kernel-alx/patches-4.4/0120-4.4.21-all-fixes.patch

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 402ab99e409f..6716413c17ba 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -346,7 +346,7 @@ address           perms offset  dev   inode      pathname
 a7cb1000-a7cb2000 ---p 00000000 00:00 0
 a7cb2000-a7eb2000 rw-p 00000000 00:00 0
 a7eb2000-a7eb3000 ---p 00000000 00:00 0
-a7eb3000-a7ed5000 rw-p 00000000 00:00 0          [stack:1001]
+a7eb3000-a7ed5000 rw-p 00000000 00:00 0
 a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
 a8008000-a800a000 r--p 00133000 03:00 4222       /lib/libc.so.6
 a800a000-a800b000 rw-p 00135000 03:00 4222       /lib/libc.so.6
@@ -378,7 +378,6 @@ is not associated with a file:
 
  [heap]                   = the heap of the program
  [stack]                  = the stack of the main process
- [stack:1001]             = the stack of the thread with tid 1001
  [vdso]                   = the "virtual dynamic shared object",
                             the kernel system call handler
 
@@ -386,10 +385,8 @@ is not associated with a file:
 
 The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint
 of the individual tasks of a process. In this file you will see a mapping marked
-as [stack] if that task sees it as a stack. This is a key difference from the
-content of /proc/PID/maps, where you will see all mappings that are being used
-as stack by all of those tasks. Hence, for the example above, the task-level
-map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
+as [stack] if that task sees it as a stack. Hence, for the example above, the
+task-level map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
 
 08048000-08049000 r-xp 00000000 03:00 8312       /opt/test
 08049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
diff --git a/Makefile b/Makefile
index b74d60081a16..d1cc9e0b7473 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 20
+SUBLEVEL = 21
 EXTRAVERSION =
 NAME = Blurry Fish Butt
 
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 871f21783866..14cdc6dea493 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -391,6 +391,15 @@ config CAVIUM_ERRATUM_22375
 
 	  If unsure, say Y.
 
+config CAVIUM_ERRATUM_23144
+	bool "Cavium erratum 23144: ITS SYNC hang on dual socket system"
+	depends on NUMA
+	default y
+	help
+	  ITS SYNC command hang for cross node io and collections/cpu mapping.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_23154
 	bool "Cavium erratum 23154: Access to ICC_IAR1_EL1 is not sync'ed"
 	default y
@@ -401,6 +410,17 @@ config CAVIUM_ERRATUM_23154
 
 	  If unsure, say Y.
 
+config CAVIUM_ERRATUM_27456
+	bool "Cavium erratum 27456: Broadcast TLBI instructions may cause icache corruption"
+	default y
+	help
+	  On ThunderX T88 pass 1.x through 2.1 parts, broadcast TLBI
+	  instructions may cause the icache to become corrupted if it
+	  contains data for a non-current ASID.  The fix is to
+	  invalidate the icache when changing the mm context.
+
+	  If unsure, say Y.
+
 endmenu
 
 
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 2731d3b25ed2..8ec88e5b290f 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -103,6 +103,7 @@ static inline u64 gic_read_iar_common(void)
 	u64 irqstat;
 
 	asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat));
+	dsb(sy);
 	return irqstat;
 }
 
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 8f271b83f910..8136afc9df0d 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -30,8 +30,9 @@
 #define ARM64_HAS_LSE_ATOMICS			5
 #define ARM64_WORKAROUND_CAVIUM_23154		6
 #define ARM64_WORKAROUND_834220			7
+#define ARM64_WORKAROUND_CAVIUM_27456		8
 
-#define ARM64_NCAPS				8
+#define ARM64_NCAPS				9
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 5e6857b6bdc4..2d960f8588b0 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -107,8 +107,6 @@
 #define TCR_EL2_MASK	(TCR_EL2_TG0 | TCR_EL2_SH0 | \
 			 TCR_EL2_ORGN0 | TCR_EL2_IRGN0 | TCR_EL2_T0SZ)
 
-#define TCR_EL2_FLAGS	(TCR_EL2_RES1 | TCR_EL2_PS_40B)
-
 /* VTCR_EL2 Registers bits */
 #define VTCR_EL2_RES1		(1 << 31)
 #define VTCR_EL2_PS_MASK	(7 << 16)
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index feb6b4efa641..a3e846a28b05 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -100,6 +100,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		MIDR_RANGE(MIDR_THUNDERX, 0x00, 0x01),
 	},
 #endif
+#ifdef CONFIG_CAVIUM_ERRATUM_27456
+	{
+	/* Cavium ThunderX, T88 pass 1.x - 2.1 */
+		.desc = "Cavium erratum 27456",
+		.capability = ARM64_WORKAROUND_CAVIUM_27456,
+		MIDR_RANGE(MIDR_THUNDERX, 0x00,
+			   (1 << MIDR_VARIANT_SHIFT) | 1),
+	},
+#endif
 	{
 	}
 };
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 178ba2248a98..84c338f017b2 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -64,7 +64,7 @@ __do_hyp_init:
 	mrs	x4, tcr_el1
 	ldr	x5, =TCR_EL2_MASK
 	and	x4, x4, x5
-	ldr	x5, =TCR_EL2_FLAGS
+	mov	x5, #TCR_EL2_RES1
 	orr	x4, x4, x5
 
 #ifndef CONFIG_ARM64_VA_BITS_48
@@ -85,15 +85,18 @@ __do_hyp_init:
 	ldr_l	x5, idmap_t0sz
 	bfi	x4, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
 #endif
-	msr	tcr_el2, x4
-
-	ldr	x4, =VTCR_EL2_FLAGS
 	/*
 	 * Read the PARange bits from ID_AA64MMFR0_EL1 and set the PS bits in
-	 * VTCR_EL2.
+	 * TCR_EL2 and VTCR_EL2.
 	 */
 	mrs	x5, ID_AA64MMFR0_EL1
 	bfi	x4, x5, #16, #3
+
+	msr	tcr_el2, x4
+
+	ldr	x4, =VTCR_EL2_FLAGS
+	bfi	x4, x5, #16, #3
+
 	msr	vtcr_el2, x4
 
 	mrs	x4, mair_el1
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 1f6bb29ca53b..18201e9e8cc7 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -25,6 +25,8 @@
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative.h>
 
 #include "proc-macros.S"
 
@@ -137,7 +139,17 @@ ENTRY(cpu_do_switch_mm)
 	bfi	x0, x1, #48, #16		// set the ASID
 	msr	ttbr0_el1, x0			// set TTBR0
 	isb
+alternative_if_not ARM64_WORKAROUND_CAVIUM_27456
 	ret
+	nop
+	nop
+	nop
+alternative_else
+	ic	iallu
+	dsb	nsh
+	isb
+	ret
+alternative_endif
 ENDPROC(cpu_do_switch_mm)
 
 	.section ".text.init", #alloc, #execinstr
diff --git a/arch/metag/include/asm/atomic_lnkget.h b/arch/metag/include/asm/atomic_lnkget.h
index a62581815624..88fa25fae8bd 100644
--- a/arch/metag/include/asm/atomic_lnkget.h
+++ b/arch/metag/include/asm/atomic_lnkget.h
@@ -61,7 +61,7 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 		"	CMPT	%0, #HI(0x02000000)\n"			\
 		"	BNZ 1b\n"					\
 		: "=&d" (temp), "=&da" (result)				\
-		: "da" (&v->counter), "bd" (i)				\
+		: "da" (&v->counter), "br" (i)				\
 		: "cc");						\
 									\
 	smp_mb();							\
diff --git a/arch/powerpc/include/asm/icswx.h b/arch/powerpc/include/asm/icswx.h
index 9f8402b35115..27e588f6c72e 100644
--- a/arch/powerpc/include/asm/icswx.h
+++ b/arch/powerpc/include/asm/icswx.h
@@ -164,6 +164,7 @@ struct coprocessor_request_block {
 #define ICSWX_INITIATED		(0x8)
 #define ICSWX_BUSY		(0x4)
 #define ICSWX_REJECTED		(0x2)
+#define ICSWX_XERS0		(0x1)	/* undefined or set from XERSO. */
 
 static inline int icswx(__be32 ccw, struct coprocessor_request_block *crb)
 {
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index bf8f34a58670..b7019b559ddb 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -110,17 +110,11 @@ _GLOBAL(tm_reclaim)
 	std	r3, STK_PARAM(R3)(r1)
 	SAVE_NVGPRS(r1)
 
-	/* We need to setup MSR for VSX register save instructions.  Here we
-	 * also clear the MSR RI since when we do the treclaim, we won't have a
-	 * valid kernel pointer for a while.  We clear RI here as it avoids
-	 * adding another mtmsr closer to the treclaim.  This makes the region
-	 * maked as non-recoverable wider than it needs to be but it saves on
-	 * inserting another mtmsrd later.
-	 */
+	/* We need to setup MSR for VSX register save instructions. */
 	mfmsr	r14
 	mr	r15, r14
 	ori	r15, r15, MSR_FP
-	li	r16, MSR_RI
+	li	r16, 0
 	ori	r16, r16, MSR_EE /* IRQs hard off */
 	andc	r15, r15, r16
 	oris	r15, r15, MSR_VEC@h
@@ -176,7 +170,17 @@ dont_backup_fp:
 1:	tdeqi   r6, 0
 	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0
 
-	/* The moment we treclaim, ALL of our GPRs will switch
+	/* Clear MSR RI since we are about to change r1, EE is already off. */
+	li	r4, 0
+	mtmsrd	r4, 1
+
+	/*
+	 * BE CAREFUL HERE:
+	 * At this point we can't take an SLB miss since we have MSR_RI
+	 * off. Load only to/from the stack/paca which are in SLB bolted regions
+	 * until we turn MSR RI back on.
+	 *
+	 * The moment we treclaim, ALL of our GPRs will switch
 	 * to user register state.  (FPRs, CCR etc. also!)
 	 * Use an sprg and a tm_scratch in the PACA to shuffle.
 	 */
@@ -197,6 +201,11 @@ dont_backup_fp:
 
 	/* Store the PPR in r11 and reset to decent value */
 	std	r11, GPR11(r1)			/* Temporary stash */
+
+	/* Reset MSR RI so we can take SLB faults again */
+	li	r11, MSR_RI
+	mtmsrd	r11, 1
+
 	mfspr	r11, SPRN_PPR
 	HMT_MEDIUM
 
@@ -397,11 +406,6 @@ restore_gprs:
 	ld	r5, THREAD_TM_DSCR(r3)
 	ld	r6, THREAD_TM_PPR(r3)
 
-	/* Clear the MSR RI since we are about to change R1.  EE is already off
-	 */
-	li	r4, 0
-	mtmsrd	r4, 1
-
 	REST_GPR(0, r7)				/* GPR0 */
 	REST_2GPRS(2, r7)			/* GPR2-3 */
 	REST_GPR(4, r7)				/* GPR4 */
@@ -439,10 +443,33 @@ restore_gprs:
 	ld	r6, _CCR(r7)
 	mtcr    r6
 
-	REST_GPR(1, r7)				/* GPR1 */
-	REST_GPR(5, r7)				/* GPR5-7 */
 	REST_GPR(6, r7)
-	ld	r7, GPR7(r7)
+
+	/*
+	 * Store r1 and r5 on the stack so that we can access them
+	 * after we clear MSR RI.
+	 */
+
+	REST_GPR(5, r7)
+	std	r5, -8(r1)
+	ld	r5, GPR1(r7)
+	std	r5, -16(r1)
+
+	REST_GPR(7, r7)
+
+	/* Clear MSR RI since we are about to change r1. EE is already off */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	/*
+	 * BE CAREFUL HERE:
+	 * At this point we can't take an SLB miss since we have MSR_RI
+	 * off. Load only to/from the stack/paca which are in SLB bolted regions
+	 * until we turn MSR RI back on.
+	 */
+
+	ld	r5, -8(r1)
+	ld	r1, -16(r1)
 
 	/* Commit register state as checkpointed state: */
 	TRECHKPT
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index b8045b97f4fb..d750cc0dfe30 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -669,11 +669,13 @@ static const struct file_operations prng_tdes_fops = {
 static struct miscdevice prng_sha512_dev = {
 	.name	= "prandom",
 	.minor	= MISC_DYNAMIC_MINOR,
+	.mode	= 0644,
 	.fops	= &prng_sha512_fops,
 };
 static struct miscdevice prng_tdes_dev = {
 	.name	= "prandom",
 	.minor	= MISC_DYNAMIC_MINOR,
+	.mode	= 0644,
 	.fops	= &prng_tdes_fops,
 };
 
diff --git a/arch/s390/include/asm/pci_dma.h b/arch/s390/include/asm/pci_dma.h
index 1aac41e83ea1..92df3eb8d14e 100644
--- a/arch/s390/include/asm/pci_dma.h
+++ b/arch/s390/include/asm/pci_dma.h
@@ -23,6 +23,8 @@ enum zpci_ioat_dtype {
 #define ZPCI_IOTA_FS_2G			2
 #define ZPCI_KEY			(PAGE_DEFAULT_KEY << 5)
 
+#define ZPCI_TABLE_SIZE_RT	(1UL << 42)
+
 #define ZPCI_IOTA_STO_FLAG	(ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_ST)
 #define ZPCI_IOTA_RTTO_FLAG	(ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_RT)
 #define ZPCI_IOTA_RSTO_FLAG	(ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_RS)
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 19442395f413..f2f6720a3331 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -701,8 +701,7 @@ static int zpci_restore(struct device *dev)
 		goto out;
 
 	zpci_map_resources(pdev);
-	zpci_register_ioat(zdev, 0, zdev->start_dma + PAGE_OFFSET,
-			   zdev->start_dma + zdev->iommu_size - 1,
+	zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
 			   (u64) zdev->dma_table);
 
 out:
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index d348f2c09a1e..3a40f718baef 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -458,7 +458,19 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
 		goto out_clean;
 	}
 
-	zdev->iommu_size = (unsigned long) high_memory - PAGE_OFFSET;
+	/*
+	 * Restrict the iommu bitmap size to the minimum of the following:
+	 * - main memory size
+	 * - 3-level pagetable address limit minus start_dma offset
+	 * - DMA address range allowed by the hardware (clp query pci fn)
+	 *
+	 * Also set zdev->end_dma to the actual end address of the usable
+	 * range, instead of the theoretical maximum as reported by hardware.
+	 */
+	zdev->iommu_size = min3((u64) high_memory,
+				ZPCI_TABLE_SIZE_RT - zdev->start_dma,
+				zdev->end_dma - zdev->start_dma + 1);
+	zdev->end_dma = zdev->start_dma + zdev->iommu_size - 1;
 	zdev->iommu_pages = zdev->iommu_size >> PAGE_SHIFT;
 	zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8);
 	if (!zdev->iommu_bitmap) {
@@ -466,10 +478,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
 		goto out_reg;
 	}
 
-	rc = zpci_register_ioat(zdev,
-				0,
-				zdev->start_dma + PAGE_OFFSET,
-				zdev->start_dma + zdev->iommu_size - 1,
+	rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
 				(u64) zdev->dma_table);
 	if (rc)
 		goto out_reg;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 2f69e3b184f6..a3e1f8497f8c 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1587,6 +1587,9 @@ void __init enable_IR_x2apic(void)
 	unsigned long flags;
 	int ret, ir_stat;
 
+	if (skip_ioapic_setup)
+		return;
+
 	ir_stat = irq_remapping_prepare();
 	if (ir_stat < 0 && !x2apic_supported())
 		return;
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 20e242ea1bc4..cfc4a966e2b9 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -152,6 +152,11 @@ static struct clocksource hyperv_cs = {
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
+static unsigned char hv_get_nmi_reason(void)
+{
+	return 0;
+}
+
 static void __init ms_hyperv_init_platform(void)
 {
 	/*
@@ -191,6 +196,13 @@ static void __init ms_hyperv_init_platform(void)
 	machine_ops.crash_shutdown = hv_machine_crash_shutdown;
 #endif
 	mark_tsc_unstable("running on Hyper-V");
+
+	/*
+	 * Generation 2 instances don't support reading the NMI status from
+	 * 0x61 port.
+	 */
+	if (efi_enabled(EFI_BOOT))
+		x86_platform.get_nmi_reason = hv_get_nmi_reason;
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index a316ca96f1b6..fc704ed587e8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -211,6 +211,20 @@ static void __put_rmid(u32 rmid)
 	list_add_tail(&entry->list, &cqm_rmid_limbo_lru);
 }
 
+static void cqm_cleanup(void)
+{
+	int i;
+
+	if (!cqm_rmid_ptrs)
+		return;
+
+	for (i = 0; i < cqm_max_rmid; i++)
+		kfree(cqm_rmid_ptrs[i]);
+
+	kfree(cqm_rmid_ptrs);
+	cqm_rmid_ptrs = NULL;
+}
+
 static int intel_cqm_setup_rmid_cache(void)
 {
 	struct cqm_rmid_entry *entry;
@@ -218,7 +232,7 @@ static int intel_cqm_setup_rmid_cache(void)
 	int r = 0;
 
 	nr_rmids = cqm_max_rmid + 1;
-	cqm_rmid_ptrs = kmalloc(sizeof(struct cqm_rmid_entry *) *
+	cqm_rmid_ptrs = kzalloc(sizeof(struct cqm_rmid_entry *) *
 				nr_rmids, GFP_KERNEL);
 	if (!cqm_rmid_ptrs)
 		return -ENOMEM;
@@ -249,11 +263,9 @@ static int intel_cqm_setup_rmid_cache(void)
 	mutex_unlock(&cache_mutex);
 
 	return 0;
-fail:
-	while (r--)
-		kfree(cqm_rmid_ptrs[r]);
 
-	kfree(cqm_rmid_ptrs);
+fail:
+	cqm_cleanup();
 	return -ENOMEM;
 }
 
@@ -281,9 +293,13 @@ static bool __match_event(struct perf_event *a, struct perf_event *b)
 
 	/*
 	 * Events that target same task are placed into the same cache group.
+	 * Mark it as a multi event group, so that we update ->count
+	 * for every event rather than just the group leader later.
 	 */
-	if (a->hw.target == b->hw.target)
+	if (a->hw.target == b->hw.target) {
+		b->hw.is_group_event = true;
 		return true;
+	}
 
 	/*
 	 * Are we an inherited event?
@@ -849,6 +865,7 @@ static void intel_cqm_setup_event(struct perf_event *event,
 	bool conflict = false;
 	u32 rmid;
 
+	event->hw.is_group_event = false;
 	list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) {
 		rmid = iter->hw.cqm_rmid;
 
@@ -940,7 +957,9 @@ static u64 intel_cqm_event_count(struct perf_event *event)
 		return __perf_event_count(event);
 
 	/*
-	 * Only the group leader gets to report values. This stops us
+	 * Only the group leader gets to report values except in case of
+	 * multiple events in the same group, we still need to read the
+	 * other events.This stops us
 	 * reporting duplicate values to userspace, and gives us a clear
 	 * rule for which task gets to report the values.
 	 *
@@ -948,7 +967,7 @@ static u64 intel_cqm_event_count(struct perf_event *event)
 	 * specific packages - we forfeit that ability when we create
 	 * task events.
 	 */
-	if (!cqm_group_leader(event))
+	if (!cqm_group_leader(event) && !event->hw.is_group_event)
 		return 0;
 
 	/*
@@ -1315,7 +1334,7 @@ static const struct x86_cpu_id intel_cqm_match[] = {
 
 static int __init intel_cqm_init(void)
 {
-	char *str, scale[20];
+	char *str = NULL, scale[20];
 	int i, cpu, ret;
 
 	if (!x86_match_cpu(intel_cqm_match))
@@ -1375,16 +1394,25 @@ static int __init intel_cqm_init(void)
 		cqm_pick_event_reader(i);
 	}
 
-	__perf_cpu_notifier(intel_cqm_cpu_notifier);
-
 	ret = perf_pmu_register(&intel_cqm_pmu, "intel_cqm", -1);
-	if (ret)
+	if (ret) {
 		pr_err("Intel CQM perf registration failed: %d\n", ret);
-	else
-		pr_info("Intel CQM monitoring enabled\n");
+		goto out;
+	}
+
+	pr_info("Intel CQM monitoring enabled\n");
 
+	/*
+	 * Register the hot cpu notifier once we are sure cqm
+	 * is enabled to avoid notifier leak.
+	 */
+	__perf_cpu_notifier(intel_cqm_cpu_notifier);
 out:
 	cpu_notifier_register_done();
+	if (ret) {
+		kfree(str);
+		cqm_cleanup();
+	}
 
 	return ret;
 }
diff --git a/block/blk-core.c b/block/blk-core.c
index f8e64cac981a..4fab5d610805 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -515,7 +515,9 @@ EXPORT_SYMBOL_GPL(blk_queue_bypass_end);
 
 void blk_set_queue_dying(struct request_queue *q)
 {
-	queue_flag_set_unlocked(QUEUE_FLAG_DYING, q);
+	spin_lock_irq(q->queue_lock);
+	queue_flag_set(QUEUE_FLAG_DYING, q);
+	spin_unlock_irq(q->queue_lock);
 
 	if (q->mq_ops)
 		blk_mq_wake_waiters(q);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index b966db8f3556..7225511cf0b4 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -92,9 +92,31 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 	bool do_split = true;
 	struct bio *new = NULL;
 	const unsigned max_sectors = get_max_io_size(q, bio);
+	unsigned bvecs = 0;
 
 	bio_for_each_segment(bv, bio, iter) {
 		/*
+		 * With arbitrary bio size, the incoming bio may be very
+		 * big. We have to split the bio into small bios so that
+		 * each holds at most BIO_MAX_PAGES bvecs because
+		 * bio_clone() can fail to allocate big bvecs.
+		 *
+		 * It should have been better to apply the limit per
+		 * request queue in which bio_clone() is involved,
+		 * instead of globally. The biggest blocker is the
+		 * bio_clone() in bio bounce.
+		 *
+		 * If bio is splitted by this reason, we should have
+		 * allowed to continue bios merging, but don't do
+		 * that now for making the change simple.
+		 *
+		 * TODO: deal with bio bounce's bio_clone() gracefully
+		 * and convert the global limit into per-queue limit.
+		 */
+		if (bvecs++ >= BIO_MAX_PAGES)
+			goto split;
+
+		/*
 		 * If the queue doesn't support SG gaps and adding this
 		 * offset would create a gap, disallow it.
 		 */
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 6d6f8feb48c0..839b1e17481b 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -601,8 +601,10 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 		 * If a request wasn't started before the queue was
 		 * marked dying, kill it here or it'll go unnoticed.
 		 */
-		if (unlikely(blk_queue_dying(rq->q)))
-			blk_mq_complete_request(rq, -EIO);
+		if (unlikely(blk_queue_dying(rq->q))) {
+			rq->errors = -EIO;
+			blk_mq_end_request(rq, rq->errors);
+		}
 		return;
 	}
 	if (rq->cmd_flags & REQ_NO_TIMEOUT)
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 79107597a594..c306b483de60 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -2056,12 +2056,13 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 		return -EINVAL;
 	}
 
-	/* At the moment only the hardware variant iBT 3.0 (LnP/SfP) is
-	 * supported by this firmware loading method. This check has been
-	 * put in place to ensure correct forward compatibility options
-	 * when newer hardware variants come along.
+	/* At the moment the iBT 3.0 hardware variants 0x0b (LnP/SfP)
+	 * and 0x0c (WsP) are supported by this firmware loading method.
+	 *
+	 * This check has been put in place to ensure correct forward
+	 * compatibility options when newer hardware variants come along.
 	 */
-	if (ver->hw_variant != 0x0b) {
+	if (ver->hw_variant != 0x0b && ver->hw_variant != 0x0c) {
 		BT_ERR("%s: Unsupported Intel hardware variant (%u)",
 		       hdev->name, ver->hw_variant);
 		kfree_skb(skb);
diff --git a/drivers/char/hw_random/exynos-rng.c b/drivers/char/hw_random/exynos-rng.c
index aa30af5f0f2b..7845a38b6604 100644
--- a/drivers/char/hw_random/exynos-rng.c
+++ b/drivers/char/hw_random/exynos-rng.c
@@ -118,6 +118,7 @@ static int exynos_rng_probe(struct platform_device *pdev)
 {
 	struct exynos_rng *exynos_rng;
 	struct resource *res;
+	int ret;
 
 	exynos_rng = devm_kzalloc(&pdev->dev, sizeof(struct exynos_rng),
 					GFP_KERNEL);
@@ -145,7 +146,13 @@ static int exynos_rng_probe(struct platform_device *pdev)
 	pm_runtime_use_autosuspend(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
 
-	return devm_hwrng_register(&pdev->dev, &exynos_rng->rng);
+	ret = devm_hwrng_register(&pdev->dev, &exynos_rng->rng);
+	if (ret) {
+		pm_runtime_dont_use_autosuspend(&pdev->dev);
+		pm_runtime_disable(&pdev->dev);
+	}
+
+	return ret;
 }
 
 #ifdef CONFIG_PM
diff --git a/drivers/clk/clk-xgene.c b/drivers/clk/clk-xgene.c
index 27c0da29eca3..10224b01b97c 100644
--- a/drivers/clk/clk-xgene.c
+++ b/drivers/clk/clk-xgene.c
@@ -351,7 +351,8 @@ static int xgene_clk_set_rate(struct clk_hw *hw, unsigned long rate,
 		/* Set new divider */
 		data = xgene_clk_read(pclk->param.divider_reg +
 				pclk->param.reg_divider_offset);
-		data &= ~((1 << pclk->param.reg_divider_width) - 1);
+		data &= ~((1 << pclk->param.reg_divider_width) - 1)
+				<< pclk->param.reg_divider_shift;
 		data |= divider;
 		xgene_clk_write(data, pclk->param.divider_reg +
 					pclk->param.reg_divider_offset);
diff --git a/drivers/cpufreq/cpufreq_userspace.c b/drivers/cpufreq/cpufreq_userspace.c
index 4dbf1db16aca..9cc8abd3d116 100644
--- a/drivers/cpufreq/cpufreq_userspace.c
+++ b/drivers/cpufreq/cpufreq_userspace.c
@@ -17,6 +17,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
 
 static DEFINE_PER_CPU(unsigned int, cpu_is_managed);
 static DEFINE_MUTEX(userspace_mutex);
@@ -31,6 +32,7 @@ static DEFINE_MUTEX(userspace_mutex);
 static int cpufreq_set(struct cpufreq_policy *policy, unsigned int freq)
 {
 	int ret = -EINVAL;
+	unsigned int *setspeed = policy->governor_data;
 
 	pr_debug("cpufreq_set for cpu %u, freq %u kHz\n", policy->cpu, freq);
 
@@ -38,6 +40,8 @@ static int cpufreq_set(struct cpufreq_policy *policy, unsigned int freq)
 	if (!per_cpu(cpu_is_managed, policy->cpu))
 		goto err;
 
+	*setspeed = freq;
+
 	ret = __cpufreq_driver_target(policy, freq, CPUFREQ_RELATION_L);
  err:
 	mutex_unlock(&userspace_mutex);
@@ -49,19 +53,45 @@ static ssize_t show_speed(struct cpufreq_policy *policy, char *buf)
 	return sprintf(buf, "%u\n", policy->cur);
 }
 
+static int cpufreq_userspace_policy_init(struct cpufreq_policy *policy)
+{
+	unsigned int *setspeed;
+
+	setspeed = kzalloc(sizeof(*setspeed), GFP_KERNEL);
+	if (!setspeed)
+		return -ENOMEM;
+
+	policy->governor_data = setspeed;
+	return 0;
+}
+
 static int cpufreq_governor_userspace(struct cpufreq_policy *policy,
 				   unsigned int event)
 {
+	unsigned int *setspeed = policy->governor_data;
 	unsigned int cpu = policy->cpu;
 	int rc = 0;
 
+	if (event == CPUFREQ_GOV_POLICY_INIT)
+		return cpufreq_userspace_policy_init(policy);
+
+	if (!setspeed)
+		return -EINVAL;
+
 	switch (event) {
+	case CPUFREQ_GOV_POLICY_EXIT:
+		mutex_lock(&userspace_mutex);
+		policy->governor_data = NULL;
+		kfree(setspeed);
+		mutex_unlock(&userspace_mutex);
+		break;
 	case CPUFREQ_GOV_START:
 		BUG_ON(!policy->cur);
 		pr_debug("started managing cpu %u\n", cpu);
 
 		mutex_lock(&userspace_mutex);
 		per_cpu(cpu_is_managed, cpu) = 1;
+		*setspeed = policy->cur;
 		mutex_unlock(&userspace_mutex);
 		break;
 	case CPUFREQ_GOV_STOP:
@@ -69,20 +99,23 @@ static int cpufreq_governor_userspace(struct cpufreq_policy *policy,
 
 		mutex_lock(&userspace_mutex);
 		per_cpu(cpu_is_managed, cpu) = 0;
+		*setspeed = 0;
 		mutex_unlock(&userspace_mutex);
 		break;
 	case CPUFREQ_GOV_LIMITS:
 		mutex_lock(&userspace_mutex);
-		pr_debug("limit event for cpu %u: %u - %u kHz, currently %u kHz\n",
-			cpu, policy->min, policy->max,
-			policy->cur);
+		pr_debug("limit event for cpu %u: %u - %u kHz, currently %u kHz, last set to %u kHz\n",
+			cpu, policy->min, policy->max, policy->cur, *setspeed);
 
-		if (policy->max < policy->cur)
+		if (policy->max < *setspeed)
 			__cpufreq_driver_target(policy, policy->max,
 						CPUFREQ_RELATION_H);
-		else if (policy->min > policy->cur)
+		else if (policy->min > *setspeed)
 			__cpufreq_driver_target(policy, policy->min,
 						CPUFREQ_RELATION_L);
+		else
+			__cpufreq_driver_target(policy, *setspeed,
+						CPUFREQ_RELATION_L);
 		mutex_unlock(&userspace_mutex);
 		break;
 	}
diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c
index 6dc597126b79..b3044219772c 100644
--- a/drivers/crypto/caam/caamalg.c
+++ b/drivers/crypto/caam/caamalg.c
@@ -556,7 +556,10 @@ skip_enc:
 
 	/* Read and write assoclen bytes */
 	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
-	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
+	if (alg->caam.geniv)
+		append_math_add_imm_u32(desc, VARSEQOUTLEN, REG3, IMM, ivsize);
+	else
+		append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
 
 	/* Skip assoc data */
 	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
@@ -565,6 +568,14 @@ skip_enc:
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS2 | FIFOLD_TYPE_MSG |
 			     KEY_VLF);
 
+	if (alg->caam.geniv) {
+		append_seq_load(desc, ivsize, LDST_CLASS_1_CCB |
+				LDST_SRCDST_BYTE_CONTEXT |
+				(ctx1_iv_off << LDST_OFFSET_SHIFT));
+		append_move(desc, MOVE_SRC_CLASS1CTX | MOVE_DEST_CLASS2INFIFO |
+			    (ctx1_iv_off << MOVE_OFFSET_SHIFT) | ivsize);
+	}
+
 	/* Load Counter into CONTEXT1 reg */
 	if (is_rfc3686)
 		append_load_imm_u32(desc, be32_to_cpu(1), LDST_IMM |
@@ -2150,7 +2161,7 @@ static void init_authenc_job(struct aead_request *req,
 
 	init_aead_job(req, edesc, all_contig, encrypt);
 
-	if (ivsize && (is_rfc3686 || !(alg->caam.geniv && encrypt)))
+	if (ivsize && ((is_rfc3686 && encrypt) || !alg->caam.geniv))
 		append_load_as_imm(desc, req->iv, ivsize,
 				   LDST_CLASS_1_CCB |
 				   LDST_SRCDST_BYTE_CONTEXT |
@@ -2537,20 +2548,6 @@ static int aead_decrypt(struct aead_request *req)
 	return ret;
 }
 
-static int aead_givdecrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	unsigned int ivsize = crypto_aead_ivsize(aead);
-
-	if (req->cryptlen < ivsize)
-		return -EINVAL;
-
-	req->cryptlen -= ivsize;
-	req->assoclen += ivsize;
-
-	return aead_decrypt(req);
-}
-
 /*
  * allocate and map the ablkcipher extended descriptor for ablkcipher
  */
@@ -3210,7 +3207,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
 		},
@@ -3256,7 +3253,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
 		},
@@ -3302,7 +3299,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
 		},
@@ -3348,7 +3345,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
 		},
@@ -3394,7 +3391,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
 		},
@@ -3440,7 +3437,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
 		},
@@ -3486,7 +3483,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
 		},
@@ -3534,7 +3531,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
 		},
@@ -3582,7 +3579,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
 		},
@@ -3630,7 +3627,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
 		},
@@ -3678,7 +3675,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
 		},
@@ -3726,7 +3723,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
 		},
@@ -3772,7 +3769,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
 		},
@@ -3818,7 +3815,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
 		},
@@ -3864,7 +3861,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
 		},
@@ -3910,7 +3907,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
 		},
@@ -3956,7 +3953,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
 		},
@@ -4002,7 +3999,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
 		},
@@ -4051,7 +4048,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
 		},
@@ -4102,7 +4099,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
 		},
@@ -4153,7 +4150,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
 		},
@@ -4204,7 +4201,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
 		},
@@ -4255,7 +4252,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
 		},
@@ -4306,7 +4303,7 @@ static struct caam_aead_alg driver_aeads[] = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
-			.decrypt = aead_givdecrypt,
+			.decrypt = aead_decrypt,
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
 		},
diff --git a/drivers/crypto/nx/nx-842-powernv.c b/drivers/crypto/nx/nx-842-powernv.c
index 9ef51fafdbff..6e105e87b8ff 100644
--- a/drivers/crypto/nx/nx-842-powernv.c
+++ b/drivers/crypto/nx/nx-842-powernv.c
@@ -442,6 +442,14 @@ static int nx842_powernv_function(const unsigned char *in, unsigned int inlen,
 			     (unsigned int)ccw,
 			     (unsigned int)be32_to_cpu(crb->ccw));
 
+	/*
+	 * NX842 coprocessor sets 3rd bit in CR register with XER[S0].
+	 * XER[S0] is the integer summary overflow bit which is nothing
+	 * to do NX. Since this bit can be set with other return values,
+	 * mask this bit.
+	 */
+	ret &= ~ICSWX_XERS0;
+
 	switch (ret) {
 	case ICSWX_INITIATED:
 		ret = wait_for_csb(wmem, csb);
@@ -454,10 +462,6 @@ static int nx842_powernv_function(const unsigned char *in, unsigned int inlen,
 		pr_err_ratelimited("ICSWX rejected\n");
 		ret = -EPROTO;
 		break;
-	default:
-		pr_err_ratelimited("Invalid ICSWX return code %x\n", ret);
-		ret = -EPROTO;
-		break;
 	}
 
 	if (!ret)
diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c
index f3801b983f42..3f8bb9a40df1 100644
--- a/drivers/crypto/vmx/aes_cbc.c
+++ b/drivers/crypto/vmx/aes_cbc.c
@@ -191,7 +191,7 @@ struct crypto_alg p8_aes_cbc_alg = {
 	.cra_init = p8_aes_cbc_init,
 	.cra_exit = p8_aes_cbc_exit,
 	.cra_blkcipher = {
-			  .ivsize = 0,
+			  .ivsize = AES_BLOCK_SIZE,
 			  .min_keysize = AES_MIN_KEY_SIZE,
 			  .max_keysize = AES_MAX_KEY_SIZE,
 			  .setkey = p8_aes_cbc_setkey,
diff --git a/drivers/crypto/vmx/aes_ctr.c b/drivers/crypto/vmx/aes_ctr.c
index 404a1b69a3ab..72f138985e18 100644
--- a/drivers/crypto/vmx/aes_ctr.c
+++ b/drivers/crypto/vmx/aes_ctr.c
@@ -175,7 +175,7 @@ struct crypto_alg p8_aes_ctr_alg = {
 	.cra_init = p8_aes_ctr_init,
 	.cra_exit = p8_aes_ctr_exit,
 	.cra_blkcipher = {
-			  .ivsize = 0,
+			  .ivsize = AES_BLOCK_SIZE,
 			  .min_keysize = AES_MIN_KEY_SIZE,
 			  .max_keysize = AES_MAX_KEY_SIZE,
 			  .setkey = p8_aes_ctr_setkey,
diff --git a/drivers/crypto/vmx/ppc-xlate.pl b/drivers/crypto/vmx/ppc-xlate.pl
index b9997335f193..b18e67d0e065 100644
--- a/drivers/crypto/vmx/ppc-xlate.pl
+++ b/drivers/crypto/vmx/ppc-xlate.pl
@@ -139,6 +139,26 @@ my $vmr = sub {
     "	vor	$vx,$vy,$vy";
 };
 
+# Some ABIs specify vrsave, special-purpose register #256, as reserved
+# for system use.
+my $no_vrsave = ($flavour =~ /linux-ppc64le/);
+my $mtspr = sub {
+    my ($f,$idx,$ra) = @_;
+    if ($idx == 256 && $no_vrsave) {
+	"	or	$ra,$ra,$ra";
+    } else {
+	"	mtspr	$idx,$ra";
+    }
+};
+my $mfspr = sub {
+    my ($f,$rd,$idx) = @_;
+    if ($idx == 256 && $no_vrsave) {
+	"	li	$rd,-1";
+    } else {
+	"	mfspr	$rd,$idx";
+    }
+};
+
 # PowerISA 2.06 stuff
 sub vsxmem_op {
     my ($f, $vrt, $ra, $rb, $op) = @_;
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
index 92b6acadfc52..21aacc1f45c1 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
@@ -243,7 +243,7 @@ static void amdgpu_atombios_dp_get_adjust_train(const u8 link_status[DP_LINK_STA
 
 /* convert bits per color to bits per pixel */
 /* get bpc from the EDID */
-static int amdgpu_atombios_dp_convert_bpc_to_bpp(int bpc)
+static unsigned amdgpu_atombios_dp_convert_bpc_to_bpp(int bpc)
 {
 	if (bpc == 0)
 		return 24;
@@ -251,64 +251,32 @@ static int amdgpu_atombios_dp_convert_bpc_to_bpp(int bpc)
 		return bpc * 3;
 }
 
-/* get the max pix clock supported by the link rate and lane num */
-static int amdgpu_atombios_dp_get_max_dp_pix_clock(int link_rate,
-					    int lane_num,
-					    int bpp)
-{
-	return (link_rate * lane_num * 8) / bpp;
-}
-
 /***** amdgpu specific DP functions *****/
 
-/* First get the min lane# when low rate is used according to pixel clock
- * (prefer low rate), second check max lane# supported by DP panel,
- * if the max lane# < low rate lane# then use max lane# instead.
- */
-static int amdgpu_atombios_dp_get_dp_lane_number(struct drm_connector *connector,
+static int amdgpu_atombios_dp_get_dp_link_config(struct drm_connector *connector,
 						 const u8 dpcd[DP_DPCD_SIZE],
-						 int pix_clock)
-{
-	int bpp = amdgpu_atombios_dp_convert_bpc_to_bpp(amdgpu_connector_get_monitor_bpc(connector));
-	int max_link_rate = drm_dp_max_link_rate(dpcd);
-	int max_lane_num = drm_dp_max_lane_count(dpcd);
-	int lane_num;
-	int max_dp_pix_clock;
-
-	for (lane_num = 1; lane_num < max_lane_num; lane_num <<= 1) {
-		max_dp_pix_clock = amdgpu_atombios_dp_get_max_dp_pix_clock(max_link_rate, lane_num, bpp);
-		if (pix_clock <= max_dp_pix_clock)
-			break;
-	}
-
-	return lane_num;
-}
-
-static int amdgpu_atombios_dp_get_dp_link_clock(struct drm_connector *connector,
-						const u8 dpcd[DP_DPCD_SIZE],
-						int pix_clock)
+						 unsigned pix_clock,
+						 unsigned *dp_lanes, unsigned *dp_rate)
 {
-	int bpp = amdgpu_atombios_dp_convert_bpc_to_bpp(amdgpu_connector_get_monitor_bpc(connector));
-	int lane_num, max_pix_clock;
-
-	if (amdgpu_connector_encoder_get_dp_bridge_encoder_id(connector) ==
-	    ENCODER_OBJECT_ID_NUTMEG)
-		return 270000;
-
-	lane_num = amdgpu_atombios_dp_get_dp_lane_number(connector, dpcd, pix_clock);
-	max_pix_clock = amdgpu_atombios_dp_get_max_dp_pix_clock(162000, lane_num, bpp);
-	if (pix_clock <= max_pix_clock)
-		return 162000;
-	max_pix_clock = amdgpu_atombios_dp_get_max_dp_pix_clock(270000, lane_num, bpp);
-	if (pix_clock <= max_pix_clock)
-		return 270000;
-	if (amdgpu_connector_is_dp12_capable(connector)) {
-		max_pix_clock = amdgpu_atombios_dp_get_max_dp_pix_clock(540000, lane_num, bpp);
-		if (pix_clock <= max_pix_clock)
-			return 540000;
+	unsigned bpp =
+		amdgpu_atombios_dp_convert_bpc_to_bpp(amdgpu_connector_get_monitor_bpc(connector));
+	static const unsigned link_rates[3] = { 162000, 270000, 540000 };
+	unsigned max_link_rate = drm_dp_max_link_rate(dpcd);
+	unsigned max_lane_num = drm_dp_max_lane_count(dpcd);
+	unsigned lane_num, i, max_pix_clock;
+
+	for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) {
+		for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) {
+			max_pix_clock = (lane_num * link_rates[i] * 8) / bpp;
+			if (max_pix_clock >= pix_clock) {
+				*dp_lanes = lane_num;
+				*dp_rate = link_rates[i];
+				return 0;
+			}
+		}
 	}
 
-	return drm_dp_max_link_rate(dpcd);
+	return -EINVAL;
 }
 
 static u8 amdgpu_atombios_dp_encoder_service(struct amdgpu_device *adev,
@@ -422,6 +390,7 @@ void amdgpu_atombios_dp_set_link_config(struct drm_connector *connector,
 {
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 	struct amdgpu_connector_atom_dig *dig_connector;
+	int ret;
 
 	if (!amdgpu_connector->con_priv)
 		return;
@@ -429,10 +398,14 @@ void amdgpu_atombios_dp_set_link_config(struct drm_connector *connector,
 
 	if ((dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) ||
 	    (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_eDP)) {
-		dig_connector->dp_clock =
-			amdgpu_atombios_dp_get_dp_link_clock(connector, dig_connector->dpcd, mode->clock);
-		dig_connector->dp_lane_count =
-			amdgpu_atombios_dp_get_dp_lane_number(connector, dig_connector->dpcd, mode->clock);
+		ret = amdgpu_atombios_dp_get_dp_link_config(connector, dig_connector->dpcd,
+							    mode->clock,
+							    &dig_connector->dp_lane_count,
+							    &dig_connector->dp_clock);
+		if (ret) {
+			dig_connector->dp_clock = 0;
+			dig_connector->dp_lane_count = 0;
+		}
 	}
 }
 
@@ -441,14 +414,17 @@ int amdgpu_atombios_dp_mode_valid_helper(struct drm_connector *connector,
 {
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 	struct amdgpu_connector_atom_dig *dig_connector;
-	int dp_clock;
+	unsigned dp_lanes, dp_clock;
+	int ret;
 
 	if (!amdgpu_connector->con_priv)
 		return MODE_CLOCK_HIGH;
 	dig_connector = amdgpu_connector->con_priv;
 
-	dp_clock =
-		amdgpu_atombios_dp_get_dp_link_clock(connector, dig_connector->dpcd, mode->clock);
+	ret = amdgpu_atombios_dp_get_dp_link_config(connector, dig_connector->dpcd,
+						    mode->clock, &dp_lanes, &dp_clock);
+	if (ret)
+		return MODE_CLOCK_HIGH;
 
 	if ((dp_clock == 540000) &&
 	    (!amdgpu_connector_is_dp12_capable(connector)))
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
index 8035d4d6a4f5..653917a3bcc2 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
@@ -1955,10 +1955,8 @@ static void cz_dpm_powergate_vce(struct amdgpu_device *adev, bool gate)
 		}
 	} else { /*pi->caps_vce_pg*/
 		cz_update_vce_dpm(adev);
-		cz_enable_vce_dpm(adev, true);
+		cz_enable_vce_dpm(adev, !gate);
 	}
-
-	return;
 }
 
 const struct amd_ip_funcs cz_dpm_ip_funcs = {
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index e5aec45bf985..1ac29d703c12 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -108,7 +108,6 @@ steal_encoder(struct drm_atomic_state *state,
 	struct drm_crtc_state *crtc_state;
 	struct drm_connector *connector;
 	struct drm_connector_state *connector_state;
-	int ret;
 
 	/*
 	 * We can only steal an encoder coming from a connector, which means we
@@ -139,9 +138,6 @@ steal_encoder(struct drm_atomic_state *state,
 		if (IS_ERR(connector_state))
 			return PTR_ERR(connector_state);
 
-		ret = drm_atomic_set_crtc_for_connector(connector_state, NULL);
-		if (ret)
-			return ret;
 		connector_state->best_encoder = NULL;
 	}
 
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index dc84003f694e..5e4bb4837bae 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -5231,6 +5231,9 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 	unsigned long flags;
 	int ret = -EINVAL;
 
+	if (!drm_core_check_feature(dev, DRIVER_MODESET))
+		return -EINVAL;
+
 	if (page_flip->flags & ~DRM_MODE_PAGE_FLIP_FLAGS ||
 	    page_flip->reserved != 0)
 		return -EINVAL;
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index c7de454e8e88..b205224f1a44 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -338,27 +338,32 @@ drm_gem_handle_create_tail(struct drm_file *file_priv,
 	spin_unlock(&file_priv->table_lock);
 	idr_preload_end();
 	mutex_unlock(&dev->object_name_lock);
-	if (ret < 0) {
-		drm_gem_object_handle_unreference_unlocked(obj);
-		return ret;
-	}
+	if (ret < 0)
+		goto err_unref;
+
 	*handlep = ret;
 
 	ret = drm_vma_node_allow(&obj->vma_node, file_priv->filp);
-	if (ret) {
-		drm_gem_handle_delete(file_priv, *handlep);
-		return ret;
-	}
+	if (ret)
+		goto err_remove;
 
 	if (dev->driver->gem_open_object) {
 		ret = dev->driver->gem_open_object(obj, file_priv);
-		if (ret) {
-			drm_gem_handle_delete(file_priv, *handlep);
-			return ret;
-		}
+		if (ret)
+			goto err_revoke;
 	}
 
 	return 0;
+
+err_revoke:
+	drm_vma_node_revoke(&obj->vma_node, file_priv->filp);
+err_remove:
+	spin_lock(&file_priv->table_lock);
+	idr_remove(&file_priv->object_idr, *handlep);
+	spin_unlock(&file_priv->table_lock);
+err_unref:
+	drm_gem_object_handle_unreference_unlocked(obj);
+	return ret;
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d3ce4da6a6ad..d400d6773bbb 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3313,6 +3313,9 @@ static inline bool intel_gmbus_is_forced_bit(struct i2c_adapter *adapter)
 }
 extern void intel_i2c_reset(struct drm_device *dev);
 
+/* intel_bios.c */
+bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port port);
+
 /* intel_opregion.c */
 #ifdef CONFIG_ACPI
 extern int intel_opregion_setup(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 9ed9f6dde86f..cace154bbdc0 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3240,19 +3240,20 @@ enum skl_disp_power_wells {
 
