diff --git a/Makefile b/Makefile
index c0c41c9fac0c..d2fe757a979d 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 9
-SUBLEVEL = 9
+SUBLEVEL = 10
 EXTRAVERSION =
 NAME = Roaring Lionus
 
diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c
index 91ebe382147f..5f69c3bd59bb 100644
--- a/arch/arc/kernel/unaligned.c
+++ b/arch/arc/kernel/unaligned.c
@@ -243,7 +243,7 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs,
 
 	/* clear any remanants of delay slot */
 	if (delay_mode(regs)) {
-		regs->ret = regs->bta ~1U;
+		regs->ret = regs->bta & ~1U;
 		regs->status32 &= ~STATUS_DE_MASK;
 	} else {
 		regs->ret += state.instr_len;
diff --git a/arch/arm/boot/dts/imx6dl.dtsi b/arch/arm/boot/dts/imx6dl.dtsi
index 1ade1951e620..7aa120fbdc71 100644
--- a/arch/arm/boot/dts/imx6dl.dtsi
+++ b/arch/arm/boot/dts/imx6dl.dtsi
@@ -137,7 +137,7 @@
 &gpio4 {
 	gpio-ranges = <&iomuxc  5 136 1>, <&iomuxc  6 145 1>, <&iomuxc  7 150 1>,
 		      <&iomuxc  8 146 1>, <&iomuxc  9 151 1>, <&iomuxc 10 147 1>,
-		      <&iomuxc 11 151 1>, <&iomuxc 12 148 1>, <&iomuxc 13 153 1>,
+		      <&iomuxc 11 152 1>, <&iomuxc 12 148 1>, <&iomuxc 13 153 1>,
 		      <&iomuxc 14 149 1>, <&iomuxc 15 154 1>, <&iomuxc 16  39 7>,
 		      <&iomuxc 23  56 1>, <&iomuxc 24  61 7>, <&iomuxc 31  46 1>;
 };
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index ce131ed5939d..ae738a6319f6 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -600,7 +600,7 @@ static int gpr_set(struct task_struct *target,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	struct pt_regs newregs;
+	struct pt_regs newregs = *task_pt_regs(target);
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				 &newregs,
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 3a2e678b8d30..0122ad1a6027 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -610,9 +610,9 @@ static int __init early_abort_handler(unsigned long addr, unsigned int fsr,
 
 void __init early_abt_enable(void)
 {
-	fsr_info[22].fn = early_abort_handler;
+	fsr_info[FSR_FS_AEA].fn = early_abort_handler;
 	local_abt_enable();
-	fsr_info[22].fn = do_bad;
+	fsr_info[FSR_FS_AEA].fn = do_bad;
 }
 
 #ifndef CONFIG_ARM_LPAE
diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h
index 67532f242271..afc1f84e763b 100644
--- a/arch/arm/mm/fault.h
+++ b/arch/arm/mm/fault.h
@@ -11,11 +11,15 @@
 #define FSR_FS5_0		(0x3f)
 
 #ifdef CONFIG_ARM_LPAE
+#define FSR_FS_AEA		17
+
 static inline int fsr_fs(unsigned int fsr)
 {
 	return fsr & FSR_FS5_0;
 }
 #else
+#define FSR_FS_AEA		22
+
 static inline int fsr_fs(unsigned int fsr)
 {
 	return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6;
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 9e1499f98def..13f5fad21066 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -641,9 +641,10 @@
 #define   SRR1_ISI_N_OR_G	0x10000000 /* ISI: Access is no-exec or G */
 #define   SRR1_ISI_PROT		0x08000000 /* ISI: Other protection fault */
 #define   SRR1_WAKEMASK		0x00380000 /* reason for wakeup */
-#define   SRR1_WAKEMASK_P8	0x003c0000 /* reason for wakeup on POWER8 */
+#define   SRR1_WAKEMASK_P8	0x003c0000 /* reason for wakeup on POWER8 and 9 */
 #define   SRR1_WAKESYSERR	0x00300000 /* System error */
 #define   SRR1_WAKEEE		0x00200000 /* External interrupt */
+#define   SRR1_WAKEHVI		0x00240000 /* Hypervisor Virtualization Interrupt (P9) */
 #define   SRR1_WAKEMT		0x00280000 /* mtctrl */
 #define	  SRR1_WAKEHMI		0x00280000 /* Hypervisor maintenance */
 #define   SRR1_WAKEDEC		0x00180000 /* Decrementer interrupt */
diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index f0b238516e9b..e0b9e576905a 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -44,6 +44,7 @@ static inline int icp_hv_init(void) { return -ENODEV; }
 
 #ifdef CONFIG_PPC_POWERNV
 extern int icp_opal_init(void);
+extern void icp_opal_flush_interrupt(void);
 #else
 static inline int icp_opal_init(void) { return -ENODEV; }
 #endif
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 3493cf4e0452..71697ff70879 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -50,9 +50,7 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 	for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) {
 		__tlbiel_pid(pid, set, ric);
 	}
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1))
-		asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
-	return;
+	asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
 }
 
 static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
@@ -85,8 +83,6 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid,
 	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
 	asm volatile("ptesync": : :"memory");
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1))
-		asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
 }
 
 static inline void _tlbie_va(unsigned long va, unsigned long pid,
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index c789258ae1e1..eec0e8d0454d 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -155,8 +155,10 @@ static void pnv_smp_cpu_kill_self(void)
 		wmask = SRR1_WAKEMASK_P8;
 
 	idle_states = pnv_get_supported_cpuidle_states();
+
 	/* We don't want to take decrementer interrupts while we are offline,
-	 * so clear LPCR:PECE1. We keep PECE2 enabled.
+	 * so clear LPCR:PECE1. We keep PECE2 (and LPCR_PECE_HVEE on P9)
+	 * enabled as to let IPIs in.
 	 */
 	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
 
@@ -206,8 +208,12 @@ static void pnv_smp_cpu_kill_self(void)
 		 * contains 0.
 		 */
 		if (((srr1 & wmask) == SRR1_WAKEEE) ||
+		    ((srr1 & wmask) == SRR1_WAKEHVI) ||
 		    (local_paca->irq_happened & PACA_IRQ_EE)) {
-			icp_native_flush_interrupt();
+			if (cpu_has_feature(CPU_FTR_ARCH_300))
+				icp_opal_flush_interrupt();
+			else
+				icp_native_flush_interrupt();
 		} else if ((srr1 & wmask) == SRR1_WAKEHDBELL) {
 			unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
 			asm volatile(PPC_MSGCLR(%0) : : "r" (msg));
@@ -221,6 +227,8 @@ static void pnv_smp_cpu_kill_self(void)
 		if (srr1 && !generic_check_cpu_restart(cpu))
 			DBG("CPU%d Unexpected exit while offline !\n", cpu);
 	}
+
+	/* Re-enable decrementer interrupts */
 	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_PECE1);
 	DBG("CPU%d coming online...\n", cpu);
 }
diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c
index 60c57657c772..c96c0cb95d87 100644
--- a/arch/powerpc/sysdev/xics/icp-opal.c
+++ b/arch/powerpc/sysdev/xics/icp-opal.c
@@ -132,6 +132,35 @@ static irqreturn_t icp_opal_ipi_action(int irq, void *dev_id)
 	return smp_ipi_demux();
 }
 
+/*
+ * Called when an interrupt is received on an off-line CPU to
+ * clear the interrupt, so that the CPU can go back to nap mode.
+ */
+void icp_opal_flush_interrupt(void)
+{
+	unsigned int xirr;
+	unsigned int vec;
+
+	do {
+		xirr = icp_opal_get_xirr();
+		vec = xirr & 0x00ffffff;
+		if (vec == XICS_IRQ_SPURIOUS)
+			break;
+		if (vec == XICS_IPI) {
+			/* Clear pending IPI */
+			int cpu = smp_processor_id();
+			kvmppc_set_host_ipi(cpu, 0);
+			opal_int_set_mfrr(get_hard_smp_processor_id(cpu), 0xff);
+		} else {
+			pr_err("XICS: hw interrupt 0x%x to offline cpu, "
+			       "disabling\n", vec);
+			xics_mask_unknown_vec(vec);
+		}
+
+		/* EOI the interrupt */
+	} while (opal_int_eoi(xirr) > 0);
+}
+
 #endif /* CONFIG_SMP */
 
 static const struct icp_ops icp_opal_ops = {
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 984a7bf17f6a..83db0eae9979 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -104,6 +104,7 @@ struct cpuinfo_x86 {
 	__u8			x86_phys_bits;
 	/* CPUID returned core id bits: */
 	__u8			x86_coreid_bits;
+	__u8			cu_id;
 	/* Max extended CPUID function supported: */
 	__u32			extended_cpuid_level;
 	/* Maximum supported CPUID level, -1=no CPUID: */
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 7249f1500bcb..d1e25564b3c1 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1876,7 +1876,6 @@ static struct irq_chip ioapic_chip __read_mostly = {
 	.irq_ack		= irq_chip_ack_parent,
 	.irq_eoi		= ioapic_ack_level,
 	.irq_set_affinity	= ioapic_set_affinity,
-	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
@@ -1888,7 +1887,6 @@ static struct irq_chip ioapic_ir_chip __read_mostly = {
 	.irq_ack		= irq_chip_ack_parent,
 	.irq_eoi		= ioapic_ir_ack_level,
 	.irq_set_affinity	= ioapic_set_affinity,
-	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 1d3167269a67..2b4cf04239b6 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -309,8 +309,22 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 
 	/* get information required for multi-node processors */
 	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+		u32 eax, ebx, ecx, edx;
 
-		node_id = cpuid_ecx(0x8000001e) & 7;
+		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
+
+		node_id  = ecx & 0xff;
+		smp_num_siblings = ((ebx >> 8) & 0xff) + 1;
+
+		if (c->x86 == 0x15)
+			c->cu_id = ebx & 0xff;
+
+		if (c->x86 >= 0x17) {
+			c->cpu_core_id = ebx & 0xff;
+
+			if (smp_num_siblings > 1)
+				c->x86_max_cores /= smp_num_siblings;
+		}
 
