Merge tag 'v5.1-rc7' into x86/mm, to pick up fixes

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

60 files changed, 404 insertions, 224 deletions

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 6af24cdb25cc..3f13d8599337 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -866,14 +866,14 @@ The intent is that compaction has less work to do in the future and to
 increase the success rate of future high-order allocations such as SLUB
 allocations, THP and hugetlbfs pages.
 
-To make it sensible with respect to the watermark_scale_factor parameter,
-the unit is in fractions of 10,000. The default value of 15,000 means
-that up to 150% of the high watermark will be reclaimed in the event of
-a pageblock being mixed due to fragmentation. The level of reclaim is
-determined by the number of fragmentation events that occurred in the
-recent past. If this value is smaller than a pageblock then a pageblocks
-worth of pages will be reclaimed (e.g.  2MB on 64-bit x86). A boost factor
-of 0 will disable the feature.
+To make it sensible with respect to the watermark_scale_factor
+parameter, the unit is in fractions of 10,000. The default value of
+15,000 on !DISCONTIGMEM configurations means that up to 150% of the high
+watermark will be reclaimed in the event of a pageblock being mixed due
+to fragmentation. The level of reclaim is determined by the number of
+fragmentation events that occurred in the recent past. If this value is
+smaller than a pageblock then a pageblocks worth of pages will be reclaimed
+(e.g.  2MB on 64-bit x86). A boost factor of 0 will disable the feature.
 
 =============================================================
 
diff --git a/Makefile b/Makefile
index abe13538a8c0..2b99679148dc 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 1
 SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
 NAME = Shy Crocodile
 
 # *DOCUMENTATION*
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 850b4805e2d1..9aed25a6019b 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -73,7 +73,7 @@ config ARM
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU
 	select HAVE_EXIT_THREAD
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
-	select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL
+	select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG
 	select HAVE_FUNCTION_TRACER if !XIP_KERNEL
 	select HAVE_GCC_PLUGINS
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7)
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 6d6e0330930b..e388af4594a6 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -47,8 +47,8 @@ config DEBUG_WX
 
 choice
 	prompt "Choose kernel unwinder"
-	default UNWINDER_ARM if AEABI && !FUNCTION_GRAPH_TRACER
-	default UNWINDER_FRAME_POINTER if !AEABI || FUNCTION_GRAPH_TRACER
+	default UNWINDER_ARM if AEABI
+	default UNWINDER_FRAME_POINTER if !AEABI
 	help
 	  This determines which method will be used for unwinding kernel stack
 	  traces for panics, oopses, bugs, warnings, perf, /proc/<pid>/stack,
@@ -65,7 +65,7 @@ config UNWINDER_FRAME_POINTER
 
 config UNWINDER_ARM
 	bool "ARM EABI stack unwinder"
-	depends on AEABI
+	depends on AEABI && !FUNCTION_GRAPH_TRACER
 	select ARM_UNWIND
 	help
 	  This option enables stack unwinding support in the kernel
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 6c7ccb428c07..7135820f76d4 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -1438,7 +1438,21 @@ ENTRY(efi_stub_entry)
 
 		@ Preserve return value of efi_entry() in r4
 		mov	r4, r0
-		bl	cache_clean_flush
+
+		@ our cache maintenance code relies on CP15 barrier instructions
+		@ but since we arrived here with the MMU and caches configured
+		@ by UEFI, we must check that the CP15BEN bit is set in SCTLR.
+		@ Note that this bit is RAO/WI on v6 and earlier, so the ISB in
+		@ the enable path will be executed on v7+ only.
+		mrc	p15, 0, r1, c1, c0, 0	@ read SCTLR
+		tst	r1, #(1 << 5)		@ CP15BEN bit set?
+		bne	0f
+		orr	r1, r1, #(1 << 5)	@ CP15 barrier instructions
+		mcr	p15, 0, r1, c1, c0, 0	@ write SCTLR
+ ARM(		.inst	0xf57ff06f		@ v7+ isb	)
+ THUMB(		isb						)
+
+0:		bl	cache_clean_flush
 		bl	cache_off
 
 		@ Set parameters for booting zImage according to boot protocol
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index c08d2d890f7b..b38bbd011b35 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -133,9 +133,9 @@ __secondary_data:
  */
 	.text
 __after_proc_init:
-#ifdef CONFIG_ARM_MPU
 M_CLASS(movw	r12, #:lower16:BASEADDR_V7M_SCB)
 M_CLASS(movt	r12, #:upper16:BASEADDR_V7M_SCB)
+#ifdef CONFIG_ARM_MPU
 M_CLASS(ldr	r3, [r12, 0x50])
 AR_CLASS(mrc	p15, 0, r3, c0, c1, 4)          @ Read ID_MMFR0
 	and	r3, r3, #(MMFR0_PMSA)           @ PMSA field
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 07b298120182..65a51331088e 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -103,10 +103,15 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 		 * to be revisited if support for multiple ftrace entry points
 		 * is added in the future, but for now, the pr_err() below
 		 * deals with a theoretical issue only.
+		 *
+		 * Note that PLTs are place relative, and plt_entries_equal()
+		 * checks whether they point to the same target. Here, we need
+		 * to check if the actual opcodes are in fact identical,
+		 * regardless of the offset in memory so use memcmp() instead.
 		 */
 		trampoline = get_plt_entry(addr, mod->arch.ftrace_trampoline);
-		if (!plt_entries_equal(mod->arch.ftrace_trampoline,
-				       &trampoline)) {
+		if (memcmp(mod->arch.ftrace_trampoline, &trampoline,
+			   sizeof(trampoline))) {
 			if (plt_entry_is_initialized(mod->arch.ftrace_trampoline)) {
 				pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
 				return -EINVAL;
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 6bc135042f5e..7cae155e81a5 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -363,7 +363,7 @@ void __init arm64_memblock_init(void)
 		 * Otherwise, this is a no-op
 		 */
 		u64 base = phys_initrd_start & PAGE_MASK;
-		u64 size = PAGE_ALIGN(phys_initrd_size);
+		u64 size = PAGE_ALIGN(phys_initrd_start + phys_initrd_size) - base;
 