 #define PORT_HOTPLUG_STAT	(dev_priv->info.display_mmio_offset + 0x61114)
 /*
- * HDMI/DP bits are gen4+
+ * HDMI/DP bits are g4x+
  *
  * WARNING: Bspec for hpd status bits on gen4 seems to be completely confused.
  * Please check the detailed lore in the commit message for for experimental
  * evidence.
  */
-#define   PORTD_HOTPLUG_LIVE_STATUS_G4X		(1 << 29)
+/* Bspec says GM45 should match G4X/VLV/CHV, but reality disagrees */
+#define   PORTD_HOTPLUG_LIVE_STATUS_GM45	(1 << 29)
+#define   PORTC_HOTPLUG_LIVE_STATUS_GM45	(1 << 28)
+#define   PORTB_HOTPLUG_LIVE_STATUS_GM45	(1 << 27)
+/* G4X/VLV/CHV DP/HDMI bits again match Bspec */
+#define   PORTD_HOTPLUG_LIVE_STATUS_G4X		(1 << 27)
 #define   PORTC_HOTPLUG_LIVE_STATUS_G4X		(1 << 28)
-#define   PORTB_HOTPLUG_LIVE_STATUS_G4X		(1 << 27)
-/* VLV DP/HDMI bits again match Bspec */
-#define   PORTD_HOTPLUG_LIVE_STATUS_VLV		(1 << 27)
-#define   PORTC_HOTPLUG_LIVE_STATUS_VLV		(1 << 28)
-#define   PORTB_HOTPLUG_LIVE_STATUS_VLV		(1 << 29)
+#define   PORTB_HOTPLUG_LIVE_STATUS_G4X		(1 << 29)
 #define   PORTD_HOTPLUG_INT_STATUS		(3 << 21)
 #define   PORTD_HOTPLUG_INT_LONG_PULSE		(2 << 21)
 #define   PORTD_HOTPLUG_INT_SHORT_PULSE		(1 << 21)
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index ce82f9c7df24..d14bdc537587 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -1351,3 +1351,42 @@ intel_parse_bios(struct drm_device *dev)
 
 	return 0;
 }
+
+/**
+ * intel_bios_is_port_present - is the specified digital port present
+ * @dev_priv:	i915 device instance
+ * @port:	port to check
+ *
+ * Return true if the device in %port is present.
+ */
+bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port port)
+{
+	static const struct {
+		u16 dp, hdmi;
+	} port_mapping[] = {
+		[PORT_B] = { DVO_PORT_DPB, DVO_PORT_HDMIB, },
+		[PORT_C] = { DVO_PORT_DPC, DVO_PORT_HDMIC, },
+		[PORT_D] = { DVO_PORT_DPD, DVO_PORT_HDMID, },
+		[PORT_E] = { DVO_PORT_DPE, DVO_PORT_HDMIE, },
+	};
+	int i;
+
+	/* FIXME maybe deal with port A as well? */
+	if (WARN_ON(port == PORT_A) || port >= ARRAY_SIZE(port_mapping))
+		return false;
+
+	if (!dev_priv->vbt.child_dev_num)
+		return false;
+
+	for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
+		const union child_device_config *p_child =
+			&dev_priv->vbt.child_dev[i];
+		if ((p_child->common.dvo_port == port_mapping[port].dp ||
+		     p_child->common.dvo_port == port_mapping[port].hdmi) &&
+		    (p_child->common.device_type & (DEVICE_TYPE_TMDS_DVI_SIGNALING |
+						    DEVICE_TYPE_DISPLAYPORT_OUTPUT)))
+			return true;
+	}
+
+	return false;
+}
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 3292495ee10f..a3254c3bcc7c 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -14160,6 +14160,8 @@ static void intel_setup_outputs(struct drm_device *dev)
 		if (I915_READ(PCH_DP_D) & DP_DETECTED)
 			intel_dp_init(dev, PCH_DP_D, PORT_D);
 	} else if (IS_VALLEYVIEW(dev)) {
+		bool has_edp, has_port;
+
 		/*
 		 * The DP_DETECTED bit is the latched state of the DDC
 		 * SDA pin at boot. However since eDP doesn't require DDC
@@ -14168,27 +14170,37 @@ static void intel_setup_outputs(struct drm_device *dev)
 		 * Thus we can't rely on the DP_DETECTED bit alone to detect
 		 * eDP ports. Consult the VBT as well as DP_DETECTED to
 		 * detect eDP ports.
+		 *
+		 * Sadly the straps seem to be missing sometimes even for HDMI
+		 * ports (eg. on Voyo V3 - CHT x7-Z8700), so check both strap
+		 * and VBT for the presence of the port. Additionally we can't
+		 * trust the port type the VBT declares as we've seen at least
+		 * HDMI ports that the VBT claim are DP or eDP.
 		 */
-		if (I915_READ(VLV_HDMIB) & SDVO_DETECTED &&
-		    !intel_dp_is_edp(dev, PORT_B))
+		has_edp = intel_dp_is_edp(dev, PORT_B);
+		has_port = intel_bios_is_port_present(dev_priv, PORT_B);
+		if (I915_READ(VLV_DP_B) & DP_DETECTED || has_port)
+			has_edp &= intel_dp_init(dev, VLV_DP_B, PORT_B);
+		if ((I915_READ(VLV_HDMIB) & SDVO_DETECTED || has_port) && !has_edp)
 			intel_hdmi_init(dev, VLV_HDMIB, PORT_B);
-		if (I915_READ(VLV_DP_B) & DP_DETECTED ||
-		    intel_dp_is_edp(dev, PORT_B))
-			intel_dp_init(dev, VLV_DP_B, PORT_B);
 
-		if (I915_READ(VLV_HDMIC) & SDVO_DETECTED &&
-		    !intel_dp_is_edp(dev, PORT_C))
+		has_edp = intel_dp_is_edp(dev, PORT_C);
+		has_port = intel_bios_is_port_present(dev_priv, PORT_C);
+		if (I915_READ(VLV_DP_C) & DP_DETECTED || has_port)
+			has_edp &= intel_dp_init(dev, VLV_DP_C, PORT_C);
+		if ((I915_READ(VLV_HDMIC) & SDVO_DETECTED || has_port) && !has_edp)
 			intel_hdmi_init(dev, VLV_HDMIC, PORT_C);
-		if (I915_READ(VLV_DP_C) & DP_DETECTED ||
-		    intel_dp_is_edp(dev, PORT_C))
-			intel_dp_init(dev, VLV_DP_C, PORT_C);
 
 		if (IS_CHERRYVIEW(dev)) {
-			/* eDP not supported on port D, so don't check VBT */
-			if (I915_READ(CHV_HDMID) & SDVO_DETECTED)
-				intel_hdmi_init(dev, CHV_HDMID, PORT_D);
-			if (I915_READ(CHV_DP_D) & DP_DETECTED)
+			/*
+			 * eDP not supported on port D,
+			 * so no need to worry about it
+			 */
+			has_port = intel_bios_is_port_present(dev_priv, PORT_D);
+			if (I915_READ(CHV_DP_D) & DP_DETECTED || has_port)
 				intel_dp_init(dev, CHV_DP_D, PORT_D);
+			if (I915_READ(CHV_HDMID) & SDVO_DETECTED || has_port)
+				intel_hdmi_init(dev, CHV_HDMID, PORT_D);
 		}
 
 		intel_dsi_init(dev);
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 8e1d6d74c203..ebbd23407a80 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -4592,20 +4592,20 @@ static bool g4x_digital_port_connected(struct drm_i915_private *dev_priv,
 	return I915_READ(PORT_HOTPLUG_STAT) & bit;
 }
 
-static bool vlv_digital_port_connected(struct drm_i915_private *dev_priv,
-				       struct intel_digital_port *port)
+static bool gm45_digital_port_connected(struct drm_i915_private *dev_priv,
+					struct intel_digital_port *port)
 {
 	u32 bit;
 
 	switch (port->port) {
 	case PORT_B:
-		bit = PORTB_HOTPLUG_LIVE_STATUS_VLV;
+		bit = PORTB_HOTPLUG_LIVE_STATUS_GM45;
 		break;
 	case PORT_C:
-		bit = PORTC_HOTPLUG_LIVE_STATUS_VLV;
+		bit = PORTC_HOTPLUG_LIVE_STATUS_GM45;
 		break;
 	case PORT_D:
-		bit = PORTD_HOTPLUG_LIVE_STATUS_VLV;
+		bit = PORTD_HOTPLUG_LIVE_STATUS_GM45;
 		break;
 	default:
 		MISSING_CASE(port->port);
@@ -4657,8 +4657,8 @@ bool intel_digital_port_connected(struct drm_i915_private *dev_priv,
 		return cpt_digital_port_connected(dev_priv, port);
 	else if (IS_BROXTON(dev_priv))
 		return bxt_digital_port_connected(dev_priv, port);
-	else if (IS_VALLEYVIEW(dev_priv))
-		return vlv_digital_port_connected(dev_priv, port);
+	else if (IS_GM45(dev_priv))
+		return gm45_digital_port_connected(dev_priv, port);
 	else
 		return g4x_digital_port_connected(dev_priv, port);
 }
@@ -6113,8 +6113,9 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	return true;
 }
 
-void
-intel_dp_init(struct drm_device *dev, int output_reg, enum port port)
+bool intel_dp_init(struct drm_device *dev,
+		   int output_reg,
+		   enum port port)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_digital_port *intel_dig_port;
@@ -6124,7 +6125,7 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port)
 
 	intel_dig_port = kzalloc(sizeof(*intel_dig_port), GFP_KERNEL);
 	if (!intel_dig_port)
-		return;
+		return false;
 
 	intel_connector = intel_connector_alloc();
 	if (!intel_connector)
@@ -6179,15 +6180,14 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port)
 	if (!intel_dp_init_connector(intel_dig_port, intel_connector))
 		goto err_init_connector;
 
-	return;
+	return true;
 
 err_init_connector:
 	drm_encoder_cleanup(encoder);
 	kfree(intel_connector);
 err_connector_alloc:
 	kfree(intel_dig_port);
-
-	return;
+	return false;
 }
 
 void intel_dp_mst_suspend(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index c5f11e0c5d5b..67f72a7ee7cb 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1195,7 +1195,7 @@ void intel_csr_ucode_fini(struct drm_device *dev);
 void assert_csr_loaded(struct drm_i915_private *dev_priv);
 
 /* intel_dp.c */
-void intel_dp_init(struct drm_device *dev, int output_reg, enum port port);
+bool intel_dp_init(struct drm_device *dev, int output_reg, enum port port);
 bool intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 			     struct intel_connector *intel_connector);
 void intel_dp_set_link_params(struct intel_dp *intel_dp,
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 4b8ed9f2dabc..dff69fef47e0 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -2030,6 +2030,9 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 	enum port port = intel_dig_port->port;
 	uint8_t alternate_ddc_pin;
 
+	DRM_DEBUG_KMS("Adding HDMI connector on port %c\n",
+		      port_name(port));
+
 	drm_connector_init(dev, connector, &intel_hdmi_connector_funcs,
 			   DRM_MODE_CONNECTOR_HDMIA);
 	drm_connector_helper_add(connector, &intel_hdmi_connector_helper_funcs);
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 6d7cd3fe21e7..1847f83b1e33 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -55,6 +55,14 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
 	return submit;
 }
 
+static inline unsigned long __must_check
+copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
+{
+	if (access_ok(VERIFY_READ, from, n))
+		return __copy_from_user_inatomic(to, from, n);
+	return -EFAULT;
+}
+
 static int submit_lookup_objects(struct msm_gem_submit *submit,
 		struct drm_msm_gem_submit *args, struct drm_file *file)
 {
@@ -62,6 +70,7 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
 	int ret = 0;
 
 	spin_lock(&file->table_lock);
+	pagefault_disable();
 
 	for (i = 0; i < args->nr_bos; i++) {
 		struct drm_msm_gem_submit_bo submit_bo;
@@ -70,10 +79,15 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
 		void __user *userptr =
 			to_user_ptr(args->bos + (i * sizeof(submit_bo)));
 
-		ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo));
-		if (ret) {
-			ret = -EFAULT;
-			goto out_unlock;
+		ret = copy_from_user_inatomic(&submit_bo, userptr, sizeof(submit_bo));
+		if (unlikely(ret)) {
+			pagefault_enable();
+			spin_unlock(&file->table_lock);
+			ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo));
+			if (ret)
+				goto out;
+			spin_lock(&file->table_lock);
+			pagefault_disable();
 		}
 
 		if (submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) {
@@ -113,9 +127,12 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
 	}
 
 out_unlock:
-	submit->nr_bos = i;
+	pagefault_enable();
 	spin_unlock(&file->table_lock);
 
+out:
+	submit->nr_bos = i;
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index bd73b4069069..44ee72e04df9 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -302,77 +302,31 @@ static int convert_bpc_to_bpp(int bpc)
 		return bpc * 3;
 }
 
-/* get the max pix clock supported by the link rate and lane num */
-static int dp_get_max_dp_pix_clock(int link_rate,
-				   int lane_num,
-				   int bpp)
-{
-	return (link_rate * lane_num * 8) / bpp;
-}
-
 /***** radeon specific DP functions *****/
 
-int radeon_dp_get_max_link_rate(struct drm_connector *connector,
-				const u8 dpcd[DP_DPCD_SIZE])
-{
-	int max_link_rate;
-
-	if (radeon_connector_is_dp12_capable(connector))
-		max_link_rate = min(drm_dp_max_link_rate(dpcd), 540000);
-	else
-		max_link_rate = min(drm_dp_max_link_rate(dpcd), 270000);
-
-	return max_link_rate;
-}
-
-/* First get the min lane# when low rate is used according to pixel clock
- * (prefer low rate), second check max lane# supported by DP panel,
- * if the max lane# < low rate lane# then use max lane# instead.
- */
-static int radeon_dp_get_dp_lane_number(struct drm_connector *connector,
-					const u8 dpcd[DP_DPCD_SIZE],
-					int pix_clock)
-{
-	int bpp = convert_bpc_to_bpp(radeon_get_monitor_bpc(connector));
-	int max_link_rate = radeon_dp_get_max_link_rate(connector, dpcd);
-	int max_lane_num = drm_dp_max_lane_count(dpcd);
-	int lane_num;
-	int max_dp_pix_clock;
-
-	for (lane_num = 1; lane_num < max_lane_num; lane_num <<= 1) {
-		max_dp_pix_clock = dp_get_max_dp_pix_clock(max_link_rate, lane_num, bpp);
-		if (pix_clock <= max_dp_pix_clock)
-			break;
-	}
-
-	return lane_num;
-}
-
-static int radeon_dp_get_dp_link_clock(struct drm_connector *connector,
-				       const u8 dpcd[DP_DPCD_SIZE],
-				       int pix_clock)
+int radeon_dp_get_dp_link_config(struct drm_connector *connector,
+				 const u8 dpcd[DP_DPCD_SIZE],
+				 unsigned pix_clock,
+				 unsigned *dp_lanes, unsigned *dp_rate)
 {
 	int bpp = convert_bpc_to_bpp(radeon_get_monitor_bpc(connector));
-	int lane_num, max_pix_clock;
-
-	if (radeon_connector_encoder_get_dp_bridge_encoder_id(connector) ==
-	    ENCODER_OBJECT_ID_NUTMEG)
-		return 270000;
-
-	lane_num = radeon_dp_get_dp_lane_number(connector, dpcd, pix_clock);
-	max_pix_clock = dp_get_max_dp_pix_clock(162000, lane_num, bpp);
-	if (pix_clock <= max_pix_clock)
-		return 162000;
-	max_pix_clock = dp_get_max_dp_pix_clock(270000, lane_num, bpp);
-	if (pix_clock <= max_pix_clock)
-		return 270000;
-	if (radeon_connector_is_dp12_capable(connector)) {
-		max_pix_clock = dp_get_max_dp_pix_clock(540000, lane_num, bpp);
-		if (pix_clock <= max_pix_clock)
-			return 540000;
+	static const unsigned link_rates[3] = { 162000, 270000, 540000 };
+	unsigned max_link_rate = drm_dp_max_link_rate(dpcd);
+	unsigned max_lane_num = drm_dp_max_lane_count(dpcd);
+	unsigned lane_num, i, max_pix_clock;
+
+	for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) {
+		for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) {
+			max_pix_clock = (lane_num * link_rates[i] * 8) / bpp;
+			if (max_pix_clock >= pix_clock) {
+				*dp_lanes = lane_num;
+				*dp_rate = link_rates[i];
+				return 0;
+			}
+		}
 	}
 
-	return radeon_dp_get_max_link_rate(connector, dpcd);
+	return -EINVAL;
 }
 
 static u8 radeon_dp_encoder_service(struct radeon_device *rdev,
@@ -491,6 +445,7 @@ void radeon_dp_set_link_config(struct drm_connector *connector,
 {
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	struct radeon_connector_atom_dig *dig_connector;
+	int ret;
 
 	if (!radeon_connector->con_priv)
 		return;
@@ -498,10 +453,14 @@ void radeon_dp_set_link_config(struct drm_connector *connector,
 
 	if ((dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) ||
 	    (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_eDP)) {
-		dig_connector->dp_clock =
-			radeon_dp_get_dp_link_clock(connector, dig_connector->dpcd, mode->clock);
-		dig_connector->dp_lane_count =
-			radeon_dp_get_dp_lane_number(connector, dig_connector->dpcd, mode->clock);
+		ret = radeon_dp_get_dp_link_config(connector, dig_connector->dpcd,
+						   mode->clock,
+						   &dig_connector->dp_lane_count,
+						   &dig_connector->dp_clock);
+		if (ret) {
+			dig_connector->dp_clock = 0;
+			dig_connector->dp_lane_count = 0;
+		}
 	}
 }
 
@@ -510,7 +469,8 @@ int radeon_dp_mode_valid_helper(struct drm_connector *connector,
 {
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	struct radeon_connector_atom_dig *dig_connector;
-	int dp_clock;
+	unsigned dp_clock, dp_lanes;
+	int ret;
 
 	if ((mode->clock > 340000) &&
 	    (!radeon_connector_is_dp12_capable(connector)))
@@ -520,8 +480,12 @@ int radeon_dp_mode_valid_helper(struct drm_connector *connector,
 		return MODE_CLOCK_HIGH;
 	dig_connector = radeon_connector->con_priv;
 
-	dp_clock =
-		radeon_dp_get_dp_link_clock(connector, dig_connector->dpcd, mode->clock);
+	ret = radeon_dp_get_dp_link_config(connector, dig_connector->dpcd,
+					   mode->clock,
+					   &dp_lanes,
+					   &dp_clock);
+	if (ret)
+		return MODE_CLOCK_HIGH;
 
 	if ((dp_clock == 540000) &&
 	    (!radeon_connector_is_dp12_capable(connector)))
diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c
index 744f5c49c664..6dd39bdedb97 100644
--- a/drivers/gpu/drm/radeon/radeon_dp_mst.c
+++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c
@@ -525,11 +525,9 @@ static bool radeon_mst_mode_fixup(struct drm_encoder *encoder,
 	drm_mode_set_crtcinfo(adjusted_mode, 0);
 	{
 	  struct radeon_connector_atom_dig *dig_connector;
-
 	  dig_connector = mst_enc->connector->con_priv;
 	  dig_connector->dp_lane_count = drm_dp_max_lane_count(dig_connector->dpcd);
-	  dig_connector->dp_clock = radeon_dp_get_max_link_rate(&mst_enc->connector->base,
-								dig_connector->dpcd);
+	  dig_connector->dp_clock = drm_dp_max_link_rate(dig_connector->dpcd);
 	  DRM_DEBUG_KMS("dig clock %p %d %d\n", dig_connector,
 			dig_connector->dp_lane_count, dig_connector->dp_clock);
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index bba112628b47..7a0666ac4e23 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -757,8 +757,10 @@ extern u8 radeon_dp_getsinktype(struct radeon_connector *radeon_connector);
 extern bool radeon_dp_getdpcd(struct radeon_connector *radeon_connector);
 extern int radeon_dp_get_panel_mode(struct drm_encoder *encoder,
 				    struct drm_connector *connector);
-int radeon_dp_get_max_link_rate(struct drm_connector *connector,
-				const u8 *dpcd);
+extern int radeon_dp_get_dp_link_config(struct drm_connector *connector,
+					const u8 *dpcd,
+					unsigned pix_clock,
+					unsigned *dp_lanes, unsigned *dp_rate);
 extern void radeon_dp_set_rx_power_state(struct drm_connector *connector,
 					 u8 power_state);
 extern void radeon_dp_aux_init(struct radeon_connector *radeon_connector);
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index f342aad79cc6..35310336dd0a 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -263,8 +263,8 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 
 	rdev = radeon_get_rdev(bo->bdev);
 	ridx = radeon_copy_ring_index(rdev);
-	old_start = old_mem->start << PAGE_SHIFT;
-	new_start = new_mem->start << PAGE_SHIFT;
+	old_start = (u64)old_mem->start << PAGE_SHIFT;
+	new_start = (u64)new_mem->start << PAGE_SHIFT;
 
 	switch (old_mem->mem_type) {
 	case TTM_PL_VRAM:
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index ec791e169f8f..936960202cf4 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1251,6 +1251,7 @@ static void hid_input_field(struct hid_device *hid, struct hid_field *field,
 		/* Ignore report if ErrorRollOver */
 		if (!(field->flags & HID_MAIN_ITEM_VARIABLE) &&
 		    value[n] >= min && value[n] <= max &&
+		    value[n] - min < field->maxusage &&
 		    field->usage[value[n] - min].hid == HID_UP_KEYBOARD + 1)
 			goto exit;
 	}
@@ -1263,11 +1264,13 @@ static void hid_input_field(struct hid_device *hid, struct hid_field *field,
 		}
 
 		if (field->value[n] >= min && field->value[n] <= max
+			&& field->value[n] - min < field->maxusage
 			&& field->usage[field->value[n] - min].hid
 			&& search(value, field->value[n], count))
 				hid_process_event(hid, field, &field->usage[field->value[n] - min], 0, interrupt);
 
 		if (value[n] >= min && value[n] <= max
+			&& value[n] - min < field->maxusage
 			&& field->usage[value[n] - min].hid
 			&& search(field->value, value[n], count))
 				hid_process_event(hid, field, &field->usage[value[n] - min], 1, interrupt);
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 9098f13f2f44..1ef37c727572 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -28,6 +28,7 @@
 #include <linux/module.h>
 #include <linux/hyperv.h>
 #include <linux/uio.h>
+#include <linux/interrupt.h>
 
 #include "hyperv_vmbus.h"
 
@@ -496,8 +497,21 @@ static void reset_channel_cb(void *arg)
 static int vmbus_close_internal(struct vmbus_channel *channel)
 {
 	struct vmbus_channel_close_channel *msg;
+	struct tasklet_struct *tasklet;
 	int ret;
 
+	/*
+	 * process_chn_event(), running in the tasklet, can race
+	 * with vmbus_close_internal() in the case of SMP guest, e.g., when
+	 * the former is accessing channel->inbound.ring_buffer, the latter
+	 * could be freeing the ring_buffer pages.
+	 *
+	 * To resolve the race, we can serialize them by disabling the
+	 * tasklet when the latter is running here.
+	 */
+	tasklet = hv_context.event_dpc[channel->target_cpu];
+	tasklet_disable(tasklet);
+
 	channel->state = CHANNEL_OPEN_STATE;
 	channel->sc_creation_callback = NULL;
 	/* Stop callback and cancel the timer asap */
@@ -525,7 +539,7 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
 		 * If we failed to post the close msg,
 		 * it is perhaps better to leak memory.
 		 */
-		return ret;
+		goto out;
 	}
 
 	/* Tear down the gpadl for the channel's ring buffer */
@@ -538,7 +552,7 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
 			 * If we failed to teardown gpadl,
 			 * it is perhaps better to leak memory.
 			 */
-			return ret;
+			goto out;
 		}
 	}
 
@@ -549,12 +563,9 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
 	free_pages((unsigned long)channel->ringbuffer_pages,
 		get_order(channel->ringbuffer_pagecount * PAGE_SIZE));
 
-	/*
-	 * If the channel has been rescinded; process device removal.
-	 */
-	if (channel->rescind)
-		hv_process_channel_removal(channel,
-					   channel->offermsg.child_relid);
+out:
+	tasklet_enable(tasklet);
+
 	return ret;
 }
 
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 652afd11a9ef..37238dffd947 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -28,6 +28,7 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/completion.h>
+#include <linux/delay.h>
 #include <linux/hyperv.h>
 
 #include "hyperv_vmbus.h"
@@ -191,6 +192,8 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
 	if (channel == NULL)
 		return;
 
+	BUG_ON(!channel->rescind);
+
 	if (channel->target_cpu != get_cpu()) {
 		put_cpu();
 		smp_call_function_single(channel->target_cpu,
@@ -230,9 +233,7 @@ void vmbus_free_channels(void)
 
 	list_for_each_entry_safe(channel, tmp, &vmbus_connection.chn_list,
 		listentry) {
-		/* if we don't set rescind to true, vmbus_close_internal()
-		 * won't invoke hv_process_channel_removal().
-		 */
+		/* hv_process_channel_removal() needs this */
 		channel->rescind = true;
 
 		vmbus_device_unregister(channel->device_obj);
@@ -459,6 +460,17 @@ static void init_vp_index(struct vmbus_channel *channel, const uuid_le *type_gui
 		    cpumask_of_node(primary->numa_node));
 
 	cur_cpu = -1;
+
+	/*
+	 * Normally Hyper-V host doesn't create more subchannels than there
+	 * are VCPUs on the node but it is possible when not all present VCPUs
+	 * on the node are initialized by guest. Clear the alloced_cpus_in_node
+	 * to start over.
+	 */
+	if (cpumask_equal(&primary->alloced_cpus_in_node,
+			  cpumask_of_node(primary->numa_node)))
+		cpumask_clear(&primary->alloced_cpus_in_node);
+
 	while (true) {
 		cur_cpu = cpumask_next(cur_cpu, &available_mask);
 		if (cur_cpu >= nr_cpu_ids) {
@@ -488,6 +500,40 @@ static void init_vp_index(struct vmbus_channel *channel, const uuid_le *type_gui
 	channel->target_vp = hv_context.vp_index[cur_cpu];
 }
 
+static void vmbus_wait_for_unload(void)
+{
+	int cpu = smp_processor_id();
+	void *page_addr = hv_context.synic_message_page[cpu];
+	struct hv_message *msg = (struct hv_message *)page_addr +
+				  VMBUS_MESSAGE_SINT;
+	struct vmbus_channel_message_header *hdr;
+	bool unloaded = false;
+
+	while (1) {
+		if (msg->header.message_type == HVMSG_NONE) {
+			mdelay(10);
+			continue;
+		}
+
+		hdr = (struct vmbus_channel_message_header *)msg->u.payload;
+		if (hdr->msgtype == CHANNELMSG_UNLOAD_RESPONSE)
+			unloaded = true;
+
+		msg->header.message_type = HVMSG_NONE;
+		/*
+		 * header.message_type needs to be written before we do
+		 * wrmsrl() below.
+		 */
+		mb();
+
+		if (msg->header.message_flags.msg_pending)
+			wrmsrl(HV_X64_MSR_EOM, 0);
+
+		if (unloaded)
+			break;
+	}
+}
+
 /*
  * vmbus_unload_response - Handler for the unload response.
  */
@@ -513,7 +559,14 @@ void vmbus_initiate_unload(void)
 	hdr.msgtype = CHANNELMSG_UNLOAD;
 	vmbus_post_msg(&hdr, sizeof(struct vmbus_channel_message_header));
 
-	wait_for_completion(&vmbus_connection.unload_event);
+	/*
+	 * vmbus_initiate_unload() is also called on crash and the crash can be
+	 * happening in an interrupt context, where scheduling is impossible.
+	 */
+	if (!in_interrupt())
+		wait_for_completion(&vmbus_connection.unload_event);
+	else
+		vmbus_wait_for_unload();
 }
 
 /*
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 6341be8739ae..63194a9a7189 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -293,8 +293,14 @@ void hv_cleanup(void)
 	 * Cleanup the TSC page based CS.
 	 */
 	if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) {
-		clocksource_change_rating(&hyperv_cs_tsc, 10);
-		clocksource_unregister(&hyperv_cs_tsc);
+		/*
+		 * Crash can happen in an interrupt context and unregistering
+		 * a clocksource is impossible and redundant in this case.
+		 */
+		if (!oops_in_progress) {
+			clocksource_change_rating(&hyperv_cs_tsc, 10);
+			clocksource_unregister(&hyperv_cs_tsc);
+		}
 
 		hypercall_msr.as_uint64 = 0;
 		wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64);
diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c
index db4b887b889d..c37a71e13de0 100644
--- a/drivers/hv/hv_fcopy.c
+++ b/drivers/hv/hv_fcopy.c
@@ -51,7 +51,6 @@ static struct {
 	struct hv_fcopy_hdr  *fcopy_msg; /* current message */
 	struct vmbus_channel *recv_channel; /* chn we got the request */
 	u64 recv_req_id; /* request ID. */
-	void *fcopy_context; /* for the channel callback */
 } fcopy_transaction;
 
 static void fcopy_respond_to_host(int error);
@@ -67,6 +66,13 @@ static struct hvutil_transport *hvt;
  */
 static int dm_reg_value;
 
+static void fcopy_poll_wrapper(void *channel)
+{
+	/* Transaction is finished, reset the state here to avoid races. */
+	fcopy_transaction.state = HVUTIL_READY;
+	hv_fcopy_onchannelcallback(channel);
+}
+
 static void fcopy_timeout_func(struct work_struct *dummy)
 {
 	/*
@@ -74,13 +80,7 @@ static void fcopy_timeout_func(struct work_struct *dummy)
 	 * process the pending transaction.
 	 */
 	fcopy_respond_to_host(HV_E_FAIL);
-
-	/* Transaction is finished, reset the state. */
-	if (fcopy_transaction.state > HVUTIL_READY)
-		fcopy_transaction.state = HVUTIL_READY;
-
-	hv_poll_channel(fcopy_transaction.fcopy_context,
-			hv_fcopy_onchannelcallback);
+	hv_poll_channel(fcopy_transaction.recv_channel, fcopy_poll_wrapper);
 }
 
 static int fcopy_handle_handshake(u32 version)
@@ -108,9 +108,7 @@ static int fcopy_handle_handshake(u32 version)
 		return -EINVAL;
 	}
 	pr_debug("FCP: userspace daemon ver. %d registered\n", version);
-	fcopy_transaction.state = HVUTIL_READY;
-	hv_poll_channel(fcopy_transaction.fcopy_context,
-			hv_fcopy_onchannelcallback);
+	hv_poll_channel(fcopy_transaction.recv_channel, fcopy_poll_wrapper);
 	return 0;
 }
 
@@ -227,15 +225,8 @@ void hv_fcopy_onchannelcallback(void *context)
 	int util_fw_version;
 	int fcopy_srv_version;
 
-	if (fcopy_transaction.state > HVUTIL_READY) {
-		/*
-		 * We will defer processing this callback once
-		 * the current transaction is complete.
-		 */
-		fcopy_transaction.fcopy_context = context;
+	if (fcopy_transaction.state > HVUTIL_READY)
 		return;
-	}
-	fcopy_transaction.fcopy_context = NULL;
 
 	vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 2, &recvlen,
 			 &requestid);
@@ -275,7 +266,8 @@ void hv_fcopy_onchannelcallback(void *context)
 		 * Send the information to the user-level daemon.
 		 */
 		schedule_work(&fcopy_send_work);
-		schedule_delayed_work(&fcopy_timeout_work, 5*HZ);
+		schedule_delayed_work(&fcopy_timeout_work,
+				      HV_UTIL_TIMEOUT * HZ);
 		return;
 	}
 	icmsghdr->icflags = ICMSGHDRFLAG_TRANSACTION | ICMSGHDRFLAG_RESPONSE;
@@ -304,9 +296,8 @@ static int fcopy_on_msg(void *msg, int len)
 	if (cancel_delayed_work_sync(&fcopy_timeout_work)) {
 		fcopy_transaction.state = HVUTIL_USERSPACE_RECV;
 		fcopy_respond_to_host(*val);
-		fcopy_transaction.state = HVUTIL_READY;
-		hv_poll_channel(fcopy_transaction.fcopy_context,
-				hv_fcopy_onchannelcallback);
+		hv_poll_channel(fcopy_transaction.recv_channel,
+				fcopy_poll_wrapper);
 	}
 
 	return 0;
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c
index 74c38a9f34a6..2a3420c4ca59 100644
--- a/drivers/hv/hv_kvp.c
+++ b/drivers/hv/hv_kvp.c
@@ -66,7 +66,6 @@ static struct {
 	struct hv_kvp_msg  *kvp_msg; /* current message */
 	struct vmbus_channel *recv_channel; /* chn we got the request */
 	u64 recv_req_id; /* request ID. */
-	void *kvp_context; /* for the channel callback */
 } kvp_transaction;
 
 /*
@@ -94,6 +93,13 @@ static struct hvutil_transport *hvt;
  */
 #define HV_DRV_VERSION           "3.1"
 
+static void kvp_poll_wrapper(void *channel)
+{
+	/* Transaction is finished, reset the state here to avoid races. */
+	kvp_transaction.state = HVUTIL_READY;
+	hv_kvp_onchannelcallback(channel);
+}
+
 static void
 kvp_register(int reg_value)
 {
@@ -121,12 +127,7 @@ static void kvp_timeout_func(struct work_struct *dummy)
 	 */
 	kvp_respond_to_host(NULL, HV_E_FAIL);
 
-	/* Transaction is finished, reset the state. */
-	if (kvp_transaction.state > HVUTIL_READY)
-		kvp_transaction.state = HVUTIL_READY;
-
-	hv_poll_channel(kvp_transaction.kvp_context,
-			hv_kvp_onchannelcallback);
+	hv_poll_channel(kvp_transaction.recv_channel, kvp_poll_wrapper);
 }
 
 static int kvp_handle_handshake(struct hv_kvp_msg *msg)
@@ -218,9 +219,7 @@ static int kvp_on_msg(void *msg, int len)
 	 */
 	if (cancel_delayed_work_sync(&kvp_timeout_work)) {
 		kvp_respond_to_host(message, error);
-		kvp_transaction.state = HVUTIL_READY;
-		hv_poll_channel(kvp_transaction.kvp_context,
-				hv_kvp_onchannelcallback);
+		hv_poll_channel(kvp_transaction.recv_channel, kvp_poll_wrapper);
 	}
 
 	return 0;
@@ -596,15 +595,8 @@ void hv_kvp_onchannelcallback(void *context)
 	int util_fw_version;
 	int kvp_srv_version;
 
-	if (kvp_transaction.state > HVUTIL_READY) {
-		/*
-		 * We will defer processing this callback once
-		 * the current transaction is complete.
-		 */
-		kvp_transaction.kvp_context = context;
+	if (kvp_transaction.state > HVUTIL_READY)
 		return;
-	}
-	kvp_transaction.kvp_context = NULL;
 
 	vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 4, &recvlen,
 			 &requestid);
@@ -668,7 +660,8 @@ void hv_kvp_onchannelcallback(void *context)
 			 * user-mode not responding.
 			 */
 			schedule_work(&kvp_sendkey_work);
-			schedule_delayed_work(&kvp_timeout_work, 5*HZ);
+			schedule_delayed_work(&kvp_timeout_work,
+					      HV_UTIL_TIMEOUT * HZ);
 
 			return;
 
diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c
index 815405f2e777..81882d4848bd 100644
--- a/drivers/hv/hv_snapshot.c
+++ b/drivers/hv/hv_snapshot.c
@@ -53,7 +53,6 @@ static struct {
 	struct vmbus_channel *recv_channel; /* chn we got the request */
 	u64 recv_req_id; /* request ID. */
 	struct hv_vss_msg  *msg; /* current message */
-	void *vss_context; /* for the channel callback */
 } vss_transaction;
 
 
@@ -74,6 +73,13 @@ static void vss_timeout_func(struct work_struct *dummy);
 static DECLARE_DELAYED_WORK(vss_timeout_work, vss_timeout_func);
 static DECLARE_WORK(vss_send_op_work, vss_send_op);
 
+static void vss_poll_wrapper(void *channel)
+{
+	/* Transaction is finished, reset the state here to avoid races. */
+	vss_transaction.state = HVUTIL_READY;
+	hv_vss_onchannelcallback(channel);
+}
+
 /*
  * Callback when data is received from user mode.
  */
@@ -86,12 +92,7 @@ static void vss_timeout_func(struct work_struct *dummy)
 	pr_warn("VSS: timeout waiting for daemon to reply\n");
 	vss_respond_to_host(HV_E_FAIL);
 
-	/* Transaction is finished, reset the state. */
-	if (vss_transaction.state > HVUTIL_READY)
-		vss_transaction.state = HVUTIL_READY;
-
-	hv_poll_channel(vss_transaction.vss_context,
-			hv_vss_onchannelcallback);
+	hv_poll_channel(vss_transaction.recv_channel, vss_poll_wrapper);
 }
 
 static int vss_handle_handshake(struct hv_vss_msg *vss_msg)
@@ -138,9 +139,8 @@ static int vss_on_msg(void *msg, int len)
 		if (cancel_delayed_work_sync(&vss_timeout_work)) {
 			vss_respond_to_host(vss_msg->error);
 			/* Transaction is finished, reset the state. */
-			vss_transaction.state = HVUTIL_READY;
-			hv_poll_channel(vss_transaction.vss_context,
-					hv_vss_onchannelcallback);
+			hv_poll_channel(vss_transaction.recv_channel,
+					vss_poll_wrapper);
 		}
 	} else {
 		/* This is a spurious call! */
@@ -238,15 +238,8 @@ void hv_vss_onchannelcallback(void *context)
 	struct icmsg_hdr *icmsghdrp;
 	struct icmsg_negotiate *negop = NULL;
 
-	if (vss_transaction.state > HVUTIL_READY) {
-		/*
-		 * We will defer processing this callback once
-		 * the current transaction is complete.
-		 */
-		vss_transaction.vss_context = context;
+	if (vss_transaction.state > HVUTIL_READY)
 		return;
-	}
-	vss_transaction.vss_context = NULL;
 
 	vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 2, &recvlen,
 			 &requestid);
@@ -338,6 +331,11 @@ static void vss_on_reset(void)
 int
 hv_vss_init(struct hv_util_service *srv)
 {
+	if (vmbus_proto_version < VERSION_WIN8_1) {
+		pr_warn("Integration service 'Backup (volume snapshot)'"
+			" not supported on this host version.\n");
+		return -ENOTSUPP;
+	}
 	recv_buffer = srv->recv_buffer;
 
 	/*
diff --git a/drivers/hv/hv_utils_transport.c b/drivers/hv/hv_utils_transport.c
index 6a9d80a5332d..1505ee6e6605 100644
--- a/drivers/hv/hv_utils_transport.c
+++ b/drivers/hv/hv_utils_transport.c
@@ -204,9 +204,12 @@ int hvutil_transport_send(struct hvutil_transport *hvt, void *msg, int len)
 		goto out_unlock;
 	}
 	hvt->outmsg = kzalloc(len, GFP_KERNEL);
-	memcpy(hvt->outmsg, msg, len);
-	hvt->outmsg_len = len;
-	wake_up_interruptible(&hvt->outmsg_q);
+	if (hvt->outmsg) {
+		memcpy(hvt->outmsg, msg, len);
+		hvt->outmsg_len = len;
+		wake_up_interruptible(&hvt->outmsg_q);
+	} else
+		ret = -ENOMEM;
 out_unlock:
 	mutex_unlock(&hvt->outmsg_lock);
 	return ret;
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 3782636562a1..12156db2e88e 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -31,6 +31,11 @@
 #include <linux/hyperv.h>
 
 /*
+ * Timeout for services such as KVP and fcopy.
+ */
+#define HV_UTIL_TIMEOUT 30
+
+/*
  * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent
  * is set by CPUID(HVCPUID_VERSION_FEATURES).
  */
@@ -759,11 +764,7 @@ static inline void hv_poll_channel(struct vmbus_channel *channel,
 	if (!channel)
 		return;
 
-	if (channel->target_cpu != smp_processor_id())
-		smp_call_function_single(channel->target_cpu,
-					 cb, channel, true);
-	else
-		cb(channel);
+	smp_call_function_single(channel->target_cpu, cb, channel, true);
 }
 
 enum hvutil_device_state {
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 9b5440f6b3b4..509ed9731630 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -105,6 +105,7 @@ static struct notifier_block hyperv_panic_block = {
 };
 
 struct resource *hyperv_mmio;
+DEFINE_SEMAPHORE(hyperv_mmio_lock);
 
 static int vmbus_exists(void)
 {
@@ -603,23 +604,11 @@ static int vmbus_remove(struct device *child_device)
 {
 	struct hv_driver *drv;
 	struct hv_device *dev = device_to_hv_device(child_device);
-	u32 relid = dev->channel->offermsg.child_relid;
 
 	if (child_device->driver) {
 		drv = drv_to_hv_drv(child_device->driver);
 		if (drv->remove)
 			drv->remove(dev);
-		else {
-			hv_process_channel_removal(dev->channel, relid);
-			pr_err("remove not set for driver %s\n",
-				dev_name(child_device));
-		}
-	} else {
-		/*
-		 * We don't have a driver for this device; deal with the
-		 * rescind message by removing the channel.
-		 */
-		hv_process_channel_removal(dev->channel, relid);
 	}
 
 	return 0;
@@ -654,7 +643,10 @@ static void vmbus_shutdown(struct device *child_device)
 static void vmbus_device_release(struct device *device)
 {
 	struct hv_device *hv_dev = device_to_hv_device(device);
+	struct vmbus_channel *channel = hv_dev->channel;
 
+	hv_process_channel_removal(channel,
+				   channel->offermsg.child_relid);
 	kfree(hv_dev);
 
 }
@@ -870,7 +862,7 @@ static int vmbus_bus_init(int irq)
 	on_each_cpu(hv_synic_init, NULL, 1);
 	ret = vmbus_connect();
 	if (ret)
-		goto err_alloc;
+		goto err_connect;
 
 	if (vmbus_proto_version > VERSION_WIN7)
 		cpu_hotplug_disable();
@@ -888,6 +880,8 @@ static int vmbus_bus_init(int irq)
 
 	return 0;
 
+err_connect:
+	on_each_cpu(hv_synic_cleanup, NULL, 1);
 err_alloc:
 	hv_synic_free();
 	hv_remove_vmbus_irq();
@@ -1147,7 +1141,10 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj,
 	resource_size_t range_min, range_max, start, local_min, local_max;
 	const char *dev_n = dev_name(&device_obj->device);
 	u32 fb_end = screen_info.lfb_base + (screen_info.lfb_size << 1);
-	int i;
+	int i, retval;
+
+	retval = -ENXIO;
+	down(&hyperv_mmio_lock);
 
 	for (iter = hyperv_mmio; iter; iter = iter->sibling) {
 		if ((iter->start >= max) || (iter->end <= min))
@@ -1184,13 +1181,17 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj,
 			for (; start + size - 1 <= local_max; start += align) {
 				*new = request_mem_region_exclusive(start, size,
 								    dev_n);
-				if (*new)
-					return 0;
+				if (*new) {
+					retval = 0;
+					goto exit;
+				}
 			}
 		}
 	}
 
-	return -ENXIO;
+exit:
+	up(&hyperv_mmio_lock);
+	return retval;
 }
 EXPORT_SYMBOL_GPL(vmbus_allocate_mmio);
 
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 146eed70bdf4..ba947df5a8c7 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -716,6 +716,26 @@ static struct cpuidle_state avn_cstates[] = {
 	{
 		.enter = NULL }
 };
+static struct cpuidle_state knl_cstates[] = {
+	{
+		.name = "C1-KNL",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00),
+		.exit_latency = 1,
+		.target_residency = 2,
+		.enter = &intel_idle,
+		.enter_freeze = intel_idle_freeze },
+	{
+		.name = "C6-KNL",
+		.desc = "MWAIT 0x10",
+		.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 120,
+		.target_residency = 500,
+		.enter = &intel_idle,
+		.enter_freeze = intel_idle_freeze },
+	{
+		.enter = NULL }
+};
 
 /**
  * intel_idle
@@ -890,6 +910,10 @@ static const struct idle_cpu idle_cpu_avn = {
 	.disable_promotion_to_c1e = true,
 };
 
+static const struct idle_cpu idle_cpu_knl = {
+	.state_table = knl_cstates,
+};
+
 #define ICPU(model, cpu) \
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT, (unsigned long)&cpu }
 
@@ -921,6 +945,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	ICPU(0x56, idle_cpu_bdw),
 	ICPU(0x4e, idle_cpu_skl),
 	ICPU(0x5e, idle_cpu_skl),
+	ICPU(0x57, idle_cpu_knl),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_idle_ids);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 5ea0c14070d1..fa9c42ff1fb0 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -245,8 +245,6 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	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/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 2b2f9d66c2c7..aff42d5e2296 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -317,6 +317,19 @@ static struct usb_device_id xpad_table[] = {
 
 MODULE_DEVICE_TABLE(usb, xpad_table);
 
+struct xpad_output_packet {
+	u8 data[XPAD_PKT_LEN];
+	u8 len;
+	bool pending;
+};
+
+#define XPAD_OUT_CMD_IDX	0
+#define XPAD_OUT_FF_IDX		1
+#define XPAD_OUT_LED_IDX	(1 + IS_ENABLED(CONFIG_JOYSTICK_XPAD_FF))
+#define XPAD_NUM_OUT_PACKETS	(1 + \
+				 IS_ENABLED(CONFIG_JOYSTICK_XPAD_FF) + \
+				 IS_ENABLED(CONFIG_JOYSTICK_XPAD_LEDS))
+
 struct usb_xpad {
 	struct input_dev *dev;		/* input device interface */
 	struct usb_device *udev;	/* usb device */
@@ -329,9 +342,13 @@ struct usb_xpad {
 	dma_addr_t idata_dma;
 
 	struct urb *irq_out;		/* urb for interrupt out report */
+	bool irq_out_active;		/* we must not use an active URB */
 	unsigned char *odata;		/* output data */
 	dma_addr_t odata_dma;
-	struct mutex odata_mutex;
+	spinlock_t odata_lock;
+
+	struct xpad_output_packet out_packets[XPAD_NUM_OUT_PACKETS];
+	int last_out_packet;
 
 #if defined(CONFIG_JOYSTICK_XPAD_LEDS)
 	struct xpad_led *led;
@@ -678,18 +695,71 @@ exit:
 			__func__, retval);
 }
 
+/* Callers must hold xpad->odata_lock spinlock */
+static bool xpad_prepare_next_out_packet(struct usb_xpad *xpad)
+{
+	struct xpad_output_packet *pkt, *packet = NULL;
+	int i;
+
+	for (i = 0; i < XPAD_NUM_OUT_PACKETS; i++) {
+		if (++xpad->last_out_packet >= XPAD_NUM_OUT_PACKETS)
+			xpad->last_out_packet = 0;
+
+		pkt = &xpad->out_packets[xpad->last_out_packet];
+		if (pkt->pending) {
+			dev_dbg(&xpad->intf->dev,
+				"%s - found pending output packet %d\n",
+				__func__, xpad->last_out_packet);
+			packet = pkt;
+			break;
+		}
+	}
+
+	if (packet) {
+		memcpy(xpad->odata, packet->data, packet->len);
+		xpad->irq_out->transfer_buffer_length = packet->len;
+		packet->pending = false;
+		return true;
+	}
+
+	return false;
+}
+
+/* Callers must hold xpad->odata_lock spinlock */
+static int xpad_try_sending_next_out_packet(struct usb_xpad *xpad)
+{
+	int error;
+
+	if (!xpad->irq_out_active && xpad_prepare_next_out_packet(xpad)) {
+		error = usb_submit_urb(xpad->irq_out, GFP_ATOMIC);
+		if (error) {
+			dev_err(&xpad->intf->dev,
+				"%s - usb_submit_urb failed with result %d\n",
+				__func__, error);
+			return -EIO;
+		}
+
+		xpad->irq_out_active = true;
+	}
+
+	return 0;
+}
+
 static void xpad_irq_out(struct urb *urb)
 {
 	struct usb_xpad *xpad = urb->context;
 	struct device *dev = &xpad->intf->dev;
-	int retval, status;
+	int status = urb->status;
+	int error;
+	unsigned long flags;
 
-	status = urb->status;
+	spin_lock_irqsave(&xpad->odata_lock, flags);
 
 	switch (status) {
 	case 0:
 		/* success */
-		return;
+		xpad->irq_out_active = xpad_prepare_next_out_packet(xpad);
+		break;
 
 	case -ECONNRESET:
 	case -ENOENT:
@@ -697,19 +767,26 @@ static void xpad_irq_out(struct urb *urb)
 		/* this urb is terminated, clean up */
 		dev_dbg(dev, "%s - urb shutting down with status: %d\n",
 			__func__, status);
-		return;
+		xpad->irq_out_active = false;
+		break;
 
 	default:
 		dev_dbg(dev, "%s - nonzero urb status received: %d\n",
 			__func__, status);
-		goto exit;
+		break;
 	}
 
-exit:
-	retval = usb_submit_urb(urb, GFP_ATOMIC);
-	if (retval)
-		dev_err(dev, "%s - usb_submit_urb failed with result %d\n",
-			__func__, retval);
+	if (xpad->irq_out_active) {
+		error = usb_submit_urb(urb, GFP_ATOMIC);
+		if (error) {
+			dev_err(dev,
+				"%s - usb_submit_urb failed with result %d\n",
+				__func__, error);
+			xpad->irq_out_active = false;
+		}
+	}
+
+	spin_unlock_irqrestore(&xpad->odata_lock, flags);
 }
 
 static int xpad_init_output(struct usb_interface *intf, struct usb_xpad *xpad)
@@ -728,7 +805,7 @@ static int xpad_init_output(struct usb_interface *intf, struct usb_xpad *xpad)
 		goto fail1;
 	}
 
-	mutex_init(&xpad->odata_mutex);
+	spin_lock_init(&xpad->odata_lock);
 
 	xpad->irq_out = usb_alloc_urb(0, GFP_KERNEL);
 	if (!xpad->irq_out) {
@@ -770,27 +847,57 @@ static void xpad_deinit_output(struct usb_xpad *xpad)
 
 static int xpad_inquiry_pad_presence(struct usb_xpad *xpad)
 {
+	struct xpad_output_packet *packet =
+			&xpad->out_packets[XPAD_OUT_CMD_IDX];
+	unsigned long flags;
 	int retval;
 
