_assoc(struct t10_vpd *, unsigned char *, int);
 int	transport_dump_vpd_ident_type(struct t10_vpd *, unsigned char *, int);
 int	transport_dump_vpd_ident(struct t10_vpd *, unsigned char *, int);
-bool	target_stop_cmd(struct se_cmd *cmd, unsigned long *flags);
 void	transport_clear_lun_ref(struct se_lun *);
 void	transport_send_task_abort(struct se_cmd *);
 sense_reason_t	target_cmd_size_check(struct se_cmd *cmd, unsigned int size);
diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index fcdcb11..82a663b 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -68,23 +68,25 @@
 
 	if (dev) {
 		spin_lock_irqsave(&dev->se_tmr_lock, flags);
-		list_del(&tmr->tmr_list);
+		list_del_init(&tmr->tmr_list);
 		spin_unlock_irqrestore(&dev->se_tmr_lock, flags);
 	}
 
 	kfree(tmr);
 }
 
-static void core_tmr_handle_tas_abort(
-	struct se_node_acl *tmr_nacl,
-	struct se_cmd *cmd,
-	int tas)
+static void core_tmr_handle_tas_abort(struct se_cmd *cmd, int tas)
 {
-	bool remove = true;
+	unsigned long flags;
+	bool remove = true, send_tas;
 	/*
 	 * TASK ABORTED status (TAS) bit support
 	 */
-	if ((tmr_nacl && (tmr_nacl != cmd->se_sess->se_node_acl)) && tas) {
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	send_tas = (cmd->transport_state & CMD_T_TAS);
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+
+	if (send_tas) {
 		remove = false;
 		transport_send_task_abort(cmd);
 	}
@@ -107,6 +109,46 @@
 	return 1;
 }
 
+static bool __target_check_io_state(struct se_cmd *se_cmd,
+				    struct se_session *tmr_sess, int tas)
+{
+	struct se_session *sess = se_cmd->se_sess;
+
+	assert_spin_locked(&sess->sess_cmd_lock);
+	WARN_ON_ONCE(!irqs_disabled());
+	/*
+	 * If command already reached CMD_T_COMPLETE state within
+	 * target_complete_cmd() or CMD_T_FABRIC_STOP due to shutdown,
+	 * this se_cmd has been passed to fabric driver and will
+	 * not be aborted.
+	 *
+	 * Otherwise, obtain a local se_cmd->cmd_kref now for TMR
+	 * ABORT_TASK + LUN_RESET for CMD_T_ABORTED processing as
+	 * long as se_cmd->cmd_kref is still active unless zero.
+	 */
+	spin_lock(&se_cmd->t_state_lock);
+	if (se_cmd->transport_state & (CMD_T_COMPLETE | CMD_T_FABRIC_STOP)) {
+		pr_debug("Attempted to abort io tag: %llu already complete or"
+			" fabric stop, skipping\n", se_cmd->tag);
+		spin_unlock(&se_cmd->t_state_lock);
+		return false;
+	}
+	if (sess->sess_tearing_down || se_cmd->cmd_wait_set) {
+		pr_debug("Attempted to abort io tag: %llu already shutdown,"
+			" skipping\n", se_cmd->tag);
+		spin_unlock(&se_cmd->t_state_lock);
+		return false;
+	}
+	se_cmd->transport_state |= CMD_T_ABORTED;
+
+	if ((tmr_sess != se_cmd->se_sess) && tas)
+		se_cmd->transport_state |= CMD_T_TAS;
+
+	spin_unlock(&se_cmd->t_state_lock);
+
+	return kref_get_unless_zero(&se_cmd->cmd_kref);
+}
+
 void core_tmr_abort_task(
 	struct se_device *dev,
 	struct se_tmr_req *tmr,
@@ -130,34 +172,22 @@
 		if (tmr->ref_task_tag != ref_tag)
 			continue;
 
-		if (!kref_get_unless_zero(&se_cmd->cmd_kref))
-			continue;
-
 		printk("ABORT_TASK: Found referenced %s task_tag: %llu\n",
 			se_cmd->se_tfo->get_fabric_name(), ref_tag);
 
-		spin_lock(&se_cmd->t_state_lock);
-		if (se_cmd->transport_state & CMD_T_COMPLETE) {
-			printk("ABORT_TASK: ref_tag: %llu already complete,"
-			       " skipping\n", ref_tag);
-			spin_unlock(&se_cmd->t_state_lock);
+		if (!__target_check_io_state(se_cmd, se_sess, 0)) {
 			spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
-
 			target_put_sess_cmd(se_cmd);
-
 			goto out;
 		}
-		se_cmd->transport_state |= CMD_T_ABORTED;
-		spin_unlock(&se_cmd->t_state_lock);
-
 		list_del_init(&se_cmd->se_cmd_list);
 		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 
 		cancel_work_sync(&se_cmd->work);
 		transport_wait_for_tasks(se_cmd);
 
-		target_put_sess_cmd(se_cmd);
 		transport_cmd_finish_abort(se_cmd, true);
+		target_put_sess_cmd(se_cmd);
 
 		printk("ABORT_TASK: Sending TMR_FUNCTION_COMPLETE for"
 				" ref_tag: %llu\n", ref_tag);
@@ -178,9 +208,11 @@
 	struct list_head *preempt_and_abort_list)
 {
 	LIST_HEAD(drain_tmr_list);
+	struct se_session *sess;
 	struct se_tmr_req *tmr_p, *tmr_pp;
 	struct se_cmd *cmd;
 	unsigned long flags;
+	bool rc;
 	/*
 	 * Release all pending and outgoing TMRs aside from the received
 	 * LUN_RESET tmr..
@@ -206,17 +238,39 @@
 		if (target_check_cdb_and_preempt(preempt_and_abort_list, cmd))
 			continue;
 
+		sess = cmd->se_sess;
+		if (WARN_ON_ONCE(!sess))
+			continue;
+
+		spin_lock(&sess->sess_cmd_lock);
 		spin_lock(&cmd->t_state_lock);
-		if (!(cmd->transport_state & CMD_T_ACTIVE)) {
+		if (!(cmd->transport_state & CMD_T_ACTIVE) ||
+		     (cmd->transport_state & CMD_T_FABRIC_STOP)) {
 			spin_unlock(&cmd->t_state_lock);
+			spin_unlock(&sess->sess_cmd_lock);
 			continue;
 		}
 		if (cmd->t_state == TRANSPORT_ISTATE_PROCESSING) {
 			spin_unlock(&cmd->t_state_lock);
+			spin_unlock(&sess->sess_cmd_lock);
 			continue;
 		}
+		if (sess->sess_tearing_down || cmd->cmd_wait_set) {
+			spin_unlock(&cmd->t_state_lock);
+			spin_unlock(&sess->sess_cmd_lock);
+			continue;
+		}
+		cmd->transport_state |= CMD_T_ABORTED;
 		spin_unlock(&cmd->t_state_lock);
 
+		rc = kref_get_unless_zero(&cmd->cmd_kref);
+		if (!rc) {
+			printk("LUN_RESET TMR: non-zero kref_get_unless_zero\n");
+			spin_unlock(&sess->sess_cmd_lock);
+			continue;
+		}
+		spin_unlock(&sess->sess_cmd_lock);
+
 		list_move_tail(&tmr_p->tmr_list, &drain_tmr_list);
 	}
 	spin_unlock_irqrestore(&dev->se_tmr_lock, flags);
@@ -230,20 +284,26 @@
 			(preempt_and_abort_list) ? "Preempt" : "", tmr_p,
 			tmr_p->function, tmr_p->response, cmd->t_state);
 
+		cancel_work_sync(&cmd->work);
+		transport_wait_for_tasks(cmd);
+
 		transport_cmd_finish_abort(cmd, 1);
+		target_put_sess_cmd(cmd);
 	}
 }
 
 static void core_tmr_drain_state_list(
 	struct se_device *dev,
 	struct se_cmd *prout_cmd,
-	struct se_node_acl *tmr_nacl,
+	struct se_session *tmr_sess,
 	int tas,
 	struct list_head *preempt_and_abort_list)
 {
 	LIST_HEAD(drain_task_list);
+	struct se_session *sess;
 	struct se_cmd *cmd, *next;
 	unsigned long flags;
+	int rc;
 
 	/*
 	 * Complete outstanding commands with TASK_ABORTED SAM status.
@@ -282,6 +342,16 @@
 		if (prout_cmd == cmd)
 			continue;
 
+		sess = cmd->se_sess;
+		if (WARN_ON_ONCE(!sess))
+			continue;
+
+		spin_lock(&sess->sess_cmd_lock);
+		rc = __target_check_io_state(cmd, tmr_sess, tas);
+		spin_unlock(&sess->sess_cmd_lock);
+		if (!rc)
+			continue;
+
 		list_move_tail(&cmd->state_list, &drain_task_list);
 		cmd->state_active = false;
 	}
@@ -289,7 +359,7 @@
 
 	while (!list_empty(&drain_task_list)) {
 		cmd = list_entry(drain_task_list.next, struct se_cmd, state_list);
-		list_del(&cmd->state_list);
+		list_del_init(&cmd->state_list);
 
 		pr_debug("LUN_RESET: %s cmd: %p"
 			" ITT/CmdSN: 0x%08llx/0x%08x, i_state: %d, t_state: %d"
@@ -313,16 +383,11 @@
 		 * loop above, but we do it down here given that
 		 * cancel_work_sync may block.
 		 */
-		if (cmd->t_state == TRANSPORT_COMPLETE)
-			cancel_work_sync(&cmd->work);
+		cancel_work_sync(&cmd->work);
+		transport_wait_for_tasks(cmd);
 
-		spin_lock_irqsave(&cmd->t_state_lock, flags);
-		target_stop_cmd(cmd, &flags);
-
-		cmd->transport_state |= CMD_T_ABORTED;
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-
-		core_tmr_handle_tas_abort(tmr_nacl, cmd, tas);
+		core_tmr_handle_tas_abort(cmd, tas);
+		target_put_sess_cmd(cmd);
 	}
 }
 
@@ -334,6 +399,7 @@
 {
 	struct se_node_acl *tmr_nacl = NULL;
 	struct se_portal_group *tmr_tpg = NULL;
+	struct se_session *tmr_sess = NULL;
 	int tas;
         /*
 	 * TASK_ABORTED status bit, this is configurable via ConfigFS
@@ -352,8 +418,9 @@
 	 * or struct se_device passthrough..
 	 */
 	if (tmr && tmr->task_cmd && tmr->task_cmd->se_sess) {
-		tmr_nacl = tmr->task_cmd->se_sess->se_node_acl;
-		tmr_tpg = tmr->task_cmd->se_sess->se_tpg;
+		tmr_sess = tmr->task_cmd->se_sess;
+		tmr_nacl = tmr_sess->se_node_acl;
+		tmr_tpg = tmr_sess->se_tpg;
 		if (tmr_nacl && tmr_tpg) {
 			pr_debug("LUN_RESET: TMR caller fabric: %s"
 				" initiator port %s\n",
@@ -366,7 +433,7 @@
 		dev->transport->name, tas);
 
 	core_tmr_drain_tmr_list(dev, tmr, preempt_and_abort_list);
-	core_tmr_drain_state_list(dev, prout_cmd, tmr_nacl, tas,
+	core_tmr_drain_state_list(dev, prout_cmd, tmr_sess, tas,
 				preempt_and_abort_list);
 
 	/*
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 9f3608e..867bc6d 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -534,9 +534,6 @@
 }
 EXPORT_SYMBOL(transport_deregister_session);
 
-/*
- * Called with cmd->t_state_lock held.
- */
 static void target_remove_from_state_list(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
@@ -561,10 +558,6 @@
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&cmd->t_state_lock, flags);
-	if (write_pending)
-		cmd->t_state = TRANSPORT_WRITE_PENDING;
-
 	if (remove_from_lists) {
 		target_remove_from_state_list(cmd);
 
@@ -574,6 +567,10 @@
 		cmd->se_lun = NULL;
 	}
 
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	if (write_pending)
+		cmd->t_state = TRANSPORT_WRITE_PENDING;
+
 	/*
 	 * Determine if frontend context caller is requesting the stopping of
 	 * this command for frontend exceptions.
@@ -627,6 +624,8 @@
 
 void transport_cmd_finish_abort(struct se_cmd *cmd, int remove)
 {
+	bool ack_kref = (cmd->se_cmd_flags & SCF_ACK_KREF);
+
 	if (cmd->se_cmd_flags & SCF_SE_LUN_CMD)
 		transport_lun_remove_cmd(cmd);
 	/*
@@ -638,7 +637,7 @@
 
 	if (transport_cmd_check_stop_to_fabric(cmd))
 		return;
-	if (remove)
+	if (remove && ack_kref)
 		transport_put_cmd(cmd);
 }
 
@@ -694,19 +693,10 @@
 	}
 
 	/*
-	 * See if we are waiting to complete for an exception condition.
-	 */
-	if (cmd->transport_state & CMD_T_REQUEST_STOP) {
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-		complete(&cmd->task_stop_comp);
-		return;
-	}
-
-	/*
 	 * Check for case where an explicit ABORT_TASK has been received
 	 * and transport_wait_for_tasks() will be waiting for completion..
 	 */
-	if (cmd->transport_state & CMD_T_ABORTED &&
+	if (cmd->transport_state & CMD_T_ABORTED ||
 	    cmd->transport_state & CMD_T_STOP) {
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 		complete_all(&cmd->t_transport_stop_comp);
@@ -721,10 +711,10 @@
 	cmd->transport_state |= (CMD_T_COMPLETE | CMD_T_ACTIVE);
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
-	if (cmd->cpuid == -1)
-		queue_work(target_completion_wq, &cmd->work);
-	else
+	if (cmd->se_cmd_flags & SCF_USE_CPUID)
 		queue_work_on(cmd->cpuid, target_completion_wq, &cmd->work);
+	else
+		queue_work(target_completion_wq, &cmd->work);
 }
 EXPORT_SYMBOL(target_complete_cmd);
 
@@ -1203,7 +1193,6 @@
 	INIT_LIST_HEAD(&cmd->state_list);
 	init_completion(&cmd->t_transport_stop_comp);
 	init_completion(&cmd->cmd_wait_comp);
-	init_completion(&cmd->task_stop_comp);
 	spin_lock_init(&cmd->t_state_lock);
 	kref_init(&cmd->cmd_kref);
 	cmd->transport_state = CMD_T_DEV_ACTIVE;
@@ -1437,6 +1426,12 @@
 	 */
 	transport_init_se_cmd(se_cmd, se_tpg->se_tpg_tfo, se_sess,
 				data_length, data_dir, task_attr, sense);
+
+	if (flags & TARGET_SCF_USE_CPUID)
+		se_cmd->se_cmd_flags |= SCF_USE_CPUID;
+	else
+		se_cmd->cpuid = WORK_CPU_UNBOUND;
+
 	if (flags & TARGET_SCF_UNKNOWN_SIZE)
 		se_cmd->unknown_data_length = 1;
 	/*
@@ -1635,33 +1630,6 @@
 EXPORT_SYMBOL(target_submit_tmr);
 
 /*
- * If the cmd is active, request it to be stopped and sleep until it
- * has completed.
- */
-bool target_stop_cmd(struct se_cmd *cmd, unsigned long *flags)
-	__releases(&cmd->t_state_lock)
-	__acquires(&cmd->t_state_lock)
-{
-	bool was_active = false;
-
-	if (cmd->transport_state & CMD_T_BUSY) {
-		cmd->transport_state |= CMD_T_REQUEST_STOP;
-		spin_unlock_irqrestore(&cmd->t_state_lock, *flags);
-
-		pr_debug("cmd %p waiting to complete\n", cmd);
-		wait_for_completion(&cmd->task_stop_comp);
-		pr_debug("cmd %p stopped successfully\n", cmd);
-
-		spin_lock_irqsave(&cmd->t_state_lock, *flags);
-		cmd->transport_state &= ~CMD_T_REQUEST_STOP;
-		cmd->transport_state &= ~CMD_T_BUSY;
-		was_active = true;
-	}
-
-	return was_active;
-}
-
-/*
  * Handle SAM-esque emulation for generic transport request failures.
  */
 void transport_generic_request_failure(struct se_cmd *cmd,
@@ -1859,19 +1827,21 @@
 	return true;
 }
 
+static int __transport_check_aborted_status(struct se_cmd *, int);
+
 void target_execute_cmd(struct se_cmd *cmd)
 {
 	/*
-	 * If the received CDB has aleady been aborted stop processing it here.
-	 */
-	if (transport_check_aborted_status(cmd, 1))
-		return;
-
-	/*
 	 * Determine if frontend context caller is requesting the stopping of
 	 * this command for frontend exceptions.
+	 *
+	 * If the received CDB has aleady been aborted stop processing it here.
 	 */
 	spin_lock_irq(&cmd->t_state_lock);
+	if (__transport_check_aborted_status(cmd, 1)) {
+		spin_unlock_irq(&cmd->t_state_lock);
+		return;
+	}
 	if (cmd->transport_state & CMD_T_STOP) {
 		pr_debug("%s:%d CMD_T_STOP for ITT: 0x%08llx\n",
 			__func__, __LINE__, cmd->tag);
@@ -2222,28 +2192,6 @@
 }
 
 /**
- * transport_release_cmd - free a command
- * @cmd:       command to free
- *
- * This routine unconditionally frees a command, and reference counting
- * or list removal must be done in the caller.
- */
-static int transport_release_cmd(struct se_cmd *cmd)
-{
-	BUG_ON(!cmd->se_tfo);
-
-	if (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)
-		core_tmr_release_req(cmd->se_tmr_req);
-	if (cmd->t_task_cdb != cmd->__t_task_cdb)
-		kfree(cmd->t_task_cdb);
-	/*
-	 * If this cmd has been setup with target_get_sess_cmd(), drop
-	 * the kref and call ->release_cmd() in kref callback.
-	 */
-	return target_put_sess_cmd(cmd);
-}
-
-/**
  * transport_put_cmd - release a reference to a command
  * @cmd:       command to release
  *
@@ -2251,8 +2199,12 @@
  */
 static int transport_put_cmd(struct se_cmd *cmd)
 {
-	transport_free_pages(cmd);
-	return transport_release_cmd(cmd);
+	BUG_ON(!cmd->se_tfo);
+	/*
+	 * If this cmd has been setup with target_get_sess_cmd(), drop
+	 * the kref and call ->release_cmd() in kref callback.
+	 */
+	return target_put_sess_cmd(cmd);
 }
 
 void *transport_kmap_data_sg(struct se_cmd *cmd)
@@ -2450,34 +2402,58 @@
 	}
 }
 
-int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
+static bool
+__transport_wait_for_tasks(struct se_cmd *, bool, bool *, bool *,
+			   unsigned long *flags);
+
+static void target_wait_free_cmd(struct se_cmd *cmd, bool *aborted, bool *tas)
 {
 	unsigned long flags;
+
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	__transport_wait_for_tasks(cmd, true, aborted, tas, &flags);
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+}
+
+int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
+{
 	int ret = 0;
+	bool aborted = false, tas = false;
 
 	if (!(cmd->se_cmd_flags & SCF_SE_LUN_CMD)) {
 		if (wait_for_tasks && (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB))
-			 transport_wait_for_tasks(cmd);
+			target_wait_free_cmd(cmd, &aborted, &tas);
 
-		ret = transport_release_cmd(cmd);
+		if (!aborted || tas)
+			ret = transport_put_cmd(cmd);
 	} else {
 		if (wait_for_tasks)
-			transport_wait_for_tasks(cmd);
+			target_wait_free_cmd(cmd, &aborted, &tas);
 		/*
 		 * Handle WRITE failure case where transport_generic_new_cmd()
 		 * has already added se_cmd to state_list, but fabric has
 		 * failed command before I/O submission.
 		 */
-		if (cmd->state_active) {
-			spin_lock_irqsave(&cmd->t_state_lock, flags);
+		if (cmd->state_active)
 			target_remove_from_state_list(cmd);
-			spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-		}
 
 		if (cmd->se_lun)
 			transport_lun_remove_cmd(cmd);
 
-		ret = transport_put_cmd(cmd);
+		if (!aborted || tas)
+			ret = transport_put_cmd(cmd);
+	}
+	/*
+	 * If the task has been internally aborted due to TMR ABORT_TASK
+	 * or LUN_RESET, target_core_tmr.c is responsible for performing
+	 * the remaining calls to target_put_sess_cmd(), and not the
+	 * callers of this function.
+	 */
+	if (aborted) {
+		pr_debug("Detected CMD_T_ABORTED for ITT: %llu\n", cmd->tag);
+		wait_for_completion(&cmd->cmd_wait_comp);
+		cmd->se_tfo->release_cmd(cmd);
+		ret = 1;
 	}
 	return ret;
 }
@@ -2517,26 +2493,46 @@
 }
 EXPORT_SYMBOL(target_get_sess_cmd);
 
+static void target_free_cmd_mem(struct se_cmd *cmd)
+{
+	transport_free_pages(cmd);
+
+	if (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)
+		core_tmr_release_req(cmd->se_tmr_req);
+	if (cmd->t_task_cdb != cmd->__t_task_cdb)
+		kfree(cmd->t_task_cdb);
+}
+
 static void target_release_cmd_kref(struct kref *kref)
 {
 	struct se_cmd *se_cmd = container_of(kref, struct se_cmd, cmd_kref);
 	struct se_session *se_sess = se_cmd->se_sess;
 	unsigned long flags;
+	bool fabric_stop;
 
 	spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
 	if (list_empty(&se_cmd->se_cmd_list)) {
 		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
+		target_free_cmd_mem(se_cmd);
 		se_cmd->se_tfo->release_cmd(se_cmd);
 		return;
 	}
-	if (se_sess->sess_tearing_down && se_cmd->cmd_wait_set) {
+
+	spin_lock(&se_cmd->t_state_lock);
+	fabric_stop = (se_cmd->transport_state & CMD_T_FABRIC_STOP);
+	spin_unlock(&se_cmd->t_state_lock);
+
+	if (se_cmd->cmd_wait_set || fabric_stop) {
+		list_del_init(&se_cmd->se_cmd_list);
 		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
+		target_free_cmd_mem(se_cmd);
 		complete(&se_cmd->cmd_wait_comp);
 		return;
 	}
-	list_del(&se_cmd->se_cmd_list);
+	list_del_init(&se_cmd->se_cmd_list);
 	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 
+	target_free_cmd_mem(se_cmd);
 	se_cmd->se_tfo->release_cmd(se_cmd);
 }
 
@@ -2548,6 +2544,7 @@
 	struct se_session *se_sess = se_cmd->se_sess;
 
 	if (!se_sess) {
+		target_free_cmd_mem(se_cmd);
 		se_cmd->se_tfo->release_cmd(se_cmd);
 		return 1;
 	}
@@ -2564,6 +2561,7 @@
 {
 	struct se_cmd *se_cmd;
 	unsigned long flags;
+	int rc;
 
 	spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
 	if (se_sess->sess_tearing_down) {
@@ -2573,8 +2571,15 @@
 	se_sess->sess_tearing_down = 1;
 	list_splice_init(&se_sess->sess_cmd_list, &se_sess->sess_wait_list);
 
-	list_for_each_entry(se_cmd, &se_sess->sess_wait_list, se_cmd_list)
-		se_cmd->cmd_wait_set = 1;
+	list_for_each_entry(se_cmd, &se_sess->sess_wait_list, se_cmd_list) {
+		rc = kref_get_unless_zero(&se_cmd->cmd_kref);
+		if (rc) {
+			se_cmd->cmd_wait_set = 1;
+			spin_lock(&se_cmd->t_state_lock);
+			se_cmd->transport_state |= CMD_T_FABRIC_STOP;
+			spin_unlock(&se_cmd->t_state_lock);
+		}
+	}
 
 	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 }
@@ -2587,15 +2592,25 @@
 {
 	struct se_cmd *se_cmd, *tmp_cmd;
 	unsigned long flags;
+	bool tas;
 
 	list_for_each_entry_safe(se_cmd, tmp_cmd,
 				&se_sess->sess_wait_list, se_cmd_list) {
-		list_del(&se_cmd->se_cmd_list);
+		list_del_init(&se_cmd->se_cmd_list);
 
 		pr_debug("Waiting for se_cmd: %p t_state: %d, fabric state:"
 			" %d\n", se_cmd, se_cmd->t_state,
 			se_cmd->se_tfo->get_cmd_state(se_cmd));
 
+		spin_lock_irqsave(&se_cmd->t_state_lock, flags);
+		tas = (se_cmd->transport_state & CMD_T_TAS);
+		spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
+
+		if (!target_put_sess_cmd(se_cmd)) {
+			if (tas)
+				target_put_sess_cmd(se_cmd);
+		}
+
 		wait_for_completion(&se_cmd->cmd_wait_comp);
 		pr_debug("After cmd_wait_comp: se_cmd: %p t_state: %d"
 			" fabric state: %d\n", se_cmd, se_cmd->t_state,
@@ -2617,6 +2632,58 @@
 	wait_for_completion(&lun->lun_ref_comp);
 }
 