 		/*
 		 * We can only add back the initrd memory if we don't end up
diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig
index 5ba131c30f6b..1bcd468ab422 100644
--- a/arch/powerpc/configs/skiroot_defconfig
+++ b/arch/powerpc/configs/skiroot_defconfig
@@ -266,6 +266,7 @@ CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_PROC_KCORE=y
+CONFIG_HUGETLBFS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 # CONFIG_NETWORK_FILESYSTEMS is not set
 CONFIG_NLS=y
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index e7a9c4f6bfca..8330f135294f 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -95,28 +95,15 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 			      unsigned long entries, unsigned long dev_hpa,
 			      struct mm_iommu_table_group_mem_t **pmem)
 {
-	struct mm_iommu_table_group_mem_t *mem;
-	long i, ret, locked_entries = 0;
+	struct mm_iommu_table_group_mem_t *mem, *mem2;
+	long i, ret, locked_entries = 0, pinned = 0;
 	unsigned int pageshift;
-
-	mutex_lock(&mem_list_mutex);
-
-	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list,
-			next) {
-		/* Overlap? */
-		if ((mem->ua < (ua + (entries << PAGE_SHIFT))) &&
-				(ua < (mem->ua +
-				       (mem->entries << PAGE_SHIFT)))) {
-			ret = -EINVAL;
-			goto unlock_exit;
-		}
-
-	}
+	unsigned long entry, chunk;
 
 	if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) {
 		ret = mm_iommu_adjust_locked_vm(mm, entries, true);
 		if (ret)
-			goto unlock_exit;
+			return ret;
 
 		locked_entries = entries;
 	}
@@ -148,17 +135,27 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 	}
 
 	down_read(&mm->mmap_sem);
-	ret = get_user_pages_longterm(ua, entries, FOLL_WRITE, mem->hpages, NULL);
+	chunk = (1UL << (PAGE_SHIFT + MAX_ORDER - 1)) /
+			sizeof(struct vm_area_struct *);
+	chunk = min(chunk, entries);
+	for (entry = 0; entry < entries; entry += chunk) {
+		unsigned long n = min(entries - entry, chunk);
+
+		ret = get_user_pages_longterm(ua + (entry << PAGE_SHIFT), n,
+				FOLL_WRITE, mem->hpages + entry, NULL);
+		if (ret == n) {
+			pinned += n;
+			continue;
+		}
+		if (ret > 0)
+			pinned += ret;
+		break;
+	}
 	up_read(&mm->mmap_sem);
-	if (ret != entries) {
-		/* free the reference taken */
-		for (i = 0; i < ret; i++)
-			put_page(mem->hpages[i]);
-
-		vfree(mem->hpas);
-		kfree(mem);
-		ret = -EFAULT;
-		goto unlock_exit;
+	if (pinned != entries) {
+		if (!ret)
+			ret = -EFAULT;
+		goto free_exit;
 	}
 
 	pageshift = PAGE_SHIFT;
@@ -183,21 +180,43 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 	}
 
 good_exit:
-	ret = 0;
 	atomic64_set(&mem->mapped, 1);
 	mem->used = 1;
 	mem->ua = ua;
 	mem->entries = entries;
-	*pmem = mem;
 
-	list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
+	mutex_lock(&mem_list_mutex);
 
-unlock_exit:
-	if (locked_entries && ret)
-		mm_iommu_adjust_locked_vm(mm, locked_entries, false);
+	list_for_each_entry_rcu(mem2, &mm->context.iommu_group_mem_list, next) {
+		/* Overlap? */
+		if ((mem2->ua < (ua + (entries << PAGE_SHIFT))) &&
+				(ua < (mem2->ua +
+				       (mem2->entries << PAGE_SHIFT)))) {
+			ret = -EINVAL;
+			mutex_unlock(&mem_list_mutex);
+			goto free_exit;
+		}
+	}
+
+	list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
 
 	mutex_unlock(&mem_list_mutex);
 
+	*pmem = mem;
+
+	return 0;
+
+free_exit:
+	/* free the reference taken */
+	for (i = 0; i < pinned; i++)
+		put_page(mem->hpages[i]);
+
+	vfree(mem->hpas);
+	kfree(mem);
+
+unlock_exit:
+	mm_iommu_adjust_locked_vm(mm, locked_entries, false);
+
 	return ret;
 }
 
@@ -266,7 +285,7 @@ static void mm_iommu_release(struct mm_iommu_table_group_mem_t *mem)
 long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
 {
 	long ret = 0;
-	unsigned long entries, dev_hpa;
+	unsigned long unlock_entries = 0;
 
 	mutex_lock(&mem_list_mutex);
 
@@ -287,17 +306,17 @@ long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
 		goto unlock_exit;
 	}
 
+	if (mem->dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
+		unlock_entries = mem->entries;
+
 	/* @mapped became 0 so now mappings are disabled, release the region */
-	entries = mem->entries;
-	dev_hpa = mem->dev_hpa;
 	mm_iommu_release(mem);
 
-	if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
-		mm_iommu_adjust_locked_vm(mm, entries, false);
-
 unlock_exit:
 	mutex_unlock(&mem_list_mutex);
 
+	mm_iommu_adjust_locked_vm(mm, unlock_entries, false);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(mm_iommu_put);
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 842b2c7e156a..50cd09b4e05d 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -324,7 +324,7 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK
 
 config PPC_RADIX_MMU
 	bool "Radix MMU Support"
-	depends on PPC_BOOK3S_64
+	depends on PPC_BOOK3S_64 && HUGETLB_PAGE
 	select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
 	default y
 	help
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index c0d6c560df69..5a237e8dbf8d 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -352,7 +352,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 	boot_params->hdr.loadflags &= ~KASLR_FLAG;
 