-	mutex_lock(&xpad->odata_mutex);
+	spin_lock_irqsave(&xpad->odata_lock, flags);
+
+	packet->data[0] = 0x08;
+	packet->data[1] = 0x00;
+	packet->data[2] = 0x0F;
+	packet->data[3] = 0xC0;
+	packet->data[4] = 0x00;
+	packet->data[5] = 0x00;
+	packet->data[6] = 0x00;
+	packet->data[7] = 0x00;
+	packet->data[8] = 0x00;
+	packet->data[9] = 0x00;
+	packet->data[10] = 0x00;
+	packet->data[11] = 0x00;
+	packet->len = 12;
+	packet->pending = true;
+
+	/* Reset the sequence so we send out presence first */
+	xpad->last_out_packet = -1;
+	retval = xpad_try_sending_next_out_packet(xpad);
+
+	spin_unlock_irqrestore(&xpad->odata_lock, flags);
 
-	xpad->odata[0] = 0x08;
-	xpad->odata[1] = 0x00;
-	xpad->odata[2] = 0x0F;
-	xpad->odata[3] = 0xC0;
-	xpad->odata[4] = 0x00;
-	xpad->odata[5] = 0x00;
-	xpad->odata[6] = 0x00;
-	xpad->odata[7] = 0x00;
-	xpad->odata[8] = 0x00;
-	xpad->odata[9] = 0x00;
-	xpad->odata[10] = 0x00;
-	xpad->odata[11] = 0x00;
-	xpad->irq_out->transfer_buffer_length = 12;
+	return retval;
+}
 
-	retval = usb_submit_urb(xpad->irq_out, GFP_KERNEL);
+static int xpad_start_xbox_one(struct usb_xpad *xpad)
+{
+	struct xpad_output_packet *packet =
+			&xpad->out_packets[XPAD_OUT_CMD_IDX];
+	unsigned long flags;
+	int retval;
+
+	spin_lock_irqsave(&xpad->odata_lock, flags);
+
+	/* Xbox one controller needs to be initialized. */
+	packet->data[0] = 0x05;
+	packet->data[1] = 0x20;
+	packet->len = 2;
+	packet->pending = true;
 
-	mutex_unlock(&xpad->odata_mutex);
+	/* Reset the sequence so we send out start packet first */
+	xpad->last_out_packet = -1;
+	retval = xpad_try_sending_next_out_packet(xpad);
+
+	spin_unlock_irqrestore(&xpad->odata_lock, flags);
 
 	return retval;
 }
@@ -799,8 +906,11 @@ static int xpad_inquiry_pad_presence(struct usb_xpad *xpad)
 static int xpad_play_effect(struct input_dev *dev, void *data, struct ff_effect *effect)
 {
 	struct usb_xpad *xpad = input_get_drvdata(dev);
+	struct xpad_output_packet *packet = &xpad->out_packets[XPAD_OUT_FF_IDX];
 	__u16 strong;
 	__u16 weak;
+	int retval;
+	unsigned long flags;
 
 	if (effect->type != FF_RUMBLE)
 		return 0;
@@ -808,69 +918,80 @@ static int xpad_play_effect(struct input_dev *dev, void *data, struct ff_effect
 	strong = effect->u.rumble.strong_magnitude;
 	weak = effect->u.rumble.weak_magnitude;
 
+	spin_lock_irqsave(&xpad->odata_lock, flags);
+
 	switch (xpad->xtype) {
 	case XTYPE_XBOX:
-		xpad->odata[0] = 0x00;
-		xpad->odata[1] = 0x06;
-		xpad->odata[2] = 0x00;
-		xpad->odata[3] = strong / 256;	/* left actuator */
-		xpad->odata[4] = 0x00;
-		xpad->odata[5] = weak / 256;	/* right actuator */
-		xpad->irq_out->transfer_buffer_length = 6;
+		packet->data[0] = 0x00;
+		packet->data[1] = 0x06;
+		packet->data[2] = 0x00;
+		packet->data[3] = strong / 256;	/* left actuator */
+		packet->data[4] = 0x00;
+		packet->data[5] = weak / 256;	/* right actuator */
+		packet->len = 6;
+		packet->pending = true;
 		break;
 
 	case XTYPE_XBOX360:
-		xpad->odata[0] = 0x00;
-		xpad->odata[1] = 0x08;
-		xpad->odata[2] = 0x00;
-		xpad->odata[3] = strong / 256;  /* left actuator? */
-		xpad->odata[4] = weak / 256;	/* right actuator? */
-		xpad->odata[5] = 0x00;
-		xpad->odata[6] = 0x00;
-		xpad->odata[7] = 0x00;
-		xpad->irq_out->transfer_buffer_length = 8;
+		packet->data[0] = 0x00;
+		packet->data[1] = 0x08;
+		packet->data[2] = 0x00;
+		packet->data[3] = strong / 256;  /* left actuator? */
+		packet->data[4] = weak / 256;	/* right actuator? */
+		packet->data[5] = 0x00;
+		packet->data[6] = 0x00;
+		packet->data[7] = 0x00;
+		packet->len = 8;
+		packet->pending = true;
 		break;
 
 	case XTYPE_XBOX360W:
-		xpad->odata[0] = 0x00;
-		xpad->odata[1] = 0x01;
-		xpad->odata[2] = 0x0F;
-		xpad->odata[3] = 0xC0;
-		xpad->odata[4] = 0x00;
-		xpad->odata[5] = strong / 256;
-		xpad->odata[6] = weak / 256;
-		xpad->odata[7] = 0x00;
-		xpad->odata[8] = 0x00;
-		xpad->odata[9] = 0x00;
-		xpad->odata[10] = 0x00;
-		xpad->odata[11] = 0x00;
-		xpad->irq_out->transfer_buffer_length = 12;
+		packet->data[0] = 0x00;
+		packet->data[1] = 0x01;
+		packet->data[2] = 0x0F;
+		packet->data[3] = 0xC0;
+		packet->data[4] = 0x00;
+		packet->data[5] = strong / 256;
+		packet->data[6] = weak / 256;
+		packet->data[7] = 0x00;
+		packet->data[8] = 0x00;
+		packet->data[9] = 0x00;
+		packet->data[10] = 0x00;
+		packet->data[11] = 0x00;
+		packet->len = 12;
+		packet->pending = true;
 		break;
 
 	case XTYPE_XBOXONE:
-		xpad->odata[0] = 0x09; /* activate rumble */
-		xpad->odata[1] = 0x08;
-		xpad->odata[2] = 0x00;
-		xpad->odata[3] = 0x08; /* continuous effect */
-		xpad->odata[4] = 0x00; /* simple rumble mode */
-		xpad->odata[5] = 0x03; /* L and R actuator only */
-		xpad->odata[6] = 0x00; /* TODO: LT actuator */
-		xpad->odata[7] = 0x00; /* TODO: RT actuator */
-		xpad->odata[8] = strong / 256;	/* left actuator */
-		xpad->odata[9] = weak / 256;	/* right actuator */
-		xpad->odata[10] = 0x80;	/* length of pulse */
-		xpad->odata[11] = 0x00;	/* stop period of pulse */
-		xpad->irq_out->transfer_buffer_length = 12;
+		packet->data[0] = 0x09; /* activate rumble */
+		packet->data[1] = 0x08;
+		packet->data[2] = 0x00;
+		packet->data[3] = 0x08; /* continuous effect */
+		packet->data[4] = 0x00; /* simple rumble mode */
+		packet->data[5] = 0x03; /* L and R actuator only */
+		packet->data[6] = 0x00; /* TODO: LT actuator */
+		packet->data[7] = 0x00; /* TODO: RT actuator */
+		packet->data[8] = strong / 256;	/* left actuator */
+		packet->data[9] = weak / 256;	/* right actuator */
+		packet->data[10] = 0x80;	/* length of pulse */
+		packet->data[11] = 0x00;	/* stop period of pulse */
+		packet->len = 12;
+		packet->pending = true;
 		break;
 
 	default:
 		dev_dbg(&xpad->dev->dev,
 			"%s - rumble command sent to unsupported xpad type: %d\n",
 			__func__, xpad->xtype);
-		return -EINVAL;
+		retval = -EINVAL;
+		goto out;
 	}
 
-	return usb_submit_urb(xpad->irq_out, GFP_ATOMIC);
+	retval = xpad_try_sending_next_out_packet(xpad);
+
+out:
+	spin_unlock_irqrestore(&xpad->odata_lock, flags);
+	return retval;
 }
 
 static int xpad_init_ff(struct usb_xpad *xpad)
@@ -921,36 +1042,44 @@ struct xpad_led {
  */
 static void xpad_send_led_command(struct usb_xpad *xpad, int command)
 {
+	struct xpad_output_packet *packet =
+			&xpad->out_packets[XPAD_OUT_LED_IDX];
+	unsigned long flags;
+
 	command %= 16;
 
-	mutex_lock(&xpad->odata_mutex);
+	spin_lock_irqsave(&xpad->odata_lock, flags);
 
 	switch (xpad->xtype) {
 	case XTYPE_XBOX360:
-		xpad->odata[0] = 0x01;
-		xpad->odata[1] = 0x03;
-		xpad->odata[2] = command;
-		xpad->irq_out->transfer_buffer_length = 3;
+		packet->data[0] = 0x01;
+		packet->data[1] = 0x03;
+		packet->data[2] = command;
+		packet->len = 3;
+		packet->pending = true;
 		break;
+
 	case XTYPE_XBOX360W:
-		xpad->odata[0] = 0x00;
-		xpad->odata[1] = 0x00;
-		xpad->odata[2] = 0x08;
-		xpad->odata[3] = 0x40 + command;
-		xpad->odata[4] = 0x00;
-		xpad->odata[5] = 0x00;
-		xpad->odata[6] = 0x00;
-		xpad->odata[7] = 0x00;
-		xpad->odata[8] = 0x00;
-		xpad->odata[9] = 0x00;
-		xpad->odata[10] = 0x00;
-		xpad->odata[11] = 0x00;
-		xpad->irq_out->transfer_buffer_length = 12;
+		packet->data[0] = 0x00;
+		packet->data[1] = 0x00;
+		packet->data[2] = 0x08;
+		packet->data[3] = 0x40 + command;
+		packet->data[4] = 0x00;
+		packet->data[5] = 0x00;
+		packet->data[6] = 0x00;
+		packet->data[7] = 0x00;
+		packet->data[8] = 0x00;
+		packet->data[9] = 0x00;
+		packet->data[10] = 0x00;
+		packet->data[11] = 0x00;
+		packet->len = 12;
+		packet->pending = true;
 		break;
 	}
 
-	usb_submit_urb(xpad->irq_out, GFP_KERNEL);
-	mutex_unlock(&xpad->odata_mutex);
+	xpad_try_sending_next_out_packet(xpad);
+
+	spin_unlock_irqrestore(&xpad->odata_lock, flags);
 }
 
 /*
@@ -1048,13 +1177,8 @@ static int xpad_open(struct input_dev *dev)
 	if (usb_submit_urb(xpad->irq_in, GFP_KERNEL))
 		return -EIO;
 
-	if (xpad->xtype == XTYPE_XBOXONE) {
-		/* Xbox one controller needs to be initialized. */
-		xpad->odata[0] = 0x05;
-		xpad->odata[1] = 0x20;
-		xpad->irq_out->transfer_buffer_length = 2;
-		return usb_submit_urb(xpad->irq_out, GFP_KERNEL);
-	}
+	if (xpad->xtype == XTYPE_XBOXONE)
+		return xpad_start_xbox_one(xpad);
 
 	return 0;
 }
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index a159529f9d53..c5f1757ac61d 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -41,6 +41,7 @@
 
 #define ITS_FLAGS_CMDQ_NEEDS_FLUSHING		(1ULL << 0)
 #define ITS_FLAGS_WORKAROUND_CAVIUM_22375	(1ULL << 1)
+#define ITS_FLAGS_WORKAROUND_CAVIUM_23144	(1ULL << 2)
 
 #define RDIST_FLAGS_PROPBASE_NEEDS_FLUSHING	(1 << 0)
 
@@ -71,6 +72,7 @@ struct its_node {
 	struct list_head	its_device_list;
 	u64			flags;
 	u32			ite_size;
+	int			numa_node;
 };
 
 #define ITS_ITT_ALIGN		SZ_256
@@ -600,11 +602,23 @@ static void its_unmask_irq(struct irq_data *d)
 static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {
-	unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
+	unsigned int cpu;
+	const struct cpumask *cpu_mask = cpu_online_mask;
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	struct its_collection *target_col;
 	u32 id = its_get_event_id(d);
 
+       /* lpi cannot be routed to a redistributor that is on a foreign node */
+	if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) {
+		if (its_dev->its->numa_node >= 0) {
+			cpu_mask = cpumask_of_node(its_dev->its->numa_node);
+			if (!cpumask_intersects(mask_val, cpu_mask))
+				return -EINVAL;
+		}
+	}
+
+	cpu = cpumask_any_and(mask_val, cpu_mask);
+
 	if (cpu >= nr_cpu_ids)
 		return -EINVAL;
 
@@ -1081,6 +1095,16 @@ static void its_cpu_init_collection(void)
 	list_for_each_entry(its, &its_nodes, entry) {
 		u64 target;
 
+		/* avoid cross node collections and its mapping */
+		if (its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) {
+			struct device_node *cpu_node;
+
+			cpu_node = of_get_cpu_node(cpu, NULL);
+			if (its->numa_node != NUMA_NO_NODE &&
+				its->numa_node != of_node_to_nid(cpu_node))
+				continue;
+		}
+
 		/*
 		 * We now have to bind each collection to its target
 		 * redistributor.
@@ -1308,9 +1332,14 @@ static void its_irq_domain_activate(struct irq_domain *domain,
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	u32 event = its_get_event_id(d);
+	const struct cpumask *cpu_mask = cpu_online_mask;
+
+	/* get the cpu_mask of local node */
+	if (its_dev->its->numa_node >= 0)
+		cpu_mask = cpumask_of_node(its_dev->its->numa_node);
 
 	/* Bind the LPI to the first possible CPU */
-	its_dev->event_map.col_map[event] = cpumask_first(cpu_online_mask);
+	its_dev->event_map.col_map[event] = cpumask_first(cpu_mask);
 
 	/* Map the GIC IRQ and event to the device */
 	its_send_mapvi(its_dev, d->hwirq, event);
@@ -1400,6 +1429,13 @@ static void __maybe_unused its_enable_quirk_cavium_22375(void *data)
 	its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_22375;
 }
 
+static void __maybe_unused its_enable_quirk_cavium_23144(void *data)
+{
+	struct its_node *its = data;
+
+	its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_23144;
+}
+
 static const struct gic_quirk its_quirks[] = {
 #ifdef CONFIG_CAVIUM_ERRATUM_22375
 	{
@@ -1409,6 +1445,14 @@ static const struct gic_quirk its_quirks[] = {
 		.init	= its_enable_quirk_cavium_22375,
 	},
 #endif
+#ifdef CONFIG_CAVIUM_ERRATUM_23144
+	{
+		.desc	= "ITS: Cavium erratum 23144",
+		.iidr	= 0xa100034c,	/* ThunderX pass 1.x */
+		.mask	= 0xffff0fff,
+		.init	= its_enable_quirk_cavium_23144,
+	},
+#endif
 	{
 	}
 };
@@ -1470,6 +1514,7 @@ static int its_probe(struct device_node *node, struct irq_domain *parent)
 	its->base = its_base;
 	its->phys_base = res.start;
 	its->ite_size = ((readl_relaxed(its_base + GITS_TYPER) >> 4) & 0xf) + 1;
+	its->numa_node = of_node_to_nid(node);
 
 	its->cmd_base = kzalloc(ITS_CMD_QUEUE_SZ, GFP_KERNEL);
 	if (!its->cmd_base) {
diff --git a/drivers/lightnvm/gennvm.c b/drivers/lightnvm/gennvm.c
index a54b339951a3..2a96ff6923f0 100644
--- a/drivers/lightnvm/gennvm.c
+++ b/drivers/lightnvm/gennvm.c
@@ -89,6 +89,7 @@ static int gennvm_block_bb(struct ppa_addr ppa, int nr_blocks, u8 *blks,
 
 		list_move_tail(&blk->list, &lun->bb_list);
 		lun->vlun.nr_bad_blocks++;
+		lun->vlun.nr_free_blocks--;
 	}
 
 	return 0;
@@ -345,7 +346,7 @@ static void gennvm_generic_to_addr_mode(struct nvm_dev *dev, struct nvm_rq *rqd)
 static int gennvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
 {
 	if (!dev->ops->submit_io)
-		return 0;
+		return -ENODEV;
 
 	/* Convert address space */
 	gennvm_generic_to_addr_mode(dev, rqd);
diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c
index 134e4faba482..a9859489acf6 100644
--- a/drivers/lightnvm/rrpc.c
+++ b/drivers/lightnvm/rrpc.c
@@ -287,6 +287,8 @@ static int rrpc_move_valid_pages(struct rrpc *rrpc, struct rrpc_block *rblk)
 	}
 
 	page = mempool_alloc(rrpc->page_pool, GFP_NOIO);
+	if (!page)
+		return -ENOMEM;
 
 	while ((slot = find_first_zero_bit(rblk->invalid_pages,
 					    nr_pgs_per_blk)) < nr_pgs_per_blk) {
@@ -427,7 +429,7 @@ static void rrpc_lun_gc(struct work_struct *work)
 	if (nr_blocks_need < rrpc->nr_luns)
 		nr_blocks_need = rrpc->nr_luns;
 
-	spin_lock(&lun->lock);
+	spin_lock(&rlun->lock);
 	while (nr_blocks_need > lun->nr_free_blocks &&
 					!list_empty(&rlun->prio_list)) {
 		struct rrpc_block *rblock = block_prio_find_max(rlun);
@@ -436,16 +438,16 @@ static void rrpc_lun_gc(struct work_struct *work)
 		if (!rblock->nr_invalid_pages)
 			break;
 
+		gcb = mempool_alloc(rrpc->gcb_pool, GFP_ATOMIC);
+		if (!gcb)
+			break;
+
 		list_del_init(&rblock->prio);
 
 		BUG_ON(!block_is_full(rrpc, rblock));
 
 		pr_debug("rrpc: selected block '%lu' for GC\n", block->id);
 
-		gcb = mempool_alloc(rrpc->gcb_pool, GFP_ATOMIC);
-		if (!gcb)
-			break;
-
 		gcb->rrpc = rrpc;
 		gcb->rblk = rblock;
 		INIT_WORK(&gcb->ws_gc, rrpc_block_gc);
@@ -454,7 +456,7 @@ static void rrpc_lun_gc(struct work_struct *work)
 
 		nr_blocks_need--;
 	}
-	spin_unlock(&lun->lock);
+	spin_unlock(&rlun->lock);
 
 	/* TODO: Hint that request queue can be started again */
 }
@@ -650,11 +652,12 @@ static int rrpc_end_io(struct nvm_rq *rqd, int error)
 	if (bio_data_dir(rqd->bio) == WRITE)
 		rrpc_end_io_write(rrpc, rrqd, laddr, npages);
 
+	bio_put(rqd->bio);
+
 	if (rrqd->flags & NVM_IOTYPE_GC)
 		return 0;
 
 	rrpc_unlock_rq(rrpc, rqd);
-	bio_put(rqd->bio);
 
 	if (npages > 1)
 		nvm_dev_dma_free(rrpc->dev, rqd->ppa_list, rqd->dma_ppa_list);
@@ -841,6 +844,13 @@ static int rrpc_submit_io(struct rrpc *rrpc, struct bio *bio,
 	err = nvm_submit_io(rrpc->dev, rqd);
 	if (err) {
 		pr_err("rrpc: I/O submission failed: %d\n", err);
+		bio_put(bio);
+		if (!(flags & NVM_IOTYPE_GC)) {
+			rrpc_unlock_rq(rrpc, rqd);
+			if (rqd->nr_pages > 1)
+				nvm_dev_dma_free(rrpc->dev,
+			rqd->ppa_list, rqd->dma_ppa_list);
+		}
 		return NVM_IO_ERR;
 	}
 
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index a296425a7270..3d5c0ba13181 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1818,7 +1818,7 @@ static int cache_alloc(struct cache_sb *sb, struct cache *ca)
 	free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;
 
 	if (!init_fifo(&ca->free[RESERVE_BTREE], 8, GFP_KERNEL) ||
-	    !init_fifo(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
+	    !init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
 	    !init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) ||
 	    !init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) ||
 	    !init_fifo(&ca->free_inc,	free << 2, GFP_KERNEL) ||
diff --git a/drivers/media/dvb-frontends/Kconfig b/drivers/media/dvb-frontends/Kconfig
index 292c9479bb75..310e4b8beae8 100644
--- a/drivers/media/dvb-frontends/Kconfig
+++ b/drivers/media/dvb-frontends/Kconfig
@@ -264,7 +264,7 @@ config DVB_MB86A16
 config DVB_TDA10071
 	tristate "NXP TDA10071"
 	depends on DVB_CORE && I2C
-	select REGMAP
+	select REGMAP_I2C
 	default m if !MEDIA_SUBDRV_AUTOSELECT
 	help
 	  Say Y when you want to support this frontend.
diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index d11fd6ac2df0..5cefca95734e 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -148,6 +148,26 @@ static struct uvc_format_desc uvc_fmts[] = {
 		.guid		= UVC_GUID_FORMAT_H264,
 		.fcc		= V4L2_PIX_FMT_H264,
 	},
+	{
+		.name		= "Greyscale 8 L/R (Y8I)",
+		.guid		= UVC_GUID_FORMAT_Y8I,
+		.fcc		= V4L2_PIX_FMT_Y8I,
+	},
+	{
+		.name		= "Greyscale 12 L/R (Y12I)",
+		.guid		= UVC_GUID_FORMAT_Y12I,
+		.fcc		= V4L2_PIX_FMT_Y12I,
+	},
+	{
+		.name		= "Depth data 16-bit (Z16)",
+		.guid		= UVC_GUID_FORMAT_Z16,
+		.fcc		= V4L2_PIX_FMT_Z16,
+	},
+	{
+		.name		= "Bayer 10-bit (SRGGB10P)",
+		.guid		= UVC_GUID_FORMAT_RW10,
+		.fcc		= V4L2_PIX_FMT_SRGGB10P,
+	},
 };
 
 /* ------------------------------------------------------------------------
diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h
index f0f2391e1b43..7e4d3eea371b 100644
--- a/drivers/media/usb/uvc/uvcvideo.h
+++ b/drivers/media/usb/uvc/uvcvideo.h
@@ -119,6 +119,18 @@
 #define UVC_GUID_FORMAT_H264 \
 	{ 'H',  '2',  '6',  '4', 0x00, 0x00, 0x10, 0x00, \
 	 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
+#define UVC_GUID_FORMAT_Y8I \
+	{ 'Y',  '8',  'I',  ' ', 0x00, 0x00, 0x10, 0x00, \
+	 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
+#define UVC_GUID_FORMAT_Y12I \
+	{ 'Y',  '1',  '2',  'I', 0x00, 0x00, 0x10, 0x00, \
+	 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
+#define UVC_GUID_FORMAT_Z16 \
+	{ 'Z',  '1',  '6',  ' ', 0x00, 0x00, 0x10, 0x00, \
+	 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
+#define UVC_GUID_FORMAT_RW10 \
+	{ 'R',  'W',  '1',  '0', 0x00, 0x00, 0x10, 0x00, \
+	 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
 
 /* ------------------------------------------------------------------------
  * Driver specific constants.
diff --git a/drivers/misc/cxl/Makefile b/drivers/misc/cxl/Makefile
index 6982f603fadc..ab6f392d3504 100644
--- a/drivers/misc/cxl/Makefile
+++ b/drivers/misc/cxl/Makefile
@@ -1,4 +1,4 @@
-ccflags-y := -Werror -Wno-unused-const-variable
+ccflags-y := -Werror $(call cc-disable-warning, unused-const-variable)
 
 cxl-y				+= main.o file.o irq.o fault.o native.o
 cxl-y				+= context.o sysfs.o debugfs.o pci.o trace.o
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 103baf0e0c5b..ea3eeb7011e1 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -25,7 +25,6 @@ struct cxl_context *cxl_dev_context_init(struct pci_dev *dev)
 
 	afu = cxl_pci_to_afu(dev);
 
-	get_device(&afu->dev);
 	ctx = cxl_context_alloc();
 	if (IS_ERR(ctx)) {
 		rc = PTR_ERR(ctx);
@@ -61,7 +60,6 @@ err_mapping:
 err_ctx:
 	kfree(ctx);
 err_dev:
-	put_device(&afu->dev);
 	return ERR_PTR(rc);
 }
 EXPORT_SYMBOL_GPL(cxl_dev_context_init);
@@ -87,8 +85,6 @@ int cxl_release_context(struct cxl_context *ctx)
 	if (ctx->status >= STARTED)
 		return -EBUSY;
 
-	put_device(&ctx->afu->dev);
-
 	cxl_context_free(ctx);
 
 	return 0;
@@ -176,7 +172,7 @@ int cxl_start_context(struct cxl_context *ctx, u64 wed,
 
 	if (task) {
 		ctx->pid = get_task_pid(task, PIDTYPE_PID);
-		get_pid(ctx->pid);
+		ctx->glpid = get_task_pid(task->group_leader, PIDTYPE_PID);
 		kernel = false;
 	}
 
diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c
index 2faa1270d085..262b88eac414 100644
--- a/drivers/misc/cxl/context.c
+++ b/drivers/misc/cxl/context.c
@@ -42,7 +42,7 @@ int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master,
 	spin_lock_init(&ctx->sste_lock);
 	ctx->afu = afu;
 	ctx->master = master;
-	ctx->pid = NULL; /* Set in start work ioctl */
+	ctx->pid = ctx->glpid = NULL; /* Set in start work ioctl */
 	mutex_init(&ctx->mapping_lock);
 	ctx->mapping = mapping;
 
@@ -97,6 +97,12 @@ int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master,
 	ctx->pe = i;
 	ctx->elem = &ctx->afu->spa[i];
 	ctx->pe_inserted = false;
+
+	/*
+	 * take a ref on the afu so that it stays alive at-least till
+	 * this context is reclaimed inside reclaim_ctx.
+	 */
+	cxl_afu_get(afu);
 	return 0;
 }
 
@@ -211,7 +217,11 @@ int __detach_context(struct cxl_context *ctx)
 	WARN_ON(cxl_detach_process(ctx) &&
 		cxl_adapter_link_ok(ctx->afu->adapter));
 	flush_work(&ctx->fault_work); /* Only needed for dedicated process */
+
+	/* release the reference to the group leader and mm handling pid */
 	put_pid(ctx->pid);
+	put_pid(ctx->glpid);
+
 	cxl_ctx_put();
 	return 0;
 }
@@ -278,6 +288,9 @@ static void reclaim_ctx(struct rcu_head *rcu)
 	if (ctx->irq_bitmap)
 		kfree(ctx->irq_bitmap);
 
+	/* Drop ref to the afu device taken during cxl_context_init */
+	cxl_afu_put(ctx->afu);
+
 	kfree(ctx);
 }
 
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index 0cfb9c129f27..a521bc72cec2 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -403,6 +403,18 @@ struct cxl_afu {
 	bool enabled;
 };
 
+/* AFU refcount management */
+static inline struct cxl_afu *cxl_afu_get(struct cxl_afu *afu)
+{
+
+	return (get_device(&afu->dev) == NULL) ? NULL : afu;
+}
+
+static inline void  cxl_afu_put(struct cxl_afu *afu)
+{
+	put_device(&afu->dev);
+}
+
 
 struct cxl_irq_name {
 	struct list_head list;
@@ -433,6 +445,9 @@ struct cxl_context {
 	unsigned int sst_size, sst_lru;
 
 	wait_queue_head_t wq;
+	/* pid of the group leader associated with the pid */
+	struct pid *glpid;
+	/* use mm context associated with this pid for ds faults */
 	struct pid *pid;
 	spinlock_t lock; /* Protects pending_irq_mask, pending_fault and fault_addr */
 	/* Only used in PR mode */
diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c
index 25a5418c55cb..81c3f75b7330 100644
--- a/drivers/misc/cxl/fault.c
+++ b/drivers/misc/cxl/fault.c
@@ -166,13 +166,92 @@ static void cxl_handle_page_fault(struct cxl_context *ctx,
 	cxl_ack_irq(ctx, CXL_PSL_TFC_An_R, 0);
 }
 
+/*
+ * Returns the mm_struct corresponding to the context ctx via ctx->pid
+ * In case the task has exited we use the task group leader accessible
+ * via ctx->glpid to find the next task in the thread group that has a
+ * valid  mm_struct associated with it. If a task with valid mm_struct
+ * is found the ctx->pid is updated to use the task struct for subsequent
+ * translations. In case no valid mm_struct is found in the task group to
+ * service the fault a NULL is returned.
+ */
+static struct mm_struct *get_mem_context(struct cxl_context *ctx)
+{
+	struct task_struct *task = NULL;
+	struct mm_struct *mm = NULL;
+	struct pid *old_pid = ctx->pid;
+
+	if (old_pid == NULL) {
+		pr_warn("%s: Invalid context for pe=%d\n",
+			 __func__, ctx->pe);
+		return NULL;
+	}
+
+	task = get_pid_task(old_pid, PIDTYPE_PID);
+
+	/*
+	 * pid_alive may look racy but this saves us from costly
+	 * get_task_mm when the task is a zombie. In worst case
+	 * we may think a task is alive, which is about to die
+	 * but get_task_mm will return NULL.
+	 */
+	if (task != NULL && pid_alive(task))
+		mm = get_task_mm(task);
+
+	/* release the task struct that was taken earlier */
+	if (task)
+		put_task_struct(task);
+	else
+		pr_devel("%s: Context owning pid=%i for pe=%i dead\n",
+			__func__, pid_nr(old_pid), ctx->pe);
+
+	/*
+	 * If we couldn't find the mm context then use the group
+	 * leader to iterate over the task group and find a task
+	 * that gives us mm_struct.
+	 */
+	if (unlikely(mm == NULL && ctx->glpid != NULL)) {
+
+		rcu_read_lock();
+		task = pid_task(ctx->glpid, PIDTYPE_PID);
+		if (task)
+			do {
+				mm = get_task_mm(task);
+				if (mm) {
+					ctx->pid = get_task_pid(task,
+								PIDTYPE_PID);
+					break;
+				}
+				task = next_thread(task);
+			} while (task && !thread_group_leader(task));
+		rcu_read_unlock();
+
+		/* check if we switched pid */
+		if (ctx->pid != old_pid) {
+			if (mm)
+				pr_devel("%s:pe=%i switch pid %i->%i\n",
+					 __func__, ctx->pe, pid_nr(old_pid),
+					 pid_nr(ctx->pid));
+			else
+				pr_devel("%s:Cannot find mm for pid=%i\n",
+					 __func__, pid_nr(old_pid));
+
+			/* drop the reference to older pid */
+			put_pid(old_pid);
+		}
+	}
+
+	return mm;
+}
+
+
+
 void cxl_handle_fault(struct work_struct *fault_work)
 {
 	struct cxl_context *ctx =
 		container_of(fault_work, struct cxl_context, fault_work);
 	u64 dsisr = ctx->dsisr;
 	u64 dar = ctx->dar;
-	struct task_struct *task = NULL;
 	struct mm_struct *mm = NULL;
 
 	if (cxl_p2n_read(ctx->afu, CXL_PSL_DSISR_An) != dsisr ||
@@ -195,17 +274,17 @@ void cxl_handle_fault(struct work_struct *fault_work)
 		"DSISR: %#llx DAR: %#llx\n", ctx->pe, dsisr, dar);
 
 	if (!ctx->kernel) {
-		if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
-			pr_devel("cxl_handle_fault unable to get task %i\n",
-				 pid_nr(ctx->pid));
+
+		mm = get_mem_context(ctx);
+		/* indicates all the thread in task group have exited */
+		if (mm == NULL) {
+			pr_devel("%s: unable to get mm for pe=%d pid=%i\n",
+				 __func__, ctx->pe, pid_nr(ctx->pid));
 			cxl_ack_ae(ctx);
 			return;
-		}
-		if (!(mm = get_task_mm(task))) {
-			pr_devel("cxl_handle_fault unable to get mm %i\n",
-				 pid_nr(ctx->pid));
-			cxl_ack_ae(ctx);
-			goto out;
+		} else {
+			pr_devel("Handling page fault for pe=%d pid=%i\n",
+				 ctx->pe, pid_nr(ctx->pid));
 		}
 	}
 
@@ -218,33 +297,22 @@ void cxl_handle_fault(struct work_struct *fault_work)
 
 	if (mm)
 		mmput(mm);
-out:
-	if (task)
-		put_task_struct(task);
 }
 
 static void cxl_prefault_one(struct cxl_context *ctx, u64 ea)
 {
-	int rc;
-	struct task_struct *task;
 	struct mm_struct *mm;
 
-	if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
-		pr_devel("cxl_prefault_one unable to get task %i\n",
-			 pid_nr(ctx->pid));
-		return;
-	}
-	if (!(mm = get_task_mm(task))) {
+	mm = get_mem_context(ctx);
+	if (mm == NULL) {
 		pr_devel("cxl_prefault_one unable to get mm %i\n",
 			 pid_nr(ctx->pid));
-		put_task_struct(task);
 		return;
 	}
 
-	rc = cxl_fault_segment(ctx, mm, ea);
+	cxl_fault_segment(ctx, mm, ea);
 
 	mmput(mm);
-	put_task_struct(task);
 }
 
 static u64 next_segment(u64 ea, u64 vsid)
@@ -263,18 +331,13 @@ static void cxl_prefault_vma(struct cxl_context *ctx)
 	struct copro_slb slb;
 	struct vm_area_struct *vma;
 	int rc;
-	struct task_struct *task;
 	struct mm_struct *mm;
 
-	if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
-		pr_devel("cxl_prefault_vma unable to get task %i\n",
-			 pid_nr(ctx->pid));
-		return;
-	}
-	if (!(mm = get_task_mm(task))) {
+	mm = get_mem_context(ctx);
+	if (mm == NULL) {
 		pr_devel("cxl_prefault_vm unable to get mm %i\n",
 			 pid_nr(ctx->pid));
-		goto out1;
+		return;
 	}
 
 	down_read(&mm->mmap_sem);
@@ -295,8 +358,6 @@ static void cxl_prefault_vma(struct cxl_context *ctx)
 	up_read(&mm->mmap_sem);
 
 	mmput(mm);
-out1:
-	put_task_struct(task);
 }
 
 void cxl_prefault(struct cxl_context *ctx, u64 wed)
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
index 7ccd2998be92..783337d22f36 100644
--- a/drivers/misc/cxl/file.c
+++ b/drivers/misc/cxl/file.c
@@ -67,7 +67,13 @@ static int __afu_open(struct inode *inode, struct file *file, bool master)
 		spin_unlock(&adapter->afu_list_lock);
 		goto err_put_adapter;
 	}
-	get_device(&afu->dev);
+
+	/*
+	 * taking a ref to the afu so that it doesn't go away
+	 * for rest of the function. This ref is released before
+	 * we return.
+	 */
+	cxl_afu_get(afu);
 	spin_unlock(&adapter->afu_list_lock);
 
 	if (!afu->current_mode)
@@ -90,13 +96,12 @@ static int __afu_open(struct inode *inode, struct file *file, bool master)
 	file->private_data = ctx;
 	cxl_ctx_get();
 
-	/* Our ref on the AFU will now hold the adapter */
-	put_device(&adapter->dev);
-
-	return 0;
+	/* indicate success */
+	rc = 0;
 
 err_put_afu:
-	put_device(&afu->dev);
+	/* release the ref taken earlier */
+	cxl_afu_put(afu);
 err_put_adapter:
 	put_device(&adapter->dev);
 	return rc;
@@ -131,8 +136,6 @@ int afu_release(struct inode *inode, struct file *file)
 		mutex_unlock(&ctx->mapping_lock);
 	}
 
-	put_device(&ctx->afu->dev);
-
 	/*
 	 * At this this point all bottom halfs have finished and we should be
 	 * getting no more IRQs from the hardware for this context.  Once it's
@@ -198,8 +201,12 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
 	 * where a process (master, some daemon, etc) has opened the chardev on
 	 * behalf of another process, so the AFU's mm gets bound to the process
 	 * that performs this ioctl and not the process that opened the file.
+	 * Also we grab the PID of the group leader so that if the task that
+	 * has performed the attach operation exits the mm context of the
+	 * process is still accessible.
 	 */
-	ctx->pid = get_pid(get_task_pid(current, PIDTYPE_PID));
+	ctx->pid = get_task_pid(current, PIDTYPE_PID);
+	ctx->glpid = get_task_pid(current->group_leader, PIDTYPE_PID);
 
 	trace_cxl_attach(ctx, work.work_element_descriptor, work.num_interrupts, amr);
 
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index be2c8e248e2e..0c6c17a1c59e 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -138,6 +138,7 @@ static const struct pci_device_id cxl_pci_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x0477), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x044b), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x04cf), },
+	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x0601), },
 	{ PCI_DEVICE_CLASS(0x120000, ~0), },
 
 	{ }
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 1a802af827ed..552a34dc4f82 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -492,7 +492,7 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 		host->align_buffer, host->align_buffer_sz, direction);
 	if (dma_mapping_error(mmc_dev(host->mmc), host->align_addr))
 		goto fail;
-	BUG_ON(host->align_addr & host->align_mask);
+	BUG_ON(host->align_addr & SDHCI_ADMA2_MASK);
 
 	host->sg_count = sdhci_pre_dma_transfer(host, data);
 	if (host->sg_count < 0)
@@ -514,8 +514,8 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 		 * the (up to three) bytes that screw up the
 		 * alignment.
 		 */
-		offset = (host->align_sz - (addr & host->align_mask)) &
-			 host->align_mask;
+		offset = (SDHCI_ADMA2_ALIGN - (addr & SDHCI_ADMA2_MASK)) &
+			 SDHCI_ADMA2_MASK;
 		if (offset) {
 			if (data->flags & MMC_DATA_WRITE) {
 				buffer = sdhci_kmap_atomic(sg, &flags);
@@ -529,8 +529,8 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 
 			BUG_ON(offset > 65536);
 
-			align += host->align_sz;
-			align_addr += host->align_sz;
+			align += SDHCI_ADMA2_ALIGN;
+			align_addr += SDHCI_ADMA2_ALIGN;
 
 			desc += host->desc_sz;
 
@@ -611,7 +611,7 @@ static void sdhci_adma_table_post(struct sdhci_host *host,
 	/* Do a quick scan of the SG list for any unaligned mappings */
 	has_unaligned = false;
 	for_each_sg(data->sg, sg, host->sg_count, i)
-		if (sg_dma_address(sg) & host->align_mask) {
+		if (sg_dma_address(sg) & SDHCI_ADMA2_MASK) {
 			has_unaligned = true;
 			break;
 		}
@@ -623,15 +623,15 @@ static void sdhci_adma_table_post(struct sdhci_host *host,
 		align = host->align_buffer;
 
 		for_each_sg(data->sg, sg, host->sg_count, i) {
-			if (sg_dma_address(sg) & host->align_mask) {
-				size = host->align_sz -
-				       (sg_dma_address(sg) & host->align_mask);
+			if (sg_dma_address(sg) & SDHCI_ADMA2_MASK) {
+				size = SDHCI_ADMA2_ALIGN -
+				       (sg_dma_address(sg) & SDHCI_ADMA2_MASK);
 
 				buffer = sdhci_kmap_atomic(sg, &flags);
 				memcpy(buffer, align, size);
 				sdhci_kunmap_atomic(buffer, &flags);
 
-				align += host->align_sz;
+				align += SDHCI_ADMA2_ALIGN;
 			}
 		}
 	}
@@ -1315,7 +1315,9 @@ static void sdhci_set_power(struct sdhci_host *host, unsigned char mode,
 			pwr = SDHCI_POWER_330;
 			break;
 		default:
-			BUG();
+			WARN(1, "%s: Invalid vdd %#x\n",
+			     mmc_hostname(host->mmc), vdd);
+			break;
 		}
 	}
 
@@ -2983,24 +2985,17 @@ int sdhci_add_host(struct sdhci_host *host)
 		if (host->flags & SDHCI_USE_64_BIT_DMA) {
 			host->adma_table_sz = (SDHCI_MAX_SEGS * 2 + 1) *
 					      SDHCI_ADMA2_64_DESC_SZ;
-			host->align_buffer_sz = SDHCI_MAX_SEGS *
-						SDHCI_ADMA2_64_ALIGN;
 			host->desc_sz = SDHCI_ADMA2_64_DESC_SZ;
-			host->align_sz = SDHCI_ADMA2_64_ALIGN;
-			host->align_mask = SDHCI_ADMA2_64_ALIGN - 1;
 		} else {
 			host->adma_table_sz = (SDHCI_MAX_SEGS * 2 + 1) *
 					      SDHCI_ADMA2_32_DESC_SZ;
-			host->align_buffer_sz = SDHCI_MAX_SEGS *
-						SDHCI_ADMA2_32_ALIGN;
 			host->desc_sz = SDHCI_ADMA2_32_DESC_SZ;
-			host->align_sz = SDHCI_ADMA2_32_ALIGN;
-			host->align_mask = SDHCI_ADMA2_32_ALIGN - 1;
 		}
 		host->adma_table = dma_alloc_coherent(mmc_dev(mmc),
 						      host->adma_table_sz,
 						      &host->adma_addr,
 						      GFP_KERNEL);
+		host->align_buffer_sz = SDHCI_MAX_SEGS * SDHCI_ADMA2_ALIGN;
 		host->align_buffer = kmalloc(host->align_buffer_sz, GFP_KERNEL);
 		if (!host->adma_table || !host->align_buffer) {
 			if (host->adma_table)
@@ -3014,7 +3009,7 @@ int sdhci_add_host(struct sdhci_host *host)
 			host->flags &= ~SDHCI_USE_ADMA;
 			host->adma_table = NULL;
 			host->align_buffer = NULL;
-		} else if (host->adma_addr & host->align_mask) {
+		} else if (host->adma_addr & (SDHCI_ADMA2_DESC_ALIGN - 1)) {
 			pr_warn("%s: unable to allocate aligned ADMA descriptor\n",
 				mmc_hostname(mmc));
 			host->flags &= ~SDHCI_USE_ADMA;
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 9c331ac5ad6b..0115e9907bf8 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -272,22 +272,27 @@
 /* ADMA2 32-bit DMA descriptor size */
 #define SDHCI_ADMA2_32_DESC_SZ	8
 
-/* ADMA2 32-bit DMA alignment */
-#define SDHCI_ADMA2_32_ALIGN	4
-
 /* ADMA2 32-bit descriptor */
 struct sdhci_adma2_32_desc {
 	__le16	cmd;
 	__le16	len;
 	__le32	addr;
-}  __packed __aligned(SDHCI_ADMA2_32_ALIGN);
+}  __packed __aligned(4);
+
+/* ADMA2 data alignment */
+#define SDHCI_ADMA2_ALIGN	4
+#define SDHCI_ADMA2_MASK	(SDHCI_ADMA2_ALIGN - 1)
+
+/*
+ * ADMA2 descriptor alignment.  Some controllers (e.g. Intel) require 8 byte
+ * alignment for the descriptor table even in 32-bit DMA mode.  Memory
+ * allocation is at least 8 byte aligned anyway, so just stipulate 8 always.
+ */
+#define SDHCI_ADMA2_DESC_ALIGN	8
 
 /* ADMA2 64-bit DMA descriptor size */
 #define SDHCI_ADMA2_64_DESC_SZ	12
 
-/* ADMA2 64-bit DMA alignment */
-#define SDHCI_ADMA2_64_ALIGN	8
-
 /*
  * ADMA2 64-bit descriptor. Note 12-byte descriptor can't always be 8-byte
  * aligned.
@@ -483,8 +488,6 @@ struct sdhci_host {
 	dma_addr_t align_addr;	/* Mapped bounce buffer */
 
 	unsigned int desc_sz;	/* ADMA descriptor size */
-	unsigned int align_sz;	/* ADMA alignment */
-	unsigned int align_mask;	/* ADMA alignment mask */
 
 	struct tasklet_struct finish_tasklet;	/* Tasklet structures */
 
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index b89504405b72..7445da218bd9 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -2526,7 +2526,7 @@ static void handle_timestamp(struct octeon_device *oct,
 
 	octeon_swap_8B_data(&resp->timestamp, 1);
 
-	if (unlikely((skb_shinfo(skb)->tx_flags | SKBTX_IN_PROGRESS) != 0)) {
+	if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS) != 0)) {
 		struct skb_shared_hwtstamps ts;
 		u64 ns = resp->timestamp;
 
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index 39ca6744a4e6..22471d283a95 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -116,6 +116,15 @@
 #define NIC_PF_INTR_ID_MBOX0		8
 #define NIC_PF_INTR_ID_MBOX1		9
 
+/* Minimum FIFO level before all packets for the CQ are dropped
+ *
+ * This value ensures that once a packet has been "accepted"
+ * for reception it will not get dropped due to non-availability
+ * of CQ descriptor. An errata in HW mandates this value to be
+ * atleast 0x100.
+ */
+#define NICPF_CQM_MIN_DROP_LEVEL       0x100
+
 /* Global timer for CQ timer thresh interrupts
  * Calculated for SCLK of 700Mhz
  * value written should be a 1/16th of what is expected
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 5f24d11cb16a..16baaafed26c 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -309,6 +309,7 @@ static void nic_set_lmac_vf_mapping(struct nicpf *nic)
 static void nic_init_hw(struct nicpf *nic)
 {
 	int i;
+	u64 cqm_cfg;
 
 	/* Enable NIC HW block */
 	nic_reg_write(nic, NIC_PF_CFG, 0x3);
@@ -345,6 +346,11 @@ static void nic_init_hw(struct nicpf *nic)
 	/* Enable VLAN ethertype matching and stripping */
 	nic_reg_write(nic, NIC_PF_RX_ETYPE_0_7,
 		      (2 << 19) | (ETYPE_ALG_VLAN_STRIP << 16) | ETH_P_8021Q);
+
+	/* Check if HW expected value is higher (could be in future chips) */
+	cqm_cfg = nic_reg_read(nic, NIC_PF_CQM_CFG);
+	if (cqm_cfg < NICPF_CQM_MIN_DROP_LEVEL)
+		nic_reg_write(nic, NIC_PF_CQM_CFG, NICPF_CQM_MIN_DROP_LEVEL);
 }
 
 /* Channel parse index configuration */
diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h
index dd536be20193..afb10e326b4f 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_reg.h
+++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h
@@ -21,7 +21,7 @@
 #define   NIC_PF_TCP_TIMER			(0x0060)
 #define   NIC_PF_BP_CFG				(0x0080)
 #define   NIC_PF_RRM_CFG			(0x0088)
-#define   NIC_PF_CQM_CF				(0x00A0)
+#define   NIC_PF_CQM_CFG			(0x00A0)
 #define   NIC_PF_CNM_CF				(0x00A8)
 #define   NIC_PF_CNM_STATUS			(0x00B0)
 #define   NIC_PF_CQ_AVG_CFG			(0x00C0)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index dde8dc720cd3..b7093b9cd1e8 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -566,8 +566,7 @@ static inline void nicvf_set_rxhash(struct net_device *netdev,
 
 static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 				  struct napi_struct *napi,
-				  struct cmp_queue *cq,
-				  struct cqe_rx_t *cqe_rx, int cqe_type)
+				  struct cqe_rx_t *cqe_rx)
 {
 	struct sk_buff *skb;
 	struct nicvf *nic = netdev_priv(netdev);
@@ -583,7 +582,7 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 	}
 
 	/* Check for errors */
-	err = nicvf_check_cqe_rx_errs(nic, cq, cqe_rx);
+	err = nicvf_check_cqe_rx_errs(nic, cqe_rx);
 	if (err && !cqe_rx->rb_cnt)
 		return;
 
@@ -674,8 +673,7 @@ loop:
 			   cq_idx, cq_desc->cqe_type);
 		switch (cq_desc->cqe_type) {
 		case CQE_TYPE_RX:
-			nicvf_rcv_pkt_handler(netdev, napi, cq,
-					      cq_desc, CQE_TYPE_RX);
+			nicvf_rcv_pkt_handler(netdev, napi, cq_desc);
 			work_done++;
 		break;
 		case CQE_TYPE_SEND:
@@ -1117,7 +1115,6 @@ int nicvf_stop(struct net_device *netdev)
 