 		/*
 		 * We may have multiple LLCs if L3 caches exist, so check if we
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 023c7bfa24df..4eece91ada37 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1015,6 +1015,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	c->x86_model_id[0] = '\0';  /* Unset */
 	c->x86_max_cores = 1;
 	c->x86_coreid_bits = 0;
+	c->cu_id = 0xff;
 #ifdef CONFIG_X86_64
 	c->x86_clflush_size = 64;
 	c->x86_phys_bits = 36;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index e9bbe02950ad..36171bcd91f8 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -423,9 +423,15 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 		int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
 
 		if (c->phys_proc_id == o->phys_proc_id &&
-		    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) &&
-		    c->cpu_core_id == o->cpu_core_id)
-			return topology_sane(c, o, "smt");
+		    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) {
+			if (c->cpu_core_id == o->cpu_core_id)
+				return topology_sane(c, o, "smt");
+
+			if ((c->cu_id != 0xff) &&
+			    (o->cu_id != 0xff) &&
+			    (c->cu_id == o->cu_id))
+				return topology_sane(c, o, "smt");
+		}
 
 	} else if (c->phys_proc_id == o->phys_proc_id &&
 		   c->cpu_core_id == o->cpu_core_id) {
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index ea9c49adaa1f..8aa6bea1cd6c 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -15,6 +15,7 @@
 #include <linux/debugfs.h>
 #include <linux/mm.h>
 #include <linux/init.h>
+#include <linux/sched.h>
 #include <linux/seq_file.h>
 
 #include <asm/pgtable.h>
@@ -406,6 +407,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
 		} else
 			note_page(m, &st, __pgprot(0), 1);
 
+		cond_resched();
 		start++;
 	}
 
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index e9c0993b131d..e8817e2f0597 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -671,9 +671,9 @@ static int aead_recvmsg_sync(struct socket *sock, struct msghdr *msg, int flags)
 unlock:
 	list_for_each_entry_safe(rsgl, tmp, &ctx->list, list) {
 		af_alg_free_sg(&rsgl->sgl);
+		list_del(&rsgl->list);
 		if (rsgl != &ctx->first_rsgl)
 			sock_kfree_s(sk, rsgl, sizeof(*rsgl));
-		list_del(&rsgl->list);
 	}
 	INIT_LIST_HEAD(&ctx->list);
 	aead_wmem_wakeup(sk);
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 312c4b4dc363..6eb6733a7a5c 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -2704,6 +2704,7 @@ static int acpi_nfit_flush_probe(struct nvdimm_bus_descriptor *nd_desc)
 	struct acpi_nfit_desc *acpi_desc = to_acpi_nfit_desc(nd_desc);
 	struct device *dev = acpi_desc->dev;
 	struct acpi_nfit_flush_work flush;
+	int rc;
 
 	/* bounce the device lock to flush acpi_nfit_add / acpi_nfit_notify */
 	device_lock(dev);
@@ -2716,7 +2717,10 @@ static int acpi_nfit_flush_probe(struct nvdimm_bus_descriptor *nd_desc)
 	INIT_WORK_ONSTACK(&flush.work, flush_probe);
 	COMPLETION_INITIALIZER_ONSTACK(flush.cmp);
 	queue_work(nfit_wq, &flush.work);
-	return wait_for_completion_interruptible(&flush.cmp);
+
+	rc = wait_for_completion_interruptible(&flush.cmp);
+	cancel_work_sync(&flush.work);
+	return rc;
 }
 
 static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc,
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 4737520ec823..80fa656da5ab 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -820,6 +820,25 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
 }
 
+#define MSR_IA32_POWER_CTL_BIT_EE	19
+
+/* Disable energy efficiency optimization */
+static void intel_pstate_disable_ee(int cpu)
+{
+	u64 power_ctl;
+	int ret;
+
+	ret = rdmsrl_on_cpu(cpu, MSR_IA32_POWER_CTL, &power_ctl);
+	if (ret)
+		return;
+
+	if (!(power_ctl & BIT(MSR_IA32_POWER_CTL_BIT_EE))) {
+		pr_info("Disabling energy efficiency optimization\n");
+		power_ctl |= BIT(MSR_IA32_POWER_CTL_BIT_EE);
+		wrmsrl_on_cpu(cpu, MSR_IA32_POWER_CTL, power_ctl);
+	}
+}
+
 static int atom_get_min_pstate(void)
 {
 	u64 value;
@@ -1420,6 +1439,11 @@ static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = {
 	{}
 };
 
+static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = {
+	ICPU(INTEL_FAM6_KABYLAKE_DESKTOP, core_params),
+	{}
+};
+
 static int intel_pstate_init_cpu(unsigned int cpunum)
 {
 	struct cpudata *cpu;
@@ -1435,6 +1459,12 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 	cpu->cpu = cpunum;
 
 	if (hwp_active) {
+		const struct x86_cpu_id *id;
+
+		id = x86_match_cpu(intel_pstate_cpu_ee_disable_ids);
+		if (id)
+			intel_pstate_disable_ee(cpunum);
+
 		intel_pstate_hwp_enable(cpu);
 		pid_params.sample_rate_ms = 50;
 		pid_params.sample_rate_ns = 50 * NSEC_PER_MSEC;
diff --git a/drivers/crypto/ccp/ccp-dev-v5.c b/drivers/crypto/ccp/ccp-dev-v5.c
index faf3cb3ddce2..a388bf2d67f4 100644
--- a/drivers/crypto/ccp/ccp-dev-v5.c
+++ b/drivers/crypto/ccp/ccp-dev-v5.c
@@ -955,7 +955,7 @@ static irqreturn_t ccp5_irq_handler(int irq, void *data)
 static void ccp5_config(struct ccp_device *ccp)
 {
 	/* Public side */
-	iowrite32(0x00001249, ccp->io_regs + CMD5_REQID_CONFIG_OFFSET);
+	iowrite32(0x0, ccp->io_regs + CMD5_REQID_CONFIG_OFFSET);
 }
 
 static void ccp5other_config(struct ccp_device *ccp)
diff --git a/drivers/crypto/ccp/ccp-dev.h b/drivers/crypto/ccp/ccp-dev.h
index da5f4a678083..340aef14d616 100644
--- a/drivers/crypto/ccp/ccp-dev.h
+++ b/drivers/crypto/ccp/ccp-dev.h
@@ -238,6 +238,7 @@ struct ccp_dma_chan {
 	struct ccp_device *ccp;
 
 	spinlock_t lock;
+	struct list_head created;
 	struct list_head pending;
 	struct list_head active;
 	struct list_head complete;
diff --git a/drivers/crypto/ccp/ccp-dmaengine.c b/drivers/crypto/ccp/ccp-dmaengine.c
index 6553912804f7..e5d9278f4019 100644
--- a/drivers/crypto/ccp/ccp-dmaengine.c
+++ b/drivers/crypto/ccp/ccp-dmaengine.c
@@ -63,6 +63,7 @@ static void ccp_free_chan_resources(struct dma_chan *dma_chan)
 	ccp_free_desc_resources(chan->ccp, &chan->complete);
 	ccp_free_desc_resources(chan->ccp, &chan->active);
 	ccp_free_desc_resources(chan->ccp, &chan->pending);
+	ccp_free_desc_resources(chan->ccp, &chan->created);
 
 	spin_unlock_irqrestore(&chan->lock, flags);
 }
@@ -273,6 +274,7 @@ static dma_cookie_t ccp_tx_submit(struct dma_async_tx_descriptor *tx_desc)
 	spin_lock_irqsave(&chan->lock, flags);
 
 	cookie = dma_cookie_assign(tx_desc);
+	list_del(&desc->entry);
 	list_add_tail(&desc->entry, &chan->pending);
 
 	spin_unlock_irqrestore(&chan->lock, flags);
@@ -426,7 +428,7 @@ static struct ccp_dma_desc *ccp_create_desc(struct dma_chan *dma_chan,
 
 	spin_lock_irqsave(&chan->lock, sflags);
 
-	list_add_tail(&desc->entry, &chan->pending);
+	list_add_tail(&desc->entry, &chan->created);
 
 	spin_unlock_irqrestore(&chan->lock, sflags);
 
@@ -610,6 +612,7 @@ static int ccp_terminate_all(struct dma_chan *dma_chan)
 	/*TODO: Purge the complete list? */
 	ccp_free_desc_resources(chan->ccp, &chan->active);
 	ccp_free_desc_resources(chan->ccp, &chan->pending);
+	ccp_free_desc_resources(chan->ccp, &chan->created);
 
 	spin_unlock_irqrestore(&chan->lock, flags);
 
@@ -679,6 +682,7 @@ int ccp_dmaengine_register(struct ccp_device *ccp)
 		chan->ccp = ccp;
 
 		spin_lock_init(&chan->lock);
+		INIT_LIST_HEAD(&chan->created);
 		INIT_LIST_HEAD(&chan->pending);
 		INIT_LIST_HEAD(&chan->active);
 		INIT_LIST_HEAD(&chan->complete);
diff --git a/drivers/crypto/chelsio/chcr_core.c b/drivers/crypto/chelsio/chcr_core.c
index fb5f9bbfa09c..6aece3f25b08 100644
--- a/drivers/crypto/chelsio/chcr_core.c
+++ b/drivers/crypto/chelsio/chcr_core.c
@@ -51,6 +51,7 @@ static struct cxgb4_uld_info chcr_uld_info = {
 int assign_chcr_device(struct chcr_dev **dev)
 {
 	struct uld_ctx *u_ctx;
+	int ret = -ENXIO;
 
