diff --git a/Makefile b/Makefile
index 382e967b0792..c8d80b50495a 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 12
-SUBLEVEL = 5
+SUBLEVEL = 6
 EXTRAVERSION =
 NAME = Fearless Coyote
 
diff --git a/arch/arm/boot/dts/armada-388-gp.dts b/arch/arm/boot/dts/armada-388-gp.dts
index 895fa6cfa15a..563901e0ec07 100644
--- a/arch/arm/boot/dts/armada-388-gp.dts
+++ b/arch/arm/boot/dts/armada-388-gp.dts
@@ -75,7 +75,7 @@
 					pinctrl-names = "default";
 					pinctrl-0 = <&pca0_pins>;
 					interrupt-parent = <&gpio0>;
-					interrupts = <18 IRQ_TYPE_EDGE_FALLING>;
+					interrupts = <18 IRQ_TYPE_LEVEL_LOW>;
 					gpio-controller;
 					#gpio-cells = <2>;
 					interrupt-controller;
@@ -87,7 +87,7 @@
 					compatible = "nxp,pca9555";
 					pinctrl-names = "default";
 					interrupt-parent = <&gpio0>;
-					interrupts = <18 IRQ_TYPE_EDGE_FALLING>;
+					interrupts = <18 IRQ_TYPE_LEVEL_LOW>;
 					gpio-controller;
 					#gpio-cells = <2>;
 					interrupt-controller;
diff --git a/arch/arm/boot/dts/tango4-vantage-1172.dts b/arch/arm/boot/dts/tango4-vantage-1172.dts
index 86d8df98802f..13bcc460bcb2 100644
--- a/arch/arm/boot/dts/tango4-vantage-1172.dts
+++ b/arch/arm/boot/dts/tango4-vantage-1172.dts
@@ -22,7 +22,7 @@
 };
 
 &eth0 {
-	phy-connection-type = "rgmii";
+	phy-connection-type = "rgmii-id";
 	phy-handle = <&eth0_phy>;
 	#address-cells = <1>;
 	#size-cells = <0>;
diff --git a/arch/arm/mach-mvebu/platsmp.c b/arch/arm/mach-mvebu/platsmp.c
index e62273aacb43..4ffbbd217e82 100644
--- a/arch/arm/mach-mvebu/platsmp.c
+++ b/arch/arm/mach-mvebu/platsmp.c
@@ -211,7 +211,7 @@ static int mv98dx3236_resume_set_cpu_boot_addr(int hw_cpu, void *boot_addr)
 		return PTR_ERR(base);
 
 	writel(0, base + MV98DX3236_CPU_RESUME_CTRL_REG);
-	writel(virt_to_phys(boot_addr), base + MV98DX3236_CPU_RESUME_ADDR_REG);
+	writel(__pa_symbol(boot_addr), base + MV98DX3236_CPU_RESUME_ADDR_REG);
 
 	iounmap(base);
 
diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
index bc179efb10ef..b69e4a4ecdd8 100644
--- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
@@ -219,7 +219,7 @@
 				reg = <0x18800 0x100>, <0x18C00 0x20>;
 				gpiosb: gpio {
 					#gpio-cells = <2>;
-					gpio-ranges = <&pinctrl_sb 0 0 29>;
+					gpio-ranges = <&pinctrl_sb 0 0 30>;
 					gpio-controller;
 					interrupts =
 					<GIC_SPI 160 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/mips/include/asm/mach-ralink/ralink_regs.h b/arch/mips/include/asm/mach-ralink/ralink_regs.h
index 9df1a53bcb36..b4e7dfa214eb 100644
--- a/arch/mips/include/asm/mach-ralink/ralink_regs.h
+++ b/arch/mips/include/asm/mach-ralink/ralink_regs.h
@@ -13,6 +13,8 @@
 #ifndef _RALINK_REGS_H_
 #define _RALINK_REGS_H_
 
+#include <linux/io.h>
+
 enum ralink_soc_type {
 	RALINK_UNKNOWN = 0,
 	RT2880_SOC,
diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h
index 88fe0aad4390..bc208136bbb2 100644
--- a/arch/parisc/include/asm/thread_info.h
+++ b/arch/parisc/include/asm/thread_info.h
@@ -34,7 +34,7 @@ struct thread_info {
 
 /* thread information allocation */
 
-#define THREAD_SIZE_ORDER	2 /* PA-RISC requires at least 16k stack */
+#define THREAD_SIZE_ORDER	3 /* PA-RISC requires at least 32k stack */
 /* Be sure to hunt all references to this down when you change the size of
  * the kernel stack */
 #define THREAD_SIZE             (PAGE_SIZE << THREAD_SIZE_ORDER)
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 85a92db70afc..19c0c141bc3f 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -587,13 +587,12 @@ void flush_cache_range(struct vm_area_struct *vma,
 	if (parisc_requires_coherency())
 		flush_tlb_range(vma, start, end);
 
-	if ((end - start) >= parisc_cache_flush_threshold) {
+	if ((end - start) >= parisc_cache_flush_threshold
+	    || vma->vm_mm->context != mfsp(3)) {
 		flush_cache_all();
 		return;
 	}
 
-	BUG_ON(vma->vm_mm->context != mfsp(3));
-
 	flush_user_dcache_range_asm(start, end);
 	if (vma->vm_flags & VM_EXEC)
 		flush_user_icache_range_asm(start, end);
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index ba5e1c7b1f17..ef9a4eea662f 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -380,7 +380,7 @@ static inline int eirr_to_irq(unsigned long eirr)
 /*
  * IRQ STACK - used for irq handler
  */
-#define IRQ_STACK_SIZE      (4096 << 2) /* 16k irq stack size */
+#define IRQ_STACK_SIZE      (4096 << 3) /* 32k irq stack size */
 
 union irq_stack_union {
 	unsigned long stack[IRQ_STACK_SIZE/sizeof(unsigned long)];
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 5c291df30fe3..40d8b552d15a 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -145,6 +145,19 @@ notrace unsigned int __check_irq_replay(void)
 
 	/* Clear bit 0 which we wouldn't clear otherwise */
 	local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
+	if (happened & PACA_IRQ_HARD_DIS) {
+		/*
+		 * We may have missed a decrementer interrupt if hard disabled.
+		 * Check the decrementer register in case we had a rollover
+		 * while hard disabled.
+		 */
+		if (!(happened & PACA_IRQ_DEC)) {
+			if (decrementer_check_overflow()) {
+				local_paca->irq_happened |= PACA_IRQ_DEC;
+				happened |= PACA_IRQ_DEC;
+			}
+		}
+	}
 
 	/*
 	 * Force the delivery of pending soft-disabled interrupts on PS3.
@@ -170,7 +183,7 @@ notrace unsigned int __check_irq_replay(void)
 	 * in case we also had a rollover while hard disabled
 	 */
 	local_paca->irq_happened &= ~PACA_IRQ_DEC;
-	if ((happened & PACA_IRQ_DEC) || decrementer_check_overflow())
+	if (happened & PACA_IRQ_DEC)
 		return 0x900;
 
 	/* Finally check if an external interrupt happened */
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 925a4ef90559..660ed39e9c9a 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -127,12 +127,19 @@ static void flush_tmregs_to_thread(struct task_struct *tsk)
 	 * If task is not current, it will have been flushed already to
 	 * it's thread_struct during __switch_to().
 	 *
-	 * A reclaim flushes ALL the state.
+	 * A reclaim flushes ALL the state or if not in TM save TM SPRs
+	 * in the appropriate thread structures from live.
 	 */
 
-	if (tsk == current && MSR_TM_SUSPENDED(mfmsr()))
-		tm_reclaim_current(TM_CAUSE_SIGNAL);
+	if (tsk != current)
+		return;
 
+	if (MSR_TM_SUSPENDED(mfmsr())) {
+		tm_reclaim_current(TM_CAUSE_SIGNAL);
+	} else {
+		tm_enable();
+		tm_save_sprs(&(tsk->thread));
+	}
 }
 #else
 static inline void flush_tmregs_to_thread(struct task_struct *tsk) { }
diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h
index 2cddcda4f85f..87841d687f8d 100644
--- a/arch/sparc/include/asm/mmu_context_64.h
+++ b/arch/sparc/include/asm/mmu_context_64.h
@@ -27,9 +27,11 @@ void destroy_context(struct mm_struct *mm);
 void __tsb_context_switch(unsigned long pgd_pa,
 			  struct tsb_config *tsb_base,
 			  struct tsb_config *tsb_huge,
-			  unsigned long tsb_descr_pa);
+			  unsigned long tsb_descr_pa,
+			  unsigned long secondary_ctx);
 
-static inline void tsb_context_switch(struct mm_struct *mm)
+static inline void tsb_context_switch_ctx(struct mm_struct *mm,
+					  unsigned long ctx)
 {
 	__tsb_context_switch(__pa(mm->pgd),
 			     &mm->context.tsb_block[MM_TSB_BASE],
@@ -40,9 +42,12 @@ static inline void tsb_context_switch(struct mm_struct *mm)
 #else
 			     NULL
 #endif
-			     , __pa(&mm->context.tsb_descr[MM_TSB_BASE]));
+			     , __pa(&mm->context.tsb_descr[MM_TSB_BASE]),
+			     ctx);
 }
 
+#define tsb_context_switch(X) tsb_context_switch_ctx(X, 0)
+
 void tsb_grow(struct mm_struct *mm,
 	      unsigned long tsb_index,
 	      unsigned long mm_rss);
@@ -112,8 +117,7 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str
 	 * cpu0 to update it's TSB because at that point the cpu_vm_mask
 	 * only had cpu1 set in it.
 	 */
-	load_secondary_context(mm);
-	tsb_context_switch(mm);
+	tsb_context_switch_ctx(mm, CTX_HWBITS(mm->context));
 
 	/* Any time a processor runs a context on an address space
 	 * for the first time, we must flush that context out of the
diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h
index ec9c04de3664..ff05992dae7a 100644
--- a/arch/sparc/include/asm/trap_block.h
+++ b/arch/sparc/include/asm/trap_block.h
@@ -54,6 +54,7 @@ extern struct trap_per_cpu trap_block[NR_CPUS];
 void init_cur_cpu_trap(struct thread_info *);
 void setup_tba(void);
 extern int ncpus_probed;
+extern u64 cpu_mondo_counter[NR_CPUS];
 
 unsigned long real_hard_smp_processor_id(void);
 
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index fdf31040a7dc..3218bc43302e 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -622,22 +622,48 @@ static void cheetah_xcall_deliver(struct trap_per_cpu *tb, int cnt)
 	}
 }
 
-/* Multi-cpu list version.  */
+#define	CPU_MONDO_COUNTER(cpuid)	(cpu_mondo_counter[cpuid])
+#define	MONDO_USEC_WAIT_MIN		2
+#define	MONDO_USEC_WAIT_MAX		100
+#define	MONDO_RETRY_LIMIT		500000
+
+/* Multi-cpu list version.
+ *
+ * Deliver xcalls to 'cnt' number of cpus in 'cpu_list'.
+ * Sometimes not all cpus receive the mondo, requiring us to re-send
+ * the mondo until all cpus have received, or cpus are truly stuck
+ * unable to receive mondo, and we timeout.
+ * Occasionally a target cpu strand is borrowed briefly by hypervisor to
+ * perform guest service, such as PCIe error handling. Consider the
+ * service time, 1 second overall wait is reasonable for 1 cpu.
+ * Here two in-between mondo check wait time are defined: 2 usec for
+ * single cpu quick turn around and up to 100usec for large cpu count.
+ * Deliver mondo to large number of cpus could take longer, we adjusts
+ * the retry count as long as target cpus are making forward progress.
+ */
 static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt)
 {
-	int retries, this_cpu, prev_sent, i, saw_cpu_error;
+	int this_cpu, tot_cpus, prev_sent, i, rem;
+	int usec_wait, retries, tot_retries;
+	u16 first_cpu = 0xffff;
+	unsigned long xc_rcvd = 0;
 	unsigned long status;
+	int ecpuerror_id = 0;
+	int enocpu_id = 0;
 	u16 *cpu_list;
+	u16 cpu;
 
 	this_cpu = smp_processor_id();
-
 	cpu_list = __va(tb->cpu_list_pa);
-
-	saw_cpu_error = 0;
-	retries = 0;
+	usec_wait = cnt * MONDO_USEC_WAIT_MIN;
+	if (usec_wait > MONDO_USEC_WAIT_MAX)
+		usec_wait = MONDO_USEC_WAIT_MAX;
+	retries = tot_retries = 0;
+	tot_cpus = cnt;
 	prev_sent = 0;
+
 	do {
-		int forward_progress, n_sent;
+		int n_sent, mondo_delivered, target_cpu_busy;
 
 		status = sun4v_cpu_mondo_send(cnt,
 					      tb->cpu_list_pa,
@@ -645,94 +671,113 @@ static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt)
 
 		/* HV_EOK means all cpus received the xcall, we're done.  */
 		if (likely(status == HV_EOK))
-			break;
+			goto xcall_done;
+
+		/* If not these non-fatal errors, panic */
+		if (unlikely((status != HV_EWOULDBLOCK) &&
+			(status != HV_ECPUERROR) &&
+			(status != HV_ENOCPU)))
+			goto fatal_errors;
 
 		/* First, see if we made any forward progress.
+		 *
+		 * Go through the cpu_list, count the target cpus that have
+		 * received our mondo (n_sent), and those that did not (rem).
+		 * Re-pack cpu_list with the cpus remain to be retried in the
+		 * front - this simplifies tracking the truly stalled cpus.
 		 *
 		 * The hypervisor indicates successful sends by setting
 		 * cpu list entries to the value 0xffff.
+		 *
+		 * EWOULDBLOCK means some target cpus did not receive the
+		 * mondo and retry usually helps.
+		 *
+		 * ECPUERROR means at least one target cpu is in error state,
+		 * it's usually safe to skip the faulty cpu and retry.
+		 *
+		 * ENOCPU means one of the target cpu doesn't belong to the
+		 * domain, perhaps offlined which is unexpected, but not
+		 * fatal and it's okay to skip the offlined cpu.
 		 */
+		rem = 0;
 		n_sent = 0;
 		for (i = 0; i < cnt; i++) {
-			if (likely(cpu_list[i] == 0xffff))
+			cpu = cpu_list[i];
+			if (likely(cpu == 0xffff)) {
 				n_sent++;
+			} else if ((status == HV_ECPUERROR) &&
+				(sun4v_cpu_state(cpu) == HV_CPU_STATE_ERROR)) {
+				ecpuerror_id = cpu + 1;
+			} else if (status == HV_ENOCPU && !cpu_online(cpu)) {
+				enocpu_id = cpu + 1;
+			} else {
+				cpu_list[rem++] = cpu;
+			}
 		}
 
-		forward_progress = 0;
-		if (n_sent > prev_sent)
-			forward_progress = 1;
+		/* No cpu remained, we're done. */
+		if (rem == 0)
+			break;
 
-		prev_sent = n_sent;
+		/* Otherwise, update the cpu count for retry. */
+		cnt = rem;
 
-		/* If we get a HV_ECPUERROR, then one or more of the cpus
-		 * in the list are in error state.  Use the cpu_state()
-		 * hypervisor call to find out which cpus are in error state.
+		/* Record the overall number of mondos received by the
+		 * first of the remaining cpus.
 		 */
-		if (unlikely(status == HV_ECPUERROR)) {
-			for (i = 0; i < cnt; i++) {
-				long err;
-				u16 cpu;
+		if (first_cpu != cpu_list[0]) {
+			first_cpu = cpu_list[0];
+			xc_rcvd = CPU_MONDO_COUNTER(first_cpu);
+		}
 
-				cpu = cpu_list[i];
-				if (cpu == 0xffff)
-					continue;
+		/* Was any mondo delivered successfully? */
+		mondo_delivered = (n_sent > prev_sent);
+		prev_sent = n_sent;
 
-				err = sun4v_cpu_state(cpu);
-				if (err == HV_CPU_STATE_ERROR) {
-					saw_cpu_error = (cpu + 1);
-					cpu_list[i] = 0xffff;
-				}
-			}
-		} else if (unlikely(status != HV_EWOULDBLOCK))
-			goto fatal_mondo_error;
+		/* or, was any target cpu busy processing other mondos? */
+		target_cpu_busy = (xc_rcvd < CPU_MONDO_COUNTER(first_cpu));
+		xc_rcvd = CPU_MONDO_COUNTER(first_cpu);
 
-		/* Don't bother rewriting the CPU list, just leave the
-		 * 0xffff and non-0xffff entries in there and the
-		 * hypervisor will do the right thing.
-		 *
-		 * Only advance timeout state if we didn't make any
-		 * forward progress.
+		/* Retry count is for no progress. If we're making progress,
+		 * reset the retry count.
 		 */
-		if (unlikely(!forward_progress)) {
-			if (unlikely(++retries > 10000))
-				goto fatal_mondo_timeout;
-
-			/* Delay a little bit to let other cpus catch up
-			 * on their cpu mondo queue work.
-			 */
-			udelay(2 * cnt);
+		if (likely(mondo_delivered || target_cpu_busy)) {
+			tot_retries += retries;
+			retries = 0;
+		} else if (unlikely(retries > MONDO_RETRY_LIMIT)) {
+			goto fatal_mondo_timeout;
 		}
-	} while (1);
 
-	if (unlikely(saw_cpu_error))
-		goto fatal_mondo_cpu_error;
+		/* Delay a little bit to let other cpus catch up on
+		 * their cpu mondo queue work.
+		 */
+		if (!mondo_delivered)
+			udelay(usec_wait);
 
-	return;
+		retries++;
+	} while (1);
 
-fatal_mondo_cpu_error:
-	printk(KERN_CRIT "CPU[%d]: SUN4V mondo cpu error, some target cpus "
-	       "(including %d) were in error state\n",
-	       this_cpu, saw_cpu_error - 1);
+xcall_done:
+	if (unlikely(ecpuerror_id > 0)) {
+		pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) was in error state\n",
+		       this_cpu, ecpuerror_id - 1);
+	} else if (unlikely(enocpu_id > 0)) {
+		pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) does not belong to the domain\n",
+		       this_cpu, enocpu_id - 1);
+	}
 	return;
 