 	/* Clear multiqset info */
 	nic->pnicvf = nic;
-	nic->sqs_count = 0;
 
 	return 0;
 }
@@ -1346,6 +1343,9 @@ void nicvf_update_stats(struct nicvf *nic)
 	drv_stats->tx_frames_ok = stats->tx_ucast_frames_ok +
 				  stats->tx_bcast_frames_ok +
 				  stats->tx_mcast_frames_ok;
+	drv_stats->rx_frames_ok = stats->rx_ucast_frames +
+				  stats->rx_bcast_frames +
+				  stats->rx_mcast_frames;
 	drv_stats->rx_drops = stats->rx_drop_red +
 			      stats->rx_drop_overrun;
 	drv_stats->tx_drops = stats->tx_drops;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index d1c217eaf417..912ee28ab58b 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -1414,16 +1414,12 @@ void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx)
 }
 
 /* Check for errors in the receive cmp.queue entry */
-int nicvf_check_cqe_rx_errs(struct nicvf *nic,
-			    struct cmp_queue *cq, struct cqe_rx_t *cqe_rx)
+int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
 {
 	struct nicvf_hw_stats *stats = &nic->hw_stats;
-	struct nicvf_drv_stats *drv_stats = &nic->drv_stats;
 
-	if (!cqe_rx->err_level && !cqe_rx->err_opcode) {
-		drv_stats->rx_frames_ok++;
+	if (!cqe_rx->err_level && !cqe_rx->err_opcode)
 		return 0;
-	}
 
 	if (netif_msg_rx_err(nic))
 		netdev_err(nic->netdev,
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
index 033e8306e91c..5652c612e20b 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
@@ -344,8 +344,7 @@ u64  nicvf_queue_reg_read(struct nicvf *nic,
 /* Stats */
 void nicvf_update_rq_stats(struct nicvf *nic, int rq_idx);
 void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx);
-int nicvf_check_cqe_rx_errs(struct nicvf *nic,
-			    struct cmp_queue *cq, struct cqe_rx_t *cqe_rx);
+int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx);
 int nicvf_check_cqe_tx_errs(struct nicvf *nic,
 			    struct cmp_queue *cq, struct cqe_send_t *cqe_tx);
 #endif /* NICVF_QUEUES_H */
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 9df26c2263bc..42718cc7d4e8 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -549,7 +549,9 @@ static int bgx_xaui_check_link(struct lmac *lmac)
 	}
 
 	/* Clear rcvflt bit (latching high) and read it back */
-	bgx_reg_modify(bgx, lmacid, BGX_SPUX_STATUS2, SPU_STATUS2_RCVFLT);
+	if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT)
+		bgx_reg_modify(bgx, lmacid,
+			       BGX_SPUX_STATUS2, SPU_STATUS2_RCVFLT);
 	if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT) {
 		dev_err(&bgx->pdev->dev, "Receive fault, retry training\n");
 		if (bgx->use_training) {
@@ -568,13 +570,6 @@ static int bgx_xaui_check_link(struct lmac *lmac)
 		return -1;
 	}
 
-	/* Wait for MAC RX to be ready */
-	if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_RX_CTL,
-			 SMU_RX_CTL_STATUS, true)) {
-		dev_err(&bgx->pdev->dev, "SMU RX link not okay\n");
-		return -1;
-	}
-
 	/* Wait for BGX RX to be idle */
 	if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_CTL, SMU_CTL_RX_IDLE, false)) {
 		dev_err(&bgx->pdev->dev, "SMU RX not idle\n");
@@ -587,29 +582,30 @@ static int bgx_xaui_check_link(struct lmac *lmac)
 		return -1;
 	}
 
-	if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT) {
-		dev_err(&bgx->pdev->dev, "Receive fault\n");
-		return -1;
-	}
-
-	/* Receive link is latching low. Force it high and verify it */
-	bgx_reg_modify(bgx, lmacid, BGX_SPUX_STATUS1, SPU_STATUS1_RCV_LNK);
-	if (bgx_poll_reg(bgx, lmacid, BGX_SPUX_STATUS1,
-			 SPU_STATUS1_RCV_LNK, false)) {
-		dev_err(&bgx->pdev->dev, "SPU receive link down\n");
-		return -1;
-	}
-
+	/* Clear receive packet disable */
 	cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_MISC_CONTROL);
 	cfg &= ~SPU_MISC_CTL_RX_DIS;
 	bgx_reg_write(bgx, lmacid, BGX_SPUX_MISC_CONTROL, cfg);
-	return 0;
+
+	/* Check for MAC RX faults */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_SMUX_RX_CTL);
+	/* 0 - Link is okay, 1 - Local fault, 2 - Remote fault */
+	cfg &= SMU_RX_CTL_STATUS;
+	if (!cfg)
+		return 0;
+
+	/* Rx local/remote fault seen.
+	 * Do lmac reinit to see if condition recovers
+	 */
+	bgx_lmac_xaui_init(bgx, lmacid, bgx->lmac_type);
+
+	return -1;
 }
 
 static void bgx_poll_for_link(struct work_struct *work)
 {
 	struct lmac *lmac;
-	u64 link;
+	u64 spu_link, smu_link;
 
 	lmac = container_of(work, struct lmac, dwork.work);
 
@@ -619,8 +615,11 @@ static void bgx_poll_for_link(struct work_struct *work)
 	bgx_poll_reg(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1,
 		     SPU_STATUS1_RCV_LNK, false);
 
-	link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1);
-	if (link & SPU_STATUS1_RCV_LNK) {
+	spu_link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1);
+	smu_link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SMUX_RX_CTL);
+
+	if ((spu_link & SPU_STATUS1_RCV_LNK) &&
+	    !(smu_link & SMU_RX_CTL_STATUS)) {
 		lmac->link_up = 1;
 		if (lmac->bgx->lmac_type == BGX_MODE_XLAUI)
 			lmac->last_speed = 40000;
@@ -634,9 +633,15 @@ static void bgx_poll_for_link(struct work_struct *work)
 	}
 
 	if (lmac->last_link != lmac->link_up) {
+		if (lmac->link_up) {
+			if (bgx_xaui_check_link(lmac)) {
+				/* Errors, clear link_up state */
+				lmac->link_up = 0;
+				lmac->last_speed = SPEED_UNKNOWN;
+				lmac->last_duplex = DUPLEX_UNKNOWN;
+			}
+		}
 		lmac->last_link = lmac->link_up;
-		if (lmac->link_up)
-			bgx_xaui_check_link(lmac);
 	}
 
 	queue_delayed_work(lmac->check_link, &lmac->dwork, HZ * 2);
@@ -708,7 +713,7 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
 static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid)
 {
 	struct lmac *lmac;
-	u64 cmrx_cfg;
+	u64 cfg;
 
 	lmac = &bgx->lmac[lmacid];
 	if (lmac->check_link) {
@@ -717,9 +722,33 @@ static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid)
 		destroy_workqueue(lmac->check_link);
 	}
 
-	cmrx_cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
-	cmrx_cfg &= ~(1 << 15);
-	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cmrx_cfg);
+	/* Disable packet reception */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+	cfg &= ~CMR_PKT_RX_EN;
+	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+
+	/* Give chance for Rx/Tx FIFO to get drained */
+	bgx_poll_reg(bgx, lmacid, BGX_CMRX_RX_FIFO_LEN, (u64)0x1FFF, true);
+	bgx_poll_reg(bgx, lmacid, BGX_CMRX_TX_FIFO_LEN, (u64)0x3FFF, true);
+
+	/* Disable packet transmission */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+	cfg &= ~CMR_PKT_TX_EN;
+	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+
+	/* Disable serdes lanes */
+        if (!lmac->is_sgmii)
+                bgx_reg_modify(bgx, lmacid,
+                               BGX_SPUX_CONTROL1, SPU_CTL_LOW_POWER);
+        else
+                bgx_reg_modify(bgx, lmacid,
+                               BGX_GMP_PCS_MRX_CTL, PCS_MRX_CTL_PWR_DN);
+
+	/* Disable LMAC */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+	cfg &= ~CMR_EN;
+	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+
 	bgx_flush_dmac_addrs(bgx, lmacid);
 
 	if ((bgx->lmac_type != BGX_MODE_XFI) &&
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index 149e179363a1..42010d2e5ddf 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -41,6 +41,7 @@
 #define BGX_CMRX_RX_STAT10		0xC0
 #define BGX_CMRX_RX_BP_DROP		0xC8
 #define BGX_CMRX_RX_DMAC_CTL		0x0E8
+#define BGX_CMRX_RX_FIFO_LEN		0x108
 #define BGX_CMR_RX_DMACX_CAM		0x200
 #define  RX_DMACX_CAM_EN			BIT_ULL(48)
 #define  RX_DMACX_CAM_LMACID(x)			(x << 49)
@@ -50,6 +51,7 @@
 #define BGX_CMR_CHAN_MSK_AND		0x450
 #define BGX_CMR_BIST_STATUS		0x460
 #define BGX_CMR_RX_LMACS		0x468
+#define BGX_CMRX_TX_FIFO_LEN		0x518
 #define BGX_CMRX_TX_STAT0		0x600
 #define BGX_CMRX_TX_STAT1		0x608
 #define BGX_CMRX_TX_STAT2		0x610
diff --git a/drivers/net/ethernet/intel/e1000/e1000.h b/drivers/net/ethernet/intel/e1000/e1000.h
index 69707108d23c..98fe5a2cd6e3 100644
--- a/drivers/net/ethernet/intel/e1000/e1000.h
+++ b/drivers/net/ethernet/intel/e1000/e1000.h
@@ -213,8 +213,11 @@ struct e1000_rx_ring {
 };
 
 #define E1000_DESC_UNUSED(R)						\
-	((((R)->next_to_clean > (R)->next_to_use)			\
-	  ? 0 : (R)->count) + (R)->next_to_clean - (R)->next_to_use - 1)
+({									\
+	unsigned int clean = smp_load_acquire(&(R)->next_to_clean);	\
+	unsigned int use = READ_ONCE((R)->next_to_use);			\
+	(clean > use ? 0 : (R)->count) + clean - use - 1;		\
+})
 
 #define E1000_RX_DESC_EXT(R, i)						\
 	(&(((union e1000_rx_desc_extended *)((R).desc))[i]))
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index fd7be860c201..068023595d84 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -3876,7 +3876,10 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter,
 		eop_desc = E1000_TX_DESC(*tx_ring, eop);
 	}
 
-	tx_ring->next_to_clean = i;
+	/* Synchronize with E1000_DESC_UNUSED called from e1000_xmit_frame,
+	 * which will reuse the cleaned buffers.
+	 */
+	smp_store_release(&tx_ring->next_to_clean, i);
 
 	netdev_completed_queue(netdev, pkts_compl, bytes_compl);
 
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 0a854a47d31a..80ec587d510e 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -1959,8 +1959,10 @@ static irqreturn_t e1000_intr_msix_rx(int __always_unused irq, void *data)
 	 * previous interrupt.
 	 */
 	if (rx_ring->set_itr) {
-		writel(1000000000 / (rx_ring->itr_val * 256),
-		       rx_ring->itr_register);
+		u32 itr = rx_ring->itr_val ?
+			  1000000000 / (rx_ring->itr_val * 256) : 0;
+
+		writel(itr, rx_ring->itr_register);
 		rx_ring->set_itr = 0;
 	}
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h
index 14440200499b..48809e5d3f79 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k.h
@@ -33,7 +33,7 @@
 #include "fm10k_pf.h"
 #include "fm10k_vf.h"
 
-#define FM10K_MAX_JUMBO_FRAME_SIZE	15358	/* Maximum supported size 15K */
+#define FM10K_MAX_JUMBO_FRAME_SIZE	15342	/* Maximum supported size 15K */
 
 #define MAX_QUEUES	FM10K_MAX_QUEUES_PF
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index e76a44cf330c..09281558bfbc 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -1428,6 +1428,10 @@ static int fm10k_poll(struct napi_struct *napi, int budget)
 	fm10k_for_each_ring(ring, q_vector->tx)
 		clean_complete &= fm10k_clean_tx_irq(q_vector, ring);
 
+	/* Handle case where we are called by netpoll with a budget of 0 */
+	if (budget <= 0)
+		return budget;
+
 	/* attempt to distribute budget to each queue fairly, but don't
 	 * allow the budget to go below 1 because we'll exit polling
 	 */
@@ -1966,8 +1970,10 @@ int fm10k_init_queueing_scheme(struct fm10k_intfc *interface)
 
 	/* Allocate memory for queues */
 	err = fm10k_alloc_q_vectors(interface);
-	if (err)
+	if (err) {
+		fm10k_reset_msix_capability(interface);
 		return err;
+	}
 
 	/* Map rings to devices, and map devices to physical queues */
 	fm10k_assign_rings(interface);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
index 74be792f3f1b..7f3fb51bc37b 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
@@ -159,13 +159,30 @@ static void fm10k_reinit(struct fm10k_intfc *interface)
 
 	fm10k_mbx_free_irq(interface);
 
+	/* free interrupts */
+	fm10k_clear_queueing_scheme(interface);
+
 	/* delay any future reset requests */
 	interface->last_reset = jiffies + (10 * HZ);
 
 	/* reset and initialize the hardware so it is in a known state */
-	err = hw->mac.ops.reset_hw(hw) ? : hw->mac.ops.init_hw(hw);
-	if (err)
+	err = hw->mac.ops.reset_hw(hw);
+	if (err) {
+		dev_err(&interface->pdev->dev, "reset_hw failed: %d\n", err);
+		goto reinit_err;
+	}
+
+	err = hw->mac.ops.init_hw(hw);
+	if (err) {
 		dev_err(&interface->pdev->dev, "init_hw failed: %d\n", err);
+		goto reinit_err;
+	}
+
+	err = fm10k_init_queueing_scheme(interface);
+	if (err) {
+		dev_err(&interface->pdev->dev, "init_queueing_scheme failed: %d\n", err);
+		goto reinit_err;
+	}
 
 	/* reassociate interrupts */
 	fm10k_mbx_request_irq(interface);
@@ -193,6 +210,10 @@ static void fm10k_reinit(struct fm10k_intfc *interface)
 
 	fm10k_iov_resume(interface->pdev);
 
+reinit_err:
+	if (err)
+		netif_device_detach(netdev);
+
 	rtnl_unlock();
 
 	clear_bit(__FM10K_RESETTING, &interface->state);
@@ -1101,6 +1122,10 @@ void fm10k_mbx_free_irq(struct fm10k_intfc *interface)
 	struct fm10k_hw *hw = &interface->hw;
 	int itr_reg;
 
+	/* no mailbox IRQ to free if MSI-X is not enabled */
+	if (!interface->msix_entries)
+		return;
+
 	/* disconnect the mailbox */
 	hw->mbx.ops.disconnect(hw, &hw->mbx);
 
@@ -1423,10 +1448,15 @@ int fm10k_mbx_request_irq(struct fm10k_intfc *interface)
 		err = fm10k_mbx_request_irq_pf(interface);
 	else
 		err = fm10k_mbx_request_irq_vf(interface);
+	if (err)
+		return err;
 
 	/* connect mailbox */
-	if (!err)
-		err = hw->mbx.ops.connect(hw, &hw->mbx);
+	err = hw->mbx.ops.connect(hw, &hw->mbx);
+
+	/* if the mailbox failed to connect, then free IRQ */
+	if (err)
+		fm10k_mbx_free_irq(interface);
 
 	return err;
 }
@@ -1684,7 +1714,13 @@ static int fm10k_sw_init(struct fm10k_intfc *interface,
 	interface->last_reset = jiffies + (10 * HZ);
 
 	/* reset and initialize the hardware so it is in a known state */
-	err = hw->mac.ops.reset_hw(hw) ? : hw->mac.ops.init_hw(hw);
+	err = hw->mac.ops.reset_hw(hw);
+	if (err) {
+		dev_err(&pdev->dev, "reset_hw failed: %d\n", err);
+		return err;
+	}
+
+	err = hw->mac.ops.init_hw(hw);
 	if (err) {
 		dev_err(&pdev->dev, "init_hw failed: %d\n", err);
 		return err;
@@ -2071,8 +2107,10 @@ static int fm10k_resume(struct pci_dev *pdev)
 
 	/* reset hardware to known state */
 	err = hw->mac.ops.init_hw(&interface->hw);
-	if (err)
+	if (err) {
+		dev_err(&pdev->dev, "init_hw failed: %d\n", err);
 		return err;
+	}
 
 	/* reset statistics starting values */
 	hw->mac.ops.rebind_hw_stats(hw, &interface->stats);
@@ -2185,6 +2223,9 @@ static pci_ers_result_t fm10k_io_error_detected(struct pci_dev *pdev,
 	if (netif_running(netdev))
 		fm10k_close(netdev);
 
+	/* free interrupts */
+	fm10k_clear_queueing_scheme(interface);
+
 	fm10k_mbx_free_irq(interface);
 
 	pci_disable_device(pdev);
@@ -2248,11 +2289,21 @@ static void fm10k_io_resume(struct pci_dev *pdev)
 	int err = 0;
 
 	/* reset hardware to known state */
-	hw->mac.ops.init_hw(&interface->hw);
+	err = hw->mac.ops.init_hw(&interface->hw);
+	if (err) {
+		dev_err(&pdev->dev, "init_hw failed: %d\n", err);
+		return;
+	}
 
 	/* reset statistics starting values */
 	hw->mac.ops.rebind_hw_stats(hw, &interface->stats);
 
+	err = fm10k_init_queueing_scheme(interface);
+	if (err) {
+		dev_err(&interface->pdev->dev, "init_queueing_scheme failed: %d\n", err);
+		return;
+	}
+
 	/* reassociate interrupts */
 	fm10k_mbx_request_irq(interface);
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_type.h b/drivers/net/ethernet/intel/fm10k/fm10k_type.h
index 318a212f0a78..35afd711d144 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_type.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_type.h
@@ -77,6 +77,7 @@ struct fm10k_hw;
 #define FM10K_PCIE_SRIOV_CTRL_VFARI		0x10
 
 #define FM10K_ERR_PARAM				-2
+#define FM10K_ERR_NO_RESOURCES			-3
 #define FM10K_ERR_REQUESTS_PENDING		-4
 #define FM10K_ERR_RESET_REQUESTED		-5
 #define FM10K_ERR_DMA_PENDING			-6
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
index 36c8b0aa08fd..d512575c33f3 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
@@ -103,7 +103,14 @@ static s32 fm10k_init_hw_vf(struct fm10k_hw *hw)
 	s32 err;
 	u16 i;
 
-	/* assume we always have at least 1 queue */
+	/* verify we have at least 1 queue */
+	if (!~fm10k_read_reg(hw, FM10K_TXQCTL(0)) ||
+	    !~fm10k_read_reg(hw, FM10K_RXQCTL(0))) {
+		err = FM10K_ERR_NO_RESOURCES;
+		goto reset_max_queues;
+	}
+
+	/* determine how many queues we have */
 	for (i = 1; tqdloc0 && (i < FM10K_MAX_QUEUES_POOL); i++) {
 		/* verify the Descriptor cache offsets are increasing */
 		tqdloc = ~fm10k_read_reg(hw, FM10K_TQDLOC(i));
@@ -119,7 +126,7 @@ static s32 fm10k_init_hw_vf(struct fm10k_hw *hw)
 	/* shut down queues we own and reset DMA configuration */
 	err = fm10k_disable_queues_generic(hw, i);
 	if (err)
-		return err;
+		goto reset_max_queues;
 
 	/* record maximum queue count */
 	hw->mac.max_queues = i;
@@ -129,6 +136,11 @@ static s32 fm10k_init_hw_vf(struct fm10k_hw *hw)
 			       FM10K_TXQCTL_VID_MASK) >> FM10K_TXQCTL_VID_SHIFT;
 
 	return 0;
+
+reset_max_queues:
+	hw->mac.max_queues = 0;
+
+	return err;
 }
 
 /* This structure defines the attibutes to be parsed below */
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 4dd3e26129b4..7e258a83ccab 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -767,6 +767,8 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid);
 int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid);
 struct i40e_mac_filter *i40e_put_mac_in_vlan(struct i40e_vsi *vsi, u8 *macaddr,
 					     bool is_vf, bool is_netdev);
+int i40e_del_mac_all_vlan(struct i40e_vsi *vsi, u8 *macaddr,
+			  bool is_vf, bool is_netdev);
 bool i40e_is_vsi_in_vlan(struct i40e_vsi *vsi);
 struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, u8 *macaddr,
 				      bool is_vf, bool is_netdev);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 3f385ffe420f..488a50d59dca 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -2164,8 +2164,7 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 	case TCP_V4_FLOW:
 		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 		case 0:
-			hena &= ~BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
-			break;
+			return -EINVAL;
 		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
 			hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
 			break;
@@ -2176,8 +2175,7 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 	case TCP_V6_FLOW:
 		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 		case 0:
-			hena &= ~BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
-			break;
+			return -EINVAL;
 		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
 			hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
 			break;
@@ -2188,9 +2186,7 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 	case UDP_V4_FLOW:
 		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 		case 0:
-			hena &= ~(BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) |
-				  BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4));
-			break;
+			return -EINVAL;
 		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
 			hena |= (BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) |
 				 BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4));
@@ -2202,9 +2198,7 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 	case UDP_V6_FLOW:
 		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 		case 0:
-			hena &= ~(BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) |
-				  BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6));
-			break;
+			return -EINVAL;
 		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
 			hena |= (BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) |
 				 BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6));
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 4a9873ec28c7..2215bebe208e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1317,6 +1317,42 @@ struct i40e_mac_filter *i40e_put_mac_in_vlan(struct i40e_vsi *vsi, u8 *macaddr,
 }
 
 /**
+ * i40e_del_mac_all_vlan - Remove a MAC filter from all VLANS
+ * @vsi: the VSI to be searched
+ * @macaddr: the mac address to be removed
+ * @is_vf: true if it is a VF
+ * @is_netdev: true if it is a netdev
+ *
+ * Removes a given MAC address from a VSI, regardless of VLAN
+ *
+ * Returns 0 for success, or error
+ **/
+int i40e_del_mac_all_vlan(struct i40e_vsi *vsi, u8 *macaddr,
+			  bool is_vf, bool is_netdev)
+{
+	struct i40e_mac_filter *f = NULL;
+	int changed = 0;
+
+	WARN(!spin_is_locked(&vsi->mac_filter_list_lock),
+	     "Missing mac_filter_list_lock\n");
+	list_for_each_entry(f, &vsi->mac_filter_list, list) {
+		if ((ether_addr_equal(macaddr, f->macaddr)) &&
+		    (is_vf == f->is_vf) &&
+		    (is_netdev == f->is_netdev)) {
+			f->counter--;
+			f->changed = true;
+			changed = 1;
+		}
+	}
+	if (changed) {
+		vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
+		vsi->back->flags |= I40E_FLAG_FILTER_SYNC;
+		return 0;
+	}
+	return -ENOENT;
+}
+
+/**
  * i40e_rm_default_mac_filter - Remove the default MAC filter set by NVM
  * @vsi: the PF Main VSI - inappropriate for any other VSI
  * @macaddr: the MAC address
@@ -1547,9 +1583,11 @@ static int i40e_set_mac(struct net_device *netdev, void *p)
 		spin_unlock_bh(&vsi->mac_filter_list_lock);
 	}
 
-	i40e_sync_vsi_filters(vsi, false);
 	ether_addr_copy(netdev->dev_addr, addr->sa_data);
-
+	/* schedule our worker thread which will take care of
+	 * applying the new filter changes
+	 */
+	i40e_service_event_schedule(vsi->back);
 	return 0;
 }
 
@@ -1935,11 +1973,13 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl)
 
 	/* Now process 'del_list' outside the lock */
 	if (!list_empty(&tmp_del_list)) {
+		int del_list_size;
+
 		filter_list_len = pf->hw.aq.asq_buf_size /
 			    sizeof(struct i40e_aqc_remove_macvlan_element_data);
-		del_list = kcalloc(filter_list_len,
-			    sizeof(struct i40e_aqc_remove_macvlan_element_data),
-			    GFP_KERNEL);
+		del_list_size = filter_list_len *
+			    sizeof(struct i40e_aqc_remove_macvlan_element_data);
+		del_list = kzalloc(del_list_size, GFP_KERNEL);
 		if (!del_list) {
 			i40e_cleanup_add_list(&tmp_add_list);
 
@@ -1971,7 +2011,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl)
 						  NULL);
 				aq_err = pf->hw.aq.asq_last_status;
 				num_del = 0;
-				memset(del_list, 0, sizeof(*del_list));
+				memset(del_list, 0, del_list_size);
 
 				if (ret && aq_err != I40E_AQ_RC_ENOENT)
 					dev_err(&pf->pdev->dev,
@@ -2004,13 +2044,14 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl)
 	}
 
 	if (!list_empty(&tmp_add_list)) {
+		int add_list_size;
 
 		/* do all the adds now */
 		filter_list_len = pf->hw.aq.asq_buf_size /
 			       sizeof(struct i40e_aqc_add_macvlan_element_data),
-		add_list = kcalloc(filter_list_len,
-			       sizeof(struct i40e_aqc_add_macvlan_element_data),
-			       GFP_KERNEL);
+		add_list_size = filter_list_len *
+			       sizeof(struct i40e_aqc_add_macvlan_element_data);
+		add_list = kzalloc(add_list_size, GFP_KERNEL);
 		if (!add_list) {
 			/* Purge element from temporary lists */
 			i40e_cleanup_add_list(&tmp_add_list);
@@ -2048,7 +2089,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl)
 
 				if (ret)
 					break;
-				memset(add_list, 0, sizeof(*add_list));
+				memset(add_list, 0, add_list_size);
 			}
 			/* Entries from tmp_add_list were cloned from MAC
 			 * filter list, hence clean those cloned entries
@@ -2112,12 +2153,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl)
 			 */
 			if (pf->cur_promisc != cur_promisc) {
 				pf->cur_promisc = cur_promisc;
-				if (grab_rtnl)
-					i40e_do_reset_safe(pf,
-						BIT(__I40E_PF_RESET_REQUESTED));
-				else
-					i40e_do_reset(pf,
-						BIT(__I40E_PF_RESET_REQUESTED));
+				set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
 			}
 		} else {
 			ret = i40e_aq_set_vsi_unicast_promiscuous(
@@ -2377,16 +2413,13 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid)
 		}
 	}
 
-	/* Make sure to release before sync_vsi_filter because that
-	 * function will lock/unlock as necessary
-	 */
 	spin_unlock_bh(&vsi->mac_filter_list_lock);
 
-	if (test_bit(__I40E_DOWN, &vsi->back->state) ||
-	    test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state))
-		return 0;
-
-	return i40e_sync_vsi_filters(vsi, false);
+	/* schedule our worker thread which will take care of
+	 * applying the new filter changes
+	 */
+	i40e_service_event_schedule(vsi->back);
+	return 0;
 }
 
 /**
@@ -2459,16 +2492,13 @@ int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid)
 		}
 	}
 
-	/* Make sure to release before sync_vsi_filter because that
-	 * function with lock/unlock as necessary
-	 */
 	spin_unlock_bh(&vsi->mac_filter_list_lock);
 
-	if (test_bit(__I40E_DOWN, &vsi->back->state) ||
-	    test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state))
-		return 0;
-
-	return i40e_sync_vsi_filters(vsi, false);
+	/* schedule our worker thread which will take care of
+	 * applying the new filter changes
+	 */
+	i40e_service_event_schedule(vsi->back);
+	return 0;
 }
 
 /**
@@ -2711,6 +2741,11 @@ static void i40e_config_xps_tx_ring(struct i40e_ring *ring)
 		netif_set_xps_queue(ring->netdev, mask, ring->queue_index);
 		free_cpumask_var(mask);
 	}
+
+	/* schedule our worker thread which will take care of
+	 * applying the new filter changes
+	 */
+	i40e_service_event_schedule(vsi->back);
 }
 
 /**
@@ -6685,6 +6720,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 	struct i40e_hw *hw = &pf->hw;
 	u8 set_fc_aq_fail = 0;
 	i40e_status ret;
+	u32 val;
 	u32 v;
 
 	/* Now we wait for GRST to settle out.
@@ -6823,6 +6859,20 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 		}
 	}
 
+	/* Reconfigure hardware for allowing smaller MSS in the case
+	 * of TSO, so that we avoid the MDD being fired and causing
+	 * a reset in the case of small MSS+TSO.
+	 */
+#define I40E_REG_MSS          0x000E64DC
+#define I40E_REG_MSS_MIN_MASK 0x3FF0000
+#define I40E_64BYTE_MSS       0x400000
+	val = rd32(hw, I40E_REG_MSS);
+	if ((val & I40E_REG_MSS_MIN_MASK) > I40E_64BYTE_MSS) {
+		val &= ~I40E_REG_MSS_MIN_MASK;
+		val |= I40E_64BYTE_MSS;
+		wr32(hw, I40E_REG_MSS, val);
+	}
+
 	if (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 33)) ||
 	    (pf->hw.aq.fw_maj_ver < 4)) {
 		msleep(75);
@@ -10183,6 +10233,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	u16 link_status;
 	int err;
 	u32 len;
+	u32 val;
 	u32 i;
 	u8 set_fc_aq_fail;
 
@@ -10493,6 +10544,17 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			 i40e_stat_str(&pf->hw, err),
 			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
 
+	/* Reconfigure hardware for allowing smaller MSS in the case
+	 * of TSO, so that we avoid the MDD being fired and causing
+	 * a reset in the case of small MSS+TSO.
+	 */
+	val = rd32(hw, I40E_REG_MSS);
+	if ((val & I40E_REG_MSS_MIN_MASK) > I40E_64BYTE_MSS) {
+		val &= ~I40E_REG_MSS_MIN_MASK;
+		val |= I40E_64BYTE_MSS;
+		wr32(hw, I40E_REG_MSS, val);
+	}
+
 	if (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 33)) ||
 	    (pf->hw.aq.fw_maj_ver < 4)) {
 		msleep(75);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 635b3ac17877..26c55bba4bf3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -235,6 +235,9 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi,
 				 "Filter deleted for PCTYPE %d loc = %d\n",
 				 fd_data->pctype, fd_data->fd_id);
 	}
+	if (err)
+		kfree(raw_packet);
+
 	return err ? -EOPNOTSUPP : 0;
 }
 
@@ -312,6 +315,9 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
 				 fd_data->pctype, fd_data->fd_id);
 	}
 
+	if (err)
+		kfree(raw_packet);
+
 	return err ? -EOPNOTSUPP : 0;
 }
 
@@ -387,6 +393,9 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi,
 		}
 	}
 
+	if (err)
+		kfree(raw_packet);
+
 	return err ? -EOPNOTSUPP : 0;
 }
 
@@ -526,11 +535,7 @@ static void i40e_unmap_and_free_tx_resource(struct i40e_ring *ring,
 					    struct i40e_tx_buffer *tx_buffer)
 {
 	if (tx_buffer->skb) {
-		if (tx_buffer->tx_flags & I40E_TX_FLAGS_FD_SB)
-			kfree(tx_buffer->raw_buf);
-		else
-			dev_kfree_skb_any(tx_buffer->skb);
-
+		dev_kfree_skb_any(tx_buffer->skb);
 		if (dma_unmap_len(tx_buffer, len))
 			dma_unmap_single(ring->dev,
 					 dma_unmap_addr(tx_buffer, dma),
@@ -542,6 +547,10 @@ static void i40e_unmap_and_free_tx_resource(struct i40e_ring *ring,
 			       dma_unmap_len(tx_buffer, len),
 			       DMA_TO_DEVICE);
 	}
+
+	if (tx_buffer->tx_flags & I40E_TX_FLAGS_FD_SB)
+		kfree(tx_buffer->raw_buf);
+
 	tx_buffer->next_to_watch = NULL;
 	tx_buffer->skb = NULL;
 	dma_unmap_len_set(tx_buffer, len, 0);
@@ -1416,31 +1425,12 @@ checksum_fail:
 }
 
 /**
- * i40e_rx_hash - returns the hash value from the Rx descriptor
- * @ring: descriptor ring
- * @rx_desc: specific descriptor
- **/
-static inline u32 i40e_rx_hash(struct i40e_ring *ring,
-			       union i40e_rx_desc *rx_desc)
-{
-	const __le64 rss_mask =
-		cpu_to_le64((u64)I40E_RX_DESC_FLTSTAT_RSS_HASH <<
-			    I40E_RX_DESC_STATUS_FLTSTAT_SHIFT);
-
-	if ((ring->netdev->features & NETIF_F_RXHASH) &&
-	    (rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask)
-		return le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss);
-	else
-		return 0;
-}
-
-/**
- * i40e_ptype_to_hash - get a hash type
+ * i40e_ptype_to_htype - get a hash type
  * @ptype: the ptype value from the descriptor
  *
  * Returns a hash type to be used by skb_set_hash
  **/
-static inline enum pkt_hash_types i40e_ptype_to_hash(u8 ptype)
+static inline enum pkt_hash_types i40e_ptype_to_htype(u8 ptype)
 {
 	struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype);
 
@@ -1458,6 +1448,30 @@ static inline enum pkt_hash_types i40e_ptype_to_hash(u8 ptype)
 }
 
 /**
+ * i40e_rx_hash - set the hash value in the skb
+ * @ring: descriptor ring
+ * @rx_desc: specific descriptor
+ **/
+static inline void i40e_rx_hash(struct i40e_ring *ring,
+				union i40e_rx_desc *rx_desc,
+				struct sk_buff *skb,
+				u8 rx_ptype)
+{
+	u32 hash;
+	const __le64 rss_mask  =
+		cpu_to_le64((u64)I40E_RX_DESC_FLTSTAT_RSS_HASH <<
+			    I40E_RX_DESC_STATUS_FLTSTAT_SHIFT);
+
+	if (ring->netdev->features & NETIF_F_RXHASH)
+		return;
+
+	if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) {
+		hash = le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss);
+		skb_set_hash(skb, hash, i40e_ptype_to_htype(rx_ptype));
+	}
+}
+
+/**
  * i40e_clean_rx_irq_ps - Reclaim resources after receive; packet split
  * @rx_ring:  rx ring to clean
  * @budget:   how many cleans we're allowed
@@ -1606,8 +1620,8 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 			continue;
 		}
 
-		skb_set_hash(skb, i40e_rx_hash(rx_ring, rx_desc),
-			     i40e_ptype_to_hash(rx_ptype));
+		i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
+
 		if (unlikely(rx_status & I40E_RXD_QW1_STATUS_TSYNVALID_MASK)) {
 			i40e_ptp_rx_hwtstamp(vsi->back, skb, (rx_status &
 					   I40E_RXD_QW1_STATUS_TSYNINDX_MASK) >>
@@ -1736,8 +1750,7 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget)
 			continue;
 		}
 
-		skb_set_hash(skb, i40e_rx_hash(rx_ring, rx_desc),
-			     i40e_ptype_to_hash(rx_ptype));
+		i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
 		if (unlikely(rx_status & I40E_RXD_QW1_STATUS_TSYNVALID_MASK)) {
 			i40e_ptp_rx_hwtstamp(vsi->back, skb, (rx_status &
 					   I40E_RXD_QW1_STATUS_TSYNINDX_MASK) >>
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 44462b40f2d7..e116d9a99b8e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -549,12 +549,15 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type)
 			i40e_vsi_add_pvid(vsi, vf->port_vlan_id);
 
 		spin_lock_bh(&vsi->mac_filter_list_lock);
-		f = i40e_add_filter(vsi, vf->default_lan_addr.addr,
-				    vf->port_vlan_id ? vf->port_vlan_id : -1,
-				    true, false);
-		if (!f)
-			dev_info(&pf->pdev->dev,
-				 "Could not allocate VF MAC addr\n");
+		if (is_valid_ether_addr(vf->default_lan_addr.addr)) {
+			f = i40e_add_filter(vsi, vf->default_lan_addr.addr,
+				       vf->port_vlan_id ? vf->port_vlan_id : -1,
+				       true, false);
+			if (!f)
+				dev_info(&pf->pdev->dev,
+					 "Could not add MAC filter %pM for VF %d\n",
+					vf->default_lan_addr.addr, vf->vf_id);
+		}
 		f = i40e_add_filter(vsi, brdcast,
 				    vf->port_vlan_id ? vf->port_vlan_id : -1,
 				    true, false);
@@ -1680,8 +1683,12 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 	spin_lock_bh(&vsi->mac_filter_list_lock);
 	/* delete addresses from the list */
 	for (i = 0; i < al->num_elements; i++)
-		i40e_del_filter(vsi, al->list[i].addr,
-				I40E_VLAN_ANY, true, false);
+		if (i40e_del_mac_all_vlan(vsi, al->list[i].addr, true, false)) {
+			ret = I40E_ERR_INVALID_MAC_ADDR;
+			spin_unlock_bh(&vsi->mac_filter_list_lock);
+			goto error_param;
+		}
+
 	spin_unlock_bh(&vsi->mac_filter_list_lock);
 
 	/* program the updated filter list */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 47e9a90d6b10..39db70a597ed 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -51,11 +51,7 @@ static void i40e_unmap_and_free_tx_resource(struct i40e_ring *ring,
 					    struct i40e_tx_buffer *tx_buffer)
 {
 	if (tx_buffer->skb) {
-		if (tx_buffer->tx_flags & I40E_TX_FLAGS_FD_SB)
-			kfree(tx_buffer->raw_buf);
-		else
-			dev_kfree_skb_any(tx_buffer->skb);
-
+		dev_kfree_skb_any(tx_buffer->skb);
 		if (dma_unmap_len(tx_buffer, len))
 			dma_unmap_single(ring->dev,
 					 dma_unmap_addr(tx_buffer, dma),
@@ -67,6 +63,10 @@ static void i40e_unmap_and_free_tx_resource(struct i40e_ring *ring,
 			       dma_unmap_len(tx_buffer, len),
 			       DMA_TO_DEVICE);
 	}
+
+	if (tx_buffer->tx_flags & I40E_TX_FLAGS_FD_SB)
+		kfree(tx_buffer->raw_buf);
+
 	tx_buffer->next_to_watch = NULL;
 	tx_buffer->skb = NULL;
 	dma_unmap_len_set(tx_buffer, len, 0);
@@ -245,16 +245,6 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 	tx_ring->q_vector->tx.total_bytes += total_bytes;
 	tx_ring->q_vector->tx.total_packets += total_packets;
 
-	/* check to see if there are any non-cache aligned descriptors
-	 * waiting to be written back, and kick the hardware to force
-	 * them to be written back in case of napi polling
-	 */
-	if (budget &&
-	    !((i & WB_STRIDE) == WB_STRIDE) &&
-	    !test_bit(__I40E_DOWN, &tx_ring->vsi->state) &&
-	    (I40E_DESC_UNUSED(tx_ring) != tx_ring->count))
-		tx_ring->arm_wb = true;
-
 	netdev_tx_completed_queue(netdev_get_tx_queue(tx_ring->netdev,
 						      tx_ring->queue_index),
 				  total_packets, total_bytes);
@@ -889,31 +879,12 @@ checksum_fail:
 }
 
 /**
- * i40e_rx_hash - returns the hash value from the Rx descriptor
- * @ring: descriptor ring
- * @rx_desc: specific descriptor
- **/
-static inline u32 i40e_rx_hash(struct i40e_ring *ring,
-			       union i40e_rx_desc *rx_desc)
-{
-	const __le64 rss_mask =
-		cpu_to_le64((u64)I40E_RX_DESC_FLTSTAT_RSS_HASH <<
-			    I40E_RX_DESC_STATUS_FLTSTAT_SHIFT);
-
-	if ((ring->netdev->features & NETIF_F_RXHASH) &&
-	    (rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask)
-		return le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss);
-	else
-		return 0;
-}
-
-/**
- * i40e_ptype_to_hash - get a hash type
+ * i40e_ptype_to_htype - get a hash type
  * @ptype: the ptype value from the descriptor
  *
  * Returns a hash type to be used by skb_set_hash
  **/
-static inline enum pkt_hash_types i40e_ptype_to_hash(u8 ptype)
+static inline enum pkt_hash_types i40e_ptype_to_htype(u8 ptype)
 {
 	struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype);
 
@@ -931,6 +902,30 @@ static inline enum pkt_hash_types i40e_ptype_to_hash(u8 ptype)
 }
 
 /**
+ * i40e_rx_hash - set the hash value in the skb
+ * @ring: descriptor ring
+ * @rx_desc: specific descriptor
+ **/
+static inline void i40e_rx_hash(struct i40e_ring *ring,
+				union i40e_rx_desc *rx_desc,
+				struct sk_buff *skb,
+				u8 rx_ptype)
+{
+	u32 hash;
+	const __le64 rss_mask  =
+		cpu_to_le64((u64)I40E_RX_DESC_FLTSTAT_RSS_HASH <<
+			    I40E_RX_DESC_STATUS_FLTSTAT_SHIFT);
+
+	if (ring->netdev->features & NETIF_F_RXHASH)
+		return;
+
+	if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) {
+		hash = le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss);
+		skb_set_hash(skb, hash, i40e_ptype_to_htype(rx_ptype));
+	}
+}
+
+/**
  * i40e_clean_rx_irq_ps - Reclaim resources after receive; packet split
  * @rx_ring:  rx ring to clean
  * @budget:   how many cleans we're allowed
@@ -1071,8 +1066,8 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 			continue;
 		}
 
-		skb_set_hash(skb, i40e_rx_hash(rx_ring, rx_desc),
-			     i40e_ptype_to_hash(rx_ptype));
+		i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
+
 		/* probably a little skewed due to removing CRC */
 		total_rx_bytes += skb->len;
 		total_rx_packets++;
@@ -1189,8 +1184,7 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget)
 			continue;
 		}
 
-		skb_set_hash(skb, i40e_rx_hash(rx_ring, rx_desc),
-			     i40e_ptype_to_hash(rx_ptype));
+		i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
 		/* probably a little skewed due to removing CRC */
 		total_rx_bytes += skb->len;
 		total_rx_packets++;
@@ -1770,6 +1764,9 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	u32 td_tag = 0;
 	dma_addr_t dma;
 	u16 gso_segs;
+	u16 desc_count = 0;
+	bool tail_bump = true;
+	bool do_rs = false;
 
 	if (tx_flags & I40E_TX_FLAGS_HW_VLAN) {
 		td_cmd |= I40E_TX_DESC_CMD_IL2TAG1;
@@ -1810,6 +1807,8 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 			tx_desc++;
 			i++;
+			desc_count++;
+
 			if (i == tx_ring->count) {
 				tx_desc = I40E_TX_DESC(tx_ring, 0);
 				i = 0;
@@ -1829,6 +1828,8 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 		tx_desc++;
 		i++;
+		desc_count++;
+
 		if (i == tx_ring->count) {
 			tx_desc = I40E_TX_DESC(tx_ring, 0);
 			i = 0;
@@ -1843,35 +1844,7 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 		tx_bi = &tx_ring->tx_bi[i];
 	}
 
-	/* Place RS bit on last descriptor of any packet that spans across the
-	 * 4th descriptor (WB_STRIDE aka 0x3) in a 64B cacheline.
-	 */
 #define WB_STRIDE 0x3
-	if (((i & WB_STRIDE) != WB_STRIDE) &&
-	    (first <= &tx_ring->tx_bi[i]) &&
-	    (first >= &tx_ring->tx_bi[i & ~WB_STRIDE])) {
-		tx_desc->cmd_type_offset_bsz =
-			build_ctob(td_cmd, td_offset, size, td_tag) |
-			cpu_to_le64((u64)I40E_TX_DESC_CMD_EOP <<
-					 I40E_TXD_QW1_CMD_SHIFT);
-	} else {
-		tx_desc->cmd_type_offset_bsz =
-			build_ctob(td_cmd, td_offset, size, td_tag) |
-			cpu_to_le64((u64)I40E_TXD_CMD <<
-					 I40E_TXD_QW1_CMD_SHIFT);
-	}
-
-	netdev_tx_sent_queue(netdev_get_tx_queue(tx_ring->netdev,
-						 tx_ring->queue_index),
-			     first->bytecount);
-
-	/* Force memory writes to complete before letting h/w
-	 * know there are new descriptors to fetch.  (Only
-	 * applicable for weak-ordered memory model archs,
-	 * such as IA-64).
-	 */
-	wmb();
-
 	/* set next_to_watch value indicating a packet is present */
 	first->next_to_watch = tx_desc;
 
@@ -1881,15 +1854,78 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 	tx_ring->next_to_use = i;
 
+	netdev_tx_sent_queue(netdev_get_tx_queue(tx_ring->netdev,
+						 tx_ring->queue_index),
+						 first->bytecount);
 	i40evf_maybe_stop_tx(tx_ring, DESC_NEEDED);
+
+	/* Algorithm to optimize tail and RS bit setting:
+	 * if xmit_more is supported
+	 *	if xmit_more is true
+	 *		do not update tail and do not mark RS bit.
+	 *	if xmit_more is false and last xmit_more was false
+	 *		if every packet spanned less than 4 desc
+	 *			then set RS bit on 4th packet and update tail
+	 *			on every packet
+	 *		else
+	 *			update tail and set RS bit on every packet.
+	 *	if xmit_more is false and last_xmit_more was true
+	 *		update tail and set RS bit.
+	 * else (kernel < 3.18)
+	 *	if every packet spanned less than 4 desc
+	 *		then set RS bit on 4th packet and update tail
+	 *		on every packet
+	 *	else
+	 *		set RS bit on EOP for every packet and update tail
+	 *
+	 * Optimization: wmb to be issued only in case of tail update.
+	 * Also optimize the Descriptor WB path for RS bit with the same
+	 * algorithm.
+	 *
+	 * Note: If there are less than 4 packets
+	 * pending and interrupts were disabled the service task will
+	 * trigger a force WB.
+	 */
+	if (skb->xmit_more  &&
+	    !netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev,
+						    tx_ring->queue_index))) {
+		tx_ring->flags |= I40E_TXR_FLAGS_LAST_XMIT_MORE_SET;
+		tail_bump = false;
+	} else if (!skb->xmit_more &&
+		   !netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev,
+						       tx_ring->queue_index)) &&
+		   (!(tx_ring->flags & I40E_TXR_FLAGS_LAST_XMIT_MORE_SET)) &&
+		   (tx_ring->packet_stride < WB_STRIDE) &&
+		   (desc_count < WB_STRIDE)) {
+		tx_ring->packet_stride++;
+	} else {
+		tx_ring->packet_stride = 0;
+		tx_ring->flags &= ~I40E_TXR_FLAGS_LAST_XMIT_MORE_SET;
+		do_rs = true;
+	}
+	if (do_rs)
+		tx_ring->packet_stride = 0;
+
+	tx_desc->cmd_type_offset_bsz =
+			build_ctob(td_cmd, td_offset, size, td_tag) |
+			cpu_to_le64((u64)(do_rs ? I40E_TXD_CMD :
+						  I40E_TX_DESC_CMD_EOP) <<
+						  I40E_TXD_QW1_CMD_SHIFT);
+
 	/* notify HW of packet */
-	if (!skb->xmit_more ||
-	    netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev,
-						   tx_ring->queue_index)))
-		writel(i, tx_ring->tail);
-	else
+	if (!tail_bump)
 		prefetchw(tx_desc + 1);
 
+	if (tail_bump) {
+		/* Force memory writes to complete before letting h/w
+		 * know there are new descriptors to fetch.  (Only
+		 * applicable for weak-ordered memory model archs,
+		 * such as IA-64).
+		 */
+		wmb();
+		writel(i, tx_ring->tail);
+	}
+
 	return;
 
 dma_error:
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index ebc1bf77f036..998976844e4e 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -267,6 +267,8 @@ struct i40e_ring {
 
 	bool ring_active;		/* is ring online or not */
 	bool arm_wb;		/* do something to arm write back */
+	u8 packet_stride;
+#define I40E_TXR_FLAGS_LAST_XMIT_MORE_SET BIT(2)
 
 	u16 flags;
 #define I40E_TXR_FLAGS_WB_ON_ITR	BIT(0)
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
index 4790437a50ac..2ac62efc36f7 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
@@ -477,54 +477,30 @@ static int i40evf_set_rss_hash_opt(struct i40evf_adapter *adapter,
 
 	switch (nfc->flow_type) {
 	case TCP_V4_FLOW:
-		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
-		case 0:
-			hena &= ~BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
-			break;
-		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+		if (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3))
 			hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
-			break;
-		default:
+		else
 			return -EINVAL;
-		}
 		break;
 	case TCP_V6_FLOW:
-		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
-		case 0:
-			hena &= ~BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
-			break;
-		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+		if (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3))
 			hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
-			break;
-		default:
+		else
 			return -EINVAL;
-		}
 		break;
 	case UDP_V4_FLOW:
-		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
-		case 0:
-			hena &= ~(BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) |
-				  BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4));
-			break;
-		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+		if (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 			hena |= (BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) |
 				 BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4));
-			break;
-		default:
+		} else {
 			return -EINVAL;
 		}
 		break;
 	case UDP_V6_FLOW:
-		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
-		case 0:
-			hena &= ~(BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) |
-				  BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6));
-			break;
-		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+		if (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 			hena |= (BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) |
 				 BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6));
-			break;
-		default:
+		} else {
 			return -EINVAL;
 		}
 		break;
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 99d2cffae0cd..5f03ab3dfa19 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -1864,6 +1864,9 @@ void i40evf_free_all_tx_resources(struct i40evf_adapter *adapter)
 {
 	int i;
 