+static bool
+__transport_wait_for_tasks(struct se_cmd *cmd, bool fabric_stop,
+			   bool *aborted, bool *tas, unsigned long *flags)
+	__releases(&cmd->t_state_lock)
+	__acquires(&cmd->t_state_lock)
+{
+
+	assert_spin_locked(&cmd->t_state_lock);
+	WARN_ON_ONCE(!irqs_disabled());
+
+	if (fabric_stop)
+		cmd->transport_state |= CMD_T_FABRIC_STOP;
+
+	if (cmd->transport_state & CMD_T_ABORTED)
+		*aborted = true;
+
+	if (cmd->transport_state & CMD_T_TAS)
+		*tas = true;
+
+	if (!(cmd->se_cmd_flags & SCF_SE_LUN_CMD) &&
+	    !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB))
+		return false;
+
+	if (!(cmd->se_cmd_flags & SCF_SUPPORTED_SAM_OPCODE) &&
+	    !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB))
+		return false;
+
+	if (!(cmd->transport_state & CMD_T_ACTIVE))
+		return false;
+
+	if (fabric_stop && *aborted)
+		return false;
+
+	cmd->transport_state |= CMD_T_STOP;
+
+	pr_debug("wait_for_tasks: Stopping %p ITT: 0x%08llx i_state: %d,"
+		 " t_state: %d, CMD_T_STOP\n", cmd, cmd->tag,
+		 cmd->se_tfo->get_cmd_state(cmd), cmd->t_state);
+
+	spin_unlock_irqrestore(&cmd->t_state_lock, *flags);
+
+	wait_for_completion(&cmd->t_transport_stop_comp);
+
+	spin_lock_irqsave(&cmd->t_state_lock, *flags);
+	cmd->transport_state &= ~(CMD_T_ACTIVE | CMD_T_STOP);
+
+	pr_debug("wait_for_tasks: Stopped wait_for_completion(&cmd->"
+		 "t_transport_stop_comp) for ITT: 0x%08llx\n", cmd->tag);
+
+	return true;
+}
+
 /**
  * transport_wait_for_tasks - wait for completion to occur
  * @cmd:	command to wait
@@ -2627,43 +2694,13 @@
 bool transport_wait_for_tasks(struct se_cmd *cmd)
 {
 	unsigned long flags;
+	bool ret, aborted = false, tas = false;
 
 	spin_lock_irqsave(&cmd->t_state_lock, flags);
-	if (!(cmd->se_cmd_flags & SCF_SE_LUN_CMD) &&
-	    !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)) {
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-		return false;
-	}
-
-	if (!(cmd->se_cmd_flags & SCF_SUPPORTED_SAM_OPCODE) &&
-	    !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)) {
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-		return false;
-	}
-
-	if (!(cmd->transport_state & CMD_T_ACTIVE)) {
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-		return false;
-	}
-
-	cmd->transport_state |= CMD_T_STOP;
-
-	pr_debug("wait_for_tasks: Stopping %p ITT: 0x%08llx i_state: %d, t_state: %d, CMD_T_STOP\n",
-		cmd, cmd->tag, cmd->se_tfo->get_cmd_state(cmd), cmd->t_state);
-
+	ret = __transport_wait_for_tasks(cmd, false, &aborted, &tas, &flags);
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
-	wait_for_completion(&cmd->t_transport_stop_comp);
-
-	spin_lock_irqsave(&cmd->t_state_lock, flags);
-	cmd->transport_state &= ~(CMD_T_ACTIVE | CMD_T_STOP);
-
-	pr_debug("wait_for_tasks: Stopped wait_for_completion(&cmd->t_transport_stop_comp) for ITT: 0x%08llx\n",
-		cmd->tag);
-
-	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-
-	return true;
+	return ret;
 }
 EXPORT_SYMBOL(transport_wait_for_tasks);
 
@@ -2845,28 +2882,49 @@
 }
 EXPORT_SYMBOL(transport_send_check_condition_and_sense);
 
-int transport_check_aborted_status(struct se_cmd *cmd, int send_status)
+static int __transport_check_aborted_status(struct se_cmd *cmd, int send_status)
+	__releases(&cmd->t_state_lock)
+	__acquires(&cmd->t_state_lock)
 {
+	assert_spin_locked(&cmd->t_state_lock);
+	WARN_ON_ONCE(!irqs_disabled());
+
 	if (!(cmd->transport_state & CMD_T_ABORTED))
 		return 0;
-
 	/*
 	 * If cmd has been aborted but either no status is to be sent or it has
 	 * already been sent, just return
 	 */
-	if (!send_status || !(cmd->se_cmd_flags & SCF_SEND_DELAYED_TAS))
+	if (!send_status || !(cmd->se_cmd_flags & SCF_SEND_DELAYED_TAS)) {
+		if (send_status)
+			cmd->se_cmd_flags |= SCF_SEND_DELAYED_TAS;
 		return 1;
+	}
 
-	pr_debug("Sending delayed SAM_STAT_TASK_ABORTED status for CDB: 0x%02x ITT: 0x%08llx\n",
-		 cmd->t_task_cdb[0], cmd->tag);
+	pr_debug("Sending delayed SAM_STAT_TASK_ABORTED status for CDB:"
+		" 0x%02x ITT: 0x%08llx\n", cmd->t_task_cdb[0], cmd->tag);
 
 	cmd->se_cmd_flags &= ~SCF_SEND_DELAYED_TAS;
 	cmd->scsi_status = SAM_STAT_TASK_ABORTED;
 	trace_target_cmd_complete(cmd);
+
+	spin_unlock_irq(&cmd->t_state_lock);
 	cmd->se_tfo->queue_status(cmd);
+	spin_lock_irq(&cmd->t_state_lock);
 
 	return 1;
 }
+
+int transport_check_aborted_status(struct se_cmd *cmd, int send_status)
+{
+	int ret;
+
+	spin_lock_irq(&cmd->t_state_lock);
+	ret = __transport_check_aborted_status(cmd, send_status);
+	spin_unlock_irq(&cmd->t_state_lock);
+
+	return ret;
+}
 EXPORT_SYMBOL(transport_check_aborted_status);
 
 void transport_send_task_abort(struct se_cmd *cmd)
@@ -2888,11 +2946,17 @@
 	 */
 	if (cmd->data_direction == DMA_TO_DEVICE) {
 		if (cmd->se_tfo->write_pending_status(cmd) != 0) {
-			cmd->transport_state |= CMD_T_ABORTED;
+			spin_lock_irqsave(&cmd->t_state_lock, flags);
+			if (cmd->se_cmd_flags & SCF_SEND_DELAYED_TAS) {
+				spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+				goto send_abort;
+			}
 			cmd->se_cmd_flags |= SCF_SEND_DELAYED_TAS;
+			spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 			return;
 		}
 	}
+send_abort:
 	cmd->scsi_status = SAM_STAT_TASK_ABORTED;
 
 	transport_lun_remove_cmd(cmd);
@@ -2909,8 +2973,17 @@
 	struct se_cmd *cmd = container_of(work, struct se_cmd, work);
 	struct se_device *dev = cmd->se_dev;
 	struct se_tmr_req *tmr = cmd->se_tmr_req;
+	unsigned long flags;
 	int ret;
 
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	if (cmd->transport_state & CMD_T_ABORTED) {
+		tmr->response = TMR_FUNCTION_REJECTED;
+		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+		goto check_stop;
+	}
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+
 	switch (tmr->function) {
 	case TMR_ABORT_TASK:
 		core_tmr_abort_task(dev, tmr, cmd->se_sess);
@@ -2943,9 +3016,17 @@
 		break;
 	}
 
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	if (cmd->transport_state & CMD_T_ABORTED) {
+		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+		goto check_stop;
+	}
 	cmd->t_state = TRANSPORT_ISTATE_PROCESSING;
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+
 	cmd->se_tfo->queue_tm_rsp(cmd);
 
+check_stop:
 	transport_cmd_check_stop_to_fabric(cmd);
 }
 
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index dd600e5..94f5154 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -903,7 +903,7 @@
 	info->version = __stringify(TCMU_MAILBOX_VERSION);
 
 	info->mem[0].name = "tcm-user command & data buffer";
-	info->mem[0].addr = (phys_addr_t) udev->mb_addr;
+	info->mem[0].addr = (phys_addr_t)(uintptr_t)udev->mb_addr;
 	info->mem[0].size = TCMU_RING_SIZE;
 	info->mem[0].memtype = UIO_MEM_VIRTUAL;
 
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 8cc4ac6..7c92c09 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -195,7 +195,7 @@
 	  passive trip is crossed.
 
 config SPEAR_THERMAL
-	bool "SPEAr thermal sensor driver"
+	tristate "SPEAr thermal sensor driver"
 	depends on PLAT_SPEAR || COMPILE_TEST
 	depends on OF
 	help
@@ -237,8 +237,8 @@
 	  framework.
 
 config DB8500_THERMAL
-	bool "DB8500 thermal management"
-	depends on ARCH_U8500
+	tristate "DB8500 thermal management"
+	depends on MFD_DB8500_PRCMU
 	default y
 	help
 	  Adds DB8500 thermal management implementation according to the thermal
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index e3fbc5a..6ceac4f 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -377,26 +377,28 @@
  * get_load() - get load for a cpu since last updated
  * @cpufreq_device:	&struct cpufreq_cooling_device for this cpu
  * @cpu:	cpu number
+ * @cpu_idx:	index of the cpu in cpufreq_device->allowed_cpus
  *
  * Return: The average load of cpu @cpu in percentage since this
  * function was last called.
  */
-static u32 get_load(struct cpufreq_cooling_device *cpufreq_device, int cpu)
+static u32 get_load(struct cpufreq_cooling_device *cpufreq_device, int cpu,
+		    int cpu_idx)
 {
 	u32 load;
 	u64 now, now_idle, delta_time, delta_idle;
 
 	now_idle = get_cpu_idle_time(cpu, &now, 0);
-	delta_idle = now_idle - cpufreq_device->time_in_idle[cpu];
-	delta_time = now - cpufreq_device->time_in_idle_timestamp[cpu];
+	delta_idle = now_idle - cpufreq_device->time_in_idle[cpu_idx];
+	delta_time = now - cpufreq_device->time_in_idle_timestamp[cpu_idx];
 
 	if (delta_time <= delta_idle)
 		load = 0;
 	else
 		load = div64_u64(100 * (delta_time - delta_idle), delta_time);
 
-	cpufreq_device->time_in_idle[cpu] = now_idle;
-	cpufreq_device->time_in_idle_timestamp[cpu] = now;
+	cpufreq_device->time_in_idle[cpu_idx] = now_idle;
+	cpufreq_device->time_in_idle_timestamp[cpu_idx] = now;
 
 	return load;
 }
@@ -598,7 +600,7 @@
 		u32 load;
 
 		if (cpu_online(cpu))
-			load = get_load(cpufreq_device, cpu);
+			load = get_load(cpufreq_device, cpu, i);
 		else
 			load = 0;
 
diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c
index be4eedc..9043f8f 100644
--- a/drivers/thermal/of-thermal.c
+++ b/drivers/thermal/of-thermal.c
@@ -475,14 +475,10 @@
 
 	sensor_np = of_node_get(dev->of_node);
 
-	for_each_child_of_node(np, child) {
+	for_each_available_child_of_node(np, child) {
 		struct of_phandle_args sensor_specs;
 		int ret, id;
 
-		/* Check whether child is enabled or not */
-		if (!of_device_is_available(child))
-			continue;
-
 		/* For now, thermal framework supports only 1 sensor per zone */
 		ret = of_parse_phandle_with_args(child, "thermal-sensors",
 						 "#thermal-sensor-cells",
@@ -881,16 +877,12 @@
 		return 0; /* Run successfully on systems without thermal DT */
 	}
 
-	for_each_child_of_node(np, child) {
+	for_each_available_child_of_node(np, child) {
 		struct thermal_zone_device *zone;
 		struct thermal_zone_params *tzp;
 		int i, mask = 0;
 		u32 prop;
 
-		/* Check whether child is enabled or not */
-		if (!of_device_is_available(child))
-			continue;
-
 		tz = thermal_of_build_thermal_zone(child);
 		if (IS_ERR(tz)) {
 			pr_err("failed to build thermal zone %s: %ld\n",
@@ -968,13 +960,9 @@
 		return;
 	}
 
-	for_each_child_of_node(np, child) {
+	for_each_available_child_of_node(np, child) {
 		struct thermal_zone_device *zone;
 
-		/* Check whether child is enabled or not */
-		if (!of_device_is_available(child))
-			continue;
-
 		zone = thermal_zone_get_zone_by_name(child->name);
 		if (IS_ERR(zone))
 			continue;
diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c
index 44b9c48..0e735ac 100644
--- a/drivers/thermal/rcar_thermal.c
+++ b/drivers/thermal/rcar_thermal.c
@@ -23,6 +23,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/reboot.h>
@@ -75,8 +76,10 @@
 #define rcar_has_irq_support(priv)	((priv)->common->base)
 #define rcar_id_to_shift(priv)		((priv)->id * 8)
 
+#define USE_OF_THERMAL	1
 static const struct of_device_id rcar_thermal_dt_ids[] = {
 	{ .compatible = "renesas,rcar-thermal", },
+	{ .compatible = "renesas,rcar-gen2-thermal", .data = (void *)USE_OF_THERMAL },
 	{},
 };
 MODULE_DEVICE_TABLE(of, rcar_thermal_dt_ids);
@@ -200,9 +203,9 @@
 	return ret;
 }
 
-static int rcar_thermal_get_temp(struct thermal_zone_device *zone, int *temp)
+static int rcar_thermal_get_current_temp(struct rcar_thermal_priv *priv,
+					 int *temp)
 {
-	struct rcar_thermal_priv *priv = rcar_zone_to_priv(zone);
 	int tmp;
 	int ret;
 
@@ -226,6 +229,20 @@
 	return 0;
 }
 
+static int rcar_thermal_of_get_temp(void *data, int *temp)
+{
+	struct rcar_thermal_priv *priv = data;
+
+	return rcar_thermal_get_current_temp(priv, temp);
+}
+
+static int rcar_thermal_get_temp(struct thermal_zone_device *zone, int *temp)
+{
+	struct rcar_thermal_priv *priv = rcar_zone_to_priv(zone);
+
+	return rcar_thermal_get_current_temp(priv, temp);
+}
+
 static int rcar_thermal_get_trip_type(struct thermal_zone_device *zone,
 				      int trip, enum thermal_trip_type *type)
 {
@@ -282,6 +299,10 @@
 	return 0;
 }
 
+static const struct thermal_zone_of_device_ops rcar_thermal_zone_of_ops = {
+	.get_temp	= rcar_thermal_of_get_temp,
+};
+
 static struct thermal_zone_device_ops rcar_thermal_zone_ops = {
 	.get_temp	= rcar_thermal_get_temp,
 	.get_trip_type	= rcar_thermal_get_trip_type,
@@ -318,14 +339,20 @@
 
 	priv = container_of(work, struct rcar_thermal_priv, work.work);
 
-	rcar_thermal_get_temp(priv->zone, &cctemp);
+	ret = rcar_thermal_get_current_temp(priv, &cctemp);
+	if (ret < 0)
+		return;
+
 	ret = rcar_thermal_update_temp(priv);
 	if (ret < 0)
 		return;
 
 	rcar_thermal_irq_enable(priv);
 
-	rcar_thermal_get_temp(priv->zone, &nctemp);
+	ret = rcar_thermal_get_current_temp(priv, &nctemp);
+	if (ret < 0)
+		return;
+
 	if (nctemp != cctemp)
 		thermal_zone_device_update(priv->zone);
 }
@@ -403,6 +430,8 @@
 	struct rcar_thermal_priv *priv;
 	struct device *dev = &pdev->dev;
 	struct resource *res, *irq;
+	const struct of_device_id *of_id = of_match_device(rcar_thermal_dt_ids, dev);
+	unsigned long of_data = (unsigned long)of_id->data;
 	int mres = 0;
 	int i;
 	int ret = -ENODEV;
@@ -463,7 +492,13 @@
 		if (ret < 0)
 			goto error_unregister;
 
-		priv->zone = thermal_zone_device_register("rcar_thermal",
+		if (of_data == USE_OF_THERMAL)
+			priv->zone = thermal_zone_of_sensor_register(
+						dev, i, priv,
+						&rcar_thermal_zone_of_ops);
+		else
+			priv->zone = thermal_zone_device_register(
+						"rcar_thermal",
 						1, 0, priv,
 						&rcar_thermal_zone_ops, NULL, 0,
 						idle);
diff --git a/drivers/thermal/spear_thermal.c b/drivers/thermal/spear_thermal.c
index 534dd91..81b35aa 100644
--- a/drivers/thermal/spear_thermal.c
+++ b/drivers/thermal/spear_thermal.c
@@ -54,8 +54,7 @@
 	.get_temp = thermal_get_temp,
 };
 
-#ifdef CONFIG_PM
-static int spear_thermal_suspend(struct device *dev)
+static int __maybe_unused spear_thermal_suspend(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct thermal_zone_device *spear_thermal = platform_get_drvdata(pdev);
@@ -72,7 +71,7 @@
 	return 0;
 }
 
-static int spear_thermal_resume(struct device *dev)
+static int __maybe_unused spear_thermal_resume(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct thermal_zone_device *spear_thermal = platform_get_drvdata(pdev);
@@ -94,7 +93,6 @@
 
 	return 0;
 }
-#endif
 
 static SIMPLE_DEV_PM_OPS(spear_thermal_pm_ops, spear_thermal_suspend,
 		spear_thermal_resume);
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index b311004..2348fa6 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -681,7 +681,14 @@
 /* this is called once with whichever end is closed last */
 static void pty_unix98_shutdown(struct tty_struct *tty)
 {
-	devpts_kill_index(tty->driver_data, tty->index);
+	struct inode *ptmx_inode;
+
+	if (tty->driver->subtype == PTY_TYPE_MASTER)
+		ptmx_inode = tty->driver_data;
+	else
+		ptmx_inode = tty->link->driver_data;
+	devpts_kill_index(ptmx_inode, tty->index);
+	devpts_del_ref(ptmx_inode);
 }
 
 static const struct tty_operations ptm_unix98_ops = {
@@ -773,6 +780,18 @@
 	set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */
 	tty->driver_data = inode;
 
+	/*
+	 * In the case where all references to ptmx inode are dropped and we
+	 * still have /dev/tty opened pointing to the master/slave pair (ptmx
+	 * is closed/released before /dev/tty), we must make sure that the inode
+	 * is still valid when we call the final pty_unix98_shutdown, thus we
+	 * hold an additional reference to the ptmx inode. For the same /dev/tty
+	 * last close case, we also need to make sure the super_block isn't
+	 * destroyed (devpts instance unmounted), before /dev/tty is closed and
+	 * on its release devpts_kill_index is called.
+	 */
+	devpts_add_ref(inode);
+
 	tty_add_file(tty, filp);
 
 	slave_inode = devpts_pty_new(inode,
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index e71ec78..7cd6f9a 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -1941,6 +1941,7 @@
 #define PCIE_VENDOR_ID_WCH		0x1c00
 #define PCIE_DEVICE_ID_WCH_CH382_2S1P	0x3250
 #define PCIE_DEVICE_ID_WCH_CH384_4S	0x3470
+#define PCIE_DEVICE_ID_WCH_CH382_2S	0x3253
 
 #define PCI_VENDOR_ID_PERICOM			0x12D8
 #define PCI_DEVICE_ID_PERICOM_PI7C9X7951	0x7951
@@ -2637,6 +2638,14 @@
 		.subdevice	= PCI_ANY_ID,
 		.setup		= pci_wch_ch353_setup,
 	},
+	/* WCH CH382 2S card (16850 clone) */
+	{
+		.vendor         = PCIE_VENDOR_ID_WCH,
+		.device         = PCIE_DEVICE_ID_WCH_CH382_2S,
+		.subvendor      = PCI_ANY_ID,
+		.subdevice      = PCI_ANY_ID,
+		.setup          = pci_wch_ch38x_setup,
+	},
 	/* WCH CH382 2S1P card (16850 clone) */
 	{
 		.vendor         = PCIE_VENDOR_ID_WCH,
@@ -2955,6 +2964,7 @@
 	pbn_fintek_4,
 	pbn_fintek_8,
 	pbn_fintek_12,
+	pbn_wch382_2,
 	pbn_wch384_4,
 	pbn_pericom_PI7C9X7951,
 	pbn_pericom_PI7C9X7952,
@@ -3775,6 +3785,13 @@
 		.base_baud	= 115200,
 		.first_offset	= 0x40,
 	},
+	[pbn_wch382_2] = {
+		.flags		= FL_BASE0,
+		.num_ports	= 2,
+		.base_baud	= 115200,
+		.uart_offset	= 8,
+		.first_offset	= 0xC0,
+	},
 	[pbn_wch384_4] = {
 		.flags		= FL_BASE0,
 		.num_ports	= 4,
@@ -5574,6 +5591,10 @@
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_b0_bt_2_115200 },
 
+	{	PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH382_2S,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0, pbn_wch382_2 },
+
 	{	PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH384_4S,
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_wch384_4 },
diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index b645f92..fa49eb1 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -1165,7 +1165,7 @@
 
 #define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE)
 
-static void wait_for_xmitr(struct uart_omap_port *up)
+static void __maybe_unused wait_for_xmitr(struct uart_omap_port *up)
 {
 	unsigned int status, tmout = 10000;
 
@@ -1343,7 +1343,7 @@
 
 /* Enable or disable the rs485 support */
 static int
-serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485conf)
+serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485)
 {
 	struct uart_omap_port *up = to_uart_omap_port(port);
 	unsigned int mode;
@@ -1356,8 +1356,12 @@
 	up->ier = 0;
 	serial_out(up, UART_IER, 0);
 
+	/* Clamp the delays to [0, 100ms] */
+	rs485->delay_rts_before_send = min(rs485->delay_rts_before_send, 100U);
+	rs485->delay_rts_after_send  = min(rs485->delay_rts_after_send, 100U);
+
 	/* store new config */
-	port->rs485 = *rs485conf;
+	port->rs485 = *rs485;
 
 	/*
 	 * Just as a precaution, only allow rs485
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 5cec01c..a7eacef 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2066,13 +2066,12 @@
 		if (tty) {
 			mutex_unlock(&tty_mutex);
 			retval = tty_lock_interruptible(tty);
+			tty_kref_put(tty);  /* drop kref from tty_driver_lookup_tty() */
 			if (retval) {
 				if (retval == -EINTR)
 					retval = -ERESTARTSYS;
 				goto err_unref;
 			}
-			/* safe to drop the kref from tty_driver_lookup_tty() */
-			tty_kref_put(tty);
 			retval = tty_reopen(tty);
 			if (retval < 0) {
 				tty_unlock(tty);
diff --git a/drivers/tty/tty_mutex.c b/drivers/tty/tty_mutex.c
index d2f3c4c..dfa9ec0 100644
--- a/drivers/tty/tty_mutex.c
+++ b/drivers/tty/tty_mutex.c
@@ -21,10 +21,15 @@
 
 int tty_lock_interruptible(struct tty_struct *tty)
 {
+	int ret;
+
 	if (WARN(tty->magic != TTY_MAGIC, "L Bad %p\n", tty))
 		return -EIO;
 	tty_kref_get(tty);
-	return mutex_lock_interruptible(&tty->legacy_mutex);
+	ret = mutex_lock_interruptible(&tty->legacy_mutex);
+	if (ret)
+		tty_kref_put(tty);
+	return ret;
 }
 
 void __lockfunc tty_unlock(struct tty_struct *tty)
diff --git a/drivers/video/fbdev/da8xx-fb.c b/drivers/video/fbdev/da8xx-fb.c
index 0081725..6b2a06d 100644
--- a/drivers/video/fbdev/da8xx-fb.c
+++ b/drivers/video/fbdev/da8xx-fb.c
@@ -152,7 +152,7 @@
 
 struct da8xx_fb_par {
 	struct device		*dev;
-	resource_size_t p_palette_base;
+	dma_addr_t		p_palette_base;
 	unsigned char *v_palette_base;
 	dma_addr_t		vram_phys;
 	unsigned long		vram_size;
@@ -1428,7 +1428,7 @@
 
 	par->vram_virt = dma_alloc_coherent(NULL,
 					    par->vram_size,
-					    (resource_size_t *) &par->vram_phys,
+					    &par->vram_phys,
 					    GFP_KERNEL | GFP_DMA);
 	if (!par->vram_virt) {
 		dev_err(&device->dev,
@@ -1448,7 +1448,7 @@
 
 	/* allocate palette buffer */
 	par->v_palette_base = dma_zalloc_coherent(NULL, PALETTE_SIZE,
-						  (resource_size_t *)&par->p_palette_base,
+						  &par->p_palette_base,
 						  GFP_KERNEL | GFP_DMA);
 	if (!par->v_palette_base) {
 		dev_err(&device->dev,
diff --git a/drivers/video/fbdev/exynos/s6e8ax0.c b/drivers/video/fbdev/exynos/s6e8ax0.c
index 95873f2..de2f3e7 100644
--- a/drivers/video/fbdev/exynos/s6e8ax0.c
+++ b/drivers/video/fbdev/exynos/s6e8ax0.c
@@ -829,8 +829,7 @@
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int s6e8ax0_suspend(struct mipi_dsim_lcd_device *dsim_dev)
+static int __maybe_unused s6e8ax0_suspend(struct mipi_dsim_lcd_device *dsim_dev)
 {
 	struct s6e8ax0 *lcd = dev_get_drvdata(&dsim_dev->dev);
 