 	/* Save RSDP address for later use. */
-	boot_params->acpi_rsdp_addr = get_rsdp_addr();
+	/* boot_params->acpi_rsdp_addr = get_rsdp_addr(); */
 
 	sanitize_boot_params(boot_params);
 
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 94a4b7fc75d0..d41de9af7a39 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -76,15 +76,15 @@
  *			       Scope: Package (physical package)
  *	MSR_PKG_C8_RESIDENCY:  Package C8 Residency Counter.
  *			       perf code: 0x04
- *			       Available model: HSW ULT,CNL
+ *			       Available model: HSW ULT,KBL,CNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C9_RESIDENCY:  Package C9 Residency Counter.
  *			       perf code: 0x05
- *			       Available model: HSW ULT,CNL
+ *			       Available model: HSW ULT,KBL,CNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
  *			       perf code: 0x06
- *			       Available model: HSW ULT,GLM,CNL
+ *			       Available model: HSW ULT,KBL,GLM,CNL
  *			       Scope: Package (physical package)
  *
  */
@@ -566,8 +566,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE,  snb_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE,  hswult_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, hswult_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_MOBILE, cnl_cstates),
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index f905a2371080..8dacdb96899e 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -5,6 +5,7 @@
 #include <linux/memblock.h>
 #include <linux/swapfile.h>
 #include <linux/swapops.h>
+#include <linux/kmemleak.h>
 
 #include <asm/set_memory.h>
 #include <asm/e820/api.h>
@@ -766,6 +767,11 @@ void free_init_pages(const char *what, unsigned long begin, unsigned long end)
 	if (debug_pagealloc_enabled()) {
 		pr_info("debug: unmapping init [mem %#010lx-%#010lx]\n",
 			begin, end - 1);
+		/*
+		 * Inform kmemleak about the hole in the memory since the
+		 * corresponding pages will be unmapped.
+		 */
+		kmemleak_free_part((void *)begin, end - begin);
 		set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
 	} else {
 		/*
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 399cad7daae7..d58a359a6622 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -774,18 +774,18 @@ struct zram_work {
 	struct zram *zram;
 	unsigned long entry;
 	struct bio *bio;
+	struct bio_vec bvec;
 };
 
 #if PAGE_SIZE != 4096
 static void zram_sync_read(struct work_struct *work)
 {
-	struct bio_vec bvec;
 	struct zram_work *zw = container_of(work, struct zram_work, work);
 	struct zram *zram = zw->zram;
 	unsigned long entry = zw->entry;
 	struct bio *bio = zw->bio;
 
-	read_from_bdev_async(zram, &bvec, entry, bio);
+	read_from_bdev_async(zram, &zw->bvec, entry, bio);
 }
 
 /*
@@ -798,6 +798,7 @@ static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
 {
 	struct zram_work work;
 
+	work.bvec = *bvec;
 	work.zram = zram;
 	work.entry = entry;
 	work.bio = bio;
diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c
index ec8a291d62ba..54093ffd0aef 100644
--- a/drivers/dma/bcm2835-dma.c
+++ b/drivers/dma/bcm2835-dma.c
@@ -671,7 +671,7 @@ static struct dma_async_tx_descriptor *bcm2835_dma_prep_slave_sg(
 	d = bcm2835_dma_create_cb_chain(chan, direction, false,
 					info, extra,
 					frames, src, dst, 0, 0,
-					GFP_KERNEL);
+					GFP_NOWAIT);
 	if (!d)
 		return NULL;
 
diff --git a/drivers/dma/mediatek/mtk-cqdma.c b/drivers/dma/mediatek/mtk-cqdma.c
index 131f3974740d..814853842e29 100644
--- a/drivers/dma/mediatek/mtk-cqdma.c
+++ b/drivers/dma/mediatek/mtk-cqdma.c
@@ -253,7 +253,7 @@ static void mtk_cqdma_start(struct mtk_cqdma_pchan *pc,
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
 	mtk_dma_set(pc, MTK_CQDMA_DST2, cvd->dest >> MTK_CQDMA_ADDR2_SHFIT);
 #else
-	mtk_dma_set(pc, MTK_CQDMA_SRC2, 0);
+	mtk_dma_set(pc, MTK_CQDMA_DST2, 0);
 #endif
 
 	/* setup the length */
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 2b4f25698169..e2a5398f89b5 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -1282,6 +1282,9 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
 	enum dma_status status;
 	unsigned int residue = 0;
 	unsigned int dptr = 0;
+	unsigned int chcrb;
+	unsigned int tcrb;
+	unsigned int i;
 
 	if (!desc)
 		return 0;
@@ -1330,14 +1333,31 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
 	}
 
 	/*
+	 * We need to read two registers.
+	 * Make sure the control register does not skip to next chunk
+	 * while reading the counter.
+	 * Trying it 3 times should be enough: Initial read, retry, retry
+	 * for the paranoid.
+	 */
+	for (i = 0; i < 3; i++) {
+		chcrb = rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
+					    RCAR_DMACHCRB_DPTR_MASK;
+		tcrb = rcar_dmac_chan_read(chan, RCAR_DMATCRB);
+		/* Still the same? */
+		if (chcrb == (rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
+			      RCAR_DMACHCRB_DPTR_MASK))
+			break;
+	}
+	WARN_ONCE(i >= 3, "residue might be not continuous!");
+
+	/*
 	 * In descriptor mode the descriptor running pointer is not maintained
 	 * by the interrupt handler, find the running descriptor from the
 	 * descriptor pointer field in the CHCRB register. In non-descriptor
 	 * mode just use the running descriptor pointer.
 	 */
 	if (desc->hwdescs.use) {
-		dptr = (rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
-			RCAR_DMACHCRB_DPTR_MASK) >> RCAR_DMACHCRB_DPTR_SHIFT;
+		dptr = chcrb >> RCAR_DMACHCRB_DPTR_SHIFT;
 		if (dptr == 0)
 			dptr = desc->nchunks;
 		dptr--;
@@ -1355,7 +1375,7 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
 	}
 