+	if (!adapter->tx_rings)
+		return;
+
 	for (i = 0; i < adapter->num_active_queues; i++)
 		if (adapter->tx_rings[i]->desc)
 			i40evf_free_tx_resources(adapter->tx_rings[i]);
@@ -1932,6 +1935,9 @@ void i40evf_free_all_rx_resources(struct i40evf_adapter *adapter)
 {
 	int i;
 
+	if (!adapter->rx_rings)
+		return;
+
 	for (i = 0; i < adapter->num_active_queues; i++)
 		if (adapter->rx_rings[i]->desc)
 			i40evf_free_rx_resources(adapter->rx_rings[i]);
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
index 32e620e1eb5c..5de3f52fd31f 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
@@ -391,6 +391,7 @@ void i40evf_add_ether_addrs(struct i40evf_adapter *adapter)
 	struct i40e_virtchnl_ether_addr_list *veal;
 	int len, i = 0, count = 0;
 	struct i40evf_mac_filter *f;
+	bool more = false;
 
 	if (adapter->current_op != I40E_VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -415,7 +416,9 @@ void i40evf_add_ether_addrs(struct i40evf_adapter *adapter)
 		count = (I40EVF_MAX_AQ_BUF_SIZE -
 			 sizeof(struct i40e_virtchnl_ether_addr_list)) /
 			sizeof(struct i40e_virtchnl_ether_addr);
-		len = I40EVF_MAX_AQ_BUF_SIZE;
+		len = sizeof(struct i40e_virtchnl_ether_addr_list) +
+		      (count * sizeof(struct i40e_virtchnl_ether_addr));
+		more = true;
 	}
 
 	veal = kzalloc(len, GFP_ATOMIC);
@@ -431,7 +434,8 @@ void i40evf_add_ether_addrs(struct i40evf_adapter *adapter)
 			f->add = false;
 		}
 	}
-	adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_MAC_FILTER;
+	if (!more)
+		adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_MAC_FILTER;
 	i40evf_send_pf_msg(adapter, I40E_VIRTCHNL_OP_ADD_ETHER_ADDRESS,
 			   (u8 *)veal, len);
 	kfree(veal);
@@ -450,6 +454,7 @@ void i40evf_del_ether_addrs(struct i40evf_adapter *adapter)
 	struct i40e_virtchnl_ether_addr_list *veal;
 	struct i40evf_mac_filter *f, *ftmp;
 	int len, i = 0, count = 0;
+	bool more = false;
 
 	if (adapter->current_op != I40E_VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -474,7 +479,9 @@ void i40evf_del_ether_addrs(struct i40evf_adapter *adapter)
 		count = (I40EVF_MAX_AQ_BUF_SIZE -
 			 sizeof(struct i40e_virtchnl_ether_addr_list)) /
 			sizeof(struct i40e_virtchnl_ether_addr);
-		len = I40EVF_MAX_AQ_BUF_SIZE;
+		len = sizeof(struct i40e_virtchnl_ether_addr_list) +
+		      (count * sizeof(struct i40e_virtchnl_ether_addr));
+		more = true;
 	}
 	veal = kzalloc(len, GFP_ATOMIC);
 	if (!veal)
@@ -490,7 +497,8 @@ void i40evf_del_ether_addrs(struct i40evf_adapter *adapter)
 			kfree(f);
 		}
 	}
-	adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_MAC_FILTER;
+	if (!more)
+		adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_MAC_FILTER;
 	i40evf_send_pf_msg(adapter, I40E_VIRTCHNL_OP_DEL_ETHER_ADDRESS,
 			   (u8 *)veal, len);
 	kfree(veal);
@@ -509,6 +517,7 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter)
 	struct i40e_virtchnl_vlan_filter_list *vvfl;
 	int len, i = 0, count = 0;
 	struct i40evf_vlan_filter *f;
+	bool more = false;
 
 	if (adapter->current_op != I40E_VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -534,7 +543,9 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter)
 		count = (I40EVF_MAX_AQ_BUF_SIZE -
 			 sizeof(struct i40e_virtchnl_vlan_filter_list)) /
 			sizeof(u16);
-		len = I40EVF_MAX_AQ_BUF_SIZE;
+		len = sizeof(struct i40e_virtchnl_vlan_filter_list) +
+		      (count * sizeof(u16));
+		more = true;
 	}
 	vvfl = kzalloc(len, GFP_ATOMIC);
 	if (!vvfl)
@@ -549,7 +560,8 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter)
 			f->add = false;
 		}
 	}
-	adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_VLAN_FILTER;
+	if (!more)
+		adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_VLAN_FILTER;
 	i40evf_send_pf_msg(adapter, I40E_VIRTCHNL_OP_ADD_VLAN, (u8 *)vvfl, len);
 	kfree(vvfl);
 }
@@ -567,6 +579,7 @@ void i40evf_del_vlans(struct i40evf_adapter *adapter)
 	struct i40e_virtchnl_vlan_filter_list *vvfl;
 	struct i40evf_vlan_filter *f, *ftmp;
 	int len, i = 0, count = 0;
+	bool more = false;
 
 	if (adapter->current_op != I40E_VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -592,7 +605,9 @@ void i40evf_del_vlans(struct i40evf_adapter *adapter)
 		count = (I40EVF_MAX_AQ_BUF_SIZE -
 			 sizeof(struct i40e_virtchnl_vlan_filter_list)) /
 			sizeof(u16);
-		len = I40EVF_MAX_AQ_BUF_SIZE;
+		len = sizeof(struct i40e_virtchnl_vlan_filter_list) +
+		      (count * sizeof(u16));
+		more = true;
 	}
 	vvfl = kzalloc(len, GFP_ATOMIC);
 	if (!vvfl)
@@ -608,7 +623,8 @@ void i40evf_del_vlans(struct i40evf_adapter *adapter)
 			kfree(f);
 		}
 	}
-	adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_VLAN_FILTER;
+	if (!more)
+		adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_VLAN_FILTER;
 	i40evf_send_pf_msg(adapter, I40E_VIRTCHNL_OP_DEL_VLAN, (u8 *)vvfl, len);
 	kfree(vvfl);
 }
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index 7a73510e547c..97bf0c3d5c69 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -294,6 +294,7 @@ static s32 igb_init_phy_params_82575(struct e1000_hw *hw)
 	case I210_I_PHY_ID:
 		phy->type		= e1000_phy_i210;
 		phy->ops.check_polarity	= igb_check_polarity_m88;
+		phy->ops.get_cfg_done	= igb_get_cfg_done_i210;
 		phy->ops.get_phy_info	= igb_get_phy_info_m88;
 		phy->ops.get_cable_length = igb_get_cable_length_m88_gen2;
 		phy->ops.set_d0_lplu_state = igb_set_d0_lplu_state_82580;
diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c
index 65d931669f81..29f59c76878a 100644
--- a/drivers/net/ethernet/intel/igb/e1000_i210.c
+++ b/drivers/net/ethernet/intel/igb/e1000_i210.c
@@ -900,3 +900,30 @@ s32 igb_pll_workaround_i210(struct e1000_hw *hw)
 	wr32(E1000_MDICNFG, mdicnfg);
 	return ret_val;
 }
+
+/**
+ *  igb_get_cfg_done_i210 - Read config done bit
+ *  @hw: pointer to the HW structure
+ *
+ *  Read the management control register for the config done bit for
+ *  completion status.  NOTE: silicon which is EEPROM-less will fail trying
+ *  to read the config done bit, so an error is *ONLY* logged and returns
+ *  0.  If we were to return with error, EEPROM-less silicon
+ *  would not be able to be reset or change link.
+ **/
+s32 igb_get_cfg_done_i210(struct e1000_hw *hw)
+{
+	s32 timeout = PHY_CFG_TIMEOUT;
+	u32 mask = E1000_NVM_CFG_DONE_PORT_0;
+
+	while (timeout) {
+		if (rd32(E1000_EEMNGCTL_I210) & mask)
+			break;
+		usleep_range(1000, 2000);
+		timeout--;
+	}
+	if (!timeout)
+		hw_dbg("MNG configuration cycle has not completed.\n");
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.h b/drivers/net/ethernet/intel/igb/e1000_i210.h
index 3442b6357d01..eaa68a50cb3b 100644
--- a/drivers/net/ethernet/intel/igb/e1000_i210.h
+++ b/drivers/net/ethernet/intel/igb/e1000_i210.h
@@ -34,6 +34,7 @@ s32 igb_write_xmdio_reg(struct e1000_hw *hw, u16 addr, u8 dev_addr, u16 data);
 s32 igb_init_nvm_params_i210(struct e1000_hw *hw);
 bool igb_get_flash_presence_i210(struct e1000_hw *hw);
 s32 igb_pll_workaround_i210(struct e1000_hw *hw);
+s32 igb_get_cfg_done_i210(struct e1000_hw *hw);
 
 #define E1000_STM_OPCODE		0xDB00
 #define E1000_EEPROM_FLASH_SIZE_WORD	0x11
diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h
index 4af2870e49f8..0fdcd4d1b982 100644
--- a/drivers/net/ethernet/intel/igb/e1000_regs.h
+++ b/drivers/net/ethernet/intel/igb/e1000_regs.h
@@ -66,6 +66,7 @@
 #define E1000_PBA      0x01000  /* Packet Buffer Allocation - RW */
 #define E1000_PBS      0x01008  /* Packet Buffer Size */
 #define E1000_EEMNGCTL 0x01010  /* MNG EEprom Control */
+#define E1000_EEMNGCTL_I210 0x12030  /* MNG EEprom Control */
 #define E1000_EEARBC_I210 0x12024  /* EEPROM Auto Read Bus Control */
 #define E1000_EEWR     0x0102C  /* EEPROM Write Register - RW */
 #define E1000_I2CCMD   0x01028  /* SFPI2C Command Register - RW */
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 1a2f1cc44b28..e3cb93bdb21a 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -389,6 +389,8 @@ struct igb_adapter {
 	u16 link_speed;
 	u16 link_duplex;
 
+	u8 __iomem *io_addr; /* Mainly for iounmap use */
+
 	struct work_struct reset_task;
 	struct work_struct watchdog_task;
 	bool fc_autoneg;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index ea7b09887245..fa3b4cbea23b 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2294,9 +2294,11 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
 
 	err = -EIO;
-	hw->hw_addr = pci_iomap(pdev, 0, 0);
-	if (!hw->hw_addr)
+	adapter->io_addr = pci_iomap(pdev, 0, 0);
+	if (!adapter->io_addr)
 		goto err_ioremap;
+	/* hw->hw_addr can be altered, we'll use adapter->io_addr for unmap */
+	hw->hw_addr = adapter->io_addr;
 
 	netdev->netdev_ops = &igb_netdev_ops;
 	igb_set_ethtool_ops(netdev);
@@ -2656,7 +2658,7 @@ err_sw_init:
 #ifdef CONFIG_PCI_IOV
 	igb_disable_sriov(pdev);
 #endif
-	pci_iounmap(pdev, hw->hw_addr);
+	pci_iounmap(pdev, adapter->io_addr);
 err_ioremap:
 	free_netdev(netdev);
 err_alloc_etherdev:
@@ -2823,7 +2825,7 @@ static void igb_remove(struct pci_dev *pdev)
 
 	igb_clear_interrupt_scheme(adapter);
 
-	pci_iounmap(pdev, hw->hw_addr);
+	pci_iounmap(pdev, adapter->io_addr);
 	if (hw->flash_address)
 		iounmap(hw->flash_address);
 	pci_release_selected_regions(pdev,
@@ -2856,6 +2858,13 @@ static void igb_probe_vfs(struct igb_adapter *adapter)
 	if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211))
 		return;
 
+	/* Of the below we really only want the effect of getting
+	 * IGB_FLAG_HAS_MSIX set (if available), without which
+	 * igb_enable_sriov() has no effect.
+	 */
+	igb_set_interrupt_capability(adapter, true);
+	igb_reset_interrupt_capability(adapter);
+
 	pci_sriov_set_totalvfs(pdev, 7);
 	igb_enable_sriov(pdev, max_vfs);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index aed8d029b23d..cd9b284bc83b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2786,7 +2786,8 @@ int ixgbe_poll(struct napi_struct *napi, int budget)
 	ixgbe_for_each_ring(ring, q_vector->tx)
 		clean_complete &= !!ixgbe_clean_tx_irq(q_vector, ring);
 
-	if (!ixgbe_qv_lock_napi(q_vector))
+	/* Exit if we are called by netpoll or busy polling is active */
+	if ((budget <= 0) || !ixgbe_qv_lock_napi(q_vector))
 		return budget;
 
 	/* attempt to distribute budget to each queue fairly, but don't allow
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 2e022e900939..7cc9df717323 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -399,6 +399,9 @@ static int mlx5e_get_coalesce(struct net_device *netdev,
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
+	if (!MLX5_CAP_GEN(priv->mdev, cq_moderation))
+		return -ENOTSUPP;
+
 	coal->rx_coalesce_usecs       = priv->params.rx_cq_moderation_usec;
 	coal->rx_max_coalesced_frames = priv->params.rx_cq_moderation_pkts;
 	coal->tx_coalesce_usecs       = priv->params.tx_cq_moderation_usec;
@@ -416,11 +419,18 @@ static int mlx5e_set_coalesce(struct net_device *netdev,
 	int tc;
 	int i;
 
+	if (!MLX5_CAP_GEN(mdev, cq_moderation))
+		return -ENOTSUPP;
+
+	mutex_lock(&priv->state_lock);
 	priv->params.tx_cq_moderation_usec = coal->tx_coalesce_usecs;
 	priv->params.tx_cq_moderation_pkts = coal->tx_max_coalesced_frames;
 	priv->params.rx_cq_moderation_usec = coal->rx_coalesce_usecs;
 	priv->params.rx_cq_moderation_pkts = coal->rx_max_coalesced_frames;
 
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto out;
+
 	for (i = 0; i < priv->params.num_channels; ++i) {
 		c = priv->channel[i];
 
@@ -436,6 +446,8 @@ static int mlx5e_set_coalesce(struct net_device *netdev,
 					       coal->rx_max_coalesced_frames);
 	}
 
+out:
+	mutex_unlock(&priv->state_lock);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index cbd17e25beeb..90e876ecc720 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -863,12 +863,10 @@ static int mlx5e_open_cq(struct mlx5e_channel *c,
 	if (err)
 		goto err_destroy_cq;
 
-	err = mlx5_core_modify_cq_moderation(mdev, &cq->mcq,
-					     moderation_usecs,
-					     moderation_frames);
-	if (err)
-		goto err_destroy_cq;
-
+	if (MLX5_CAP_GEN(mdev, cq_moderation))
+		mlx5_core_modify_cq_moderation(mdev, &cq->mcq,
+					       moderation_usecs,
+					       moderation_frames);
 	return 0;
 
 err_destroy_cq:
@@ -1963,6 +1961,8 @@ static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev)
 	}
 	if (!MLX5_CAP_ETH(mdev, self_lb_en_modifiable))
 		mlx5_core_warn(mdev, "Self loop back prevention is not supported\n");
+	if (!MLX5_CAP_GEN(mdev, cq_moderation))
+		mlx5_core_warn(mdev, "CQ modiration is not supported\n");
 
 	return 0;
 }
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 289a5df0d44a..c851bc53831c 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2725,7 +2725,7 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 	return 0;
 
  disable:
-	pci_release_regions(pdev);
+	pci_disable_device(pdev);
 
 	return result;
 }
diff --git a/drivers/pwm/pwm-fsl-ftm.c b/drivers/pwm/pwm-fsl-ftm.c
index f9dfc8b6407a..7225ac6b3df5 100644
--- a/drivers/pwm/pwm-fsl-ftm.c
+++ b/drivers/pwm/pwm-fsl-ftm.c
@@ -80,7 +80,6 @@ struct fsl_pwm_chip {
 
 	struct mutex lock;
 
-	unsigned int use_count;
 	unsigned int cnt_select;
 	unsigned int clk_ps;
 
@@ -300,9 +299,6 @@ static int fsl_counter_clock_enable(struct fsl_pwm_chip *fpc)
 {
 	int ret;
 
-	if (fpc->use_count++ != 0)
-		return 0;
-
 	/* select counter clock source */
 	regmap_update_bits(fpc->regmap, FTM_SC, FTM_SC_CLK_MASK,
 			   FTM_SC_CLK(fpc->cnt_select));
@@ -334,25 +330,6 @@ static int fsl_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
 	return ret;
 }
 
-static void fsl_counter_clock_disable(struct fsl_pwm_chip *fpc)
-{
-	/*
-	 * already disabled, do nothing
-	 */
-	if (fpc->use_count == 0)
-		return;
-
-	/* there are still users, so can't disable yet */
-	if (--fpc->use_count > 0)
-		return;
-
-	/* no users left, disable PWM counter clock */
-	regmap_update_bits(fpc->regmap, FTM_SC, FTM_SC_CLK_MASK, 0);
-
-	clk_disable_unprepare(fpc->clk[FSL_PWM_CLK_CNTEN]);
-	clk_disable_unprepare(fpc->clk[fpc->cnt_select]);
-}
-
 static void fsl_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
 {
 	struct fsl_pwm_chip *fpc = to_fsl_chip(chip);
@@ -362,7 +339,8 @@ static void fsl_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
 	regmap_update_bits(fpc->regmap, FTM_OUTMASK, BIT(pwm->hwpwm),
 			   BIT(pwm->hwpwm));
 
-	fsl_counter_clock_disable(fpc);
+	clk_disable_unprepare(fpc->clk[FSL_PWM_CLK_CNTEN]);
+	clk_disable_unprepare(fpc->clk[fpc->cnt_select]);
 
 	regmap_read(fpc->regmap, FTM_OUTMASK, &val);
 	if ((val & 0xFF) == 0xFF)
@@ -492,17 +470,24 @@ static int fsl_pwm_remove(struct platform_device *pdev)
 static int fsl_pwm_suspend(struct device *dev)
 {
 	struct fsl_pwm_chip *fpc = dev_get_drvdata(dev);
-	u32 val;
+	int i;
 
 	regcache_cache_only(fpc->regmap, true);
 	regcache_mark_dirty(fpc->regmap);
 
-	/* read from cache */
-	regmap_read(fpc->regmap, FTM_OUTMASK, &val);
-	if ((val & 0xFF) != 0xFF) {
+	for (i = 0; i < fpc->chip.npwm; i++) {
+		struct pwm_device *pwm = &fpc->chip.pwms[i];
+
+		if (!test_bit(PWMF_REQUESTED, &pwm->flags))
+			continue;
+
+		clk_disable_unprepare(fpc->clk[FSL_PWM_CLK_SYS]);
+
+		if (!pwm_is_enabled(pwm))
+			continue;
+
 		clk_disable_unprepare(fpc->clk[FSL_PWM_CLK_CNTEN]);
 		clk_disable_unprepare(fpc->clk[fpc->cnt_select]);
-		clk_disable_unprepare(fpc->clk[FSL_PWM_CLK_SYS]);
 	}
 
 	return 0;
@@ -511,12 +496,19 @@ static int fsl_pwm_suspend(struct device *dev)
 static int fsl_pwm_resume(struct device *dev)
 {
 	struct fsl_pwm_chip *fpc = dev_get_drvdata(dev);
-	u32 val;
+	int i;
+
+	for (i = 0; i < fpc->chip.npwm; i++) {
+		struct pwm_device *pwm = &fpc->chip.pwms[i];
+
+		if (!test_bit(PWMF_REQUESTED, &pwm->flags))
+			continue;
 
-	/* read from cache */
-	regmap_read(fpc->regmap, FTM_OUTMASK, &val);
-	if ((val & 0xFF) != 0xFF) {
 		clk_prepare_enable(fpc->clk[FSL_PWM_CLK_SYS]);
+
+		if (!pwm_is_enabled(pwm))
+			continue;
+
 		clk_prepare_enable(fpc->clk[fpc->cnt_select]);
 		clk_prepare_enable(fpc->clk[FSL_PWM_CLK_CNTEN]);
 	}
diff --git a/drivers/pwm/pwm-lpc32xx.c b/drivers/pwm/pwm-lpc32xx.c
index 9fde60ce8e7b..6e203a65effb 100644
--- a/drivers/pwm/pwm-lpc32xx.c
+++ b/drivers/pwm/pwm-lpc32xx.c
@@ -24,9 +24,7 @@ struct lpc32xx_pwm_chip {
 	void __iomem *base;
 };
 
-#define PWM_ENABLE	(1 << 31)
-#define PWM_RELOADV(x)	(((x) & 0xFF) << 8)
-#define PWM_DUTY(x)	((x) & 0xFF)
+#define PWM_ENABLE	BIT(31)
 
 #define to_lpc32xx_pwm_chip(_chip) \
 	container_of(_chip, struct lpc32xx_pwm_chip, chip)
@@ -38,40 +36,27 @@ static int lpc32xx_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	unsigned long long c;
 	int period_cycles, duty_cycles;
 	u32 val;
-
-	c = clk_get_rate(lpc32xx->clk) / 256;
-	c = c * period_ns;
-	do_div(c, NSEC_PER_SEC);
-
-	/* Handle high and low extremes */
-	if (c == 0)
-		c = 1;
-	if (c > 255)
-		c = 0; /* 0 set division by 256 */
-	period_cycles = c;
-
-	/* The duty-cycle value is as follows:
-	 *
-	 *  DUTY-CYCLE     HIGH LEVEL
-	 *      1            99.9%
-	 *      25           90.0%
-	 *      128          50.0%
-	 *      220          10.0%
-	 *      255           0.1%
-	 *      0             0.0%
-	 *
-	 * In other words, the register value is duty-cycle % 256 with
-	 * duty-cycle in the range 1-256.
-	 */
-	c = 256 * duty_ns;
-	do_div(c, period_ns);
-	if (c > 255)
-		c = 255;
-	duty_cycles = 256 - c;
+	c = clk_get_rate(lpc32xx->clk);
+
+	/* The highest acceptable divisor is 256, which is represented by 0 */
+	period_cycles = div64_u64(c * period_ns,
+			       (unsigned long long)NSEC_PER_SEC * 256);
+	if (!period_cycles)
+		period_cycles = 1;
+	if (period_cycles > 255)
+		period_cycles = 0;
+
+	/* Compute 256 x #duty/period value and care for corner cases */
+	duty_cycles = div64_u64((unsigned long long)(period_ns - duty_ns) * 256,
+				period_ns);
+	if (!duty_cycles)
+		duty_cycles = 1;
+	if (duty_cycles > 255)
+		duty_cycles = 255;
 
 	val = readl(lpc32xx->base + (pwm->hwpwm << 2));
 	val &= ~0xFFFF;
-	val |= PWM_RELOADV(period_cycles) | PWM_DUTY(duty_cycles);
+	val |= (period_cycles << 8) | duty_cycles;
 	writel(val, lpc32xx->base + (pwm->hwpwm << 2));
 
 	return 0;
@@ -134,7 +119,7 @@ static int lpc32xx_pwm_probe(struct platform_device *pdev)
 
 	lpc32xx->chip.dev = &pdev->dev;
 	lpc32xx->chip.ops = &lpc32xx_pwm_ops;
-	lpc32xx->chip.npwm = 2;
+	lpc32xx->chip.npwm = 1;
 	lpc32xx->chip.base = -1;
 
 	ret = pwmchip_add(&lpc32xx->chip);
diff --git a/drivers/regulator/anatop-regulator.c b/drivers/regulator/anatop-regulator.c
index 63cd5e68c864..3a6d0290c54c 100644
--- a/drivers/regulator/anatop-regulator.c
+++ b/drivers/regulator/anatop-regulator.c
@@ -296,7 +296,7 @@ static int anatop_regulator_probe(struct platform_device *pdev)
 		if (!sreg->sel && !strcmp(sreg->name, "vddpu"))
 			sreg->sel = 22;
 
-		if (!sreg->sel) {
+		if (!sreg->bypass && !sreg->sel) {
 			dev_err(&pdev->dev, "Failed to read a valid default voltage selector.\n");
 			return -EINVAL;
 		}
diff --git a/drivers/s390/char/sclp_ctl.c b/drivers/s390/char/sclp_ctl.c
index 648cb86afd42..ea607a4a1bdd 100644
--- a/drivers/s390/char/sclp_ctl.c
+++ b/drivers/s390/char/sclp_ctl.c
@@ -56,6 +56,7 @@ static int sclp_ctl_ioctl_sccb(void __user *user_area)
 {
 	struct sclp_ctl_sccb ctl_sccb;
 	struct sccb_header *sccb;
+	unsigned long copied;
 	int rc;
 
 	if (copy_from_user(&ctl_sccb, user_area, sizeof(ctl_sccb)))
@@ -65,14 +66,15 @@ static int sclp_ctl_ioctl_sccb(void __user *user_area)
 	sccb = (void *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
 	if (!sccb)
 		return -ENOMEM;
-	if (copy_from_user(sccb, u64_to_uptr(ctl_sccb.sccb), sizeof(*sccb))) {
+	copied = PAGE_SIZE -
+		copy_from_user(sccb, u64_to_uptr(ctl_sccb.sccb), PAGE_SIZE);
+	if (offsetof(struct sccb_header, length) +
+	    sizeof(sccb->length) > copied || sccb->length > copied) {
 		rc = -EFAULT;
 		goto out_free;
 	}
-	if (sccb->length > PAGE_SIZE || sccb->length < 8)
-		return -EINVAL;
-	if (copy_from_user(sccb, u64_to_uptr(ctl_sccb.sccb), sccb->length)) {
-		rc = -EFAULT;
+	if (sccb->length < 8) {
+		rc = -EINVAL;
 		goto out_free;
 	}
 	rc = sclp_sync_request(ctl_sccb.cmdw, sccb);
diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c
index c692dfebd0ba..50597f9522fe 100644
--- a/drivers/s390/cio/chp.c
+++ b/drivers/s390/cio/chp.c
@@ -139,11 +139,11 @@ static ssize_t chp_measurement_chars_read(struct file *filp,
 
 	device = container_of(kobj, struct device, kobj);
 	chp = to_channelpath(device);
-	if (!chp->cmg_chars)
+	if (chp->cmg == -1)
 		return 0;
 
-	return memory_read_from_buffer(buf, count, &off,
-				chp->cmg_chars, sizeof(struct cmg_chars));
+	return memory_read_from_buffer(buf, count, &off, &chp->cmg_chars,
+				       sizeof(chp->cmg_chars));
 }
 
 static struct bin_attribute chp_measurement_chars_attr = {
@@ -416,7 +416,8 @@ static void chp_release(struct device *dev)
  * chp_update_desc - update channel-path description
  * @chp - channel-path
  *
- * Update the channel-path description of the specified channel-path.
+ * Update the channel-path description of the specified channel-path
+ * including channel measurement related information.
  * Return zero on success, non-zero otherwise.
  */
 int chp_update_desc(struct channel_path *chp)
@@ -428,8 +429,10 @@ int chp_update_desc(struct channel_path *chp)
 		return rc;
 
 	rc = chsc_determine_fmt1_channel_path_desc(chp->chpid, &chp->desc_fmt1);
+	if (rc)
+		return rc;
 
-	return rc;
+	return chsc_get_channel_measurement_chars(chp);
 }
 
 /**
@@ -466,14 +469,6 @@ int chp_new(struct chp_id chpid)
 		ret = -ENODEV;
 		goto out_free;
 	}
-	/* Get channel-measurement characteristics. */
-	if (css_chsc_characteristics.scmc && css_chsc_characteristics.secm) {
-		ret = chsc_get_channel_measurement_chars(chp);
-		if (ret)
-			goto out_free;
-	} else {
-		chp->cmg = -1;
-	}
 	dev_set_name(&chp->dev, "chp%x.%02x", chpid.cssid, chpid.id);
 
 	/* make it known to the system */
diff --git a/drivers/s390/cio/chp.h b/drivers/s390/cio/chp.h
index 4efd5b867cc3..af0232290dc4 100644
--- a/drivers/s390/cio/chp.h
+++ b/drivers/s390/cio/chp.h
@@ -48,7 +48,7 @@ struct channel_path {
 	/* Channel-measurement related stuff: */
 	int cmg;
 	int shared;
-	void *cmg_chars;
+	struct cmg_chars cmg_chars;
 };
 
 /* Return channel_path struct for given chpid. */
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index a831d18596a5..c424c0c7367e 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/device.h>
+#include <linux/mutex.h>
 #include <linux/pci.h>
 
 #include <asm/cio.h>
@@ -224,8 +225,9 @@ out_unreg:
 
 void chsc_chp_offline(struct chp_id chpid)
 {
-	char dbf_txt[15];
+	struct channel_path *chp = chpid_to_chp(chpid);
 	struct chp_link link;
+	char dbf_txt[15];
 
 	sprintf(dbf_txt, "chpr%x.%02x", chpid.cssid, chpid.id);
 	CIO_TRACE_EVENT(2, dbf_txt);
@@ -236,6 +238,11 @@ void chsc_chp_offline(struct chp_id chpid)
 	link.chpid = chpid;
 	/* Wait until previous actions have settled. */
 	css_wait_for_slow_path();
+
+	mutex_lock(&chp->lock);
+	chp_update_desc(chp);
+	mutex_unlock(&chp->lock);
+
 	for_each_subchannel_staged(s390_subchannel_remove_chpid, NULL, &link);
 }
 
@@ -690,8 +697,9 @@ static void chsc_process_crw(struct crw *crw0, struct crw *crw1, int overflow)
 
 void chsc_chp_online(struct chp_id chpid)
 {
-	char dbf_txt[15];
+	struct channel_path *chp = chpid_to_chp(chpid);
 	struct chp_link link;
+	char dbf_txt[15];
 
 	sprintf(dbf_txt, "cadd%x.%02x", chpid.cssid, chpid.id);
 	CIO_TRACE_EVENT(2, dbf_txt);
@@ -701,6 +709,11 @@ void chsc_chp_online(struct chp_id chpid)
 		link.chpid = chpid;
 		/* Wait until previous actions have settled. */
 		css_wait_for_slow_path();
+
+		mutex_lock(&chp->lock);
+		chp_update_desc(chp);
+		mutex_unlock(&chp->lock);
+
 		for_each_subchannel_staged(__s390_process_res_acc, NULL,
 					   &link);
 		css_schedule_reprobe();
@@ -967,22 +980,19 @@ static void
 chsc_initialize_cmg_chars(struct channel_path *chp, u8 cmcv,
 			  struct cmg_chars *chars)
 {
-	struct cmg_chars *cmg_chars;
 	int i, mask;
 
-	cmg_chars = chp->cmg_chars;
 	for (i = 0; i < NR_MEASUREMENT_CHARS; i++) {
 		mask = 0x80 >> (i + 3);
 		if (cmcv & mask)
-			cmg_chars->values[i] = chars->values[i];
+			chp->cmg_chars.values[i] = chars->values[i];
 		else
-			cmg_chars->values[i] = 0;
+			chp->cmg_chars.values[i] = 0;
 	}
 }
 
 int chsc_get_channel_measurement_chars(struct channel_path *chp)
 {
-	struct cmg_chars *cmg_chars;
 	int ccode, ret;
 
 	struct {
@@ -1006,10 +1016,11 @@ int chsc_get_channel_measurement_chars(struct channel_path *chp)
 		u32 data[NR_MEASUREMENT_CHARS];
 	} __attribute__ ((packed)) *scmc_area;
 
-	chp->cmg_chars = NULL;
-	cmg_chars = kmalloc(sizeof(*cmg_chars), GFP_KERNEL);
-	if (!cmg_chars)
-		return -ENOMEM;
+	chp->shared = -1;
+	chp->cmg = -1;
+
+	if (!css_chsc_characteristics.scmc || !css_chsc_characteristics.secm)
+		return 0;
 
 	spin_lock_irq(&chsc_page_lock);
 	memset(chsc_page, 0, PAGE_SIZE);
@@ -1031,25 +1042,19 @@ int chsc_get_channel_measurement_chars(struct channel_path *chp)
 			      scmc_area->response.code);
 		goto out;
 	}
-	if (scmc_area->not_valid) {
-		chp->cmg = -1;
-		chp->shared = -1;
+	if (scmc_area->not_valid)
 		goto out;
-	}
+
 	chp->cmg = scmc_area->cmg;
 	chp->shared = scmc_area->shared;
 	if (chp->cmg != 2 && chp->cmg != 3) {
 		/* No cmg-dependent data. */
 		goto out;
 	}
-	chp->cmg_chars = cmg_chars;
 	chsc_initialize_cmg_chars(chp, scmc_area->cmcv,
 				  (struct cmg_chars *) &scmc_area->data);
 out:
 	spin_unlock_irq(&chsc_page_lock);
-	if (!chp->cmg_chars)
-		kfree(cmg_chars);
-
 	return ret;
 }
 
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 12b2cb7769f9..df036b872b05 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1127,6 +1127,7 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 	qeth_l2_request_initial_mac(card);
 	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
 	netif_napi_add(card->dev, &card->napi, qeth_l2_poll, QETH_NAPI_WEIGHT);
+	netif_carrier_off(card->dev);
 	return register_netdev(card->dev);
 }
 
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 50cec6b13d27..cc4d3c3d8cc5 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3220,6 +3220,7 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 
 	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
 	netif_napi_add(card->dev, &card->napi, qeth_l3_poll, QETH_NAPI_WEIGHT);
+	netif_carrier_off(card->dev);
 	return register_netdev(card->dev);
 }
 
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index 333db5953607..41f9a00e4f74 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -2664,7 +2664,7 @@ static bool arcmsr_hbaB_get_config(struct AdapterControlBlock *acb)
 	if (!arcmsr_hbaB_wait_msgint_ready(acb)) {
 		printk(KERN_NOTICE "arcmsr%d: wait 'get adapter firmware \
 			miscellaneous data' timeout \n", acb->host->host_no);
-		return false;
+		goto err_free_dma;
 	}
 	count = 8;
 	while (count){
@@ -2694,19 +2694,23 @@ static bool arcmsr_hbaB_get_config(struct AdapterControlBlock *acb)
 		acb->firm_model,
 		acb->firm_version);
 
-	acb->signature = readl(&reg->message_rwbuffer[1]);
+	acb->signature = readl(&reg->message_rwbuffer[0]);
 	/*firm_signature,1,00-03*/
-	acb->firm_request_len = readl(&reg->message_rwbuffer[2]);
+	acb->firm_request_len = readl(&reg->message_rwbuffer[1]);
 	/*firm_request_len,1,04-07*/
-	acb->firm_numbers_queue = readl(&reg->message_rwbuffer[3]);
+	acb->firm_numbers_queue = readl(&reg->message_rwbuffer[2]);
 	/*firm_numbers_queue,2,08-11*/
-	acb->firm_sdram_size = readl(&reg->message_rwbuffer[4]);
+	acb->firm_sdram_size = readl(&reg->message_rwbuffer[3]);
 	/*firm_sdram_size,3,12-15*/
-	acb->firm_hd_channels = readl(&reg->message_rwbuffer[5]);
+	acb->firm_hd_channels = readl(&reg->message_rwbuffer[4]);
 	/*firm_ide_channels,4,16-19*/
 	acb->firm_cfg_version = readl(&reg->message_rwbuffer[25]);  /*firm_cfg_version,25,100-103*/
 	/*firm_ide_channels,4,16-19*/
 	return true;
+err_free_dma:
+	dma_free_coherent(&acb->pdev->dev, acb->roundup_ccbsize,
+			acb->dma_coherent2, acb->dma_coherent_handle2);
+	return false;
 }
 
 static bool arcmsr_hbaC_get_config(struct AdapterControlBlock *pACB)
@@ -2880,15 +2884,15 @@ static bool arcmsr_hbaD_get_config(struct AdapterControlBlock *acb)
 		iop_device_map++;
 		count--;
 	}
-	acb->signature = readl(&reg->msgcode_rwbuffer[1]);
+	acb->signature = readl(&reg->msgcode_rwbuffer[0]);
 	/*firm_signature,1,00-03*/
-	acb->firm_request_len = readl(&reg->msgcode_rwbuffer[2]);
+	acb->firm_request_len = readl(&reg->msgcode_rwbuffer[1]);
 	/*firm_request_len,1,04-07*/
-	acb->firm_numbers_queue = readl(&reg->msgcode_rwbuffer[3]);
+	acb->firm_numbers_queue = readl(&reg->msgcode_rwbuffer[2]);
 	/*firm_numbers_queue,2,08-11*/
-	acb->firm_sdram_size = readl(&reg->msgcode_rwbuffer[4]);
+	acb->firm_sdram_size = readl(&reg->msgcode_rwbuffer[3]);
 	/*firm_sdram_size,3,12-15*/
-	acb->firm_hd_channels = readl(&reg->msgcode_rwbuffer[5]);
+	acb->firm_hd_channels = readl(&reg->msgcode_rwbuffer[4]);
 	/*firm_hd_channels,4,16-19*/
 	acb->firm_cfg_version = readl(&reg->msgcode_rwbuffer[25]);
 	pr_notice("Areca RAID Controller%d: Model %s, F/W %s\n",
diff --git a/drivers/scsi/constants.c b/drivers/scsi/constants.c
index fa09d4be2b53..2b456ca69d5c 100644
--- a/drivers/scsi/constants.c
+++ b/drivers/scsi/constants.c
@@ -1181,8 +1181,9 @@ static const char * const snstext[] = {
 
 /* Get sense key string or NULL if not available */
 const char *
-scsi_sense_key_string(unsigned char key) {
-	if (key <= 0xE)
+scsi_sense_key_string(unsigned char key)
+{
+	if (key < ARRAY_SIZE(snstext))
 		return snstext[key];
 	return NULL;
 }
diff --git a/drivers/scsi/cxlflash/common.h b/drivers/scsi/cxlflash/common.h
index c11cd193f896..5ada9268a450 100644
--- a/drivers/scsi/cxlflash/common.h
+++ b/drivers/scsi/cxlflash/common.h
@@ -165,6 +165,8 @@ struct afu {
 	struct sisl_host_map __iomem *host_map;		/* MC host map */
 	struct sisl_ctrl_map __iomem *ctrl_map;		/* MC control map */
 
+	struct kref mapcount;
+
 	ctx_hndl_t ctx_hndl;	/* master's context handle */
 	u64 *hrrq_start;
 	u64 *hrrq_end;
diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c
index 1e5bf0ca81da..c86847c68448 100644
--- a/drivers/scsi/cxlflash/main.c
+++ b/drivers/scsi/cxlflash/main.c
@@ -289,7 +289,7 @@ static void context_reset(struct afu_cmd *cmd)
 		atomic64_set(&afu->room, room);
 		if (room)
 			goto write_rrin;
-		udelay(nretry);
+		udelay(1 << nretry);
 	} while (nretry++ < MC_ROOM_RETRY_CNT);
 
 	pr_err("%s: no cmd_room to send reset\n", __func__);
@@ -303,7 +303,7 @@ write_rrin:
 		if (rrin != 0x1)
 			break;
 		/* Double delay each time */
-		udelay(2 << nretry);
+		udelay(1 << nretry);
 	} while (nretry++ < MC_ROOM_RETRY_CNT);
 }
 
@@ -338,7 +338,7 @@ retry:
 			atomic64_set(&afu->room, room);
 			if (room)
 				goto write_ioarrin;
-			udelay(nretry);
+			udelay(1 << nretry);
 		} while (nretry++ < MC_ROOM_RETRY_CNT);
 
 		dev_err(dev, "%s: no cmd_room to send 0x%X\n",
@@ -352,7 +352,7 @@ retry:
 		 * afu->room.
 		 */
 		if (nretry++ < MC_ROOM_RETRY_CNT) {
-			udelay(nretry);
+			udelay(1 << nretry);
 			goto retry;
 		}
 
@@ -368,6 +368,7 @@ out:
 
 no_room:
 	afu->read_room = true;
+	kref_get(&cfg->afu->mapcount);
 	schedule_work(&cfg->work_q);
 	rc = SCSI_MLQUEUE_HOST_BUSY;
 	goto out;
@@ -473,6 +474,16 @@ out:
 	return rc;
 }
 
+static void afu_unmap(struct kref *ref)
+{
+	struct afu *afu = container_of(ref, struct afu, mapcount);
+
+	if (likely(afu->afu_map)) {
+		cxl_psa_unmap((void __iomem *)afu->afu_map);
+		afu->afu_map = NULL;
+	}
+}
+
 /**
  * cxlflash_driver_info() - information handler for this host driver
  * @host:	SCSI host associated with device.
@@ -503,6 +514,7 @@ static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
 	ulong lock_flags;
 	short lflag = 0;
 	int rc = 0;
+	int kref_got = 0;
 
 	dev_dbg_ratelimited(dev, "%s: (scp=%p) %d/%d/%d/%llu "
 			    "cdb=(%08X-%08X-%08X-%08X)\n",
@@ -547,6 +559,9 @@ static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
 		goto out;
 	}
 
+	kref_get(&cfg->afu->mapcount);
+	kref_got = 1;
+
 	cmd->rcb.ctx_id = afu->ctx_hndl;
 	cmd->rcb.port_sel = port_sel;
 	cmd->rcb.lun_id = lun_to_lunid(scp->device->lun);
@@ -587,6 +602,8 @@ static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
 	}
 
 out:
+	if (kref_got)
+		kref_put(&afu->mapcount, afu_unmap);
 	pr_devel("%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
@@ -632,20 +649,36 @@ static void free_mem(struct cxlflash_cfg *cfg)
  * @cfg:	Internal structure associated with the host.
  *
  * Safe to call with AFU in a partially allocated/initialized state.
+ *
+ * Cleans up all state associated with the command queue, and unmaps
+ * the MMIO space.
+ *
+ *  - complete() will take care of commands we initiated (they'll be checked
+ *  in as part of the cleanup that occurs after the completion)
+ *
+ *  - cmd_checkin() will take care of entries that we did not initiate and that
+ *  have not (and will not) complete because they are sitting on a [now stale]
+ *  hardware queue
  */
 static void stop_afu(struct cxlflash_cfg *cfg)
 {
 	int i;
 	struct afu *afu = cfg->afu;
+	struct afu_cmd *cmd;
 
 	if (likely(afu)) {
-		for (i = 0; i < CXLFLASH_NUM_CMDS; i++)
-			complete(&afu->cmd[i].cevent);
+		for (i = 0; i < CXLFLASH_NUM_CMDS; i++) {
+			cmd = &afu->cmd[i];
+			complete(&cmd->cevent);
+			if (!atomic_read(&cmd->free))
+				cmd_checkin(cmd);
+		}
 
 		if (likely(afu->afu_map)) {
 			cxl_psa_unmap((void __iomem *)afu->afu_map);
 			afu->afu_map = NULL;
 		}
+		kref_put(&afu->mapcount, afu_unmap);
 	}
 }
 
@@ -731,8 +764,8 @@ static void cxlflash_remove(struct pci_dev *pdev)
 		scsi_remove_host(cfg->host);
 		/* fall through */
 	case INIT_STATE_AFU:
-		term_afu(cfg);
 		cancel_work_sync(&cfg->work_q);
+		term_afu(cfg);
 	case INIT_STATE_PCI:
 		pci_release_regions(cfg->dev);
 		pci_disable_device(pdev);
@@ -1108,7 +1141,7 @@ static const struct asyc_intr_info ainfo[] = {
 	{SISL_ASTATUS_FC1_OTHER, "other error", 1, CLR_FC_ERROR | LINK_RESET},
 	{SISL_ASTATUS_FC1_LOGO, "target initiated LOGO", 1, 0},
 	{SISL_ASTATUS_FC1_CRC_T, "CRC threshold exceeded", 1, LINK_RESET},
-	{SISL_ASTATUS_FC1_LOGI_R, "login timed out, retrying", 1, 0},
+	{SISL_ASTATUS_FC1_LOGI_R, "login timed out, retrying", 1, LINK_RESET},
 	{SISL_ASTATUS_FC1_LOGI_F, "login failed", 1, CLR_FC_ERROR},
 	{SISL_ASTATUS_FC1_LOGI_S, "login succeeded", 1, SCAN_HOST},
 	{SISL_ASTATUS_FC1_LINK_DN, "link down", 1, 0},
@@ -1316,6 +1349,7 @@ static irqreturn_t cxlflash_async_err_irq(int irq, void *data)
 				__func__, port);
 			cfg->lr_state = LINK_RESET_REQUIRED;
 			cfg->lr_port = port;
+			kref_get(&cfg->afu->mapcount);
 			schedule_work(&cfg->work_q);
 		}
 
@@ -1336,6 +1370,7 @@ static irqreturn_t cxlflash_async_err_irq(int irq, void *data)
 
 		if (info->action & SCAN_HOST) {
 			atomic_inc(&cfg->scan_host_needed);
+			kref_get(&cfg->afu->mapcount);
 			schedule_work(&cfg->work_q);
 		}
 	}
@@ -1731,6 +1766,7 @@ static int init_afu(struct cxlflash_cfg *cfg)
 		rc = -ENOMEM;
 		goto err1;
 	}
+	kref_init(&afu->mapcount);
 
 	/* No byte reverse on reading afu_version or string will be backwards */
 	reg = readq(&afu->afu_map->global.regs.afu_version);
@@ -1765,8 +1801,7 @@ out:
 	return rc;
 
 err2:
-	cxl_psa_unmap((void __iomem *)afu->afu_map);
-	afu->afu_map = NULL;
+	kref_put(&afu->mapcount, afu_unmap);
 err1:
 	term_mc(cfg, UNDO_START);
 	goto out;
@@ -2114,6 +2149,16 @@ static ssize_t lun_mode_store(struct device *dev,
 	rc = kstrtouint(buf, 10, &lun_mode);
 	if (!rc && (lun_mode < 5) && (lun_mode != afu->internal_lun)) {
 		afu->internal_lun = lun_mode;
+
+		/*
+		 * When configured for internal LUN, there is only one channel,
+		 * channel number 0, else there will be 2 (default).
+		 */
+		if (afu->internal_lun)
+			shost->max_channel = 0;
+		else
+			shost->max_channel = NUM_FC_PORTS - 1;
+
 		afu_reset(cfg);
 		scsi_scan_host(cfg->host);
 	}
@@ -2274,6 +2319,7 @@ static struct scsi_host_template driver_template = {
  * Device dependent values
  */
 static struct dev_dependent_vals dev_corsa_vals = { CXLFLASH_MAX_SECTORS };
+static struct dev_dependent_vals dev_flash_gt_vals = { CXLFLASH_MAX_SECTORS };
 
 /*
  * PCI device binding table
@@ -2281,6 +2327,8 @@ static struct dev_dependent_vals dev_corsa_vals = { CXLFLASH_MAX_SECTORS };
 static struct pci_device_id cxlflash_pci_table[] = {
 	{PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CORSA,
 	 PCI_ANY_ID, PCI_ANY_ID, 0, 0, (kernel_ulong_t)&dev_corsa_vals},
+	{PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_FLASH_GT,
+	 PCI_ANY_ID, PCI_ANY_ID, 0, 0, (kernel_ulong_t)&dev_flash_gt_vals},
 	{}
 };
 
@@ -2339,6 +2387,7 @@ static void cxlflash_worker_thread(struct work_struct *work)
 
 	if (atomic_dec_if_positive(&cfg->scan_host_needed) >= 0)
 		scsi_scan_host(cfg->host);
+	kref_put(&afu->mapcount, afu_unmap);
 }
 
 /**
diff --git a/drivers/scsi/cxlflash/main.h b/drivers/scsi/cxlflash/main.h
index 60324566c14f..3d2d606fafb3 100644
--- a/drivers/scsi/cxlflash/main.h
+++ b/drivers/scsi/cxlflash/main.h
@@ -24,8 +24,8 @@
 #define CXLFLASH_ADAPTER_NAME	"IBM POWER CXL Flash Adapter"
 #define CXLFLASH_DRIVER_DATE	"(August 13, 2015)"
 
-#define PCI_DEVICE_ID_IBM_CORSA	0x04F0
-#define CXLFLASH_SUBS_DEV_ID	0x04F0
+#define PCI_DEVICE_ID_IBM_CORSA		0x04F0
+#define PCI_DEVICE_ID_IBM_FLASH_GT	0x0600
 