@@ -843,7 +842,7 @@
 	return 0;
 }
 
-static int s6e8ax0_resume(struct mipi_dsim_lcd_device *dsim_dev)
+static int __maybe_unused s6e8ax0_resume(struct mipi_dsim_lcd_device *dsim_dev)
 {
 	struct s6e8ax0 *lcd = dev_get_drvdata(&dsim_dev->dev);
 
@@ -855,10 +854,6 @@
 
 	return 0;
 }
-#else
-#define s6e8ax0_suspend		NULL
-#define s6e8ax0_resume		NULL
-#endif
 
 static struct mipi_dsim_lcd_driver s6e8ax0_dsim_ddi_driver = {
 	.name = "s6e8ax0",
@@ -867,8 +862,8 @@
 	.power_on = s6e8ax0_power_on,
 	.set_sequence = s6e8ax0_set_sequence,
 	.probe = s6e8ax0_probe,
-	.suspend = s6e8ax0_suspend,
-	.resume = s6e8ax0_resume,
+	.suspend = IS_ENABLED(CONFIG_PM) ? s6e8ax0_suspend : NULL,
+	.resume = IS_ENABLED(CONFIG_PM) ? s6e8ax0_resume : NULL,
 };
 
 static int s6e8ax0_init(void)
diff --git a/drivers/video/fbdev/imxfb.c b/drivers/video/fbdev/imxfb.c
index cee8860..bb2f1e8 100644
--- a/drivers/video/fbdev/imxfb.c
+++ b/drivers/video/fbdev/imxfb.c
@@ -902,6 +902,21 @@
 		goto failed_getclock;
 	}
 
+	/*
+	 * The LCDC controller does not have an enable bit. The
+	 * controller starts directly when the clocks are enabled.
+	 * If the clocks are enabled when the controller is not yet
+	 * programmed with proper register values (enabled at the
+	 * bootloader, for example) then it just goes into some undefined
+	 * state.
+	 * To avoid this issue, let's enable and disable LCDC IPG clock
+	 * so that we force some kind of 'reset' to the LCDC block.
+	 */
+	ret = clk_prepare_enable(fbi->clk_ipg);
+	if (ret)
+		goto failed_getclock;
+	clk_disable_unprepare(fbi->clk_ipg);
+
 	fbi->clk_ahb = devm_clk_get(&pdev->dev, "ahb");
 	if (IS_ERR(fbi->clk_ahb)) {
 		ret = PTR_ERR(fbi->clk_ahb);
diff --git a/drivers/video/fbdev/mmp/hw/mmp_ctrl.c b/drivers/video/fbdev/mmp/hw/mmp_ctrl.c
index de54a47..b6f83d5 100644
--- a/drivers/video/fbdev/mmp/hw/mmp_ctrl.c
+++ b/drivers/video/fbdev/mmp/hw/mmp_ctrl.c
@@ -503,8 +503,7 @@
 	ctrl->reg_base = devm_ioremap_nocache(ctrl->dev,
 			res->start, resource_size(res));
 	if (ctrl->reg_base == NULL) {
-		dev_err(ctrl->dev, "%s: res %x - %x map failed\n", __func__,
-			res->start, res->end);
+		dev_err(ctrl->dev, "%s: res %pR map failed\n", __func__, res);
 		ret = -ENOMEM;
 		goto failed;
 	}
diff --git a/drivers/video/fbdev/ocfb.c b/drivers/video/fbdev/ocfb.c
index c9293ae..a970edc2 100644
--- a/drivers/video/fbdev/ocfb.c
+++ b/drivers/video/fbdev/ocfb.c
@@ -123,11 +123,11 @@
 
 	/* Horizontal timings */
 	ocfb_writereg(fbdev, OCFB_HTIM, (var->hsync_len - 1) << 24 |
-		      (var->right_margin - 1) << 16 | (var->xres - 1));
+		      (var->left_margin - 1) << 16 | (var->xres - 1));
 
 	/* Vertical timings */
 	ocfb_writereg(fbdev, OCFB_VTIM, (var->vsync_len - 1) << 24 |
-		      (var->lower_margin - 1) << 16 | (var->yres - 1));
+		      (var->upper_margin - 1) << 16 | (var->yres - 1));
 
 	/* Total length of frame */
 	hlen = var->left_margin + var->right_margin + var->hsync_len +
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index b90cd37..f6dac40 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1406,7 +1406,8 @@
 			read_extent_buffer(eb, dest + bytes_left,
 					   name_off, name_len);
 		if (eb != eb_in) {
-			btrfs_tree_read_unlock_blocking(eb);
+			if (!path->skip_locking)
+				btrfs_tree_read_unlock_blocking(eb);
 			free_extent_buffer(eb);
 		}
 		ret = btrfs_find_item(fs_root, path, parent, 0,
@@ -1426,9 +1427,10 @@
 		eb = path->nodes[0];
 		/* make sure we can use eb after releasing the path */
 		if (eb != eb_in) {
-			atomic_inc(&eb->refs);
-			btrfs_tree_read_lock(eb);
-			btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+			if (!path->skip_locking)
+				btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+			path->nodes[0] = NULL;
+			path->locks[0] = 0;
 		}
 		btrfs_release_path(path);
 		iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index c473c42..3346cd8 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -637,11 +637,7 @@
 	faili = nr_pages - 1;
 	cb->nr_pages = nr_pages;
 
-	/* In the parent-locked case, we only locked the range we are
-	 * interested in.  In all other cases, we can opportunistically
-	 * cache decompressed data that goes beyond the requested range. */
-	if (!(bio_flags & EXTENT_BIO_PARENT_LOCKED))
-		add_ra_bio_pages(inode, em_start + em_len, cb);
+	add_ra_bio_pages(inode, em_start + em_len, cb);
 
 	/* include any pages we added in add_ra-bio_pages */
 	uncompressed_len = bio->bi_vcnt * PAGE_CACHE_SIZE;
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 0be47e4..b57daa8 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1689,7 +1689,7 @@
  *
  */
 int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
-				    struct list_head *ins_list)
+				    struct list_head *ins_list, bool *emitted)
 {
 	struct btrfs_dir_item *di;
 	struct btrfs_delayed_item *curr, *next;
@@ -1733,6 +1733,7 @@
 
 		if (over)
 			return 1;
+		*emitted = true;
 	}
 	return 0;
 }
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index f70119f..0167853 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -144,7 +144,7 @@
 int btrfs_should_delete_dir_index(struct list_head *del_list,
 				  u64 index);
 int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
-				    struct list_head *ins_list);
+				    struct list_head *ins_list, bool *emitted);
 
 /* for init */
 int __init btrfs_delayed_inode_init(void);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 2e7c97a..392592d 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2897,12 +2897,11 @@
 	struct block_device *bdev;
 	int ret;
 	int nr = 0;
-	int parent_locked = *bio_flags & EXTENT_BIO_PARENT_LOCKED;
 	size_t pg_offset = 0;
 	size_t iosize;
 	size_t disk_io_size;
 	size_t blocksize = inode->i_sb->s_blocksize;
-	unsigned long this_bio_flag = *bio_flags & EXTENT_BIO_PARENT_LOCKED;
+	unsigned long this_bio_flag = 0;
 
 	set_page_extent_mapped(page);
 
@@ -2942,18 +2941,16 @@
 			kunmap_atomic(userpage);
 			set_extent_uptodate(tree, cur, cur + iosize - 1,
 					    &cached, GFP_NOFS);
-			if (!parent_locked)
-				unlock_extent_cached(tree, cur,
-						     cur + iosize - 1,
-						     &cached, GFP_NOFS);
+			unlock_extent_cached(tree, cur,
+					     cur + iosize - 1,
+					     &cached, GFP_NOFS);
 			break;
 		}
 		em = __get_extent_map(inode, page, pg_offset, cur,
 				      end - cur + 1, get_extent, em_cached);
 		if (IS_ERR_OR_NULL(em)) {
 			SetPageError(page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, end);
+			unlock_extent(tree, cur, end);
 			break;
 		}
 		extent_offset = cur - em->start;
@@ -3038,12 +3035,9 @@
 
 			set_extent_uptodate(tree, cur, cur + iosize - 1,
 					    &cached, GFP_NOFS);
-			if (parent_locked)
-				free_extent_state(cached);
-			else
-				unlock_extent_cached(tree, cur,
-						     cur + iosize - 1,
-						     &cached, GFP_NOFS);
+			unlock_extent_cached(tree, cur,
+					     cur + iosize - 1,
+					     &cached, GFP_NOFS);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -3052,8 +3046,7 @@
 		if (test_range_bit(tree, cur, cur_end,
 				   EXTENT_UPTODATE, 1, NULL)) {
 			check_page_uptodate(tree, page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, cur + iosize - 1);
+			unlock_extent(tree, cur, cur + iosize - 1);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -3063,8 +3056,7 @@
 		 */
 		if (block_start == EXTENT_MAP_INLINE) {
 			SetPageError(page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, cur + iosize - 1);
+			unlock_extent(tree, cur, cur + iosize - 1);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -3083,8 +3075,7 @@
 			*bio_flags = this_bio_flag;
 		} else {
 			SetPageError(page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, cur + iosize - 1);
+			unlock_extent(tree, cur, cur + iosize - 1);
 		}
 		cur = cur + iosize;
 		pg_offset += iosize;
@@ -3213,20 +3204,6 @@
 	return ret;
 }
 
-int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page,
-				 get_extent_t *get_extent, int mirror_num)
-{
-	struct bio *bio = NULL;
-	unsigned long bio_flags = EXTENT_BIO_PARENT_LOCKED;
-	int ret;
-
-	ret = __do_readpage(tree, page, get_extent, NULL, &bio, mirror_num,
-			    &bio_flags, READ, NULL);
-	if (bio)
-		ret = submit_one_bio(READ, bio, mirror_num, bio_flags);
-	return ret;
-}
-
 static noinline void update_nr_written(struct page *page,
 				      struct writeback_control *wbc,
 				      unsigned long nr_written)
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 0377413..880d529 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -29,7 +29,6 @@
  */
 #define EXTENT_BIO_COMPRESSED 1
 #define EXTENT_BIO_TREE_LOG 2
-#define EXTENT_BIO_PARENT_LOCKED 4
 #define EXTENT_BIO_FLAG_SHIFT 16
 
 /* these are bit numbers for test/set bit */
@@ -210,8 +209,6 @@
 int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
 int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 			  get_extent_t *get_extent, int mirror_num);
-int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page,
-				 get_extent_t *get_extent, int mirror_num);
 int __init extent_io_init(void);
 void extent_io_exit(void);
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5f06eb1..151b7c7 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5717,6 +5717,7 @@
 	char *name_ptr;
 	int name_len;
 	int is_curr = 0;	/* ctx->pos points to the current index? */
+	bool emitted;
 
 	/* FIXME, use a real flag for deciding about the key type */
 	if (root->fs_info->tree_root == root)
@@ -5745,6 +5746,7 @@
 	if (ret < 0)
 		goto err;
 
+	emitted = false;
 	while (1) {
 		leaf = path->nodes[0];
 		slot = path->slots[0];
@@ -5824,6 +5826,7 @@
 
 			if (over)
 				goto nopos;
+			emitted = true;
 			di_len = btrfs_dir_name_len(leaf, di) +
 				 btrfs_dir_data_len(leaf, di) + sizeof(*di);
 			di_cur += di_len;
@@ -5836,11 +5839,20 @@
 	if (key_type == BTRFS_DIR_INDEX_KEY) {
 		if (is_curr)
 			ctx->pos++;
-		ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list);
+		ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list, &emitted);
 		if (ret)
 			goto nopos;
 	}
 
+	/*
+	 * If we haven't emitted any dir entry, we must not touch ctx->pos as
+	 * it was was set to the termination value in previous call. We assume
+	 * that "." and ".." were emitted if we reach this point and set the
+	 * termination value as well for an empty directory.
+	 */
+	if (ctx->pos > 2 && !emitted)
+		goto nopos;
+
 	/* Reached end of directory/root. Bump pos past the last item. */
 	ctx->pos++;
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 952172c..48aee98 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2794,24 +2794,29 @@
 static struct page *extent_same_get_page(struct inode *inode, pgoff_t index)
 {
 	struct page *page;
-	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
 
 	page = grab_cache_page(inode->i_mapping, index);
 	if (!page)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	if (!PageUptodate(page)) {
-		if (extent_read_full_page_nolock(tree, page, btrfs_get_extent,
-						 0))
-			return NULL;
+		int ret;
+
+		ret = btrfs_readpage(NULL, page);
+		if (ret)
+			return ERR_PTR(ret);
 		lock_page(page);
 		if (!PageUptodate(page)) {
 			unlock_page(page);
 			page_cache_release(page);
-			return NULL;
+			return ERR_PTR(-EIO);
+		}
+		if (page->mapping != inode->i_mapping) {
+			unlock_page(page);
+			page_cache_release(page);
+			return ERR_PTR(-EAGAIN);
 		}
 	}
-	unlock_page(page);
 
 	return page;
 }
@@ -2823,17 +2828,31 @@
 	pgoff_t index = off >> PAGE_CACHE_SHIFT;
 
 	for (i = 0; i < num_pages; i++) {
+again:
 		pages[i] = extent_same_get_page(inode, index + i);
-		if (!pages[i])
-			return -ENOMEM;
+		if (IS_ERR(pages[i])) {
+			int err = PTR_ERR(pages[i]);
+
+			if (err == -EAGAIN)
+				goto again;
+			pages[i] = NULL;
+			return err;
+		}
 	}
 	return 0;
 }
 
-static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
+static int lock_extent_range(struct inode *inode, u64 off, u64 len,
+			     bool retry_range_locking)
 {
-	/* do any pending delalloc/csum calc on src, one way or
-	   another, and lock file content */
+	/*
+	 * Do any pending delalloc/csum calculations on inode, one way or
+	 * another, and lock file content.
+	 * The locking order is:
+	 *
+	 *   1) pages
+	 *   2) range in the inode's io tree
+	 */
 	while (1) {
 		struct btrfs_ordered_extent *ordered;
 		lock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
@@ -2851,8 +2870,11 @@
 		unlock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
 		if (ordered)
 			btrfs_put_ordered_extent(ordered);
+		if (!retry_range_locking)
+			return -EAGAIN;
 		btrfs_wait_ordered_range(inode, off, len);
 	}
+	return 0;
 }
 
 static void btrfs_double_inode_unlock(struct inode *inode1, struct inode *inode2)
@@ -2877,15 +2899,24 @@
 	unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
 }
 
-static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
-				     struct inode *inode2, u64 loff2, u64 len)
+static int btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
+				    struct inode *inode2, u64 loff2, u64 len,
+				    bool retry_range_locking)
 {
+	int ret;
+
 	if (inode1 < inode2) {
 		swap(inode1, inode2);
 		swap(loff1, loff2);
 	}
-	lock_extent_range(inode1, loff1, len);
-	lock_extent_range(inode2, loff2, len);
+	ret = lock_extent_range(inode1, loff1, len, retry_range_locking);
+	if (ret)
+		return ret;
+	ret = lock_extent_range(inode2, loff2, len, retry_range_locking);
+	if (ret)
+		unlock_extent(&BTRFS_I(inode1)->io_tree, loff1,
+			      loff1 + len - 1);
+	return ret;
 }
 
 struct cmp_pages {
@@ -2901,11 +2932,15 @@
 
 	for (i = 0; i < cmp->num_pages; i++) {
 		pg = cmp->src_pages[i];
-		if (pg)
+		if (pg) {
+			unlock_page(pg);
 			page_cache_release(pg);
+		}
 		pg = cmp->dst_pages[i];
-		if (pg)
+		if (pg) {
+			unlock_page(pg);
 			page_cache_release(pg);
+		}
 	}
 	kfree(cmp->src_pages);
 	kfree(cmp->dst_pages);
@@ -2966,6 +3001,8 @@
 
 		src_page = cmp->src_pages[i];
 		dst_page = cmp->dst_pages[i];
+		ASSERT(PageLocked(src_page));
+		ASSERT(PageLocked(dst_page));
 
 		addr = kmap_atomic(src_page);
 		dst_addr = kmap_atomic(dst_page);
@@ -3078,14 +3115,46 @@
 		goto out_unlock;
 	}
 
+again:
 	ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, &cmp);
 	if (ret)
 		goto out_unlock;
 
 	if (same_inode)
-		lock_extent_range(src, same_lock_start, same_lock_len);
+		ret = lock_extent_range(src, same_lock_start, same_lock_len,
+					false);
 	else
-		btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
+		ret = btrfs_double_extent_lock(src, loff, dst, dst_loff, len,
+					       false);
+	/*
+	 * If one of the inodes has dirty pages in the respective range or
+	 * ordered extents, we need to flush dellaloc and wait for all ordered
+	 * extents in the range. We must unlock the pages and the ranges in the
+	 * io trees to avoid deadlocks when flushing delalloc (requires locking
+	 * pages) and when waiting for ordered extents to complete (they require
+	 * range locking).
+	 */
+	if (ret == -EAGAIN) {
+		/*
+		 * Ranges in the io trees already unlocked. Now unlock all
+		 * pages before waiting for all IO to complete.
+		 */
+		btrfs_cmp_data_free(&cmp);
+		if (same_inode) {
+			btrfs_wait_ordered_range(src, same_lock_start,
+						 same_lock_len);
+		} else {
+			btrfs_wait_ordered_range(src, loff, len);
+			btrfs_wait_ordered_range(dst, dst_loff, len);
+		}
+		goto again;
+	}
+	ASSERT(ret == 0);
+	if (WARN_ON(ret)) {
+		/* ranges in the io trees already unlocked */
+		btrfs_cmp_data_free(&cmp);
+		return ret;
+	}
 
 	/* pass original length for comparison so we stay within i_size */
 	ret = btrfs_cmp_data(src, loff, dst, dst_loff, olen, &cmp);
@@ -3795,9 +3864,15 @@
 		u64 lock_start = min_t(u64, off, destoff);
 		u64 lock_len = max_t(u64, off, destoff) + len - lock_start;
 
-		lock_extent_range(src, lock_start, lock_len);
+		ret = lock_extent_range(src, lock_start, lock_len, true);
 	} else {
-		btrfs_double_extent_lock(src, off, inode, destoff, len);
+		ret = btrfs_double_extent_lock(src, off, inode, destoff, len,
+					       true);
+	}
+	ASSERT(ret == 0);
+	if (WARN_ON(ret)) {
+		/* ranges in the io trees already unlocked */
+		goto out_unlock;
 	}
 
 	ret = btrfs_clone(src, inode, off, olen, len, destoff, 0);
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 1f107fd..655f21f 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -575,6 +575,26 @@
 	mutex_unlock(&allocated_ptys_lock);
 }
 
+/*
+ * pty code needs to hold extra references in case of last /dev/tty close
+ */
+
+void devpts_add_ref(struct inode *ptmx_inode)
+{
+	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+
+	atomic_inc(&sb->s_active);
+	ihold(ptmx_inode);
+}
+
+void devpts_del_ref(struct inode *ptmx_inode)
+{
+	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+
+	iput(ptmx_inode);
+	deactivate_super(sb);
+}
+
 /**
  * devpts_pty_new -- create a new inode in /dev/pts/
  * @ptmx_inode: inode of the master
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index da37beb..594f7e6 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -4491,7 +4491,7 @@
 	 * know precisely what failed.
 	 */
 	if (pass == XLOG_RECOVER_CRCPASS) {
-		if (rhead->h_crc && crc != le32_to_cpu(rhead->h_crc))
+		if (rhead->h_crc && crc != rhead->h_crc)
 			return -EFSBADCRC;
 		return 0;
 	}
@@ -4502,7 +4502,7 @@
 	 * zero CRC check prevents warnings from being emitted when upgrading
 	 * the kernel from one that does not add CRCs by default.
 	 */
-	if (crc != le32_to_cpu(rhead->h_crc)) {
+	if (crc != rhead->h_crc) {
 		if (rhead->h_crc || xfs_sb_version_hascrc(&log->l_mp->m_sb)) {
 			xfs_alert(log->l_mp,
 		"log record CRC mismatch: found 0x%x, expected 0x%x.",
diff --git a/include/asm-generic/cputime_nsecs.h b/include/asm-generic/cputime_nsecs.h
index 0419485..0f1c6f3 100644
--- a/include/asm-generic/cputime_nsecs.h
+++ b/include/asm-generic/cputime_nsecs.h
@@ -75,7 +75,7 @@
  */
 static inline cputime_t timespec_to_cputime(const struct timespec *val)
 {
-	u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_nsec;
+	u64 ret = (u64)val->tv_sec * NSEC_PER_SEC + val->tv_nsec;
 	return (__force cputime_t) ret;
 }
 static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val)
@@ -91,7 +91,8 @@
  */
 static inline cputime_t timeval_to_cputime(const struct timeval *val)
 {
-	u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_usec * NSEC_PER_USEC;
+	u64 ret = (u64)val->tv_sec * NSEC_PER_SEC +
+			val->tv_usec * NSEC_PER_USEC;
 	return (__force cputime_t) ret;
 }
 static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 29189ae..4571ef1 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -682,9 +682,12 @@
 /*
  * q->prep_rq_fn return values
  */
-#define BLKPREP_OK		0	/* serve it */
-#define BLKPREP_KILL		1	/* fatal error, kill */
-#define BLKPREP_DEFER		2	/* leave on queue */
+enum {
+	BLKPREP_OK,		/* serve it */
+	BLKPREP_KILL,		/* fatal error, kill, return -EIO */
+	BLKPREP_DEFER,		/* leave on queue */
+	BLKPREP_INVALID,	/* invalid command, kill, return -EREMOTEIO */
+};
 
 extern unsigned long blk_max_low_pfn, blk_max_pfn;
 
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 7f540f7..789471d 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -127,6 +127,12 @@
 	 */
 	u64 serial_nr;
 
+	/*
+	 * Incremented by online self and children.  Used to guarantee that
+	 * parents are not offlined before their children.
+	 */
+	atomic_t online_cnt;
+
 	/* percpu_ref killing and RCU release */
 	struct rcu_head rcu_head;
 	struct work_struct destroy_work;
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 85a868c..fea160e 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -137,6 +137,8 @@
 	task_unlock(current);
 }
 
+extern void cpuset_post_attach_flush(void);
+
 #else /* !CONFIG_CPUSETS */
 
 static inline bool cpusets_enabled(void) { return false; }
@@ -243,6 +245,10 @@
 	return false;
 }
 
+static inline void cpuset_post_attach_flush(void)
+{
+}
+
 #endif /* !CONFIG_CPUSETS */
 
 #endif /* _LINUX_CPUSET_H */
diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h
index 251a209..e0ee0b3 100644
--- a/include/linux/devpts_fs.h
+++ b/include/linux/devpts_fs.h
@@ -19,6 +19,8 @@
 
 int devpts_new_index(struct inode *ptmx_inode);
 void devpts_kill_index(struct inode *ptmx_inode, int idx);
+void devpts_add_ref(struct inode *ptmx_inode);
+void devpts_del_ref(struct inode *ptmx_inode);
 /* mknod in devpts */
 struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
 		void *priv);
@@ -32,6 +34,8 @@
 /* Dummy stubs in the no-pty case */
 static inline int devpts_new_index(struct inode *ptmx_inode) { return -EINVAL; }
 static inline void devpts_kill_index(struct inode *ptmx_inode, int idx) { }
+static inline void devpts_add_ref(struct inode *ptmx_inode) { }
+static inline void devpts_del_ref(struct inode *ptmx_inode) { }
 static inline struct inode *devpts_pty_new(struct inode *ptmx_inode,
 		dev_t device, int index, void *priv)
 {
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 851821b..bec2abb 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -526,6 +526,7 @@
 enum ata_lpm_hints {
 	ATA_LPM_EMPTY		= (1 << 0), /* port empty/probing */
 	ATA_LPM_HIPM		= (1 << 1), /* may use HIPM */
+	ATA_LPM_WAKE_ONLY	= (1 << 2), /* only wake up link */
 };
 
 /* forward declarations */
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index c57e424..4dca42f 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -66,7 +66,7 @@
 	/*
 	 * class-hash:
 	 */
-	struct list_head		hash_entry;
+	struct hlist_node		hash_entry;
 
 	/*
 	 * global list of all lock-classes:
@@ -199,7 +199,7 @@
 	u8				irq_context;
 	u8				depth;
 	u16				base;
-	struct list_head		entry;
+	struct hlist_node		entry;
 	u64				chain_key;
 };
 
diff --git a/include/linux/module.h b/include/linux/module.h
index 4560d8f..2bb0c30 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -324,6 +324,12 @@
 #define __module_layout_align
 #endif
 
+struct mod_kallsyms {
+	Elf_Sym *symtab;
+	unsigned int num_symtab;
+	char *strtab;
+};
+
 struct module {
 	enum module_state state;
 