 	/*
 	 * Which device to use if multiple devices are available TODO
@@ -58,15 +59,14 @@ int assign_chcr_device(struct chcr_dev **dev)
 	 * must go to the same device to maintain the ordering.
 	 */
 	mutex_lock(&dev_mutex); /* TODO ? */
-	u_ctx = list_first_entry(&uld_ctx_list, struct uld_ctx, entry);
-	if (!u_ctx) {
-		mutex_unlock(&dev_mutex);
-		return -ENXIO;
+	list_for_each_entry(u_ctx, &uld_ctx_list, entry)
+		if (u_ctx && u_ctx->dev) {
+			*dev = u_ctx->dev;
+			ret = 0;
+			break;
 	}
-
-	*dev = u_ctx->dev;
 	mutex_unlock(&dev_mutex);
-	return 0;
+	return ret;
 }
 
 static int chcr_dev_add(struct uld_ctx *u_ctx)
@@ -203,10 +203,8 @@ static int chcr_uld_state_change(void *handle, enum cxgb4_state state)
 
 static int __init chcr_crypto_init(void)
 {
-	if (cxgb4_register_uld(CXGB4_ULD_CRYPTO, &chcr_uld_info)) {
+	if (cxgb4_register_uld(CXGB4_ULD_CRYPTO, &chcr_uld_info))
 		pr_err("ULD register fail: No chcr crypto support in cxgb4");
-		return -1;
-	}
 
 	return 0;
 }
diff --git a/drivers/crypto/qat/qat_c62x/adf_drv.c b/drivers/crypto/qat/qat_c62x/adf_drv.c
index bc5cbc193aae..5b2d78a5b5aa 100644
--- a/drivers/crypto/qat/qat_c62x/adf_drv.c
+++ b/drivers/crypto/qat/qat_c62x/adf_drv.c
@@ -233,7 +233,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			      &hw_data->accel_capabilities_mask);
 
 	/* Find and map all the device's BARS */
-	i = 0;
+	i = (hw_data->fuses & ADF_DEVICE_FUSECTL_MASK) ? 1 : 0;
 	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
 	for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
 			 ADF_PCI_MAX_BARS * 2) {
diff --git a/drivers/crypto/qat/qat_common/adf_accel_devices.h b/drivers/crypto/qat/qat_common/adf_accel_devices.h
index e8822536530b..33f0a6251e38 100644
--- a/drivers/crypto/qat/qat_common/adf_accel_devices.h
+++ b/drivers/crypto/qat/qat_common/adf_accel_devices.h
@@ -69,6 +69,7 @@
 #define ADF_ERRSOU5 (0x3A000 + 0xD8)
 #define ADF_DEVICE_FUSECTL_OFFSET 0x40
 #define ADF_DEVICE_LEGFUSE_OFFSET 0x4C
+#define ADF_DEVICE_FUSECTL_MASK 0x80000000
 #define ADF_PCI_MAX_BARS 3
 #define ADF_DEVICE_NAME_LENGTH 32
 #define ADF_ETR_MAX_RINGS_PER_BANK 16
diff --git a/drivers/crypto/qat/qat_common/qat_hal.c b/drivers/crypto/qat/qat_common/qat_hal.c
index 1e480f140663..8c4fd255a601 100644
--- a/drivers/crypto/qat/qat_common/qat_hal.c
+++ b/drivers/crypto/qat/qat_common/qat_hal.c
@@ -456,7 +456,7 @@ static int qat_hal_init_esram(struct icp_qat_fw_loader_handle *handle)
 	unsigned int csr_val;
 	int times = 30;
 
-	if (handle->pci_dev->device == ADF_C3XXX_PCI_DEVICE_ID)
+	if (handle->pci_dev->device != ADF_DH895XCC_PCI_DEVICE_ID)
 		return 0;
 
 	csr_val = ADF_CSR_RD(csr_addr, 0);
@@ -716,7 +716,7 @@ int qat_hal_init(struct adf_accel_dev *accel_dev)
 		(void __iomem *)((uintptr_t)handle->hal_cap_ae_xfer_csr_addr_v +
 				 LOCAL_TO_XFER_REG_OFFSET);
 	handle->pci_dev = pci_info->pci_dev;
-	if (handle->pci_dev->device != ADF_C3XXX_PCI_DEVICE_ID) {
+	if (handle->pci_dev->device == ADF_DH895XCC_PCI_DEVICE_ID) {
 		sram_bar =
 			&pci_info->pci_bars[hw_data->get_sram_bar_id(hw_data)];
 		handle->hal_sram_addr_v = sram_bar->virt_addr;
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index e6862a744210..4e19bde4bbff 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -1759,16 +1759,16 @@ int drm_mode_atomic_ioctl(struct drm_device *dev,
 
 	if (ret && arg->flags & DRM_MODE_PAGE_FLIP_EVENT) {
 		/*
-		 * TEST_ONLY and PAGE_FLIP_EVENT are mutually exclusive,
-		 * if they weren't, this code should be called on success
-		 * for TEST_ONLY too.
+		 * Free the allocated event. drm_atomic_helper_setup_commit
+		 * can allocate an event too, so only free it if it's ours
+		 * to prevent a double free in drm_atomic_state_clear.
 		 */
-
 		for_each_crtc_in_state(state, crtc, crtc_state, i) {
-			if (!crtc_state->event)
-				continue;
-
-			drm_event_cancel_free(dev, &crtc_state->event->base);
+			struct drm_pending_vblank_event *event = crtc_state->event;
+			if (event && (event->base.fence || event->base.file_priv)) {
+				drm_event_cancel_free(dev, &event->base);
+				crtc_state->event = NULL;
+			}
 		}
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index a218c2e395e7..0c400f852a76 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1215,14 +1215,14 @@ validate_exec_list(struct drm_device *dev,
 			if (exec[i].offset !=
 			    gen8_canonical_addr(exec[i].offset & PAGE_MASK))
 				return -EINVAL;
-
-			/* From drm_mm perspective address space is continuous,
-			 * so from this point we're always using non-canonical
-			 * form internally.
-			 */
-			exec[i].offset = gen8_noncanonical_addr(exec[i].offset);
 		}
 
+		/* From drm_mm perspective address space is continuous,
+		 * so from this point we're always using non-canonical
+		 * form internally.
+		 */
+		exec[i].offset = gen8_noncanonical_addr(exec[i].offset);
+
 		if (exec[i].alignment && !is_power_of_2(exec[i].alignment))
 			return -EINVAL;
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 8079e5b380cb..b9be8a6141d8 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -4280,10 +4280,10 @@ static void page_flip_completed(struct intel_crtc *intel_crtc)
 	drm_crtc_vblank_put(&intel_crtc->base);
 
 	wake_up_all(&dev_priv->pending_flip_queue);
-	queue_work(dev_priv->wq, &work->unpin_work);
-
 	trace_i915_flip_complete(intel_crtc->plane,
 				 work->pending_flip_obj);
+
+	queue_work(dev_priv->wq, &work->unpin_work);
 }
 
 static int intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc)
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index 1c59ca50c430..cae27c55dd99 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -1723,7 +1723,8 @@ bxt_get_dpll(struct intel_crtc *crtc,
 		return NULL;
 
 	if ((encoder->type == INTEL_OUTPUT_DP ||
-	     encoder->type == INTEL_OUTPUT_EDP) &&
+	     encoder->type == INTEL_OUTPUT_EDP ||
+	     encoder->type == INTEL_OUTPUT_DP_MST) &&
 	    !bxt_ddi_dp_set_dpll_hw_state(clock, &dpll_hw_state))
 		return NULL;
 
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 16f91c8490fe..5fb4c6d9209b 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -39,7 +39,7 @@
  * vmbus_setevent- Trigger an event notification on the specified
  * channel.
  */
-static void vmbus_setevent(struct vmbus_channel *channel)
+void vmbus_setevent(struct vmbus_channel *channel)
 {
 	struct hv_monitor_page *monitorpage;
 
@@ -65,6 +65,7 @@ static void vmbus_setevent(struct vmbus_channel *channel)
 		vmbus_set_event(channel);
 	}
 }
+EXPORT_SYMBOL_GPL(vmbus_setevent);
 
 /*
  * vmbus_open - Open the specified channel.
@@ -635,8 +636,6 @@ int vmbus_sendpacket_ctl(struct vmbus_channel *channel, void *buffer,
 	u32 packetlen_aligned = ALIGN(packetlen, sizeof(u64));
 	struct kvec bufferlist[3];
 	u64 aligned_data = 0;
-	int ret;
-	bool signal = false;
 	bool lock = channel->acquire_ring_lock;
 	int num_vecs = ((bufferlen != 0) ? 3 : 1);
 
@@ -656,33 +655,9 @@ int vmbus_sendpacket_ctl(struct vmbus_channel *channel, void *buffer,
 	bufferlist[2].iov_base = &aligned_data;
 	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
-	ret = hv_ringbuffer_write(&channel->outbound, bufferlist, num_vecs,
-				  &signal, lock, channel->signal_policy);
-
-	/*
-	 * Signalling the host is conditional on many factors:
-	 * 1. The ring state changed from being empty to non-empty.
-	 *    This is tracked by the variable "signal".
-	 * 2. The variable kick_q tracks if more data will be placed
-	 *    on the ring. We will not signal if more data is
-	 *    to be placed.
-	 *
-	 * Based on the channel signal state, we will decide
-	 * which signaling policy will be applied.
-	 *
-	 * If we cannot write to the ring-buffer; signal the host
-	 * even if we may not have written anything. This is a rare
-	 * enough condition that it should not matter.
-	 * NOTE: in this case, the hvsock channel is an exception, because
-	 * it looks the host side's hvsock implementation has a throttling
-	 * mechanism which can hurt the performance otherwise.
-	 */
-
-	if (((ret == 0) && kick_q && signal) ||
-	    (ret && !is_hvsock_channel(channel)))
-		vmbus_setevent(channel);
+	return hv_ringbuffer_write(channel, bufferlist, num_vecs,
+				   lock, kick_q);
 
-	return ret;
 }
 EXPORT_SYMBOL(vmbus_sendpacket_ctl);
 