 /* Since there is only one target, make it 0 */
 #define CXLFLASH_TARGET		0
diff --git a/drivers/scsi/cxlflash/superpipe.c b/drivers/scsi/cxlflash/superpipe.c
index cac2e6a50efd..babe7ccc1777 100644
--- a/drivers/scsi/cxlflash/superpipe.c
+++ b/drivers/scsi/cxlflash/superpipe.c
@@ -1380,7 +1380,7 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 	}
 
 	ctxid = cxl_process_element(ctx);
-	if (unlikely((ctxid > MAX_CONTEXT) || (ctxid < 0))) {
+	if (unlikely((ctxid >= MAX_CONTEXT) || (ctxid < 0))) {
 		dev_err(dev, "%s: ctxid (%d) invalid!\n", __func__, ctxid);
 		rc = -EPERM;
 		goto err2;
@@ -1508,7 +1508,7 @@ static int recover_context(struct cxlflash_cfg *cfg, struct ctx_info *ctxi)
 	}
 
 	ctxid = cxl_process_element(ctx);
-	if (unlikely((ctxid > MAX_CONTEXT) || (ctxid < 0))) {
+	if (unlikely((ctxid >= MAX_CONTEXT) || (ctxid < 0))) {
 		dev_err(dev, "%s: ctxid (%d) invalid!\n", __func__, ctxid);
 		rc = -EPERM;
 		goto err1;
@@ -1590,6 +1590,13 @@ err1:
  * place at the same time and the failure was due to CXL services being
  * unable to keep up.
  *
+ * As this routine is called on ioctl context, it holds the ioctl r/w
+ * semaphore that is used to drain ioctls in recovery scenarios. The
+ * implementation to achieve the pacing described above (a local mutex)
+ * requires that the ioctl r/w semaphore be dropped and reacquired to
+ * avoid a 3-way deadlock when multiple process recoveries operate in
+ * parallel.
+ *
  * Because a user can detect an error condition before the kernel, it is
  * quite possible for this routine to act as the kernel's EEH detection
  * source (MMIO read of mbox_r). Because of this, there is a window of
@@ -1617,9 +1624,17 @@ static int cxlflash_afu_recover(struct scsi_device *sdev,
 	int rc = 0;
 
 	atomic_inc(&cfg->recovery_threads);
+	up_read(&cfg->ioctl_rwsem);
 	rc = mutex_lock_interruptible(mutex);
+	down_read(&cfg->ioctl_rwsem);
 	if (rc)
 		goto out;
+	rc = check_state(cfg);
+	if (rc) {
+		dev_err(dev, "%s: Failed state! rc=%d\n", __func__, rc);
+		rc = -ENODEV;
+		goto out;
+	}
 
 	dev_dbg(dev, "%s: reason 0x%016llX rctxid=%016llX\n",
 		__func__, recover->reason, rctxid);
diff --git a/drivers/scsi/cxlflash/vlun.c b/drivers/scsi/cxlflash/vlun.c
index a53f583e2d7b..50f8e9300770 100644
--- a/drivers/scsi/cxlflash/vlun.c
+++ b/drivers/scsi/cxlflash/vlun.c
@@ -1008,6 +1008,8 @@ int cxlflash_disk_virtual_open(struct scsi_device *sdev, void *arg)
 	virt->last_lba = last_lba;
 	virt->rsrc_handle = rsrc_handle;
 
+	if (lli->port_sel == BOTH_PORTS)
+		virt->hdr.return_flags |= DK_CXLFLASH_ALL_PORTS_ACTIVE;
 out:
 	if (likely(ctxi))
 		put_context(ctxi);
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index b0e6fe46448d..80d3c740a8a8 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -72,6 +72,7 @@ void lpfc_cancel_all_vport_retry_delay_timer(struct lpfc_hba *);
 void lpfc_retry_pport_discovery(struct lpfc_hba *);
 void lpfc_release_rpi(struct lpfc_hba *, struct lpfc_vport *, uint16_t);
 
+void lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_mbx_cmpl_reg_login(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_mbx_cmpl_dflt_rpi(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_mbx_cmpl_fabric_reg_login(struct lpfc_hba *, LPFC_MBOXQ_t *);
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index b6fa257ea3e0..59ced8864b2f 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -455,9 +455,9 @@ int
 lpfc_issue_reg_vfi(struct lpfc_vport *vport)
 {
 	struct lpfc_hba  *phba = vport->phba;
-	LPFC_MBOXQ_t *mboxq;
+	LPFC_MBOXQ_t *mboxq = NULL;
 	struct lpfc_nodelist *ndlp;
-	struct lpfc_dmabuf *dmabuf;
+	struct lpfc_dmabuf *dmabuf = NULL;
 	int rc = 0;
 
 	/* move forward in case of SLI4 FC port loopback test and pt2pt mode */
@@ -471,25 +471,33 @@ lpfc_issue_reg_vfi(struct lpfc_vport *vport)
 		}
 	}
 
-	dmabuf = kzalloc(sizeof(struct lpfc_dmabuf), GFP_KERNEL);
-	if (!dmabuf) {
+	mboxq = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+	if (!mboxq) {
 		rc = -ENOMEM;
 		goto fail;
 	}
-	dmabuf->virt = lpfc_mbuf_alloc(phba, MEM_PRI, &dmabuf->phys);
-	if (!dmabuf->virt) {
-		rc = -ENOMEM;
-		goto fail_free_dmabuf;
-	}
 
-	mboxq = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
-	if (!mboxq) {
-		rc = -ENOMEM;
-		goto fail_free_coherent;
+	/* Supply CSP's only if we are fabric connect or pt-to-pt connect */
+	if ((vport->fc_flag & FC_FABRIC) || (vport->fc_flag & FC_PT2PT)) {
+		dmabuf = kzalloc(sizeof(struct lpfc_dmabuf), GFP_KERNEL);
+		if (!dmabuf) {
+			rc = -ENOMEM;
+			goto fail;
+		}
+		dmabuf->virt = lpfc_mbuf_alloc(phba, MEM_PRI, &dmabuf->phys);
+		if (!dmabuf->virt) {
+			rc = -ENOMEM;
+			goto fail;
+		}
+		memcpy(dmabuf->virt, &phba->fc_fabparam,
+		       sizeof(struct serv_parm));
 	}
+
 	vport->port_state = LPFC_FABRIC_CFG_LINK;
-	memcpy(dmabuf->virt, &phba->fc_fabparam, sizeof(vport->fc_sparam));
-	lpfc_reg_vfi(mboxq, vport, dmabuf->phys);
+	if (dmabuf)
+		lpfc_reg_vfi(mboxq, vport, dmabuf->phys);
+	else
+		lpfc_reg_vfi(mboxq, vport, 0);
 
 	mboxq->mbox_cmpl = lpfc_mbx_cmpl_reg_vfi;
 	mboxq->vport = vport;
@@ -497,17 +505,19 @@ lpfc_issue_reg_vfi(struct lpfc_vport *vport)
 	rc = lpfc_sli_issue_mbox(phba, mboxq, MBX_NOWAIT);
 	if (rc == MBX_NOT_FINISHED) {
 		rc = -ENXIO;
-		goto fail_free_mbox;
+		goto fail;
 	}
 	return 0;
 
-fail_free_mbox:
-	mempool_free(mboxq, phba->mbox_mem_pool);
-fail_free_coherent:
-	lpfc_mbuf_free(phba, dmabuf->virt, dmabuf->phys);
-fail_free_dmabuf:
-	kfree(dmabuf);
 fail:
+	if (mboxq)
+		mempool_free(mboxq, phba->mbox_mem_pool);
+	if (dmabuf) {
+		if (dmabuf->virt)
+			lpfc_mbuf_free(phba, dmabuf->virt, dmabuf->phys);
+		kfree(dmabuf);
+	}
+
 	lpfc_vport_set_state(vport, FC_VPORT_FAILED);
 	lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS,
 		"0289 Issue Register VFI failed: Err %d\n", rc);
@@ -711,9 +721,10 @@ lpfc_cmpl_els_flogi_fabric(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	 * For FC we need to do some special processing because of the SLI
 	 * Port's default settings of the Common Service Parameters.
 	 */
-	if (phba->sli4_hba.lnk_info.lnk_tp == LPFC_LNK_TYPE_FC) {
+	if ((phba->sli_rev == LPFC_SLI_REV4) &&
+	    (phba->sli4_hba.lnk_info.lnk_tp == LPFC_LNK_TYPE_FC)) {
 		/* If physical FC port changed, unreg VFI and ALL VPIs / RPIs */
-		if ((phba->sli_rev == LPFC_SLI_REV4) && fabric_param_changed)
+		if (fabric_param_changed)
 			lpfc_unregister_fcf_prep(phba);
 
 		/* This should just update the VFI CSPs*/
@@ -824,13 +835,21 @@ lpfc_cmpl_els_flogi_nport(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	spin_lock_irq(shost->host_lock);
 	vport->fc_flag &= ~(FC_FABRIC | FC_PUBLIC_LOOP);
+	vport->fc_flag |= FC_PT2PT;
 	spin_unlock_irq(shost->host_lock);
 
-	phba->fc_edtov = FF_DEF_EDTOV;
-	phba->fc_ratov = FF_DEF_RATOV;
+	/* If physical FC port changed, unreg VFI and ALL VPIs / RPIs */
+	if ((phba->sli_rev == LPFC_SLI_REV4) && phba->fc_topology_changed) {
+		lpfc_unregister_fcf_prep(phba);
+
+		spin_lock_irq(shost->host_lock);
+		vport->fc_flag &= ~FC_VFI_REGISTERED;
+		spin_unlock_irq(shost->host_lock);
+		phba->fc_topology_changed = 0;
+	}
+
 	rc = memcmp(&vport->fc_portname, &sp->portName,
 		    sizeof(vport->fc_portname));
-	memcpy(&phba->fc_fabparam, sp, sizeof(struct serv_parm));
 
 	if (rc >= 0) {
 		/* This side will initiate the PLOGI */
@@ -839,38 +858,14 @@ lpfc_cmpl_els_flogi_nport(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		spin_unlock_irq(shost->host_lock);
 
 		/*
-		 * N_Port ID cannot be 0, set our to LocalID the other
-		 * side will be RemoteID.
+		 * N_Port ID cannot be 0, set our Id to LocalID
+		 * the other side will be RemoteID.
 		 */
 
 		/* not equal */
 		if (rc)
 			vport->fc_myDID = PT2PT_LocalID;
 
-		mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
-		if (!mbox)
-			goto fail;
-
-		lpfc_config_link(phba, mbox);
-
-		mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
-		mbox->vport = vport;
-		rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
-		if (rc == MBX_NOT_FINISHED) {
-			mempool_free(mbox, phba->mbox_mem_pool);
-			goto fail;
-		}
-
-		/*
-		 * For SLI4, the VFI/VPI are registered AFTER the
-		 * Nport with the higher WWPN sends the PLOGI with
-		 * an assigned NPortId.
-		 */
-
-		/* not equal */
-		if ((phba->sli_rev == LPFC_SLI_REV4) && rc)
-			lpfc_issue_reg_vfi(vport);
-
 		/* Decrement ndlp reference count indicating that ndlp can be
 		 * safely released when other references to it are done.
 		 */
@@ -912,29 +907,20 @@ lpfc_cmpl_els_flogi_nport(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	/* If we are pt2pt with another NPort, force NPIV off! */
 	phba->sli3_options &= ~LPFC_SLI3_NPIV_ENABLED;
 
-	spin_lock_irq(shost->host_lock);
-	vport->fc_flag |= FC_PT2PT;
-	spin_unlock_irq(shost->host_lock);
-	/* If physical FC port changed, unreg VFI and ALL VPIs / RPIs */
-	if ((phba->sli_rev == LPFC_SLI_REV4) && phba->fc_topology_changed) {
-		lpfc_unregister_fcf_prep(phba);
+	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+	if (!mbox)
+		goto fail;
 
-		/* The FC_VFI_REGISTERED flag will get clear in the cmpl
-		 * handler for unreg_vfi, but if we don't force the
-		 * FC_VFI_REGISTERED flag then the reg_vfi mailbox could be
-		 * built with the update bit set instead of just the vp bit to
-		 * change the Nport ID.  We need to have the vp set and the
-		 * Upd cleared on topology changes.
-		 */
-		spin_lock_irq(shost->host_lock);
-		vport->fc_flag &= ~FC_VFI_REGISTERED;
-		spin_unlock_irq(shost->host_lock);
-		phba->fc_topology_changed = 0;
-		lpfc_issue_reg_vfi(vport);
+	lpfc_config_link(phba, mbox);
+
+	mbox->mbox_cmpl = lpfc_mbx_cmpl_local_config_link;
+	mbox->vport = vport;
+	rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
+	if (rc == MBX_NOT_FINISHED) {
+		mempool_free(mbox, phba->mbox_mem_pool);
+		goto fail;
 	}
 
-	/* Start discovery - this should just do CLEAR_LA */
-	lpfc_disc_start(vport);
 	return 0;
 fail:
 	return -ENXIO;
@@ -1157,6 +1143,7 @@ flogifail:
 	spin_lock_irq(&phba->hbalock);
 	phba->fcf.fcf_flag &= ~FCF_DISCOVERY;
 	spin_unlock_irq(&phba->hbalock);
+
 	lpfc_nlp_put(ndlp);
 
 	if (!lpfc_error_lost_link(irsp)) {
@@ -3792,14 +3779,17 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 				lpfc_nlp_set_state(vport, ndlp,
 					   NLP_STE_REG_LOGIN_ISSUE);
 			}
+
+			ndlp->nlp_flag |= NLP_REG_LOGIN_SEND;
 			if (lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT)
 			    != MBX_NOT_FINISHED)
 				goto out;
-			else
-				/* Decrement the ndlp reference count we
-				 * set for this failed mailbox command.
-				 */
-				lpfc_nlp_put(ndlp);
+
+			/* Decrement the ndlp reference count we
+			 * set for this failed mailbox command.
+			 */
+			lpfc_nlp_put(ndlp);
+			ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
 
 			/* ELS rsp: Cannot issue reg_login for <NPortid> */
 			lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS,
@@ -3856,6 +3846,7 @@ out:
 				 * the routine lpfc_els_free_iocb.
 				 */
 				cmdiocb->context1 = NULL;
+
 	}
 
 	lpfc_els_free_iocb(phba, cmdiocb);
@@ -3898,6 +3889,7 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 	IOCB_t *oldcmd;
 	struct lpfc_iocbq *elsiocb;
 	uint8_t *pcmd;
+	struct serv_parm *sp;
 	uint16_t cmdsize;
 	int rc;
 	ELS_PKT *els_pkt_ptr;
@@ -3927,6 +3919,7 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 			"Issue ACC:       did:x%x flg:x%x",
 			ndlp->nlp_DID, ndlp->nlp_flag, 0);
 		break;
+	case ELS_CMD_FLOGI:
 	case ELS_CMD_PLOGI:
 		cmdsize = (sizeof(struct serv_parm) + sizeof(uint32_t));
 		elsiocb = lpfc_prep_els_iocb(vport, 0, cmdsize, oldiocb->retry,
@@ -3944,10 +3937,34 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 
 		*((uint32_t *) (pcmd)) = ELS_CMD_ACC;
 		pcmd += sizeof(uint32_t);
-		memcpy(pcmd, &vport->fc_sparam, sizeof(struct serv_parm));
+		sp = (struct serv_parm *)pcmd;
+
+		if (flag == ELS_CMD_FLOGI) {
+			/* Copy the received service parameters back */
+			memcpy(sp, &phba->fc_fabparam,
+			       sizeof(struct serv_parm));
+
+			/* Clear the F_Port bit */
+			sp->cmn.fPort = 0;
+
+			/* Mark all class service parameters as invalid */
+			sp->cls1.classValid = 0;
+			sp->cls2.classValid = 0;
+			sp->cls3.classValid = 0;
+			sp->cls4.classValid = 0;
+
+			/* Copy our worldwide names */
+			memcpy(&sp->portName, &vport->fc_sparam.portName,
+			       sizeof(struct lpfc_name));
+			memcpy(&sp->nodeName, &vport->fc_sparam.nodeName,
+			       sizeof(struct lpfc_name));
+		} else {
+			memcpy(pcmd, &vport->fc_sparam,
+			       sizeof(struct serv_parm));
+		}
 
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
-			"Issue ACC PLOGI: did:x%x flg:x%x",
+			"Issue ACC FLOGI/PLOGI: did:x%x flg:x%x",
 			ndlp->nlp_DID, ndlp->nlp_flag, 0);
 		break;
 	case ELS_CMD_PRLO:
@@ -4681,28 +4698,25 @@ lpfc_rdp_res_speed(struct fc_rdp_port_speed_desc *desc, struct lpfc_hba *phba)
 
 	desc->tag = cpu_to_be32(RDP_PORT_SPEED_DESC_TAG);
 
-	switch (phba->sli4_hba.link_state.speed) {
-	case LPFC_FC_LA_SPEED_1G:
+	switch (phba->fc_linkspeed) {
+	case LPFC_LINK_SPEED_1GHZ:
 		rdp_speed = RDP_PS_1GB;
 		break;
-	case LPFC_FC_LA_SPEED_2G:
+	case LPFC_LINK_SPEED_2GHZ:
 		rdp_speed = RDP_PS_2GB;
 		break;
-	case LPFC_FC_LA_SPEED_4G:
+	case LPFC_LINK_SPEED_4GHZ:
 		rdp_speed = RDP_PS_4GB;
 		break;
-	case LPFC_FC_LA_SPEED_8G:
+	case LPFC_LINK_SPEED_8GHZ:
 		rdp_speed = RDP_PS_8GB;
 		break;
-	case LPFC_FC_LA_SPEED_10G:
+	case LPFC_LINK_SPEED_10GHZ:
 		rdp_speed = RDP_PS_10GB;
 		break;
-	case LPFC_FC_LA_SPEED_16G:
+	case LPFC_LINK_SPEED_16GHZ:
 		rdp_speed = RDP_PS_16GB;
 		break;
-	case LPFC_FC_LA_SPEED_32G:
-		rdp_speed = RDP_PS_32GB;
-		break;
 	default:
 		rdp_speed = RDP_PS_UNKNOWN;
 		break;
@@ -5739,7 +5753,6 @@ lpfc_els_rcv_flogi(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 	IOCB_t *icmd = &cmdiocb->iocb;
 	struct serv_parm *sp;
 	LPFC_MBOXQ_t *mbox;
-	struct ls_rjt stat;
 	uint32_t cmd, did;
 	int rc;
 	uint32_t fc_flag = 0;
@@ -5765,135 +5778,92 @@ lpfc_els_rcv_flogi(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 		return 1;
 	}
 
-	if ((lpfc_check_sparm(vport, ndlp, sp, CLASS3, 1))) {
-		/* For a FLOGI we accept, then if our portname is greater
-		 * then the remote portname we initiate Nport login.
-		 */
+	(void) lpfc_check_sparm(vport, ndlp, sp, CLASS3, 1);
 
-		rc = memcmp(&vport->fc_portname, &sp->portName,
-			    sizeof(struct lpfc_name));
 
-		if (!rc) {
-			if (phba->sli_rev < LPFC_SLI_REV4) {
-				mbox = mempool_alloc(phba->mbox_mem_pool,
-						     GFP_KERNEL);
-				if (!mbox)
-					return 1;
-				lpfc_linkdown(phba);
-				lpfc_init_link(phba, mbox,
-					       phba->cfg_topology,
-					       phba->cfg_link_speed);
-				mbox->u.mb.un.varInitLnk.lipsr_AL_PA = 0;
-				mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
-				mbox->vport = vport;
-				rc = lpfc_sli_issue_mbox(phba, mbox,
-							 MBX_NOWAIT);
-				lpfc_set_loopback_flag(phba);
-				if (rc == MBX_NOT_FINISHED)
-					mempool_free(mbox, phba->mbox_mem_pool);
-				return 1;
-			} else {
-				/* abort the flogi coming back to ourselves
-				 * due to external loopback on the port.
-				 */
-				lpfc_els_abort_flogi(phba);
-				return 0;
-			}
-		} else if (rc > 0) {	/* greater than */
-			spin_lock_irq(shost->host_lock);
-			vport->fc_flag |= FC_PT2PT_PLOGI;
-			spin_unlock_irq(shost->host_lock);
+	/*
+	 * If our portname is greater than the remote portname,
+	 * then we initiate Nport login.
+	 */
 
-			/* If we have the high WWPN we can assign our own
-			 * myDID; otherwise, we have to WAIT for a PLOGI
-			 * from the remote NPort to find out what it
-			 * will be.
-			 */
-			vport->fc_myDID = PT2PT_LocalID;
-		} else
-			vport->fc_myDID = PT2PT_RemoteID;
+	rc = memcmp(&vport->fc_portname, &sp->portName,
+		    sizeof(struct lpfc_name));
 
-		/*
-		 * The vport state should go to LPFC_FLOGI only
-		 * AFTER we issue a FLOGI, not receive one.
+	if (!rc) {
+		if (phba->sli_rev < LPFC_SLI_REV4) {
+			mbox = mempool_alloc(phba->mbox_mem_pool,
+					     GFP_KERNEL);
+			if (!mbox)
+				return 1;
+			lpfc_linkdown(phba);
+			lpfc_init_link(phba, mbox,
+				       phba->cfg_topology,
+				       phba->cfg_link_speed);
+			mbox->u.mb.un.varInitLnk.lipsr_AL_PA = 0;
+			mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
+			mbox->vport = vport;
+			rc = lpfc_sli_issue_mbox(phba, mbox,
+						 MBX_NOWAIT);
+			lpfc_set_loopback_flag(phba);
+			if (rc == MBX_NOT_FINISHED)
+				mempool_free(mbox, phba->mbox_mem_pool);
+			return 1;
+		}
+
+		/* abort the flogi coming back to ourselves
+		 * due to external loopback on the port.
 		 */
+		lpfc_els_abort_flogi(phba);
+		return 0;
+
+	} else if (rc > 0) {	/* greater than */
 		spin_lock_irq(shost->host_lock);
-		fc_flag = vport->fc_flag;
-		port_state = vport->port_state;
-		vport->fc_flag |= FC_PT2PT;
-		vport->fc_flag &= ~(FC_FABRIC | FC_PUBLIC_LOOP);
+		vport->fc_flag |= FC_PT2PT_PLOGI;
 		spin_unlock_irq(shost->host_lock);
-		lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
-				 "3311 Rcv Flogi PS x%x new PS x%x "
-				 "fc_flag x%x new fc_flag x%x\n",
-				 port_state, vport->port_state,
-				 fc_flag, vport->fc_flag);
 
-		/*
-		 * We temporarily set fc_myDID to make it look like we are
-		 * a Fabric. This is done just so we end up with the right
-		 * did / sid on the FLOGI ACC rsp.
+		/* If we have the high WWPN we can assign our own
+		 * myDID; otherwise, we have to WAIT for a PLOGI
+		 * from the remote NPort to find out what it
+		 * will be.
 		 */
-		did = vport->fc_myDID;
-		vport->fc_myDID = Fabric_DID;
-
+		vport->fc_myDID = PT2PT_LocalID;
 	} else {
-		/* Reject this request because invalid parameters */
-		stat.un.b.lsRjtRsvd0 = 0;
-		stat.un.b.lsRjtRsnCode = LSRJT_UNABLE_TPC;
-		stat.un.b.lsRjtRsnCodeExp = LSEXP_SPARM_OPTIONS;
-		stat.un.b.vendorUnique = 0;
-
-		/*
-		 * We temporarily set fc_myDID to make it look like we are
-		 * a Fabric. This is done just so we end up with the right
-		 * did / sid on the FLOGI LS_RJT rsp.
-		 */
-		did = vport->fc_myDID;
-		vport->fc_myDID = Fabric_DID;
-
-		lpfc_els_rsp_reject(vport, stat.un.lsRjtError, cmdiocb, ndlp,
-			NULL);
+		vport->fc_myDID = PT2PT_RemoteID;
+	}
 
-		/* Now lets put fc_myDID back to what its supposed to be */
-		vport->fc_myDID = did;
+	/*
+	 * The vport state should go to LPFC_FLOGI only
+	 * AFTER we issue a FLOGI, not receive one.
+	 */
+	spin_lock_irq(shost->host_lock);
+	fc_flag = vport->fc_flag;
+	port_state = vport->port_state;
+	vport->fc_flag |= FC_PT2PT;
+	vport->fc_flag &= ~(FC_FABRIC | FC_PUBLIC_LOOP);
+	spin_unlock_irq(shost->host_lock);
+	lpfc_printf_vlog(vport, KERN_INFO, LOG_ELS,
+			 "3311 Rcv Flogi PS x%x new PS x%x "
+			 "fc_flag x%x new fc_flag x%x\n",
+			 port_state, vport->port_state,
+			 fc_flag, vport->fc_flag);
 
-		return 1;
-	}
+	/*
+	 * We temporarily set fc_myDID to make it look like we are
+	 * a Fabric. This is done just so we end up with the right
+	 * did / sid on the FLOGI ACC rsp.
+	 */
+	did = vport->fc_myDID;
+	vport->fc_myDID = Fabric_DID;
 
-	/* send our FLOGI first */
-	if (vport->port_state < LPFC_FLOGI) {
-		vport->fc_myDID = 0;
-		lpfc_initial_flogi(vport);
-		vport->fc_myDID = Fabric_DID;
-	}
+	memcpy(&phba->fc_fabparam, sp, sizeof(struct serv_parm));
 
 	/* Send back ACC */
-	lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, cmdiocb, ndlp, NULL);
+	lpfc_els_rsp_acc(vport, ELS_CMD_FLOGI, cmdiocb, ndlp, NULL);
 
 	/* Now lets put fc_myDID back to what its supposed to be */
 	vport->fc_myDID = did;
 
-	if (!(vport->fc_flag & FC_PT2PT_PLOGI)) {
-
-		mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
-		if (!mbox)
-			goto fail;
-
-		lpfc_config_link(phba, mbox);
-
-		mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
-		mbox->vport = vport;
-		rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
-		if (rc == MBX_NOT_FINISHED) {
-			mempool_free(mbox, phba->mbox_mem_pool);
-			goto fail;
-		}
-	}
-
 	return 0;
-fail:
-	return 1;
 }
 
 /**
@@ -7345,7 +7315,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 
 	/* reject till our FLOGI completes */
 	if ((vport->port_state < LPFC_FABRIC_CFG_LINK) &&
-		(cmd != ELS_CMD_FLOGI)) {
+	    (cmd != ELS_CMD_FLOGI)) {
 		rjt_err = LSRJT_UNABLE_TPC;
 		rjt_exp = LSEXP_NOTHING_MORE;
 		goto lsrjt;
@@ -7381,6 +7351,7 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 			rjt_exp = LSEXP_NOTHING_MORE;
 			break;
 		}
+
 		if (vport->port_state < LPFC_DISC_AUTH) {
 			if (!(phba->pport->fc_flag & FC_PT2PT) ||
 				(phba->pport->fc_flag & FC_PT2PT_PLOGI)) {
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index bfc2442dd74a..d3668aa555d5 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -1083,7 +1083,7 @@ out:
 }
 
 
-static void
+void
 lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 {
 	struct lpfc_vport *vport = pmb->vport;
@@ -1113,8 +1113,10 @@ lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	/* Start discovery by sending a FLOGI. port_state is identically
 	 * LPFC_FLOGI while waiting for FLOGI cmpl
 	 */
-	if (vport->port_state != LPFC_FLOGI || vport->fc_flag & FC_PT2PT_PLOGI)
+	if (vport->port_state != LPFC_FLOGI)
 		lpfc_initial_flogi(vport);
+	else if (vport->fc_flag & FC_PT2PT)
+		lpfc_disc_start(vport);
 	return;
 
 out:
@@ -2963,8 +2965,10 @@ lpfc_mbx_cmpl_reg_vfi(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 
 out_free_mem:
 	mempool_free(mboxq, phba->mbox_mem_pool);
-	lpfc_mbuf_free(phba, dmabuf->virt, dmabuf->phys);
-	kfree(dmabuf);
+	if (dmabuf) {
+		lpfc_mbuf_free(phba, dmabuf->virt, dmabuf->phys);
+		kfree(dmabuf);
+	}
 	return;
 }
 
@@ -3448,10 +3452,10 @@ lpfc_mbx_cmpl_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 		spin_lock_irq(shost->host_lock);
 		ndlp->nlp_flag &= ~NLP_IGNR_REG_CMPL;
 		spin_unlock_irq(shost->host_lock);
-	} else
-		/* Good status, call state machine */
-		lpfc_disc_state_machine(vport, ndlp, pmb,
-				NLP_EVT_CMPL_REG_LOGIN);
+	}
+
+	/* Call state machine */
+	lpfc_disc_state_machine(vport, ndlp, pmb, NLP_EVT_CMPL_REG_LOGIN);
 
 	lpfc_mbuf_free(phba, mp->virt, mp->phys);
 	kfree(mp);
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index b0d92b84bcdc..c14ab6c3ae40 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -8834,9 +8834,12 @@ found:
 				 * already mapped to this phys_id.
 				 */
 				if (cpup->irq != LPFC_VECTOR_MAP_EMPTY) {
-					chann[saved_chann] =
-						cpup->channel_id;
-					saved_chann++;
+					if (saved_chann <=
+					    LPFC_FCP_IO_CHAN_MAX) {
+						chann[saved_chann] =
+							cpup->channel_id;
+						saved_chann++;
+					}
 					goto out;
 				}
 
diff --git a/drivers/scsi/lpfc/lpfc_mbox.c b/drivers/scsi/lpfc/lpfc_mbox.c
index f87f90e9b7df..1e34b5408a29 100644
--- a/drivers/scsi/lpfc/lpfc_mbox.c
+++ b/drivers/scsi/lpfc/lpfc_mbox.c
@@ -2145,10 +2145,12 @@ lpfc_reg_vfi(struct lpfcMboxq *mbox, struct lpfc_vport *vport, dma_addr_t phys)
 	reg_vfi->wwn[1] = cpu_to_le32(reg_vfi->wwn[1]);
 	reg_vfi->e_d_tov = phba->fc_edtov;
 	reg_vfi->r_a_tov = phba->fc_ratov;
-	reg_vfi->bde.addrHigh = putPaddrHigh(phys);
-	reg_vfi->bde.addrLow = putPaddrLow(phys);
-	reg_vfi->bde.tus.f.bdeSize = sizeof(vport->fc_sparam);
-	reg_vfi->bde.tus.f.bdeFlags = BUFF_TYPE_BDE_64;
+	if (phys) {
+		reg_vfi->bde.addrHigh = putPaddrHigh(phys);
+		reg_vfi->bde.addrLow = putPaddrLow(phys);
+		reg_vfi->bde.tus.f.bdeSize = sizeof(vport->fc_sparam);
+		reg_vfi->bde.tus.f.bdeFlags = BUFF_TYPE_BDE_64;
+	}
 	bf_set(lpfc_reg_vfi_nport_id, reg_vfi, vport->fc_myDID);
 
 	/* Only FC supports upd bit */
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index ed9a2c80c4aa..193733e8c823 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -280,38 +280,12 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	uint32_t *lp;
 	IOCB_t *icmd;
 	struct serv_parm *sp;
+	uint32_t ed_tov;
 	LPFC_MBOXQ_t *mbox;
 	struct ls_rjt stat;
 	int rc;
 
 	memset(&stat, 0, sizeof (struct ls_rjt));
-	if (vport->port_state <= LPFC_FDISC) {
-		/* Before responding to PLOGI, check for pt2pt mode.
-		 * If we are pt2pt, with an outstanding FLOGI, abort
-		 * the FLOGI and resend it first.
-		 */
-		if (vport->fc_flag & FC_PT2PT) {
-			 lpfc_els_abort_flogi(phba);
-		        if (!(vport->fc_flag & FC_PT2PT_PLOGI)) {
-				/* If the other side is supposed to initiate
-				 * the PLOGI anyway, just ACC it now and
-				 * move on with discovery.
-				 */
-				phba->fc_edtov = FF_DEF_EDTOV;
-				phba->fc_ratov = FF_DEF_RATOV;
-				/* Start discovery - this should just do
-				   CLEAR_LA */
-				lpfc_disc_start(vport);
-			} else
-				lpfc_initial_flogi(vport);
-		} else {
-			stat.un.b.lsRjtRsnCode = LSRJT_LOGICAL_BSY;
-			stat.un.b.lsRjtRsnCodeExp = LSEXP_NOTHING_MORE;
-			lpfc_els_rsp_reject(vport, stat.un.lsRjtError, cmdiocb,
-					    ndlp, NULL);
-			return 0;
-		}
-	}
 	pcmd = (struct lpfc_dmabuf *) cmdiocb->context2;
 	lp = (uint32_t *) pcmd->virt;
 	sp = (struct serv_parm *) ((uint8_t *) lp + sizeof (uint32_t));
@@ -404,30 +378,46 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	/* Check for Nport to NPort pt2pt protocol */
 	if ((vport->fc_flag & FC_PT2PT) &&
 	    !(vport->fc_flag & FC_PT2PT_PLOGI)) {
-
 		/* rcv'ed PLOGI decides what our NPortId will be */
 		vport->fc_myDID = icmd->un.rcvels.parmRo;
-		mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
-		if (mbox == NULL)
-			goto out;
-		lpfc_config_link(phba, mbox);
-		mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
-		mbox->vport = vport;
-		rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
-		if (rc == MBX_NOT_FINISHED) {
-			mempool_free(mbox, phba->mbox_mem_pool);
-			goto out;
+
+		ed_tov = be32_to_cpu(sp->cmn.e_d_tov);
+		if (sp->cmn.edtovResolution) {
+			/* E_D_TOV ticks are in nanoseconds */
+			ed_tov = (phba->fc_edtov + 999999) / 1000000;
 		}
+
 		/*
-		 * For SLI4, the VFI/VPI are registered AFTER the
-		 * Nport with the higher WWPN sends us a PLOGI with
-		 * our assigned NPortId.
+		 * For pt-to-pt, use the larger EDTOV
+		 * RATOV = 2 * EDTOV
 		 */
+		if (ed_tov > phba->fc_edtov)
+			phba->fc_edtov = ed_tov;
+		phba->fc_ratov = (2 * phba->fc_edtov) / 1000;
+
+		memcpy(&phba->fc_fabparam, sp, sizeof(struct serv_parm));
+
+		/* Issue config_link / reg_vfi to account for updated TOV's */
+
 		if (phba->sli_rev == LPFC_SLI_REV4)
 			lpfc_issue_reg_vfi(vport);
+		else {
+			mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+			if (mbox == NULL)
+				goto out;
+			lpfc_config_link(phba, mbox);
+			mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
+			mbox->vport = vport;
+			rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
+			if (rc == MBX_NOT_FINISHED) {
+				mempool_free(mbox, phba->mbox_mem_pool);
+				goto out;
+			}
+		}
 
 		lpfc_can_disctmo(vport);
 	}
+
 	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 	if (!mbox)
 		goto out;
@@ -1038,7 +1028,9 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 	uint32_t *lp;
 	IOCB_t *irsp;
 	struct serv_parm *sp;
+	uint32_t ed_tov;
 	LPFC_MBOXQ_t *mbox;
+	int rc;
 
 	cmdiocb = (struct lpfc_iocbq *) arg;
 	rspiocb = cmdiocb->context_un.rsp_iocb;
@@ -1094,18 +1086,63 @@ lpfc_cmpl_plogi_plogi_issue(struct lpfc_vport *vport,
 	ndlp->nlp_maxframe =
 		((sp->cmn.bbRcvSizeMsb & 0x0F) << 8) | sp->cmn.bbRcvSizeLsb;
 
+	if ((vport->fc_flag & FC_PT2PT) &&
+	    (vport->fc_flag & FC_PT2PT_PLOGI)) {
+		ed_tov = be32_to_cpu(sp->cmn.e_d_tov);
+		if (sp->cmn.edtovResolution) {
+			/* E_D_TOV ticks are in nanoseconds */
+			ed_tov = (phba->fc_edtov + 999999) / 1000000;
+		}
+
+		/*
+		 * Use the larger EDTOV
+		 * RATOV = 2 * EDTOV for pt-to-pt
+		 */
+		if (ed_tov > phba->fc_edtov)
+			phba->fc_edtov = ed_tov;
+		phba->fc_ratov = (2 * phba->fc_edtov) / 1000;
+
+		memcpy(&phba->fc_fabparam, sp, sizeof(struct serv_parm));
+
+		/* Issue config_link / reg_vfi to account for updated TOV's */
+		if (phba->sli_rev == LPFC_SLI_REV4) {
+			lpfc_issue_reg_vfi(vport);
+		} else {
+			mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+			if (!mbox) {
+				lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS,
+						 "0133 PLOGI: no memory "
+						 "for config_link "
+						 "Data: x%x x%x x%x x%x\n",
+						 ndlp->nlp_DID, ndlp->nlp_state,
+						 ndlp->nlp_flag, ndlp->nlp_rpi);
+				goto out;
+			}
+
+			lpfc_config_link(phba, mbox);
+
+			mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
+			mbox->vport = vport;
+			rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
+			if (rc == MBX_NOT_FINISHED) {
+				mempool_free(mbox, phba->mbox_mem_pool);
+				goto out;
+			}
+		}
+	}
+
+	lpfc_unreg_rpi(vport, ndlp);
+
 	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 	if (!mbox) {
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS,
-			"0133 PLOGI: no memory for reg_login "
-			"Data: x%x x%x x%x x%x\n",
-			ndlp->nlp_DID, ndlp->nlp_state,
-			ndlp->nlp_flag, ndlp->nlp_rpi);
+				 "0018 PLOGI: no memory for reg_login "
+				 "Data: x%x x%x x%x x%x\n",
+				 ndlp->nlp_DID, ndlp->nlp_state,
+				 ndlp->nlp_flag, ndlp->nlp_rpi);
 		goto out;
 	}
 
-	lpfc_unreg_rpi(vport, ndlp);
-
 	if (lpfc_reg_rpi(phba, vport->vpi, irsp->un.elsreq64.remoteID,
 			 (uint8_t *) sp, mbox, ndlp->nlp_rpi) == 0) {
 		switch (ndlp->nlp_DID) {
@@ -2299,6 +2336,9 @@ lpfc_cmpl_reglogin_npr_node(struct lpfc_vport *vport,
 		if (vport->phba->sli_rev < LPFC_SLI_REV4)
 			ndlp->nlp_rpi = mb->un.varWords[0];
 		ndlp->nlp_flag |= NLP_RPI_REGISTERED;
+		if (ndlp->nlp_flag & NLP_LOGO_ACC) {
+			lpfc_unreg_rpi(vport, ndlp);
+		}
 	} else {
 		if (ndlp->nlp_flag & NLP_NODEV_REMOVE) {
 			lpfc_drop_node(vport, ndlp);
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 9e165bc05ee1..bae36cc3740b 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -3908,9 +3908,9 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 	uint32_t logit = LOG_FCP;
 
 	/* Sanity check on return of outstanding command */
-	if (!(lpfc_cmd->pCmd))
-		return;
 	cmd = lpfc_cmd->pCmd;
+	if (!cmd)
+		return;
 	shost = cmd->device->host;
 
 	lpfc_cmd->result = (pIocbOut->iocb.un.ulpWord[4] & IOERR_PARAM_MASK);
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index f9585cdd8933..92dfd6a5178c 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -14842,10 +14842,12 @@ lpfc_fc_frame_add(struct lpfc_vport *vport, struct hbq_dmabuf *dmabuf)
 	struct lpfc_dmabuf *h_buf;
 	struct hbq_dmabuf *seq_dmabuf = NULL;
 	struct hbq_dmabuf *temp_dmabuf = NULL;
+	uint8_t	found = 0;
 
 	INIT_LIST_HEAD(&dmabuf->dbuf.list);
 	dmabuf->time_stamp = jiffies;
 	new_hdr = (struct fc_frame_header *)dmabuf->hbuf.virt;
+
 	/* Use the hdr_buf to find the sequence that this frame belongs to */
 	list_for_each_entry(h_buf, &vport->rcv_buffer_list, list) {
 		temp_hdr = (struct fc_frame_header *)h_buf->virt;
@@ -14885,7 +14887,8 @@ lpfc_fc_frame_add(struct lpfc_vport *vport, struct hbq_dmabuf *dmabuf)
 		return seq_dmabuf;
 	}
 	/* find the correct place in the sequence to insert this frame */
-	list_for_each_entry_reverse(d_buf, &seq_dmabuf->dbuf.list, list) {
+	d_buf = list_entry(seq_dmabuf->dbuf.list.prev, typeof(*d_buf), list);
+	while (!found) {
 		temp_dmabuf = container_of(d_buf, struct hbq_dmabuf, dbuf);
 		temp_hdr = (struct fc_frame_header *)temp_dmabuf->hbuf.virt;
 		/*
@@ -14895,9 +14898,17 @@ lpfc_fc_frame_add(struct lpfc_vport *vport, struct hbq_dmabuf *dmabuf)
 		if (be16_to_cpu(new_hdr->fh_seq_cnt) >
 			be16_to_cpu(temp_hdr->fh_seq_cnt)) {
 			list_add(&dmabuf->dbuf.list, &temp_dmabuf->dbuf.list);
-			return seq_dmabuf;
+			found = 1;
+			break;
 		}
+
+		if (&d_buf->list == &seq_dmabuf->dbuf.list)
+			break;
+		d_buf = list_entry(d_buf->list.prev, typeof(*d_buf), list);
 	}
+
+	if (found)
+		return seq_dmabuf;
 	return NULL;
 }
 
@@ -16173,7 +16184,7 @@ fail_fcf_read:
 }
 
 /**
- * lpfc_check_next_fcf_pri
+ * lpfc_check_next_fcf_pri_level
  * phba pointer to the lpfc_hba struct for this port.
  * This routine is called from the lpfc_sli4_fcf_rr_next_index_get
  * routine when the rr_bmask is empty. The FCF indecies are put into the
@@ -16329,8 +16340,12 @@ next_priority:
 
 	if (next_fcf_index < LPFC_SLI4_FCF_TBL_INDX_MAX &&
 		phba->fcf.fcf_pri[next_fcf_index].fcf_rec.flag &
-		LPFC_FCF_FLOGI_FAILED)
+		LPFC_FCF_FLOGI_FAILED) {
+		if (list_is_singular(&phba->fcf.fcf_pri_list))
+			return LPFC_FCOE_FCF_NEXT_NONE;
+
 		goto next_priority;
+	}
 
 	lpfc_printf_log(phba, KERN_INFO, LOG_FIP,
 			"2845 Get next roundrobin failover FCF (x%x)\n",
diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index c0f7c8ce54aa..ef4ff03242ea 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -1083,6 +1083,8 @@ struct megasas_ctrl_info {
 
 #define VD_EXT_DEBUG 0
 
+#define SCAN_PD_CHANNEL	0x1
+#define SCAN_VD_CHANNEL	0x2
 
 enum MR_SCSI_CMD_TYPE {
 	READ_WRITE_LDIO = 0,
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index e994ff944091..3f8d357b1bac 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -735,6 +735,7 @@ megasas_fire_cmd_skinny(struct megasas_instance *instance,
 	       &(regs)->inbound_high_queue_port);
 	writel((lower_32_bits(frame_phys_addr) | (frame_count<<1))|1,
 	       &(regs)->inbound_low_queue_port);
+	mmiowb();
 	spin_unlock_irqrestore(&instance->hba_lock, flags);
 }
 
@@ -5476,7 +5477,6 @@ static int megasas_probe_one(struct pci_dev *pdev,
 	spin_lock_init(&instance->hba_lock);
 	spin_lock_init(&instance->completion_lock);
 
-	mutex_init(&instance->aen_mutex);
 	mutex_init(&instance->reset_mutex);
 
 	/*
@@ -6443,10 +6443,10 @@ static int megasas_mgmt_ioctl_aen(struct file *file, unsigned long arg)
 	}
 	spin_unlock_irqrestore(&instance->hba_lock, flags);
 
-	mutex_lock(&instance->aen_mutex);
+	mutex_lock(&instance->reset_mutex);
 	error = megasas_register_aen(instance, aen.seq_num,
 				     aen.class_locale_word);
-	mutex_unlock(&instance->aen_mutex);
+	mutex_unlock(&instance->reset_mutex);
 	return error;
 }
 
@@ -6477,9 +6477,9 @@ static int megasas_mgmt_compat_ioctl_fw(struct file *file, unsigned long arg)
 	int i;
 	int error = 0;
 	compat_uptr_t ptr;
-	unsigned long local_raw_ptr;
 	u32 local_sense_off;
 	u32 local_sense_len;
+	u32 user_sense_off;
 
 	if (clear_user(ioc, sizeof(*ioc)))
 		return -EFAULT;
@@ -6497,17 +6497,16 @@ static int megasas_mgmt_compat_ioctl_fw(struct file *file, unsigned long arg)
 	 * sense_len is not null, so prepare the 64bit value under
 	 * the same condition.
 	 */
-	if (get_user(local_raw_ptr, ioc->frame.raw) ||
-		get_user(local_sense_off, &ioc->sense_off) ||
-		get_user(local_sense_len, &ioc->sense_len))
+	if (get_user(local_sense_off, &ioc->sense_off) ||
+		get_user(local_sense_len, &ioc->sense_len) ||
+		get_user(user_sense_off, &cioc->sense_off))
 		return -EFAULT;
 
-
 	if (local_sense_len) {
 		void __user **sense_ioc_ptr =
-			(void __user **)((u8*)local_raw_ptr + local_sense_off);
+			(void __user **)((u8 *)((unsigned long)&ioc->frame.raw) + local_sense_off);
 		compat_uptr_t *sense_cioc_ptr =
-			(compat_uptr_t *)(cioc->frame.raw + cioc->sense_off);
+			(compat_uptr_t *)(((unsigned long)&cioc->frame.raw) + user_sense_off);
 		if (get_user(ptr, sense_cioc_ptr) ||
 		    put_user(compat_ptr(ptr), sense_ioc_ptr))
 			return -EFAULT;
@@ -6648,6 +6647,7 @@ megasas_aen_polling(struct work_struct *work)
 	int     i, j, doscan = 0;
 	u32 seq_num, wait_time = MEGASAS_RESET_WAIT_TIME;
 	int error;
+	u8  dcmd_ret = 0;
 
 	if (!instance) {
 		printk(KERN_ERR "invalid instance!\n");
@@ -6660,16 +6660,7 @@ megasas_aen_polling(struct work_struct *work)
 		wait_time = MEGASAS_ROUTINE_WAIT_TIME_VF;
 
 	/* Don't run the event workqueue thread if OCR is running */
-	for (i = 0; i < wait_time; i++) {
-		if (instance->adprecovery == MEGASAS_HBA_OPERATIONAL)
-			break;
-		if (!(i % MEGASAS_RESET_NOTICE_INTERVAL)) {
-			dev_notice(&instance->pdev->dev, "%s waiting for "
-			       "controller reset to finish for scsi%d\n",
-			       __func__, instance->host->host_no);
-		}
-		msleep(1000);
-	}
+	mutex_lock(&instance->reset_mutex);
 
 	instance->ev = NULL;
 	host = instance->host;
@@ -6677,212 +6668,127 @@ megasas_aen_polling(struct work_struct *work)
 		megasas_decode_evt(instance);
 
 		switch (le32_to_cpu(instance->evt_detail->code)) {
-		case MR_EVT_PD_INSERTED:
-			if (megasas_get_pd_list(instance) == 0) {
-			for (i = 0; i < MEGASAS_MAX_PD_CHANNELS; i++) {
-				for (j = 0;
-				j < MEGASAS_MAX_DEV_PER_CHANNEL;
-				j++) {
-
-				pd_index =
-				(i * MEGASAS_MAX_DEV_PER_CHANNEL) + j;
-
-				sdev1 = scsi_device_lookup(host, i, j, 0);
-
-				if (instance->pd_list[pd_index].driveState
-						== MR_PD_STATE_SYSTEM) {
-					if (!sdev1)
-						scsi_add_device(host, i, j, 0);
-
-					if (sdev1)
-						scsi_device_put(sdev1);
-					}
-				}
-			}
-			}
-			doscan = 0;
-			break;
 