+fatal_errors:
+	/* fatal errors include bad alignment, etc */
+	pr_crit("CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) mondo_block_pa(%lx)\n",
+	       this_cpu, tot_cpus, tb->cpu_list_pa, tb->cpu_mondo_block_pa);
+	panic("Unexpected SUN4V mondo error %lu\n", status);
+
 fatal_mondo_timeout:
-	printk(KERN_CRIT "CPU[%d]: SUN4V mondo timeout, no forward "
-	       " progress after %d retries.\n",
-	       this_cpu, retries);
-	goto dump_cpu_list_and_out;
-
-fatal_mondo_error:
-	printk(KERN_CRIT "CPU[%d]: Unexpected SUN4V mondo error %lu\n",
-	       this_cpu, status);
-	printk(KERN_CRIT "CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) "
-	       "mondo_block_pa(%lx)\n",
-	       this_cpu, cnt, tb->cpu_list_pa, tb->cpu_mondo_block_pa);
-
-dump_cpu_list_and_out:
-	printk(KERN_CRIT "CPU[%d]: CPU list [ ", this_cpu);
-	for (i = 0; i < cnt; i++)
-		printk("%u ", cpu_list[i]);
-	printk("]\n");
+	/* some cpus being non-responsive to the cpu mondo */
+	pr_crit("CPU[%d]: SUN4V mondo timeout, cpu(%d) made no forward progress after %d retries. Total target cpus(%d).\n",
+	       this_cpu, first_cpu, (tot_retries + retries), tot_cpus);
+	panic("SUN4V mondo timeout panic\n");
 }
 
 static void (*xcall_deliver_impl)(struct trap_per_cpu *, int);
diff --git a/arch/sparc/kernel/sun4v_ivec.S b/arch/sparc/kernel/sun4v_ivec.S
index 559bc5e9c199..34631995859a 100644
--- a/arch/sparc/kernel/sun4v_ivec.S
+++ b/arch/sparc/kernel/sun4v_ivec.S
@@ -26,6 +26,21 @@ sun4v_cpu_mondo:
 	ldxa	[%g0] ASI_SCRATCHPAD, %g4
 	sub	%g4, TRAP_PER_CPU_FAULT_INFO, %g4
 
+	/* Get smp_processor_id() into %g3 */
+	sethi	%hi(trap_block), %g5
+	or	%g5, %lo(trap_block), %g5
+	sub	%g4, %g5, %g3
+	srlx	%g3, TRAP_BLOCK_SZ_SHIFT, %g3
+
+	/* Increment cpu_mondo_counter[smp_processor_id()] */
+	sethi	%hi(cpu_mondo_counter), %g5
+	or	%g5, %lo(cpu_mondo_counter), %g5
+	sllx	%g3, 3, %g3
+	add	%g5, %g3, %g5
+	ldx	[%g5], %g3
+	add	%g3, 1, %g3
+	stx	%g3, [%g5]
+
 	/* Get CPU mondo queue base phys address into %g7.  */
 	ldx	[%g4 + TRAP_PER_CPU_CPU_MONDO_PA], %g7
 
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 196ee5eb4d48..ad31af1dd726 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2733,6 +2733,7 @@ void do_getpsr(struct pt_regs *regs)
 	}
 }
 
+u64 cpu_mondo_counter[NR_CPUS] = {0};
 struct trap_per_cpu trap_block[NR_CPUS];
 EXPORT_SYMBOL(trap_block);
 
diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S
index 07c0df924960..db872dbfafe9 100644
--- a/arch/sparc/kernel/tsb.S
+++ b/arch/sparc/kernel/tsb.S
@@ -360,6 +360,7 @@ tsb_flush:
 	 * %o1:	TSB base config pointer
 	 * %o2:	TSB huge config pointer, or NULL if none
 	 * %o3:	Hypervisor TSB descriptor physical address
+	 * %o4: Secondary context to load, if non-zero
 	 *
 	 * We have to run this whole thing with interrupts
 	 * disabled so that the current cpu doesn't change
@@ -372,6 +373,17 @@ __tsb_context_switch:
 	rdpr	%pstate, %g1
 	wrpr	%g1, PSTATE_IE, %pstate
 
+	brz,pn	%o4, 1f
+	 mov	SECONDARY_CONTEXT, %o5
+
+661:	stxa	%o4, [%o5] ASI_DMMU
+	.section .sun4v_1insn_patch, "ax"
+	.word	661b
+	stxa	%o4, [%o5] ASI_MMU
+	.previous
+	flush	%g6
+
+1:
 	TRAP_LOAD_TRAP_BLOCK(%g2, %g3)
 
 	stx	%o0, [%g2 + TRAP_PER_CPU_PGD_PADDR]
diff --git a/arch/sparc/lib/U3memcpy.S b/arch/sparc/lib/U3memcpy.S
index 54f98706b03b..5a8cb37f0a3b 100644
--- a/arch/sparc/lib/U3memcpy.S
+++ b/arch/sparc/lib/U3memcpy.S
@@ -145,13 +145,13 @@ ENDPROC(U3_retl_o2_plus_GS_plus_0x08)
 ENTRY(U3_retl_o2_and_7_plus_GS)
 	and	%o2, 7, %o2
 	retl
-	 add	%o2, GLOBAL_SPARE, %o2
+	 add	%o2, GLOBAL_SPARE, %o0
 ENDPROC(U3_retl_o2_and_7_plus_GS)
 ENTRY(U3_retl_o2_and_7_plus_GS_plus_8)
 	add	GLOBAL_SPARE, 8, GLOBAL_SPARE
 	and	%o2, 7, %o2
 	retl
-	 add	%o2, GLOBAL_SPARE, %o2
+	 add	%o2, GLOBAL_SPARE, %o0
 ENDPROC(U3_retl_o2_and_7_plus_GS_plus_8)
 #endif
 
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 3c40ebd50f92..fed73f14aa49 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -325,6 +325,29 @@ static void __update_mmu_tsb_insert(struct mm_struct *mm, unsigned long tsb_inde
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
+static void __init add_huge_page_size(unsigned long size)
+{
+	unsigned int order;
+
+	if (size_to_hstate(size))
+		return;
+
+	order = ilog2(size) - PAGE_SHIFT;
+	hugetlb_add_hstate(order);
+}
+
+static int __init hugetlbpage_init(void)
+{
+	add_huge_page_size(1UL << HPAGE_64K_SHIFT);
+	add_huge_page_size(1UL << HPAGE_SHIFT);
+	add_huge_page_size(1UL << HPAGE_256MB_SHIFT);
+	add_huge_page_size(1UL << HPAGE_2GB_SHIFT);
+
+	return 0;
+}
+
+arch_initcall(hugetlbpage_init);
+
 static int __init setup_hugepagesz(char *string)
 {
 	unsigned long long hugepage_size;
@@ -364,7 +387,7 @@ static int __init setup_hugepagesz(char *string)
 		goto out;
 	}
 
-	hugetlb_add_hstate(hugepage_shift - PAGE_SHIFT);
+	add_huge_page_size(hugepage_size);
 	rc = 1;
 
 out:
diff --git a/arch/sparc/power/hibernate.c b/arch/sparc/power/hibernate.c
index 17bd2e167e07..df707a8ad311 100644
--- a/arch/sparc/power/hibernate.c
+++ b/arch/sparc/power/hibernate.c
@@ -35,6 +35,5 @@ void restore_processor_state(void)
 {
 	struct mm_struct *mm = current->active_mm;
 
-	load_secondary_context(mm);
-	tsb_context_switch(mm);
+	tsb_context_switch_ctx(mm, CTX_HWBITS(mm->context));
 }
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 43e10d6fdbed..44adcde7a0ca 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -151,6 +151,8 @@ void kvm_async_pf_task_wait(u32 token)
 		if (hlist_unhashed(&n.link))
 			break;
 
+		rcu_irq_exit();
+
 		if (!n.halted) {
 			local_irq_enable();
 			schedule();
@@ -159,11 +161,11 @@ void kvm_async_pf_task_wait(u32 token)
 			/*
 			 * We cannot reschedule. So halt.
 			 */
-			rcu_irq_exit();
 			native_safe_halt();
 			local_irq_disable();
-			rcu_irq_enter();
 		}
+
+		rcu_irq_enter();
 	}
 	if (!n.halted)
 		finish_swait(&n.wq, &wait);
diff --git a/block/blk-core.c b/block/blk-core.c
index a7421b772d0e..56a7fac71439 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -3307,6 +3307,10 @@ EXPORT_SYMBOL(blk_finish_plug);
  */
 void blk_pm_runtime_init(struct request_queue *q, struct device *dev)
 {
+	/* not support for RQF_PM and ->rpm_status in blk-mq yet */
+	if (q->mq_ops)
+		return;
+
 	q->dev = dev;
 	q->rpm_status = RPM_ACTIVE;
 	pm_runtime_set_autosuspend_delay(q->dev, -1);
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index 8e61e8640e17..5eaecd40f701 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -35,7 +35,6 @@ int blk_mq_map_queues(struct blk_mq_tag_set *set)
 {
 	unsigned int *map = set->mq_map;
 	unsigned int nr_queues = set->nr_hw_queues;
-	const struct cpumask *online_mask = cpu_online_mask;
 	unsigned int i, nr_cpus, nr_uniq_cpus, queue, first_sibling;
 	cpumask_var_t cpus;
 
@@ -44,7 +43,7 @@ int blk_mq_map_queues(struct blk_mq_tag_set *set)
 
 	cpumask_clear(cpus);
 	nr_cpus = nr_uniq_cpus = 0;
-	for_each_cpu(i, online_mask) {
+	for_each_present_cpu(i) {
 		nr_cpus++;
 		first_sibling = get_first_sibling(i);
 		if (!cpumask_test_cpu(first_sibling, cpus))
@@ -54,7 +53,7 @@ int blk_mq_map_queues(struct blk_mq_tag_set *set)
 
 	queue = 0;
 	for_each_possible_cpu(i) {
-		if (!cpumask_test_cpu(i, online_mask)) {
+		if (!cpumask_test_cpu(i, cpu_present_mask)) {
 			map[i] = 0;
 			continue;
 		}
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 958cedaff8b8..7353e0080062 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -37,9 +37,6 @@
 #include "blk-wbt.h"
 #include "blk-mq-sched.h"
 
-static DEFINE_MUTEX(all_q_mutex);
-static LIST_HEAD(all_q_list);
-
 static void blk_mq_poll_stats_start(struct request_queue *q);
 static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
 static void __blk_mq_stop_hw_queues(struct request_queue *q, bool sync);
@@ -1975,8 +1972,8 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
 		INIT_LIST_HEAD(&__ctx->rq_list);
 		__ctx->queue = q;
 
-		/* If the cpu isn't online, the cpu is mapped to first hctx */
-		if (!cpu_online(i))
+		/* If the cpu isn't present, the cpu is mapped to first hctx */
+		if (!cpu_present(i))
 			continue;
 
 		hctx = blk_mq_map_queue(q, i);
@@ -2019,8 +2016,7 @@ static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set,
 	}
 }
 
-static void blk_mq_map_swqueue(struct request_queue *q,
-			       const struct cpumask *online_mask)
+static void blk_mq_map_swqueue(struct request_queue *q)
 {
 	unsigned int i, hctx_idx;
 	struct blk_mq_hw_ctx *hctx;
@@ -2038,13 +2034,11 @@ static void blk_mq_map_swqueue(struct request_queue *q,
 	}
 
 	/*
-	 * Map software to hardware queues
+	 * Map software to hardware queues.
+	 *
+	 * If the cpu isn't present, the cpu is mapped to first hctx.
 	 */
-	for_each_possible_cpu(i) {
-		/* If the cpu isn't online, the cpu is mapped to first hctx */
-		if (!cpumask_test_cpu(i, online_mask))
-			continue;
-
+	for_each_present_cpu(i) {
 		hctx_idx = q->mq_map[i];
 		/* unmapped hw queue can be remapped after CPU topo changed */
 		if (!set->tags[hctx_idx] &&
@@ -2340,16 +2334,8 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 		blk_queue_softirq_done(q, set->ops->complete);
 
 	blk_mq_init_cpu_queues(q, set->nr_hw_queues);
-
-	get_online_cpus();
-	mutex_lock(&all_q_mutex);
-
-	list_add_tail(&q->all_q_node, &all_q_list);
 	blk_mq_add_queue_tag_set(set, q);
-	blk_mq_map_swqueue(q, cpu_online_mask);
-
-	mutex_unlock(&all_q_mutex);
-	put_online_cpus();
+	blk_mq_map_swqueue(q);
 
 	if (!(set->flags & BLK_MQ_F_NO_SCHED)) {
 		int ret;
@@ -2375,18 +2361,12 @@ void blk_mq_free_queue(struct request_queue *q)
 {
 	struct blk_mq_tag_set	*set = q->tag_set;
 
-	mutex_lock(&all_q_mutex);
-	list_del_init(&q->all_q_node);
-	mutex_unlock(&all_q_mutex);
-
 	blk_mq_del_queue_tag_set(q);
-
 	blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
 }
 
 /* Basically redo blk_mq_init_queue with queue frozen */
-static void blk_mq_queue_reinit(struct request_queue *q,
-				const struct cpumask *online_mask)
+static void blk_mq_queue_reinit(struct request_queue *q)
 {
 	WARN_ON_ONCE(!atomic_read(&q->mq_freeze_depth));
 
@@ -2399,76 +2379,12 @@ static void blk_mq_queue_reinit(struct request_queue *q,
 	 * involves free and re-allocate memory, worthy doing?)
 	 */
 
-	blk_mq_map_swqueue(q, online_mask);
+	blk_mq_map_swqueue(q);
 
 	blk_mq_sysfs_register(q);
 	blk_mq_debugfs_register_hctxs(q);
 }
 
-/*
- * New online cpumask which is going to be set in this hotplug event.
- * Declare this cpumasks as global as cpu-hotplug operation is invoked
- * one-by-one and dynamically allocating this could result in a failure.
- */
-static struct cpumask cpuhp_online_new;
-
-static void blk_mq_queue_reinit_work(void)
-{
-	struct request_queue *q;
-
-	mutex_lock(&all_q_mutex);
-	/*
-	 * We need to freeze and reinit all existing queues.  Freezing
-	 * involves synchronous wait for an RCU grace period and doing it
-	 * one by one may take a long time.  Start freezing all queues in
-	 * one swoop and then wait for the completions so that freezing can
-	 * take place in parallel.
-	 */
-	list_for_each_entry(q, &all_q_list, all_q_node)
-		blk_freeze_queue_start(q);
-	list_for_each_entry(q, &all_q_list, all_q_node)
-		blk_mq_freeze_queue_wait(q);
-
-	list_for_each_entry(q, &all_q_list, all_q_node)
-		blk_mq_queue_reinit(q, &cpuhp_online_new);
-
-	list_for_each_entry(q, &all_q_list, all_q_node)
-		blk_mq_unfreeze_queue(q);
-
-	mutex_unlock(&all_q_mutex);
-}
-
-static int blk_mq_queue_reinit_dead(unsigned int cpu)
-{
-	cpumask_copy(&cpuhp_online_new, cpu_online_mask);
-	blk_mq_queue_reinit_work();
-	return 0;
-}
-
-/*
- * Before hotadded cpu starts handling requests, new mappings must be
- * established.  Otherwise, these requests in hw queue might never be
- * dispatched.
- *
- * For example, there is a single hw queue (hctx) and two CPU queues (ctx0
- * for CPU0, and ctx1 for CPU1).
- *
- * Now CPU1 is just onlined and a request is inserted into ctx1->rq_list
- * and set bit0 in pending bitmap as ctx1->index_hw is still zero.
- *
- * And then while running hw queue, blk_mq_flush_busy_ctxs() finds bit0 is set
- * in pending bitmap and tries to retrieve requests in hctx->ctxs[0]->rq_list.
- * But htx->ctxs[0] is a pointer to ctx0, so the request in ctx1->rq_list is
- * ignored.
- */
-static int blk_mq_queue_reinit_prepare(unsigned int cpu)
-{
-	cpumask_copy(&cpuhp_online_new, cpu_online_mask);
-	cpumask_set_cpu(cpu, &cpuhp_online_new);
-	blk_mq_queue_reinit_work();
-	return 0;
-}
-
 static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
 {
 	int i;
@@ -2679,7 +2595,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	blk_mq_update_queue_map(set);
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_realloc_hw_ctxs(set, q);
-		blk_mq_queue_reinit(q, cpu_online_mask);
+		blk_mq_queue_reinit(q);
 	}
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
@@ -2895,24 +2811,10 @@ bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie)
 }
 EXPORT_SYMBOL_GPL(blk_mq_poll);
 
-void blk_mq_disable_hotplug(void)
-{
-	mutex_lock(&all_q_mutex);
-}
-
-void blk_mq_enable_hotplug(void)
-{
-	mutex_unlock(&all_q_mutex);
-}
-
 static int __init blk_mq_init(void)
 {
 	cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL,
 				blk_mq_hctx_notify_dead);
-
-	cpuhp_setup_state_nocalls(CPUHP_BLK_MQ_PREPARE, "block/mq:prepare",
-				  blk_mq_queue_reinit_prepare,
-				  blk_mq_queue_reinit_dead);
 	return 0;
 }
 subsys_initcall(blk_mq_init);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index cc67b48e3551..558df56544d2 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -56,11 +56,6 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 				bool at_head);
 void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 				struct list_head *list);
-/*
- * CPU hotplug helpers
- */
-void blk_mq_enable_hotplug(void);
-void blk_mq_disable_hotplug(void);
 
 /*
  * CPU -> queue mappings
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 10347e3d73ad..5bd58bd4ab05 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -85,6 +85,7 @@ static const struct lpss_device_desc lpss_dma_desc = {
 };
 
 struct lpss_private_data {
+	struct acpi_device *adev;
 	void __iomem *mmio_base;
 	resource_size_t mmio_size;
 	unsigned int fixed_clk_rate;
@@ -155,6 +156,12 @@ static struct pwm_lookup byt_pwm_lookup[] = {
 
 static void byt_pwm_setup(struct lpss_private_data *pdata)
 {
+	struct acpi_device *adev = pdata->adev;
+
+	/* Only call pwm_add_table for the first PWM controller */
+	if (!adev->pnp.unique_id || strcmp(adev->pnp.unique_id, "1"))
+		return;
+
 	if (!acpi_dev_present("INT33FD", NULL, -1))
 		pwm_add_table(byt_pwm_lookup, ARRAY_SIZE(byt_pwm_lookup));
 }
@@ -180,6 +187,12 @@ static struct pwm_lookup bsw_pwm_lookup[] = {
 
 static void bsw_pwm_setup(struct lpss_private_data *pdata)
 {
+	struct acpi_device *adev = pdata->adev;
+
+	/* Only call pwm_add_table for the first PWM controller */
+	if (!adev->pnp.unique_id || strcmp(adev->pnp.unique_id, "1"))
+		return;
+
 	pwm_add_table(bsw_pwm_lookup, ARRAY_SIZE(bsw_pwm_lookup));
 }
 
@@ -456,6 +469,7 @@ static int acpi_lpss_create_device(struct acpi_device *adev,
 		goto err_out;
 	}
 
+	pdata->adev = adev;
 	pdata->dev_desc = dev_desc;
 
 	if (dev_desc->setup)
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 49ba9834c715..12d59968020f 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -3028,10 +3028,12 @@ static unsigned int atapi_xlat(struct ata_queued_cmd *qc)
 static struct ata_device *ata_find_dev(struct ata_port *ap, int devno)
 {
 	if (!sata_pmp_attached(ap)) {
-		if (likely(devno < ata_link_max_devices(&ap->link)))
+		if (likely(devno >= 0 &&
+			   devno < ata_link_max_devices(&ap->link)))
 			return &ap->link.device[devno];
 	} else {
-		if (likely(devno < ap->nr_pmp_links))
+		if (likely(devno >= 0 &&
+			   devno < ap->nr_pmp_links))
 			return &ap->pmp_link[devno].device[0];
 	}
 
diff --git a/drivers/clk/sunxi-ng/ccu-sun5i.c b/drivers/clk/sunxi-ng/ccu-sun5i.c
index 5372bf8be5e6..31d7ffda9aab 100644
--- a/drivers/clk/sunxi-ng/ccu-sun5i.c
+++ b/drivers/clk/sunxi-ng/ccu-sun5i.c
@@ -184,7 +184,7 @@ static struct ccu_mux cpu_clk = {
 		.hw.init	= CLK_HW_INIT_PARENTS("cpu",
 						      cpu_parents,
 						      &ccu_mux_ops,
-						      CLK_IS_CRITICAL),
+						      CLK_SET_RATE_PARENT | CLK_IS_CRITICAL),
 	}
 };
 