 	/* Add the residue for the current chunk. */
-	residue += rcar_dmac_chan_read(chan, RCAR_DMATCRB) << desc->xfer_shift;
+	residue += tcrb << desc->xfer_shift;
 
 	return residue;
 }
@@ -1368,6 +1388,7 @@ static enum dma_status rcar_dmac_tx_status(struct dma_chan *chan,
 	enum dma_status status;
 	unsigned long flags;
 	unsigned int residue;
+	bool cyclic;
 
 	status = dma_cookie_status(chan, cookie, txstate);
 	if (status == DMA_COMPLETE || !txstate)
@@ -1375,10 +1396,11 @@ static enum dma_status rcar_dmac_tx_status(struct dma_chan *chan,
 
 	spin_lock_irqsave(&rchan->lock, flags);
 	residue = rcar_dmac_chan_get_residue(rchan, cookie);
+	cyclic = rchan->desc.running ? rchan->desc.running->cyclic : false;
 	spin_unlock_irqrestore(&rchan->lock, flags);
 
 	/* if there's no residue, the cookie is complete */
-	if (!residue)
+	if (!residue && !cyclic)
 		return DMA_COMPLETE;
 
 	dma_set_residue(txstate, residue);
diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c
index f0223cee9774..77092268ee95 100644
--- a/drivers/gpio/gpio-eic-sprd.c
+++ b/drivers/gpio/gpio-eic-sprd.c
@@ -414,6 +414,7 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type)
 			irq_set_handler_locked(data, handle_edge_irq);
 			break;
 		case IRQ_TYPE_EDGE_BOTH:
+			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 1);
 			irq_set_handler_locked(data, handle_edge_irq);
 			break;
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 0495bf1d480a..bca3e7740ef6 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1379,7 +1379,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,
 
 	status = gpiochip_add_irqchip(chip, lock_key, request_key);
 	if (status)
-		goto err_remove_chip;
+		goto err_free_gpiochip_mask;
 
 	status = of_gpiochip_add(chip);
 	if (status)
@@ -1387,7 +1387,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,
 
 	status = gpiochip_init_valid_mask(chip);
 	if (status)
-		goto err_remove_chip;
+		goto err_remove_of_chip;
 
 	for (i = 0; i < chip->ngpio; i++) {
 		struct gpio_desc *desc = &gdev->descs[i];
@@ -1415,14 +1415,18 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,
 	if (gpiolib_initialized) {
 		status = gpiochip_setup_dev(gdev);
 		if (status)
-			goto err_remove_chip;
+			goto err_remove_acpi_chip;
 	}
 	return 0;
 
-err_remove_chip:
+err_remove_acpi_chip:
 	acpi_gpiochip_remove(chip);
+err_remove_of_chip:
 	gpiochip_free_hogs(chip);
 	of_gpiochip_remove(chip);
+err_remove_chip:
+	gpiochip_irqchip_remove(chip);
+err_free_gpiochip_mask:
 	gpiochip_free_valid_mask(chip);
 err_remove_irqchip_mask:
 	gpiochip_irqchip_free_valid_mask(chip);
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
index db761329a1e3..ab7968c8f6a2 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
@@ -1046,6 +1046,10 @@ static bool dw_hdmi_support_scdc(struct dw_hdmi *hdmi)
 	if (hdmi->version < 0x200a)
 		return false;
 
+	/* Disable if no DDC bus */
+	if (!hdmi->ddc)
+		return false;
+
 	/* Disable if SCDC is not supported, or if an HF-VSDB block is absent */
 	if (!display->hdmi.scdc.supported ||
 	    !display->hdmi.scdc.scrambling.supported)
@@ -1684,13 +1688,13 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi,
 			 * Source Devices compliant shall set the
 			 * Source Version = 1.
 			 */
-			drm_scdc_readb(&hdmi->i2c->adap, SCDC_SINK_VERSION,
+			drm_scdc_readb(hdmi->ddc, SCDC_SINK_VERSION,
 				       &bytes);
-			drm_scdc_writeb(&hdmi->i2c->adap, SCDC_SOURCE_VERSION,
+			drm_scdc_writeb(hdmi->ddc, SCDC_SOURCE_VERSION,
 				min_t(u8, bytes, SCDC_MIN_SOURCE_VERSION));
 
 			/* Enabled Scrambling in the Sink */
-			drm_scdc_set_scrambling(&hdmi->i2c->adap, 1);
+			drm_scdc_set_scrambling(hdmi->ddc, 1);
 
 			/*
 			 * To activate the scrambler feature, you must ensure
@@ -1706,7 +1710,7 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi,
 			hdmi_writeb(hdmi, 0, HDMI_FC_SCRAMBLER_CTRL);
 			hdmi_writeb(hdmi, (u8)~HDMI_MC_SWRSTZ_TMDSSWRST_REQ,
 				    HDMI_MC_SWRSTZ);
-			drm_scdc_set_scrambling(&hdmi->i2c->adap, 0);
+			drm_scdc_set_scrambling(hdmi->ddc, 0);
 		}
 	}
 
@@ -1800,6 +1804,8 @@ static void dw_hdmi_clear_overflow(struct dw_hdmi *hdmi)
 	 * iteration for others.
 	 * The Amlogic Meson GX SoCs (v2.01a) have been identified as needing
 	 * the workaround with a single iteration.
+	 * The Rockchip RK3288 SoC (v2.00a) and RK3328/RK3399 SoCs (v2.11a) have
+	 * been identified as needing the workaround with a single iteration.
 	 */
 
 	switch (hdmi->version) {
@@ -1808,7 +1814,9 @@ static void dw_hdmi_clear_overflow(struct dw_hdmi *hdmi)
 		break;
 	case 0x131a:
 	case 0x132a:
+	case 0x200a:
 	case 0x201a:
+	case 0x211a:
 	case 0x212a:
 		count = 1;
 		break;
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index ab4e60dfd6a3..98cea1f4b3bf 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -3862,14 +3862,16 @@ static int intel_ddi_compute_config(struct intel_encoder *encoder,
 		ret = intel_hdmi_compute_config(encoder, pipe_config, conn_state);
 	else
 		ret = intel_dp_compute_config(encoder, pipe_config, conn_state);
+	if (ret)
+		return ret;
 