+		case MR_EVT_PD_INSERTED:
 		case MR_EVT_PD_REMOVED:
-			if (megasas_get_pd_list(instance) == 0) {
-			for (i = 0; i < MEGASAS_MAX_PD_CHANNELS; i++) {
-				for (j = 0;
-				j < MEGASAS_MAX_DEV_PER_CHANNEL;
-				j++) {
-
-				pd_index =
-				(i * MEGASAS_MAX_DEV_PER_CHANNEL) + j;
-
-				sdev1 = scsi_device_lookup(host, i, j, 0);
-
-				if (instance->pd_list[pd_index].driveState
-					== MR_PD_STATE_SYSTEM) {
-					if (sdev1)
-						scsi_device_put(sdev1);
-				} else {
-					if (sdev1) {
-						scsi_remove_device(sdev1);
-						scsi_device_put(sdev1);
-					}
-				}
-				}
-			}
-			}
-			doscan = 0;
+			dcmd_ret = megasas_get_pd_list(instance);
+			if (dcmd_ret == 0)
+				doscan = SCAN_PD_CHANNEL;
 			break;
 
 		case MR_EVT_LD_OFFLINE:
 		case MR_EVT_CFG_CLEARED:
 		case MR_EVT_LD_DELETED:
-			if (!instance->requestorId ||
-			    megasas_get_ld_vf_affiliation(instance, 0)) {
-				if (megasas_ld_list_query(instance,
-							  MR_LD_QUERY_TYPE_EXPOSED_TO_HOST))
-					megasas_get_ld_list(instance);
-				for (i = 0; i < MEGASAS_MAX_LD_CHANNELS; i++) {
-					for (j = 0;
-					     j < MEGASAS_MAX_DEV_PER_CHANNEL;
-					     j++) {
-
-						ld_index =
-							(i * MEGASAS_MAX_DEV_PER_CHANNEL) + j;
-
-						sdev1 = scsi_device_lookup(host, MEGASAS_MAX_PD_CHANNELS + i, j, 0);
-
-						if (instance->ld_ids[ld_index]
-						    != 0xff) {
-							if (sdev1)
-								scsi_device_put(sdev1);
-						} else {
-							if (sdev1) {
-								scsi_remove_device(sdev1);
-								scsi_device_put(sdev1);
-							}
-						}
-					}
-				}
-				doscan = 0;
-			}
-			break;
 		case MR_EVT_LD_CREATED:
 			if (!instance->requestorId ||
-			    megasas_get_ld_vf_affiliation(instance, 0)) {
-				if (megasas_ld_list_query(instance,
-							  MR_LD_QUERY_TYPE_EXPOSED_TO_HOST))
-					megasas_get_ld_list(instance);
-				for (i = 0; i < MEGASAS_MAX_LD_CHANNELS; i++) {
-					for (j = 0;
-					     j < MEGASAS_MAX_DEV_PER_CHANNEL;
-					     j++) {
-						ld_index =
-							(i * MEGASAS_MAX_DEV_PER_CHANNEL) + j;
-
-						sdev1 = scsi_device_lookup(host, MEGASAS_MAX_PD_CHANNELS + i, j, 0);
-
-						if (instance->ld_ids[ld_index]
-						    != 0xff) {
-							if (!sdev1)
-								scsi_add_device(host, MEGASAS_MAX_PD_CHANNELS + i, j, 0);
-						}
-						if (sdev1)
-							scsi_device_put(sdev1);
-					}
-				}
-				doscan = 0;
-			}
+				(instance->requestorId && megasas_get_ld_vf_affiliation(instance, 0)))
+				dcmd_ret = megasas_ld_list_query(instance, MR_LD_QUERY_TYPE_EXPOSED_TO_HOST);
+
+			if (dcmd_ret == 0)
+				doscan = SCAN_VD_CHANNEL;
+
 			break;
+
 		case MR_EVT_CTRL_HOST_BUS_SCAN_REQUESTED:
 		case MR_EVT_FOREIGN_CFG_IMPORTED:
 		case MR_EVT_LD_STATE_CHANGE:
-			doscan = 1;
+			dcmd_ret = megasas_get_pd_list(instance);
+
+			if (dcmd_ret != 0)
+				break;
+
+			if (!instance->requestorId ||
+				(instance->requestorId && megasas_get_ld_vf_affiliation(instance, 0)))
+				dcmd_ret = megasas_ld_list_query(instance, MR_LD_QUERY_TYPE_EXPOSED_TO_HOST);
+
+			if (dcmd_ret != 0)
+				break;
+
+			doscan = SCAN_VD_CHANNEL | SCAN_PD_CHANNEL;
+			dev_info(&instance->pdev->dev, "scanning for scsi%d...\n",
+				instance->host->host_no);
 			break;
+
 		case MR_EVT_CTRL_PROP_CHANGED:
-			megasas_get_ctrl_info(instance);
-			break;
+				dcmd_ret = megasas_get_ctrl_info(instance);
+				break;
 		default:
 			doscan = 0;
 			break;
 		}
 	} else {
 		dev_err(&instance->pdev->dev, "invalid evt_detail!\n");
+		mutex_unlock(&instance->reset_mutex);
 		kfree(ev);
 		return;
 	}
 
-	if (doscan) {
-		dev_info(&instance->pdev->dev, "scanning for scsi%d...\n",
-		       instance->host->host_no);
-		if (megasas_get_pd_list(instance) == 0) {
-			for (i = 0; i < MEGASAS_MAX_PD_CHANNELS; i++) {
-				for (j = 0; j < MEGASAS_MAX_DEV_PER_CHANNEL; j++) {
-					pd_index = i*MEGASAS_MAX_DEV_PER_CHANNEL + j;
-					sdev1 = scsi_device_lookup(host, i, j, 0);
-					if (instance->pd_list[pd_index].driveState ==
-					    MR_PD_STATE_SYSTEM) {
-						if (!sdev1) {
-							scsi_add_device(host, i, j, 0);
-						}
-						if (sdev1)
-							scsi_device_put(sdev1);
-					} else {
-						if (sdev1) {
-							scsi_remove_device(sdev1);
-							scsi_device_put(sdev1);
-						}
+	mutex_unlock(&instance->reset_mutex);
+
+	if (doscan & SCAN_PD_CHANNEL) {
+		for (i = 0; i < MEGASAS_MAX_PD_CHANNELS; i++) {
+			for (j = 0; j < MEGASAS_MAX_DEV_PER_CHANNEL; j++) {
+				pd_index = i*MEGASAS_MAX_DEV_PER_CHANNEL + j;
+				sdev1 = scsi_device_lookup(host, i, j, 0);
+				if (instance->pd_list[pd_index].driveState ==
+							MR_PD_STATE_SYSTEM) {
+					if (!sdev1)
+						scsi_add_device(host, i, j, 0);
+					else
+						scsi_device_put(sdev1);
+				} else {
+					if (sdev1) {
+						scsi_remove_device(sdev1);
+						scsi_device_put(sdev1);
 					}
 				}
 			}
 		}
+	}
 
-		if (!instance->requestorId ||
-		    megasas_get_ld_vf_affiliation(instance, 0)) {
-			if (megasas_ld_list_query(instance,
-						  MR_LD_QUERY_TYPE_EXPOSED_TO_HOST))
-				megasas_get_ld_list(instance);
-			for (i = 0; i < MEGASAS_MAX_LD_CHANNELS; i++) {
-				for (j = 0; j < MEGASAS_MAX_DEV_PER_CHANNEL;
-				     j++) {
-					ld_index =
-						(i * MEGASAS_MAX_DEV_PER_CHANNEL) + j;
-
-					sdev1 = scsi_device_lookup(host,
-								   MEGASAS_MAX_PD_CHANNELS + i, j, 0);
-					if (instance->ld_ids[ld_index]
-					    != 0xff) {
-						if (!sdev1)
-							scsi_add_device(host, MEGASAS_MAX_PD_CHANNELS + i, j, 0);
-						else
-							scsi_device_put(sdev1);
-					} else {
-						if (sdev1) {
-							scsi_remove_device(sdev1);
-							scsi_device_put(sdev1);
-						}
+	if (doscan & SCAN_VD_CHANNEL) {
+		for (i = 0; i < MEGASAS_MAX_LD_CHANNELS; i++) {
+			for (j = 0; j < MEGASAS_MAX_DEV_PER_CHANNEL; j++) {
+				ld_index = (i * MEGASAS_MAX_DEV_PER_CHANNEL) + j;
+				sdev1 = scsi_device_lookup(host, MEGASAS_MAX_PD_CHANNELS + i, j, 0);
+				if (instance->ld_ids[ld_index] != 0xff) {
+					if (!sdev1)
+						scsi_add_device(host, MEGASAS_MAX_PD_CHANNELS + i, j, 0);
+					else
+						scsi_device_put(sdev1);
+				} else {
+					if (sdev1) {
+						scsi_remove_device(sdev1);
+						scsi_device_put(sdev1);
 					}
 				}
 			}
 		}
 	}
 
-	if (instance->aen_cmd != NULL) {
-		kfree(ev);
-		return ;
-	}
-
-	seq_num = le32_to_cpu(instance->evt_detail->seq_num) + 1;
+	if (dcmd_ret == 0)
+		seq_num = le32_to_cpu(instance->evt_detail->seq_num) + 1;
+	else
+		seq_num = instance->last_seq_num;
 
 	/* Register AEN with FW for latest sequence number plus 1 */
 	class_locale.members.reserved = 0;
 	class_locale.members.locale = MR_EVT_LOCALE_ALL;
 	class_locale.members.class = MR_EVT_CLASS_DEBUG;
-	mutex_lock(&instance->aen_mutex);
+
+	if (instance->aen_cmd != NULL) {
+		kfree(ev);
+		return;
+	}
+
+	mutex_lock(&instance->reset_mutex);
 	error = megasas_register_aen(instance, seq_num,
 					class_locale.word);
-	mutex_unlock(&instance->aen_mutex);
-
 	if (error)
-		dev_err(&instance->pdev->dev, "register aen failed error %x\n", error);
+		dev_err(&instance->pdev->dev,
+			"register aen failed error %x\n", error);
 
+	mutex_unlock(&instance->reset_mutex);
 	kfree(ev);
 }
 
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 4f391e747be2..021b994fdae8 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -201,6 +201,7 @@ megasas_fire_cmd_fusion(struct megasas_instance *instance,
 		&instance->reg_set->inbound_low_queue_port);
 	writel(le32_to_cpu(req_desc->u.high),
 		&instance->reg_set->inbound_high_queue_port);
+	mmiowb();
 	spin_unlock_irqrestore(&instance->hba_lock, flags);
 #endif
 }
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 356233f86064..5b2c37f1e908 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -2020,8 +2020,10 @@ mpt3sas_base_unmap_resources(struct MPT3SAS_ADAPTER *ioc)
 	_base_free_irq(ioc);
 	_base_disable_msix(ioc);
 
-	if (ioc->msix96_vector)
+	if (ioc->msix96_vector) {
 		kfree(ioc->replyPostRegisterIndex);
+		ioc->replyPostRegisterIndex = NULL;
+	}
 
 	if (ioc->chip_phys) {
 		iounmap(ioc->chip);
@@ -2240,6 +2242,12 @@ mpt3sas_base_get_reply_virt_addr(struct MPT3SAS_ADAPTER *ioc, u32 phys_addr)
 	return ioc->reply + (phys_addr - (u32)ioc->reply_dma);
 }
 
+static inline u8
+_base_get_msix_index(struct MPT3SAS_ADAPTER *ioc)
+{
+	return ioc->cpu_msix_table[raw_smp_processor_id()];
+}
+
 /**
  * mpt3sas_base_get_smid - obtain a free smid from internal queue
  * @ioc: per adapter object
@@ -2300,6 +2308,7 @@ mpt3sas_base_get_smid_scsiio(struct MPT3SAS_ADAPTER *ioc, u8 cb_idx,
 	request->scmd = scmd;
 	request->cb_idx = cb_idx;
 	smid = request->smid;
+	request->msix_io = _base_get_msix_index(ioc);
 	list_del(&request->tracker_list);
 	spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags);
 	return smid;
@@ -2422,12 +2431,6 @@ _base_writeq(__u64 b, volatile void __iomem *addr, spinlock_t *writeq_lock)
 }
 #endif
 
-static inline u8
-_base_get_msix_index(struct MPT3SAS_ADAPTER *ioc)
-{
-	return ioc->cpu_msix_table[raw_smp_processor_id()];
-}
-
 /**
  * mpt3sas_base_put_smid_scsi_io - send SCSI_IO request to firmware
  * @ioc: per adapter object
@@ -2481,18 +2484,19 @@ mpt3sas_base_put_smid_fast_path(struct MPT3SAS_ADAPTER *ioc, u16 smid,
  * mpt3sas_base_put_smid_hi_priority - send Task Managment request to firmware
  * @ioc: per adapter object
  * @smid: system request message index
- *
+ * @msix_task: msix_task will be same as msix of IO incase of task abort else 0.
  * Return nothing.
  */
 void
-mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc, u16 smid)
+mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc, u16 smid,
+	u16 msix_task)
 {
 	Mpi2RequestDescriptorUnion_t descriptor;
 	u64 *request = (u64 *)&descriptor;
 
 	descriptor.HighPriority.RequestFlags =
 	    MPI2_REQ_DESCRIPT_FLAGS_HIGH_PRIORITY;
-	descriptor.HighPriority.MSIxIndex =  0;
+	descriptor.HighPriority.MSIxIndex =  msix_task;
 	descriptor.HighPriority.SMID = cpu_to_le16(smid);
 	descriptor.HighPriority.LMID = 0;
 	descriptor.HighPriority.Reserved1 = 0;
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 5ad271efbd45..92648a5ea2d2 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -643,6 +643,7 @@ struct chain_tracker {
  * @cb_idx: callback index
  * @direct_io: To indicate whether I/O is direct (WARPDRIVE)
  * @tracker_list: list of free request (ioc->free_list)
+ * @msix_io: IO's msix
  */
 struct scsiio_tracker {
 	u16	smid;
@@ -651,6 +652,7 @@ struct scsiio_tracker {
 	u8	direct_io;
 	struct list_head chain_list;
 	struct list_head tracker_list;
+	u16     msix_io;
 };
 
 /**
@@ -1213,7 +1215,8 @@ void mpt3sas_base_put_smid_scsi_io(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 	u16 handle);
 void mpt3sas_base_put_smid_fast_path(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 	u16 handle);
-void mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc, u16 smid);
+void mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc,
+	u16 smid, u16 msix_task);
 void mpt3sas_base_put_smid_default(struct MPT3SAS_ADAPTER *ioc, u16 smid);
 void mpt3sas_base_initialize_callback_handler(void);
 u8 mpt3sas_base_register_callback_handler(MPT_CALLBACK cb_func);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index d8366b056b70..4ccde5a05b70 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -817,7 +817,7 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 		    tm_request->DevHandle));
 		ioc->build_sg_mpi(ioc, psge, data_out_dma, data_out_sz,
 		    data_in_dma, data_in_sz);
-		mpt3sas_base_put_smid_hi_priority(ioc, smid);
+		mpt3sas_base_put_smid_hi_priority(ioc, smid, 0);
 		break;
 	}
 	case MPI2_FUNCTION_SMP_PASSTHROUGH:
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 9ab77b06434d..6180f7970bbf 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -2193,6 +2193,7 @@ mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle, uint channel,
 	unsigned long timeleft;
 	struct scsiio_tracker *scsi_lookup = NULL;
 	int rc;
+	u16 msix_task = 0;
 
 	if (m_type == TM_MUTEX_ON)
 		mutex_lock(&ioc->tm_cmds.mutex);
@@ -2256,7 +2257,12 @@ mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle, uint channel,
 	int_to_scsilun(lun, (struct scsi_lun *)mpi_request->LUN);
 	mpt3sas_scsih_set_tm_flag(ioc, handle);
 	init_completion(&ioc->tm_cmds.done);
-	mpt3sas_base_put_smid_hi_priority(ioc, smid);
+	if ((type == MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK) &&
+			(scsi_lookup->msix_io < ioc->reply_queue_count))
+		msix_task = scsi_lookup->msix_io;
+	else
+		msix_task = 0;
+	mpt3sas_base_put_smid_hi_priority(ioc, smid, msix_task);
 	timeleft = wait_for_completion_timeout(&ioc->tm_cmds.done, timeout*HZ);
 	if (!(ioc->tm_cmds.status & MPT3_CMD_COMPLETE)) {
 		pr_err(MPT3SAS_FMT "%s: timeout\n",
@@ -3151,7 +3157,7 @@ _scsih_tm_tr_send(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 	mpi_request->Function = MPI2_FUNCTION_SCSI_TASK_MGMT;
 	mpi_request->DevHandle = cpu_to_le16(handle);
 	mpi_request->TaskType = MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET;
-	mpt3sas_base_put_smid_hi_priority(ioc, smid);
+	mpt3sas_base_put_smid_hi_priority(ioc, smid, 0);
 	mpt3sas_trigger_master(ioc, MASTER_TRIGGER_DEVICE_REMOVAL);
 
 out:
@@ -3332,7 +3338,7 @@ _scsih_tm_tr_volume_send(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 	mpi_request->Function = MPI2_FUNCTION_SCSI_TASK_MGMT;
 	mpi_request->DevHandle = cpu_to_le16(handle);
 	mpi_request->TaskType = MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET;
-	mpt3sas_base_put_smid_hi_priority(ioc, smid);
+	mpt3sas_base_put_smid_hi_priority(ioc, smid, 0);
 }
 
 /**
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 75514a15bea0..f57d96984ae4 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1578,7 +1578,7 @@ void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *mcmd)
 		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
diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index 9096d311e45d..c2d9b793759d 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -631,8 +631,6 @@ struct ll_file_data {
 
 struct lov_stripe_md;
 
-extern spinlock_t inode_lock;
-
 extern struct dentry *llite_root;
 extern struct kset *llite_kset;
 
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 29cfc57d496e..e4110d6de0b5 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -88,7 +88,7 @@ struct vhost_scsi_cmd {
 	struct scatterlist *tvc_prot_sgl;
 	struct page **tvc_upages;
 	/* Pointer to response header iovec */
-	struct iovec *tvc_resp_iov;
+	struct iovec tvc_resp_iov;
 	/* Pointer to vhost_scsi for our device */
 	struct vhost_scsi *tvc_vhost;
 	/* Pointer to vhost_virtqueue for the cmd */
@@ -557,7 +557,7 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
 		memcpy(v_rsp.sense, cmd->tvc_sense_buf,
 		       se_cmd->scsi_sense_length);
 
-		iov_iter_init(&iov_iter, READ, cmd->tvc_resp_iov,
+		iov_iter_init(&iov_iter, READ, &cmd->tvc_resp_iov,
 			      cmd->tvc_in_iovs, sizeof(v_rsp));
 		ret = copy_to_iter(&v_rsp, sizeof(v_rsp), &iov_iter);
 		if (likely(ret == sizeof(v_rsp))) {
@@ -1054,7 +1054,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 		}
 		cmd->tvc_vhost = vs;
 		cmd->tvc_vq = vq;
-		cmd->tvc_resp_iov = &vq->iov[out];
+		cmd->tvc_resp_iov = vq->iov[out];
 		cmd->tvc_in_iovs = in;
 
 		pr_debug("vhost_scsi got command opcode: %#02x, lun: %d\n",
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 5e5db3687e34..353f4bae658c 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1526,27 +1526,24 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 
 		reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
 
-		if (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
-					     BTRFS_INODE_PREALLOC)) {
-			ret = check_can_nocow(inode, pos, &write_bytes);
-			if (ret < 0)
-				break;
-			if (ret > 0) {
-				/*
-				 * For nodata cow case, no need to reserve
-				 * data space.
-				 */
-				only_release_metadata = true;
-				/*
-				 * our prealloc extent may be smaller than
-				 * write_bytes, so scale down.
-				 */
-				num_pages = DIV_ROUND_UP(write_bytes + offset,
-							 PAGE_CACHE_SIZE);
-				reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
-				goto reserve_metadata;
-			}
+		if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
+					      BTRFS_INODE_PREALLOC)) &&
+		    check_can_nocow(inode, pos, &write_bytes) > 0) {
+			/*
+			 * For nodata cow case, no need to reserve
+			 * data space.
+			 */
+			only_release_metadata = true;
+			/*
+			 * our prealloc extent may be smaller than
+			 * write_bytes, so scale down.
+			 */
+			num_pages = DIV_ROUND_UP(write_bytes + offset,
+						 PAGE_CACHE_SIZE);
+			reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
+			goto reserve_metadata;
 		}
+
 		ret = btrfs_check_data_free_space(inode, pos, write_bytes);
 		if (ret < 0)
 			break;
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 11309683d65f..27794b137b24 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -112,7 +112,6 @@ static int ecryptfs_readdir(struct file *file, struct dir_context *ctx)
 		.sb = inode->i_sb,
 	};
 	lower_file = ecryptfs_file_to_lower(file);
-	lower_file->f_pos = ctx->pos;
 	rc = iterate_dir(lower_file, &buf.ctx);
 	ctx->pos = buf.ctx.pos;
 	if (rc < 0)
@@ -236,14 +235,6 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
 	}
 	ecryptfs_set_file_lower(
 		file, ecryptfs_inode_to_private(inode)->lower_file);
-	if (d_is_dir(ecryptfs_dentry)) {
-		ecryptfs_printk(KERN_DEBUG, "This is a directory\n");
-		mutex_lock(&crypt_stat->cs_mutex);
-		crypt_stat->flags &= ~(ECRYPTFS_ENCRYPTED);
-		mutex_unlock(&crypt_stat->cs_mutex);
-		rc = 0;
-		goto out;
-	}
 	rc = read_or_initialize_metadata(ecryptfs_dentry);
 	if (rc)
 		goto out_put;
@@ -260,6 +251,45 @@ out:
 	return rc;
 }
 
+/**
+ * ecryptfs_dir_open
+ * @inode: inode speciying file to open
+ * @file: Structure to return filled in
+ *
+ * Opens the file specified by inode.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+static int ecryptfs_dir_open(struct inode *inode, struct file *file)
+{
+	struct dentry *ecryptfs_dentry = file->f_path.dentry;
+	/* Private value of ecryptfs_dentry allocated in
+	 * ecryptfs_lookup() */
+	struct ecryptfs_file_info *file_info;
+	struct file *lower_file;
+
+	/* Released in ecryptfs_release or end of function if failure */
+	file_info = kmem_cache_zalloc(ecryptfs_file_info_cache, GFP_KERNEL);
+	ecryptfs_set_file_private(file, file_info);
+	if (unlikely(!file_info)) {
+		ecryptfs_printk(KERN_ERR,
+				"Error attempting to allocate memory\n");
+		return -ENOMEM;
+	}
+	lower_file = dentry_open(ecryptfs_dentry_to_lower_path(ecryptfs_dentry),
+				 file->f_flags, current_cred());
+	if (IS_ERR(lower_file)) {
+		printk(KERN_ERR "%s: Error attempting to initialize "
+			"the lower file for the dentry with name "
+			"[%pd]; rc = [%ld]\n", __func__,
+			ecryptfs_dentry, PTR_ERR(lower_file));
+		kmem_cache_free(ecryptfs_file_info_cache, file_info);
+		return PTR_ERR(lower_file);
+	}
+	ecryptfs_set_file_lower(file, lower_file);
+	return 0;
+}
+
 static int ecryptfs_flush(struct file *file, fl_owner_t td)
 {
 	struct file *lower_file = ecryptfs_file_to_lower(file);
@@ -280,6 +310,19 @@ static int ecryptfs_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
+static int ecryptfs_dir_release(struct inode *inode, struct file *file)
+{
+	fput(ecryptfs_file_to_lower(file));
+	kmem_cache_free(ecryptfs_file_info_cache,
+			ecryptfs_file_to_private(file));
+	return 0;
+}
+
+static loff_t ecryptfs_dir_llseek(struct file *file, loff_t offset, int whence)
+{
+	return vfs_llseek(ecryptfs_file_to_lower(file), offset, whence);
+}
+
 static int
 ecryptfs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
@@ -359,20 +402,16 @@ const struct file_operations ecryptfs_dir_fops = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = ecryptfs_compat_ioctl,
 #endif
-	.open = ecryptfs_open,
-	.flush = ecryptfs_flush,
-	.release = ecryptfs_release,
+	.open = ecryptfs_dir_open,
+	.release = ecryptfs_dir_release,
 	.fsync = ecryptfs_fsync,
-	.fasync = ecryptfs_fasync,
-	.splice_read = generic_file_splice_read,
-	.llseek = default_llseek,
+	.llseek = ecryptfs_dir_llseek,
 };
 
 const struct file_operations ecryptfs_main_fops = {
 	.llseek = generic_file_llseek,
 	.read_iter = ecryptfs_read_update_atime,
 	.write_iter = generic_file_write_iter,
-	.iterate = ecryptfs_readdir,
 	.unlocked_ioctl = ecryptfs_unlocked_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = ecryptfs_compat_ioctl,
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 9a5ad0f0d3ed..28702932a908 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -51,25 +51,31 @@ static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
 			      struct ext4_inode_info *ei)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	__u16 csum_lo;
-	__u16 csum_hi = 0;
 	__u32 csum;
+	__u16 dummy_csum = 0;
+	int offset = offsetof(struct ext4_inode, i_checksum_lo);
+	unsigned int csum_size = sizeof(dummy_csum);
 
-	csum_lo = le16_to_cpu(raw->i_checksum_lo);
-	raw->i_checksum_lo = 0;
-	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
-	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
-		csum_hi = le16_to_cpu(raw->i_checksum_hi);
-		raw->i_checksum_hi = 0;
-	}
+	csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw, offset);
+	csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, csum_size);
+	offset += csum_size;
+	csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
+			   EXT4_GOOD_OLD_INODE_SIZE - offset);
 
-	csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw,
-			   EXT4_INODE_SIZE(inode->i_sb));
-
-	raw->i_checksum_lo = cpu_to_le16(csum_lo);
-	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
-	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
-		raw->i_checksum_hi = cpu_to_le16(csum_hi);
+	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
+		offset = offsetof(struct ext4_inode, i_checksum_hi);
+		csum = ext4_chksum(sbi, csum, (__u8 *)raw +
+				   EXT4_GOOD_OLD_INODE_SIZE,
+				   offset - EXT4_GOOD_OLD_INODE_SIZE);
+		if (EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
+			csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum,
+					   csum_size);
+			offset += csum_size;
+			csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
+					   EXT4_INODE_SIZE(inode->i_sb) -
+					   offset);
+		}
+	}
 
 	return csum;
 }
@@ -5186,8 +5192,6 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 						      sbi->s_want_extra_isize,
 						      iloc, handle);
 			if (ret) {
-				ext4_set_inode_state(inode,
-						     EXT4_STATE_NO_EXPAND);
 				if (mnt_count !=
 					le16_to_cpu(sbi->s_es->s_mnt_count)) {
 					ext4_warning(inode->i_sb,
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 91bf36f22dbf..38eb0c8e43b9 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -420,15 +420,14 @@ static __le32 ext4_dx_csum(struct inode *inode, struct ext4_dir_entry *dirent,
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	__u32 csum;
-	__le32 save_csum;
 	int size;
+	__u32 dummy_csum = 0;
+	int offset = offsetof(struct dx_tail, dt_checksum);
 
 	size = count_offset + (count * sizeof(struct dx_entry));
-	save_csum = t->dt_checksum;
-	t->dt_checksum = 0;
 	csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)dirent, size);
-	csum = ext4_chksum(sbi, csum, (__u8 *)t, sizeof(struct dx_tail));
-	t->dt_checksum = save_csum;
+	csum = ext4_chksum(sbi, csum, (__u8 *)t, offset);
+	csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, sizeof(dummy_csum));
 
 	return cpu_to_le32(csum);
 }
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c542ebcf7a92..5bab28caa9d4 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2030,23 +2030,25 @@ failed:
 static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group,
 				   struct ext4_group_desc *gdp)
 {
-	int offset;
+	int offset = offsetof(struct ext4_group_desc, bg_checksum);
 	__u16 crc = 0;
 	__le32 le_group = cpu_to_le32(block_group);
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	if (ext4_has_metadata_csum(sbi->s_sb)) {
 		/* Use new metadata_csum algorithm */
-		__le16 save_csum;
 		__u32 csum32;
+		__u16 dummy_csum = 0;
 
-		save_csum = gdp->bg_checksum;
-		gdp->bg_checksum = 0;
 		csum32 = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&le_group,
 				     sizeof(le_group));
-		csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp,
-				     sbi->s_desc_size);
-		gdp->bg_checksum = save_csum;
+		csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp, offset);
+		csum32 = ext4_chksum(sbi, csum32, (__u8 *)&dummy_csum,
+				     sizeof(dummy_csum));
+		offset += sizeof(dummy_csum);
+		if (offset < sbi->s_desc_size)
+			csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp + offset,
+					     sbi->s_desc_size - offset);
 
 		crc = csum32 & 0xFFFF;
 		goto out;
@@ -2056,8 +2058,6 @@ static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group,
 	if (!ext4_has_feature_gdt_csum(sb))
 		return 0;
 
-	offset = offsetof(struct ext4_group_desc, bg_checksum);
-
 	crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid));
 	crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group));
 	crc = crc16(crc, (__u8 *)gdp, offset);
@@ -2093,6 +2093,7 @@ void ext4_group_desc_csum_set(struct super_block *sb, __u32 block_group,
 
 /* Called at mount-time, super-block is locked */
 static int ext4_check_descriptors(struct super_block *sb,
+				  ext4_fsblk_t sb_block,
 				  ext4_group_t *first_not_zeroed)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -2123,6 +2124,11 @@ static int ext4_check_descriptors(struct super_block *sb,
 			grp = i;
 
 		block_bitmap = ext4_block_bitmap(sb, gdp);
+		if (block_bitmap == sb_block) {
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+				 "Block bitmap for group %u overlaps "
+				 "superblock", i);
+		}
 		if (block_bitmap < first_block || block_bitmap > last_block) {
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
 			       "Block bitmap for group %u not in group "
@@ -2130,6 +2136,11 @@ static int ext4_check_descriptors(struct super_block *sb,
 			return 0;
 		}
 		inode_bitmap = ext4_inode_bitmap(sb, gdp);
+		if (inode_bitmap == sb_block) {
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+				 "Inode bitmap for group %u overlaps "
+				 "superblock", i);
+		}
 		if (inode_bitmap < first_block || inode_bitmap > last_block) {
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
 			       "Inode bitmap for group %u not in group "
@@ -2137,6 +2148,11 @@ static int ext4_check_descriptors(struct super_block *sb,
 			return 0;
 		}
 		inode_table = ext4_inode_table(sb, gdp);
+		if (inode_table == sb_block) {
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+				 "Inode table for group %u overlaps "
+				 "superblock", i);
+		}
 		if (inode_table < first_block ||
 		    inode_table + sbi->s_itb_per_group - 1 > last_block) {
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
@@ -3640,7 +3656,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			goto failed_mount2;
 		}
 	}
-	if (!ext4_check_descriptors(sb, &first_not_zeroed)) {
+	if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) {
 		ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
 		ret = -EFSCORRUPTED;
 		goto failed_mount2;
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 6b6b3e751f8c..263002f0389d 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -123,17 +123,18 @@ static __le32 ext4_xattr_block_csum(struct inode *inode,
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	__u32 csum;
-	__le32 save_csum;
 	__le64 dsk_block_nr = cpu_to_le64(block_nr);
+	__u32 dummy_csum = 0;
+	int offset = offsetof(struct ext4_xattr_header, h_checksum);
 
-	save_csum = hdr->h_checksum;
-	hdr->h_checksum = 0;
 	csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&dsk_block_nr,
 			   sizeof(dsk_block_nr));
-	csum = ext4_chksum(sbi, csum, (__u8 *)hdr,
-			   EXT4_BLOCK_SIZE(inode->i_sb));
+	csum = ext4_chksum(sbi, csum, (__u8 *)hdr, offset);
+	csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, sizeof(dummy_csum));
+	offset += sizeof(dummy_csum);
+	csum = ext4_chksum(sbi, csum, (__u8 *)hdr + offset,
+			   EXT4_BLOCK_SIZE(inode->i_sb) - offset);
 
-	hdr->h_checksum = save_csum;
 	return cpu_to_le32(csum);
 }
 
@@ -1264,15 +1265,19 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 	size_t min_offs, free;
 	int total_ino;
 	void *base, *start, *end;
-	int extra_isize = 0, error = 0, tried_min_extra_isize = 0;
+	int error = 0, tried_min_extra_isize = 0;
 	int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize);
+	int isize_diff;	/* How much do we need to grow i_extra_isize */
 
 	down_write(&EXT4_I(inode)->xattr_sem);
+	/*
+	 * Set EXT4_STATE_NO_EXPAND to avoid recursion when marking inode dirty
+	 */
+	ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
 retry:
-	if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) {
-		up_write(&EXT4_I(inode)->xattr_sem);
-		return 0;
-	}
+	isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize;
+	if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
+		goto out;
 
 	header = IHDR(inode, raw_inode);
 	entry = IFIRST(header);
@@ -1289,7 +1294,7 @@ retry:
 	total_ino = sizeof(struct ext4_xattr_ibody_header);
 
 	free = ext4_xattr_free_space(last, &min_offs, base, &total_ino);
-	if (free >= new_extra_isize) {
+	if (free >= isize_diff) {
 		entry = IFIRST(header);
 		ext4_xattr_shift_entries(entry,	EXT4_I(inode)->i_extra_isize
 				- new_extra_isize, (void *)raw_inode +
@@ -1297,8 +1302,7 @@ retry:
 				(void *)header, total_ino,
 				inode->i_sb->s_blocksize);
 		EXT4_I(inode)->i_extra_isize = new_extra_isize;
-		error = 0;
-		goto cleanup;
+		goto out;
 	}
 
 	/*
@@ -1321,7 +1325,7 @@ retry:
 		end = bh->b_data + bh->b_size;
 		min_offs = end - base;
 		free = ext4_xattr_free_space(first, &min_offs, base, NULL);
-		if (free < new_extra_isize) {
+		if (free < isize_diff) {
 			if (!tried_min_extra_isize && s_min_extra_isize) {
 				tried_min_extra_isize++;
 				new_extra_isize = s_min_extra_isize;
@@ -1335,7 +1339,7 @@ retry:
 		free = inode->i_sb->s_blocksize;
 	}
 
-	while (new_extra_isize > 0) {
+	while (isize_diff > 0) {
 		size_t offs, size, entry_size;
 		struct ext4_xattr_entry *small_entry = NULL;
 		struct ext4_xattr_info i = {
@@ -1366,7 +1370,7 @@ retry:
 			EXT4_XATTR_SIZE(le32_to_cpu(last->e_value_size)) +
 					EXT4_XATTR_LEN(last->e_name_len);
 			if (total_size <= free && total_size < min_total_size) {
-				if (total_size < new_extra_isize) {
+				if (total_size < isize_diff) {
 					small_entry = last;
 				} else {
 					entry = last;
@@ -1421,22 +1425,22 @@ retry:
 		error = ext4_xattr_ibody_set(handle, inode, &i, is);
 		if (error)
 			goto cleanup;
+		total_ino -= entry_size;
 
 		entry = IFIRST(header);
-		if (entry_size + EXT4_XATTR_SIZE(size) >= new_extra_isize)
-			shift_bytes = new_extra_isize;
+		if (entry_size + EXT4_XATTR_SIZE(size) >= isize_diff)
+			shift_bytes = isize_diff;
 		else
-			shift_bytes = entry_size + size;
+			shift_bytes = entry_size + EXT4_XATTR_SIZE(size);
 		/* Adjust the offsets and shift the remaining entries ahead */
-		ext4_xattr_shift_entries(entry, EXT4_I(inode)->i_extra_isize -
-			shift_bytes, (void *)raw_inode +
-			EXT4_GOOD_OLD_INODE_SIZE + extra_isize + shift_bytes,
-			(void *)header, total_ino - entry_size,
-			inode->i_sb->s_blocksize);
+		ext4_xattr_shift_entries(entry, -shift_bytes,
+			(void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE +
+			EXT4_I(inode)->i_extra_isize + shift_bytes,
+			(void *)header, total_ino, inode->i_sb->s_blocksize);
 
-		extra_isize += shift_bytes;
-		new_extra_isize -= shift_bytes;
-		EXT4_I(inode)->i_extra_isize = extra_isize;
+		isize_diff -= shift_bytes;
+		EXT4_I(inode)->i_extra_isize += shift_bytes;
+		header = IHDR(inode, raw_inode);
 
 		i.name = b_entry_name;
 		i.value = buffer;
@@ -1458,6 +1462,8 @@ retry:
 		kfree(bs);
 	}
 	brelse(bh);
+out:
+	ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
 	up_write(&EXT4_I(inode)->xattr_sem);
 	return 0;
 
@@ -1469,6 +1475,10 @@ cleanup:
 	kfree(is);
 	kfree(bs);
 	brelse(bh);
+	/*
+	 * We deliberately leave EXT4_STATE_NO_EXPAND set here since inode
+	 * size expansion failed.
+	 */
 	up_write(&EXT4_I(inode)->xattr_sem);
 	return error;
 }
diff --git a/fs/namei.c b/fs/namei.c
index 209ca7737cb2..0b0acba72a71 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -887,6 +887,7 @@ static inline int may_follow_link(struct nameidata *nd)
 {
 	const struct inode *inode;
 	const struct inode *parent;
+	kuid_t puid;
 
 	if (!sysctl_protected_symlinks)
 		return 0;
@@ -902,7 +903,8 @@ static inline int may_follow_link(struct nameidata *nd)
 		return 0;
 
 	/* Allowed if parent directory and link owner match. */
-	if (uid_eq(parent->i_uid, inode->i_uid))
+	puid = parent->i_uid;
+	if (uid_valid(puid) && uid_eq(puid, inode->i_uid))
 		return 0;
 
 	if (nd->flags & LOOKUP_RCU)
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index eff6319d5037..9e52609cd683 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -48,6 +48,8 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new)
 	}
 
 	for (name = buf; name < (buf + list_size); name += strlen(name) + 1) {
+		if (ovl_is_private_xattr(name))
+			continue;
 retry:
 		size = vfs_getxattr(old, name, value, value_size);
 		if (size == -ERANGE)
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 4f729ffff75d..220b04f04523 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -219,7 +219,7 @@ static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
 }
 
 
-static bool ovl_is_private_xattr(const char *name)
+bool ovl_is_private_xattr(const char *name)
 {
 	return strncmp(name, OVL_XATTR_PRE_NAME, OVL_XATTR_PRE_LEN) == 0;
 }
@@ -277,7 +277,8 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
 	struct path realpath;
 	enum ovl_path_type type = ovl_path_real(dentry, &realpath);
 	ssize_t res;
-	int off;
+	size_t len;
+	char *s;
 
 	res = vfs_listxattr(realpath.dentry, list, size);
 	if (res <= 0 || size == 0)
@@ -287,17 +288,19 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
 		return res;
 
 	/* filter out private xattrs */
-	for (off = 0; off < res;) {
-		char *s = list + off;
-		size_t slen = strlen(s) + 1;
+	for (s = list, len = res; len;) {
+		size_t slen = strnlen(s, len) + 1;
 
-		BUG_ON(off + slen > res);
+		/* underlying fs providing us with an broken xattr list? */
+		if (WARN_ON(slen > len))
+			return -EIO;
 
+		len -= slen;
 		if (ovl_is_private_xattr(s)) {
 			res -= slen;
-			memmove(s, s + slen, res - off);
+			memmove(s, s + slen, len);
 		} else {
-			off += slen;
+			s += slen;
 		}
 	}
 
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 735e1d49b301..c319d5eaabcf 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -174,6 +174,7 @@ ssize_t ovl_getxattr(struct dentry *dentry, const char *name,
 ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size);
 int ovl_removexattr(struct dentry *dentry, const char *name);
 struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags);
+bool ovl_is_private_xattr(const char *name);
 
 struct inode *ovl_new_inode(struct super_block *sb, umode_t mode,
 			    struct ovl_entry *oe);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 70a7bbe199d0..d70208c0de84 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -763,6 +763,10 @@ retry:
 		struct kstat stat = {
 			.mode = S_IFDIR | 0,
 		};
+		struct iattr attr = {
+			.ia_valid = ATTR_MODE,
+			.ia_mode = stat.mode,
+		};
 
 		if (work->d_inode) {
 			err = -EEXIST;
@@ -778,6 +782,21 @@ retry:
 		err = ovl_create_real(dir, work, &stat, NULL, NULL, true);
 		if (err)
 			goto out_dput;
+
+		err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_DEFAULT);
+		if (err && err != -ENODATA && err != -EOPNOTSUPP)
+			goto out_dput;
+
+		err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_ACCESS);
+		if (err && err != -ENODATA && err != -EOPNOTSUPP)
+			goto out_dput;
+
+		/* Clear any inherited mode bits */
+		inode_lock(work->d_inode);
+		err = notify_change(work, &attr, NULL);
+		inode_unlock(work->d_inode);
+		if (err)
+			goto out_dput;
 	}
 out_unlock:
 	mutex_unlock(&dir->i_mutex);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index f6478301db00..d598b9c809c1 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -248,23 +248,29 @@ static int do_maps_open(struct inode *inode, struct file *file,
 				sizeof(struct proc_maps_private));
 }
 
-static pid_t pid_of_stack(struct proc_maps_private *priv,
-				struct vm_area_struct *vma, bool is_pid)
+/*
+ * Indicate if the VMA is a stack for the given task; for
+ * /proc/PID/maps that is the stack of the main task.
+ */
+static int is_stack(struct proc_maps_private *priv,
+		    struct vm_area_struct *vma, int is_pid)
 {
-	struct inode *inode = priv->inode;
-	struct task_struct *task;
-	pid_t ret = 0;
+	int stack = 0;
+
+	if (is_pid) {
+		stack = vma->vm_start <= vma->vm_mm->start_stack &&
+			vma->vm_end >= vma->vm_mm->start_stack;
+	} else {
+		struct inode *inode = priv->inode;
+		struct task_struct *task;
 
-	rcu_read_lock();
-	task = pid_task(proc_pid(inode), PIDTYPE_PID);
-	if (task) {
-		task = task_of_stack(task, vma, is_pid);
+		rcu_read_lock();
+		task = pid_task(proc_pid(inode), PIDTYPE_PID);
 		if (task)
-			ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
+			stack = vma_is_stack_for_task(vma, task);
+		rcu_read_unlock();
 	}
-	rcu_read_unlock();
-
-	return ret;
+	return stack;
 }
 
 static void
@@ -324,8 +330,6 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 
 	name = arch_vma_name(vma);
 	if (!name) {
-		pid_t tid;
-
 		if (!mm) {
 			name = "[vdso]";
 			goto done;
@@ -337,21 +341,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 			goto done;
 		}
 
-		tid = pid_of_stack(priv, vma, is_pid);
-		if (tid != 0) {
-			/*
-			 * Thread stack in /proc/PID/task/TID/maps or
-			 * the main process stack.
-			 */
-			if (!is_pid || (vma->vm_start <= mm->start_stack &&
-			    vma->vm_end >= mm->start_stack)) {
-				name = "[stack]";
-			} else {
-				/* Thread stack in /proc/PID/maps */
-				seq_pad(m, ' ');
-				seq_printf(m, "[stack:%d]", tid);
-			}
-		}
+		if (is_stack(priv, vma, is_pid))
+			name = "[stack]";
 	}
 
 done:
@@ -1566,19 +1557,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 		seq_file_path(m, file, "\n\t= ");
 	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
 		seq_puts(m, " heap");
-	} else {
-		pid_t tid = pid_of_stack(proc_priv, vma, is_pid);
-		if (tid != 0) {
-			/*
-			 * Thread stack in /proc/PID/task/TID/maps or
-			 * the main process stack.
-			 */
-			if (!is_pid || (vma->vm_start <= mm->start_stack &&
-			    vma->vm_end >= mm->start_stack))
-				seq_puts(m, " stack");
-			else
-				seq_printf(m, " stack:%d", tid);
-		}
+	} else if (is_stack(proc_priv, vma, is_pid)) {
+		seq_puts(m, " stack");
 	}
 
 	if (is_vm_hugetlb_page(vma))
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index e0d64c92e4f6..faacb0c0d857 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -123,23 +123,26 @@ unsigned long task_statm(struct mm_struct *mm,
 	return size;
 }
 
-static pid_t pid_of_stack(struct proc_maps_private *priv,
-				struct vm_area_struct *vma, bool is_pid)
+static int is_stack(struct proc_maps_private *priv,
+		    struct vm_area_struct *vma, int is_pid)
 {
-	struct inode *inode = priv->inode;
-	struct task_struct *task;
-	pid_t ret = 0;
-
-	rcu_read_lock();
-	task = pid_task(proc_pid(inode), PIDTYPE_PID);
-	if (task) {
-		task = task_of_stack(task, vma, is_pid);
+	struct mm_struct *mm = vma->vm_mm;
+	int stack = 0;
+
+	if (is_pid) {
+		stack = vma->vm_start <= mm->start_stack &&
+			vma->vm_end >= mm->start_stack;
+	} else {
+		struct inode *inode = priv->inode;
+		struct task_struct *task;
+
+		rcu_read_lock();
+		task = pid_task(proc_pid(inode), PIDTYPE_PID);
 		if (task)
-			ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
+			stack = vma_is_stack_for_task(vma, task);
+		rcu_read_unlock();
 	}
-	rcu_read_unlock();
-
-	return ret;
+	return stack;
 }
 
 /*
@@ -181,21 +184,9 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
 	if (file) {
 		seq_pad(m, ' ');
 		seq_file_path(m, file, "");
-	} else if (mm) {
-		pid_t tid = pid_of_stack(priv, vma, is_pid);
-
-		if (tid != 0) {
-			seq_pad(m, ' ');
-			/*
-			 * Thread stack in /proc/PID/task/TID/maps or
-			 * the main process stack.
-			 */
-			if (!is_pid || (vma->vm_start <= mm->start_stack &&
-			    vma->vm_end >= mm->start_stack))
-				seq_printf(m, "[stack]");
-			else
-				seq_printf(m, "[stack:%d]", tid);
-		}
+	} else if (mm && is_stack(priv, vma, is_pid)) {
+		seq_pad(m, ' ');
+		seq_printf(m, "[stack]");
 	}
 
 	seq_putc(m, '\n');
diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c
index b45345d701e7..51157da3f76e 100644
--- a/fs/ubifs/tnc_commit.c
+++ b/fs/ubifs/tnc_commit.c
@@ -370,7 +370,7 @@ static int layout_in_gaps(struct ubifs_info *c, int cnt)
 
 	p = c->gap_lebs;
 	do {
-		ubifs_assert(p < c->gap_lebs + sizeof(int) * c->lst.idx_lebs);
+		ubifs_assert(p < c->gap_lebs + c->lst.idx_lebs);
 		written = layout_leb_in_gaps(c, p);
 		if (written < 0) {
 			err = written;
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 8a53eaa349f4..7088be6afb3c 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -581,7 +581,8 @@ xfs_sb_verify(
 	 * Only check the in progress field for the primary superblock as
 	 * mkfs.xfs doesn't clear it from secondary superblocks.
 	 */
-	return xfs_mount_validate_sb(mp, &sb, bp->b_bn == XFS_SB_DADDR,
+	return xfs_mount_validate_sb(mp, &sb,
+				     bp->b_maps[0].bm_bn == XFS_SB_DADDR,
 				     check_version);
 }
 
diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index 17c445612e01..2cdc723d750f 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -277,7 +277,9 @@
 	INTEL_VGA_DEVICE(0x191D, info)  /* WKS GT2 */
 
 #define INTEL_SKL_GT3_IDS(info) \
+	INTEL_VGA_DEVICE(0x1923, info), /* ULT GT3 */ \
 	INTEL_VGA_DEVICE(0x1926, info), /* ULT GT3 */ \
+	INTEL_VGA_DEVICE(0x1927, info), /* ULT GT3 */ \
 	INTEL_VGA_DEVICE(0x192B, info), /* Halo GT3 */ \
 	INTEL_VGA_DEVICE(0x192A, info) /* SRV GT3 */ \
 
@@ -289,6 +291,8 @@
 #define INTEL_BXT_IDS(info) \
 	INTEL_VGA_DEVICE(0x0A84, info), \
 	INTEL_VGA_DEVICE(0x1A84, info), \
-	INTEL_VGA_DEVICE(0x5A84, info)
+	INTEL_VGA_DEVICE(0x1A85, info), \
+	INTEL_VGA_DEVICE(0x5A84, info), /* APL HD Graphics 505 */ \
+	INTEL_VGA_DEVICE(0x5A85, info)  /* APL HD Graphics 500 */
 
 #endif /* _I915_PCIIDS_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 168755791ec8..fe14382f9664 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -890,7 +890,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
-	if (unlikely(rq->cmd_type == REQ_TYPE_BLOCK_PC))
+	if (unlikely(rq->cmd_type != REQ_TYPE_FS))
 		return q->limits.max_hw_sectors;
 
 	if (!q->limits.chunk_sectors || (rq->cmd_flags & REQ_DISCARD))
diff --git a/include/linux/capability.h b/include/linux/capability.h
index af9f0b9e80e6..5f8249d378a2 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -214,6 +214,7 @@ extern bool has_ns_capability_noaudit(struct task_struct *t,
 				      struct user_namespace *ns, int cap);
 extern bool capable(int cap);
 extern bool ns_capable(struct user_namespace *ns, int cap);
+extern bool ns_capable_noaudit(struct user_namespace *ns, int cap);
 #else
 static inline bool has_capability(struct task_struct *t, int cap)
 {
@@ -241,6 +242,10 @@ static inline bool ns_capable(struct user_namespace *ns, int cap)
 {
 	return true;
 }
+static inline bool ns_capable_noaudit(struct user_namespace *ns, int cap)
+{
+	return true;
+}
 #endif /* CONFIG_MULTIUSER */
 extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap);
 extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ab3d8d9bb3ef..0166582c4d78 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -710,6 +710,31 @@ enum inode_i_mutex_lock_class
 	I_MUTEX_PARENT2,
 };
 