@@ -723,7 +698,6 @@ int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel,
 				     u32 flags,
 				     bool kick_q)
 {
-	int ret;
 	int i;
 	struct vmbus_channel_packet_page_buffer desc;
 	u32 descsize;
@@ -731,7 +705,6 @@ int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel,
 	u32 packetlen_aligned;
 	struct kvec bufferlist[3];
 	u64 aligned_data = 0;
-	bool signal = false;
 	bool lock = channel->acquire_ring_lock;
 
 	if (pagecount > MAX_PAGE_BUFFER_COUNT)
@@ -769,29 +742,8 @@ int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel,
 	bufferlist[2].iov_base = &aligned_data;
 	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
-	ret = hv_ringbuffer_write(&channel->outbound, bufferlist, 3,
-				  &signal, lock, channel->signal_policy);
-
-	/*
-	 * Signalling the host is conditional on many factors:
-	 * 1. The ring state changed from being empty to non-empty.
-	 *    This is tracked by the variable "signal".
-	 * 2. The variable kick_q tracks if more data will be placed
-	 *    on the ring. We will not signal if more data is
-	 *    to be placed.
-	 *
-	 * Based on the channel signal state, we will decide
-	 * which signaling policy will be applied.
-	 *
-	 * If we cannot write to the ring-buffer; signal the host
-	 * even if we may not have written anything. This is a rare
-	 * enough condition that it should not matter.
-	 */
-
-	if (((ret == 0) && kick_q && signal) || (ret))
-		vmbus_setevent(channel);
-
-	return ret;
+	return hv_ringbuffer_write(channel, bufferlist, 3,
+				   lock, kick_q);
 }
 EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer_ctl);
 
@@ -822,12 +774,10 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
 			      u32 desc_size,
 			      void *buffer, u32 bufferlen, u64 requestid)
 {
-	int ret;
 	u32 packetlen;
 	u32 packetlen_aligned;
 	struct kvec bufferlist[3];
 	u64 aligned_data = 0;
-	bool signal = false;
 	bool lock = channel->acquire_ring_lock;
 
 	packetlen = desc_size + bufferlen;
@@ -848,13 +798,8 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
 	bufferlist[2].iov_base = &aligned_data;
 	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
-	ret = hv_ringbuffer_write(&channel->outbound, bufferlist, 3,
-				  &signal, lock, channel->signal_policy);
-
-	if (ret == 0 && signal)
-		vmbus_setevent(channel);
-
-	return ret;
+	return hv_ringbuffer_write(channel, bufferlist, 3,
+				   lock, true);
 }
 EXPORT_SYMBOL_GPL(vmbus_sendpacket_mpb_desc);
 
@@ -866,14 +811,12 @@ int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel,
 				struct hv_multipage_buffer *multi_pagebuffer,
 				void *buffer, u32 bufferlen, u64 requestid)
 {
-	int ret;
 	struct vmbus_channel_packet_multipage_buffer desc;
 	u32 descsize;
 	u32 packetlen;
 	u32 packetlen_aligned;
 	struct kvec bufferlist[3];
 	u64 aligned_data = 0;
-	bool signal = false;
 	bool lock = channel->acquire_ring_lock;
 	u32 pfncount = NUM_PAGES_SPANNED(multi_pagebuffer->offset,
 					 multi_pagebuffer->len);
@@ -913,13 +856,8 @@ int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel,
 	bufferlist[2].iov_base = &aligned_data;
 	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
-	ret = hv_ringbuffer_write(&channel->outbound, bufferlist, 3,
-				  &signal, lock, channel->signal_policy);
-
-	if (ret == 0 && signal)
-		vmbus_setevent(channel);
-
-	return ret;
+	return hv_ringbuffer_write(channel, bufferlist, 3,
+				   lock, true);
 }
 EXPORT_SYMBOL_GPL(vmbus_sendpacket_multipagebuffer);
 
@@ -941,16 +879,9 @@ __vmbus_recvpacket(struct vmbus_channel *channel, void *buffer,
 		   u32 bufferlen, u32 *buffer_actual_len, u64 *requestid,
 		   bool raw)
 {
-	int ret;
-	bool signal = false;
+	return hv_ringbuffer_read(channel, buffer, bufferlen,
+				  buffer_actual_len, requestid, raw);
 
-	ret = hv_ringbuffer_read(&channel->inbound, buffer, bufferlen,
-				 buffer_actual_len, requestid, &signal, raw);
-
-	if (signal)
-		vmbus_setevent(channel);
-
-	return ret;
 }
 
 int vmbus_recvpacket(struct vmbus_channel *channel, void *buffer,
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 1bc1d4795243..caf341842464 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -449,8 +449,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
 	}
 
 	dev_type = hv_get_dev_type(newchannel);
-	if (dev_type == HV_NIC)
-		set_channel_signal_state(newchannel, HV_SIGNAL_POLICY_EXPLICIT);
 
 	init_vp_index(newchannel, dev_type);
 
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index a5b4442433c8..2b13f2a0a71e 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -527,14 +527,14 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info,
 
 void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info);
 
-int hv_ringbuffer_write(struct hv_ring_buffer_info *ring_info,
+int hv_ringbuffer_write(struct vmbus_channel *channel,
 		    struct kvec *kv_list,
-		    u32 kv_count, bool *signal, bool lock,
-		    enum hv_signal_policy policy);
+		    u32 kv_count, bool lock,
+		    bool kick_q);
 
-int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info,
+int hv_ringbuffer_read(struct vmbus_channel *channel,
 		       void *buffer, u32 buflen, u32 *buffer_actual_len,
-		       u64 *requestid, bool *signal, bool raw);
+		       u64 *requestid, bool raw);
 
 void hv_ringbuffer_get_debuginfo(struct hv_ring_buffer_info *ring_info,
 			    struct hv_ring_buffer_debug_info *debug_info);
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index 08043da1a61c..308dbda700eb 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -66,21 +66,25 @@ u32 hv_end_read(struct hv_ring_buffer_info *rbi)
  *	   once the ring buffer is empty, it will clear the
  *	   interrupt_mask and re-check to see if new data has
  *	   arrived.
+ *
+ * KYS: Oct. 30, 2016:
+ * It looks like Windows hosts have logic to deal with DOS attacks that
+ * can be triggered if it receives interrupts when it is not expecting
+ * the interrupt. The host expects interrupts only when the ring
+ * transitions from empty to non-empty (or full to non full on the guest
+ * to host ring).
+ * So, base the signaling decision solely on the ring state until the
+ * host logic is fixed.
  */
 
-static bool hv_need_to_signal(u32 old_write, struct hv_ring_buffer_info *rbi,
-			      enum hv_signal_policy policy)
+static void hv_signal_on_write(u32 old_write, struct vmbus_channel *channel,
+			       bool kick_q)
 {
+	struct hv_ring_buffer_info *rbi = &channel->outbound;
+
 	virt_mb();
 	if (READ_ONCE(rbi->ring_buffer->interrupt_mask))
-		return false;
-
-	/*
-	 * When the client wants to control signaling,
-	 * we only honour the host interrupt mask.
-	 */
-	if (policy == HV_SIGNAL_POLICY_EXPLICIT)
-		return true;
+		return;
 
 	/* check interrupt_mask before read_index */
 	virt_rmb();
@@ -89,9 +93,9 @@ static bool hv_need_to_signal(u32 old_write, struct hv_ring_buffer_info *rbi,
 	 * ring transitions from being empty to non-empty.
 	 */
 	if (old_write == READ_ONCE(rbi->ring_buffer->read_index))
-		return true;
+		vmbus_setevent(channel);
 
-	return false;
+	return;
 }
 
 /* Get the next write location for the specified ring buffer. */
@@ -280,9 +284,9 @@ void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info)
 }
 
 /* Write to the ring buffer. */
-int hv_ringbuffer_write(struct hv_ring_buffer_info *outring_info,
-		    struct kvec *kv_list, u32 kv_count, bool *signal, bool lock,
-		    enum hv_signal_policy policy)
+int hv_ringbuffer_write(struct vmbus_channel *channel,
+		    struct kvec *kv_list, u32 kv_count, bool lock,
+		    bool kick_q)
 {
 	int i = 0;
 	u32 bytes_avail_towrite;
@@ -292,6 +296,7 @@ int hv_ringbuffer_write(struct hv_ring_buffer_info *outring_info,
 	u32 old_write;
 	u64 prev_indices = 0;
 	unsigned long flags = 0;
+	struct hv_ring_buffer_info *outring_info = &channel->outbound;
 
 	for (i = 0; i < kv_count; i++)
 		totalbytes_towrite += kv_list[i].iov_len;
@@ -344,13 +349,13 @@ int hv_ringbuffer_write(struct hv_ring_buffer_info *outring_info,
 	if (lock)
 		spin_unlock_irqrestore(&outring_info->ring_lock, flags);
 
-	*signal = hv_need_to_signal(old_write, outring_info, policy);
+	hv_signal_on_write(old_write, channel, kick_q);
 	return 0;
 }
 
-int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info,
+int hv_ringbuffer_read(struct vmbus_channel *channel,
 		       void *buffer, u32 buflen, u32 *buffer_actual_len,
-		       u64 *requestid, bool *signal, bool raw)
+		       u64 *requestid, bool raw)
 {
 	u32 bytes_avail_toread;
 	u32 next_read_location = 0;
@@ -359,6 +364,7 @@ int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info,
 	u32 offset;
 	u32 packetlen;
 	int ret = 0;
+	struct hv_ring_buffer_info *inring_info = &channel->inbound;
 
 	if (buflen <= 0)
 		return -EINVAL;
@@ -377,6 +383,7 @@ int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info,
 		return ret;
 	}
 
+	init_cached_read_index(channel);
 	next_read_location = hv_get_next_read_location(inring_info);
 	next_read_location = hv_copyfrom_ringbuffer(inring_info, &desc,
 						    sizeof(desc),
@@ -416,7 +423,7 @@ int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info,
 	/* Update the read index */
 	hv_set_next_read_location(inring_info, next_read_location);
 
-	*signal = hv_need_to_signal_on_read(inring_info);
+	hv_signal_on_read(channel);
 
 	return ret;
 }
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index 1869152f1d23..9b732c5f89e1 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -59,9 +59,11 @@ int mem_check_range(struct rxe_mem *mem, u64 iova, size_t length)
 
 	case RXE_MEM_TYPE_MR:
 	case RXE_MEM_TYPE_FMR:
-		return ((iova < mem->iova) ||
-			((iova + length) > (mem->iova + mem->length))) ?
-			-EFAULT : 0;
+		if (iova < mem->iova ||
+		    length > mem->length ||
+		    iova > mem->iova + mem->length - length)
+			return -EFAULT;
+		return 0;
 
 	default:
 		return -EFAULT;
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index dd3d88adc003..ccf624763565 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -472,7 +472,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 				goto err2;
 			}
 