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index a42a1eea5714..2e96b3d46e0c 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -704,24 +704,23 @@ static irqreturn_t lineevent_irq_thread(int irq, void *p)
 {
 	struct lineevent_state *le = p;
 	struct gpioevent_data ge;
-	int ret;
+	int ret, level;
 
 	ge.timestamp = ktime_get_real_ns();
+	level = gpiod_get_value_cansleep(le->desc);
 
 	if (le->eflags & GPIOEVENT_REQUEST_RISING_EDGE
 	    && le->eflags & GPIOEVENT_REQUEST_FALLING_EDGE) {
-		int level = gpiod_get_value_cansleep(le->desc);
-
 		if (level)
 			/* Emit low-to-high event */
 			ge.id = GPIOEVENT_EVENT_RISING_EDGE;
 		else
 			/* Emit high-to-low event */
 			ge.id = GPIOEVENT_EVENT_FALLING_EDGE;
-	} else if (le->eflags & GPIOEVENT_REQUEST_RISING_EDGE) {
+	} else if (le->eflags & GPIOEVENT_REQUEST_RISING_EDGE && level) {
 		/* Emit low-to-high event */
 		ge.id = GPIOEVENT_EVENT_RISING_EDGE;
-	} else if (le->eflags & GPIOEVENT_REQUEST_FALLING_EDGE) {
+	} else if (le->eflags & GPIOEVENT_REQUEST_FALLING_EDGE && !level) {
 		/* Emit high-to-low event */
 		ge.id = GPIOEVENT_EVENT_FALLING_EDGE;
 	} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/clearstate_gfx9.h b/drivers/gpu/drm/amd/amdgpu/clearstate_gfx9.h
index 18fd01f3e4b2..003a131bad47 100644
--- a/drivers/gpu/drm/amd/amdgpu/clearstate_gfx9.h
+++ b/drivers/gpu/drm/amd/amdgpu/clearstate_gfx9.h
@@ -1,24 +1,25 @@
-
 /*
-***************************************************************************************************
-*
-*  Trade secret of Advanced Micro Devices, Inc.
-*  Copyright (c) 2010 Advanced Micro Devices, Inc. (unpublished)
-*
-*  All rights reserved.  This notice is intended as a precaution against inadvertent publication and
-*  does not imply publication or any waiver of confidentiality.  The year included in the foregoing
-*  notice is the year of creation of the work.
-*
-***************************************************************************************************
-*/
-/**
-***************************************************************************************************
-* @brief gfx9 Clearstate Definitions
-***************************************************************************************************
-*
-*   Do not edit! This is a machine-generated file!
-*
-*/
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
 
 static const unsigned int gfx9_SECT_CONTEXT_def_1[] =
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c
index c0b1aabf282f..7dbb7cf47986 100644
--- a/drivers/gpu/drm/amd/amdgpu/si.c
+++ b/drivers/gpu/drm/amd/amdgpu/si.c
@@ -1385,6 +1385,7 @@ static void si_init_golden_registers(struct amdgpu_device *adev)
 		amdgpu_program_register_sequence(adev,
 						 pitcairn_mgcg_cgcg_init,
 						 (const u32)ARRAY_SIZE(pitcairn_mgcg_cgcg_init));
+		break;
 	case CHIP_VERDE:
 		amdgpu_program_register_sequence(adev,
 						 verde_golden_registers,
@@ -1409,6 +1410,7 @@ static void si_init_golden_registers(struct amdgpu_device *adev)
 		amdgpu_program_register_sequence(adev,
 						 oland_mgcg_cgcg_init,
 						 (const u32)ARRAY_SIZE(oland_mgcg_cgcg_init));
+		break;
 	case CHIP_HAINAN:
 		amdgpu_program_register_sequence(adev,
 						 hainan_golden_registers,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 1d2db5d912b0..f8a977f86ec7 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -384,6 +384,12 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
 
 	hotspot_x = du->hotspot_x;
 	hotspot_y = du->hotspot_y;
+
+	if (plane->fb) {
+		hotspot_x += plane->fb->hot_x;
+		hotspot_y += plane->fb->hot_y;
+	}
+
 	du->cursor_surface = vps->surf;
 	du->cursor_dmabuf = vps->dmabuf;
 
@@ -411,6 +417,9 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
 		vmw_cursor_update_position(dev_priv, true,
 					   du->cursor_x + hotspot_x,
 					   du->cursor_y + hotspot_y);
+
+		du->core_hotspot_x = hotspot_x - du->hotspot_x;
+		du->core_hotspot_y = hotspot_y - du->hotspot_y;
 	} else {
 		DRM_ERROR("Failed to update cursor image\n");
 	}
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 0f1219fa8561..28fbc81c6e9e 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -4316,6 +4316,7 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
 		/* Setting */
 		irte->hi.fields.ga_root_ptr = (pi_data->base >> 12);
 		irte->hi.fields.vector = vcpu_pi_info->vector;
+		irte->lo.fields_vapic.ga_log_intr = 1;
 		irte->lo.fields_vapic.guest_mode = 1;
 		irte->lo.fields_vapic.ga_tag = pi_data->ga_tag;
 
diff --git a/drivers/media/pci/saa7164/saa7164-bus.c b/drivers/media/pci/saa7164/saa7164-bus.c
index b2ff82fa7116..ecfeac5cdbed 100644
--- a/drivers/media/pci/saa7164/saa7164-bus.c
+++ b/drivers/media/pci/saa7164/saa7164-bus.c
@@ -389,11 +389,11 @@ int saa7164_bus_get(struct saa7164_dev *dev, struct tmComResInfo* msg,
 	msg_tmp.size = le16_to_cpu((__force __le16)msg_tmp.size);
 	msg_tmp.command = le32_to_cpu((__force __le32)msg_tmp.command);
 	msg_tmp.controlselector = le16_to_cpu((__force __le16)msg_tmp.controlselector);
+	memcpy(msg, &msg_tmp, sizeof(*msg));
 
 	/* No need to update the read positions, because this was a peek */
 	/* If the caller specifically want to peek, return */
 	if (peekonly) {
-		memcpy(msg, &msg_tmp, sizeof(*msg));
 		goto peekout;
 	}
 
@@ -438,21 +438,15 @@ int saa7164_bus_get(struct saa7164_dev *dev, struct tmComResInfo* msg,
 		space_rem = bus->m_dwSizeGetRing - curr_grp;
 
 		if (space_rem < sizeof(*msg)) {
-			/* msg wraps around the ring */
-			memcpy_fromio(msg, bus->m_pdwGetRing + curr_grp, space_rem);
-			memcpy_fromio((u8 *)msg + space_rem, bus->m_pdwGetRing,
-				sizeof(*msg) - space_rem);
 			if (buf)
 				memcpy_fromio(buf, bus->m_pdwGetRing + sizeof(*msg) -
 					space_rem, buf_size);
 
 		} else if (space_rem == sizeof(*msg)) {
-			memcpy_fromio(msg, bus->m_pdwGetRing + curr_grp, sizeof(*msg));
 			if (buf)
 				memcpy_fromio(buf, bus->m_pdwGetRing, buf_size);
 		} else {
 			/* Additional data wraps around the ring */
-			memcpy_fromio(msg, bus->m_pdwGetRing + curr_grp, sizeof(*msg));
 			if (buf) {
 				memcpy_fromio(buf, bus->m_pdwGetRing + curr_grp +
 					sizeof(*msg), space_rem - sizeof(*msg));
@@ -465,15 +459,10 @@ int saa7164_bus_get(struct saa7164_dev *dev, struct tmComResInfo* msg,
 
 	} else {
 		/* No wrapping */
-		memcpy_fromio(msg, bus->m_pdwGetRing + curr_grp, sizeof(*msg));
 		if (buf)
 			memcpy_fromio(buf, bus->m_pdwGetRing + curr_grp + sizeof(*msg),
 				buf_size);
 	}
-	/* Convert from little endian to CPU */
-	msg->size = le16_to_cpu((__force __le16)msg->size);
-	msg->command = le32_to_cpu((__force __le32)msg->command);
-	msg->controlselector = le16_to_cpu((__force __le16)msg->controlselector);
 
 	/* Update the read positions, adjusting the ring */
 	saa7164_writel(bus->m_dwGetReadPos, new_grp);
diff --git a/drivers/media/platform/davinci/vpfe_capture.c b/drivers/media/platform/davinci/vpfe_capture.c
index e3fe3e0635aa..1831bf5ccca5 100644
--- a/drivers/media/platform/davinci/vpfe_capture.c
+++ b/drivers/media/platform/davinci/vpfe_capture.c
@@ -1719,27 +1719,9 @@ static long vpfe_param_handler(struct file *file, void *priv,
 
 	switch (cmd) {
 	case VPFE_CMD_S_CCDC_RAW_PARAMS:
+		ret = -EINVAL;
 		v4l2_warn(&vpfe_dev->v4l2_dev,
-			  "VPFE_CMD_S_CCDC_RAW_PARAMS: experimental ioctl\n");
-		if (ccdc_dev->hw_ops.set_params) {
-			ret = ccdc_dev->hw_ops.set_params(param);
-			if (ret) {
-				v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev,
-					"Error setting parameters in CCDC\n");
-				goto unlock_out;
-			}
-			ret = vpfe_get_ccdc_image_format(vpfe_dev,
-							 &vpfe_dev->fmt);
-			if (ret < 0) {
-				v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev,
-					"Invalid image format at CCDC\n");
-				goto unlock_out;
-			}
-		} else {
-			ret = -EINVAL;
-			v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev,
-				"VPFE_CMD_S_CCDC_RAW_PARAMS not supported\n");
-		}
+			"VPFE_CMD_S_CCDC_RAW_PARAMS not supported\n");
 		break;
 	default:
 		ret = -ENOTTY;
diff --git a/drivers/media/rc/ir-lirc-codec.c b/drivers/media/rc/ir-lirc-codec.c
index de85f1d7ce43..c01b655571a2 100644
--- a/drivers/media/rc/ir-lirc-codec.c
+++ b/drivers/media/rc/ir-lirc-codec.c
@@ -266,7 +266,7 @@ static long ir_lirc_ioctl(struct file *filep, unsigned int cmd,
 		if (!dev->rx_resolution)
 			return -ENOTTY;
 
-		val = dev->rx_resolution;
+		val = dev->rx_resolution / 1000;
 		break;
 
 	case LIRC_SET_WIDEBAND_RECEIVER:
diff --git a/drivers/media/rc/ir-spi.c b/drivers/media/rc/ir-spi.c
index c8863f36686a..f39cf8cb639f 100644
--- a/drivers/media/rc/ir-spi.c
+++ b/drivers/media/rc/ir-spi.c
@@ -57,10 +57,13 @@ static int ir_spi_tx(struct rc_dev *dev,
 
 	/* convert the pulse/space signal to raw binary signal */
 	for (i = 0; i < count; i++) {
+		unsigned int periods;
 		int j;
 		u16 val = ((i + 1) % 2) ? idata->pulse : idata->space;
 
-		if (len + buffer[i] >= IR_SPI_MAX_BUFSIZE)
+		periods = DIV_ROUND_CLOSEST(buffer[i] * idata->freq, 1000000);
+
+		if (len + periods >= IR_SPI_MAX_BUFSIZE)
 			return -EINVAL;
 
 		/*
@@ -69,13 +72,13 @@ static int ir_spi_tx(struct rc_dev *dev,
 		 * contain a space duration.
 		 */
 		val = (i % 2) ? idata->space : idata->pulse;
-		for (j = 0; j < buffer[i]; j++)
+		for (j = 0; j < periods; j++)
 			idata->tx_buf[len++] = val;
 	}
 
 	memset(&xfer, 0, sizeof(xfer));
 
-	xfer.speed_hz = idata->freq;
+	xfer.speed_hz = idata->freq * 16;
 	xfer.len = len * sizeof(*idata->tx_buf);
 	xfer.tx_buf = idata->tx_buf;
 
diff --git a/drivers/media/usb/pulse8-cec/pulse8-cec.c b/drivers/media/usb/pulse8-cec/pulse8-cec.c
index 1dfc2de1fe77..4767f4341ba9 100644
--- a/drivers/media/usb/pulse8-cec/pulse8-cec.c
+++ b/drivers/media/usb/pulse8-cec/pulse8-cec.c
@@ -51,7 +51,7 @@ MODULE_DESCRIPTION("Pulse Eight HDMI CEC driver");
 MODULE_LICENSE("GPL");
 
 static int debug;
-static int persistent_config = 1;
+static int persistent_config;
 module_param(debug, int, 0644);
 module_param(persistent_config, int, 0644);
 MODULE_PARM_DESC(debug, "debug level (0-1)");
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 3f8c85d5aa09..88fa03142e92 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -176,19 +176,17 @@ static void mmc_retune_timer(unsigned long data)
  */
 int mmc_of_parse(struct mmc_host *host)
 {
-	struct device_node *np;
+	struct device *dev = host->parent;
 	u32 bus_width;
 	int ret;
 	bool cd_cap_invert, cd_gpio_invert = false;
 	bool ro_cap_invert, ro_gpio_invert = false;
 
-	if (!host->parent || !host->parent->of_node)
+	if (!dev || !dev_fwnode(dev))
 		return 0;
 
-	np = host->parent->of_node;
-
 	/* "bus-width" is translated to MMC_CAP_*_BIT_DATA flags */
-	if (of_property_read_u32(np, "bus-width", &bus_width) < 0) {
+	if (device_property_read_u32(dev, "bus-width", &bus_width) < 0) {
 		dev_dbg(host->parent,
 			"\"bus-width\" property is missing, assuming 1 bit.\n");
 		bus_width = 1;
@@ -210,7 +208,7 @@ int mmc_of_parse(struct mmc_host *host)
 	}
 
 	/* f_max is obtained from the optional "max-frequency" property */
-	of_property_read_u32(np, "max-frequency", &host->f_max);
+	device_property_read_u32(dev, "max-frequency", &host->f_max);
 
 	/*
 	 * Configure CD and WP pins. They are both by default active low to
@@ -225,12 +223,12 @@ int mmc_of_parse(struct mmc_host *host)
 	 */
 
 	/* Parse Card Detection */
-	if (of_property_read_bool(np, "non-removable")) {
+	if (device_property_read_bool(dev, "non-removable")) {
 		host->caps |= MMC_CAP_NONREMOVABLE;
 	} else {
-		cd_cap_invert = of_property_read_bool(np, "cd-inverted");
+		cd_cap_invert = device_property_read_bool(dev, "cd-inverted");
 
-		if (of_property_read_bool(np, "broken-cd"))
+		if (device_property_read_bool(dev, "broken-cd"))
 			host->caps |= MMC_CAP_NEEDS_POLL;
 
 		ret = mmc_gpiod_request_cd(host, "cd", 0, true,
@@ -256,7 +254,7 @@ int mmc_of_parse(struct mmc_host *host)
 	}
 
 	/* Parse Write Protection */
-	ro_cap_invert = of_property_read_bool(np, "wp-inverted");
+	ro_cap_invert = device_property_read_bool(dev, "wp-inverted");
 
 	ret = mmc_gpiod_request_ro(host, "wp", 0, false, 0, &ro_gpio_invert);
 	if (!ret)
@@ -264,64 +262,64 @@ int mmc_of_parse(struct mmc_host *host)
 	else if (ret != -ENOENT && ret != -ENOSYS)
 		return ret;
 
-	if (of_property_read_bool(np, "disable-wp"))
+	if (device_property_read_bool(dev, "disable-wp"))
 		host->caps2 |= MMC_CAP2_NO_WRITE_PROTECT;
 
 	/* See the comment on CD inversion above */
 	if (ro_cap_invert ^ ro_gpio_invert)
 		host->caps2 |= MMC_CAP2_RO_ACTIVE_HIGH;
 
-	if (of_property_read_bool(np, "cap-sd-highspeed"))
+	if (device_property_read_bool(dev, "cap-sd-highspeed"))
 		host->caps |= MMC_CAP_SD_HIGHSPEED;
-	if (of_property_read_bool(np, "cap-mmc-highspeed"))
+	if (device_property_read_bool(dev, "cap-mmc-highspeed"))
 		host->caps |= MMC_CAP_MMC_HIGHSPEED;
-	if (of_property_read_bool(np, "sd-uhs-sdr12"))
+	if (device_property_read_bool(dev, "sd-uhs-sdr12"))
 		host->caps |= MMC_CAP_UHS_SDR12;
-	if (of_property_read_bool(np, "sd-uhs-sdr25"))
+	if (device_property_read_bool(dev, "sd-uhs-sdr25"))
 		host->caps |= MMC_CAP_UHS_SDR25;
-	if (of_property_read_bool(np, "sd-uhs-sdr50"))
+	if (device_property_read_bool(dev, "sd-uhs-sdr50"))
 		host->caps |= MMC_CAP_UHS_SDR50;
-	if (of_property_read_bool(np, "sd-uhs-sdr104"))
+	if (device_property_read_bool(dev, "sd-uhs-sdr104"))
 		host->caps |= MMC_CAP_UHS_SDR104;
-	if (of_property_read_bool(np, "sd-uhs-ddr50"))
+	if (device_property_read_bool(dev, "sd-uhs-ddr50"))
 		host->caps |= MMC_CAP_UHS_DDR50;
-	if (of_property_read_bool(np, "cap-power-off-card"))
+	if (device_property_read_bool(dev, "cap-power-off-card"))
 		host->caps |= MMC_CAP_POWER_OFF_CARD;
-	if (of_property_read_bool(np, "cap-mmc-hw-reset"))
+	if (device_property_read_bool(dev, "cap-mmc-hw-reset"))
 		host->caps |= MMC_CAP_HW_RESET;
-	if (of_property_read_bool(np, "cap-sdio-irq"))
+	if (device_property_read_bool(dev, "cap-sdio-irq"))
 		host->caps |= MMC_CAP_SDIO_IRQ;
-	if (of_property_read_bool(np, "full-pwr-cycle"))
+	if (device_property_read_bool(dev, "full-pwr-cycle"))
 		host->caps2 |= MMC_CAP2_FULL_PWR_CYCLE;
-	if (of_property_read_bool(np, "keep-power-in-suspend"))
+	if (device_property_read_bool(dev, "keep-power-in-suspend"))
 		host->pm_caps |= MMC_PM_KEEP_POWER;
-	if (of_property_read_bool(np, "wakeup-source") ||
-	    of_property_read_bool(np, "enable-sdio-wakeup")) /* legacy */
+	if (device_property_read_bool(dev, "wakeup-source") ||
+	    device_property_read_bool(dev, "enable-sdio-wakeup")) /* legacy */
 		host->pm_caps |= MMC_PM_WAKE_SDIO_IRQ;
-	if (of_property_read_bool(np, "mmc-ddr-3_3v"))
+	if (device_property_read_bool(dev, "mmc-ddr-3_3v"))
 		host->caps |= MMC_CAP_3_3V_DDR;
-	if (of_property_read_bool(np, "mmc-ddr-1_8v"))
+	if (device_property_read_bool(dev, "mmc-ddr-1_8v"))
 		host->caps |= MMC_CAP_1_8V_DDR;
-	if (of_property_read_bool(np, "mmc-ddr-1_2v"))
+	if (device_property_read_bool(dev, "mmc-ddr-1_2v"))
 		host->caps |= MMC_CAP_1_2V_DDR;
-	if (of_property_read_bool(np, "mmc-hs200-1_8v"))
+	if (device_property_read_bool(dev, "mmc-hs200-1_8v"))
 		host->caps2 |= MMC_CAP2_HS200_1_8V_SDR;
-	if (of_property_read_bool(np, "mmc-hs200-1_2v"))
+	if (device_property_read_bool(dev, "mmc-hs200-1_2v"))
 		host->caps2 |= MMC_CAP2_HS200_1_2V_SDR;
-	if (of_property_read_bool(np, "mmc-hs400-1_8v"))
+	if (device_property_read_bool(dev, "mmc-hs400-1_8v"))
 		host->caps2 |= MMC_CAP2_HS400_1_8V | MMC_CAP2_HS200_1_8V_SDR;
-	if (of_property_read_bool(np, "mmc-hs400-1_2v"))
+	if (device_property_read_bool(dev, "mmc-hs400-1_2v"))
 		host->caps2 |= MMC_CAP2_HS400_1_2V | MMC_CAP2_HS200_1_2V_SDR;
-	if (of_property_read_bool(np, "mmc-hs400-enhanced-strobe"))
+	if (device_property_read_bool(dev, "mmc-hs400-enhanced-strobe"))
 		host->caps2 |= MMC_CAP2_HS400_ES;
-	if (of_property_read_bool(np, "no-sdio"))
+	if (device_property_read_bool(dev, "no-sdio"))
 		host->caps2 |= MMC_CAP2_NO_SDIO;
-	if (of_property_read_bool(np, "no-sd"))
+	if (device_property_read_bool(dev, "no-sd"))
 		host->caps2 |= MMC_CAP2_NO_SD;
-	if (of_property_read_bool(np, "no-mmc"))
+	if (device_property_read_bool(dev, "no-mmc"))
 		host->caps2 |= MMC_CAP2_NO_MMC;
 