-	if (IS_GEN9_LP(dev_priv) && ret)
+	if (IS_GEN9_LP(dev_priv))
 		pipe_config->lane_lat_optim_mask =
 			bxt_ddi_phy_calc_lane_lat_optim_mask(pipe_config->lane_count);
 
 	intel_ddi_compute_min_voltage_level(dev_priv, pipe_config);
 
-	return ret;
+	return 0;
 
 }
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 8891f29a8c7f..48da4a969a0a 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1886,6 +1886,9 @@ static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp,
 	int pipe_bpp;
 	int ret;
 
+	pipe_config->fec_enable = !intel_dp_is_edp(intel_dp) &&
+		intel_dp_supports_fec(intel_dp, pipe_config);
+
 	if (!intel_dp_supports_dsc(intel_dp, pipe_config))
 		return -EINVAL;
 
@@ -2116,9 +2119,6 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK)
 		return -EINVAL;
 
-	pipe_config->fec_enable = !intel_dp_is_edp(intel_dp) &&
-				  intel_dp_supports_fec(intel_dp, pipe_config);
-
 	ret = intel_dp_compute_link_config(encoder, pipe_config, conn_state);
 	if (ret < 0)
 		return ret;
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index ec3602ebbc1c..54011df8c2e8 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -71,7 +71,7 @@ static void ipu_crtc_disable_planes(struct ipu_crtc *ipu_crtc,
 	if (disable_partial)
 		ipu_plane_disable(ipu_crtc->plane[1], true);
 	if (disable_full)
-		ipu_plane_disable(ipu_crtc->plane[0], false);
+		ipu_plane_disable(ipu_crtc->plane[0], true);
 }
 
 static void ipu_crtc_atomic_disable(struct drm_crtc *crtc,
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 19fc601c9eeb..a1bec2779e76 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -366,10 +366,9 @@ void drm_sched_increase_karma(struct drm_sched_job *bad)
 EXPORT_SYMBOL(drm_sched_increase_karma);
 
 /**
- * drm_sched_hw_job_reset - stop the scheduler if it contains the bad job
+ * drm_sched_stop - stop the scheduler
  *
  * @sched: scheduler instance
- * @bad: bad scheduler job
  *
  */
 void drm_sched_stop(struct drm_gpu_scheduler *sched)
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index 3ebd9f5e2719..29258b404e54 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -16,6 +16,7 @@
 #include <linux/of_reserved_mem.h>
 
 #include <drm/drmP.h>
+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_gem_cma_helper.h>
@@ -85,6 +86,8 @@ static int sun4i_drv_bind(struct device *dev)
 		ret = -ENOMEM;
 		goto free_drm;
 	}
+
+	dev_set_drvdata(dev, drm);
 	drm->dev_private = drv;
 	INIT_LIST_HEAD(&drv->frontend_list);
 	INIT_LIST_HEAD(&drv->engine_list);
@@ -144,8 +147,12 @@ static void sun4i_drv_unbind(struct device *dev)
 
 	drm_dev_unregister(drm);
 	drm_kms_helper_poll_fini(drm);
+	drm_atomic_helper_shutdown(drm);
 	drm_mode_config_cleanup(drm);
+
+	component_unbind_all(dev, NULL);
 	of_reserved_mem_device_release(dev);
+
 	drm_dev_put(drm);
 }
 
@@ -395,6 +402,8 @@ static int sun4i_drv_probe(struct platform_device *pdev)
 
 static int sun4i_drv_remove(struct platform_device *pdev)
 {
+	component_master_del(&pdev->dev, &sun4i_drv_master_ops);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 0fa5034b9f9e..1a01669b159a 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -49,9 +49,8 @@ static void ttm_bo_global_kobj_release(struct kobject *kobj);
  * ttm_global_mutex - protecting the global BO state
  */
 DEFINE_MUTEX(ttm_global_mutex);
-struct ttm_bo_global ttm_bo_glob = {
-	.use_count = 0
-};
+unsigned ttm_bo_glob_use_count;
+struct ttm_bo_global ttm_bo_glob;
 
 static struct attribute ttm_bo_count = {
 	.name = "bo_count",
@@ -1531,12 +1530,13 @@ static void ttm_bo_global_release(void)
 	struct ttm_bo_global *glob = &ttm_bo_glob;
 
 	mutex_lock(&ttm_global_mutex);
-	if (--glob->use_count > 0)
+	if (--ttm_bo_glob_use_count > 0)
 		goto out;
 
 	kobject_del(&glob->kobj);
 	kobject_put(&glob->kobj);
 	ttm_mem_global_release(&ttm_mem_glob);
+	memset(glob, 0, sizeof(*glob));
 out:
 	mutex_unlock(&ttm_global_mutex);
 }
@@ -1548,7 +1548,7 @@ static int ttm_bo_global_init(void)
 	unsigned i;
 
 	mutex_lock(&ttm_global_mutex);
-	if (++glob->use_count > 1)
+	if (++ttm_bo_glob_use_count > 1)
 		goto out;
 
 	ret = ttm_mem_global_init(&ttm_mem_glob);
diff --git a/drivers/gpu/drm/ttm/ttm_memory.c b/drivers/gpu/drm/ttm/ttm_memory.c
index f1567c353b54..9a0909decb36 100644
--- a/drivers/gpu/drm/ttm/ttm_memory.c
+++ b/drivers/gpu/drm/ttm/ttm_memory.c
@@ -461,8 +461,8 @@ out_no_zone:
 
 void ttm_mem_global_release(struct ttm_mem_global *glob)
 {
-	unsigned int i;
 	struct ttm_mem_zone *zone;
+	unsigned int i;
 