-			resid = mtu;
+			qp->resp.resid = mtu;
 		} else {
 			if (pktlen != resid) {
 				state = RESPST_ERR_LENGTH;
diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c
index 92595b98e7ed..022be0e22eba 100644
--- a/drivers/input/misc/uinput.c
+++ b/drivers/input/misc/uinput.c
@@ -263,13 +263,21 @@ static int uinput_create_device(struct uinput_device *udev)
 		return -EINVAL;
 	}
 
-	if (test_bit(ABS_MT_SLOT, dev->absbit)) {
-		nslot = input_abs_get_max(dev, ABS_MT_SLOT) + 1;
-		error = input_mt_init_slots(dev, nslot, 0);
-		if (error)
+	if (test_bit(EV_ABS, dev->evbit)) {
+		input_alloc_absinfo(dev);
+		if (!dev->absinfo) {
+			error = -EINVAL;
 			goto fail1;
-	} else if (test_bit(ABS_MT_POSITION_X, dev->absbit)) {
-		input_set_events_per_packet(dev, 60);
+		}
+
+		if (test_bit(ABS_MT_SLOT, dev->absbit)) {
+			nslot = input_abs_get_max(dev, ABS_MT_SLOT) + 1;
+			error = input_mt_init_slots(dev, nslot, 0);
+			if (error)
+				goto fail1;
+		} else if (test_bit(ABS_MT_POSITION_X, dev->absbit)) {
+			input_set_events_per_packet(dev, 60);
+		}
 	}
 
 	if (test_bit(EV_FF, dev->evbit) && !udev->ff_effects_max) {
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 31a89c8832c0..2c965424d383 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -804,6 +804,10 @@ static void dm_old_request_fn(struct request_queue *q)
 		int srcu_idx;
 		struct dm_table *map = dm_get_live_table(md, &srcu_idx);
 
+		if (unlikely(!map)) {
+			dm_put_live_table(md, srcu_idx);
+			return;
+		}
 		ti = dm_table_find_target(map, pos);
 		dm_put_live_table(md, srcu_idx);
 	}
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
index 878950a42e6c..2cf8b1d82d6a 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
@@ -1007,9 +1007,7 @@
 
 static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value)
 {
-	u8 __iomem *reg_addr = ACCESS_ONCE(base);
-
-	writel(value, reg_addr + reg);
+	writel(value, base + reg);
 }
 
 #define dsaf_write_dev(a, reg, value) \
@@ -1017,9 +1015,7 @@ static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value)
 
 static inline u32 dsaf_read_reg(u8 __iomem *base, u32 reg)
 {
-	u8 __iomem *reg_addr = ACCESS_ONCE(base);
-
-	return readl(reg_addr + reg);
+	return readl(base + reg);
 }
 
 static inline void dsaf_write_syscon(struct regmap *base, u32 reg, u32 value)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 27ff401cec20..51c6a57ca873 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -991,6 +991,7 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	int inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
+	bool hash_changed = false;
 	void *in;
 
 	if ((hfunc != ETH_RSS_HASH_NO_CHANGE) &&
@@ -1012,14 +1013,21 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 		mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, 0);
 	}
 
-	if (key)
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    hfunc != priv->params.rss_hfunc) {
+		priv->params.rss_hfunc = hfunc;
+		hash_changed = true;
+	}
+
+	if (key) {
 		memcpy(priv->params.toeplitz_hash_key, key,
 		       sizeof(priv->params.toeplitz_hash_key));
+		hash_changed = hash_changed ||
+			       priv->params.rss_hfunc == ETH_RSS_HASH_TOP;
+	}
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE)
-		priv->params.rss_hfunc = hfunc;
-
-	mlx5e_modify_tirs_hash(priv, in, inlen);
+	if (hash_changed)
+		mlx5e_modify_tirs_hash(priv, in, inlen);
 
 	mutex_unlock(&priv->state_lock);
 
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 720b5fa9e625..c2ac39a940f7 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -1288,6 +1288,9 @@ void netvsc_channel_cb(void *context)
 	ndev = hv_get_drvdata(device);
 	buffer = get_per_channel_state(channel);
 
+	/* commit_rd_index() -> hv_signal_on_read() needs this. */
+	init_cached_read_index(channel);
+
 	do {
 		desc = get_next_pkt_raw(channel);
 		if (desc != NULL) {
@@ -1340,6 +1343,9 @@ void netvsc_channel_cb(void *context)
 
 			bufferlen = bytes_recvd;
 		}
+
+		init_cached_read_index(channel);
+
 	} while (1);
 
 	if (bufferlen > NETVSC_PACKET_SIZE)
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
index 8b6e37ce3f66..20bfb373dcd6 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
@@ -96,7 +96,7 @@ int rtl92c_init_sw_vars(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
-	char *fw_name = "rtlwifi/rtl8192cfwU.bin";
+	char *fw_name;
 
 	rtl8192ce_bt_reg_init(hw);
 
@@ -168,8 +168,13 @@ int rtl92c_init_sw_vars(struct ieee80211_hw *hw)
 	}
 
 	/* request fw */
-	if (IS_81XXC_VENDOR_UMC_B_CUT(rtlhal->version))
+	if (IS_VENDOR_UMC_A_CUT(rtlhal->version) &&
+	    !IS_92C_SERIAL(rtlhal->version))
+		fw_name = "rtlwifi/rtl8192cfwU.bin";
+	else if (IS_81XXC_VENDOR_UMC_B_CUT(rtlhal->version))
 		fw_name = "rtlwifi/rtl8192cfwU_B.bin";
+	else
+		fw_name = "rtlwifi/rtl8192cfw.bin";
 
 	rtlpriv->max_fw_size = 0x4000;
 	pr_info("Using firmware %s\n", fw_name);
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index bf2744e1e3db..0cdcb2169083 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1397,6 +1397,8 @@ static void xennet_disconnect_backend(struct netfront_info *info)
 	for (i = 0; i < num_queues && info->queues; ++i) {
 		struct netfront_queue *queue = &info->queues[i];
 
+		del_timer_sync(&queue->rx_refill_timer);
+
 		if (queue->tx_irq && (queue->tx_irq == queue->rx_irq))
 			unbind_from_irqhandler(queue->tx_irq, queue);
 		if (queue->tx_irq && (queue->tx_irq != queue->rx_irq)) {
@@ -1751,7 +1753,6 @@ static void xennet_destroy_queues(struct netfront_info *info)
 
 		if (netif_running(info->netdev))
 			napi_disable(&queue->napi);
-		del_timer_sync(&queue->rx_refill_timer);
 		netif_napi_del(&queue->napi);
 	}
 
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index 1480734c2d6e..aefca644219b 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -962,8 +962,8 @@ static ssize_t __size_store(struct device *dev, unsigned long long val)
 	struct nvdimm_drvdata *ndd;
 	struct nd_label_id label_id;
 	u32 flags = 0, remainder;
+	int rc, i, id = -1;
 	u8 *uuid = NULL;
-	int rc, i;
 
 	if (dev->driver || ndns->claim)
 		return -EBUSY;
@@ -972,11 +972,13 @@ static ssize_t __size_store(struct device *dev, unsigned long long val)
 		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
 
 		uuid = nspm->uuid;
+		id = nspm->id;
 	} else if (is_namespace_blk(dev)) {
 		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
 
 		uuid = nsblk->uuid;
 		flags = NSLABEL_FLAG_LOCAL;
+		id = nsblk->id;
 	}
 
 	/*
@@ -1039,10 +1041,11 @@ static ssize_t __size_store(struct device *dev, unsigned long long val)
 
 	/*
 	 * Try to delete the namespace if we deleted all of its
-	 * allocation, this is not the seed device for the region, and
-	 * it is not actively claimed by a btt instance.
+	 * allocation, this is not the seed or 0th device for the
+	 * region, and it is not actively claimed by a btt, pfn, or dax
+	 * instance.
 	 */
-	if (val == 0 && nd_region->ns_seed != dev && !ndns->claim)
+	if (val == 0 && id != 0 && nd_region->ns_seed != dev && !ndns->claim)
 		nd_device_unregister(dev, ND_ASYNC);
 
 	return rc;
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index a2ac9e641aa9..6c033c9a2f06 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -627,15 +627,12 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 	size = resource_size(&nsio->res);
 	npfns = (size - start_pad - end_trunc - SZ_8K) / SZ_4K;
 	if (nd_pfn->mode == PFN_MODE_PMEM) {
-		unsigned long memmap_size;
-
 		/*
 		 * vmemmap_populate_hugepages() allocates the memmap array in
 		 * HPAGE_SIZE chunks.
 		 */
-		memmap_size = ALIGN(64 * npfns, HPAGE_SIZE);
-		offset = ALIGN(start + SZ_8K + memmap_size + dax_label_reserve,
-				nd_pfn->align) - start;
+		offset = ALIGN(start + SZ_8K + 64 * npfns + dax_label_reserve,
+				max(nd_pfn->align, HPAGE_SIZE)) - start;
 	} else if (nd_pfn->mode == PFN_MODE_RAM)
 		offset = ALIGN(start + SZ_8K + dax_label_reserve,
 				nd_pfn->align) - start;
diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c
index 75f820ca17b7..27ff38f839fc 100644
--- a/drivers/s390/scsi/zfcp_fsf.c
+++ b/drivers/s390/scsi/zfcp_fsf.c
@@ -1583,7 +1583,7 @@ static void zfcp_fsf_open_wka_port_handler(struct zfcp_fsf_req *req)
 int zfcp_fsf_open_wka_port(struct zfcp_fc_wka_port *wka_port)
 {
 	struct zfcp_qdio *qdio = wka_port->adapter->qdio;
-	struct zfcp_fsf_req *req = NULL;
+	struct zfcp_fsf_req *req;
 	int retval = -EIO;
 