+static inline void inode_lock(struct inode *inode)
+{
+	mutex_lock(&inode->i_mutex);
+}
+
+static inline void inode_unlock(struct inode *inode)
+{
+	mutex_unlock(&inode->i_mutex);
+}
+
+static inline int inode_trylock(struct inode *inode)
+{
+	return mutex_trylock(&inode->i_mutex);
+}
+
+static inline int inode_is_locked(struct inode *inode)
+{
+	return mutex_is_locked(&inode->i_mutex);
+}
+
+static inline void inode_lock_nested(struct inode *inode, unsigned subclass)
+{
+	mutex_lock_nested(&inode->i_mutex, subclass);
+}
+
 void lock_two_nondirectories(struct inode *, struct inode*);
 void unlock_two_nondirectories(struct inode *, struct inode*);
 
@@ -3029,8 +3054,8 @@ static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx)
 }
 static inline bool dir_relax(struct inode *inode)
 {
-	mutex_unlock(&inode->i_mutex);
-	mutex_lock(&inode->i_mutex);
+	inode_unlock(inode);
+	inode_lock(inode);
 	return !IS_DEADDIR(inode);
 }
 
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 034117b3be5f..f09648d14694 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -58,8 +58,9 @@ enum {
 	/* Block Types */
 	NVM_BLK_T_FREE		= 0x0,
 	NVM_BLK_T_BAD		= 0x1,
-	NVM_BLK_T_DEV		= 0x2,
-	NVM_BLK_T_HOST		= 0x4,
+	NVM_BLK_T_GRWN_BAD	= 0x2,
+	NVM_BLK_T_DEV		= 0x4,
+	NVM_BLK_T_HOST		= 0x8,
 };
 
 struct nvm_id_group {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f24df9c0b9df..8a761248d01e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1311,8 +1311,7 @@ static inline int stack_guard_page_end(struct vm_area_struct *vma,
 		!vma_growsup(vma->vm_next, addr);
 }
 
-extern struct task_struct *task_of_stack(struct task_struct *task,
-				struct vm_area_struct *vma, bool in_group);
+int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t);
 
 extern unsigned long move_page_tables(struct vm_area_struct *vma,
 		unsigned long old_addr, struct vm_area_struct *new_vma,
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f9828a48f16a..6cdd50f7f52d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -121,6 +121,7 @@ struct hw_perf_event {
 		struct { /* intel_cqm */
 			int			cqm_state;
 			u32			cqm_rmid;
+			int			is_group_event;
 			struct list_head	cqm_events_entry;
 			struct list_head	cqm_groups_entry;
 			struct list_head	cqm_group_entry;
diff --git a/include/linux/time.h b/include/linux/time.h
index beebe3a02d43..297f09f23896 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -125,6 +125,32 @@ static inline bool timeval_valid(const struct timeval *tv)
 
 extern struct timespec timespec_trunc(struct timespec t, unsigned gran);
 
+/*
+ * Validates if a timespec/timeval used to inject a time offset is valid.
+ * Offsets can be postive or negative. The value of the timeval/timespec
+ * is the sum of its fields, but *NOTE*: the field tv_usec/tv_nsec must
+ * always be non-negative.
+ */
+static inline bool timeval_inject_offset_valid(const struct timeval *tv)
+{
+	/* We don't check the tv_sec as it can be positive or negative */
+
+	/* Can't have more microseconds then a second */
+	if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC)
+		return false;
+	return true;
+}
+
+static inline bool timespec_inject_offset_valid(const struct timespec *ts)
+{
+	/* We don't check the tv_sec as it can be positive or negative */
+
+	/* Can't have more nanoseconds then a second */
+	if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC)
+		return false;
+	return true;
+}
+
 #define CURRENT_TIME		(current_kernel_time())
 #define CURRENT_TIME_SEC	((struct timespec) { get_seconds(), 0 })
 
diff --git a/include/uapi/linux/hyperv.h b/include/uapi/linux/hyperv.h
index e4c0a35d6417..e347b24ef9fb 100644
--- a/include/uapi/linux/hyperv.h
+++ b/include/uapi/linux/hyperv.h
@@ -313,6 +313,7 @@ enum hv_kvp_exchg_pool {
 #define HV_INVALIDARG			0x80070057
 #define HV_GUID_NOTFOUND		0x80041002
 #define HV_ERROR_ALREADY_EXISTS		0x80070050
+#define HV_ERROR_DISK_FULL		0x80070070
 
 #define ADDR_FAMILY_NONE	0x00
 #define ADDR_FAMILY_IPV4	0x01
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index a0e87d16b726..421d27413731 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -621,6 +621,9 @@ struct v4l2_pix_format {
 #define V4L2_PIX_FMT_JPGL	v4l2_fourcc('J', 'P', 'G', 'L') /* JPEG-Lite */
 #define V4L2_PIX_FMT_SE401      v4l2_fourcc('S', '4', '0', '1') /* se401 janggu compressed rgb */
 #define V4L2_PIX_FMT_S5C_UYVY_JPG v4l2_fourcc('S', '5', 'C', 'I') /* S5C73M3 interleaved UYVY/JPEG */
+#define V4L2_PIX_FMT_Y8I      v4l2_fourcc('Y', '8', 'I', ' ') /* Greyscale 8-bit L/R interleaved */
+#define V4L2_PIX_FMT_Y12I     v4l2_fourcc('Y', '1', '2', 'I') /* Greyscale 12-bit L/R interleaved */
+#define V4L2_PIX_FMT_Z16      v4l2_fourcc('Z', '1', '6', ' ') /* Depth data 16-bit */
 
 /* SDR formats - used only for Software Defined Radio devices */
 #define V4L2_SDR_FMT_CU8          v4l2_fourcc('C', 'U', '0', '8') /* IQ u8 */
diff --git a/include/uapi/scsi/cxlflash_ioctl.h b/include/uapi/scsi/cxlflash_ioctl.h
index 831351b2e660..2302f3ce5f86 100644
--- a/include/uapi/scsi/cxlflash_ioctl.h
+++ b/include/uapi/scsi/cxlflash_ioctl.h
@@ -31,6 +31,16 @@ struct dk_cxlflash_hdr {
 };
 
 /*
+ * Return flag definitions available to all ioctls
+ *
+ * Similar to the input flags, these are grown from the bottom-up with the
+ * intention that ioctl-specific return flag definitions would grow from the
+ * top-down, allowing the two sets to co-exist. While not required/enforced
+ * at this time, this provides future flexibility.
+ */
+#define DK_CXLFLASH_ALL_PORTS_ACTIVE	0x0000000000000001ULL
+
+/*
  * Notes:
  * -----
  * The 'context_id' field of all ioctl structures contains the context
diff --git a/kernel/capability.c b/kernel/capability.c
index 45432b54d5c6..00411c82dac5 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -361,6 +361,24 @@ bool has_capability_noaudit(struct task_struct *t, int cap)
 	return has_ns_capability_noaudit(t, &init_user_ns, cap);
 }
 
+static bool ns_capable_common(struct user_namespace *ns, int cap, bool audit)
+{
+	int capable;
+
+	if (unlikely(!cap_valid(cap))) {
+		pr_crit("capable() called with invalid cap=%u\n", cap);
+		BUG();
+	}
+
+	capable = audit ? security_capable(current_cred(), ns, cap) :
+			  security_capable_noaudit(current_cred(), ns, cap);
+	if (capable == 0) {
+		current->flags |= PF_SUPERPRIV;
+		return true;
+	}
+	return false;
+}
+
 /**
  * ns_capable - Determine if the current task has a superior capability in effect
  * @ns:  The usernamespace we want the capability in
@@ -374,19 +392,27 @@ bool has_capability_noaudit(struct task_struct *t, int cap)
  */
 bool ns_capable(struct user_namespace *ns, int cap)
 {
-	if (unlikely(!cap_valid(cap))) {
-		pr_crit("capable() called with invalid cap=%u\n", cap);
-		BUG();
-	}
-
-	if (security_capable(current_cred(), ns, cap) == 0) {
-		current->flags |= PF_SUPERPRIV;
-		return true;
-	}
-	return false;
+	return ns_capable_common(ns, cap, true);
 }
 EXPORT_SYMBOL(ns_capable);
 
+/**
+ * ns_capable_noaudit - Determine if the current task has a superior capability
+ * (unaudited) in effect
+ * @ns:  The usernamespace we want the capability in
+ * @cap: The capability to be tested for
+ *
+ * Return true if the current task has the given superior capability currently
+ * available for use, false if not.
+ *
+ * This sets PF_SUPERPRIV on the task if the capability is available on the
+ * assumption that it's about to be used.
+ */
+bool ns_capable_noaudit(struct user_namespace *ns, int cap)
+{
+	return ns_capable_common(ns, cap, false);
+}
+EXPORT_SYMBOL(ns_capable_noaudit);
 
 /**
  * capable - Determine if the current task has a superior capability in effect
diff --git a/kernel/cred.c b/kernel/cred.c
index 71179a09c1d6..ff8606f77d90 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -689,6 +689,8 @@ EXPORT_SYMBOL(set_security_override_from_ctx);
  */
 int set_create_files_as(struct cred *new, struct inode *inode)
 {
+	if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid))
+		return -EINVAL;
 	new->fsuid = inode->i_uid;
 	new->fsgid = inode->i_gid;
 	return security_kernel_create_files_as(new, inode);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 7dad84913abf..da0c09ff6112 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -171,8 +171,10 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	err = -EAGAIN;
 	ptep = page_check_address(page, mm, addr, &ptl, 0);
-	if (!ptep)
+	if (!ptep) {
+		mem_cgroup_cancel_charge(kpage, memcg);
 		goto unlock;
+	}
 
 	get_page(kpage);
 	page_add_new_anon_rmap(kpage, vma, addr);
@@ -199,7 +201,6 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 
 	err = 0;
  unlock:
-	mem_cgroup_cancel_charge(kpage, memcg);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	unlock_page(page);
 	return err;
diff --git a/kernel/fork.c b/kernel/fork.c
index 1155eac61687..c485cb156772 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1369,7 +1369,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->real_start_time = ktime_get_boot_ns();
 	p->io_context = NULL;
 	p->audit_context = NULL;
-	threadgroup_change_begin(current);
 	cgroup_fork(p);
 #ifdef CONFIG_NUMA
 	p->mempolicy = mpol_dup(p->mempolicy);
@@ -1521,6 +1520,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
 
+	threadgroup_change_begin(current);
 	/*
 	 * Ensure that the cgroup subsystem policies allow the new process to be
 	 * forked. It should be noted the the new process's css_set can be changed
@@ -1621,6 +1621,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 bad_fork_cancel_cgroup:
 	cgroup_cancel_fork(p, cgrp_ss_priv);
 bad_fork_free_pid:
+	threadgroup_change_end(current);
 	if (pid != &init_struct_pid)
 		free_pid(pid);
 bad_fork_cleanup_io:
@@ -1651,7 +1652,6 @@ bad_fork_cleanup_policy:
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_threadgroup_lock:
 #endif
-	threadgroup_change_end(current);
 	delayacct_tsk_free(p);
 bad_fork_cleanup_count:
 	atomic_dec(&p->cred->user->processes);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b8b516c37bf1..8f258f437ac2 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1191,8 +1191,6 @@ static void task_numa_assign(struct task_numa_env *env,
 {
 	if (env->best_task)
 		put_task_struct(env->best_task);
-	if (p)
-		get_task_struct(p);
 
 	env->best_task = p;
 	env->best_imp = imp;
@@ -1260,20 +1258,30 @@ static void task_numa_compare(struct task_numa_env *env,
 	long imp = env->p->numa_group ? groupimp : taskimp;
 	long moveimp = imp;
 	int dist = env->dist;
+	bool assigned = false;
 
 	rcu_read_lock();
 
 	raw_spin_lock_irq(&dst_rq->lock);
 	cur = dst_rq->curr;
 	/*
-	 * No need to move the exiting task, and this ensures that ->curr
-	 * wasn't reaped and thus get_task_struct() in task_numa_assign()
-	 * is safe under RCU read lock.
-	 * Note that rcu_read_lock() itself can't protect from the final
-	 * put_task_struct() after the last schedule().
+	 * No need to move the exiting task or idle task.
 	 */
 	if ((cur->flags & PF_EXITING) || is_idle_task(cur))
 		cur = NULL;
+	else {
+		/*
+		 * The task_struct must be protected here to protect the
+		 * p->numa_faults access in the task_weight since the
+		 * numa_faults could already be freed in the following path:
+		 * finish_task_switch()
+		 *     --> put_task_struct()
+		 *         --> __put_task_struct()
+		 *             --> task_numa_free()
+		 */
+		get_task_struct(cur);
+	}
+
 	raw_spin_unlock_irq(&dst_rq->lock);
 
 	/*
@@ -1357,6 +1365,7 @@ balance:
 		 */
 		if (!load_too_imbalanced(src_load, dst_load, env)) {
 			imp = moveimp - 1;
+			put_task_struct(cur);
 			cur = NULL;
 			goto assign;
 		}
@@ -1382,9 +1391,16 @@ balance:
 		env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu);
 
 assign:
+	assigned = true;
 	task_numa_assign(env, cur, imp);
 unlock:
 	rcu_read_unlock();
+	/*
+	 * The dst_rq->curr isn't assigned. The protection for task_struct is
+	 * finished.
+	 */
+	if (cur && !assigned)
+		put_task_struct(cur);
 }
 
 static void task_numa_find_cpu(struct task_numa_env *env,
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 1347882d131e..b98810d2f3b4 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -323,13 +323,42 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
 		/* cs is a watchdog. */
 		if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
 			cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
+	}
+	spin_unlock_irqrestore(&watchdog_lock, flags);
+}
+
+static void clocksource_select_watchdog(bool fallback)
+{
+	struct clocksource *cs, *old_wd;
+	unsigned long flags;
+
+	spin_lock_irqsave(&watchdog_lock, flags);
+	/* save current watchdog */
+	old_wd = watchdog;
+	if (fallback)
+		watchdog = NULL;
+
+	list_for_each_entry(cs, &clocksource_list, list) {
+		/* cs is a clocksource to be watched. */
+		if (cs->flags & CLOCK_SOURCE_MUST_VERIFY)
+			continue;
+
+		/* Skip current if we were requested for a fallback. */
+		if (fallback && cs == old_wd)
+			continue;
+
 		/* Pick the best watchdog. */
-		if (!watchdog || cs->rating > watchdog->rating) {
+		if (!watchdog || cs->rating > watchdog->rating)
 			watchdog = cs;
-			/* Reset watchdog cycles */
-			clocksource_reset_watchdog();
-		}
 	}
+	/* If we failed to find a fallback restore the old one. */
+	if (!watchdog)
+		watchdog = old_wd;
+
+	/* If we changed the watchdog we need to reset cycles. */
+	if (watchdog != old_wd)
+		clocksource_reset_watchdog();
+
 	/* Check if the watchdog timer needs to be started. */
 	clocksource_start_watchdog();
 	spin_unlock_irqrestore(&watchdog_lock, flags);
@@ -404,6 +433,7 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
 		cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
 }
 
+static void clocksource_select_watchdog(bool fallback) { }
 static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { }
 static inline void clocksource_resume_watchdog(void) { }
 static inline int __clocksource_watchdog_kthread(void) { return 0; }
@@ -736,6 +766,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 	clocksource_enqueue(cs);
 	clocksource_enqueue_watchdog(cs);
 	clocksource_select();
+	clocksource_select_watchdog(false);
 	mutex_unlock(&clocksource_mutex);
 	return 0;
 }
@@ -758,6 +789,7 @@ void clocksource_change_rating(struct clocksource *cs, int rating)
 	mutex_lock(&clocksource_mutex);
 	__clocksource_change_rating(cs, rating);
 	clocksource_select();
+	clocksource_select_watchdog(false);
 	mutex_unlock(&clocksource_mutex);
 }
 EXPORT_SYMBOL(clocksource_change_rating);
@@ -767,12 +799,12 @@ EXPORT_SYMBOL(clocksource_change_rating);
  */
 static int clocksource_unbind(struct clocksource *cs)
 {
-	/*
-	 * I really can't convince myself to support this on hardware
-	 * designed by lobotomized monkeys.
-	 */
-	if (clocksource_is_watchdog(cs))
-		return -EBUSY;
+	if (clocksource_is_watchdog(cs)) {
+		/* Select and try to install a replacement watchdog. */
+		clocksource_select_watchdog(true);
+		if (clocksource_is_watchdog(cs))
+			return -EBUSY;
+	}
 
 	if (cs == curr_clocksource) {
 		/* Select and try to install a replacement clock source */
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index fa909f9fd559..17f7bcff1e02 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -94,6 +94,9 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 };
 
 static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
+	/* Make sure we catch unsupported clockids */
+	[0 ... MAX_CLOCKS - 1]	= HRTIMER_MAX_CLOCK_BASES,
+
 	[CLOCK_REALTIME]	= HRTIMER_BASE_REALTIME,
 	[CLOCK_MONOTONIC]	= HRTIMER_BASE_MONOTONIC,
 	[CLOCK_BOOTTIME]	= HRTIMER_BASE_BOOTTIME,
@@ -102,7 +105,9 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
 
 static inline int hrtimer_clockid_to_base(clockid_t clock_id)
 {
-	return hrtimer_clock_to_base_table[clock_id];
+	int base = hrtimer_clock_to_base_table[clock_id];
+	BUG_ON(base == HRTIMER_MAX_CLOCK_BASES);
+	return base;
 }
 
 /*
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 149cc8086aea..ab861771e37f 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -674,8 +674,24 @@ int ntp_validate_timex(struct timex *txc)
 			return -EINVAL;
 	}
 
-	if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME)))
-		return -EPERM;
+	if (txc->modes & ADJ_SETOFFSET) {
+		/* In order to inject time, you gotta be super-user! */
+		if (!capable(CAP_SYS_TIME))
+			return -EPERM;
+
+		if (txc->modes & ADJ_NANO) {
+			struct timespec ts;
+
+			ts.tv_sec = txc->time.tv_sec;
+			ts.tv_nsec = txc->time.tv_usec;
+			if (!timespec_inject_offset_valid(&ts))
+				return -EINVAL;
+
+		} else {
+			if (!timeval_inject_offset_valid(&txc->time))
+				return -EINVAL;
+		}
+	}
 
 	/*
 	 * Check for potential multiplication overflows that can
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 99188ee5d9d0..4ff237dbc006 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -383,7 +383,10 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
 	do {
 		seq = raw_read_seqcount_latch(&tkf->seq);
 		tkr = tkf->base + (seq & 0x01);
-		now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr);
+		now = ktime_to_ns(tkr->base);
+
+		now += clocksource_delta(tkr->read(tkr->clock),
+					 tkr->cycle_last, tkr->mask);
 	} while (read_seqcount_retry(&tkf->seq, seq));
 
 	return now;
@@ -958,7 +961,7 @@ int timekeeping_inject_offset(struct timespec *ts)
 	struct timespec64 ts64, tmp;
 	int ret = 0;
 
-	if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
+	if (!timespec_inject_offset_valid(ts))
 		return -EINVAL;
 
 	ts64 = timespec_to_timespec64(*ts);
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
index f6bd65236712..107310a6f36f 100644
--- a/kernel/time/timekeeping_debug.c
+++ b/kernel/time/timekeeping_debug.c
@@ -23,7 +23,9 @@
 
 #include "timekeeping_internal.h"
 
-static unsigned int sleep_time_bin[32] = {0};
+#define NUM_BINS 32
+
+static unsigned int sleep_time_bin[NUM_BINS] = {0};
 
 static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
 {
@@ -69,6 +71,9 @@ late_initcall(tk_debug_sleep_time_init);
 
 void tk_debug_account_sleep_time(struct timespec64 *t)
 {
-	sleep_time_bin[fls(t->tv_sec)]++;
+	/* Cap bin index so we don't overflow the array */
+	int bin = min(fls(t->tv_sec), NUM_BINS-1);
+
+	sleep_time_bin[bin]++;
 }
 
diff --git a/lib/asn1_decoder.c b/lib/asn1_decoder.c
index 2b3f46c049d4..554522934c44 100644
--- a/lib/asn1_decoder.c
+++ b/lib/asn1_decoder.c
@@ -74,7 +74,7 @@ next_tag:
 
 	/* Extract a tag from the data */
 	tag = data[dp++];
-	if (tag == 0) {
+	if (tag == ASN1_EOC) {
 		/* It appears to be an EOC. */
 		if (data[dp++] != 0)
 			goto invalid_eoc;
@@ -96,10 +96,8 @@ next_tag:
 
 	/* Extract the length */
 	len = data[dp++];
-	if (len <= 0x7f) {
-		dp += len;
-		goto next_tag;
-	}
+	if (len <= 0x7f)
+		goto check_length;
 
 	if (unlikely(len == ASN1_INDEFINITE_LENGTH)) {
 		/* Indefinite length */
@@ -110,14 +108,18 @@ next_tag:
 	}
 
 	n = len - 0x80;
-	if (unlikely(n > sizeof(size_t) - 1))
+	if (unlikely(n > sizeof(len) - 1))
 		goto length_too_long;
 	if (unlikely(n > datalen - dp))
 		goto data_overrun_error;
-	for (len = 0; n > 0; n--) {
+	len = 0;
+	for (; n > 0; n--) {
 		len <<= 8;
 		len |= data[dp++];
 	}
+check_length:
+	if (len > datalen - dp)
+		goto data_overrun_error;
 	dp += len;
 	goto next_tag;
 
diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c
index e00ff00e861c..e37dbf53e226 100644
--- a/lib/mpi/mpicoder.c
+++ b/lib/mpi/mpicoder.c
@@ -367,7 +367,9 @@ int mpi_write_to_sgl(MPI a, struct scatterlist *sgl, unsigned *nbytes,
 	buf_len = sgl->length;
 	p2 = sg_virt(sgl);
 
-	for (i = a->nlimbs - 1; i >= 0; i--) {
+	for (i = a->nlimbs - 1 - lzeros / BYTES_PER_MPI_LIMB,
+			lzeros %= BYTES_PER_MPI_LIMB;
+		i >= 0; i--) {
 		alimb = a->d[i];
 		p = (u8 *)&alimb2;
 #if BYTES_PER_MPI_LIMB == 4
@@ -388,17 +390,12 @@ int mpi_write_to_sgl(MPI a, struct scatterlist *sgl, unsigned *nbytes,
 #error please implement for this limb size.
 #endif
 		if (lzeros > 0) {
-			if (lzeros >= sizeof(alimb)) {
-				p -= sizeof(alimb);
-				continue;
-			} else {
-				mpi_limb_t *limb1 = (void *)p - sizeof(alimb);
-				mpi_limb_t *limb2 = (void *)p - sizeof(alimb)
-							+ lzeros;
-				*limb1 = *limb2;
-				p -= lzeros;
-				y = lzeros;
-			}
+			mpi_limb_t *limb1 = (void *)p - sizeof(alimb);
+			mpi_limb_t *limb2 = (void *)p - sizeof(alimb)
+				+ lzeros;
+			*limb1 = *limb2;
+			p -= lzeros;
+			y = lzeros;
 			lzeros -= sizeof(alimb);
 		}
 
diff --git a/mm/util.c b/mm/util.c
index 9af1c12b310c..d5259b62f8d7 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -199,36 +199,11 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 /* Check if the vma is being used as a stack by this task */
-static int vm_is_stack_for_task(struct task_struct *t,
-				struct vm_area_struct *vma)
+int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t)
 {
 	return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
 }
 
-/*
- * Check if the vma is being used as a stack.
- * If is_group is non-zero, check in the entire thread group or else
- * just check in the current task. Returns the task_struct of the task
- * that the vma is stack for. Must be called under rcu_read_lock().
- */
-struct task_struct *task_of_stack(struct task_struct *task,
-				struct vm_area_struct *vma, bool in_group)
-{
-	if (vm_is_stack_for_task(task, vma))
-		return task;
-
-	if (in_group) {
-		struct task_struct *t;
-
-		for_each_thread(task, t) {
-			if (vm_is_stack_for_task(t, vma))
-				return t;
-		}
-	}
-
-	return NULL;
-}
-
 #if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 44e1632370dd..0b1ea5abcc04 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1275,6 +1275,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 	int peeked, off = 0;
 	int err;
 	int is_udplite = IS_UDPLITE(sk);
+	bool checksum_valid = false;
 	bool slow;
 
 	if (flags & MSG_ERRQUEUE)
@@ -1300,11 +1301,12 @@ try_again:
 	 */
 
 	if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) {
-		if (udp_lib_checksum_complete(skb))
+		checksum_valid = !udp_lib_checksum_complete(skb);
+		if (!checksum_valid)
 			goto csum_copy_err;
 	}
 
-	if (skb_csum_unnecessary(skb))
+	if (checksum_valid || skb_csum_unnecessary(skb))
 		err = skb_copy_datagram_msg(skb, sizeof(struct udphdr),
 					    msg, copied);
 	else {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 275af43306f9..e6092bd72ee2 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -402,6 +402,7 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	int peeked, off = 0;
 	int err;
 	int is_udplite = IS_UDPLITE(sk);
+	bool checksum_valid = false;
 	int is_udp4;
 	bool slow;
 
@@ -433,11 +434,12 @@ try_again:
 	 */
 
 	if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) {
-		if (udp_lib_checksum_complete(skb))
+		checksum_valid = !udp_lib_checksum_complete(skb);
+		if (!checksum_valid)
 			goto csum_copy_err;
 	}
 
-	if (skb_csum_unnecessary(skb))
+	if (checksum_valid || skb_csum_unnecessary(skb))
 		err = skb_copy_datagram_msg(skb, sizeof(struct udphdr),
 					    msg, copied);
 	else {
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 25391fb25516..2fc6ca9d1286 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -897,6 +897,12 @@ struct xt_table_info *xt_alloc_table_info(unsigned int size)
 	struct xt_table_info *info = NULL;
 	size_t sz = sizeof(*info) + size;
 
+	if (sz < sizeof(*info))
+		return NULL;
+
+	if (sz < sizeof(*info))
+		return NULL;
+
 	/* Pedantry: prevent them from hitting BUG() in vmalloc.c --RR */
 	if ((SMP_ALIGN(size) >> PAGE_SHIFT) + 2 > totalram_pages)
 		return NULL;
diff --git a/net/rds/recv.c b/net/rds/recv.c
index a00462b0d01d..0514af3ab378 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -545,5 +545,7 @@ void rds_inc_info_copy(struct rds_incoming *inc,
 		minfo.fport = inc->i_hdr.h_dport;
 	}
 
+	minfo.flags = 0;
+
 	rds_info_copy(iter, &minfo, sizeof(minfo));
 }
diff --git a/net/sysctl_net.c b/net/sysctl_net.c
index ed98c1fc3de1..46a71c701e7c 100644
--- a/net/sysctl_net.c
+++ b/net/sysctl_net.c
@@ -46,7 +46,7 @@ static int net_ctl_permissions(struct ctl_table_header *head,
 	kgid_t root_gid = make_kgid(net->user_ns, 0);
 
 	/* Allow network administrator to have same access as root. */
-	if (ns_capable(net->user_ns, CAP_NET_ADMIN) ||
+	if (ns_capable_noaudit(net->user_ns, CAP_NET_ADMIN) ||
 	    uid_eq(root_uid, current_euid())) {
 		int mode = (table->mode >> 6) & 7;
 		return (mode << 6) | (mode << 3) | mode;
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 2ed732bfe94b..a0c90572d0e5 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -574,7 +574,8 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg,
 
 	link_info.dest = nla_get_flag(link[TIPC_NLA_LINK_DEST]);
 	link_info.up = htonl(nla_get_flag(link[TIPC_NLA_LINK_UP]));
-	strcpy(link_info.str, nla_data(link[TIPC_NLA_LINK_NAME]));
+	nla_strlcpy(link_info.str, link[TIPC_NLA_LINK_NAME],
+		    TIPC_MAX_LINK_NAME);
 
 	return tipc_add_tlv(msg->rep, TIPC_TLV_LINK_INFO,
 			    &link_info, sizeof(link_info));
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index 69ee2eeef968..f9ff73a8d815 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -296,7 +296,8 @@ static void tipc_subscrb_rcv_cb(struct net *net, int conid,
 	if (tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscrb, &sub))
 		return tipc_conn_terminate(tn->topsrv, subscrb->conid);
 
-	tipc_nametbl_subscribe(sub);
+	if (sub)
+		tipc_nametbl_subscribe(sub);
 }
 
 /* Handle one request to establish a new subscriber */
diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index 795437b10082..b450a27588c8 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -1633,11 +1633,13 @@ static int snd_rawmidi_dev_register(struct snd_device *device)
 		return -EBUSY;
 	}
 	list_add_tail(&rmidi->list, &snd_rawmidi_devices);
+	mutex_unlock(&register_mutex);
 	err = snd_register_device(SNDRV_DEVICE_TYPE_RAWMIDI,
 				  rmidi->card, rmidi->device,
 				  &snd_rawmidi_f_ops, rmidi, &rmidi->dev);
 	if (err < 0) {
 		rmidi_err(rmidi, "unable to register\n");
+		mutex_lock(&register_mutex);
 		list_del(&rmidi->list);
 		mutex_unlock(&register_mutex);
 		return err;
@@ -1645,6 +1647,7 @@ static int snd_rawmidi_dev_register(struct snd_device *device)
 	if (rmidi->ops && rmidi->ops->dev_register &&
 	    (err = rmidi->ops->dev_register(rmidi)) < 0) {
 		snd_unregister_device(&rmidi->dev);
+		mutex_lock(&register_mutex);
 		list_del(&rmidi->list);
 		mutex_unlock(&register_mutex);
 		return err;
@@ -1677,7 +1680,6 @@ static int snd_rawmidi_dev_register(struct snd_device *device)
 		}
 	}
 #endif /* CONFIG_SND_OSSEMUL */
-	mutex_unlock(&register_mutex);
 	sprintf(name, "midi%d", rmidi->device);
 	entry = snd_info_create_card_entry(rmidi->card, name, rmidi->card->proc_root);
 	if (entry) {
diff --git a/sound/core/timer.c b/sound/core/timer.c
index 637d034bb084..ae4ea2e2e7fe 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -296,8 +296,21 @@ int snd_timer_open(struct snd_timer_instance **ti,
 		get_device(&timer->card->card_dev);
 	timeri->slave_class = tid->dev_sclass;
 	timeri->slave_id = slave_id;
-	if (list_empty(&timer->open_list_head) && timer->hw.open)
-		timer->hw.open(timer);
+
+	if (list_empty(&timer->open_list_head) && timer->hw.open) {
+		int err = timer->hw.open(timer);
+		if (err) {
+			kfree(timeri->owner);
+			kfree(timeri);
+
+			if (timer->card)
+				put_device(&timer->card->card_dev);
+			module_put(timer->module);
+			mutex_unlock(&register_mutex);
+			return err;
+		}
+	}
+
 	list_add_tail(&timeri->open_list, &timer->open_list_head);
 	snd_timer_check_master(timeri);
 	mutex_unlock(&register_mutex);
@@ -837,6 +850,7 @@ int snd_timer_new(struct snd_card *card, char *id, struct snd_timer_id *tid,
 	timer->tmr_subdevice = tid->subdevice;
 	if (id)
 		strlcpy(timer->id, id, sizeof(timer->id));
+	timer->sticks = 1;
 	INIT_LIST_HEAD(&timer->device_list);
 	INIT_LIST_HEAD(&timer->open_list_head);
 	INIT_LIST_HEAD(&timer->active_list_head);
@@ -1967,6 +1981,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 		tu->qused--;
 		spin_unlock_irq(&tu->qlock);
 
+		mutex_lock(&tu->ioctl_lock);
 		if (tu->tread) {
 			if (copy_to_user(buffer, &tu->tqueue[qhead],
 					 sizeof(struct snd_timer_tread)))
@@ -1976,6 +1991,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 					 sizeof(struct snd_timer_read)))
 				err = -EFAULT;
 		}
+		mutex_unlock(&tu->ioctl_lock);
 
 		spin_lock_irq(&tu->qlock);
 		if (err < 0)
diff --git a/sound/firewire/fireworks/fireworks.h b/sound/firewire/fireworks/fireworks.h
index c7cb7deafe48..2c316a9bc7f6 100644
--- a/sound/firewire/fireworks/fireworks.h
+++ b/sound/firewire/fireworks/fireworks.h
@@ -106,7 +106,6 @@ struct snd_efw {
 	u8 *resp_buf;
 	u8 *pull_ptr;
 	u8 *push_ptr;
-	unsigned int resp_queues;
 };
 
 int snd_efw_transaction_cmd(struct fw_unit *unit,
diff --git a/sound/firewire/fireworks/fireworks_hwdep.c b/sound/firewire/fireworks/fireworks_hwdep.c
index 33df8655fe81..2e1d9a23920c 100644
--- a/sound/firewire/fireworks/fireworks_hwdep.c
+++ b/sound/firewire/fireworks/fireworks_hwdep.c
@@ -25,6 +25,7 @@ hwdep_read_resp_buf(struct snd_efw *efw, char __user *buf, long remained,
 {
 	unsigned int length, till_end, type;
 	struct snd_efw_transaction *t;
+	u8 *pull_ptr;
 	long count = 0;
 
 	if (remained < sizeof(type) + sizeof(struct snd_efw_transaction))
@@ -38,8 +39,17 @@ hwdep_read_resp_buf(struct snd_efw *efw, char __user *buf, long remained,
 	buf += sizeof(type);
 
 	/* write into buffer as many responses as possible */
-	while (efw->resp_queues > 0) {
-		t = (struct snd_efw_transaction *)(efw->pull_ptr);
+	spin_lock_irq(&efw->lock);
+
+	/*
+	 * When another task reaches here during this task's access to user
+	 * space, it picks up current position in buffer and can read the same
+	 * series of responses.
+	 */
+	pull_ptr = efw->pull_ptr;
+
+	while (efw->push_ptr != pull_ptr) {
+		t = (struct snd_efw_transaction *)(pull_ptr);
 		length = be32_to_cpu(t->length) * sizeof(__be32);
 
 		/* confirm enough space for this response */
@@ -49,26 +59,39 @@ hwdep_read_resp_buf(struct snd_efw *efw, char __user *buf, long remained,
 		/* copy from ring buffer to user buffer */
 		while (length > 0) {
 			till_end = snd_efw_resp_buf_size -
-				(unsigned int)(efw->pull_ptr - efw->resp_buf);
+				(unsigned int)(pull_ptr - efw->resp_buf);
 			till_end = min_t(unsigned int, length, till_end);
 
-			if (copy_to_user(buf, efw->pull_ptr, till_end))
+			spin_unlock_irq(&efw->lock);
+
+			if (copy_to_user(buf, pull_ptr, till_end))
 				return -EFAULT;
 
-			efw->pull_ptr += till_end;
-			if (efw->pull_ptr >= efw->resp_buf +
-					     snd_efw_resp_buf_size)
-				efw->pull_ptr -= snd_efw_resp_buf_size;
+			spin_lock_irq(&efw->lock);
+
+			pull_ptr += till_end;
+			if (pull_ptr >= efw->resp_buf + snd_efw_resp_buf_size)
+				pull_ptr -= snd_efw_resp_buf_size;
 
 			length -= till_end;
 			buf += till_end;
 			count += till_end;
 			remained -= till_end;
 		}
-
-		efw->resp_queues--;
 	}
 
+	/*
+	 * All of tasks can read from the buffer nearly simultaneously, but the
+	 * last position for each task is different depending on the length of
+	 * given buffer. Here, for simplicity, a position of buffer is set by
+	 * the latest task. It's better for a listening application to allow one
+	 * thread to read from the buffer. Unless, each task can read different
+	 * sequence of responses depending on variation of buffer length.
+	 */
+	efw->pull_ptr = pull_ptr;
+
+	spin_unlock_irq(&efw->lock);
+
 	return count;
 }
 
@@ -76,14 +99,17 @@ static long
 hwdep_read_locked(struct snd_efw *efw, char __user *buf, long count,
 		  loff_t *offset)
 {
-	union snd_firewire_event event;
+	union snd_firewire_event event = {
+		.lock_status.type = SNDRV_FIREWIRE_EVENT_LOCK_STATUS,
+	};
 
-	memset(&event, 0, sizeof(event));
+	spin_lock_irq(&efw->lock);
 
-	event.lock_status.type = SNDRV_FIREWIRE_EVENT_LOCK_STATUS;
 	event.lock_status.status = (efw->dev_lock_count > 0);
 	efw->dev_lock_changed = false;
 
+	spin_unlock_irq(&efw->lock);
+
 	count = min_t(long, count, sizeof(event.lock_status));
 
 	if (copy_to_user(buf, &event, count))
@@ -98,10 +124,15 @@ hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count,
 {
 	struct snd_efw *efw = hwdep->private_data;
 	DEFINE_WAIT(wait);
+	bool dev_lock_changed;
+	bool queued;
 
 	spin_lock_irq(&efw->lock);
 
-	while ((!efw->dev_lock_changed) && (efw->resp_queues == 0)) {
+	dev_lock_changed = efw->dev_lock_changed;
+	queued = efw->push_ptr != efw->pull_ptr;
+
+	while (!dev_lock_changed && !queued) {
 		prepare_to_wait(&efw->hwdep_wait, &wait, TASK_INTERRUPTIBLE);
 		spin_unlock_irq(&efw->lock);
 		schedule();
@@ -109,15 +140,17 @@ hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count,
 		if (signal_pending(current))
 			return -ERESTARTSYS;
 		spin_lock_irq(&efw->lock);
+		dev_lock_changed = efw->dev_lock_changed;
+		queued = efw->push_ptr != efw->pull_ptr;
 	}
 
-	if (efw->dev_lock_changed)
+	spin_unlock_irq(&efw->lock);
+
+	if (dev_lock_changed)
 		count = hwdep_read_locked(efw, buf, count, offset);
-	else if (efw->resp_queues > 0)
+	else if (queued)
 		count = hwdep_read_resp_buf(efw, buf, count, offset);
 
-	spin_unlock_irq(&efw->lock);
-
 	return count;
 }
 
@@ -160,7 +193,7 @@ hwdep_poll(struct snd_hwdep *hwdep, struct file *file, poll_table *wait)
 	poll_wait(file, &efw->hwdep_wait, wait);
 
 	spin_lock_irq(&efw->lock);
-	if (efw->dev_lock_changed || (efw->resp_queues > 0))
+	if (efw->dev_lock_changed || efw->pull_ptr != efw->push_ptr)
 		events = POLLIN | POLLRDNORM;
 	else
 		events = 0;
diff --git a/sound/firewire/fireworks/fireworks_proc.c b/sound/firewire/fireworks/fireworks_proc.c
index 0639dcb13f7d..beb0a0ffee57 100644
--- a/sound/firewire/fireworks/fireworks_proc.c
+++ b/sound/firewire/fireworks/fireworks_proc.c
@@ -188,8 +188,8 @@ proc_read_queues_state(struct snd_info_entry *entry,
 	else
 		consumed = (unsigned int)(efw->push_ptr - efw->pull_ptr);
 
-	snd_iprintf(buffer, "%d %d/%d\n",
-		    efw->resp_queues, consumed, snd_efw_resp_buf_size);
+	snd_iprintf(buffer, "%d/%d\n",
+		    consumed, snd_efw_resp_buf_size);
 }
 
 static void
diff --git a/sound/firewire/fireworks/fireworks_transaction.c b/sound/firewire/fireworks/fireworks_transaction.c
index f550808d1784..36a08ba51ec7 100644
--- a/sound/firewire/fireworks/fireworks_transaction.c
+++ b/sound/firewire/fireworks/fireworks_transaction.c
@@ -121,11 +121,11 @@ copy_resp_to_buf(struct snd_efw *efw, void *data, size_t length, int *rcode)
 	size_t capacity, till_end;
 	struct snd_efw_transaction *t;
 
-	spin_lock_irq(&efw->lock);
-
 	t = (struct snd_efw_transaction *)data;
 	length = min_t(size_t, be32_to_cpu(t->length) * sizeof(u32), length);
 
+	spin_lock_irq(&efw->lock);
+
 	if (efw->push_ptr < efw->pull_ptr)
 		capacity = (unsigned int)(efw->pull_ptr - efw->push_ptr);
 	else
@@ -155,7 +155,6 @@ copy_resp_to_buf(struct snd_efw *efw, void *data, size_t length, int *rcode)
 	}
 
 	/* for hwdep */
-	efw->resp_queues++;
 	wake_up(&efw->hwdep_wait);
 
 	*rcode = RCODE_COMPLETE;
diff --git a/sound/firewire/tascam/tascam-hwdep.c b/sound/firewire/tascam/tascam-hwdep.c
index 131267c3a042..106406cbfaa3 100644
--- a/sound/firewire/tascam/tascam-hwdep.c
+++ b/sound/firewire/tascam/tascam-hwdep.c
@@ -16,31 +16,14 @@
 
 #include "tascam.h"
 
-static long hwdep_read_locked(struct snd_tscm *tscm, char __user *buf,
-			      long count)
-{
-	union snd_firewire_event event;
-
-	memset(&event, 0, sizeof(event));
-
-	event.lock_status.type = SNDRV_FIREWIRE_EVENT_LOCK_STATUS;
-	event.lock_status.status = (tscm->dev_lock_count > 0);
-	tscm->dev_lock_changed = false;
-
-	count = min_t(long, count, sizeof(event.lock_status));
-
-	if (copy_to_user(buf, &event, count))
-		return -EFAULT;
-
-	return count;
-}
-
 static long hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count,
 		       loff_t *offset)
 {
 	struct snd_tscm *tscm = hwdep->private_data;
 	DEFINE_WAIT(wait);
-	union snd_firewire_event event;
+	union snd_firewire_event event = {
+		.lock_status.type = SNDRV_FIREWIRE_EVENT_LOCK_STATUS,
+	};
 
 	spin_lock_irq(&tscm->lock);
 
@@ -54,10 +37,16 @@ static long hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count,
 		spin_lock_irq(&tscm->lock);
 	}
 
-	memset(&event, 0, sizeof(event));
-	count = hwdep_read_locked(tscm, buf, count);
+	event.lock_status.status = (tscm->dev_lock_count > 0);
+	tscm->dev_lock_changed = false;
+
 	spin_unlock_irq(&tscm->lock);
 
+	count = min_t(long, count, sizeof(event.lock_status));
+
+	if (copy_to_user(buf, &event, count))
+		return -EFAULT;
+
 	return count;
 }
 
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 12f7f6fdae4d..d4671973d889 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2366,6 +2366,10 @@ static const struct pci_device_id azx_ids[] = {
 	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	{ PCI_DEVICE(0x1002, 0xaae8),
 	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
+	{ PCI_DEVICE(0x1002, 0xaae0),
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
+	{ PCI_DEVICE(0x1002, 0xaaf0),
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	/* VIA VT8251/VT8237A */
 	{ PCI_DEVICE(0x1106, 0x3288),
 	  .driver_data = AZX_DRIVER_VIA | AZX_DCAPS_POSFIX_VIA },
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index f7bcd8dbac14..a8045b8a2a18 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -51,8 +51,10 @@ MODULE_PARM_DESC(static_hdmi_pcm, "Don't restrict PCM parameters per ELD info");
 #define is_broadwell(codec)    ((codec)->core.vendor_id == 0x80862808)
 #define is_skylake(codec) ((codec)->core.vendor_id == 0x80862809)
 #define is_broxton(codec) ((codec)->core.vendor_id == 0x8086280a)
+#define is_kabylake(codec) ((codec)->core.vendor_id == 0x8086280b)
 #define is_haswell_plus(codec) (is_haswell(codec) || is_broadwell(codec) \
-				|| is_skylake(codec) || is_broxton(codec))
+				|| is_skylake(codec) || is_broxton(codec) \
+				|| is_kabylake(codec))
 
 #define is_valleyview(codec) ((codec)->core.vendor_id == 0x80862882)
 #define is_cherryview(codec) ((codec)->core.vendor_id == 0x80862883)
@@ -3584,6 +3586,7 @@ HDA_CODEC_ENTRY(0x80862807, "Haswell HDMI",	patch_generic_hdmi),
 HDA_CODEC_ENTRY(0x80862808, "Broadwell HDMI",	patch_generic_hdmi),
 HDA_CODEC_ENTRY(0x80862809, "Skylake HDMI",	patch_generic_hdmi),
 HDA_CODEC_ENTRY(0x8086280a, "Broxton HDMI",	patch_generic_hdmi),
+HDA_CODEC_ENTRY(0x8086280b, "Kabylake HDMI",	patch_generic_hdmi),
 HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI",	patch_generic_hdmi),
 HDA_CODEC_ENTRY(0x80862882, "Valleyview2 HDMI",	patch_generic_hdmi),
 HDA_CODEC_ENTRY(0x80862883, "Braswell HDMI",	patch_generic_hdmi),
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index f25479ba3981..eaee626ab185 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4840,6 +4840,7 @@ enum {
 	ALC221_FIXUP_HP_FRONT_MIC,
 	ALC292_FIXUP_TPT460,
 	ALC298_FIXUP_SPK_VOLUME,
+	ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -5501,6 +5502,15 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
 	},
+	[ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x1b, 0x90170151 },
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -5545,6 +5555,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x06df, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
 	SND_PCI_QUIRK(0x1028, 0x06e0, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
 	SND_PCI_QUIRK(0x1028, 0x0704, "Dell XPS 13 9350", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
+	SND_PCI_QUIRK(0x1028, 0x0706, "Dell Inspiron 7559", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER),
 	SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE),
 	SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
 	SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME),
@@ -5879,6 +5890,10 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x12, 0x90a60170},
 		{0x14, 0x90170120},
 		{0x21, 0x02211030}),
+	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell Inspiron 5468", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x90a60180},
+		{0x14, 0x90170120},
+		{0x21, 0x02211030}),
 	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC256_STANDARD_PINS),
 	SND_HDA_PIN_QUIRK(0x10ec0280, 0x103c, "HP", ALC280_FIXUP_HP_GPIO4,
diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c
index ba8def5665c4..6726143c7fc5 100644
--- a/sound/soc/atmel/atmel_ssc_dai.c
+++ b/sound/soc/atmel/atmel_ssc_dai.c
@@ -298,8 +298,9 @@ static int atmel_ssc_startup(struct snd_pcm_substream *substream,
 	clk_enable(ssc_p->ssc->clk);
 	ssc_p->mck_rate = clk_get_rate(ssc_p->ssc->clk);
 
-	/* Reset the SSC to keep it at a clean status */
-	ssc_writel(ssc_p->ssc->regs, CR, SSC_BIT(CR_SWRST));
+	/* Reset the SSC unless initialized to keep it in a clean state */
+	if (!ssc_p->initialized)
+		ssc_writel(ssc_p->ssc->regs, CR, SSC_BIT(CR_SWRST));
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
 		dir = 0;
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index a3e1252ce242..3039e907f1f8 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1142,6 +1142,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip)
 	case USB_ID(0x0556, 0x0014): /* Phoenix Audio TMX320VC */
 	case USB_ID(0x05A3, 0x9420): /* ELP HD USB Camera */
 	case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */
+	case USB_ID(0x1901, 0x0191): /* GE B850V3 CP2114 audio interface */
 	case USB_ID(0x1de7, 0x0013): /* Phoenix Audio MT202exe */
 	case USB_ID(0x1de7, 0x0014): /* Phoenix Audio TMX320 */
 	case USB_ID(0x1de7, 0x0114): /* Phoenix Audio MT202pcs */
diff --git a/tools/hv/hv_fcopy_daemon.c b/tools/hv/hv_fcopy_daemon.c
index 5480e4e424eb..f1d742682317 100644
--- a/tools/hv/hv_fcopy_daemon.c
+++ b/tools/hv/hv_fcopy_daemon.c
@@ -37,12 +37,14 @@
 
 static int target_fd;
 static char target_fname[W_MAX_PATH];
+static unsigned long long filesize;
 
 static int hv_start_fcopy(struct hv_start_fcopy *smsg)
 {
 	int error = HV_E_FAIL;
 	char *q, *p;
 
+	filesize = 0;
 	p = (char *)smsg->path_name;
 	snprintf(target_fname, sizeof(target_fname), "%s/%s",
 		 (char *)smsg->path_name, (char *)smsg->file_name);
@@ -98,14 +100,26 @@ done:
 static int hv_copy_data(struct hv_do_fcopy *cpmsg)
 {
 	ssize_t bytes_written;
+	int ret = 0;
 
 	bytes_written = pwrite(target_fd, cpmsg->data, cpmsg->size,
 				cpmsg->offset);
 
-	if (bytes_written != cpmsg->size)
-		return HV_E_FAIL;
+	filesize += cpmsg->size;
+	if (bytes_written != cpmsg->size) {
+		switch (errno) {
+		case ENOSPC:
+			ret = HV_ERROR_DISK_FULL;
+			break;
+		default:
+			ret = HV_E_FAIL;
+			break;
+		}
+		syslog(LOG_ERR, "pwrite failed to write %llu bytes: %ld (%s)",
+		       filesize, (long)bytes_written, strerror(errno));
+	}
 
-	return 0;
+	return ret;
 }
 
 static int hv_copy_finished(void)