@@ -405,15 +411,10 @@
 #endif
 
 #ifdef CONFIG_KALLSYMS
-	/*
-	 * We keep the symbol and string tables for kallsyms.
-	 * The core_* fields below are temporary, loader-only (they
-	 * could really be discarded after module init).
-	 */
-	Elf_Sym *symtab, *core_symtab;
-	unsigned int num_symtab, core_num_syms;
-	char *strtab, *core_strtab;
-
+	/* Protected by RCU and/or module_mutex: use rcu_dereference() */
+	struct mod_kallsyms *kallsyms;
+	struct mod_kallsyms core_kallsyms;
+	
 	/* Section attributes */
 	struct module_sect_attrs *sect_attrs;
 
diff --git a/include/linux/pfn.h b/include/linux/pfn.h
index 2d8e497..1132953 100644
--- a/include/linux/pfn.h
+++ b/include/linux/pfn.h
@@ -10,7 +10,7 @@
  * backing is indicated by flags in the high bits of the value.
  */
 typedef struct {
-	unsigned long val;
+	u64 val;
 } pfn_t;
 #endif
 
diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h
index 37448ab..9499481 100644
--- a/include/linux/pfn_t.h
+++ b/include/linux/pfn_t.h
@@ -9,14 +9,13 @@
  * PFN_DEV - pfn is not covered by system memmap by default
  * PFN_MAP - pfn has a dynamic page mapping established by a device driver
  */
-#define PFN_FLAGS_MASK (((unsigned long) ~PAGE_MASK) \
-		<< (BITS_PER_LONG - PAGE_SHIFT))
-#define PFN_SG_CHAIN (1UL << (BITS_PER_LONG - 1))
-#define PFN_SG_LAST (1UL << (BITS_PER_LONG - 2))
-#define PFN_DEV (1UL << (BITS_PER_LONG - 3))
-#define PFN_MAP (1UL << (BITS_PER_LONG - 4))
+#define PFN_FLAGS_MASK (((u64) ~PAGE_MASK) << (BITS_PER_LONG_LONG - PAGE_SHIFT))
+#define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1))
+#define PFN_SG_LAST (1ULL << (BITS_PER_LONG_LONG - 2))
+#define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3))
+#define PFN_MAP (1ULL << (BITS_PER_LONG_LONG - 4))
 
-static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, unsigned long flags)
+static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, u64 flags)
 {
 	pfn_t pfn_t = { .val = pfn | (flags & PFN_FLAGS_MASK), };
 
@@ -29,7 +28,7 @@
 	return __pfn_to_pfn_t(pfn, 0);
 }
 
-extern pfn_t phys_to_pfn_t(phys_addr_t addr, unsigned long flags);
+extern pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags);
 
 static inline bool pfn_t_has_page(pfn_t pfn)
 {
@@ -87,7 +86,7 @@
 #ifdef __HAVE_ARCH_PTE_DEVMAP
 static inline bool pfn_t_devmap(pfn_t pfn)
 {
-	const unsigned long flags = PFN_DEV|PFN_MAP;
+	const u64 flags = PFN_DEV|PFN_MAP;
 
 	return (pfn.val & flags) == flags;
 }
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 11f935c..4ce9ff7 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -299,6 +299,7 @@
 #else
 #define MAX_SKB_FRAGS (65536/PAGE_SIZE + 1)
 #endif
+extern int sysctl_max_skb_frags;
 
 typedef struct skb_frag_struct skb_frag_t;
 
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 0e32bc7..ca73c503 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -311,6 +311,7 @@
 
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
 	__WQ_ORDERED		= 1 << 17, /* internal: workqueue is ordered */
+	__WQ_LEGACY		= 1 << 18, /* internal: create*_workqueue() */
 
 	WQ_MAX_ACTIVE		= 512,	  /* I like 512, better ideas? */
 	WQ_MAX_UNBOUND_PER_CPU	= 4,	  /* 4 * #cpus for unbound wq */
@@ -411,12 +412,12 @@
 	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
 
 #define create_workqueue(name)						\
-	alloc_workqueue("%s", WQ_MEM_RECLAIM, 1, (name))
+	alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name))
 #define create_freezable_workqueue(name)				\
-	alloc_workqueue("%s", WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, \
-			1, (name))
+	alloc_workqueue("%s", __WQ_LEGACY | WQ_FREEZABLE | WQ_UNBOUND |	\
+			WQ_MEM_RECLAIM, 1, (name))
 #define create_singlethread_workqueue(name)				\
-	alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, name)
+	alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name)
 
 extern void destroy_workqueue(struct workqueue_struct *wq);
 
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 2a91a05..9b4c418 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -6,8 +6,8 @@
 #include <linux/mutex.h>
 #include <net/sock.h>
 
-void unix_inflight(struct file *fp);
-void unix_notinflight(struct file *fp);
+void unix_inflight(struct user_struct *user, struct file *fp);
+void unix_notinflight(struct user_struct *user, struct file *fp);
 void unix_gc(void);
 void wait_for_unix_gc(void);
 struct sock *unix_get_socket(struct file *filp);
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 6db96ea..dda9abf 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -230,6 +230,7 @@
 int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd);
 int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
 		    u8 *protocol, struct flowi4 *fl4);
+int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict);
 int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu);
 
 struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
diff --git a/include/net/scm.h b/include/net/scm.h
index 262532d..59fa93c 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -21,6 +21,7 @@
 struct scm_fp_list {
 	short			count;
 	short			max;
+	struct user_struct	*user;
 	struct file		*fp[SCM_MAX_FD];
 };
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f6f8f03..ae6468f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -447,7 +447,7 @@
 
 void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb);
 void tcp_v4_mtu_reduced(struct sock *sk);
-void tcp_req_err(struct sock *sk, u32 seq);
+void tcp_req_err(struct sock *sk, u32 seq, bool abort);
 int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
 struct sock *tcp_create_openreq_child(const struct sock *sk,
 				      struct request_sock *req,
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 56cf8e4..28ee5c2 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -94,5 +94,8 @@
 	sense_reason_t (*exec_cmd)(struct se_cmd *cmd));
 
 bool target_sense_desc_format(struct se_device *dev);
+sector_t target_to_linux_sector(struct se_device *dev, sector_t lb);
+bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib,
+				       struct request_queue *q, int block_size);
 
 #endif /* TARGET_CORE_BACKEND_H */
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 5d82816..e8c8c08 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -140,6 +140,8 @@
 	SCF_COMPARE_AND_WRITE		= 0x00080000,
 	SCF_COMPARE_AND_WRITE_POST	= 0x00100000,
 	SCF_PASSTHROUGH_PROT_SG_TO_MEM_NOALLOC = 0x00200000,
+	SCF_ACK_KREF			= 0x00400000,
+	SCF_USE_CPUID			= 0x00800000,
 };
 
 /* struct se_dev_entry->lun_flags and struct se_lun->lun_access */
@@ -187,6 +189,7 @@
 	TARGET_SCF_BIDI_OP		= 0x01,
 	TARGET_SCF_ACK_KREF		= 0x02,
 	TARGET_SCF_UNKNOWN_SIZE		= 0x04,
+	TARGET_SCF_USE_CPUID	= 0x08,
 };
 
 /* fabric independent task management function values */
@@ -490,8 +493,9 @@
 #define CMD_T_SENT		(1 << 4)
 #define CMD_T_STOP		(1 << 5)
 #define CMD_T_DEV_ACTIVE	(1 << 7)
-#define CMD_T_REQUEST_STOP	(1 << 8)
 #define CMD_T_BUSY		(1 << 9)
+#define CMD_T_TAS		(1 << 10)
+#define CMD_T_FABRIC_STOP	(1 << 11)
 	spinlock_t		t_state_lock;
 	struct kref		cmd_kref;
 	struct completion	t_transport_stop_comp;
@@ -511,9 +515,6 @@
 
 	struct list_head	state_list;
 
-	/* old task stop completion, consider merging with some of the above */
-	struct completion	task_stop_comp;
-
 	/* backend private data */
 	void			*priv;
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d1d3e8f..2e7f7ab 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2082,7 +2082,7 @@
 		/* adjust offset of jmps if necessary */
 		if (i < pos && i + insn->off + 1 > pos)
 			insn->off += delta;
-		else if (i > pos && i + insn->off + 1 < pos)
+		else if (i > pos + delta && i + insn->off + 1 <= pos + delta)
 			insn->off -= delta;
 	}
 }
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c03a640..d27904c 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -58,6 +58,7 @@
 #include <linux/kthread.h>
 #include <linux/delay.h>
 #include <linux/atomic.h>
+#include <linux/cpuset.h>
 #include <net/sock.h>
 
 /*
@@ -2739,6 +2740,7 @@
 out_unlock_threadgroup:
 	percpu_up_write(&cgroup_threadgroup_rwsem);
 	cgroup_kn_unlock(of->kn);
+	cpuset_post_attach_flush();
 	return ret ?: nbytes;
 }
 
@@ -4655,14 +4657,15 @@
 
 	if (ss) {
 		/* css free path */
+		struct cgroup_subsys_state *parent = css->parent;
 		int id = css->id;
 
-		if (css->parent)
-			css_put(css->parent);
-
 		ss->css_free(css);
 		cgroup_idr_remove(&ss->css_idr, id);
 		cgroup_put(cgrp);
+
+		if (parent)
+			css_put(parent);
 	} else {
 		/* cgroup free path */
 		atomic_dec(&cgrp->root->nr_cgrps);
@@ -4758,6 +4761,7 @@
 	INIT_LIST_HEAD(&css->sibling);
 	INIT_LIST_HEAD(&css->children);
 	css->serial_nr = css_serial_nr_next++;
+	atomic_set(&css->online_cnt, 0);
 
 	if (cgroup_parent(cgrp)) {
 		css->parent = cgroup_css(cgroup_parent(cgrp), ss);
@@ -4780,6 +4784,10 @@
 	if (!ret) {
 		css->flags |= CSS_ONLINE;
 		rcu_assign_pointer(css->cgroup->subsys[ss->id], css);
+
+		atomic_inc(&css->online_cnt);
+		if (css->parent)
+			atomic_inc(&css->parent->online_cnt);
 	}
 	return ret;
 }
@@ -5017,10 +5025,15 @@
 		container_of(work, struct cgroup_subsys_state, destroy_work);
 
 	mutex_lock(&cgroup_mutex);
-	offline_css(css);
-	mutex_unlock(&cgroup_mutex);
 
-	css_put(css);
+	do {
+		offline_css(css);
+		css_put(css);
+		/* @css can't go away while we're holding cgroup_mutex */
+		css = css->parent;
+	} while (css && atomic_dec_and_test(&css->online_cnt));
+
+	mutex_unlock(&cgroup_mutex);
 }
 
 /* css kill confirmation processing requires process context, bounce */
@@ -5029,8 +5042,10 @@
 	struct cgroup_subsys_state *css =
 		container_of(ref, struct cgroup_subsys_state, refcnt);
 
-	INIT_WORK(&css->destroy_work, css_killed_work_fn);
-	queue_work(cgroup_destroy_wq, &css->destroy_work);
+	if (atomic_dec_and_test(&css->online_cnt)) {
+		INIT_WORK(&css->destroy_work, css_killed_work_fn);
+		queue_work(cgroup_destroy_wq, &css->destroy_work);
+	}
 }
 
 /**
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 3e945fc..41989ab 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -287,6 +287,8 @@
 static DEFINE_MUTEX(cpuset_mutex);
 static DEFINE_SPINLOCK(callback_lock);
 
+static struct workqueue_struct *cpuset_migrate_mm_wq;
+
 /*
  * CPU / memory hotplug is handled asynchronously.
  */
@@ -972,31 +974,51 @@
 }
 
 /*
- * cpuset_migrate_mm
- *
- *    Migrate memory region from one set of nodes to another.
- *
- *    Temporarilly set tasks mems_allowed to target nodes of migration,
- *    so that the migration code can allocate pages on these nodes.
- *
- *    While the mm_struct we are migrating is typically from some
- *    other task, the task_struct mems_allowed that we are hacking
- *    is for our current task, which must allocate new pages for that
- *    migrating memory region.
+ * Migrate memory region from one set of nodes to another.  This is
+ * performed asynchronously as it can be called from process migration path
+ * holding locks involved in process management.  All mm migrations are
+ * performed in the queued order and can be waited for by flushing
+ * cpuset_migrate_mm_wq.
  */
 
+struct cpuset_migrate_mm_work {
+	struct work_struct	work;
+	struct mm_struct	*mm;
+	nodemask_t		from;
+	nodemask_t		to;
+};
+
+static void cpuset_migrate_mm_workfn(struct work_struct *work)
+{
+	struct cpuset_migrate_mm_work *mwork =
+		container_of(work, struct cpuset_migrate_mm_work, work);
+
+	/* on a wq worker, no need to worry about %current's mems_allowed */
+	do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL);
+	mmput(mwork->mm);
+	kfree(mwork);
+}
+
 static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
 							const nodemask_t *to)
 {
-	struct task_struct *tsk = current;
+	struct cpuset_migrate_mm_work *mwork;
 
-	tsk->mems_allowed = *to;
+	mwork = kzalloc(sizeof(*mwork), GFP_KERNEL);
+	if (mwork) {
+		mwork->mm = mm;
+		mwork->from = *from;
+		mwork->to = *to;
+		INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn);
+		queue_work(cpuset_migrate_mm_wq, &mwork->work);
+	} else {
+		mmput(mm);
+	}
+}
 
-	do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
-
-	rcu_read_lock();
-	guarantee_online_mems(task_cs(tsk), &tsk->mems_allowed);
-	rcu_read_unlock();
+void cpuset_post_attach_flush(void)
+{
+	flush_workqueue(cpuset_migrate_mm_wq);
 }
 
 /*
@@ -1097,7 +1119,8 @@
 		mpol_rebind_mm(mm, &cs->mems_allowed);
 		if (migrate)
 			cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems);
-		mmput(mm);
+		else
+			mmput(mm);
 	}
 	css_task_iter_end(&it);
 
@@ -1545,11 +1568,11 @@
 			 * @old_mems_allowed is the right nodesets that we
 			 * migrate mm from.
 			 */
-			if (is_memory_migrate(cs)) {
+			if (is_memory_migrate(cs))
 				cpuset_migrate_mm(mm, &oldcs->old_mems_allowed,
 						  &cpuset_attach_nodemask_to);
-			}
-			mmput(mm);
+			else
+				mmput(mm);
 		}
 	}
 
@@ -1714,6 +1737,7 @@
 	mutex_unlock(&cpuset_mutex);
 	kernfs_unbreak_active_protection(of->kn);
 	css_put(&cs->css);
+	flush_workqueue(cpuset_migrate_mm_wq);
 	return retval ?: nbytes;
 }
 
@@ -2359,6 +2383,9 @@
 	top_cpuset.effective_mems = node_states[N_MEMORY];
 
 	register_hotmemory_notifier(&cpuset_track_online_nodes_nb);
+
+	cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0);
+	BUG_ON(!cpuset_migrate_mm_wq);
 }
 
 /**
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 60ace56..716547f 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -292,7 +292,7 @@
 #define __classhashfn(key)	hash_long((unsigned long)key, CLASSHASH_BITS)
 #define classhashentry(key)	(classhash_table + __classhashfn((key)))
 
-static struct list_head classhash_table[CLASSHASH_SIZE];
+static struct hlist_head classhash_table[CLASSHASH_SIZE];
 
 /*
  * We put the lock dependency chains into a hash-table as well, to cache
@@ -303,7 +303,7 @@
 #define __chainhashfn(chain)	hash_long(chain, CHAINHASH_BITS)
 #define chainhashentry(chain)	(chainhash_table + __chainhashfn((chain)))
 
-static struct list_head chainhash_table[CHAINHASH_SIZE];
+static struct hlist_head chainhash_table[CHAINHASH_SIZE];
 
 /*
  * The hash key of the lock dependency chains is a hash itself too:
@@ -666,7 +666,7 @@
 look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
 {
 	struct lockdep_subclass_key *key;
-	struct list_head *hash_head;
+	struct hlist_head *hash_head;
 	struct lock_class *class;
 
 #ifdef CONFIG_DEBUG_LOCKDEP
@@ -719,7 +719,7 @@
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return NULL;
 
-	list_for_each_entry_rcu(class, hash_head, hash_entry) {
+	hlist_for_each_entry_rcu(class, hash_head, hash_entry) {
 		if (class->key == key) {
 			/*
 			 * Huh! same key, different name? Did someone trample
@@ -742,7 +742,7 @@
 register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 {
 	struct lockdep_subclass_key *key;
-	struct list_head *hash_head;
+	struct hlist_head *hash_head;
 	struct lock_class *class;
 
 	DEBUG_LOCKS_WARN_ON(!irqs_disabled());
@@ -774,7 +774,7 @@
 	 * We have to do the hash-walk again, to avoid races
 	 * with another CPU:
 	 */
-	list_for_each_entry_rcu(class, hash_head, hash_entry) {
+	hlist_for_each_entry_rcu(class, hash_head, hash_entry) {
 		if (class->key == key)
 			goto out_unlock_set;
 	}
@@ -805,7 +805,7 @@
 	 * We use RCU's safe list-add method to make
 	 * parallel walking of the hash-list safe:
 	 */
-	list_add_tail_rcu(&class->hash_entry, hash_head);
+	hlist_add_head_rcu(&class->hash_entry, hash_head);
 	/*
 	 * Add it to the global list of classes:
 	 */
@@ -1822,7 +1822,7 @@
  */
 static int
 check_prev_add(struct task_struct *curr, struct held_lock *prev,
-	       struct held_lock *next, int distance, int trylock_loop)
+	       struct held_lock *next, int distance, int *stack_saved)
 {
 	struct lock_list *entry;
 	int ret;
@@ -1883,8 +1883,11 @@
 		}
 	}
 
-	if (!trylock_loop && !save_trace(&trace))
-		return 0;
+	if (!*stack_saved) {
+		if (!save_trace(&trace))
+			return 0;
+		*stack_saved = 1;
+	}
 
 	/*
 	 * Ok, all validations passed, add the new lock
@@ -1907,6 +1910,8 @@
 	 * Debugging printouts:
 	 */
 	if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) {
+		/* We drop graph lock, so another thread can overwrite trace. */
+		*stack_saved = 0;
 		graph_unlock();
 		printk("\n new dependency: ");
 		print_lock_name(hlock_class(prev));
@@ -1929,7 +1934,7 @@
 check_prevs_add(struct task_struct *curr, struct held_lock *next)
 {
 	int depth = curr->lockdep_depth;
-	int trylock_loop = 0;
+	int stack_saved = 0;
 	struct held_lock *hlock;
 
 	/*
@@ -1956,7 +1961,7 @@
 		 */
 		if (hlock->read != 2 && hlock->check) {
 			if (!check_prev_add(curr, hlock, next,
-						distance, trylock_loop))
+						distance, &stack_saved))
 				return 0;
 			/*
 			 * Stop after the first non-trylock entry,
@@ -1979,7 +1984,6 @@
 		if (curr->held_locks[depth].irq_context !=
 				curr->held_locks[depth-1].irq_context)
 			break;
-		trylock_loop = 1;
 	}
 	return 1;
 out_bug:
@@ -2017,7 +2021,7 @@
 				     u64 chain_key)
 {
 	struct lock_class *class = hlock_class(hlock);
-	struct list_head *hash_head = chainhashentry(chain_key);
+	struct hlist_head *hash_head = chainhashentry(chain_key);
 	struct lock_chain *chain;
 	struct held_lock *hlock_curr;
 	int i, j;
@@ -2033,7 +2037,7 @@
 	 * We can walk it lock-free, because entries only get added
 	 * to the hash:
 	 */
-	list_for_each_entry_rcu(chain, hash_head, entry) {
+	hlist_for_each_entry_rcu(chain, hash_head, entry) {
 		if (chain->chain_key == chain_key) {
 cache_hit:
 			debug_atomic_inc(chain_lookup_hits);
@@ -2057,7 +2061,7 @@
 	/*
 	 * We have to walk the chain again locked - to avoid duplicates:
 	 */
-	list_for_each_entry(chain, hash_head, entry) {
+	hlist_for_each_entry(chain, hash_head, entry) {
 		if (chain->chain_key == chain_key) {
 			graph_unlock();
 			goto cache_hit;
@@ -2091,7 +2095,7 @@
 		}
 		chain_hlocks[chain->base + j] = class - lock_classes;
 	}
-	list_add_tail_rcu(&chain->entry, hash_head);
+	hlist_add_head_rcu(&chain->entry, hash_head);
 	debug_atomic_inc(chain_lookup_misses);
 	inc_chains();
 
@@ -3875,7 +3879,7 @@
 	nr_process_chains = 0;
 	debug_locks = 1;
 	for (i = 0; i < CHAINHASH_SIZE; i++)
-		INIT_LIST_HEAD(chainhash_table + i);
+		INIT_HLIST_HEAD(chainhash_table + i);
 	raw_local_irq_restore(flags);
 }
 
@@ -3894,7 +3898,7 @@
 	/*
 	 * Unhash the class and remove it from the all_lock_classes list:
 	 */
-	list_del_rcu(&class->hash_entry);
+	hlist_del_rcu(&class->hash_entry);
 	list_del_rcu(&class->lock_entry);
 
 	RCU_INIT_POINTER(class->key, NULL);
@@ -3917,7 +3921,7 @@
 void lockdep_free_key_range(void *start, unsigned long size)
 {
 	struct lock_class *class;
-	struct list_head *head;
+	struct hlist_head *head;
 	unsigned long flags;
 	int i;
 	int locked;
@@ -3930,9 +3934,7 @@
 	 */
 	for (i = 0; i < CLASSHASH_SIZE; i++) {
 		head = classhash_table + i;
-		if (list_empty(head))
-			continue;
-		list_for_each_entry_rcu(class, head, hash_entry) {
+		hlist_for_each_entry_rcu(class, head, hash_entry) {
 			if (within(class->key, start, size))
 				zap_class(class);
 			else if (within(class->name, start, size))
@@ -3962,7 +3964,7 @@
 void lockdep_reset_lock(struct lockdep_map *lock)
 {
 	struct lock_class *class;
-	struct list_head *head;
+	struct hlist_head *head;
 	unsigned long flags;
 	int i, j;
 	int locked;
@@ -3987,9 +3989,7 @@
 	locked = graph_lock();
 	for (i = 0; i < CLASSHASH_SIZE; i++) {
 		head = classhash_table + i;
-		if (list_empty(head))
-			continue;
-		list_for_each_entry_rcu(class, head, hash_entry) {
+		hlist_for_each_entry_rcu(class, head, hash_entry) {
 			int match = 0;
 
 			for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++)
@@ -4027,10 +4027,10 @@
 		return;
 
 	for (i = 0; i < CLASSHASH_SIZE; i++)
-		INIT_LIST_HEAD(classhash_table + i);
+		INIT_HLIST_HEAD(classhash_table + i);
 
 	for (i = 0; i < CHAINHASH_SIZE; i++)
-		INIT_LIST_HEAD(chainhash_table + i);
+		INIT_HLIST_HEAD(chainhash_table + i);
 
 	lockdep_initialized = 1;
 }
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 70ee377..2c468de 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -150,7 +150,7 @@
 }
 EXPORT_SYMBOL(devm_memunmap);
 
-pfn_t phys_to_pfn_t(phys_addr_t addr, unsigned long flags)
+pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags)
 {
 	return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags);
 }
diff --git a/kernel/module.c b/kernel/module.c
index 8358f46..9537da3 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -303,6 +303,9 @@
 	struct _ddebug *debug;
 	unsigned int num_debug;
 	bool sig_ok;
+#ifdef CONFIG_KALLSYMS
+	unsigned long mod_kallsyms_init_off;
+#endif
 	struct {
 		unsigned int sym, str, mod, vers, info, pcpu;
 	} index;
@@ -2480,10 +2483,21 @@
 	strsect->sh_flags |= SHF_ALLOC;
 	strsect->sh_entsize = get_offset(mod, &mod->init_layout.size, strsect,
 					 info->index.str) | INIT_OFFSET_MASK;
-	mod->init_layout.size = debug_align(mod->init_layout.size);
 	pr_debug("\t%s\n", info->secstrings + strsect->sh_name);
+
+	/* We'll tack temporary mod_kallsyms on the end. */
+	mod->init_layout.size = ALIGN(mod->init_layout.size,
+				      __alignof__(struct mod_kallsyms));
+	info->mod_kallsyms_init_off = mod->init_layout.size;
+	mod->init_layout.size += sizeof(struct mod_kallsyms);
+	mod->init_layout.size = debug_align(mod->init_layout.size);
 }
 
+/*
+ * We use the full symtab and strtab which layout_symtab arranged to
+ * be appended to the init section.  Later we switch to the cut-down
+ * core-only ones.
+ */
 static void add_kallsyms(struct module *mod, const struct load_info *info)
 {
 	unsigned int i, ndst;
@@ -2492,29 +2506,34 @@
 	char *s;
 	Elf_Shdr *symsec = &info->sechdrs[info->index.sym];
 