 	/* let the page allocator first stop the shrink work. */
 	ttm_page_alloc_fini();
@@ -475,9 +475,10 @@ void ttm_mem_global_release(struct ttm_mem_global *glob)
 		zone = glob->zones[i];
 		kobject_del(&zone->kobj);
 		kobject_put(&zone->kobj);
-			}
+	}
 	kobject_del(&glob->kobj);
 	kobject_put(&glob->kobj);
+	memset(glob, 0, sizeof(*glob));
 }
 
 static void ttm_check_swapping(struct ttm_mem_global *glob)
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index 730008d3da76..1baa10e94484 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -1042,7 +1042,7 @@ static void
 vc4_crtc_reset(struct drm_crtc *crtc)
 {
 	if (crtc->state)
-		__drm_atomic_helper_crtc_destroy_state(crtc->state);
+		vc4_crtc_destroy_state(crtc, crtc->state);
 
 	crtc->state = kzalloc(sizeof(struct vc4_crtc_state), GFP_KERNEL);
 	if (crtc->state)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 6165fe2c4504..1bfa353d995c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -546,29 +546,13 @@ static void vmw_get_initial_size(struct vmw_private *dev_priv)
 }
 
 /**
- * vmw_assume_iommu - Figure out whether coherent dma-remapping might be
- * taking place.
- * @dev: Pointer to the struct drm_device.
- *
- * Return: true if iommu present, false otherwise.
- */
-static bool vmw_assume_iommu(struct drm_device *dev)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev->dev);
-
-	return !dma_is_direct(ops) && ops &&
-		ops->map_page != dma_direct_map_page;
-}
-
-/**
  * vmw_dma_select_mode - Determine how DMA mappings should be set up for this
  * system.
  *
  * @dev_priv: Pointer to a struct vmw_private
  *
- * This functions tries to determine the IOMMU setup and what actions
- * need to be taken by the driver to make system pages visible to the
- * device.
+ * This functions tries to determine what actions need to be taken by the
+ * driver to make system pages visible to the device.
  * If this function decides that DMA is not possible, it returns -EINVAL.
  * The driver may then try to disable features of the device that require
  * DMA.
@@ -578,23 +562,16 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv)
 	static const char *names[vmw_dma_map_max] = {
 		[vmw_dma_phys] = "Using physical TTM page addresses.",
 		[vmw_dma_alloc_coherent] = "Using coherent TTM pages.",
-		[vmw_dma_map_populate] = "Keeping DMA mappings.",
+		[vmw_dma_map_populate] = "Caching DMA mappings.",
 		[vmw_dma_map_bind] = "Giving up DMA mappings early."};
 
 	if (vmw_force_coherent)
 		dev_priv->map_mode = vmw_dma_alloc_coherent;
-	else if (vmw_assume_iommu(dev_priv->dev))
-		dev_priv->map_mode = vmw_dma_map_populate;
-	else if (!vmw_force_iommu)
-		dev_priv->map_mode = vmw_dma_phys;
-	else if (IS_ENABLED(CONFIG_SWIOTLB) && swiotlb_nr_tbl())
-		dev_priv->map_mode = vmw_dma_alloc_coherent;
+	else if (vmw_restrict_iommu)
+		dev_priv->map_mode = vmw_dma_map_bind;
 	else
 		dev_priv->map_mode = vmw_dma_map_populate;
 
-	if (dev_priv->map_mode == vmw_dma_map_populate && vmw_restrict_iommu)
-		dev_priv->map_mode = vmw_dma_map_bind;
-
 	/* No TTM coherent page pool? FIXME: Ask TTM instead! */
         if (!(IS_ENABLED(CONFIG_SWIOTLB) || IS_ENABLED(CONFIG_INTEL_IOMMU)) &&
 	    (dev_priv->map_mode == vmw_dma_alloc_coherent))
diff --git a/drivers/gpu/ipu-v3/ipu-dp.c b/drivers/gpu/ipu-v3/ipu-dp.c
index 9b2b3fa479c4..5e44ff1f2085 100644
--- a/drivers/gpu/ipu-v3/ipu-dp.c
+++ b/drivers/gpu/ipu-v3/ipu-dp.c
@@ -195,7 +195,8 @@ int ipu_dp_setup_channel(struct ipu_dp *dp,
 		ipu_dp_csc_init(flow, flow->foreground.in_cs, flow->out_cs,
 				DP_COM_CONF_CSC_DEF_BOTH);
 	} else {
-		if (flow->foreground.in_cs == flow->out_cs)
+		if (flow->foreground.in_cs == IPUV3_COLORSPACE_UNKNOWN ||
+		    flow->foreground.in_cs == flow->out_cs)
 			/*
 			 * foreground identical to output, apply color
 			 * conversion on background
@@ -261,6 +262,8 @@ void ipu_dp_disable_channel(struct ipu_dp *dp, bool sync)
 	struct ipu_dp_priv *priv = flow->priv;
 	u32 reg, csc;
 
+	dp->in_cs = IPUV3_COLORSPACE_UNKNOWN;
+
 	if (!dp->foreground)
 		return;
 
@@ -268,8 +271,9 @@ void ipu_dp_disable_channel(struct ipu_dp *dp, bool sync)
 
 	reg = readl(flow->base + DP_COM_CONF);
 	csc = reg & DP_COM_CONF_CSC_DEF_MASK;
-	if (csc == DP_COM_CONF_CSC_DEF_FG)
-		reg &= ~DP_COM_CONF_CSC_DEF_MASK;
+	reg &= ~DP_COM_CONF_CSC_DEF_MASK;
+	if (csc == DP_COM_CONF_CSC_DEF_BOTH || csc == DP_COM_CONF_CSC_DEF_BG)
+		reg |= DP_COM_CONF_CSC_DEF_BG;
 
 	reg &= ~DP_COM_CONF_FG_EN;
 	writel(reg, flow->base + DP_COM_CONF);
@@ -347,6 +351,8 @@ int ipu_dp_init(struct ipu_soc *ipu, struct device *dev, unsigned long base)
 	mutex_init(&priv->mutex);
 