 	spin_lock_irq(&qdio->req_q_lock);
@@ -1612,7 +1612,7 @@ int zfcp_fsf_open_wka_port(struct zfcp_fc_wka_port *wka_port)
 		zfcp_fsf_req_free(req);
 out:
 	spin_unlock_irq(&qdio->req_q_lock);
-	if (req && !IS_ERR(req))
+	if (!retval)
 		zfcp_dbf_rec_run_wka("fsowp_1", wka_port, req->req_id);
 	return retval;
 }
@@ -1638,7 +1638,7 @@ static void zfcp_fsf_close_wka_port_handler(struct zfcp_fsf_req *req)
 int zfcp_fsf_close_wka_port(struct zfcp_fc_wka_port *wka_port)
 {
 	struct zfcp_qdio *qdio = wka_port->adapter->qdio;
-	struct zfcp_fsf_req *req = NULL;
+	struct zfcp_fsf_req *req;
 	int retval = -EIO;
 
 	spin_lock_irq(&qdio->req_q_lock);
@@ -1667,7 +1667,7 @@ int zfcp_fsf_close_wka_port(struct zfcp_fc_wka_port *wka_port)
 		zfcp_fsf_req_free(req);
 out:
 	spin_unlock_irq(&qdio->req_q_lock);
-	if (req && !IS_ERR(req))
+	if (!retval)
 		zfcp_dbf_rec_run_wka("fscwp_1", wka_port, req->req_id);
 	return retval;
 }
diff --git a/drivers/scsi/aacraid/comminit.c b/drivers/scsi/aacraid/comminit.c
index 341ea327ae79..792d3e7e35e2 100644
--- a/drivers/scsi/aacraid/comminit.c
+++ b/drivers/scsi/aacraid/comminit.c
@@ -50,9 +50,13 @@ struct aac_common aac_config = {
 
 static inline int aac_is_msix_mode(struct aac_dev *dev)
 {
-	u32 status;
+	u32 status = 0;
 
-	status = src_readl(dev, MUnit.OMR);
+	if (dev->pdev->device == PMC_DEVICE_S6 ||
+		dev->pdev->device == PMC_DEVICE_S7 ||
+		dev->pdev->device == PMC_DEVICE_S8) {
+		status = src_readl(dev, MUnit.OMR);
+	}
 	return (status & AAC_INT_MODE_MSIX);
 }
 
diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index e3b911c895b4..91dfd58b175d 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -3929,6 +3929,7 @@ static struct configfs_attribute *ibmvscsis_tpg_attrs[] = {
 static const struct target_core_fabric_ops ibmvscsis_ops = {
 	.module				= THIS_MODULE,
 	.name				= "ibmvscsis",
+	.max_data_sg_nents		= MAX_TXU / PAGE_SIZE,
 	.get_fabric_name		= ibmvscsis_get_fabric_name,
 	.tpg_get_wwn			= ibmvscsis_get_fabric_wwn,
 	.tpg_get_tag			= ibmvscsis_get_tag,
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index f84a6087cebd..8a7941b8189f 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -51,6 +51,7 @@
 #include <linux/workqueue.h>
 #include <linux/delay.h>
 #include <linux/pci.h>
+#include <linux/pci-aspm.h>
 #include <linux/interrupt.h>
 #include <linux/aer.h>
 #include <linux/raid_class.h>
@@ -8706,6 +8707,8 @@ _scsih_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	switch (hba_mpi_version) {
 	case MPI2_VERSION:
+		pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S |
+			PCIE_LINK_STATE_L1 | PCIE_LINK_STATE_CLKPM);
 		/* Use mpt2sas driver host template for SAS 2.0 HBA's */
 		shost = scsi_host_alloc(&mpt2sas_driver_template,
 		  sizeof(struct MPT3SAS_ADAPTER));
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 078d797cb492..bea819e5336d 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1459,7 +1459,7 @@ qla2x00_abort_all_cmds(scsi_qla_host_t *vha, int res)
 				/* Don't abort commands in adapter during EEH
 				 * recovery as it's not accessible/responding.
 				 */
-				if (!ha->flags.eeh_busy) {
+				if (GET_CMD_SP(sp) && !ha->flags.eeh_busy) {
 					/* Get a reference to the sp and drop the lock.
 					 * The reference ensures this sp->done() call
 					 * - and not the call in qla2xxx_eh_abort() -
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 6b423485c5d6..ea9617c7b403 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -351,7 +351,15 @@ int core_enable_device_list_for_node(
 			kfree(new);
 			return -EINVAL;
 		}
-		BUG_ON(orig->se_lun_acl != NULL);
+		if (orig->se_lun_acl != NULL) {
+			pr_warn_ratelimited("Detected existing explicit"
+				" se_lun_acl->se_lun_group reference for %s"
+				" mapped_lun: %llu, failing\n",
+				 nacl->initiatorname, mapped_lun);
+			mutex_unlock(&nacl->lun_entry_mutex);
+			kfree(new);
+			return -EINVAL;
+		}
 
 		rcu_assign_pointer(new->se_lun, lun);
 		rcu_assign_pointer(new->se_lun_acl, lun_acl);
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 04f616b3ba0a..aabd6602da6c 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -450,6 +450,7 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success,
 					     int *post_ret)
 {
 	struct se_device *dev = cmd->se_dev;
+	sense_reason_t ret = TCM_NO_SENSE;
 
 	/*
 	 * Only set SCF_COMPARE_AND_WRITE_POST to force a response fall-through
@@ -457,9 +458,12 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success,
 	 * sent to the backend driver.
 	 */
 	spin_lock_irq(&cmd->t_state_lock);
-	if ((cmd->transport_state & CMD_T_SENT) && !cmd->scsi_status) {
+	if (cmd->transport_state & CMD_T_SENT) {
 		cmd->se_cmd_flags |= SCF_COMPARE_AND_WRITE_POST;
 		*post_ret = 1;
+
+		if (cmd->scsi_status == SAM_STAT_CHECK_CONDITION)
+			ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 	spin_unlock_irq(&cmd->t_state_lock);
 
@@ -469,7 +473,7 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success,
 	 */
 	up(&dev->caw_sem);
 
-	return TCM_NO_SENSE;
+	return ret;
 }
 
 static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool success,
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 7dfefd66df93..767d1eb6e035 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -457,8 +457,20 @@ static void target_complete_nacl(struct kref *kref)
 {
 	struct se_node_acl *nacl = container_of(kref,
 				struct se_node_acl, acl_kref);
+	struct se_portal_group *se_tpg = nacl->se_tpg;
 
-	complete(&nacl->acl_free_comp);
+	if (!nacl->dynamic_stop) {
+		complete(&nacl->acl_free_comp);
+		return;
+	}
+
+	mutex_lock(&se_tpg->acl_node_mutex);
+	list_del(&nacl->acl_list);
+	mutex_unlock(&se_tpg->acl_node_mutex);
+
+	core_tpg_wait_for_nacl_pr_ref(nacl);
+	core_free_device_list_for_node(nacl, se_tpg);
+	kfree(nacl);
 }
 
 void target_put_nacl(struct se_node_acl *nacl)
@@ -499,12 +511,39 @@ EXPORT_SYMBOL(transport_deregister_session_configfs);
 void transport_free_session(struct se_session *se_sess)
 {
 	struct se_node_acl *se_nacl = se_sess->se_node_acl;
+
 	/*
 	 * Drop the se_node_acl->nacl_kref obtained from within
 	 * core_tpg_get_initiator_node_acl().
 	 */
 	if (se_nacl) {
+		struct se_portal_group *se_tpg = se_nacl->se_tpg;
+		const struct target_core_fabric_ops *se_tfo = se_tpg->se_tpg_tfo;
+		unsigned long flags;
+
 		se_sess->se_node_acl = NULL;
+
+		/*
+		 * Also determine if we need to drop the extra ->cmd_kref if
+		 * it had been previously dynamically generated, and
+		 * the endpoint is not caching dynamic ACLs.
+		 */
+		mutex_lock(&se_tpg->acl_node_mutex);
+		if (se_nacl->dynamic_node_acl &&
+		    !se_tfo->tpg_check_demo_mode_cache(se_tpg)) {
+			spin_lock_irqsave(&se_nacl->nacl_sess_lock, flags);
+			if (list_empty(&se_nacl->acl_sess_list))
+				se_nacl->dynamic_stop = true;
+			spin_unlock_irqrestore(&se_nacl->nacl_sess_lock, flags);
+
+			if (se_nacl->dynamic_stop)
+				list_del(&se_nacl->acl_list);
+		}
+		mutex_unlock(&se_tpg->acl_node_mutex);
+
+		if (se_nacl->dynamic_stop)
+			target_put_nacl(se_nacl);
+
 		target_put_nacl(se_nacl);
 	}
 	if (se_sess->sess_cmd_map) {
@@ -518,16 +557,12 @@ EXPORT_SYMBOL(transport_free_session);
 void transport_deregister_session(struct se_session *se_sess)
 {
 	struct se_portal_group *se_tpg = se_sess->se_tpg;
-	const struct target_core_fabric_ops *se_tfo;
-	struct se_node_acl *se_nacl;
 	unsigned long flags;
-	bool drop_nacl = false;
 
 	if (!se_tpg) {
 		transport_free_session(se_sess);
 		return;
 	}
-	se_tfo = se_tpg->se_tpg_tfo;
 
 	spin_lock_irqsave(&se_tpg->session_lock, flags);
 	list_del(&se_sess->sess_list);
@@ -535,33 +570,15 @@ void transport_deregister_session(struct se_session *se_sess)
 	se_sess->fabric_sess_ptr = NULL;
 	spin_unlock_irqrestore(&se_tpg->session_lock, flags);
 