-	mod->symtab = (void *)symsec->sh_addr;
-	mod->num_symtab = symsec->sh_size / sizeof(Elf_Sym);
+	/* Set up to point into init section. */
+	mod->kallsyms = mod->init_layout.base + info->mod_kallsyms_init_off;
+
+	mod->kallsyms->symtab = (void *)symsec->sh_addr;
+	mod->kallsyms->num_symtab = symsec->sh_size / sizeof(Elf_Sym);
 	/* Make sure we get permanent strtab: don't use info->strtab. */
-	mod->strtab = (void *)info->sechdrs[info->index.str].sh_addr;
+	mod->kallsyms->strtab = (void *)info->sechdrs[info->index.str].sh_addr;
 
 	/* Set types up while we still have access to sections. */
-	for (i = 0; i < mod->num_symtab; i++)
-		mod->symtab[i].st_info = elf_type(&mod->symtab[i], info);
+	for (i = 0; i < mod->kallsyms->num_symtab; i++)
+		mod->kallsyms->symtab[i].st_info
+			= elf_type(&mod->kallsyms->symtab[i], info);
 
-	mod->core_symtab = dst = mod->core_layout.base + info->symoffs;
-	mod->core_strtab = s = mod->core_layout.base + info->stroffs;
-	src = mod->symtab;
-	for (ndst = i = 0; i < mod->num_symtab; i++) {
+	/* Now populate the cut down core kallsyms for after init. */
+	mod->core_kallsyms.symtab = dst = mod->core_layout.base + info->symoffs;
+	mod->core_kallsyms.strtab = s = mod->core_layout.base + info->stroffs;
+	src = mod->kallsyms->symtab;
+	for (ndst = i = 0; i < mod->kallsyms->num_symtab; i++) {
 		if (i == 0 ||
 		    is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum,
 				   info->index.pcpu)) {
 			dst[ndst] = src[i];
-			dst[ndst++].st_name = s - mod->core_strtab;
-			s += strlcpy(s, &mod->strtab[src[i].st_name],
+			dst[ndst++].st_name = s - mod->core_kallsyms.strtab;
+			s += strlcpy(s, &mod->kallsyms->strtab[src[i].st_name],
 				     KSYM_NAME_LEN) + 1;
 		}
 	}
-	mod->core_num_syms = ndst;
+	mod->core_kallsyms.num_symtab = ndst;
 }
 #else
 static inline void layout_symtab(struct module *mod, struct load_info *info)
@@ -3263,9 +3282,8 @@
 	module_put(mod);
 	trim_init_extable(mod);
 #ifdef CONFIG_KALLSYMS
-	mod->num_symtab = mod->core_num_syms;
-	mod->symtab = mod->core_symtab;
-	mod->strtab = mod->core_strtab;
+	/* Switch to core kallsyms now init is done: kallsyms may be walking! */
+	rcu_assign_pointer(mod->kallsyms, &mod->core_kallsyms);
 #endif
 	mod_tree_remove_init(mod);
 	disable_ro_nx(&mod->init_layout);
@@ -3496,7 +3514,7 @@
 
 	/* Module is ready to execute: parsing args may do that. */
 	after_dashes = parse_args(mod->name, mod->args, mod->kp, mod->num_kp,
-				  -32768, 32767, NULL,
+				  -32768, 32767, mod,
 				  unknown_module_param_cb);
 	if (IS_ERR(after_dashes)) {
 		err = PTR_ERR(after_dashes);
@@ -3627,6 +3645,11 @@
 	       && (str[2] == '\0' || str[2] == '.');
 }
 
+static const char *symname(struct mod_kallsyms *kallsyms, unsigned int symnum)
+{
+	return kallsyms->strtab + kallsyms->symtab[symnum].st_name;
+}
+
 static const char *get_ksymbol(struct module *mod,
 			       unsigned long addr,
 			       unsigned long *size,
@@ -3634,6 +3657,7 @@
 {
 	unsigned int i, best = 0;
 	unsigned long nextval;
+	struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms);
 
 	/* At worse, next value is at end of module */
 	if (within_module_init(addr, mod))
@@ -3643,32 +3667,32 @@
 
 	/* Scan for closest preceding symbol, and next symbol. (ELF
 	   starts real symbols at 1). */
-	for (i = 1; i < mod->num_symtab; i++) {
-		if (mod->symtab[i].st_shndx == SHN_UNDEF)
+	for (i = 1; i < kallsyms->num_symtab; i++) {
+		if (kallsyms->symtab[i].st_shndx == SHN_UNDEF)
 			continue;
 
 		/* We ignore unnamed symbols: they're uninformative
 		 * and inserted at a whim. */
-		if (mod->symtab[i].st_value <= addr
-		    && mod->symtab[i].st_value > mod->symtab[best].st_value
-		    && *(mod->strtab + mod->symtab[i].st_name) != '\0'
-		    && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name))
+		if (*symname(kallsyms, i) == '\0'
+		    || is_arm_mapping_symbol(symname(kallsyms, i)))
+			continue;
+
+		if (kallsyms->symtab[i].st_value <= addr
+		    && kallsyms->symtab[i].st_value > kallsyms->symtab[best].st_value)
 			best = i;
-		if (mod->symtab[i].st_value > addr
-		    && mod->symtab[i].st_value < nextval
-		    && *(mod->strtab + mod->symtab[i].st_name) != '\0'
-		    && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name))
-			nextval = mod->symtab[i].st_value;
+		if (kallsyms->symtab[i].st_value > addr
+		    && kallsyms->symtab[i].st_value < nextval)
+			nextval = kallsyms->symtab[i].st_value;
 	}
 
 	if (!best)
 		return NULL;
 
 	if (size)
-		*size = nextval - mod->symtab[best].st_value;
+		*size = nextval - kallsyms->symtab[best].st_value;
 	if (offset)
-		*offset = addr - mod->symtab[best].st_value;
-	return mod->strtab + mod->symtab[best].st_name;
+		*offset = addr - kallsyms->symtab[best].st_value;
+	return symname(kallsyms, best);
 }
 
 /* For kallsyms to ask for address resolution.  NULL means not found.  Careful
@@ -3758,19 +3782,21 @@
 
 	preempt_disable();
 	list_for_each_entry_rcu(mod, &modules, list) {
+		struct mod_kallsyms *kallsyms;
+
 		if (mod->state == MODULE_STATE_UNFORMED)
 			continue;
-		if (symnum < mod->num_symtab) {
-			*value = mod->symtab[symnum].st_value;
-			*type = mod->symtab[symnum].st_info;
-			strlcpy(name, mod->strtab + mod->symtab[symnum].st_name,
-				KSYM_NAME_LEN);
+		kallsyms = rcu_dereference_sched(mod->kallsyms);
+		if (symnum < kallsyms->num_symtab) {
+			*value = kallsyms->symtab[symnum].st_value;
+			*type = kallsyms->symtab[symnum].st_info;
+			strlcpy(name, symname(kallsyms, symnum), KSYM_NAME_LEN);
 			strlcpy(module_name, mod->name, MODULE_NAME_LEN);
 			*exported = is_exported(name, *value, mod);
 			preempt_enable();
 			return 0;
 		}
-		symnum -= mod->num_symtab;
+		symnum -= kallsyms->num_symtab;
 	}
 	preempt_enable();
 	return -ERANGE;
@@ -3779,11 +3805,12 @@
 static unsigned long mod_find_symname(struct module *mod, const char *name)
 {
 	unsigned int i;
+	struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms);
 
-	for (i = 0; i < mod->num_symtab; i++)
-		if (strcmp(name, mod->strtab+mod->symtab[i].st_name) == 0 &&
-		    mod->symtab[i].st_info != 'U')
-			return mod->symtab[i].st_value;
+	for (i = 0; i < kallsyms->num_symtab; i++)
+		if (strcmp(name, symname(kallsyms, i)) == 0 &&
+		    kallsyms->symtab[i].st_info != 'U')
+			return kallsyms->symtab[i].st_value;
 	return 0;
 }
 
@@ -3822,11 +3849,14 @@
 	module_assert_mutex();
 
 	list_for_each_entry(mod, &modules, list) {
+		/* We hold module_mutex: no need for rcu_dereference_sched */
+		struct mod_kallsyms *kallsyms = mod->kallsyms;
+
 		if (mod->state == MODULE_STATE_UNFORMED)
 			continue;
-		for (i = 0; i < mod->num_symtab; i++) {
-			ret = fn(data, mod->strtab + mod->symtab[i].st_name,
-				 mod, mod->symtab[i].st_value);
+		for (i = 0; i < kallsyms->num_symtab; i++) {
+			ret = fn(data, symname(kallsyms, i),
+				 mod, kallsyms->symtab[i].st_value);
 			if (ret != 0)
 				return ret;
 		}
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 61a0264..7ff5dc7 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -301,7 +301,23 @@
 static LIST_HEAD(workqueues);		/* PR: list of all workqueues */
 static bool workqueue_freezing;		/* PL: have wqs started freezing? */
 
-static cpumask_var_t wq_unbound_cpumask; /* PL: low level cpumask for all unbound wqs */
+/* PL: allowable cpus for unbound wqs and work items */
+static cpumask_var_t wq_unbound_cpumask;
+
+/* CPU where unbound work was last round robin scheduled from this CPU */
+static DEFINE_PER_CPU(int, wq_rr_cpu_last);
+
+/*
+ * Local execution of unbound work items is no longer guaranteed.  The
+ * following always forces round-robin CPU selection on unbound work items
+ * to uncover usages which depend on it.
+ */
+#ifdef CONFIG_DEBUG_WQ_FORCE_RR_CPU
+static bool wq_debug_force_rr_cpu = true;
+#else
+static bool wq_debug_force_rr_cpu = false;
+#endif
+module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644);
 
 /* the per-cpu worker pools */
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS],
@@ -570,6 +586,16 @@
 						  int node)
 {
 	assert_rcu_or_wq_mutex_or_pool_mutex(wq);
+
+	/*
+	 * XXX: @node can be NUMA_NO_NODE if CPU goes offline while a
+	 * delayed item is pending.  The plan is to keep CPU -> NODE
+	 * mapping valid and stable across CPU on/offlines.  Once that
+	 * happens, this workaround can be removed.
+	 */
+	if (unlikely(node == NUMA_NO_NODE))
+		return wq->dfl_pwq;
+
 	return rcu_dereference_raw(wq->numa_pwq_tbl[node]);
 }
 
@@ -1298,6 +1324,39 @@
 	return worker && worker->current_pwq->wq == wq;
 }
 
+/*
+ * When queueing an unbound work item to a wq, prefer local CPU if allowed
+ * by wq_unbound_cpumask.  Otherwise, round robin among the allowed ones to
+ * avoid perturbing sensitive tasks.
+ */
+static int wq_select_unbound_cpu(int cpu)
+{
+	static bool printed_dbg_warning;
+	int new_cpu;
+
+	if (likely(!wq_debug_force_rr_cpu)) {
+		if (cpumask_test_cpu(cpu, wq_unbound_cpumask))
+			return cpu;
+	} else if (!printed_dbg_warning) {
+		pr_warn("workqueue: round-robin CPU selection forced, expect performance impact\n");
+		printed_dbg_warning = true;
+	}
+
+	if (cpumask_empty(wq_unbound_cpumask))
+		return cpu;
+
+	new_cpu = __this_cpu_read(wq_rr_cpu_last);
+	new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask);
+	if (unlikely(new_cpu >= nr_cpu_ids)) {
+		new_cpu = cpumask_first_and(wq_unbound_cpumask, cpu_online_mask);
+		if (unlikely(new_cpu >= nr_cpu_ids))
+			return cpu;
+	}
+	__this_cpu_write(wq_rr_cpu_last, new_cpu);
+
+	return new_cpu;
+}
+
 static void __queue_work(int cpu, struct workqueue_struct *wq,
 			 struct work_struct *work)
 {
@@ -1323,7 +1382,7 @@
 		return;
 retry:
 	if (req_cpu == WORK_CPU_UNBOUND)
-		cpu = raw_smp_processor_id();
+		cpu = wq_select_unbound_cpu(raw_smp_processor_id());
 
 	/* pwq which will be used unless @work is executing elsewhere */
 	if (!(wq->flags & WQ_UNBOUND))
@@ -1464,13 +1523,13 @@
 	timer_stats_timer_set_start_info(&dwork->timer);
 
 	dwork->wq = wq;
-	/* timer isn't guaranteed to run in this cpu, record earlier */
-	if (cpu == WORK_CPU_UNBOUND)
-		cpu = raw_smp_processor_id();
 	dwork->cpu = cpu;
 	timer->expires = jiffies + delay;
 
-	add_timer_on(timer, cpu);
+	if (unlikely(cpu != WORK_CPU_UNBOUND))
+		add_timer_on(timer, cpu);
+	else
+		add_timer(timer);
 }
 
 /**
@@ -2355,7 +2414,8 @@
 	WARN_ONCE(current->flags & PF_MEMALLOC,
 		  "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%pf",
 		  current->pid, current->comm, target_wq->name, target_func);
-	WARN_ONCE(worker && (worker->current_pwq->wq->flags & WQ_MEM_RECLAIM),
+	WARN_ONCE(worker && ((worker->current_pwq->wq->flags &
+			      (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM),
 		  "workqueue: WQ_MEM_RECLAIM %s:%pf is flushing !WQ_MEM_RECLAIM %s:%pf",
 		  worker->current_pwq->wq->name, worker->current_func,
 		  target_wq->name, target_func);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index ecb9e75..8bfd1ac 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1400,6 +1400,21 @@
 
 endmenu # "RCU Debugging"
 
+config DEBUG_WQ_FORCE_RR_CPU
+	bool "Force round-robin CPU selection for unbound work items"
+	depends on DEBUG_KERNEL
+	default n
+	help
+	  Workqueue used to implicitly guarantee that work items queued
+	  without explicit CPU specified are put on the local CPU.  This
+	  guarantee is no longer true and while local CPU is still
+	  preferred work items may be put on foreign CPUs.  Kernel
+	  parameter "workqueue.debug_force_rr_cpu" is added to force
+	  round-robin CPU selection to flush out usages which depend on the
+	  now broken guarantee.  This config option enables the debug
+	  feature by default.  When enabled, memory and cache locality will
+	  be impacted.
+
 config DEBUG_BLOCK_EXT_DEVT
         bool "Force extended block device numbers and spread them"
 	depends on DEBUG_KERNEL
diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan
index 49518fb..e07c1ba 100644
--- a/lib/Kconfig.ubsan
+++ b/lib/Kconfig.ubsan
@@ -18,6 +18,8 @@
 	  This option activates instrumentation for the entire kernel.
 	  If you don't enable this option, you have to explicitly specify
 	  UBSAN_SANITIZE := y for the files/directories you want to check for UB.
+	  Enabling this option will get kernel image size increased
+	  significantly.
 
 config UBSAN_ALIGNMENT
 	bool "Enable checking of pointers alignment"
@@ -25,5 +27,5 @@
 	default y if !HAVE_EFFICIENT_UNALIGNED_ACCESS
 	help
 	  This option enables detection of unaligned memory accesses.
-	  Enabling this option on architectures that support unalligned
+	  Enabling this option on architectures that support unaligned
 	  accesses may produce a lot of false positives.
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index bafa993..004fc70 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -598,9 +598,9 @@
  *
  * Description:
  *   Stops mapping iterator @miter.  @miter should have been started
- *   started using sg_miter_start().  A stopped iteration can be
- *   resumed by calling sg_miter_next() on it.  This is useful when
- *   resources (kmap) need to be released during iteration.
+ *   using sg_miter_start().  A stopped iteration can be resumed by
+ *   calling sg_miter_next() on it.  This is useful when resources (kmap)
+ *   need to be released during iteration.
  *
  * Context:
  *   Preemption disabled if the SG_MITER_ATOMIC is set.  Don't care
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 48ff9c3..f44e178 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -1590,22 +1590,23 @@
 			return buf;
 		}
 	case 'K':
-		/*
-		 * %pK cannot be used in IRQ context because its test
-		 * for CAP_SYSLOG would be meaningless.
-		 */
-		if (kptr_restrict && (in_irq() || in_serving_softirq() ||
-				      in_nmi())) {
-			if (spec.field_width == -1)
-				spec.field_width = default_width;
-			return string(buf, end, "pK-error", spec);
-		}
-
 		switch (kptr_restrict) {
 		case 0:
 			/* Always print %pK values */
 			break;
 		case 1: {
+			const struct cred *cred;
+
+			/*
+			 * kptr_restrict==1 cannot be used in IRQ context
+			 * because its test for CAP_SYSLOG would be meaningless.
+			 */
+			if (in_irq() || in_serving_softirq() || in_nmi()) {
+				if (spec.field_width == -1)
+					spec.field_width = default_width;
+				return string(buf, end, "pK-error", spec);
+			}
+
 			/*
 			 * Only print the real pointer value if the current
 			 * process has CAP_SYSLOG and is running with the
@@ -1615,8 +1616,7 @@
 			 * leak pointer values if a binary opens a file using
 			 * %pK and then elevates privileges before reading it.
 			 */
-			const struct cred *cred = current_cred();
-
+			cred = current_cred();
 			if (!has_capability_noaudit(current, CAP_SYSLOG) ||
 			    !uid_eq(cred->euid, cred->uid) ||
 			    !gid_eq(cred->egid, cred->gid))
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 926c76d..c554d17 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -328,7 +328,7 @@
 	return 0;
 
 out_destroy_stat:
-	while (--i)
+	while (i--)
 		percpu_counter_destroy(&wb->stat[i]);
 	fprop_local_destroy_percpu(&wb->completions);
 out_put_cong:
diff --git a/mm/filemap.c b/mm/filemap.c
index bc94386..23edcce 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1890,6 +1890,7 @@
  * page_cache_read - adds requested page to the page cache if not already there
  * @file:	file to read
  * @offset:	page index
+ * @gfp_mask:	memory allocation flags
  *
  * This adds the requested page to the page cache if it isn't already there,
  * and schedules an I/O to read in its contents from disk.
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 8eb7bb4..f7cb3d4 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -160,9 +160,11 @@
 		}
 
 		if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
-			if (next - addr != HPAGE_PMD_SIZE)
+			if (next - addr != HPAGE_PMD_SIZE) {
 				split_huge_pmd(vma, pmd, addr);
-			else {
+				if (pmd_none(*pmd))
+					continue;
+			} else {
 				int nr_ptes = change_huge_pmd(vma, pmd, addr,
 						newprot, prot_numa);
 
diff --git a/mm/mremap.c b/mm/mremap.c
index d77946a..8eeba02 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -210,6 +210,8 @@
 				}
 			}
 			split_huge_pmd(vma, old_pmd, old_addr);
+			if (pmd_none(*old_pmd))
+				continue;
 			VM_BUG_ON(pmd_trans_huge(*old_pmd));
 		}
 		if (pmd_none(*new_pmd) && __pte_alloc(new_vma->vm_mm, new_vma,
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 9d47676..06a005b 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -90,9 +90,9 @@
  * ARCHes with special requirements for evicting THP backing TLB entries can
  * implement this. Otherwise also, it can help optimize normal TLB flush in
  * THP regime. stock flush_tlb_range() typically has optimization to nuke the
- * entire TLB TLB if flush span is greater than a threshhold, which will
+ * entire TLB if flush span is greater than a threshold, which will
  * likely be true for a single huge page. Thus a single thp flush will
- * invalidate the entire TLB which is not desitable.
+ * invalidate the entire TLB which is not desirable.
  * e.g. see arch/arc: flush_pmd_tlb_range
  */
 #define flush_pmd_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
@@ -195,7 +195,9 @@
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 	VM_BUG_ON(pmd_trans_huge(*pmdp));
 	pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
-	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+
+	/* collapse entails shooting down ptes not pmd */
+	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	return pmd;
 }
 #endif
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index d79699c..eab81bc 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -208,7 +208,6 @@
 	case htons(ETH_P_IPV6): {
 		const struct ipv6hdr *iph;
 		struct ipv6hdr _iph;
-		__be32 flow_label;
 
 ipv6:
 		iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
@@ -230,8 +229,12 @@
 			key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
 		}
 
-		flow_label = ip6_flowlabel(iph);
-		if (flow_label) {
+		if ((dissector_uses_key(flow_dissector,
+					FLOW_DISSECTOR_KEY_FLOW_LABEL) ||
+		     (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL)) &&
+		    ip6_flowlabel(iph)) {
+			__be32 flow_label = ip6_flowlabel(iph);
+
 			if (dissector_uses_key(flow_dissector,
 					       FLOW_DISSECTOR_KEY_FLOW_LABEL)) {
 				key_tags = skb_flow_dissector_target(flow_dissector,
diff --git a/net/core/scm.c b/net/core/scm.c
index 14596fb..2696aef 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -87,6 +87,7 @@
 		*fplp = fpl;
 		fpl->count = 0;
 		fpl->max = SCM_MAX_FD;
+		fpl->user = NULL;
 	}
 	fpp = &fpl->fp[fpl->count];
 
@@ -107,6 +108,10 @@
 		*fpp++ = file;
 		fpl->count++;
 	}
+
+	if (!fpl->user)
+		fpl->user = get_uid(current_user());
+
 	return num;
 }
 
@@ -119,6 +124,7 @@
 		scm->fp = NULL;
 		for (i=fpl->count-1; i>=0; i--)
 			fput(fpl->fp[i]);
+		free_uid(fpl->user);
 		kfree(fpl);
 	}
 }
@@ -336,6 +342,7 @@
 		for (i = 0; i < fpl->count; i++)
 			get_file(fpl->fp[i]);
 		new_fpl->max = new_fpl->count;
+		new_fpl->user = get_uid(fpl->user);
 	}
 	return new_fpl;
 }
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b2df375..5bf88f5 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -79,6 +79,8 @@
 
 struct kmem_cache *skbuff_head_cache __read_mostly;
 static struct kmem_cache *skbuff_fclone_cache __read_mostly;
+int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;
+EXPORT_SYMBOL(sysctl_max_skb_frags);
 
 /**
  *	skb_panic - private function for out-of-line support
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 95b6139..a6beb7b 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -26,6 +26,7 @@
 static int one = 1;
 static int min_sndbuf = SOCK_MIN_SNDBUF;
 static int min_rcvbuf = SOCK_MIN_RCVBUF;
+static int max_skb_frags = MAX_SKB_FRAGS;
 
 static int net_msg_warn;	/* Unused, but still a sysctl */
 
@@ -392,6 +393,15 @@
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "max_skb_frags",
+		.data		= &sysctl_max_skb_frags,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
+		.extra2		= &max_skb_frags,
+	},
 	{ }
 };
 
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 7c51c4e..56fdf4e0d 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1240,6 +1240,14 @@
 	err = ipgre_newlink(net, dev, tb, NULL);
 	if (err < 0)
 		goto out;
+
+	/* openvswitch users expect packet sizes to be unrestricted,
+	 * so set the largest MTU we can.
+	 */
+	err = __ip_tunnel_change_mtu(dev, IP_MAX_MTU, false);
+	if (err)
+		goto out;
+
 	return dev;
 out:
 	free_netdev(dev);
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index c7bd72e..89e8861 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -943,17 +943,31 @@
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_ioctl);
 
-int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
+int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
+	int max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;
 
-	if (new_mtu < 68 ||
-	    new_mtu > 0xFFF8 - dev->hard_header_len - t_hlen)
+	if (new_mtu < 68)
 		return -EINVAL;
+
+	if (new_mtu > max_mtu) {
+		if (strict)
+			return -EINVAL;
+
+		new_mtu = max_mtu;
+	}
+
 	dev->mtu = new_mtu;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(__ip_tunnel_change_mtu);
+
+int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
+{
+	return __ip_tunnel_change_mtu(dev, new_mtu, true);
+}
 EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu);
 
 static void ip_tunnel_dev_free(struct net_device *dev)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 19746b3..0c36ef4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -940,7 +940,7 @@
 
 		i = skb_shinfo(skb)->nr_frags;
 		can_coalesce = skb_can_coalesce(skb, i, page, offset);
-		if (!can_coalesce && i >= MAX_SKB_FRAGS) {
+		if (!can_coalesce && i >= sysctl_max_skb_frags) {
 			tcp_mark_push(tp, skb);
 			goto new_segment;
 		}
@@ -1213,7 +1213,7 @@
 
 			if (!skb_can_coalesce(skb, i, pfrag->page,
 					      pfrag->offset)) {
-				if (i == MAX_SKB_FRAGS || !sg) {
+				if (i == sysctl_max_skb_frags || !sg) {
 					tcp_mark_push(tp, skb);
 					goto new_segment;
 				}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a4d5237..7f6ff03 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -311,7 +311,7 @@
 