 	for (i = 0; i < IPUV3_NUM_FLOWS; i++) {
+		priv->flow[i].background.in_cs = IPUV3_COLORSPACE_UNKNOWN;
+		priv->flow[i].foreground.in_cs = IPUV3_COLORSPACE_UNKNOWN;
 		priv->flow[i].foreground.foreground = true;
 		priv->flow[i].base = priv->base + ipu_dp_flow_base[i];
 		priv->flow[i].priv = priv;
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index ea0bc6885517..32cc8fe7902f 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -160,6 +160,7 @@ struct ib_uverbs_file {
 
 	struct mutex umap_lock;
 	struct list_head umaps;
+	struct page *disassociate_page;
 
 	struct idr		idr;
 	/* spinlock protects write access to idr */
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index f2e7ffe6fc54..7843e89235c3 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -208,6 +208,9 @@ void ib_uverbs_release_file(struct kref *ref)
 		kref_put(&file->async_file->ref,
 			 ib_uverbs_release_async_event_file);
 	put_device(&file->device->dev);
+
+	if (file->disassociate_page)
+		__free_pages(file->disassociate_page, 0);
 	kfree(file);
 }
 
@@ -877,9 +880,50 @@ static void rdma_umap_close(struct vm_area_struct *vma)
 	kfree(priv);
 }
 
+/*
+ * Once the zap_vma_ptes has been called touches to the VMA will come here and
+ * we return a dummy writable zero page for all the pfns.
+ */
+static vm_fault_t rdma_umap_fault(struct vm_fault *vmf)
+{
+	struct ib_uverbs_file *ufile = vmf->vma->vm_file->private_data;
+	struct rdma_umap_priv *priv = vmf->vma->vm_private_data;
+	vm_fault_t ret = 0;
+
+	if (!priv)
+		return VM_FAULT_SIGBUS;
+
+	/* Read only pages can just use the system zero page. */
+	if (!(vmf->vma->vm_flags & (VM_WRITE | VM_MAYWRITE))) {
+		vmf->page = ZERO_PAGE(vmf->vm_start);
+		get_page(vmf->page);
+		return 0;
+	}
+
+	mutex_lock(&ufile->umap_lock);
+	if (!ufile->disassociate_page)
+		ufile->disassociate_page =
+			alloc_pages(vmf->gfp_mask | __GFP_ZERO, 0);
+
+	if (ufile->disassociate_page) {
+		/*
+		 * This VMA is forced to always be shared so this doesn't have
+		 * to worry about COW.
+		 */
+		vmf->page = ufile->disassociate_page;
+		get_page(vmf->page);
+	} else {
+		ret = VM_FAULT_SIGBUS;
+	}
+	mutex_unlock(&ufile->umap_lock);
+
+	return ret;
+}
+
 static const struct vm_operations_struct rdma_umap_ops = {
 	.open = rdma_umap_open,
 	.close = rdma_umap_close,
+	.fault = rdma_umap_fault,
 };
 
 static struct rdma_umap_priv *rdma_user_mmap_pre(struct ib_ucontext *ucontext,
@@ -889,6 +933,9 @@ static struct rdma_umap_priv *rdma_user_mmap_pre(struct ib_ucontext *ucontext,
 	struct ib_uverbs_file *ufile = ucontext->ufile;
 	struct rdma_umap_priv *priv;
 
+	if (!(vma->vm_flags & VM_SHARED))
+		return ERR_PTR(-EINVAL);
+
 	if (vma->vm_end - vma->vm_start != size)
 		return ERR_PTR(-EINVAL);
 
@@ -992,7 +1039,7 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile)
 		 * at a time to get the lock ordering right. Typically there
 		 * will only be one mm, so no big deal.
 		 */
-		down_write(&mm->mmap_sem);
+		down_read(&mm->mmap_sem);
 		if (!mmget_still_valid(mm))
 			goto skip_mm;
 		mutex_lock(&ufile->umap_lock);
@@ -1006,11 +1053,10 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile)
 
 			zap_vma_ptes(vma, vma->vm_start,
 				     vma->vm_end - vma->vm_start);
-			vma->vm_flags &= ~(VM_SHARED | VM_MAYSHARE);
 		}
 		mutex_unlock(&ufile->umap_lock);
 	skip_mm:
-		up_write(&mm->mmap_sem);
+		up_read(&mm->mmap_sem);
 		mmput(mm);
 	}
 }
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index 66cdf625534f..60cf9f03e941 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -533,7 +533,7 @@ static int hns_roce_set_kernel_sq_size(struct hns_roce_dev *hr_dev,
 
 static int hns_roce_qp_has_sq(struct ib_qp_init_attr *attr)
 {
-	if (attr->qp_type == IB_QPT_XRC_TGT)
+	if (attr->qp_type == IB_QPT_XRC_TGT || !attr->cap.max_send_wr)
 		return 0;
 
 	return 1;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 531ff20b32ad..d3dd290ae1b1 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1119,6 +1119,8 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		if (MLX5_CAP_GEN(mdev, qp_packet_based))
 			resp.flags |=
 				MLX5_IB_QUERY_DEV_RESP_PACKET_BASED_CREDIT_MODE;
+
+		resp.flags |= MLX5_IB_QUERY_DEV_RESP_FLAGS_SCAT2CQE_DCT;
 	}
 
 	if (field_avail(typeof(resp), sw_parsing_caps,
@@ -2066,6 +2068,7 @@ static int mlx5_ib_mmap_clock_info_page(struct mlx5_ib_dev *dev,
 
 	if (vma->vm_flags & VM_WRITE)
 		return -EPERM;
+	vma->vm_flags &= ~VM_MAYWRITE;
 
 	if (!dev->mdev->clock_info_page)
 		return -EOPNOTSUPP;
@@ -2231,19 +2234,18 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm
 
 		if (vma->vm_flags & VM_WRITE)
 			return -EPERM;
+		vma->vm_flags &= ~VM_MAYWRITE;
 