-	host->dsr_req = !of_property_read_u32(np, "dsr", &host->dsr);
+	host->dsr_req = !device_property_read_u32(dev, "dsr", &host->dsr);
 	if (host->dsr_req && (host->dsr & ~0xffff)) {
 		dev_err(host->parent,
 			"device tree specified broken value for DSR: 0x%x, ignoring\n",
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index e45129f48174..efde0f20dd24 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -2707,8 +2707,8 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 	host->slot[id] = slot;
 
 	mmc->ops = &dw_mci_ops;
-	if (of_property_read_u32_array(host->dev->of_node,
-				       "clock-freq-min-max", freq, 2)) {
+	if (device_property_read_u32_array(host->dev, "clock-freq-min-max",
+					   freq, 2)) {
 		mmc->f_min = DW_MCI_FREQ_MIN;
 		mmc->f_max = DW_MCI_FREQ_MAX;
 	} else {
@@ -2808,7 +2808,6 @@ static void dw_mci_init_dma(struct dw_mci *host)
 {
 	int addr_config;
 	struct device *dev = host->dev;
-	struct device_node *np = dev->of_node;
 
 	/*
 	* Check tansfer mode from HCON[17:16]
@@ -2869,8 +2868,9 @@ static void dw_mci_init_dma(struct dw_mci *host)
 		dev_info(host->dev, "Using internal DMA controller.\n");
 	} else {
 		/* TRANS_MODE_EDMAC: check dma bindings again */
-		if ((of_property_count_strings(np, "dma-names") < 0) ||
-		    (!of_find_property(np, "dmas", NULL))) {
+		if ((device_property_read_string_array(dev, "dma-names",
+						       NULL, 0) < 0) ||
+		    !device_property_present(dev, "dmas")) {
 			goto no_dma;
 		}
 		host->dma_ops = &dw_mci_edmac_ops;
@@ -2937,7 +2937,6 @@ static struct dw_mci_board *dw_mci_parse_dt(struct dw_mci *host)
 {
 	struct dw_mci_board *pdata;
 	struct device *dev = host->dev;
-	struct device_node *np = dev->of_node;
 	const struct dw_mci_drv_data *drv_data = host->drv_data;
 	int ret;
 	u32 clock_frequency;
@@ -2954,20 +2953,21 @@ static struct dw_mci_board *dw_mci_parse_dt(struct dw_mci *host)
 	}
 
 	/* find out number of slots supported */
-	of_property_read_u32(np, "num-slots", &pdata->num_slots);
+	device_property_read_u32(dev, "num-slots", &pdata->num_slots);
 
-	if (of_property_read_u32(np, "fifo-depth", &pdata->fifo_depth))
+	if (device_property_read_u32(dev, "fifo-depth", &pdata->fifo_depth))
 		dev_info(dev,
 			 "fifo-depth property not found, using value of FIFOTH register as default\n");
 
-	of_property_read_u32(np, "card-detect-delay", &pdata->detect_delay_ms);
+	device_property_read_u32(dev, "card-detect-delay",
+				 &pdata->detect_delay_ms);
 
-	of_property_read_u32(np, "data-addr", &host->data_addr_override);
+	device_property_read_u32(dev, "data-addr", &host->data_addr_override);
 
-	if (of_get_property(np, "fifo-watermark-aligned", NULL))
+	if (device_property_present(dev, "fifo-watermark-aligned"))
 		host->wm_aligned = true;
 
-	if (!of_property_read_u32(np, "clock-frequency", &clock_frequency))
+	if (!device_property_read_u32(dev, "clock-frequency", &clock_frequency))
 		pdata->bus_hz = clock_frequency;
 
 	if (drv_data && drv_data->parse_dt) {
diff --git a/drivers/mmc/host/sdhci-of-at91.c b/drivers/mmc/host/sdhci-of-at91.c
index 7611fd679f1a..1485530c3592 100644
--- a/drivers/mmc/host/sdhci-of-at91.c
+++ b/drivers/mmc/host/sdhci-of-at91.c
@@ -31,6 +31,7 @@
 
 #define SDMMC_MC1R	0x204
 #define		SDMMC_MC1R_DDR		BIT(3)
+#define		SDMMC_MC1R_FCD		BIT(7)
 #define SDMMC_CACR	0x230
 #define		SDMMC_CACR_CAPWREN	BIT(0)
 #define		SDMMC_CACR_KEY		(0x46 << 8)
@@ -43,6 +44,15 @@ struct sdhci_at91_priv {
 	struct clk *mainck;
 };
 
+static void sdhci_at91_set_force_card_detect(struct sdhci_host *host)
+{
+	u8 mc1r;
+
+	mc1r = readb(host->ioaddr + SDMMC_MC1R);
+	mc1r |= SDMMC_MC1R_FCD;
+	writeb(mc1r, host->ioaddr + SDMMC_MC1R);
+}
+
 static void sdhci_at91_set_clock(struct sdhci_host *host, unsigned int clock)
 {
 	u16 clk;
@@ -110,10 +120,18 @@ void sdhci_at91_set_uhs_signaling(struct sdhci_host *host, unsigned int timing)
 	sdhci_set_uhs_signaling(host, timing);
 }
 
+static void sdhci_at91_reset(struct sdhci_host *host, u8 mask)
+{
+	sdhci_reset(host, mask);
+
+	if (host->mmc->caps & MMC_CAP_NONREMOVABLE)
+		sdhci_at91_set_force_card_detect(host);
+}
+
 static const struct sdhci_ops sdhci_at91_sama5d2_ops = {
 	.set_clock		= sdhci_at91_set_clock,
 	.set_bus_width		= sdhci_set_bus_width,
-	.reset			= sdhci_reset,
+	.reset			= sdhci_at91_reset,
 	.set_uhs_signaling	= sdhci_at91_set_uhs_signaling,
 	.set_power		= sdhci_at91_set_power,
 };
@@ -324,6 +342,21 @@ static int sdhci_at91_probe(struct platform_device *pdev)
 		host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION;
 	}
 
+	/*
+	 * If the device attached to the MMC bus is not removable, it is safer
+	 * to set the Force Card Detect bit. People often don't connect the
+	 * card detect signal and use this pin for another purpose. If the card
+	 * detect pin is not muxed to SDHCI controller, a default value is
+	 * used. This value can be different from a SoC revision to another
+	 * one. Problems come when this default value is not card present. To
+	 * avoid this case, if the device is non removable then the card
+	 * detection procedure using the SDMCC_CD signal is bypassed.
+	 * This bit is reset when a software reset for all command is performed
+	 * so we need to implement our own reset function to set back this bit.
+	 */
+	if (host->mmc->caps & MMC_CAP_NONREMOVABLE)
+		sdhci_at91_set_force_card_detect(host);
+
 	pm_runtime_put_autosuspend(&pdev->dev);
 
 	return 0;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 8ab6bdbe1682..224e93aa6d23 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2047,6 +2047,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 				continue;
 
 			bond_propose_link_state(slave, BOND_LINK_FAIL);
+			commit++;
 			slave->delay = bond->params.downdelay;
 			if (slave->delay) {
 				netdev_info(bond->dev, "link status down for %sinterface %s, disabling it in %d ms\n",
@@ -2085,6 +2086,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 				continue;
 
 			bond_propose_link_state(slave, BOND_LINK_BACK);
+			commit++;
 			slave->delay = bond->params.updelay;
 
 			if (slave->delay) {
@@ -4598,7 +4600,7 @@ static int bond_check_params(struct bond_params *params)
 	}
 	ad_user_port_key = valptr->value;
 
-	if (bond_mode == BOND_MODE_TLB) {
+	if ((bond_mode == BOND_MODE_TLB) || (bond_mode == BOND_MODE_ALB)) {
 		bond_opt_initstr(&newval, "default");
 		valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB),
 					&newval);
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index fa0eece21eef..d9cc94a7d44e 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1668,6 +1668,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.dev_name = "BCM53125",
 		.vlans = 4096,
 		.enabled_ports = 0xff,
+		.arl_entries = 4,
 		.cpu_port = B53_CPU_PORT,
 		.vta_regs = B53_VTA_REGS,
 		.duplex_reg = B53_DUPLEX_STAT_GE,
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index d034d8cd7d22..32864a47c4c1 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -3377,6 +3377,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6390_port_pause_config,
+	.port_set_cmode = mv88e6390x_port_set_cmode,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
index 5711fbbd6ae3..878cffd37e1f 100644
--- a/drivers/net/ethernet/aurora/nb8800.c
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -609,7 +609,7 @@ static void nb8800_mac_config(struct net_device *dev)
 		mac_mode |= HALF_DUPLEX;
 
 	if (gigabit) {
-		if (priv->phy_mode == PHY_INTERFACE_MODE_RGMII)
+		if (phy_interface_is_rgmii(dev->phydev))
 			mac_mode |= RGMII_MODE;
 
 		mac_mode |= GMAC_MODE;
@@ -1268,11 +1268,10 @@ static int nb8800_tangox_init(struct net_device *dev)
 		break;
 
 	case PHY_INTERFACE_MODE_RGMII:
-		pad_mode = PAD_MODE_RGMII;
-		break;
-
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
 	case PHY_INTERFACE_MODE_RGMII_TXID:
-		pad_mode = PAD_MODE_RGMII | PAD_MODE_GTX_CLK_DELAY;
+		pad_mode = PAD_MODE_RGMII;
 		break;
 
 	default:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 10d282841f5b..ac0a460c006a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -777,6 +777,10 @@ static void cb_timeout_handler(struct work_struct *work)
 	mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
 }
 
+static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg);
+static void mlx5_free_cmd_msg(struct mlx5_core_dev *dev,
+			      struct mlx5_cmd_msg *msg);
+
 static void cmd_work_handler(struct work_struct *work)
 {
 	struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work);
@@ -786,16 +790,27 @@ static void cmd_work_handler(struct work_struct *work)
 	struct mlx5_cmd_layout *lay;
 	struct semaphore *sem;
 	unsigned long flags;
+	int alloc_ret;
 
 	sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
 	down(sem);
 	if (!ent->page_queue) {
-		ent->idx = alloc_ent(cmd);
-		if (ent->idx < 0) {
+		alloc_ret = alloc_ent(cmd);
+		if (alloc_ret < 0) {
 			mlx5_core_err(dev, "failed to allocate command entry\n");
+			if (ent->callback) {
+				ent->callback(-EAGAIN, ent->context);
+				mlx5_free_cmd_msg(dev, ent->out);
+				free_msg(dev, ent->in);
+				free_cmd(ent);
+			} else {
+				ent->ret = -EAGAIN;
+				complete(&ent->done);
+			}
 			up(sem);
 			return;
 		}
+		ent->idx = alloc_ret;
 	} else {
 		ent->idx = cmd->max_reg_cmds;
 		spin_lock_irqsave(&cmd->alloc_lock, flags);
@@ -955,7 +970,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 
 	err = wait_func(dev, ent);
 	if (err == -ETIMEDOUT)
-		goto out_free;
+		goto out;
 
 	ds = ent->ts2 - ent->ts1;
 	op = MLX5_GET(mbox_in, in->first.data, opcode);
@@ -1419,6 +1434,7 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced)
 					mlx5_core_err(dev, "Command completion arrived after timeout (entry idx = %d).\n",
 						      ent->idx);
 					free_ent(cmd, ent->idx);
+					free_cmd(ent);
 				}
 				continue;
 			}
@@ -1477,7 +1493,8 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced)
 				free_msg(dev, ent->in);
 
 				err = err ? err : ent->status;
-				free_cmd(ent);
+				if (!forced)
+					free_cmd(ent);
 				callback(err, context);
 			} else {
 				complete(&ent->done);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 944fc1742464..3b39dbd97e57 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -261,6 +261,14 @@ struct mlx5e_dcbx {
 };
 #endif
 
+#define MAX_PIN_NUM	8
+struct mlx5e_pps {
+	u8                         pin_caps[MAX_PIN_NUM];
+	struct work_struct         out_work;
+	u64                        start[MAX_PIN_NUM];
+	u8                         enabled;
+};
+
 struct mlx5e_tstamp {
 	rwlock_t                   lock;
 	struct cyclecounter        cycles;
@@ -272,7 +280,7 @@ struct mlx5e_tstamp {
 	struct mlx5_core_dev      *mdev;
 	struct ptp_clock          *ptp;
 	struct ptp_clock_info      ptp_info;
-	u8                        *pps_pin_caps;
+	struct mlx5e_pps           pps_info;
 };
 
 enum {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
index e706a87fc8b2..80c500f87ab6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
@@ -53,6 +53,15 @@ enum {
 	MLX5E_EVENT_MODE_ONCE_TILL_ARM	= 0x2,
 };
 
+enum {
+	MLX5E_MTPPS_FS_ENABLE			= BIT(0x0),
+	MLX5E_MTPPS_FS_PATTERN			= BIT(0x2),
+	MLX5E_MTPPS_FS_PIN_MODE			= BIT(0x3),
+	MLX5E_MTPPS_FS_TIME_STAMP		= BIT(0x4),
+	MLX5E_MTPPS_FS_OUT_PULSE_DURATION	= BIT(0x5),
+	MLX5E_MTPPS_FS_ENH_OUT_PER_ADJ		= BIT(0x7),
+};
+
 void mlx5e_fill_hwstamp(struct mlx5e_tstamp *tstamp, u64 timestamp,
 			struct skb_shared_hwtstamps *hwts)
 {
@@ -73,17 +82,46 @@ static u64 mlx5e_read_internal_timer(const struct cyclecounter *cc)
 	return mlx5_read_internal_timer(tstamp->mdev) & cc->mask;
 }
 
+static void mlx5e_pps_out(struct work_struct *work)
+{
+	struct mlx5e_pps *pps_info = container_of(work, struct mlx5e_pps,
+						  out_work);
+	struct mlx5e_tstamp *tstamp = container_of(pps_info, struct mlx5e_tstamp,
+						   pps_info);
+	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
+	unsigned long flags;
+	int i;
+
+	for (i = 0; i < tstamp->ptp_info.n_pins; i++) {
+		u64 tstart;
+
+		write_lock_irqsave(&tstamp->lock, flags);
+		tstart = tstamp->pps_info.start[i];
+		tstamp->pps_info.start[i] = 0;
+		write_unlock_irqrestore(&tstamp->lock, flags);
+		if (!tstart)
+			continue;
+
+		MLX5_SET(mtpps_reg, in, pin, i);
+		MLX5_SET64(mtpps_reg, in, time_stamp, tstart);
+		MLX5_SET(mtpps_reg, in, field_select, MLX5E_MTPPS_FS_TIME_STAMP);
+		mlx5_set_mtpps(tstamp->mdev, in, sizeof(in));
+	}
+}
+
 static void mlx5e_timestamp_overflow(struct work_struct *work)
 {
 	struct delayed_work *dwork = to_delayed_work(work);
 	struct mlx5e_tstamp *tstamp = container_of(dwork, struct mlx5e_tstamp,
 						   overflow_work);
+	struct mlx5e_priv *priv = container_of(tstamp, struct mlx5e_priv, tstamp);
 	unsigned long flags;
 
 	write_lock_irqsave(&tstamp->lock, flags);
 	timecounter_read(&tstamp->clock);
 	write_unlock_irqrestore(&tstamp->lock, flags);
-	schedule_delayed_work(&tstamp->overflow_work, tstamp->overflow_period);
+	queue_delayed_work(priv->wq, &tstamp->overflow_work,
+			   msecs_to_jiffies(tstamp->overflow_period * 1000));
 }
 
 int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr)
@@ -214,18 +252,6 @@ static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta)
 	int neg_adj = 0;
 	struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp,
 						  ptp_info);
-	struct mlx5e_priv *priv =
-		container_of(tstamp, struct mlx5e_priv, tstamp);
-
-	if (MLX5_CAP_GEN(priv->mdev, pps_modify)) {
-		u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
-
-		/* For future use need to add a loop for finding all 1PPS out pins */
-		MLX5_SET(mtpps_reg, in, pin_mode, MLX5E_PIN_MODE_OUT);
-		MLX5_SET(mtpps_reg, in, out_periodic_adjustment, delta & 0xFFFF);
-
-		mlx5_set_mtpps(priv->mdev, in, sizeof(in));
-	}
 
 	if (delta < 0) {
 		neg_adj = 1;
@@ -254,12 +280,13 @@ static int mlx5e_extts_configure(struct ptp_clock_info *ptp,
 	struct mlx5e_priv *priv =
 		container_of(tstamp, struct mlx5e_priv, tstamp);
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
+	u32 field_select = 0;
+	u8 pin_mode = 0;
 	u8 pattern = 0;
 	int pin = -1;
 	int err = 0;
 