 
 /* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */
-void tcp_req_err(struct sock *sk, u32 seq)
+void tcp_req_err(struct sock *sk, u32 seq, bool abort)
 {
 	struct request_sock *req = inet_reqsk(sk);
 	struct net *net = sock_net(sk);
@@ -323,7 +323,7 @@
 
 	if (seq != tcp_rsk(req)->snt_isn) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
-	} else {
+	} else if (abort) {
 		/*
 		 * Still in SYN_RECV, just remove it silently.
 		 * There is no good way to pass the error to the newly
@@ -383,7 +383,12 @@
 	}
 	seq = ntohl(th->seq);
 	if (sk->sk_state == TCP_NEW_SYN_RECV)
-		return tcp_req_err(sk, seq);
+		return tcp_req_err(sk, seq,
+				  type == ICMP_PARAMETERPROB ||
+				  type == ICMP_TIME_EXCEEDED ||
+				  (type == ICMP_DEST_UNREACH &&
+				   (code == ICMP_NET_UNREACH ||
+				    code == ICMP_HOST_UNREACH)));
 
 	bh_lock_sock(sk);
 	/* If too many ICMPs get dropped on busy
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 38eedde..9efd9ff 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3538,6 +3538,7 @@
 {
 	struct inet6_dev *idev = ifp->idev;
 	struct net_device *dev = idev->dev;
+	bool notify = false;
 
 	addrconf_join_solict(dev, &ifp->addr);
 
@@ -3583,7 +3584,7 @@
 			/* Because optimistic nodes can use this address,
 			 * notify listeners. If DAD fails, RTM_DELADDR is sent.
 			 */
-			ipv6_ifa_notify(RTM_NEWADDR, ifp);
+			notify = true;
 		}
 	}
 
@@ -3591,6 +3592,8 @@
 out:
 	spin_unlock(&ifp->lock);
 	read_unlock_bh(&idev->lock);
+	if (notify)
+		ipv6_ifa_notify(RTM_NEWADDR, ifp);
 }
 
 static void addrconf_dad_start(struct inet6_ifaddr *ifp)
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 1f9ebe3..dc2db4f 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -540,12 +540,13 @@
 		}
 		spin_lock_bh(&ip6_sk_fl_lock);
 		for (sflp = &np->ipv6_fl_list;
-		     (sfl = rcu_dereference(*sflp)) != NULL;
+		     (sfl = rcu_dereference_protected(*sflp,
+						      lockdep_is_held(&ip6_sk_fl_lock))) != NULL;
 		     sflp = &sfl->next) {
 			if (sfl->fl->label == freq.flr_label) {
 				if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK))
 					np->flow_label &= ~IPV6_FLOWLABEL_MASK;
-				*sflp = rcu_dereference(sfl->next);
+				*sflp = sfl->next;
 				spin_unlock_bh(&ip6_sk_fl_lock);
 				fl_release(sfl->fl);
 				kfree_rcu(sfl, rcu);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 006396e..1a5a70f 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -327,6 +327,7 @@
 	struct tcp_sock *tp;
 	__u32 seq, snd_una;
 	struct sock *sk;
+	bool fatal;
 	int err;
 
 	sk = __inet6_lookup_established(net, &tcp_hashinfo,
@@ -345,8 +346,9 @@
 		return;
 	}
 	seq = ntohl(th->seq);
+	fatal = icmpv6_err_convert(type, code, &err);
 	if (sk->sk_state == TCP_NEW_SYN_RECV)
-		return tcp_req_err(sk, seq);
+		return tcp_req_err(sk, seq, fatal);
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG)
@@ -400,7 +402,6 @@
 		goto out;
 	}
 
-	icmpv6_err_convert(type, code, &err);
 
 	/* Might be for an request_sock */
 	switch (sk->sk_state) {
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index 1605691..de9cb19 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -91,6 +91,8 @@
 	struct vxlan_config conf = {
 		.no_share = true,
 		.flags = VXLAN_F_COLLECT_METADATA,
+		/* Don't restrict the packets that can be sent by MTU */
+		.mtu = IP_MAX_MTU,
 	};
 
 	if (!options) {
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 5ca2ebf..e878da0 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -5538,6 +5538,7 @@
 	struct sctp_hmac_algo_param *hmacs;
 	__u16 data_len = 0;
 	u32 num_idents;
+	int i;
 
 	if (!ep->auth_enable)
 		return -EACCES;
@@ -5555,8 +5556,12 @@
 		return -EFAULT;
 	if (put_user(num_idents, &p->shmac_num_idents))
 		return -EFAULT;
-	if (copy_to_user(p->shmac_idents, hmacs->hmac_ids, data_len))
-		return -EFAULT;
+	for (i = 0; i < num_idents; i++) {
+		__u16 hmacid = ntohs(hmacs->hmac_ids[i]);
+
+		if (copy_to_user(&p->shmac_idents[i], &hmacid, sizeof(__u16)))
+			return -EFAULT;
+	}
 	return 0;
 }
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 49d5093..29be035 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1496,7 +1496,7 @@
 	UNIXCB(skb).fp = NULL;
 
 	for (i = scm->fp->count-1; i >= 0; i--)
-		unix_notinflight(scm->fp->fp[i]);
+		unix_notinflight(scm->fp->user, scm->fp->fp[i]);
 }
 
 static void unix_destruct_scm(struct sk_buff *skb)
@@ -1561,7 +1561,7 @@
 		return -ENOMEM;
 
 	for (i = scm->fp->count - 1; i >= 0; i--)
-		unix_inflight(scm->fp->fp[i]);
+		unix_inflight(scm->fp->user, scm->fp->fp[i]);
 	return max_level;
 }
 
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 8fcdc22..6a0d485 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -116,7 +116,7 @@
  * descriptor if it is for an AF_UNIX socket.
  */
 
-void unix_inflight(struct file *fp)
+void unix_inflight(struct user_struct *user, struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
 
@@ -133,11 +133,11 @@
 		}
 		unix_tot_inflight++;
 	}
-	fp->f_cred->user->unix_inflight++;
+	user->unix_inflight++;
 	spin_unlock(&unix_gc_lock);
 }
 
-void unix_notinflight(struct file *fp)
+void unix_notinflight(struct user_struct *user, struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
 
@@ -152,7 +152,7 @@
 			list_del_init(&u->link);
 		unix_tot_inflight--;
 	}
-	fp->f_cred->user->unix_inflight--;
+	user->unix_inflight--;
 	spin_unlock(&unix_gc_lock);
 }
 
diff --git a/scripts/prune-kernel b/scripts/prune-kernel
new file mode 100755
index 0000000..ab5034e
--- /dev/null
+++ b/scripts/prune-kernel
@@ -0,0 +1,20 @@
+#!/bin/bash
+
+# because I use CONFIG_LOCALVERSION_AUTO, not the same version again and
+# again, /boot and /lib/modules/ eventually fill up.
+# Dumb script to purge that stuff:
+
+for f in "$@"
+do
+        if rpm -qf "/lib/modules/$f" >/dev/null; then
+                echo "keeping $f (installed from rpm)"
+        elif [ $(uname -r) = "$f" ]; then
+                echo "keeping $f (running kernel) "
+        else
+                echo "removing $f"
+                rm -f "/boot/initramfs-$f.img" "/boot/System.map-$f"
+                rm -f "/boot/vmlinuz-$f"   "/boot/config-$f"
+                rm -rf "/lib/modules/$f"
+                new-kernel-pkg --remove $f
+        fi
+done
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index f716025..e6ea9d4 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -23,6 +23,7 @@
 #include <linux/integrity.h>
 #include <linux/evm.h>
 #include <crypto/hash.h>
+#include <crypto/algapi.h>
 #include "evm.h"
 
 int evm_initialized;
@@ -148,7 +149,7 @@
 				   xattr_value_len, calc.digest);
 		if (rc)
 			break;
-		rc = memcmp(xattr_data->digest, calc.digest,
+		rc = crypto_memneq(xattr_data->digest, calc.digest,
 			    sizeof(calc.digest));
 		if (rc)
 			rc = -EINVAL;
diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c
index 2bbb418..8495b93 100644
--- a/security/selinux/nlmsgtab.c
+++ b/security/selinux/nlmsgtab.c
@@ -83,6 +83,7 @@
 	{ TCPDIAG_GETSOCK,	NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
 	{ DCCPDIAG_GETSOCK,	NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
 	{ SOCK_DIAG_BY_FAMILY,	NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
+	{ SOCK_DESTROY,		NETLINK_TCPDIAG_SOCKET__NLMSG_WRITE },
 };
 
 static struct nlmsg_perm nlmsg_xfrm_perms[] =
diff --git a/sound/core/timer.c b/sound/core/timer.c
index 9b513a0..dca817f 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -422,7 +422,7 @@
 	spin_lock_irqsave(&timer->lock, flags);
 	list_for_each_entry(ts, &ti->slave_active_head, active_list)
 		if (ts->ccallback)
-			ts->ccallback(ti, event + 100, &tstamp, resolution);
+			ts->ccallback(ts, event + 100, &tstamp, resolution);
 	spin_unlock_irqrestore(&timer->lock, flags);
 }
 
@@ -518,9 +518,13 @@
 			spin_unlock_irqrestore(&slave_active_lock, flags);
 			return -EBUSY;
 		}
+		if (timeri->timer)
+			spin_lock(&timeri->timer->lock);
 		timeri->flags &= ~SNDRV_TIMER_IFLG_RUNNING;
 		list_del_init(&timeri->ack_list);
 		list_del_init(&timeri->active_list);
+		if (timeri->timer)
+			spin_unlock(&timeri->timer->lock);
 		spin_unlock_irqrestore(&slave_active_lock, flags);
 		goto __end;
 	}
@@ -1929,6 +1933,7 @@
 {
 	struct snd_timer_user *tu;
 	long result = 0, unit;
+	int qhead;
 	int err = 0;
 
 	tu = file->private_data;
@@ -1940,7 +1945,7 @@
 
 			if ((file->f_flags & O_NONBLOCK) != 0 || result > 0) {
 				err = -EAGAIN;
-				break;
+				goto _error;
 			}
 
 			set_current_state(TASK_INTERRUPTIBLE);
@@ -1955,42 +1960,37 @@
 
 			if (tu->disconnected) {
 				err = -ENODEV;
-				break;
+				goto _error;
 			}
 			if (signal_pending(current)) {
 				err = -ERESTARTSYS;
-				break;
+				goto _error;
 			}
 		}
 
+		qhead = tu->qhead++;
+		tu->qhead %= tu->queue_size;
 		spin_unlock_irq(&tu->qlock);
-		if (err < 0)
-			goto _error;
 
 		if (tu->tread) {
-			if (copy_to_user(buffer, &tu->tqueue[tu->qhead++],
-					 sizeof(struct snd_timer_tread))) {
+			if (copy_to_user(buffer, &tu->tqueue[qhead],
+					 sizeof(struct snd_timer_tread)))
 				err = -EFAULT;
-				goto _error;
-			}
 		} else {
-			if (copy_to_user(buffer, &tu->queue[tu->qhead++],
-					 sizeof(struct snd_timer_read))) {
+			if (copy_to_user(buffer, &tu->queue[qhead],
+					 sizeof(struct snd_timer_read)))
 				err = -EFAULT;
-				goto _error;
-			}
 		}
 
-		tu->qhead %= tu->queue_size;
-
-		result += unit;
-		buffer += unit;
-
 		spin_lock_irq(&tu->qlock);
 		tu->qused--;
+		if (err < 0)
+			goto _error;
+		result += unit;
+		buffer += unit;
 	}
-	spin_unlock_irq(&tu->qlock);
  _error:
+	spin_unlock_irq(&tu->qlock);
 	return result > 0 ? result : err;
 }
 
diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c
index bde3330..c0f8f61 100644
--- a/sound/drivers/dummy.c
+++ b/sound/drivers/dummy.c
@@ -87,7 +87,7 @@
 module_param(fake_buffer, bool, 0444);
 MODULE_PARM_DESC(fake_buffer, "Fake buffer allocations.");
 #ifdef CONFIG_HIGH_RES_TIMERS
-module_param(hrtimer, bool, 0444);
+module_param(hrtimer, bool, 0644);
 MODULE_PARM_DESC(hrtimer, "Use hrtimer as the timer source.");
 #endif
 
@@ -109,6 +109,9 @@
 	snd_pcm_uframes_t (*pointer)(struct snd_pcm_substream *);
 };
 
+#define get_dummy_ops(substream) \
+	(*(const struct dummy_timer_ops **)(substream)->runtime->private_data)
+
 struct dummy_model {
 	const char *name;
 	int (*playback_constraints)(struct snd_pcm_runtime *runtime);
@@ -137,7 +140,6 @@
 	int iobox;
 	struct snd_kcontrol *cd_volume_ctl;
 	struct snd_kcontrol *cd_switch_ctl;
-	const struct dummy_timer_ops *timer_ops;
 };
 
 /*
@@ -231,6 +233,8 @@
  */
 
 struct dummy_systimer_pcm {
+	/* ops must be the first item */
+	const struct dummy_timer_ops *timer_ops;
 	spinlock_t lock;
 	struct timer_list timer;
 	unsigned long base_time;
@@ -366,6 +370,8 @@
  */
 
 struct dummy_hrtimer_pcm {
+	/* ops must be the first item */
+	const struct dummy_timer_ops *timer_ops;
 	ktime_t base_time;
 	ktime_t period_time;
 	atomic_t running;
@@ -492,31 +498,25 @@
 
 static int dummy_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 {
-	struct snd_dummy *dummy = snd_pcm_substream_chip(substream);
-
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_RESUME:
-		return dummy->timer_ops->start(substream);
+		return get_dummy_ops(substream)->start(substream);
 	case SNDRV_PCM_TRIGGER_STOP:
 	case SNDRV_PCM_TRIGGER_SUSPEND:
-		return dummy->timer_ops->stop(substream);
+		return get_dummy_ops(substream)->stop(substream);
 	}
 	return -EINVAL;
 }
 
 static int dummy_pcm_prepare(struct snd_pcm_substream *substream)
 {
-	struct snd_dummy *dummy = snd_pcm_substream_chip(substream);
-
-	return dummy->timer_ops->prepare(substream);
+	return get_dummy_ops(substream)->prepare(substream);
 }
 
 static snd_pcm_uframes_t dummy_pcm_pointer(struct snd_pcm_substream *substream)
 {
-	struct snd_dummy *dummy = snd_pcm_substream_chip(substream);
-
-	return dummy->timer_ops->pointer(substream);
+	return get_dummy_ops(substream)->pointer(substream);
 }
 
 static struct snd_pcm_hardware dummy_pcm_hardware = {
@@ -562,17 +562,19 @@
 	struct snd_dummy *dummy = snd_pcm_substream_chip(substream);
 	struct dummy_model *model = dummy->model;
 	struct snd_pcm_runtime *runtime = substream->runtime;
+	const struct dummy_timer_ops *ops;
 	int err;
 
-	dummy->timer_ops = &dummy_systimer_ops;
+	ops = &dummy_systimer_ops;
 #ifdef CONFIG_HIGH_RES_TIMERS
 	if (hrtimer)
-		dummy->timer_ops = &dummy_hrtimer_ops;
+		ops = &dummy_hrtimer_ops;
 #endif
 
-	err = dummy->timer_ops->create(substream);
+	err = ops->create(substream);
 	if (err < 0)
 		return err;
+	get_dummy_ops(substream) = ops;
 
 	runtime->hw = dummy->pcm_hw;
 	if (substream->pcm->device & 1) {
@@ -594,7 +596,7 @@
 			err = model->capture_constraints(substream->runtime);
 	}
 	if (err < 0) {
-		dummy->timer_ops->free(substream);
+		get_dummy_ops(substream)->free(substream);
 		return err;
 	}
 	return 0;
@@ -602,8 +604,7 @@
 
 static int dummy_pcm_close(struct snd_pcm_substream *substream)
 {
-	struct snd_dummy *dummy = snd_pcm_substream_chip(substream);
-	dummy->timer_ops->free(substream);
+	get_dummy_ops(substream)->free(substream);
 	return 0;
 }
 
diff --git a/sound/firewire/digi00x/amdtp-dot.c b/sound/firewire/digi00x/amdtp-dot.c
index b02a5e8c..0ac92ab 100644
--- a/sound/firewire/digi00x/amdtp-dot.c
+++ b/sound/firewire/digi00x/amdtp-dot.c
@@ -63,7 +63,7 @@
 #define BYTE_PER_SAMPLE (4)
 #define MAGIC_DOT_BYTE (2)
 #define MAGIC_BYTE_OFF(x) (((x) * BYTE_PER_SAMPLE) + MAGIC_DOT_BYTE)
-static const u8 dot_scrt(const u8 idx, const unsigned int off)
+static u8 dot_scrt(const u8 idx, const unsigned int off)
 {
 	/*
 	 * the length of the added pattern only depends on the lower nibble
diff --git a/sound/firewire/tascam/tascam-transaction.c b/sound/firewire/tascam/tascam-transaction.c
index 904ce03..040a96d 100644
--- a/sound/firewire/tascam/tascam-transaction.c
+++ b/sound/firewire/tascam/tascam-transaction.c
@@ -230,6 +230,7 @@
 	return err;
 error:
 	fw_core_remove_address_handler(&tscm->async_handler);
+	tscm->async_handler.callback_data = NULL;
 	return err;
 }
 
@@ -276,6 +277,9 @@
 	__be32 reg;
 	unsigned int i;
 
+	if (tscm->async_handler.callback_data == NULL)
+		return;
+
 	/* Turn off FireWire LED. */
 	reg = cpu_to_be32(0x0000008e);
 	snd_fw_transaction(tscm->unit, TCODE_WRITE_QUADLET_REQUEST,
@@ -297,6 +301,8 @@
 			   &reg, sizeof(reg), 0);
 
 	fw_core_remove_address_handler(&tscm->async_handler);
+	tscm->async_handler.callback_data = NULL;
+
 	for (i = 0; i < TSCM_MIDI_OUT_PORT_MAX; i++)
 		snd_fw_async_midi_port_destroy(&tscm->out_ports[i]);
 }
diff --git a/sound/firewire/tascam/tascam.c b/sound/firewire/tascam/tascam.c
index ee0bc18..e281c33 100644
--- a/sound/firewire/tascam/tascam.c
+++ b/sound/firewire/tascam/tascam.c
@@ -21,7 +21,6 @@
 		.pcm_playback_analog_channels = 8,
 		.midi_capture_ports = 4,
 		.midi_playback_ports = 4,
-		.is_controller = true,
 	},
 	{
 		.name = "FW-1082",
@@ -31,9 +30,16 @@
 		.pcm_playback_analog_channels = 2,
 		.midi_capture_ports = 2,
 		.midi_playback_ports = 2,
-		.is_controller = true,
 	},
-	/* FW-1804 may be supported. */
+	{
+		.name = "FW-1804",
+		.has_adat = true,
+		.has_spdif = true,
+		.pcm_capture_analog_channels = 8,
+		.pcm_playback_analog_channels = 2,
+		.midi_capture_ports = 2,
+		.midi_playback_ports = 4,
+	},
 };
 
 static int identify_model(struct snd_tscm *tscm)
diff --git a/sound/firewire/tascam/tascam.h b/sound/firewire/tascam/tascam.h
index 2d028d2..30ab77e 100644
--- a/sound/firewire/tascam/tascam.h
+++ b/sound/firewire/tascam/tascam.h
@@ -39,7 +39,6 @@
 	unsigned int pcm_playback_analog_channels;
 	unsigned int midi_capture_ports;
 	unsigned int midi_playback_ports;
-	bool is_controller;
 };
 
 #define TSCM_MIDI_IN_PORT_MAX	4
@@ -72,9 +71,6 @@
 	struct snd_fw_async_midi_port out_ports[TSCM_MIDI_OUT_PORT_MAX];
 	u8 running_status[TSCM_MIDI_OUT_PORT_MAX];
 	bool on_sysex[TSCM_MIDI_OUT_PORT_MAX];
-
-	/* For control messages. */
-	struct snd_firewire_tascam_status *status;
 };
 
 #define TSCM_ADDR_BASE			0xffff00000000ull
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index 30c8efe..7ca5b89 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -4028,9 +4028,9 @@
 			       struct hda_jack_callback *jack,
 			       bool on)
 {
-	if (jack && jack->tbl->nid)
+	if (jack && jack->nid)
 		sync_power_state_change(codec,
-					set_pin_power_jack(codec, jack->tbl->nid, on));
+					set_pin_power_jack(codec, jack->nid, on));
 }
 
 /* callback only doing power up -- called at first */
diff --git a/sound/pci/hda/hda_jack.c b/sound/pci/hda/hda_jack.c
index c945e25..a33234e 100644
--- a/sound/pci/hda/hda_jack.c
+++ b/sound/pci/hda/hda_jack.c
@@ -259,7 +259,7 @@
 		if (!callback)
 			return ERR_PTR(-ENOMEM);
 		callback->func = func;
-		callback->tbl = jack;
+		callback->nid = jack->nid;
 		callback->next = jack->callback;
 		jack->callback = callback;
 	}
diff --git a/sound/pci/hda/hda_jack.h b/sound/pci/hda/hda_jack.h
index 858708a..e9814c0 100644
--- a/sound/pci/hda/hda_jack.h
+++ b/sound/pci/hda/hda_jack.h
@@ -21,7 +21,7 @@
 typedef void (*hda_jack_callback_fn) (struct hda_codec *, struct hda_jack_callback *);
 
 struct hda_jack_callback {
-	struct hda_jack_tbl *tbl;
+	hda_nid_t nid;
 	hda_jack_callback_fn func;
 	unsigned int private_data;	/* arbitrary data */
 	struct hda_jack_callback *next;
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 4ef2259..9ceb2bc 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -4427,13 +4427,16 @@
 static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb)
 {
 	struct ca0132_spec *spec = codec->spec;
+	struct hda_jack_tbl *tbl;
 
 	/* Delay enabling the HP amp, to let the mic-detection
 	 * state machine run.
 	 */
 	cancel_delayed_work_sync(&spec->unsol_hp_work);
 	schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500));
-	cb->tbl->block_report = 1;
+	tbl = snd_hda_jack_tbl_get(codec, cb->nid);
+	if (tbl)
+		tbl->block_report = 1;
 }
 
 static void amic_callback(struct hda_codec *codec, struct hda_jack_callback *cb)
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 1f52b55..8ee78db 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -448,7 +448,8 @@
 	eld = &per_pin->sink_eld;
 
 	mutex_lock(&per_pin->lock);
-	if (eld->eld_size > ARRAY_SIZE(ucontrol->value.bytes.data)) {
+	if (eld->eld_size > ARRAY_SIZE(ucontrol->value.bytes.data) ||
+	    eld->eld_size > ELD_MAX_SIZE) {
 		mutex_unlock(&per_pin->lock);
 		snd_BUG();
 		return -EINVAL;
@@ -1193,7 +1194,7 @@
 static void jack_callback(struct hda_codec *codec,
 			  struct hda_jack_callback *jack)
 {
-	check_presence_and_report(codec, jack->tbl->nid);
+	check_presence_and_report(codec, jack->nid);
 }
 
 static void hdmi_intrinsic_event(struct hda_codec *codec, unsigned int res)
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 21992fb..efd4980 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -282,7 +282,7 @@
 	uctl = kzalloc(sizeof(*uctl), GFP_KERNEL);
 	if (!uctl)
 		return;
-	val = snd_hda_codec_read(codec, jack->tbl->nid, 0,
+	val = snd_hda_codec_read(codec, jack->nid, 0,
 				 AC_VERB_GET_VOLUME_KNOB_CONTROL, 0);
 	val &= HDA_AMP_VOLMASK;
 	uctl->value.integer.value[0] = val;
@@ -1787,7 +1787,6 @@
 	ALC882_FIXUP_NO_PRIMARY_HP,
 	ALC887_FIXUP_ASUS_BASS,
 	ALC887_FIXUP_BASS_CHMAP,
-	ALC882_FIXUP_DISABLE_AAMIX,
 };
 
 static void alc889_fixup_coef(struct hda_codec *codec,
@@ -1949,8 +1948,6 @@
 
 static void alc_fixup_bass_chmap(struct hda_codec *codec,
 				 const struct hda_fixup *fix, int action);
-static void alc_fixup_disable_aamix(struct hda_codec *codec,
-				    const struct hda_fixup *fix, int action);
 
 static const struct hda_fixup alc882_fixups[] = {
 	[ALC882_FIXUP_ABIT_AW9D_MAX] = {
@@ -2188,10 +2185,6 @@
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_bass_chmap,
 	},
-	[ALC882_FIXUP_DISABLE_AAMIX] = {
-		.type = HDA_FIXUP_FUNC,
-		.v.func = alc_fixup_disable_aamix,
-	},
 };
 
 static const struct snd_pci_quirk alc882_fixup_tbl[] = {
@@ -2230,6 +2223,7 @@
 	SND_PCI_QUIRK(0x104d, 0x9047, "Sony Vaio TT", ALC889_FIXUP_VAIO_TT),
 	SND_PCI_QUIRK(0x104d, 0x905a, "Sony Vaio Z", ALC882_FIXUP_NO_PRIMARY_HP),
 	SND_PCI_QUIRK(0x104d, 0x9043, "Sony Vaio VGC-LN51JGB", ALC882_FIXUP_NO_PRIMARY_HP),
+	SND_PCI_QUIRK(0x104d, 0x9044, "Sony VAIO AiO", ALC882_FIXUP_NO_PRIMARY_HP),
 