-	/*
-	 * Determine if we need to do extra work for this initiator node's
-	 * struct se_node_acl if it had been previously dynamically generated.
-	 */
-	se_nacl = se_sess->se_node_acl;
-
-	mutex_lock(&se_tpg->acl_node_mutex);
-	if (se_nacl && se_nacl->dynamic_node_acl) {
-		if (!se_tfo->tpg_check_demo_mode_cache(se_tpg)) {
-			list_del(&se_nacl->acl_list);
-			drop_nacl = true;
-		}
-	}
-	mutex_unlock(&se_tpg->acl_node_mutex);
-
-	if (drop_nacl) {
-		core_tpg_wait_for_nacl_pr_ref(se_nacl);
-		core_free_device_list_for_node(se_nacl, se_tpg);
-		se_sess->se_node_acl = NULL;
-		kfree(se_nacl);
-	}
 	pr_debug("TARGET_CORE[%s]: Deregistered fabric_sess\n",
 		se_tpg->se_tpg_tfo->get_fabric_name());
 	/*
 	 * If last kref is dropping now for an explicit NodeACL, awake sleeping
 	 * ->acl_free_comp caller to wakeup configfs se_node_acl->acl_group
 	 * removal context from within transport_free_session() code.
+	 *
+	 * For dynamic ACL, target_put_nacl() uses target_complete_nacl()
+	 * to release all remaining generate_node_acl=1 created ACL resources.
 	 */
 
 	transport_free_session(se_sess);
@@ -3086,7 +3103,6 @@ static void target_tmr_work(struct work_struct *work)
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 		goto check_stop;
 	}
-	cmd->t_state = TRANSPORT_ISTATE_PROCESSING;
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
 	cmd->se_tfo->queue_tm_rsp(cmd);
@@ -3099,11 +3115,25 @@ int transport_generic_handle_tmr(
 	struct se_cmd *cmd)
 {
 	unsigned long flags;
+	bool aborted = false;
 
 	spin_lock_irqsave(&cmd->t_state_lock, flags);
-	cmd->transport_state |= CMD_T_ACTIVE;
+	if (cmd->transport_state & CMD_T_ABORTED) {
+		aborted = true;
+	} else {
+		cmd->t_state = TRANSPORT_ISTATE_PROCESSING;
+		cmd->transport_state |= CMD_T_ACTIVE;
+	}
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
+	if (aborted) {
+		pr_warn_ratelimited("handle_tmr caught CMD_T_ABORTED TMR %d"
+			"ref_tag: %llu tag: %llu\n", cmd->se_tmr_req->function,
+			cmd->se_tmr_req->ref_task_tag, cmd->tag);
+		transport_cmd_check_stop_to_fabric(cmd);
+		return 0;
+	}
+
 	INIT_WORK(&cmd->work, target_tmr_work);
 	queue_work(cmd->se_dev->tmr_wq, &cmd->work);
 	return 0;
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index 094a1440eacb..18848ba8d2ba 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -836,7 +836,7 @@ static void target_xcopy_do_work(struct work_struct *work)
 			" CHECK_CONDITION -> sending response\n", rc);
 		ec_cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
 	}
-	target_complete_cmd(ec_cmd, SAM_STAT_CHECK_CONDITION);
+	target_complete_cmd(ec_cmd, ec_cmd->scsi_status);
 }
 
 sense_reason_t target_do_xcopy(struct se_cmd *se_cmd)
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 7acbd2cf6192..1782804f6c26 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -5648,6 +5648,10 @@ long btrfs_ioctl(struct file *file, unsigned int
 #ifdef CONFIG_COMPAT
 long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
+	/*
+	 * These all access 32-bit values anyway so no further
+	 * handling is necessary.
+	 */
 	switch (cmd) {
 	case FS_IOC32_GETFLAGS:
 		cmd = FS_IOC_GETFLAGS;
@@ -5658,8 +5662,6 @@ long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case FS_IOC32_GETVERSION:
 		cmd = FS_IOC_GETVERSION;
 		break;
-	default:
-		return -ENOIOCTLCMD;
 	}
 
 	return btrfs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index da7fbf1cdd56..fa3b155ce7e1 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -560,7 +560,7 @@ static inline void cpumask_copy(struct cpumask *dstp,
 static inline int cpumask_parse_user(const char __user *buf, int len,
 				     struct cpumask *dstp)
 {
-	return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpu_ids);
+	return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits);
 }
 
 /**
@@ -575,7 +575,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len,
 				     struct cpumask *dstp)
 {
 	return bitmap_parselist_user(buf, len, cpumask_bits(dstp),
-				     nr_cpu_ids);
+				     nr_cpumask_bits);
 }
 
 /**
@@ -590,7 +590,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
 	char *nl = strchr(buf, '\n');
 	unsigned int len = nl ? (unsigned int)(nl - buf) : strlen(buf);
 
-	return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpu_ids);
+	return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpumask_bits);
 }
 
 /**
@@ -602,7 +602,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
  */
 static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
 {
-	return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpu_ids);
+	return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits);
 }
 
 /**
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index cd184bdca58f..c92a083bcf16 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -128,6 +128,7 @@ struct hv_ring_buffer_info {
 	u32 ring_data_startoffset;
 	u32 priv_write_index;
 	u32 priv_read_index;
+	u32 cached_read_index;
 };
 
 /*
@@ -180,6 +181,19 @@ static inline u32 hv_get_bytes_to_write(struct hv_ring_buffer_info *rbi)
 	return write;
 }
 
+static inline u32 hv_get_cached_bytes_to_write(
+	const struct hv_ring_buffer_info *rbi)
+{
+	u32 read_loc, write_loc, dsize, write;
+
+	dsize = rbi->ring_datasize;
+	read_loc = rbi->cached_read_index;
+	write_loc = rbi->ring_buffer->write_index;
+
+	write = write_loc >= read_loc ? dsize - (write_loc - read_loc) :
+		read_loc - write_loc;
+	return write;
+}
 /*
  * VMBUS version is 32 bit entity broken up into
  * two 16 bit quantities: major_number. minor_number.
@@ -1447,6 +1461,7 @@ void hv_event_tasklet_enable(struct vmbus_channel *channel);
 
 void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid);
 
+void vmbus_setevent(struct vmbus_channel *channel);
 /*
  * Negotiated version with the Host.
  */
@@ -1479,10 +1494,11 @@ hv_get_ring_buffer(struct hv_ring_buffer_info *ring_info)
  *    there is room for the producer to send the pending packet.
  */
 
-static inline  bool hv_need_to_signal_on_read(struct hv_ring_buffer_info *rbi)
+static inline  void hv_signal_on_read(struct vmbus_channel *channel)
 {
-	u32 cur_write_sz;
+	u32 cur_write_sz, cached_write_sz;
 	u32 pending_sz;
+	struct hv_ring_buffer_info *rbi = &channel->inbound;
 
 	/*
 	 * Issue a full memory barrier before making the signaling decision.
@@ -1500,14 +1516,26 @@ static inline  bool hv_need_to_signal_on_read(struct hv_ring_buffer_info *rbi)
 	pending_sz = READ_ONCE(rbi->ring_buffer->pending_send_sz);
 	/* If the other end is not blocked on write don't bother. */
 	if (pending_sz == 0)
-		return false;
+		return;
 
 	cur_write_sz = hv_get_bytes_to_write(rbi);
 
-	if (cur_write_sz >= pending_sz)
-		return true;
+	if (cur_write_sz < pending_sz)
+		return;
+
+	cached_write_sz = hv_get_cached_bytes_to_write(rbi);
+	if (cached_write_sz < pending_sz)
+		vmbus_setevent(channel);
+
+	return;
+}
+
+static inline void
+init_cached_read_index(struct vmbus_channel *channel)
+{
+	struct hv_ring_buffer_info *rbi = &channel->inbound;
 
-	return false;
+	rbi->cached_read_index = rbi->ring_buffer->read_index;
 }
 
 /*
@@ -1571,6 +1599,8 @@ static inline void put_pkt_raw(struct vmbus_channel *channel,
  * This call commits the read index and potentially signals the host.
  * Here is the pattern for using the "in-place" consumption APIs:
  *
+ * init_cached_read_index();
+ *
  * while (get_next_pkt_raw() {
  *	process the packet "in-place";
  *	put_pkt_raw();
@@ -1589,8 +1619,7 @@ static inline void commit_rd_index(struct vmbus_channel *channel)
 	virt_rmb();
 	ring_info->ring_buffer->read_index = ring_info->priv_read_index;
 
-	if (hv_need_to_signal_on_read(ring_info))
-		vmbus_set_event(channel);
+	hv_signal_on_read(channel);
 }
 
 
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index c2119008990a..48bc1ac1da43 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -538,6 +538,7 @@ struct se_node_acl {
 	char			initiatorname[TRANSPORT_IQN_LEN];
 	/* Used to signal demo mode created ACL, disabled by default */
 	bool			dynamic_node_acl;
+	bool			dynamic_stop;
 	u32			queue_depth;
 	u32			acl_index;
 	enum target_prot_type	saved_prot_type;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index b1cfd7416db0..4b3323151a2f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3461,14 +3461,15 @@ struct perf_read_data {
 	int ret;
 };
 
-static int find_cpu_to_read(struct perf_event *event, int local_cpu)
+static int __perf_event_read_cpu(struct perf_event *event, int event_cpu)
 {
-	int event_cpu = event->oncpu;
 	u16 local_pkg, event_pkg;
 
 	if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) {
-		event_pkg =  topology_physical_package_id(event_cpu);
-		local_pkg =  topology_physical_package_id(local_cpu);
+		int local_cpu = smp_processor_id();
+
+		event_pkg = topology_physical_package_id(event_cpu);
+		local_pkg = topology_physical_package_id(local_cpu);
 
 		if (event_pkg == local_pkg)
 			return local_cpu;
@@ -3598,7 +3599,7 @@ u64 perf_event_read_local(struct perf_event *event)
 
 static int perf_event_read(struct perf_event *event, bool group)
 {
-	int ret = 0, cpu_to_read, local_cpu;
+	int event_cpu, ret = 0;
 
 	/*
 	 * If event is enabled and currently active on a CPU, update the
@@ -3611,21 +3612,25 @@ static int perf_event_read(struct perf_event *event, bool group)
 			.ret = 0,
 		};
 
-		local_cpu = get_cpu();
-		cpu_to_read = find_cpu_to_read(event, local_cpu);
-		put_cpu();
+		event_cpu = READ_ONCE(event->oncpu);
+		if ((unsigned)event_cpu >= nr_cpu_ids)
+			return 0;
+
+		preempt_disable();
+		event_cpu = __perf_event_read_cpu(event, event_cpu);
 