-	if (!MLX5_CAP_GEN(priv->mdev, pps) ||
-	    !MLX5_CAP_GEN(priv->mdev, pps_modify))
+	if (!MLX5_PPS_CAP(priv->mdev))
 		return -EOPNOTSUPP;
 
 	if (rq->extts.index >= tstamp->ptp_info.n_pins)
@@ -269,15 +296,21 @@ static int mlx5e_extts_configure(struct ptp_clock_info *ptp,
 		pin = ptp_find_pin(tstamp->ptp, PTP_PF_EXTTS, rq->extts.index);
 		if (pin < 0)
 			return -EBUSY;
+		pin_mode = MLX5E_PIN_MODE_IN;
+		pattern = !!(rq->extts.flags & PTP_FALLING_EDGE);
+		field_select = MLX5E_MTPPS_FS_PIN_MODE |
+			       MLX5E_MTPPS_FS_PATTERN |
+			       MLX5E_MTPPS_FS_ENABLE;
+	} else {
+		pin = rq->extts.index;
+		field_select = MLX5E_MTPPS_FS_ENABLE;
 	}
 
-	if (rq->extts.flags & PTP_FALLING_EDGE)
-		pattern = 1;
-
 	MLX5_SET(mtpps_reg, in, pin, pin);
-	MLX5_SET(mtpps_reg, in, pin_mode, MLX5E_PIN_MODE_IN);
+	MLX5_SET(mtpps_reg, in, pin_mode, pin_mode);
 	MLX5_SET(mtpps_reg, in, pattern, pattern);
 	MLX5_SET(mtpps_reg, in, enable, on);
+	MLX5_SET(mtpps_reg, in, field_select, field_select);
 
 	err = mlx5_set_mtpps(priv->mdev, in, sizeof(in));
 	if (err)
@@ -296,14 +329,18 @@ static int mlx5e_perout_configure(struct ptp_clock_info *ptp,
 	struct mlx5e_priv *priv =
 		container_of(tstamp, struct mlx5e_priv, tstamp);
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
-	u64 nsec_now, nsec_delta, time_stamp;
+	u64 nsec_now, nsec_delta, time_stamp = 0;
 	u64 cycles_now, cycles_delta;
 	struct timespec64 ts;
 	unsigned long flags;
+	u32 field_select = 0;
+	u8 pin_mode = 0;
+	u8 pattern = 0;
 	int pin = -1;
+	int err = 0;
 	s64 ns;
 
-	if (!MLX5_CAP_GEN(priv->mdev, pps_modify))
+	if (!MLX5_PPS_CAP(priv->mdev))
 		return -EOPNOTSUPP;
 
 	if (rq->perout.index >= tstamp->ptp_info.n_pins)
@@ -314,32 +351,60 @@ static int mlx5e_perout_configure(struct ptp_clock_info *ptp,
 				   rq->perout.index);
 		if (pin < 0)
 			return -EBUSY;
-	}
 
-	ts.tv_sec = rq->perout.period.sec;
-	ts.tv_nsec = rq->perout.period.nsec;
-	ns = timespec64_to_ns(&ts);
-	if (on)
+		pin_mode = MLX5E_PIN_MODE_OUT;
+		pattern = MLX5E_OUT_PATTERN_PERIODIC;
+		ts.tv_sec = rq->perout.period.sec;
+		ts.tv_nsec = rq->perout.period.nsec;
+		ns = timespec64_to_ns(&ts);
+
 		if ((ns >> 1) != 500000000LL)
 			return -EINVAL;
-	ts.tv_sec = rq->perout.start.sec;
-	ts.tv_nsec = rq->perout.start.nsec;
-	ns = timespec64_to_ns(&ts);
-	cycles_now = mlx5_read_internal_timer(tstamp->mdev);
-	write_lock_irqsave(&tstamp->lock, flags);
-	nsec_now = timecounter_cyc2time(&tstamp->clock, cycles_now);
-	nsec_delta = ns - nsec_now;
-	cycles_delta = div64_u64(nsec_delta << tstamp->cycles.shift,
-				 tstamp->cycles.mult);
-	write_unlock_irqrestore(&tstamp->lock, flags);
-	time_stamp = cycles_now + cycles_delta;
+
+		ts.tv_sec = rq->perout.start.sec;
+		ts.tv_nsec = rq->perout.start.nsec;
+		ns = timespec64_to_ns(&ts);
+		cycles_now = mlx5_read_internal_timer(tstamp->mdev);
+		write_lock_irqsave(&tstamp->lock, flags);
+		nsec_now = timecounter_cyc2time(&tstamp->clock, cycles_now);
+		nsec_delta = ns - nsec_now;
+		cycles_delta = div64_u64(nsec_delta << tstamp->cycles.shift,
+					 tstamp->cycles.mult);
+		write_unlock_irqrestore(&tstamp->lock, flags);
+		time_stamp = cycles_now + cycles_delta;
+		field_select = MLX5E_MTPPS_FS_PIN_MODE |
+			       MLX5E_MTPPS_FS_PATTERN |
+			       MLX5E_MTPPS_FS_ENABLE |
+			       MLX5E_MTPPS_FS_TIME_STAMP;
+	} else {
+		pin = rq->perout.index;
+		field_select = MLX5E_MTPPS_FS_ENABLE;
+	}
+
 	MLX5_SET(mtpps_reg, in, pin, pin);
-	MLX5_SET(mtpps_reg, in, pin_mode, MLX5E_PIN_MODE_OUT);
-	MLX5_SET(mtpps_reg, in, pattern, MLX5E_OUT_PATTERN_PERIODIC);
+	MLX5_SET(mtpps_reg, in, pin_mode, pin_mode);
+	MLX5_SET(mtpps_reg, in, pattern, pattern);
 	MLX5_SET(mtpps_reg, in, enable, on);
 	MLX5_SET64(mtpps_reg, in, time_stamp, time_stamp);
+	MLX5_SET(mtpps_reg, in, field_select, field_select);
+
+	err = mlx5_set_mtpps(priv->mdev, in, sizeof(in));
+	if (err)
+		return err;
 
-	return mlx5_set_mtpps(priv->mdev, in, sizeof(in));
+	return mlx5_set_mtppse(priv->mdev, pin, 0,
+			       MLX5E_EVENT_MODE_REPETETIVE & on);
+}
+
+static int mlx5e_pps_configure(struct ptp_clock_info *ptp,
+			       struct ptp_clock_request *rq,
+			       int on)
+{
+	struct mlx5e_tstamp *tstamp =
+		container_of(ptp, struct mlx5e_tstamp, ptp_info);
+
+	tstamp->pps_info.enabled = !!on;
+	return 0;
 }
 
 static int mlx5e_ptp_enable(struct ptp_clock_info *ptp,
@@ -351,6 +416,8 @@ static int mlx5e_ptp_enable(struct ptp_clock_info *ptp,
 		return mlx5e_extts_configure(ptp, rq, on);
 	case PTP_CLK_REQ_PEROUT:
 		return mlx5e_perout_configure(ptp, rq, on);
+	case PTP_CLK_REQ_PPS:
+		return mlx5e_pps_configure(ptp, rq, on);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -396,6 +463,7 @@ static int mlx5e_init_pin_config(struct mlx5e_tstamp *tstamp)
 		return -ENOMEM;
 	tstamp->ptp_info.enable = mlx5e_ptp_enable;
 	tstamp->ptp_info.verify = mlx5e_ptp_verify;
+	tstamp->ptp_info.pps = 1;
 
 	for (i = 0; i < tstamp->ptp_info.n_pins; i++) {
 		snprintf(tstamp->ptp_info.pin_config[i].name,
@@ -423,22 +491,56 @@ static void mlx5e_get_pps_caps(struct mlx5e_priv *priv,
 	tstamp->ptp_info.n_per_out = MLX5_GET(mtpps_reg, out,
 					      cap_max_num_of_pps_out_pins);
 
-	tstamp->pps_pin_caps[0] = MLX5_GET(mtpps_reg, out, cap_pin_0_mode);
-	tstamp->pps_pin_caps[1] = MLX5_GET(mtpps_reg, out, cap_pin_1_mode);
-	tstamp->pps_pin_caps[2] = MLX5_GET(mtpps_reg, out, cap_pin_2_mode);
-	tstamp->pps_pin_caps[3] = MLX5_GET(mtpps_reg, out, cap_pin_3_mode);
-	tstamp->pps_pin_caps[4] = MLX5_GET(mtpps_reg, out, cap_pin_4_mode);
-	tstamp->pps_pin_caps[5] = MLX5_GET(mtpps_reg, out, cap_pin_5_mode);
-	tstamp->pps_pin_caps[6] = MLX5_GET(mtpps_reg, out, cap_pin_6_mode);
-	tstamp->pps_pin_caps[7] = MLX5_GET(mtpps_reg, out, cap_pin_7_mode);
+	tstamp->pps_info.pin_caps[0] = MLX5_GET(mtpps_reg, out, cap_pin_0_mode);
+	tstamp->pps_info.pin_caps[1] = MLX5_GET(mtpps_reg, out, cap_pin_1_mode);
+	tstamp->pps_info.pin_caps[2] = MLX5_GET(mtpps_reg, out, cap_pin_2_mode);
+	tstamp->pps_info.pin_caps[3] = MLX5_GET(mtpps_reg, out, cap_pin_3_mode);
+	tstamp->pps_info.pin_caps[4] = MLX5_GET(mtpps_reg, out, cap_pin_4_mode);
+	tstamp->pps_info.pin_caps[5] = MLX5_GET(mtpps_reg, out, cap_pin_5_mode);
+	tstamp->pps_info.pin_caps[6] = MLX5_GET(mtpps_reg, out, cap_pin_6_mode);
+	tstamp->pps_info.pin_caps[7] = MLX5_GET(mtpps_reg, out, cap_pin_7_mode);
 }
 
 void mlx5e_pps_event_handler(struct mlx5e_priv *priv,
 			     struct ptp_clock_event *event)
 {
+	struct net_device *netdev = priv->netdev;
 	struct mlx5e_tstamp *tstamp = &priv->tstamp;
+	struct timespec64 ts;
+	u64 nsec_now, nsec_delta;
+	u64 cycles_now, cycles_delta;
+	int pin = event->index;
+	s64 ns;
+	unsigned long flags;
 
-	ptp_clock_event(tstamp->ptp, event);
+	switch (tstamp->ptp_info.pin_config[pin].func) {
+	case PTP_PF_EXTTS:
+		if (tstamp->pps_info.enabled) {
+			event->type = PTP_CLOCK_PPSUSR;
+			event->pps_times.ts_real = ns_to_timespec64(event->timestamp);
+		} else {
+			event->type = PTP_CLOCK_EXTTS;
+		}
+		ptp_clock_event(tstamp->ptp, event);
+		break;
+	case PTP_PF_PEROUT:
+		mlx5e_ptp_gettime(&tstamp->ptp_info, &ts);
+		cycles_now = mlx5_read_internal_timer(tstamp->mdev);
+		ts.tv_sec += 1;
+		ts.tv_nsec = 0;
+		ns = timespec64_to_ns(&ts);
+		write_lock_irqsave(&tstamp->lock, flags);
+		nsec_now = timecounter_cyc2time(&tstamp->clock, cycles_now);
+		nsec_delta = ns - nsec_now;
+		cycles_delta = div64_u64(nsec_delta << tstamp->cycles.shift,
+					 tstamp->cycles.mult);
+		tstamp->pps_info.start[pin] = cycles_now + cycles_delta;
+		queue_work(priv->wq, &tstamp->pps_info.out_work);
+		write_unlock_irqrestore(&tstamp->lock, flags);
+		break;
+	default:
+		netdev_err(netdev, "%s: Unhandled event\n", __func__);
+	}
 }
 
 void mlx5e_timestamp_init(struct mlx5e_priv *priv)
@@ -474,9 +576,10 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv)
 	do_div(ns, NSEC_PER_SEC / 2 / HZ);
 	tstamp->overflow_period = ns;
 
+	INIT_WORK(&tstamp->pps_info.out_work, mlx5e_pps_out);
 	INIT_DELAYED_WORK(&tstamp->overflow_work, mlx5e_timestamp_overflow);
 	if (tstamp->overflow_period)
-		schedule_delayed_work(&tstamp->overflow_work, 0);
+		queue_delayed_work(priv->wq, &tstamp->overflow_work, 0);
 	else
 		mlx5_core_warn(priv->mdev, "invalid overflow period, overflow_work is not scheduled\n");
 
@@ -485,16 +588,10 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv)
 	snprintf(tstamp->ptp_info.name, 16, "mlx5 ptp");
 
 	/* Initialize 1PPS data structures */
-#define MAX_PIN_NUM	8
-	tstamp->pps_pin_caps = kzalloc(sizeof(u8) * MAX_PIN_NUM, GFP_KERNEL);
-	if (tstamp->pps_pin_caps) {
-		if (MLX5_CAP_GEN(priv->mdev, pps))
-			mlx5e_get_pps_caps(priv, tstamp);
-		if (tstamp->ptp_info.n_pins)
-			mlx5e_init_pin_config(tstamp);
-	} else {
-		mlx5_core_warn(priv->mdev, "1PPS initialization failed\n");
-	}
+	if (MLX5_PPS_CAP(priv->mdev))
+		mlx5e_get_pps_caps(priv, tstamp);
+	if (tstamp->ptp_info.n_pins)
+		mlx5e_init_pin_config(tstamp);
 
 	tstamp->ptp = ptp_clock_register(&tstamp->ptp_info,
 					 &priv->mdev->pdev->dev);
@@ -517,8 +614,7 @@ void mlx5e_timestamp_cleanup(struct mlx5e_priv *priv)
 		priv->tstamp.ptp = NULL;
 	}
 
-	kfree(tstamp->pps_pin_caps);
-	kfree(tstamp->ptp_info.pin_config);
-
+	cancel_work_sync(&tstamp->pps_info.out_work);
 	cancel_delayed_work_sync(&tstamp->overflow_work);
+	kfree(tstamp->ptp_info.pin_config);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 85bf4a389295..986387de13ee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -276,7 +276,7 @@ static void add_rule_to_list(struct mlx5e_priv *priv,
 
 static bool outer_header_zero(u32 *match_criteria)
 {
-	int size = MLX5_ST_SZ_BYTES(fte_match_param);
+	int size = MLX5_FLD_SZ_BYTES(fte_match_param, outer_headers);
 	char *outer_headers_c = MLX5_ADDR_OF(fte_match_param, match_criteria,
 					     outer_headers);
 
@@ -320,7 +320,7 @@ add_ethtool_flow_rule(struct mlx5e_priv *priv,
 
 	spec->match_criteria_enable = (!outer_header_zero(spec->match_criteria));
 	flow_act.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
-	rule = mlx5_add_flow_rules(ft, spec, &flow_act, dst, 1);
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, dst, dst ? 1 : 0);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
 		netdev_err(priv->netdev, "%s: failed to add ethtool steering rule: %d\n",
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 7819fe9ede22..072aa8a13a0a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -365,7 +365,6 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv,
 		break;
 	case MLX5_DEV_EVENT_PPS:
 		eqe = (struct mlx5_eqe *)param;
-		ptp_event.type = PTP_CLOCK_EXTTS;
 		ptp_event.index = eqe->data.pps.pin;
 		ptp_event.timestamp =
 			timecounter_cyc2time(&priv->tstamp.clock,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 33eae5ad2fb0..58a9f5c96d10 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -690,7 +690,7 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev)
 	else
 		mlx5_core_dbg(dev, "port_module_event is not set\n");
 
-	if (MLX5_CAP_GEN(dev, pps))
+	if (MLX5_PPS_CAP(dev))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_PPS_EVENT);
 
 	err = mlx5_create_map_eq(dev, &table->cmd_eq, MLX5_EQ_VEC_CMD,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c
index cc1858752e70..6d90e9e3bfd1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c
@@ -160,8 +160,6 @@ static int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core
 
 static void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp)
 {
-	mlx5_fs_remove_rx_underlay_qpn(mdev, qp->qpn);
-
 	mlx5_core_destroy_qp(mdev, qp);
 }
 
@@ -176,8 +174,6 @@ static int mlx5i_init_tx(struct mlx5e_priv *priv)
 		return err;
 	}
 
-	mlx5_fs_add_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn);
-
 	err = mlx5e_create_tis(priv->mdev, 0 /* tc */, ipriv->qp.qpn, &priv->tisn[0]);
 	if (err) {
 		mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err);
@@ -235,6 +231,7 @@ static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv)
 
 static int mlx5i_init_rx(struct mlx5e_priv *priv)
 {
+	struct mlx5i_priv *ipriv  = priv->ppriv;
 	int err;
 
 	err = mlx5e_create_indirect_rqt(priv);
@@ -253,12 +250,18 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
 	if (err)
 		goto err_destroy_indirect_tirs;
 
-	err = mlx5i_create_flow_steering(priv);
+	err = mlx5_fs_add_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn);
 	if (err)
 		goto err_destroy_direct_tirs;
 
+	err = mlx5i_create_flow_steering(priv);
+	if (err)
+		goto err_remove_rx_underlay_qpn;
+
 	return 0;
 
+err_remove_rx_underlay_qpn:
+	mlx5_fs_remove_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn);
 err_destroy_direct_tirs:
 	mlx5e_destroy_direct_tirs(priv);
 err_destroy_indirect_tirs:
@@ -272,6 +275,9 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
 
 static void mlx5i_cleanup_rx(struct mlx5e_priv *priv)
 {
+	struct mlx5i_priv *ipriv  = priv->ppriv;
+
+	mlx5_fs_remove_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn);
 	mlx5i_destroy_flow_steering(priv);
 	mlx5e_destroy_direct_tirs(priv);
 	mlx5e_destroy_indirect_tirs(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index b5d5519542e8..0ca4623bda6b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -157,22 +157,17 @@ static bool mlx5_lag_is_bonded(struct mlx5_lag *ldev)
 static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker,
 					   u8 *port1, u8 *port2)
 {
-	if (tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) {
-		if (tracker->netdev_state[0].tx_enabled) {
-			*port1 = 1;
-			*port2 = 1;
-		} else {
-			*port1 = 2;
-			*port2 = 2;
-		}
-	} else {
-		*port1 = 1;
-		*port2 = 2;
-		if (!tracker->netdev_state[0].link_up)
-			*port1 = 2;
-		else if (!tracker->netdev_state[1].link_up)
-			*port2 = 1;
+	*port1 = 1;
+	*port2 = 2;
+	if (!tracker->netdev_state[0].tx_enabled ||
+	    !tracker->netdev_state[0].link_up) {
+		*port1 = 2;
+		return;
 	}
+
+	if (!tracker->netdev_state[1].tx_enabled ||
+	    !tracker->netdev_state[1].link_up)
+		*port2 = 1;
 }
 
 static void mlx5_activate_lag(struct mlx5_lag *ldev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index fbc6e9e9e305..1874aa96c1a1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -153,6 +153,11 @@ int mlx5_set_mtpps(struct mlx5_core_dev *mdev, u32 *mtpps, u32 mtpps_size);
 int mlx5_query_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 *arm, u8 *mode);
 int mlx5_set_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 arm, u8 mode);
 