 	/* All Apple entries are in codec SSIDs */
 	SND_PCI_QUIRK(0x106b, 0x00a0, "MacBookPro 3,1", ALC889_FIXUP_MBP_VREF),
@@ -2259,7 +2253,6 @@
 	SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD),
 	SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),
 	SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte EP45-DS3/Z87X-UD3H", ALC889_FIXUP_FRONT_HP_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1458, 0xa182, "Gigabyte Z170X-UD3", ALC882_FIXUP_DISABLE_AAMIX),
 	SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX),
 	SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD),
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 2c7c5eb..37b70f8 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -493,9 +493,9 @@
 	if (!spec->num_pwrs)
 		return;
 
-	if (jack && jack->tbl->nid) {
-		stac_toggle_power_map(codec, jack->tbl->nid,
-				      snd_hda_jack_detect(codec, jack->tbl->nid),
+	if (jack && jack->nid) {
+		stac_toggle_power_map(codec, jack->nid,
+				      snd_hda_jack_detect(codec, jack->nid),
 				      true);
 		return;
 	}
diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index 3191e0a..d1fb035 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -635,6 +635,7 @@
 					    SNDRV_PCM_HW_PARAM_PERIODS);
 	if (ret < 0) {
 		dev_err(prtd->platform->dev, "set integer constraint failed\n");
+		kfree(adata);
 		return ret;
 	}
 
diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c
index 33143fe..9178531 100644
--- a/sound/soc/codecs/arizona.c
+++ b/sound/soc/codecs/arizona.c
@@ -1929,6 +1929,25 @@
 	{ 1000000, 13500000, 0,  1 },
 };
 
+static const unsigned int pseudo_fref_max[ARIZONA_FLL_MAX_FRATIO] = {
+	13500000,
+	 6144000,
+	 6144000,
+	 3072000,
+	 3072000,
+	 2822400,
+	 2822400,
+	 1536000,
+	 1536000,
+	 1536000,
+	 1536000,
+	 1536000,
+	 1536000,
+	 1536000,
+	 1536000,
+	  768000,
+};
+
 static struct {
 	unsigned int min;
 	unsigned int max;
@@ -2042,16 +2061,32 @@
 	/* Adjust FRATIO/refdiv to avoid integer mode if possible */
 	refdiv = cfg->refdiv;
 
+	arizona_fll_dbg(fll, "pseudo: initial ratio=%u fref=%u refdiv=%u\n",
+			init_ratio, Fref, refdiv);
+
 	while (div <= ARIZONA_FLL_MAX_REFDIV) {
 		for (ratio = init_ratio; ratio <= ARIZONA_FLL_MAX_FRATIO;
 		     ratio++) {
 			if ((ARIZONA_FLL_VCO_CORNER / 2) /
-			    (fll->vco_mult * ratio) < Fref)
+			    (fll->vco_mult * ratio) < Fref) {
+				arizona_fll_dbg(fll, "pseudo: hit VCO corner\n");
 				break;
+			}
+
+			if (Fref > pseudo_fref_max[ratio - 1]) {
+				arizona_fll_dbg(fll,
+					"pseudo: exceeded max fref(%u) for ratio=%u\n",
+					pseudo_fref_max[ratio - 1],
+					ratio);
+				break;
+			}
 
 			if (target % (ratio * Fref)) {
 				cfg->refdiv = refdiv;
 				cfg->fratio = ratio - 1;
+				arizona_fll_dbg(fll,
+					"pseudo: found fref=%u refdiv=%d(%d) ratio=%d\n",
+					Fref, refdiv, div, ratio);
 				return ratio;
 			}
 		}
@@ -2060,6 +2095,9 @@
 			if (target % (ratio * Fref)) {
 				cfg->refdiv = refdiv;
 				cfg->fratio = ratio - 1;
+				arizona_fll_dbg(fll,
+					"pseudo: found fref=%u refdiv=%d(%d) ratio=%d\n",
+					Fref, refdiv, div, ratio);
 				return ratio;
 			}
 		}
@@ -2068,6 +2106,9 @@
 		Fref /= 2;
 		refdiv++;
 		init_ratio = arizona_find_fratio(Fref, NULL);
+		arizona_fll_dbg(fll,
+				"pseudo: change fref=%u refdiv=%d(%d) ratio=%u\n",
+				Fref, refdiv, div, init_ratio);
 	}
 
 	arizona_fll_warn(fll, "Falling back to integer mode operation\n");
diff --git a/sound/soc/codecs/rt286.c b/sound/soc/codecs/rt286.c
index bc08f0c..1bd3164 100644
--- a/sound/soc/codecs/rt286.c
+++ b/sound/soc/codecs/rt286.c
@@ -266,6 +266,8 @@
 		} else {
 			*mic = false;
 			regmap_write(rt286->regmap, RT286_SET_MIC1, 0x20);
+			regmap_update_bits(rt286->regmap,
+				RT286_CBJ_CTRL1, 0x0400, 0x0000);
 		}
 	} else {
 		regmap_read(rt286->regmap, RT286_GET_HP_SENSE, &buf);
@@ -470,24 +472,6 @@
 	return 0;
 }
 
-static int rt286_vref_event(struct snd_soc_dapm_widget *w,
-			     struct snd_kcontrol *kcontrol, int event)
-{
-	struct snd_soc_codec *codec = snd_soc_dapm_to_codec(w->dapm);
-
-	switch (event) {
-	case SND_SOC_DAPM_PRE_PMU:
-		snd_soc_update_bits(codec,
-			RT286_CBJ_CTRL1, 0x0400, 0x0000);
-		mdelay(50);
-		break;
-	default:
-		return 0;
-	}
-
-	return 0;
-}
-
 static int rt286_ldo2_event(struct snd_soc_dapm_widget *w,
 			     struct snd_kcontrol *kcontrol, int event)
 {
@@ -536,7 +520,7 @@
 	SND_SOC_DAPM_SUPPLY_S("HV", 1, RT286_POWER_CTRL1,
 		12, 1, NULL, 0),
 	SND_SOC_DAPM_SUPPLY("VREF", RT286_POWER_CTRL1,
-		0, 1, rt286_vref_event, SND_SOC_DAPM_PRE_PMU),
+		0, 1, NULL, 0),
 	SND_SOC_DAPM_SUPPLY_S("LDO1", 1, RT286_POWER_CTRL2,
 		2, 0, NULL, 0),
 	SND_SOC_DAPM_SUPPLY_S("LDO2", 2, RT286_POWER_CTRL1,
@@ -911,8 +895,6 @@
 	case SND_SOC_BIAS_ON:
 		mdelay(10);
 		snd_soc_update_bits(codec,
-			RT286_CBJ_CTRL1, 0x0400, 0x0400);
-		snd_soc_update_bits(codec,
 			RT286_DC_GAIN, 0x200, 0x0);
 
 		break;
@@ -920,8 +902,6 @@
 	case SND_SOC_BIAS_STANDBY:
 		snd_soc_write(codec,
 			RT286_SET_AUDIO_POWER, AC_PWRST_D3);
-		snd_soc_update_bits(codec,
-			RT286_CBJ_CTRL1, 0x0400, 0x0000);
 		break;
 
 	default:
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index c61d38b..93e8c90 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -776,7 +776,7 @@
 
 	/* IN1/IN2 Control */
 	SOC_SINGLE_TLV("IN1 Boost", RT5645_IN1_CTRL1,
-		RT5645_BST_SFT1, 8, 0, bst_tlv),
+		RT5645_BST_SFT1, 12, 0, bst_tlv),
 	SOC_SINGLE_TLV("IN2 Boost", RT5645_IN2_CTRL,
 		RT5645_BST_SFT2, 8, 0, bst_tlv),
 
diff --git a/sound/soc/codecs/rt5659.c b/sound/soc/codecs/rt5659.c
index 820d8fa..fb8ea05 100644
--- a/sound/soc/codecs/rt5659.c
+++ b/sound/soc/codecs/rt5659.c
@@ -3985,7 +3985,6 @@
 	if (rt5659 == NULL)
 		return -ENOMEM;
 
-	rt5659->i2c = i2c;
 	i2c_set_clientdata(i2c, rt5659);
 
 	if (pdata)
@@ -4157,24 +4156,17 @@
 
 	INIT_DELAYED_WORK(&rt5659->jack_detect_work, rt5659_jack_detect_work);
 
-	if (rt5659->i2c->irq) {
-		ret = request_threaded_irq(rt5659->i2c->irq, NULL, rt5659_irq,
-			IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING
+	if (i2c->irq) {
+		ret = devm_request_threaded_irq(&i2c->dev, i2c->irq, NULL,
+			rt5659_irq, IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING
 			| IRQF_ONESHOT, "rt5659", rt5659);
 		if (ret)
 			dev_err(&i2c->dev, "Failed to reguest IRQ: %d\n", ret);
 
 	}
 
-	ret = snd_soc_register_codec(&i2c->dev, &soc_codec_dev_rt5659,
+	return snd_soc_register_codec(&i2c->dev, &soc_codec_dev_rt5659,
 			rt5659_dai, ARRAY_SIZE(rt5659_dai));
-
-	if (ret) {
-		if (rt5659->i2c->irq)
-			free_irq(rt5659->i2c->irq, rt5659);
-	}
-
-	return 0;
 }
 
 static int rt5659_i2c_remove(struct i2c_client *i2c)
@@ -4191,24 +4183,29 @@
 	regmap_write(rt5659->regmap, RT5659_RESET, 0);
 }
 
+#ifdef CONFIG_OF
 static const struct of_device_id rt5659_of_match[] = {
 	{ .compatible = "realtek,rt5658", },
 	{ .compatible = "realtek,rt5659", },
-	{},
+	{ },
 };
+MODULE_DEVICE_TABLE(of, rt5659_of_match);
+#endif
 
+#ifdef CONFIG_ACPI
 static struct acpi_device_id rt5659_acpi_match[] = {
-		{ "10EC5658", 0},
-		{ "10EC5659", 0},
-		{ },
+	{ "10EC5658", 0, },
+	{ "10EC5659", 0, },
+	{ },
 };
 MODULE_DEVICE_TABLE(acpi, rt5659_acpi_match);
+#endif
 
 struct i2c_driver rt5659_i2c_driver = {
 	.driver = {
 		.name = "rt5659",
 		.owner = THIS_MODULE,
-		.of_match_table = rt5659_of_match,
+		.of_match_table = of_match_ptr(rt5659_of_match),
 		.acpi_match_table = ACPI_PTR(rt5659_acpi_match),
 	},
 	.probe = rt5659_i2c_probe,
diff --git a/sound/soc/codecs/rt5659.h b/sound/soc/codecs/rt5659.h
index 8f07ee9..d31c9e5 100644
--- a/sound/soc/codecs/rt5659.h
+++ b/sound/soc/codecs/rt5659.h
@@ -1792,7 +1792,6 @@
 	struct snd_soc_codec *codec;
 	struct rt5659_platform_data pdata;
 	struct regmap *regmap;
-	struct i2c_client *i2c;
 	struct gpio_desc *gpiod_ldo1_en;
 	struct gpio_desc *gpiod_reset;
 	struct snd_soc_jack *hs_jack;
diff --git a/sound/soc/codecs/sigmadsp-i2c.c b/sound/soc/codecs/sigmadsp-i2c.c
index 21ca3a5..d374c18 100644
--- a/sound/soc/codecs/sigmadsp-i2c.c
+++ b/sound/soc/codecs/sigmadsp-i2c.c
@@ -31,7 +31,10 @@
 
 	kfree(buf);
 
-	return ret;
+	if (ret < 0)
+		return ret;
+
+	return 0;
 }
 
 static int sigmadsp_read_i2c(void *control_data,
diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c
index 6088d30..97c0f1e 100644
--- a/sound/soc/codecs/wm5110.c
+++ b/sound/soc/codecs/wm5110.c
@@ -2382,6 +2382,7 @@
 
 static int wm5110_remove(struct platform_device *pdev)
 {
+	snd_soc_unregister_platform(&pdev->dev);
 	snd_soc_unregister_codec(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c
index ff23772..d7f444f 100644
--- a/sound/soc/codecs/wm8960.c
+++ b/sound/soc/codecs/wm8960.c
@@ -240,13 +240,13 @@
 SOC_DOUBLE_R("Capture Switch", WM8960_LINVOL, WM8960_RINVOL,
 	7, 1, 1),
 
-SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT3 Volume",
-	       WM8960_INBMIX1, 4, 7, 0, lineinboost_tlv),
-SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT2 Volume",
-	       WM8960_INBMIX1, 1, 7, 0, lineinboost_tlv),
 SOC_SINGLE_TLV("Left Input Boost Mixer LINPUT3 Volume",
-	       WM8960_INBMIX2, 4, 7, 0, lineinboost_tlv),
+	       WM8960_INBMIX1, 4, 7, 0, lineinboost_tlv),
 SOC_SINGLE_TLV("Left Input Boost Mixer LINPUT2 Volume",
+	       WM8960_INBMIX1, 1, 7, 0, lineinboost_tlv),
+SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT3 Volume",
+	       WM8960_INBMIX2, 4, 7, 0, lineinboost_tlv),
+SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT2 Volume",
 	       WM8960_INBMIX2, 1, 7, 0, lineinboost_tlv),
 SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT1 Volume",
 		WM8960_RINPATH, 4, 3, 0, micboost_tlv),
@@ -643,29 +643,31 @@
 		return -EINVAL;
 	}
 
-	/* check if the sysclk frequency is available. */
-	for (i = 0; i < ARRAY_SIZE(sysclk_divs); ++i) {
-		if (sysclk_divs[i] == -1)
-			continue;
-		sysclk = freq_out / sysclk_divs[i];
-		for (j = 0; j < ARRAY_SIZE(dac_divs); ++j) {
-			if (sysclk == dac_divs[j] * lrclk) {
+	if (wm8960->clk_id != WM8960_SYSCLK_PLL) {
+		/* check if the sysclk frequency is available. */
+		for (i = 0; i < ARRAY_SIZE(sysclk_divs); ++i) {
+			if (sysclk_divs[i] == -1)
+				continue;
+			sysclk = freq_out / sysclk_divs[i];
+			for (j = 0; j < ARRAY_SIZE(dac_divs); ++j) {
+				if (sysclk != dac_divs[j] * lrclk)
+					continue;
 				for (k = 0; k < ARRAY_SIZE(bclk_divs); ++k)
 					if (sysclk == bclk * bclk_divs[k] / 10)
 						break;
 				if (k != ARRAY_SIZE(bclk_divs))
 					break;
 			}
+			if (j != ARRAY_SIZE(dac_divs))
+				break;
 		}
-		if (j != ARRAY_SIZE(dac_divs))
-			break;
-	}
 
-	if (i != ARRAY_SIZE(sysclk_divs)) {
-		goto configure_clock;
-	} else if (wm8960->clk_id != WM8960_SYSCLK_AUTO) {
-		dev_err(codec->dev, "failed to configure clock\n");
-		return -EINVAL;
+		if (i != ARRAY_SIZE(sysclk_divs)) {
+			goto configure_clock;
+		} else if (wm8960->clk_id != WM8960_SYSCLK_AUTO) {
+			dev_err(codec->dev, "failed to configure clock\n");
+			return -EINVAL;
+		}
 	}
 	/* get a available pll out frequency and set pll */
 	for (i = 0; i < ARRAY_SIZE(sysclk_divs); ++i) {
diff --git a/sound/soc/dwc/designware_i2s.c b/sound/soc/dwc/designware_i2s.c
index ce664c2..bff258d 100644
--- a/sound/soc/dwc/designware_i2s.c
+++ b/sound/soc/dwc/designware_i2s.c
@@ -645,6 +645,8 @@
 
 	dev->dev = &pdev->dev;
 
+	dev->i2s_reg_comp1 = I2S_COMP_PARAM_1;
+	dev->i2s_reg_comp2 = I2S_COMP_PARAM_2;
 	if (pdata) {
 		dev->capability = pdata->cap;
 		clk_id = NULL;
@@ -652,9 +654,6 @@
 		if (dev->quirks & DW_I2S_QUIRK_COMP_REG_OFFSET) {
 			dev->i2s_reg_comp1 = pdata->i2s_reg_comp1;
 			dev->i2s_reg_comp2 = pdata->i2s_reg_comp2;
-		} else {
-			dev->i2s_reg_comp1 = I2S_COMP_PARAM_1;
-			dev->i2s_reg_comp2 = I2S_COMP_PARAM_2;
 		}
 		ret = dw_configure_dai_by_pd(dev, dw_i2s_dai, res, pdata);
 	} else {
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index 40dfd8a..ed8de10 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -112,20 +112,6 @@
 	struct fsl_ssi_reg_val tx;
 };
 
-static const struct reg_default fsl_ssi_reg_defaults[] = {
-	{CCSR_SSI_SCR,     0x00000000},
-	{CCSR_SSI_SIER,    0x00003003},
-	{CCSR_SSI_STCR,    0x00000200},
-	{CCSR_SSI_SRCR,    0x00000200},
-	{CCSR_SSI_STCCR,   0x00040000},
-	{CCSR_SSI_SRCCR,   0x00040000},
-	{CCSR_SSI_SACNT,   0x00000000},
-	{CCSR_SSI_STMSK,   0x00000000},
-	{CCSR_SSI_SRMSK,   0x00000000},
-	{CCSR_SSI_SACCEN,  0x00000000},
-	{CCSR_SSI_SACCDIS, 0x00000000},
-};
-
 static bool fsl_ssi_readable_reg(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
@@ -190,8 +176,7 @@
 	.val_bits = 32,
 	.reg_stride = 4,
 	.val_format_endian = REGMAP_ENDIAN_NATIVE,
-	.reg_defaults = fsl_ssi_reg_defaults,
-	.num_reg_defaults = ARRAY_SIZE(fsl_ssi_reg_defaults),
+	.num_reg_defaults_raw = CCSR_SSI_SACCDIS / sizeof(uint32_t) + 1,
 	.readable_reg = fsl_ssi_readable_reg,
 	.volatile_reg = fsl_ssi_volatile_reg,
 	.precious_reg = fsl_ssi_precious_reg,
@@ -201,6 +186,7 @@
 
 struct fsl_ssi_soc_data {
 	bool imx;
+	bool imx21regs; /* imx21-class SSI - no SACC{ST,EN,DIS} regs */
 	bool offline_config;
 	u32 sisr_write_mask;
 };
@@ -303,6 +289,7 @@
 
 static struct fsl_ssi_soc_data fsl_ssi_imx21 = {
 	.imx = true,
+	.imx21regs = true,
 	.offline_config = true,
 	.sisr_write_mask = 0,
 };
@@ -586,8 +573,12 @@
 	 */
 	regmap_write(regs, CCSR_SSI_SACNT,
 			CCSR_SSI_SACNT_AC97EN | CCSR_SSI_SACNT_FV);
-	regmap_write(regs, CCSR_SSI_SACCDIS, 0xff);
-	regmap_write(regs, CCSR_SSI_SACCEN, 0x300);
+
+	/* no SACC{ST,EN,DIS} regs on imx21-class SSI */
+	if (!ssi_private->soc->imx21regs) {
+		regmap_write(regs, CCSR_SSI_SACCDIS, 0xff);
+		regmap_write(regs, CCSR_SSI_SACCEN, 0x300);
+	}
 
 	/*
 	 * Enable SSI, Transmit and Receive. AC97 has to communicate with the
@@ -1397,6 +1388,7 @@
 	struct resource *res;
 	void __iomem *iomem;
 	char name[64];
+	struct regmap_config regconfig = fsl_ssi_regconfig;
 
 	of_id = of_match_device(fsl_ssi_ids, &pdev->dev);
 	if (!of_id || !of_id->data)
@@ -1444,15 +1436,25 @@
 		return PTR_ERR(iomem);
 	ssi_private->ssi_phys = res->start;
 
+	if (ssi_private->soc->imx21regs) {
+		/*
+		 * According to datasheet imx21-class SSI
+		 * don't have SACC{ST,EN,DIS} regs.
+		 */
+		regconfig.max_register = CCSR_SSI_SRMSK;
+		regconfig.num_reg_defaults_raw =
+			CCSR_SSI_SRMSK / sizeof(uint32_t) + 1;
+	}
+
 	ret = of_property_match_string(np, "clock-names", "ipg");
 	if (ret < 0) {
 		ssi_private->has_ipg_clk_name = false;
 		ssi_private->regs = devm_regmap_init_mmio(&pdev->dev, iomem,
-			&fsl_ssi_regconfig);
+			&regconfig);
 	} else {
 		ssi_private->has_ipg_clk_name = true;
 		ssi_private->regs = devm_regmap_init_mmio_clk(&pdev->dev,
-			"ipg", iomem, &fsl_ssi_regconfig);
+			"ipg", iomem, &regconfig);
 	}
 	if (IS_ERR(ssi_private->regs)) {
 		dev_err(&pdev->dev, "Failed to init register map\n");
diff --git a/sound/soc/fsl/imx-spdif.c b/sound/soc/fsl/imx-spdif.c
index a407e83..fb896b2 100644
--- a/sound/soc/fsl/imx-spdif.c
+++ b/sound/soc/fsl/imx-spdif.c
@@ -72,8 +72,6 @@
 		goto end;
 	}
 
-	platform_set_drvdata(pdev, data);
-
 end:
 	of_node_put(spdif_np);
 
diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index 1ded881..2389ab4 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -99,7 +99,7 @@
 		if (ret && ret != -ENOTSUPP)
 			goto err;
 	}
-
+	return 0;
 err:
 	return ret;
 }
diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig
index 803f95e..7d7c872 100644
--- a/sound/soc/intel/Kconfig
+++ b/sound/soc/intel/Kconfig
@@ -30,11 +30,15 @@
 config SND_SOC_INTEL_SST
 	tristate
 	select SND_SOC_INTEL_SST_ACPI if ACPI
+	select SND_SOC_INTEL_SST_MATCH if ACPI
 	depends on (X86 || COMPILE_TEST)
 
 config SND_SOC_INTEL_SST_ACPI
 	tristate
 
+config SND_SOC_INTEL_SST_MATCH
+	tristate
+
 config SND_SOC_INTEL_HASWELL
 	tristate
 
@@ -57,7 +61,7 @@
 config SND_SOC_INTEL_BYT_RT5640_MACH
 	tristate "ASoC Audio driver for Intel Baytrail with RT5640 codec"
 	depends on X86_INTEL_LPSS && I2C
-	depends on DW_DMAC_CORE=y && (SND_SOC_INTEL_BYTCR_RT5640_MACH = n)
+	depends on DW_DMAC_CORE=y && (SND_SST_IPC_ACPI = n)
 	select SND_SOC_INTEL_SST
 	select SND_SOC_INTEL_BAYTRAIL
 	select SND_SOC_RT5640
@@ -69,7 +73,7 @@
 config SND_SOC_INTEL_BYT_MAX98090_MACH
 	tristate "ASoC Audio driver for Intel Baytrail with MAX98090 codec"
 	depends on X86_INTEL_LPSS && I2C
-	depends on DW_DMAC_CORE=y
+	depends on DW_DMAC_CORE=y && (SND_SST_IPC_ACPI = n)
 	select SND_SOC_INTEL_SST
 	select SND_SOC_INTEL_BAYTRAIL
 	select SND_SOC_MAX98090
@@ -97,6 +101,7 @@
 	select SND_SOC_RT5640
 	select SND_SST_MFLD_PLATFORM
 	select SND_SST_IPC_ACPI
+	select SND_SOC_INTEL_SST_MATCH if ACPI
 	help
           This adds support for ASoC machine driver for Intel(R) Baytrail and Baytrail-CR
           platforms with RT5640 audio codec.
@@ -109,6 +114,7 @@
 	select SND_SOC_RT5651
 	select SND_SST_MFLD_PLATFORM
 	select SND_SST_IPC_ACPI
+	select SND_SOC_INTEL_SST_MATCH if ACPI
 	help
           This adds support for ASoC machine driver for Intel(R) Baytrail and Baytrail-CR
           platforms with RT5651 audio codec.
@@ -121,6 +127,7 @@
         select SND_SOC_RT5670
         select SND_SST_MFLD_PLATFORM
         select SND_SST_IPC_ACPI
+	select SND_SOC_INTEL_SST_MATCH if ACPI
         help
           This adds support for ASoC machine driver for Intel(R) Cherrytrail & Braswell
           platforms with RT5672 audio codec.
@@ -133,6 +140,7 @@
 	select SND_SOC_RT5645
 	select SND_SST_MFLD_PLATFORM
 	select SND_SST_IPC_ACPI
+	select SND_SOC_INTEL_SST_MATCH if ACPI
 	help
 	  This adds support for ASoC machine driver for Intel(R) Cherrytrail & Braswell
 	  platforms with RT5645/5650 audio codec.
@@ -145,6 +153,7 @@
 	select SND_SOC_TS3A227E
 	select SND_SST_MFLD_PLATFORM
 	select SND_SST_IPC_ACPI
+	select SND_SOC_INTEL_SST_MATCH if ACPI
 	help
       This adds support for ASoC machine driver for Intel(R) Cherrytrail & Braswell
       platforms with MAX98090 audio codec it also can support TI jack chip as aux device.
diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
index 55c33dc7..52ed434 100644
--- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c
+++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
@@ -528,6 +528,7 @@
 	.ops = &sst_compr_dai_ops,
 	.playback = {
 		.stream_name = "Compress Playback",
+		.channels_min = 1,
 	},
 },
 /* BE CPU  Dais */
diff --git a/sound/soc/intel/boards/skl_rt286.c b/sound/soc/intel/boards/skl_rt286.c
index 7396ddb..2cbcbe4 100644
--- a/sound/soc/intel/boards/skl_rt286.c
+++ b/sound/soc/intel/boards/skl_rt286.c
@@ -212,7 +212,10 @@
 {
 	struct snd_interval *channels = hw_param_interval(params,
 						SNDRV_PCM_HW_PARAM_CHANNELS);
-	channels->min = channels->max = 4;
+	if (params_channels(params) == 2)
+		channels->min = channels->max = 2;
+	else
+		channels->min = channels->max = 4;
 
 	return 0;
 }
diff --git a/sound/soc/intel/common/Makefile b/sound/soc/intel/common/Makefile
index 668fdee..fbbb25c 100644
--- a/sound/soc/intel/common/Makefile
+++ b/sound/soc/intel/common/Makefile
@@ -1,13 +1,10 @@
 snd-soc-sst-dsp-objs := sst-dsp.o
-ifneq ($(CONFIG_SND_SST_IPC_ACPI),)
-snd-soc-sst-acpi-objs := sst-match-acpi.o
-else
-snd-soc-sst-acpi-objs := sst-acpi.o sst-match-acpi.o
-endif
-
+snd-soc-sst-acpi-objs := sst-acpi.o
+snd-soc-sst-match-objs := sst-match-acpi.o
 snd-soc-sst-ipc-objs := sst-ipc.o
 
 snd-soc-sst-dsp-$(CONFIG_DW_DMAC_CORE) += sst-firmware.o
 
 obj-$(CONFIG_SND_SOC_INTEL_SST) += snd-soc-sst-dsp.o snd-soc-sst-ipc.o
 obj-$(CONFIG_SND_SOC_INTEL_SST_ACPI) += snd-soc-sst-acpi.o
+obj-$(CONFIG_SND_SOC_INTEL_SST_MATCH) += snd-soc-sst-match.o
diff --git a/sound/soc/intel/common/sst-acpi.c b/sound/soc/intel/common/sst-acpi.c
index 7a85c57..2c5eda1 100644
--- a/sound/soc/intel/common/sst-acpi.c
+++ b/sound/soc/intel/common/sst-acpi.c
@@ -215,6 +215,7 @@
 	.dma_size = SST_LPT_DSP_DMA_SIZE,
 };
 