 		/*
 		 * Purposely ignore the smp_call_function_single() return
 		 * value.
 		 *
-		 * If event->oncpu isn't a valid CPU it means the event got
+		 * If event_cpu isn't a valid CPU it means the event got
 		 * scheduled out and that will have updated the event count.
 		 *
 		 * Therefore, either way, we'll have an up-to-date event count
 		 * after this.
 		 */
-		(void)smp_call_function_single(cpu_to_read, __perf_event_read, &data, 1);
+		(void)smp_call_function_single(event_cpu, __perf_event_read, &data, 1);
+		preempt_enable();
 		ret = data.ret;
 	} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
 		struct perf_event_context *ctx = event->ctx;
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index b6e4c16377c7..9c15a9124e83 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -18,10 +18,8 @@ void print_stack_trace(struct stack_trace *trace, int spaces)
 	if (WARN_ON(!trace->entries))
 		return;
 
-	for (i = 0; i < trace->nr_entries; i++) {
-		printk("%*c", 1 + spaces, ' ');
-		print_ip_sym(trace->entries[i]);
-	}
+	for (i = 0; i < trace->nr_entries; i++)
+		printk("%*c%pS\n", 1 + spaces, ' ', (void *)trace->entries[i]);
 }
 EXPORT_SYMBOL_GPL(print_stack_trace);
 
@@ -29,7 +27,6 @@ int snprint_stack_trace(char *buf, size_t size,
 			struct stack_trace *trace, int spaces)
 {
 	int i;
-	unsigned long ip;
 	int generated;
 	int total = 0;
 
@@ -37,9 +34,8 @@ int snprint_stack_trace(char *buf, size_t size,
 		return 0;
 
 	for (i = 0; i < trace->nr_entries; i++) {
-		ip = trace->entries[i];
-		generated = snprintf(buf, size, "%*c[<%p>] %pS\n",
-				1 + spaces, ' ', (void *) ip, (void *) ip);
+		generated = snprintf(buf, size, "%*c%pS\n", 1 + spaces, ' ',
+				     (void *)trace->entries[i]);
 
 		total += generated;
 
diff --git a/mm/slub.c b/mm/slub.c
index 2b3e740609e9..7aa0e97af928 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1419,6 +1419,10 @@ static int init_cache_random_seq(struct kmem_cache *s)
 	int err;
 	unsigned long i, count = oo_objects(s->oo);
 
+	/* Bailout if already initialised */
+	if (s->random_seq)
+		return 0;
+
 	err = cache_random_seq_create(s, count, GFP_KERNEL);
 	if (err) {
 		pr_err("SLUB: Unable to initialize free list for %s\n",
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 42120d965263..50e1b7f78bd4 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -339,7 +339,7 @@ int mesh_add_vendor_ies(struct ieee80211_sub_if_data *sdata,
 	/* fast-forward to vendor IEs */
 	offset = ieee80211_ie_split_vendor(ifmsh->ie, ifmsh->ie_len, 0);
 
-	if (offset) {
+	if (offset < ifmsh->ie_len) {
 		len = ifmsh->ie_len - offset;
 		data = ifmsh->ie + offset;
 		if (skb_tailroom(skb) < len)
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 1b3c18c2c1ec..cd7a419faa21 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -5874,6 +5874,7 @@ do {									    \
 			break;
 		}
 		cfg->ht_opmode = ht_opmode;
+		mask |= (1 << (NL80211_MESHCONF_HT_OPMODE - 1));
 	}
 	FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPactivePathToRootTimeout,
 				  1, 65535, mask,
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 09fd6108e421..c2da45ae5b2a 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -5858,7 +5858,7 @@ static int selinux_setprocattr(struct task_struct *p,
 		return error;
 
 	/* Obtain a SID for the context, if one was specified. */
-	if (size && str[1] && str[1] != '\n') {
+	if (size && str[0] && str[0] != '\n') {
 		if (str[size-1] == '\n') {
 			str[size-1] = 0;
 			size--;
diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c
index c850345c43b5..dfa5156f3585 100644
--- a/sound/core/seq/seq_memory.c
+++ b/sound/core/seq/seq_memory.c
@@ -419,7 +419,6 @@ int snd_seq_pool_done(struct snd_seq_pool *pool)
 {
 	unsigned long flags;
 	struct snd_seq_event_cell *ptr;
-	int max_count = 5 * HZ;
 
 	if (snd_BUG_ON(!pool))
 		return -EINVAL;
@@ -432,14 +431,8 @@ int snd_seq_pool_done(struct snd_seq_pool *pool)
 	if (waitqueue_active(&pool->output_sleep))
 		wake_up(&pool->output_sleep);
 
-	while (atomic_read(&pool->counter) > 0) {
-		if (max_count == 0) {
-			pr_warn("ALSA: snd_seq_pool_done timeout: %d cells remain\n", atomic_read(&pool->counter));
-			break;
-		}
+	while (atomic_read(&pool->counter) > 0)
 		schedule_timeout_uninterruptible(1);
-		max_count--;
-	}
 	
 	/* release all resources */
 	spin_lock_irqsave(&pool->lock, flags);
diff --git a/sound/core/seq/seq_queue.c b/sound/core/seq/seq_queue.c
index 0bec02e89d51..450c5187eecb 100644
--- a/sound/core/seq/seq_queue.c
+++ b/sound/core/seq/seq_queue.c
@@ -181,6 +181,8 @@ void __exit snd_seq_queues_delete(void)
 	}
 }
 
+static void queue_use(struct snd_seq_queue *queue, int client, int use);
+
 /* allocate a new queue -
  * return queue index value or negative value for error
  */
@@ -192,11 +194,11 @@ int snd_seq_queue_alloc(int client, int locked, unsigned int info_flags)
 	if (q == NULL)
 		return -ENOMEM;
 	q->info_flags = info_flags;
+	queue_use(q, client, 1);
 	if (queue_list_add(q) < 0) {
 		queue_delete(q);
 		return -ENOMEM;
 	}
-	snd_seq_queue_use(q->queue, client, 1); /* use this queue */
 	return q->queue;
 }
 
@@ -502,19 +504,9 @@ int snd_seq_queue_timer_set_tempo(int queueid, int client,
 	return result;
 }
 
-
-/* use or unuse this queue -
- * if it is the first client, starts the timer.
- * if it is not longer used by any clients, stop the timer.
- */
-int snd_seq_queue_use(int queueid, int client, int use)
+/* use or unuse this queue */
+static void queue_use(struct snd_seq_queue *queue, int client, int use)
 {
-	struct snd_seq_queue *queue;
-
-	queue = queueptr(queueid);
-	if (queue == NULL)
-		return -EINVAL;
-	mutex_lock(&queue->timer_mutex);
 	if (use) {
 		if (!test_and_set_bit(client, queue->clients_bitmap))
 			queue->clients++;
@@ -529,6 +521,21 @@ int snd_seq_queue_use(int queueid, int client, int use)
 	} else {
 		snd_seq_timer_close(queue);
 	}
+}
+
+/* use or unuse this queue -
+ * if it is the first client, starts the timer.
+ * if it is not longer used by any clients, stop the timer.
+ */
+int snd_seq_queue_use(int queueid, int client, int use)
+{
+	struct snd_seq_queue *queue;
+
+	queue = queueptr(queueid);
+	if (queue == NULL)
+		return -EINVAL;
+	mutex_lock(&queue->timer_mutex);
+	queue_use(queue, client, use);
 	mutex_unlock(&queue->timer_mutex);
 	queuefree(queue);
 	return 0;
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 56e5204ac9c1..4bf48336b0fc 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -3638,6 +3638,7 @@ HDA_CODEC_ENTRY(0x10de0070, "GPU 70 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de0071, "GPU 71 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de0072, "GPU 72 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de007d, "GPU 7d HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de0080, "GPU 80 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de0082, "GPU 82 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de0083, "GPU 83 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI",	patch_nvhdmi_2ch),
diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c
index 90009c0b3a92..ab3c280a23d1 100644
--- a/sound/usb/line6/driver.c
+++ b/sound/usb/line6/driver.c
@@ -754,8 +754,9 @@ int line6_probe(struct usb_interface *interface,
 		goto error;
 	}
 
+	line6_get_interval(line6);
+
 	if (properties->capabilities & LINE6_CAP_CONTROL) {
-		line6_get_interval(line6);
 		ret = line6_init_cap_control(line6);
 		if (ret < 0)
 			goto error;
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 9ff0db4e2d0c..933aeec46f4a 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -1199,7 +1199,7 @@ static int ui_init(void)
 		BUG_ON(1);
 	}
 
-	perf_hpp__register_sort_field(fmt);
+	perf_hpp__prepend_sort_field(fmt);
 	return 0;
 }
 
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 37388397b5bc..18cfcdc90356 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -521,6 +521,12 @@ void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
 	list_add_tail(&format->sort_list, &list->sorts);
 }
 
+void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
+				       struct perf_hpp_fmt *format)
+{
+	list_add(&format->sort_list, &list->sorts);
+}
+
 void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 {
 	list_del(&format->list);
@@ -560,6 +566,10 @@ void perf_hpp__setup_output_field(struct perf_hpp_list *list)
 	perf_hpp_list__for_each_sort_list(list, fmt) {
 		struct perf_hpp_fmt *pos;
 
+		/* skip sort-only fields ("sort_compute" in perf diff) */
+		if (!fmt->entry && !fmt->color)
+			continue;
+
 		perf_hpp_list__for_each_format(list, pos) {
 			if (fmt_equal(fmt, pos))
 				goto next;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 9928fed8bc59..a440a04a29ff 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -282,6 +282,8 @@ void perf_hpp_list__column_register(struct perf_hpp_list *list,
 				    struct perf_hpp_fmt *format);
 void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
 					struct perf_hpp_fmt *format);
+void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
+				       struct perf_hpp_fmt *format);
 
 static inline void perf_hpp__column_register(struct perf_hpp_fmt *format)
 {
@@ -293,6 +295,11 @@ static inline void perf_hpp__register_sort_field(struct perf_hpp_fmt *format)
 	perf_hpp_list__register_sort_field(&perf_hpp_list, format);
 }
 
+static inline void perf_hpp__prepend_sort_field(struct perf_hpp_fmt *format)
+{
+	perf_hpp_list__prepend_sort_field(&perf_hpp_list, format);
+}
+
 #define perf_hpp_list__for_each_format(_list, format) \
 	list_for_each_entry(format, &(_list)->fields, list)