+#define MLX5_PPS_CAP(mdev) (MLX5_CAP_GEN((mdev), pps) &&		\
+			    MLX5_CAP_GEN((mdev), pps_modify) &&		\
+			    MLX5_CAP_MCAM_FEATURE((mdev), mtpps_fs) &&	\
+			    MLX5_CAP_MCAM_FEATURE((mdev), mtpps_enh_out_per_adj))
+
 void mlx5e_init(void);
 void mlx5e_cleanup(void);
 
diff --git a/drivers/net/irda/mcs7780.c b/drivers/net/irda/mcs7780.c
index 6f6ed75b63c9..765de3bedb88 100644
--- a/drivers/net/irda/mcs7780.c
+++ b/drivers/net/irda/mcs7780.c
@@ -141,9 +141,19 @@ static int mcs_set_reg(struct mcs_cb *mcs, __u16 reg, __u16 val)
 static int mcs_get_reg(struct mcs_cb *mcs, __u16 reg, __u16 * val)
 {
 	struct usb_device *dev = mcs->usbdev;
-	int ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), MCS_RDREQ,
-				  MCS_RD_RTYPE, 0, reg, val, 2,
-				  msecs_to_jiffies(MCS_CTRL_TIMEOUT));
+	void *dmabuf;
+	int ret;
+
+	dmabuf = kmalloc(sizeof(__u16), GFP_KERNEL);
+	if (!dmabuf)
+		return -ENOMEM;
+
+	ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), MCS_RDREQ,
+			      MCS_RD_RTYPE, 0, reg, dmabuf, 2,
+			      msecs_to_jiffies(MCS_CTRL_TIMEOUT));
+
+	memcpy(val, dmabuf, sizeof(__u16));
+	kfree(dmabuf);
 
 	return ret;
 }
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index eebb0e1c70ff..b30d9ceee8bc 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -749,6 +749,9 @@ void phy_stop_machine(struct phy_device *phydev)
 	if (phydev->state > PHY_UP && phydev->state != PHY_HALTED)
 		phydev->state = PHY_UP;
 	mutex_unlock(&phydev->lock);
+
+	/* Now we can run the state machine synchronously */
+	phy_state_machine(&phydev->state_queue.work);
 }
 
 /**
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 6633dd4bb649..acb754eb1ccb 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -889,21 +889,20 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi,
 
 	buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
 	buf += headroom; /* advance address leaving hole at front of pkt */
-	ctx = (void *)(unsigned long)len;
 	get_page(alloc_frag->page);
 	alloc_frag->offset += len + headroom;
 	hole = alloc_frag->size - alloc_frag->offset;
 	if (hole < len + headroom) {
 		/* To avoid internal fragmentation, if there is very likely not
 		 * enough space for another buffer, add the remaining space to
-		 * the current buffer. This extra space is not included in
-		 * the truesize stored in ctx.
+		 * the current buffer.
 		 */
 		len += hole;
 		alloc_frag->offset += hole;
 	}
 
 	sg_init_one(rq->sg, buf, len);
+	ctx = (void *)(unsigned long)len;
 	err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
 	if (err < 0)
 		put_page(virt_to_head_page(buf));
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index 5653d6dd38f6..d44f59ef4f72 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -4168,11 +4168,6 @@ struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev)
 		goto fail;
 	}
 
-	/* allocate scatter-gather table. sg support
-	 * will be disabled upon allocation failure.
-	 */
-	brcmf_sdiod_sgtable_alloc(bus->sdiodev);
-
 	/* Query the F2 block size, set roundup accordingly */
 	bus->blocksize = bus->sdiodev->func[2]->cur_blksize;
 	bus->roundup = min(max_roundup, bus->blocksize);
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/tx.c b/drivers/net/wireless/intel/iwlwifi/dvm/tx.c
index 4b97371c3b42..838946d17b59 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/tx.c
@@ -1190,11 +1190,11 @@ void iwlagn_rx_reply_tx(struct iwl_priv *priv, struct iwl_rx_cmd_buffer *rxb)
 				next_reclaimed;
 			IWL_DEBUG_TX_REPLY(priv, "Next reclaimed packet:%d\n",
 						  next_reclaimed);
+			iwlagn_check_ratid_empty(priv, sta_id, tid);
 		}
 
 		iwl_trans_reclaim(priv->trans, txq_id, ssn, &skbs);
 
-		iwlagn_check_ratid_empty(priv, sta_id, tid);
 		freed = 0;
 
 		/* process frames */
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 3c52867dfe28..d145e0d90227 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -1241,6 +1241,8 @@ config SCSI_LPFC
 	tristate "Emulex LightPulse Fibre Channel Support"
 	depends on PCI && SCSI
 	depends on SCSI_FC_ATTRS
+	depends on NVME_TARGET_FC || NVME_TARGET_FC=n
+	depends on NVME_FC || NVME_FC=n
 	select CRC_T10DIF
 	---help---
           This lpfc driver supports the Emulex LightPulse
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index beb5f098f32d..05804227234d 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -437,7 +437,7 @@ static int scatter_data_area(struct tcmu_dev *udev,
 			to_offset = get_block_offset_user(udev, dbi,
 					block_remaining);
 			offset = DATA_BLOCK_SIZE - block_remaining;
-			to = (void *)(unsigned long)to + offset;
+			to += offset;
 
 			if (*iov_cnt != 0 &&
 			    to_offset == iov_tail(udev, *iov)) {
@@ -510,7 +510,7 @@ static void gather_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd,
 			copy_bytes = min_t(size_t, sg_remaining,
 					block_remaining);
 			offset = DATA_BLOCK_SIZE - block_remaining;
-			from = (void *)(unsigned long)from + offset;
+			from += offset;
 			tcmu_flush_dcache_range(from, copy_bytes);
 			memcpy(to + sg->length - sg_remaining, from,
 					copy_bytes);
@@ -699,25 +699,24 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
 		size_t pad_size = head_to_end(cmd_head, udev->cmdr_size);
 
 		entry = (void *) mb + CMDR_OFF + cmd_head;
-		tcmu_flush_dcache_range(entry, sizeof(*entry));
 		tcmu_hdr_set_op(&entry->hdr.len_op, TCMU_OP_PAD);
 		tcmu_hdr_set_len(&entry->hdr.len_op, pad_size);
 		entry->hdr.cmd_id = 0; /* not used for PAD */
 		entry->hdr.kflags = 0;
 		entry->hdr.uflags = 0;
+		tcmu_flush_dcache_range(entry, sizeof(*entry));
 
 		UPDATE_HEAD(mb->cmd_head, pad_size, udev->cmdr_size);
+		tcmu_flush_dcache_range(mb, sizeof(*mb));
 
 		cmd_head = mb->cmd_head % udev->cmdr_size; /* UAM */
 		WARN_ON(cmd_head != 0);
 	}
 
 	entry = (void *) mb + CMDR_OFF + cmd_head;
-	tcmu_flush_dcache_range(entry, sizeof(*entry));
+	memset(entry, 0, command_size);
 	tcmu_hdr_set_op(&entry->hdr.len_op, TCMU_OP_CMD);
 	entry->hdr.cmd_id = tcmu_cmd->cmd_id;
-	entry->hdr.kflags = 0;
-	entry->hdr.uflags = 0;
 
 	/* Handle allocating space from the data area */
 	tcmu_cmd_reset_dbi_cur(tcmu_cmd);
@@ -736,11 +735,10 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 	entry->req.iov_cnt = iov_cnt;
-	entry->req.iov_dif_cnt = 0;
 
 	/* Handle BIDI commands */
+	iov_cnt = 0;
 	if (se_cmd->se_cmd_flags & SCF_BIDI) {
-		iov_cnt = 0;
 		iov++;
 		ret = scatter_data_area(udev, tcmu_cmd,
 					se_cmd->t_bidi_data_sg,
@@ -753,8 +751,8 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
 			pr_err("tcmu: alloc and scatter bidi data failed\n");
 			return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 		}
-		entry->req.iov_bidi_cnt = iov_cnt;
 	}
+	entry->req.iov_bidi_cnt = iov_cnt;
 
 	/*
 	 * Recalaulate the command's base size and size according
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 33d979e9ea2a..83eecd33ad96 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4776,10 +4776,6 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig,
 		else
 			flush = BTRFS_RESERVE_NO_FLUSH;
 		spin_lock(&space_info->lock);
-		if (can_overcommit(root, space_info, orig, flush)) {
-			spin_unlock(&space_info->lock);
-			break;
-		}
 		if (list_empty(&space_info->tickets) &&
 		    list_empty(&space_info->priority_tickets)) {
 			spin_unlock(&space_info->lock);
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 3ec0e46de95f..22a8d532cca6 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -193,13 +193,6 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type,
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
-		if (acl) {
-			error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
-			if (error)
-				return error;
-			inode->i_ctime = current_time(inode);
-			ext4_mark_inode_dirty(handle, inode);
-		}
 		break;
 
 	case ACL_TYPE_DEFAULT:
@@ -221,8 +214,9 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type,
 				      value, size, 0);
 
 	kfree(value);
-	if (!error)
+	if (!error) {
 		set_cached_acl(inode, type, acl);
+	}
 
 	return error;
 }
@@ -232,6 +226,8 @@ ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
 	handle_t *handle;
 	int error, retries = 0;
+	umode_t mode = inode->i_mode;
+	int update_mode = 0;
 
 	error = dquot_initialize(inode);
 	if (error)
@@ -242,7 +238,20 @@ ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
+	if ((type == ACL_TYPE_ACCESS) && acl) {
+		error = posix_acl_update_mode(inode, &mode, &acl);
+		if (error)
+			goto out_stop;
+		update_mode = 1;
+	}
+
 	error = __ext4_set_acl(handle, inode, type, acl);
+	if (!error && update_mode) {
+		inode->i_mode = mode;
+		inode->i_ctime = current_time(inode);
+		ext4_mark_inode_dirty(handle, inode);
+	}
+out_stop:
 	ext4_journal_stop(handle);
 	if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
 		goto retry;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 02ce7e7bbdf5..407fc5aa32a7 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -521,6 +521,8 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 				lastoff = page_offset(page);
 				bh = head = page_buffers(page);
 				do {
+					if (lastoff + bh->b_size <= startoff)
+						goto next;
 					if (buffer_uptodate(bh) ||
 					    buffer_unwritten(bh)) {
 						if (whence == SEEK_DATA)
@@ -535,6 +537,7 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 						unlock_page(page);
 						goto out;
 					}
+next:
 					lastoff += bh->b_size;
 					bh = bh->b_this_page;
 				} while (bh != head);
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index c3ed9021b781..035cd3f4785e 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1927,7 +1927,8 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
 			n_desc_blocks = o_desc_blocks +
 				le16_to_cpu(es->s_reserved_gdt_blocks);
 			n_group = n_desc_blocks * EXT4_DESC_PER_BLOCK(sb);
-			n_blocks_count = n_group * EXT4_BLOCKS_PER_GROUP(sb);
+			n_blocks_count = (ext4_fsblk_t)n_group *
+				EXT4_BLOCKS_PER_GROUP(sb);
 			n_group--; /* set to last group number */
 		}
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index f5a7faac39a7..074169a54162 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7407,7 +7407,7 @@ static void nfs4_exchange_id_done(struct rpc_task *task, void *data)
 			cdata->res.server_scope = NULL;
 		}
 		/* Save the EXCHANGE_ID verifier session trunk tests */
-		memcpy(clp->cl_confirm.data, cdata->args.verifier->data,
+		memcpy(clp->cl_confirm.data, cdata->args.verifier.data,
 		       sizeof(clp->cl_confirm.data));
 	}
 out:
@@ -7444,7 +7444,6 @@ static const struct rpc_call_ops nfs4_exchange_id_call_ops = {
 static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
 			u32 sp4_how, struct rpc_xprt *xprt)
 {
-	nfs4_verifier verifier;
 	struct rpc_message msg = {
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_EXCHANGE_ID],
 		.rpc_cred = cred,
@@ -7468,8 +7467,7 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
 		return -ENOMEM;
 	}
 
-	if (!xprt)
-		nfs4_init_boot_verifier(clp, &verifier);
+	nfs4_init_boot_verifier(clp, &calldata->args.verifier);
 
 	status = nfs4_init_uniform_client_string(clp);
 	if (status)
@@ -7510,9 +7508,8 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
 		task_setup_data.rpc_xprt = xprt;
 		task_setup_data.flags =
 				RPC_TASK_SOFT|RPC_TASK_SOFTCONN|RPC_TASK_ASYNC;
-		calldata->args.verifier = &clp->cl_confirm;
-	} else {
-		calldata->args.verifier = &verifier;
+		memcpy(calldata->args.verifier.data, clp->cl_confirm.data,
+				sizeof(calldata->args.verifier.data));
 	}
 	calldata->args.client = clp;
 #ifdef CONFIG_NFS_V4_1_MIGRATION
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 3aebfdc82b30..b0cbee2b2422 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1765,7 +1765,7 @@ static void encode_exchange_id(struct xdr_stream *xdr,
 	int len = 0;
 
 	encode_op_hdr(xdr, OP_EXCHANGE_ID, decode_exchange_id_maxsz, hdr);
-	encode_nfs4_verifier(xdr, args->verifier);
+	encode_nfs4_verifier(xdr, &args->verifier);
 
 	encode_string(xdr, strlen(args->client->cl_owner_id),
 			args->client->cl_owner_id);
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index dc22ba8c710f..e50a387959bf 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -240,18 +240,6 @@ int ocfs2_set_acl(handle_t *handle,
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name_index = OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS;
-		if (acl) {
-			umode_t mode;
-
-			ret = posix_acl_update_mode(inode, &mode, &acl);
-			if (ret)
-				return ret;
-
-			ret = ocfs2_acl_set_mode(inode, di_bh,
-						 handle, mode);
-			if (ret)
-				return ret;
-		}
 		break;
 	case ACL_TYPE_DEFAULT:
 		name_index = OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT;
@@ -289,7 +277,19 @@ int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	had_lock = ocfs2_inode_lock_tracker(inode, &bh, 1, &oh);
 	if (had_lock < 0)
 		return had_lock;
+	if (type == ACL_TYPE_ACCESS && acl) {
+		umode_t mode;
+
+		status = posix_acl_update_mode(inode, &mode, &acl);
+		if (status)
+			goto unlock;
+
+		status = ocfs2_acl_set_mode(inode, bh, NULL, mode);
+		if (status)
+			goto unlock;
+	}
 	status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL);
+unlock:
 	ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock);
 	brelse(bh);
 	return status;
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 1d622f276e3a..26f9591b04b1 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -851,6 +851,9 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 	__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, &range);
 	spin_unlock(&ctx->fault_pending_wqh.lock);
 
+	/* Flush pending events that may still wait on event_wqh */
+	wake_up_all(&ctx->event_wqh);
+
 	wake_up_poll(&ctx->fd_wqh, POLLHUP);
 	userfaultfd_ctx_put(ctx);
 	return 0;
@@ -1645,6 +1648,8 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
 		ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start,
 				     uffdio_zeropage.range.len);
 		mmput(ctx->mm);
+	} else {
+		return -ENOSPC;
 	}
 	if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
 		return -EFAULT;
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 0f2a80377520..30b86efea2bc 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -58,7 +58,6 @@ enum cpuhp_state {
 	CPUHP_XEN_EVTCHN_PREPARE,
 	CPUHP_ARM_SHMOBILE_SCU_PREPARE,
 	CPUHP_SH_SH3X_PREPARE,
-	CPUHP_BLK_MQ_PREPARE,
 	CPUHP_NET_FLOW_PREPARE,
 	CPUHP_TOPOLOGY_PREPARE,
 	CPUHP_NET_IUCV_PREPARE,
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 119a3f9604b0..898cfe2eeb42 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -18,6 +18,19 @@
 
 #ifdef CONFIG_CPUSETS
 
+/*
+ * Static branch rewrites can happen in an arbitrary order for a given
+ * key. In code paths where we need to loop with read_mems_allowed_begin() and
+ * read_mems_allowed_retry() to get a consistent view of mems_allowed, we need
+ * to ensure that begin() always gets rewritten before retry() in the
+ * disabled -> enabled transition. If not, then if local irqs are disabled
+ * around the loop, we can deadlock since retry() would always be
+ * comparing the latest value of the mems_allowed seqcount against 0 as
+ * begin() still would see cpusets_enabled() as false. The enabled -> disabled
+ * transition should happen in reverse order for the same reasons (want to stop
+ * looking at real value of mems_allowed.sequence in retry() first).
+ */
+extern struct static_key_false cpusets_pre_enable_key;
 extern struct static_key_false cpusets_enabled_key;
 static inline bool cpusets_enabled(void)
 {
@@ -32,12 +45,14 @@ static inline int nr_cpusets(void)
 
 static inline void cpuset_inc(void)
 {
+	static_branch_inc(&cpusets_pre_enable_key);
 	static_branch_inc(&cpusets_enabled_key);
 }
 
 static inline void cpuset_dec(void)
 {
 	static_branch_dec(&cpusets_enabled_key);
+	static_branch_dec(&cpusets_pre_enable_key);
 }
 
 extern int cpuset_init(void);
@@ -115,7 +130,7 @@ extern void cpuset_print_current_mems_allowed(void);
  */
 static inline unsigned int read_mems_allowed_begin(void)
 {
-	if (!cpusets_enabled())
+	if (!static_branch_unlikely(&cpusets_pre_enable_key))
 		return 0;
 
 	return read_seqcount_begin(&current->mems_allowed_seq);
@@ -129,7 +144,7 @@ static inline unsigned int read_mems_allowed_begin(void)
  */
 static inline bool read_mems_allowed_retry(unsigned int seq)
 {
-	if (!cpusets_enabled())
+	if (!static_branch_unlikely(&cpusets_enabled_key))
 		return false;
 
 	return read_seqcount_retry(&current->mems_allowed_seq, seq);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index edafedb7b509..e21a0b3d6454 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -7718,8 +7718,10 @@ struct mlx5_ifc_pcam_reg_bits {
 };
 
 struct mlx5_ifc_mcam_enhanced_features_bits {
-	u8         reserved_at_0[0x7f];
+	u8         reserved_at_0[0x7d];
 
+	u8         mtpps_enh_out_per_adj[0x1];
+	u8         mtpps_fs[0x1];
 	u8         pcie_performance_group[0x1];
 };
 
@@ -8115,7 +8117,8 @@ struct mlx5_ifc_mtpps_reg_bits {
 	u8         reserved_at_78[0x4];
 	u8         cap_pin_4_mode[0x4];
 
-	u8         reserved_at_80[0x80];
+	u8         field_select[0x20];
+	u8         reserved_at_a0[0x60];
 
 	u8         enable[0x1];
 	u8         reserved_at_101[0xb];
@@ -8130,8 +8133,9 @@ struct mlx5_ifc_mtpps_reg_bits {
 
 	u8         out_pulse_duration[0x10];
 	u8         out_periodic_adjustment[0x10];
+	u8         enhanced_out_periodic_adjustment[0x20];
 
-	u8         reserved_at_1a0[0x60];
+	u8         reserved_at_1c0[0x20];
 };
 
 struct mlx5_ifc_mtppse_reg_bits {
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 45cdb27791a3..ab8f7e11c160 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -494,6 +494,10 @@ struct mm_struct {
 	 * PROT_NONE or PROT_NUMA mapped page.
 	 */
 	bool tlb_flush_pending;
+#endif
+#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+	/* See flush_tlb_batched_pending() */
+	bool tlb_flush_batched;
 #endif
 	struct uprobes_state uprobes_state;
 #ifdef CONFIG_HUGETLB_PAGE
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index b28c83475ee8..7882a07d973e 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1222,7 +1222,7 @@ struct nfs41_state_protection {
 
 struct nfs41_exchange_id_args {
 	struct nfs_client		*client;
-	nfs4_verifier			*verifier;
+	nfs4_verifier			verifier;
 	u32				flags;
 	struct nfs41_state_protection	state_protect;
 };
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index c102ef65cb64..db6dc9dc0482 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -323,6 +323,7 @@ enum {
 