+#if !IS_ENABLED(CONFIG_SND_SST_IPC_ACPI)
 static struct sst_acpi_mach baytrail_machines[] = {
 	{ "10EC5640", "byt-rt5640", "intel/fw_sst_0f28.bin-48kHz_i2s_master", NULL, NULL, NULL },
 	{ "193C9890", "byt-max98090", "intel/fw_sst_0f28.bin-48kHz_i2s_master", NULL, NULL, NULL },
@@ -231,11 +232,14 @@
 	.sst_id = SST_DEV_ID_BYT,
 	.resindex_dma_base = -1,
 };
+#endif
 
 static const struct acpi_device_id sst_acpi_match[] = {
 	{ "INT33C8", (unsigned long)&sst_acpi_haswell_desc },
 	{ "INT3438", (unsigned long)&sst_acpi_broadwell_desc },
+#if !IS_ENABLED(CONFIG_SND_SST_IPC_ACPI)
 	{ "80860F28", (unsigned long)&sst_acpi_baytrail_desc },
+#endif
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, sst_acpi_match);
diff --git a/sound/soc/intel/common/sst-match-acpi.c b/sound/soc/intel/common/sst-match-acpi.c
index dd077e1..3b4539d 100644
--- a/sound/soc/intel/common/sst-match-acpi.c
+++ b/sound/soc/intel/common/sst-match-acpi.c
@@ -41,3 +41,6 @@
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(sst_acpi_find_machine);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Intel Common ACPI Match module");
diff --git a/sound/soc/intel/skylake/skl-messages.c b/sound/soc/intel/skylake/skl-messages.c
index de6dac4..4629372 100644
--- a/sound/soc/intel/skylake/skl-messages.c
+++ b/sound/soc/intel/skylake/skl-messages.c
@@ -688,14 +688,14 @@
 	/* get src queue index */
 	src_index = skl_get_queue_index(src_mcfg->m_out_pin, dst_id, out_max);
 	if (src_index < 0)
-		return -EINVAL;
+		return 0;
 
 	msg.src_queue = src_index;
 
 	/* get dst queue index */
 	dst_index  = skl_get_queue_index(dst_mcfg->m_in_pin, src_id, in_max);
 	if (dst_index < 0)
-		return -EINVAL;
+		return 0;
 
 	msg.dst_queue = dst_index;
 
@@ -747,7 +747,7 @@
 
 	skl_dump_bind_info(ctx, src_mcfg, dst_mcfg);
 
-	if (src_mcfg->m_state < SKL_MODULE_INIT_DONE &&
+	if (src_mcfg->m_state < SKL_MODULE_INIT_DONE ||
 		dst_mcfg->m_state < SKL_MODULE_INIT_DONE)
 		return 0;
 
diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c
index f355325..b6e6b61 100644
--- a/sound/soc/intel/skylake/skl-pcm.c
+++ b/sound/soc/intel/skylake/skl-pcm.c
@@ -863,6 +863,7 @@
 		else
 			delay += hstream->bufsize;
 	}
+	delay = (hstream->bufsize == delay) ? 0 : delay;
 
 	if (delay >= hstream->period_bytes) {
 		dev_info(bus->dev,
diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c
index 4624556..a294fee 100644
--- a/sound/soc/intel/skylake/skl-topology.c
+++ b/sound/soc/intel/skylake/skl-topology.c
@@ -54,12 +54,9 @@
 
 /*
  * Each pipelines needs memory to be allocated. Check if we have free memory
- * from available pool. Then only add this to pool
- * This is freed when pipe is deleted
- * Note: DSP does actual memory management we only keep track for complete
- * pool
+ * from available pool.
  */
-static bool skl_tplg_alloc_pipe_mem(struct skl *skl,
+static bool skl_is_pipe_mem_avail(struct skl *skl,
 				struct skl_module_cfg *mconfig)
 {
 	struct skl_sst *ctx = skl->skl_sst;
@@ -74,10 +71,20 @@
 				"exceeds ppl memory available %d mem %d\n",
 				skl->resource.max_mem, skl->resource.mem);
 		return false;
+	} else {
+		return true;
 	}
+}
 
+/*
+ * Add the mem to the mem pool. This is freed when pipe is deleted.
+ * Note: DSP does actual memory management we only keep track for complete
+ * pool
+ */
+static void skl_tplg_alloc_pipe_mem(struct skl *skl,
+				struct skl_module_cfg *mconfig)
+{
 	skl->resource.mem += mconfig->pipe->memory_pages;
-	return true;
 }
 
 /*
@@ -85,10 +92,10 @@
  * quantified in MCPS (Million Clocks Per Second) required for module/pipe
  *
  * Each pipelines needs mcps to be allocated. Check if we have mcps for this
- * pipe. This adds the mcps to driver counter
- * This is removed on pipeline delete
+ * pipe.
  */
-static bool skl_tplg_alloc_pipe_mcps(struct skl *skl,
+
+static bool skl_is_pipe_mcps_avail(struct skl *skl,
 				struct skl_module_cfg *mconfig)
 {
 	struct skl_sst *ctx = skl->skl_sst;
@@ -98,13 +105,18 @@
 			"%s: module_id %d instance %d\n", __func__,
 			mconfig->id.module_id, mconfig->id.instance_id);
 		dev_err(ctx->dev,
-			"exceeds ppl memory available %d > mem %d\n",
+			"exceeds ppl mcps available %d > mem %d\n",
 			skl->resource.max_mcps, skl->resource.mcps);
 		return false;
+	} else {
+		return true;
 	}
+}
 
+static void skl_tplg_alloc_pipe_mcps(struct skl *skl,
+				struct skl_module_cfg *mconfig)
+{
 	skl->resource.mcps += mconfig->mcps;
-	return true;
 }
 
 /*
@@ -411,7 +423,7 @@
 		mconfig = w->priv;
 
 		/* check resource available */
-		if (!skl_tplg_alloc_pipe_mcps(skl, mconfig))
+		if (!skl_is_pipe_mcps_avail(skl, mconfig))
 			return -ENOMEM;
 
 		if (mconfig->is_loadable && ctx->dsp->fw_ops.load_mod) {
@@ -435,6 +447,7 @@
 		ret = skl_tplg_set_module_params(w, ctx);
 		if (ret < 0)
 			return ret;
+		skl_tplg_alloc_pipe_mcps(skl, mconfig);
 	}
 
 	return 0;
@@ -477,10 +490,10 @@
 	struct skl_sst *ctx = skl->skl_sst;
 
 	/* check resource available */
-	if (!skl_tplg_alloc_pipe_mcps(skl, mconfig))
+	if (!skl_is_pipe_mcps_avail(skl, mconfig))
 		return -EBUSY;
 
-	if (!skl_tplg_alloc_pipe_mem(skl, mconfig))
+	if (!skl_is_pipe_mem_avail(skl, mconfig))
 		return -ENOMEM;
 
 	/*
@@ -526,11 +539,15 @@
 		src_module = dst_module;
 	}
 
+	skl_tplg_alloc_pipe_mem(skl, mconfig);
+	skl_tplg_alloc_pipe_mcps(skl, mconfig);
+
 	return 0;
 }
 
 static int skl_tplg_bind_sinks(struct snd_soc_dapm_widget *w,
 				struct skl *skl,
+				struct snd_soc_dapm_widget *src_w,
 				struct skl_module_cfg *src_mconfig)
 {
 	struct snd_soc_dapm_path *p;
@@ -547,6 +564,10 @@
 		dev_dbg(ctx->dev, "%s: sink widget=%s\n", __func__, p->sink->name);
 
 		next_sink = p->sink;
+
+		if (!is_skl_dsp_widget_type(p->sink))
+			return skl_tplg_bind_sinks(p->sink, skl, src_w, src_mconfig);
+
 		/*
 		 * here we will check widgets in sink pipelines, so that
 		 * can be any widgets type and we are only interested if
@@ -576,7 +597,7 @@
 	}
 
 	if (!sink)
-		return skl_tplg_bind_sinks(next_sink, skl, src_mconfig);
+		return skl_tplg_bind_sinks(next_sink, skl, src_w, src_mconfig);
 
 	return 0;
 }
@@ -605,7 +626,7 @@
 	 * if sink is not started, start sink pipe first, then start
 	 * this pipe
 	 */
-	ret = skl_tplg_bind_sinks(w, skl, src_mconfig);
+	ret = skl_tplg_bind_sinks(w, skl, w, src_mconfig);
 	if (ret)
 		return ret;
 
@@ -773,10 +794,7 @@
 			continue;
 		}
 
-		ret = skl_unbind_modules(ctx, src_module, dst_module);
-		if (ret < 0)
-			return ret;
-
+		skl_unbind_modules(ctx, src_module, dst_module);
 		src_module = dst_module;
 	}
 
@@ -814,9 +832,6 @@
 			 * This is a connecter and if path is found that means
 			 * unbind between source and sink has not happened yet
 			 */
-			ret = skl_stop_pipe(ctx, sink_mconfig->pipe);
-			if (ret < 0)
-				return ret;
 			ret = skl_unbind_modules(ctx, src_mconfig,
 							sink_mconfig);
 		}
@@ -842,6 +857,12 @@
 	case SND_SOC_DAPM_PRE_PMU:
 		return skl_tplg_mixer_dapm_pre_pmu_event(w, skl);
 
+	case SND_SOC_DAPM_POST_PMU:
+		return skl_tplg_mixer_dapm_post_pmu_event(w, skl);
+
+	case SND_SOC_DAPM_PRE_PMD:
+		return skl_tplg_mixer_dapm_pre_pmd_event(w, skl);
+
 	case SND_SOC_DAPM_POST_PMD:
 		return skl_tplg_mixer_dapm_post_pmd_event(w, skl);
 	}
@@ -916,6 +937,13 @@
 		skl_get_module_params(skl->skl_sst, (u32 *)bc->params,
 				      bc->max, bc->param_id, mconfig);
 
+	/* decrement size for TLV header */
+	size -= 2 * sizeof(u32);
+
+	/* check size as we don't want to send kernel data */
+	if (size > bc->max)
+		size = bc->max;
+
 	if (bc->params) {
 		if (copy_to_user(data, &bc->param_id, sizeof(u32)))
 			return -EFAULT;
@@ -1510,6 +1538,7 @@
 					&skl_tplg_ops, fw, 0);
 	if (ret < 0) {
 		dev_err(bus->dev, "tplg component load failed%d\n", ret);
+		release_firmware(fw);
 		return -EINVAL;
 	}
 
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index 443a15d..092705e 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -614,8 +614,6 @@
 		goto out_unregister;
 
 	/*configure PM */
-	pm_runtime_set_autosuspend_delay(bus->dev, SKL_SUSPEND_DELAY);
-	pm_runtime_use_autosuspend(bus->dev);
 	pm_runtime_put_noidle(bus->dev);
 	pm_runtime_allow(bus->dev);
 
diff --git a/sound/soc/mediatek/Kconfig b/sound/soc/mediatek/Kconfig
index 15c04e2..9769676 100644
--- a/sound/soc/mediatek/Kconfig
+++ b/sound/soc/mediatek/Kconfig
@@ -9,7 +9,7 @@
 
 config SND_SOC_MT8173_MAX98090
 	tristate "ASoC Audio driver for MT8173 with MAX98090 codec"
-	depends on SND_SOC_MEDIATEK
+	depends on SND_SOC_MEDIATEK && I2C
 	select SND_SOC_MAX98090
 	help
 	  This adds ASoC driver for Mediatek MT8173 boards
@@ -19,7 +19,7 @@
 
 config SND_SOC_MT8173_RT5650_RT5676
 	tristate "ASoC Audio driver for MT8173 with RT5650 RT5676 codecs"
-	depends on SND_SOC_MEDIATEK
+	depends on SND_SOC_MEDIATEK && I2C
 	select SND_SOC_RT5645
 	select SND_SOC_RT5677
 	help
diff --git a/sound/soc/mxs/mxs-saif.c b/sound/soc/mxs/mxs-saif.c
index c866ade..a6c7b8d 100644
--- a/sound/soc/mxs/mxs-saif.c
+++ b/sound/soc/mxs/mxs-saif.c
@@ -381,9 +381,19 @@
 	__raw_writel(BM_SAIF_CTRL_CLKGATE,
 		saif->base + SAIF_CTRL + MXS_CLR_ADDR);
 
+	clk_prepare(saif->clk);
+
 	return 0;
 }
 
+static void mxs_saif_shutdown(struct snd_pcm_substream *substream,
+			      struct snd_soc_dai *cpu_dai)
+{
+	struct mxs_saif *saif = snd_soc_dai_get_drvdata(cpu_dai);
+
+	clk_unprepare(saif->clk);
+}
+
 /*
  * Should only be called when port is inactive.
  * although can be called multiple times by upper layers.
@@ -424,8 +434,6 @@
 		return ret;
 	}
 
-	/* prepare clk in hw_param, enable in trigger */
-	clk_prepare(saif->clk);
 	if (saif != master_saif) {
 		/*
 		* Set an initial clock rate for the saif internal logic to work
@@ -611,6 +619,7 @@
 
 static const struct snd_soc_dai_ops mxs_saif_dai_ops = {
 	.startup = mxs_saif_startup,
+	.shutdown = mxs_saif_shutdown,
 	.trigger = mxs_saif_trigger,
 	.prepare = mxs_saif_prepare,
 	.hw_params = mxs_saif_hw_params,
diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c
index 79688aa..4aeb8e1 100644
--- a/sound/soc/qcom/lpass-platform.c
+++ b/sound/soc/qcom/lpass-platform.c
@@ -440,18 +440,18 @@
 }
 
 static int lpass_platform_alloc_buffer(struct snd_pcm_substream *substream,
-		struct snd_soc_pcm_runtime *soc_runtime)
+		struct snd_soc_pcm_runtime *rt)
 {
 	struct snd_dma_buffer *buf = &substream->dma_buffer;
 	size_t size = lpass_platform_pcm_hardware.buffer_bytes_max;
 
 	buf->dev.type = SNDRV_DMA_TYPE_DEV;
-	buf->dev.dev = soc_runtime->dev;
+	buf->dev.dev = rt->platform->dev;
 	buf->private_data = NULL;
-	buf->area = dma_alloc_coherent(soc_runtime->dev, size, &buf->addr,
+	buf->area = dma_alloc_coherent(rt->platform->dev, size, &buf->addr,
 			GFP_KERNEL);
 	if (!buf->area) {
-		dev_err(soc_runtime->dev, "%s: Could not allocate DMA buffer\n",
+		dev_err(rt->platform->dev, "%s: Could not allocate DMA buffer\n",
 				__func__);
 		return -ENOMEM;
 	}
@@ -461,12 +461,12 @@
 }
 
 static void lpass_platform_free_buffer(struct snd_pcm_substream *substream,
-		struct snd_soc_pcm_runtime *soc_runtime)
+		struct snd_soc_pcm_runtime *rt)
 {
 	struct snd_dma_buffer *buf = &substream->dma_buffer;
 
 	if (buf->area) {
-		dma_free_coherent(soc_runtime->dev, buf->bytes, buf->area,
+		dma_free_coherent(rt->dev, buf->bytes, buf->area,
 				buf->addr);
 	}
 	buf->area = NULL;
@@ -499,9 +499,6 @@
 
 	snd_soc_pcm_set_drvdata(soc_runtime, data);
 
-	soc_runtime->dev->coherent_dma_mask = DMA_BIT_MASK(32);
-	soc_runtime->dev->dma_mask = &soc_runtime->dev->coherent_dma_mask;
-
 	ret = lpass_platform_alloc_buffer(substream, soc_runtime);
 	if (ret)
 		return ret;
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 5a2812f..0d37079 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -310,7 +310,7 @@
 };
 
 static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget,
-	struct snd_kcontrol *kcontrol)
+	struct snd_kcontrol *kcontrol, const char *ctrl_name)
 {
 	struct dapm_kcontrol_data *data;
 	struct soc_mixer_control *mc;
@@ -333,7 +333,7 @@
 		if (mc->autodisable) {
 			struct snd_soc_dapm_widget template;
 
-			name = kasprintf(GFP_KERNEL, "%s %s", kcontrol->id.name,
+			name = kasprintf(GFP_KERNEL, "%s %s", ctrl_name,
 					 "Autodisable");
 			if (!name) {
 				ret = -ENOMEM;
@@ -371,7 +371,7 @@
 		if (e->autodisable) {
 			struct snd_soc_dapm_widget template;
 
-			name = kasprintf(GFP_KERNEL, "%s %s", kcontrol->id.name,
+			name = kasprintf(GFP_KERNEL, "%s %s", ctrl_name,
 					 "Autodisable");
 			if (!name) {
 				ret = -ENOMEM;
@@ -871,7 +871,7 @@
 
 		kcontrol->private_free = dapm_kcontrol_free;
 
-		ret = dapm_kcontrol_data_alloc(w, kcontrol);
+		ret = dapm_kcontrol_data_alloc(w, kcontrol, name);
 		if (ret) {
 			snd_ctl_free_one(kcontrol);
 			goto exit_free;
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index e898b42..1af4f23 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1810,7 +1810,8 @@
 		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_PREPARE) &&
 		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_HW_FREE) &&
 		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_PAUSED) &&
-		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP))
+		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP) &&
+		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_SUSPEND))
 			continue;
 
 		dev_dbg(be->dev, "ASoC: hw_free BE %s\n",
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index cc39f63..007cf58 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -2455,7 +2455,6 @@
 	else
 		err = snd_usbmidi_create_endpoints(umidi, endpoints);
 	if (err < 0) {
-		snd_usbmidi_free(umidi);
 		return err;
 	}
 
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 81a2eb7..05d8158 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2068,6 +2068,15 @@
 		err = -ENOMEM;
 		goto err_free_queues;
 	}
+
+	/*
+	 * Since this thread will not be kept in any rbtree not in a
+	 * list, initialize its list node so that at thread__put() the
+	 * current thread lifetime assuption is kept and we don't segfault
+	 * at list_del_init().
+	 */
+	INIT_LIST_HEAD(&pt->unknown_thread->node);
+
 	err = thread__set_comm(pt->unknown_thread, "unknown", 0);
 	if (err)
 		goto err_delete_thread;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 4f7b0ef..813d9b2 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -399,6 +399,9 @@
 {
 	char help[BUFSIZ];
 
+	if (!e)
+		return;
+
 	/*
 	 * We get error directly from syscall errno ( > 0),
 	 * or from encoded pointer's error ( < 0).
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 2be10fb..4ce5c5e 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -686,8 +686,9 @@
 		pf->fb_ops = NULL;
 #if _ELFUTILS_PREREQ(0, 142)
 	} else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa &&
-		   pf->cfi != NULL) {
-		if (dwarf_cfi_addrframe(pf->cfi, pf->addr, &frame) != 0 ||
+		   (pf->cfi_eh != NULL || pf->cfi_dbg != NULL)) {
+		if ((dwarf_cfi_addrframe(pf->cfi_eh, pf->addr, &frame) != 0 &&
+		     (dwarf_cfi_addrframe(pf->cfi_dbg, pf->addr, &frame) != 0)) ||
 		    dwarf_frame_cfa(frame, &pf->fb_ops, &nops) != 0) {
 			pr_warning("Failed to get call frame on 0x%jx\n",
 				   (uintmax_t)pf->addr);
@@ -1015,8 +1016,7 @@
 	return DWARF_CB_OK;
 }
 
-/* Find probe points from debuginfo */
-static int debuginfo__find_probes(struct debuginfo *dbg,
+static int debuginfo__find_probe_location(struct debuginfo *dbg,
 				  struct probe_finder *pf)
 {
 	struct perf_probe_point *pp = &pf->pev->point;
@@ -1025,27 +1025,6 @@
 	Dwarf_Die *diep;
 	int ret = 0;
 
-#if _ELFUTILS_PREREQ(0, 142)
-	Elf *elf;
-	GElf_Ehdr ehdr;
-	GElf_Shdr shdr;
-
-	/* Get the call frame information from this dwarf */
-	elf = dwarf_getelf(dbg->dbg);
-	if (elf == NULL)
-		return -EINVAL;
-
-	if (gelf_getehdr(elf, &ehdr) == NULL)
-		return -EINVAL;
-
-	if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) &&
-	    shdr.sh_type == SHT_PROGBITS) {
-		pf->cfi = dwarf_getcfi_elf(elf);
-	} else {
-		pf->cfi = dwarf_getcfi(dbg->dbg);
-	}
-#endif
-
 	off = 0;
 	pf->lcache = intlist__new(NULL);
 	if (!pf->lcache)
@@ -1108,6 +1087,39 @@
 	return ret;
 }
 
+/* Find probe points from debuginfo */
+static int debuginfo__find_probes(struct debuginfo *dbg,
+				  struct probe_finder *pf)
+{
+	int ret = 0;
+
+#if _ELFUTILS_PREREQ(0, 142)
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	GElf_Shdr shdr;
+
+	if (pf->cfi_eh || pf->cfi_dbg)
+		return debuginfo__find_probe_location(dbg, pf);
+
+	/* Get the call frame information from this dwarf */
+	elf = dwarf_getelf(dbg->dbg);
+	if (elf == NULL)
+		return -EINVAL;
+
+	if (gelf_getehdr(elf, &ehdr) == NULL)
+		return -EINVAL;
+
+	if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) &&
+	    shdr.sh_type == SHT_PROGBITS)
+		pf->cfi_eh = dwarf_getcfi_elf(elf);
+
+	pf->cfi_dbg = dwarf_getcfi(dbg->dbg);
+#endif
+
+	ret = debuginfo__find_probe_location(dbg, pf);
+	return ret;
+}
+
 struct local_vars_finder {
 	struct probe_finder *pf;
 	struct perf_probe_arg *args;
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index bed8271..0aec770 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -76,7 +76,10 @@
 
 	/* For variable searching */
 #if _ELFUTILS_PREREQ(0, 142)
-	Dwarf_CFI		*cfi;		/* Call Frame Information */
+	/* Call Frame Information from .eh_frame */
+	Dwarf_CFI		*cfi_eh;
+	/* Call Frame Information from .debug_frame */
+	Dwarf_CFI		*cfi_dbg;
 #endif
 	Dwarf_Op		*fb_ops;	/* Frame base attribute */
 	struct perf_probe_arg	*pvar;		/* Current target variable */
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 2b58edc..afb0c45 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -311,6 +311,16 @@
 
 	aggr->val = aggr->ena = aggr->run = 0;
 
+	/*
+	 * We calculate counter's data every interval,
+	 * and the display code shows ps->res_stats
+	 * avg value. We need to zero the stats for
+	 * interval mode, otherwise overall avg running
+	 * averages will be shown for each interval.
+	 */
+	if (config->interval)
+		init_stats(ps->res_stats);
+
 	if (counter->per_pkg)
 		zero_per_pkg(counter);