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
 	__WQ_ORDERED		= 1 << 17, /* internal: workqueue is ordered */
+	__WQ_ORDERED_EXPLICIT	= 1 << 18, /* internal: alloc_ordered_workqueue() */
 	__WQ_LEGACY		= 1 << 18, /* internal: create*_workqueue() */
 
 	WQ_MAX_ACTIVE		= 512,	  /* I like 512, better ideas? */
@@ -422,7 +423,8 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
  * Pointer to the allocated workqueue on success, %NULL on failure.
  */
 #define alloc_ordered_workqueue(fmt, flags, args...)			\
-	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
+	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED |		\
+			__WQ_ORDERED_EXPLICIT | (flags), 1, ##args)
 
 #define create_workqueue(name)						\
 	alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name))
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 069582ee5d7f..06db0c3ec384 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -469,6 +469,8 @@ _sctp_walk_params((pos), (chunk), ntohs((chunk)->chunk_hdr.length), member)
 
 #define _sctp_walk_params(pos, chunk, end, member)\
 for (pos.v = chunk->member;\
+     (pos.v + offsetof(struct sctp_paramhdr, length) + sizeof(pos.p->length) <=\
+      (void *)chunk + end) &&\
      pos.v <= (void *)chunk + end - ntohs(pos.p->length) &&\
      ntohs(pos.p->length) >= sizeof(sctp_paramhdr_t);\
      pos.v += SCTP_PAD4(ntohs(pos.p->length)))
@@ -479,6 +481,8 @@ _sctp_walk_errors((err), (chunk_hdr), ntohs((chunk_hdr)->length))
 #define _sctp_walk_errors(err, chunk_hdr, end)\
 for (err = (sctp_errhdr_t *)((void *)chunk_hdr + \
 	    sizeof(sctp_chunkhdr_t));\
+     ((void *)err + offsetof(sctp_errhdr_t, length) + sizeof(err->length) <=\
+      (void *)chunk_hdr + end) &&\
      (void *)err <= (void *)chunk_hdr + end - ntohs(err->length) &&\
      ntohs(err->length) >= sizeof(sctp_errhdr_t); \
      err = (sctp_errhdr_t *)((void *)err + SCTP_PAD4(ntohs(err->length))))
diff --git a/include/net/udp.h b/include/net/udp.h
index 3391dbd73959..1933442cf1a6 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -265,6 +265,7 @@ static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags,
 }
 
 void udp_v4_early_demux(struct sk_buff *skb);
+void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst);
 int udp_get_port(struct sock *sk, unsigned short snum,
 		 int (*saddr_cmp)(const struct sock *,
 				  const struct sock *));
diff --git a/include/sound/soc.h b/include/sound/soc.h
index 5170fd81e1fd..375893d8d4a5 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -795,10 +795,6 @@ struct snd_soc_component_driver {
 	int (*suspend)(struct snd_soc_component *);
 	int (*resume)(struct snd_soc_component *);
 
-	/* pcm creation and destruction */
-	int (*pcm_new)(struct snd_soc_pcm_runtime *);
-	void (*pcm_free)(struct snd_pcm *);
-
 	/* DT */
 	int (*of_xlate_dai_name)(struct snd_soc_component *component,
 				 struct of_phandle_args *args,
@@ -872,8 +868,6 @@ struct snd_soc_component {
 	void (*remove)(struct snd_soc_component *);
 	int (*suspend)(struct snd_soc_component *);
 	int (*resume)(struct snd_soc_component *);
-	int (*pcm_new)(struct snd_soc_pcm_runtime *);
-	void (*pcm_free)(struct snd_pcm *);
 
 	/* machine specific init */
 	int (*init)(struct snd_soc_component *component);
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index 00f4d6bf048f..7a01568e5e22 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -33,6 +33,9 @@ struct cgroup_taskset {
 	struct list_head	src_csets;
 	struct list_head	dst_csets;
 
+	/* the number of tasks in the set */
+	int			nr_tasks;
+
 	/* the subsys currently being processed */
 	int			ssid;
 
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 8d4e85eae42c..2c62e4b3f198 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1948,6 +1948,8 @@ static void cgroup_migrate_add_task(struct task_struct *task,
 	if (!cset->mg_src_cgrp)
 		return;
 
+	mgctx->tset.nr_tasks++;
+
 	list_move_tail(&task->cg_list, &cset->mg_tasks);
 	if (list_empty(&cset->mg_node))
 		list_add_tail(&cset->mg_node,
@@ -2036,21 +2038,19 @@ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx)
 	struct css_set *cset, *tmp_cset;
 	int ssid, failed_ssid, ret;
 
-	/* methods shouldn't be called if no task is actually migrating */
-	if (list_empty(&tset->src_csets))
-		return 0;
-
 	/* check that we can legitimately attach to the cgroup */
-	do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
-		if (ss->can_attach) {
-			tset->ssid = ssid;
-			ret = ss->can_attach(tset);
-			if (ret) {
-				failed_ssid = ssid;
-				goto out_cancel_attach;
+	if (tset->nr_tasks) {
+		do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
+			if (ss->can_attach) {
+				tset->ssid = ssid;
+				ret = ss->can_attach(tset);
+				if (ret) {
+					failed_ssid = ssid;
+					goto out_cancel_attach;
+				}
 			}
-		}
-	} while_each_subsys_mask();
+		} while_each_subsys_mask();
+	}
 
 	/*
 	 * Now that we're guaranteed success, proceed to move all tasks to
@@ -2077,25 +2077,29 @@ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx)
 	 */
 	tset->csets = &tset->dst_csets;
 
-	do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
-		if (ss->attach) {
-			tset->ssid = ssid;
-			ss->attach(tset);
-		}
-	} while_each_subsys_mask();
+	if (tset->nr_tasks) {
+		do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
+			if (ss->attach) {
+				tset->ssid = ssid;
+				ss->attach(tset);
+			}
+		} while_each_subsys_mask();
+	}
 
 	ret = 0;
 	goto out_release_tset;
 
 out_cancel_attach:
-	do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
-		if (ssid == failed_ssid)
-			break;
-		if (ss->cancel_attach) {
-			tset->ssid = ssid;
-			ss->cancel_attach(tset);
-		}
-	} while_each_subsys_mask();
+	if (tset->nr_tasks) {
+		do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
+			if (ssid == failed_ssid)
+				break;
+			if (ss->cancel_attach) {
+				tset->ssid = ssid;
+				ss->cancel_attach(tset);
+			}
+		} while_each_subsys_mask();
+	}
 out_release_tset:
 	spin_lock_irq(&css_set_lock);
 	list_splice_init(&tset->dst_csets, &tset->src_csets);
@@ -2917,11 +2921,11 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
 	cgrp->subtree_control &= ~disable;
 
 	ret = cgroup_apply_control(cgrp);
-
 	cgroup_finalize_control(cgrp, ret);
+	if (ret)
+		goto out_unlock;
 
 	kernfs_activate(cgrp->kn);
-	ret = 0;
 out_unlock:
 	cgroup_kn_unlock(of->kn);
 	return ret ?: nbytes;
@@ -4574,6 +4578,10 @@ int __init cgroup_init(void)
 
 		if (ss->bind)
 			ss->bind(init_css_set.subsys[ssid]);
+
+		mutex_lock(&cgroup_mutex);
+		css_populate_dir(init_css_set.subsys[ssid]);
+		mutex_unlock(&cgroup_mutex);
 	}
 
 	/* init_css_set.subsys[] has been updated, re-hash */
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index ae643412948a..8f26927f16a1 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -63,6 +63,7 @@
 #include <linux/cgroup.h>
 #include <linux/wait.h>
 
+DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key);
 DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key);
 
 /* See "Frequency meter" comments, below. */
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 152a706ef8b8..d3f33020a06b 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1495,7 +1495,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 		base->is_idle = false;
 	} else {
 		if (!is_max_delta)
-			expires = basem + (nextevt - basej) * TICK_NSEC;
+			expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
 		/*
 		 * If we expect to sleep more than a tick, mark the base idle:
 		 */
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index c74bf39ef764..6effbcb7a3d6 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3744,8 +3744,12 @@ static int apply_workqueue_attrs_locked(struct workqueue_struct *wq,
 		return -EINVAL;
 
 	/* creating multiple pwqs breaks ordering guarantee */
-	if (WARN_ON((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs)))
-		return -EINVAL;
+	if (!list_empty(&wq->pwqs)) {
+		if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
+			return -EINVAL;
+
+		wq->flags &= ~__WQ_ORDERED;
+	}
 
 	ctx = apply_wqattrs_prepare(wq, attrs);
 	if (!ctx)
@@ -3929,6 +3933,16 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
 	struct workqueue_struct *wq;
 	struct pool_workqueue *pwq;
 
+	/*
+	 * Unbound && max_active == 1 used to imply ordered, which is no
+	 * longer the case on NUMA machines due to per-node pools.  While
+	 * alloc_ordered_workqueue() is the right way to create an ordered
+	 * workqueue, keep the previous behavior to avoid subtle breakages
+	 * on NUMA.
+	 */
+	if ((flags & WQ_UNBOUND) && max_active == 1)
+		flags |= __WQ_ORDERED;
+
 	/* see the comment above the definition of WQ_POWER_EFFICIENT */
 	if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
 		flags |= WQ_UNBOUND;
@@ -4119,13 +4133,14 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
 	struct pool_workqueue *pwq;
 
 	/* disallow meddling with max_active for ordered workqueues */
-	if (WARN_ON(wq->flags & __WQ_ORDERED))
+	if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
 		return;
 
 	max_active = wq_clamp_max_active(max_active, wq->flags, wq->name);
 
 	mutex_lock(&wq->mutex);
 
+	wq->flags &= ~__WQ_ORDERED;
 	wq->saved_max_active = max_active;
 
 	for_each_pwq(pwq, wq)
@@ -5253,7 +5268,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq)
 	 * attributes breaks ordering guarantee.  Disallow exposing ordered
 	 * workqueues.
 	 */
-	if (WARN_ON(wq->flags & __WQ_ORDERED))
+	if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
 		return -EINVAL;
 
 	wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 3eedb187e549..cc289933f462 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4095,6 +4095,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long vaddr = *position;
 	unsigned long remainder = *nr_pages;
 	struct hstate *h = hstate_vma(vma);
+	int err = -EFAULT;
 
 	while (vaddr < vma->vm_end && remainder) {
 		pte_t *pte;
@@ -4170,11 +4171,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			}
 			ret = hugetlb_fault(mm, vma, vaddr, fault_flags);
 			if (ret & VM_FAULT_ERROR) {
-				int err = vm_fault_to_errno(ret, flags);
-
-				if (err)
-					return err;
-
+				err = vm_fault_to_errno(ret, flags);
 				remainder = 0;
 				break;
 			}
@@ -4229,7 +4226,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 */
 	*position = vaddr;
 
-	return i ? i : -EFAULT;
+	return i ? i : err;
 }
 
 #ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE
diff --git a/mm/internal.h b/mm/internal.h
index 0e4f558412fb..9c8a2bfb975c 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -498,6 +498,7 @@ extern struct workqueue_struct *mm_percpu_wq;
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 void try_to_unmap_flush(void);
 void try_to_unmap_flush_dirty(void);
+void flush_tlb_batched_pending(struct mm_struct *mm);
 #else
 static inline void try_to_unmap_flush(void)
 {
@@ -505,7 +506,9 @@ static inline void try_to_unmap_flush(void)
 static inline void try_to_unmap_flush_dirty(void)
 {
 }
-
+static inline void flush_tlb_batched_pending(struct mm_struct *mm)
+{
+}
 #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */
 
 extern const struct trace_print_flags pageflag_names[];
diff --git a/mm/madvise.c b/mm/madvise.c
index 25b78ee4fc2c..75d2cffbe61d 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -320,6 +320,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 
 	tlb_remove_check_page_size_change(tlb, PAGE_SIZE);
 	orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+	flush_tlb_batched_pending(mm);
 	arch_enter_lazy_mmu_mode();
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
 		ptent = *pte;
diff --git a/mm/memory.c b/mm/memory.c
index bb11c474857e..b0c3d1556a94 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1197,6 +1197,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	init_rss_vec(rss);
 	start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
 	pte = start_pte;
+	flush_tlb_batched_pending(mm);
 	arch_enter_lazy_mmu_mode();
 	do {
 		pte_t ptent = *pte;
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 8edd0d576254..f42749e6bf4e 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -66,6 +66,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	    atomic_read(&vma->vm_mm->mm_users) == 1)
 		target_node = numa_node_id();
 
+	flush_tlb_batched_pending(vma->vm_mm);
 	arch_enter_lazy_mmu_mode();
 	do {
 		oldpte = *pte;
diff --git a/mm/mremap.c b/mm/mremap.c
index cd8a1b199ef9..3f23715d3c69 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -152,6 +152,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	new_ptl = pte_lockptr(mm, new_pmd);
 	if (new_ptl != old_ptl)
 		spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
+	flush_tlb_batched_pending(vma->vm_mm);
 	arch_enter_lazy_mmu_mode();
 
 	for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE,
@@ -428,6 +429,7 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr,
 static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
 		unsigned long new_addr, unsigned long new_len, bool *locked,
 		struct vm_userfaultfd_ctx *uf,
+		struct list_head *uf_unmap_early,
 		struct list_head *uf_unmap)
 {
 	struct mm_struct *mm = current->mm;
@@ -446,7 +448,7 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
 	if (addr + old_len > new_addr && new_addr + new_len > addr)
 		goto out;
 
-	ret = do_munmap(mm, new_addr, new_len, NULL);
+	ret = do_munmap(mm, new_addr, new_len, uf_unmap_early);
 	if (ret)
 		goto out;
 
@@ -514,6 +516,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	unsigned long charged = 0;
 	bool locked = false;
 	struct vm_userfaultfd_ctx uf = NULL_VM_UFFD_CTX;
+	LIST_HEAD(uf_unmap_early);
 	LIST_HEAD(uf_unmap);
 
 	if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
@@ -541,7 +544,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 
 	if (flags & MREMAP_FIXED) {
 		ret = mremap_to(addr, old_len, new_addr, new_len,
-				&locked, &uf, &uf_unmap);
+				&locked, &uf, &uf_unmap_early, &uf_unmap);
 		goto out;
 	}
 
@@ -621,6 +624,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	up_write(&current->mm->mmap_sem);
 	if (locked && new_len > old_len)
 		mm_populate(new_addr + old_len, new_len - old_len);
+	userfaultfd_unmap_complete(mm, &uf_unmap_early);
 	mremap_userfaultfd_complete(&uf, addr, new_addr, old_len);
 	userfaultfd_unmap_complete(mm, &uf_unmap);
 	return ret;
diff --git a/mm/rmap.c b/mm/rmap.c
index d405f0e0ee96..9835d19fe143 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -616,6 +616,13 @@ static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
 	cpumask_or(&tlb_ubc->cpumask, &tlb_ubc->cpumask, mm_cpumask(mm));
 	tlb_ubc->flush_required = true;
 
+	/*
+	 * Ensure compiler does not re-order the setting of tlb_flush_batched
+	 * before the PTE is cleared.
+	 */
+	barrier();
+	mm->tlb_flush_batched = true;
+
 	/*
 	 * If the PTE was dirty then it's best to assume it's writable. The
 	 * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush()
@@ -643,6 +650,35 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
 
 	return should_defer;
 }
+
+/*
+ * Reclaim unmaps pages under the PTL but do not flush the TLB prior to
+ * releasing the PTL if TLB flushes are batched. It's possible for a parallel
+ * operation such as mprotect or munmap to race between reclaim unmapping
+ * the page and flushing the page. If this race occurs, it potentially allows
+ * access to data via a stale TLB entry. Tracking all mm's that have TLB
+ * batching in flight would be expensive during reclaim so instead track
+ * whether TLB batching occurred in the past and if so then do a flush here
+ * if required. This will cost one additional flush per reclaim cycle paid
+ * by the first operation at risk such as mprotect and mumap.
+ *
+ * This must be called under the PTL so that an access to tlb_flush_batched
+ * that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise
+ * via the PTL.
+ */
+void flush_tlb_batched_pending(struct mm_struct *mm)
+{
+	if (mm->tlb_flush_batched) {
+		flush_tlb_mm(mm);
+
+		/*
+		 * Do not allow the compiler to re-order the clearing of
+		 * tlb_flush_batched before the tlb is flushed.
+		 */
+		barrier();
+		mm->tlb_flush_batched = false;
+	}
+}
 #else
 static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
 {
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 27fad31784a8..18f9cb9aa87d 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -28,6 +28,7 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg)
 
 	if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
 		return -EFAULT;
+	ifr.ifr_name[IFNAMSIZ-1] = 0;
 
 	error = netdev_get_name(net, ifr.ifr_name, ifr.ifr_ifindex);
 	if (error)
@@ -423,6 +424,8 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 		if (copy_from_user(&iwr, arg, sizeof(iwr)))
 			return -EFAULT;
 
+		iwr.ifr_name[sizeof(iwr.ifr_name) - 1] = 0;
+
 		return wext_handle_ioctl(net, &iwr, cmd, arg);
 	}
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 467a2f4510a7..52bfeb60c886 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1977,7 +1977,8 @@ static int do_setlink(const struct sk_buff *skb,
 		struct sockaddr *sa;
 		int len;
 
-		len = sizeof(sa_family_t) + dev->addr_len;
+		len = sizeof(sa_family_t) + max_t(size_t, dev->addr_len,
+						  sizeof(*sa));
 		sa = kmalloc(len, GFP_KERNEL);
 		if (!sa) {
 			err = -ENOMEM;
@@ -4165,6 +4166,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi
 
 	switch (event) {
 	case NETDEV_REBOOT:
+	case NETDEV_CHANGEADDR:
 	case NETDEV_CHANGENAME:
 	case NETDEV_FEAT_CHANGE:
 	case NETDEV_BONDING_FAILOVER:
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index 1704948e6a12..f227f002c73d 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -1471,9 +1471,12 @@ int dccp_feat_init(struct sock *sk)
 	 * singleton values (which always leads to failure).
 	 * These settings can still (later) be overridden via sockopts.
 	 */
-	if (ccid_get_builtin_ccids(&tx.val, &tx.len) ||
-	    ccid_get_builtin_ccids(&rx.val, &rx.len))
+	if (ccid_get_builtin_ccids(&tx.val, &tx.len))
 		return -ENOBUFS;
+	if (ccid_get_builtin_ccids(&rx.val, &rx.len)) {
+		kfree(tx.val);
+		return -ENOBUFS;
+	}
 
 	if (!dccp_feat_prefer(sysctl_dccp_tx_ccid, tx.val, tx.len) ||
 	    !dccp_feat_prefer(sysctl_dccp_rx_ccid, rx.val, rx.len))
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index f75482bdee9a..97368f229876 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -631,6 +631,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 		goto drop_and_free;
 
 	inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
+	reqsk_put(req);
 	return 0;
 
 drop_and_free:
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 992621172220..cf3e40df4765 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -380,6 +380,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 		goto drop_and_free;
 
 	inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
+	reqsk_put(req);
 	return 0;
 
 drop_and_free:
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 83e3ed258467..3acc8261477c 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1327,13 +1327,14 @@ static struct pernet_operations fib_net_ops = {
 
 void __init ip_fib_init(void)
 {
-	rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL);
-	rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL);
-	rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL);
+	fib_trie_init();
 
 	register_pernet_subsys(&fib_net_ops);
+
 	register_netdevice_notifier(&fib_netdev_notifier);
 	register_inetaddr_notifier(&fib_inetaddr_notifier);
 
-	fib_trie_init();
+	rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL);
+	rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL);
+	rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL);
 }
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index ad9ad4aab5da..ce7bc2e5175a 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1372,7 +1372,7 @@ static int call_fib_nh_notifiers(struct fib_nh *fib_nh,
 		return call_fib_notifiers(dev_net(fib_nh->nh_dev), event_type,
 					  &info.info);
 	case FIB_EVENT_NH_DEL:
-		if ((IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
+		if ((in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
 		     fib_nh->nh_flags & RTNH_F_LINKDOWN) ||
 		    (fib_nh->nh_flags & RTNH_F_DEAD))
 			return call_fib_notifiers(dev_net(fib_nh->nh_dev),
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 0257d965f111..4a97fe20f59e 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -332,6 +332,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	treq->rcv_isn		= ntohl(th->seq) - 1;
 	treq->snt_isn		= cookie;
 	treq->ts_off		= 0;
+	treq->txhash		= net_tx_rndhash();
 	req->mss		= mss;
 	ireq->ir_num		= ntohs(th->dest);
 	ireq->ir_rmt_port	= th->source;
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index b89bce4c721e..96c95c8d981e 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -113,7 +113,8 @@ struct bbr {
 		cwnd_gain:10,	/* current gain for setting cwnd */
 		full_bw_cnt:3,	/* number of rounds without large bw gains */
 		cycle_idx:3,	/* current index in pacing_gain cycle array */
-		unused_b:6;
+		has_seen_rtt:1, /* have we seen an RTT sample yet? */
+		unused_b:5;
 	u32	prior_cwnd;	/* prior cwnd upon entering loss recovery */
 	u32	full_bw;	/* recent bw, to estimate if pipe is full */
 };
@@ -212,6 +213,35 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain)
 	return rate >> BW_SCALE;
 }
 
+/* Convert a BBR bw and gain factor to a pacing rate in bytes per second. */
+static u32 bbr_bw_to_pacing_rate(struct sock *sk, u32 bw, int gain)
+{
+	u64 rate = bw;
+
+	rate = bbr_rate_bytes_per_sec(sk, rate, gain);
+	rate = min_t(u64, rate, sk->sk_max_pacing_rate);
+	return rate;
+}
+
+/* Initialize pacing rate to: high_gain * init_cwnd / RTT. */
+static void bbr_init_pacing_rate_from_rtt(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bbr *bbr = inet_csk_ca(sk);
+	u64 bw;
+	u32 rtt_us;
+
+	if (tp->srtt_us) {		/* any RTT sample yet? */
+		rtt_us = max(tp->srtt_us >> 3, 1U);
+		bbr->has_seen_rtt = 1;
+	} else {			 /* no RTT sample yet */
+		rtt_us = USEC_PER_MSEC;	 /* use nominal default RTT */
+	}
+	bw = (u64)tp->snd_cwnd * BW_UNIT;
+	do_div(bw, rtt_us);
+	sk->sk_pacing_rate = bbr_bw_to_pacing_rate(sk, bw, bbr_high_gain);
+}
+
 /* Pace using current bw estimate and a gain factor. In order to help drive the
  * network toward lower queues while maintaining high utilization and low
  * latency, the average pacing rate aims to be slightly (~1%) lower than the
@@ -221,12 +251,13 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain)
  */
 static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
 	struct bbr *bbr = inet_csk_ca(sk);
-	u64 rate = bw;
+	u32 rate = bbr_bw_to_pacing_rate(sk, bw, gain);
 
-	rate = bbr_rate_bytes_per_sec(sk, rate, gain);
-	rate = min_t(u64, rate, sk->sk_max_pacing_rate);
-	if (bbr->mode != BBR_STARTUP || rate > sk->sk_pacing_rate)
+	if (unlikely(!bbr->has_seen_rtt && tp->srtt_us))
+		bbr_init_pacing_rate_from_rtt(sk);
+	if (bbr_full_bw_reached(sk) || rate > sk->sk_pacing_rate)
 		sk->sk_pacing_rate = rate;
 }
 
@@ -799,7 +830,6 @@ static void bbr_init(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bbr *bbr = inet_csk_ca(sk);
-	u64 bw;
 
 	bbr->prior_cwnd = 0;
 	bbr->tso_segs_goal = 0;	 /* default segs per skb until first ACK */
@@ -815,11 +845,8 @@ static void bbr_init(struct sock *sk)
 
 	minmax_reset(&bbr->bw, bbr->rtt_cnt, 0);  /* init max bw to 0 */
 
-	/* Initialize pacing rate to: high_gain * init_cwnd / RTT. */
-	bw = (u64)tp->snd_cwnd * BW_UNIT;
-	do_div(bw, (tp->srtt_us >> 3) ? : USEC_PER_MSEC);
-	sk->sk_pacing_rate = 0;		/* force an update of sk_pacing_rate */
-	bbr_set_pacing_rate(sk, bw, bbr_high_gain);
+	bbr->has_seen_rtt = 0;
+	bbr_init_pacing_rate_from_rtt(sk);
 
 	bbr->restore_cwnd = 0;
 	bbr->round_start = 0;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1d6219bf2d6b..b9a84eba60b8 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1762,7 +1762,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 /* For TCP sockets, sk_rx_dst is protected by socket lock
  * For UDP, we use xchg() to guard against concurrent changes.
  */
-static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
+void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
 {
 	struct dst_entry *old;
 
@@ -2120,6 +2120,7 @@ void udp_destroy_sock(struct sock *sk)
 			encap_destroy(sk);
 	}
 }
+EXPORT_SYMBOL(udp_sk_rx_dst_set);
 
 /*
  *	Socket option code for UDP
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 1699acb2fa2c..be0306778938 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -673,8 +673,6 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		*prevhdr = NEXTHDR_FRAGMENT;
 		tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC);
 		if (!tmp_hdr) {
-			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
-				      IPSTATS_MIB_FRAGFAILS);
 			err = -ENOMEM;
 			goto fail;
 		}
@@ -793,8 +791,6 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) +
 				 hroom + troom, GFP_ATOMIC);
 		if (!frag) {
-			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
-				      IPSTATS_MIB_FRAGFAILS);
 			err = -ENOMEM;
 			goto fail;
 		}
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index e9065b8d3af8..abb2c307fbe8 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -78,7 +78,7 @@ EXPORT_SYMBOL(ipv6_select_ident);
 
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
-	u16 offset = sizeof(struct ipv6hdr);
+	unsigned int offset = sizeof(struct ipv6hdr);
 	unsigned int packet_len = skb_tail_pointer(skb) -
 		skb_network_header(skb);
 	int found_rhdr = 0;
@@ -86,6 +86,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 
 	while (offset <= packet_len) {
 		struct ipv6_opt_hdr *exthdr;
+		unsigned int len;
 
 		switch (**nexthdr) {
 
@@ -111,7 +112,10 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 
 		exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) +
 						 offset);
-		offset += ipv6_optlen(exthdr);
+		len = ipv6_optlen(exthdr);
+		if (len + offset >= IPV6_MAXPLEN)
+			return -EINVAL;
+		offset += len;
 		*nexthdr = &exthdr->nexthdr;
 	}
 
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 5abc3692b901..ca7895454cec 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -215,6 +215,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	treq->rcv_isn = ntohl(th->seq) - 1;
 	treq->snt_isn = cookie;
 	treq->ts_off = 0;
+	treq->txhash = net_tx_rndhash();
 
 	/*
 	 * We need to lookup the dst_entry to get the correct window size.
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 75703fda23e7..592270c310f4 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -291,11 +291,7 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
 					  struct udp_table *udptable)
 {
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
-	struct sock *sk;
 
-	sk = skb_steal_sock(skb);
-	if (unlikely(sk))
-		return sk;
 	return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
 				 &iph->daddr, dport, inet6_iif(skb),
 				 udptable, skb);
@@ -798,6 +794,24 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (udp6_csum_init(skb, uh, proto))
 		goto csum_error;
 
+	/* Check if the socket is already available, e.g. due to early demux */
+	sk = skb_steal_sock(skb);
+	if (sk) {
+		struct dst_entry *dst = skb_dst(skb);
+		int ret;
+
+		if (unlikely(sk->sk_rx_dst != dst))
+			udp_sk_rx_dst_set(sk, dst);
+
+		ret = udpv6_queue_rcv_skb(sk, skb);
+		sock_put(sk);
+
+		/* a return value > 0 means to resubmit the input */
+		if (ret > 0)
+			return ret;
+		return 0;
+	}
+
 	/*
 	 *	Multicast receive code
 	 */
@@ -806,11 +820,6 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 				saddr, daddr, udptable, proto);
 
 	/* Unicast */
-
-	/*
-	 * check socket cache ... must talk to Alan about his plans
-	 * for sock caches... i'll skip this for now.
-	 */
 	sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
 	if (sk) {
 		int ret;
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 08679ebb3068..b3bf66bbf4dc 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1289,8 +1289,8 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 
 	nla_for_each_nested(a, attr, rem) {
 		int type = nla_type(a);
-		int maxlen = ovs_ct_attr_lens[type].maxlen;
-		int minlen = ovs_ct_attr_lens[type].minlen;
+		int maxlen;
+		int minlen;
 
 		if (type > OVS_CT_ATTR_MAX) {
 			OVS_NLERR(log,
@@ -1298,6 +1298,9 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 				  type, OVS_CT_ATTR_MAX);
 			return -EINVAL;
 		}
+
+		maxlen = ovs_ct_attr_lens[type].maxlen;
+		minlen = ovs_ct_attr_lens[type].minlen;
 		if (nla_len(a) < minlen || nla_len(a) > maxlen) {
 			OVS_NLERR(log,
 				  "Conntrack attr type has unexpected length (type=%d, length=%d, expected=%d)",
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index e3eeed19cc7a..0880e0a9d151 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4334,7 +4334,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		register_prot_hook(sk);
 	}
 	spin_unlock(&po->bind_lock);
-	if (closing && (po->tp_version > TPACKET_V2)) {
+	if (pg_vec && (po->tp_version > TPACKET_V2)) {
 		/* Because we don't support block-based V3 on tx-ring */
 		if (!tx_ring)
 			prb_shutdown_retire_blk_timer(po, rb_queue);
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 92e332e17391..961a6f81ae64 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -228,7 +228,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc,
 	sctp_adaptation_ind_param_t aiparam;
 	sctp_supported_ext_param_t ext_param;
 	int num_ext = 0;
-	__u8 extensions[3];
+	__u8 extensions[4];
 	sctp_paramhdr_t *auth_chunks = NULL,
 			*auth_hmacs = NULL;
 
@@ -396,7 +396,7 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc,
 	sctp_adaptation_ind_param_t aiparam;
 	sctp_supported_ext_param_t ext_param;
 	int num_ext = 0;
-	__u8 extensions[3];
+	__u8 extensions[4];
 	sctp_paramhdr_t *auth_chunks = NULL,
 			*auth_hmacs = NULL,
 			*auth_random = NULL;
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index a808332d02d0..606d5333ff98 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -2296,6 +2296,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x8691, "ASUS ROG Ranger VIII", ALC882_FIXUP_GPIO3),
 	SND_PCI_QUIRK(0x104d, 0x9047, "Sony Vaio TT", ALC889_FIXUP_VAIO_TT),
 	SND_PCI_QUIRK(0x104d, 0x905a, "Sony Vaio Z", ALC882_FIXUP_NO_PRIMARY_HP),
+	SND_PCI_QUIRK(0x104d, 0x9060, "Sony Vaio VPCL14M1R", ALC882_FIXUP_NO_PRIMARY_HP),
 	SND_PCI_QUIRK(0x104d, 0x9043, "Sony Vaio VGC-LN51JGB", ALC882_FIXUP_NO_PRIMARY_HP),
 	SND_PCI_QUIRK(0x104d, 0x9044, "Sony VAIO AiO", ALC882_FIXUP_NO_PRIMARY_HP),
 
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 754e3ef8d7ae..d05acc8eed1f 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -3139,8 +3139,6 @@ static int snd_soc_component_initialize(struct snd_soc_component *component,
 	component->remove = component->driver->remove;
 	component->suspend = component->driver->suspend;
 	component->resume = component->driver->resume;
-	component->pcm_new = component->driver->pcm_new;
-	component->pcm_free = component->driver->pcm_free;
 
 	dapm = &component->dapm;
 	dapm->dev = dev;
@@ -3328,25 +3326,6 @@ static void snd_soc_platform_drv_remove(struct snd_soc_component *component)
 	platform->driver->remove(platform);
 }
 
-static int snd_soc_platform_drv_pcm_new(struct snd_soc_pcm_runtime *rtd)
-{
-	struct snd_soc_platform *platform = rtd->platform;
-
-	if (platform->driver->pcm_new)
-		return platform->driver->pcm_new(rtd);
-	else
-		return 0;
-}
-
-static void snd_soc_platform_drv_pcm_free(struct snd_pcm *pcm)
-{
-	struct snd_soc_pcm_runtime *rtd = pcm->private_data;
-	struct snd_soc_platform *platform = rtd->platform;
-
-	if (platform->driver->pcm_free)
-		platform->driver->pcm_free(pcm);
-}
-
 /**
  * snd_soc_add_platform - Add a platform to the ASoC core
  * @dev: The parent device for the platform
@@ -3370,10 +3349,6 @@ int snd_soc_add_platform(struct device *dev, struct snd_soc_platform *platform,
 		platform->component.probe = snd_soc_platform_drv_probe;
 	if (platform_drv->remove)
 		platform->component.remove = snd_soc_platform_drv_remove;
-	if (platform_drv->pcm_new)
-		platform->component.pcm_new = snd_soc_platform_drv_pcm_new;
-	if (platform_drv->pcm_free)
-		platform->component.pcm_free = snd_soc_platform_drv_pcm_free;
 
 #ifdef CONFIG_DEBUG_FS
 	platform->component.debugfs_prefix = "platform";
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index efc5831f205d..8ff7cd3b8c1f 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -181,6 +181,10 @@ int dpcm_dapm_stream_event(struct snd_soc_pcm_runtime *fe, int dir,
 		dev_dbg(be->dev, "ASoC: BE %s event %d dir %d\n",
 				be->dai_link->name, event, dir);
 
+		if ((event == SND_SOC_DAPM_STREAM_STOP) &&
+		    (be->dpcm[dir].users >= 1))
+			continue;
+
 		snd_soc_dapm_stream_event(be, dir, event);
 	}
 
@@ -2628,25 +2632,12 @@ static int dpcm_fe_dai_close(struct snd_pcm_substream *fe_substream)
 	return ret;
 }
 
-static void soc_pcm_free(struct snd_pcm *pcm)
-{
-	struct snd_soc_pcm_runtime *rtd = pcm->private_data;
-	struct snd_soc_component *component;
-
-	list_for_each_entry(component, &rtd->card->component_dev_list,
-			    card_list) {
-		if (component->pcm_free)
-			component->pcm_free(pcm);
-	}
-}
-
 /* create a new pcm */
 int soc_new_pcm(struct snd_soc_pcm_runtime *rtd, int num)
 {
 	struct snd_soc_platform *platform = rtd->platform;
 	struct snd_soc_dai *codec_dai;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
-	struct snd_soc_component *component;
 	struct snd_pcm *pcm;
 	char new_name[64];
 	int ret = 0, playback = 0, capture = 0;
@@ -2755,18 +2746,17 @@ int soc_new_pcm(struct snd_soc_pcm_runtime *rtd, int num)
 	if (capture)
 		snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &rtd->ops);
 
-	list_for_each_entry(component, &rtd->card->component_dev_list, card_list) {
-		if (component->pcm_new) {
-			ret = component->pcm_new(rtd);
-			if (ret < 0) {
-				dev_err(component->dev,
-					"ASoC: pcm constructor failed: %d\n",
-					ret);
-				return ret;
-			}
+	if (platform->driver->pcm_new) {
+		ret = platform->driver->pcm_new(rtd);
+		if (ret < 0) {
+			dev_err(platform->dev,
+				"ASoC: pcm constructor failed: %d\n",
+				ret);
+			return ret;
 		}
 	}
-	pcm->private_free = soc_pcm_free;
+
+	pcm->private_free = platform->driver->pcm_free;
 out:
 	dev_info(rtd->card->dev, "%s <-> %s mapping ok\n",
 		 (rtd->num_codecs > 1) ? "multicodec" : rtd->codec_dai->name,
diff --git a/sound/soc/ux500/mop500.c b/sound/soc/ux500/mop500.c
index b50f68a439ce..ba9fc099cf67 100644
--- a/sound/soc/ux500/mop500.c
+++ b/sound/soc/ux500/mop500.c
@@ -33,6 +33,7 @@ static struct snd_soc_dai_link mop500_dai_links[] = {
 		.stream_name = "ab8500_0",
 		.cpu_dai_name = "ux500-msp-i2s.1",
 		.codec_dai_name = "ab8500-codec-dai.0",
+		.platform_name = "ux500-msp-i2s.1",
 		.codec_name = "ab8500-codec.0",
 		.init = mop500_ab8500_machine_init,
 		.ops = mop500_ab8500_ops,
@@ -42,6 +43,7 @@ static struct snd_soc_dai_link mop500_dai_links[] = {
 		.stream_name = "ab8500_1",
 		.cpu_dai_name = "ux500-msp-i2s.3",
 		.codec_dai_name = "ab8500-codec-dai.1",
+		.platform_name = "ux500-msp-i2s.3",
 		.codec_name = "ab8500-codec.0",
 		.init = NULL,
 		.ops = mop500_ab8500_ops,
@@ -85,6 +87,8 @@ static int mop500_of_probe(struct platform_device *pdev,
 	for (i = 0; i < 2; i++) {
 		mop500_dai_links[i].cpu_of_node = msp_np[i];
 		mop500_dai_links[i].cpu_dai_name = NULL;
+		mop500_dai_links[i].platform_of_node = msp_np[i];
+		mop500_dai_links[i].platform_name = NULL;
 		mop500_dai_links[i].codec_of_node = codec_np;
 		mop500_dai_links[i].codec_name = NULL;
 	}
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index e2e5effba2a9..db1c7b25a44c 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -1665,12 +1665,16 @@ static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *
 
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 {
+	if (!kvm->arch.pgd)
+		return 0;
 	trace_kvm_age_hva(start, end);
 	return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL);
 }
 
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
 {
+	if (!kvm->arch.pgd)
+		return 0;
 	trace_kvm_test_age_hva(hva);
 	return handle_hva_to_gpa(kvm, hva, hva, kvm_test_age_hva_handler, NULL);
 }