 		/* Don't expose to user-space information it shouldn't have */
 		if (PAGE_SIZE > 4096)
 			return -EOPNOTSUPP;
 
-		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 		pfn = (dev->mdev->iseg_base +
 		       offsetof(struct mlx5_init_seg, internal_timer_h)) >>
 			PAGE_SHIFT;
-		if (io_remap_pfn_range(vma, vma->vm_start, pfn,
-				       PAGE_SIZE, vma->vm_page_prot))
-			return -EAGAIN;
-		break;
+		return rdma_user_mmap_io(&context->ibucontext, vma, pfn,
+					 PAGE_SIZE,
+					 pgprot_noncached(vma->vm_page_prot));
 	case MLX5_IB_MMAP_CLOCK_INFO:
 		return mlx5_ib_mmap_clock_info_page(dev, vma, context);
 
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 7cd006da1dae..8870c350fda0 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1818,13 +1818,16 @@ static void configure_responder_scat_cqe(struct ib_qp_init_attr *init_attr,
 
 	rcqe_sz = mlx5_ib_get_cqe_size(init_attr->recv_cq);
 
-	if (rcqe_sz == 128) {
-		MLX5_SET(qpc, qpc, cs_res, MLX5_RES_SCAT_DATA64_CQE);
+	if (init_attr->qp_type == MLX5_IB_QPT_DCT) {
+		if (rcqe_sz == 128)
+			MLX5_SET(dctc, qpc, cs_res, MLX5_RES_SCAT_DATA64_CQE);
+
 		return;
 	}
 
-	if (init_attr->qp_type != MLX5_IB_QPT_DCT)
-		MLX5_SET(qpc, qpc, cs_res, MLX5_RES_SCAT_DATA32_CQE);
+	MLX5_SET(qpc, qpc, cs_res,
+		 rcqe_sz == 128 ? MLX5_RES_SCAT_DATA64_CQE :
+				  MLX5_RES_SCAT_DATA32_CQE);
 }
 
 static void configure_requester_scat_cqe(struct mlx5_ib_dev *dev,
diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c
index 728795043496..0bb6e39dd03a 100644
--- a/drivers/infiniband/sw/rdmavt/mr.c
+++ b/drivers/infiniband/sw/rdmavt/mr.c
@@ -608,11 +608,6 @@ static int rvt_set_page(struct ib_mr *ibmr, u64 addr)
 	if (unlikely(mapped_segs == mr->mr.max_segs))
 		return -ENOMEM;
 
-	if (mr->mr.length == 0) {
-		mr->mr.user_base = addr;
-		mr->mr.iova = addr;
-	}
-
 	m = mapped_segs / RVT_SEGSZ;
 	n = mapped_segs % RVT_SEGSZ;
 	mr->mr.map[m]->segs[n].vaddr = (void *)addr;
@@ -630,17 +625,24 @@ static int rvt_set_page(struct ib_mr *ibmr, u64 addr)
  * @sg_nents: number of entries in sg
  * @sg_offset: offset in bytes into sg
  *
+ * Overwrite rvt_mr length with mr length calculated by ib_sg_to_pages.
+ *
  * Return: number of sg elements mapped to the memory region
  */
 int rvt_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg,
 		  int sg_nents, unsigned int *sg_offset)
 {
 	struct rvt_mr *mr = to_imr(ibmr);
+	int ret;
 
 	mr->mr.length = 0;
 	mr->mr.page_shift = PAGE_SHIFT;
-	return ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset,
-			      rvt_set_page);
+	ret = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, rvt_set_page);
+	mr->mr.user_base = ibmr->iova;
+	mr->mr.iova = ibmr->iova;
+	mr->mr.offset = ibmr->iova - (u64)mr->mr.map[0]->segs[0].vaddr;
+	mr->mr.length = (size_t)ibmr->length;
+	return ret;
 }
 
 /**
@@ -671,6 +673,7 @@ int rvt_fast_reg_mr(struct rvt_qp *qp, struct ib_mr *ibmr, u32 key,
 	ibmr->rkey = key;
 	mr->mr.lkey = key;
 	mr->mr.access_flags = access;
+	mr->mr.iova = ibmr->iova;
 	atomic_set(&mr->mr.lkey_invalid, 0);
 
 	return 0;
diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig
index a878351f1643..52d7f55fca32 100644
--- a/drivers/input/keyboard/Kconfig
+++ b/drivers/input/keyboard/Kconfig
@@ -420,7 +420,7 @@ config KEYBOARD_MPR121
 
 config KEYBOARD_SNVS_PWRKEY
 	tristate "IMX SNVS Power Key Driver"
-	depends on SOC_IMX6SX || SOC_IMX7D
+	depends on ARCH_MXC || COMPILE_TEST
 	depends on OF
 	help
 	  This is the snvs powerkey driver for the Freescale i.MX application
diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c
index fc3ab93b7aea..7fb358f96195 100644
--- a/drivers/input/rmi4/rmi_driver.c
+++ b/drivers/input/rmi4/rmi_driver.c
@@ -860,7 +860,7 @@ static int rmi_create_function(struct rmi_device *rmi_dev,
 
 	error = rmi_register_function(fn);
 	if (error)
-		goto err_put_fn;
+		return error;
 
 	if (pdt->function_number == 0x01)
 		data->f01_container = fn;
@@ -870,10 +870,6 @@ static int rmi_create_function(struct rmi_device *rmi_dev,
 	list_add_tail(&fn->node, &data->function_list);
 
 	return RMI_SCAN_CONTINUE;
-
-err_put_fn:
-	put_device(&fn->dev);
-	return error;
 }
 
 void rmi_enable_irq(struct rmi_device *rmi_dev, bool clear_wake)
diff --git a/drivers/input/rmi4/rmi_f11.c b/drivers/input/rmi4/rmi_f11.c
index df64d6aed4f7..93901ebd122a 100644
--- a/drivers/input/rmi4/rmi_f11.c
+++ b/drivers/input/rmi4/rmi_f11.c
@@ -1230,7 +1230,7 @@ static int rmi_f11_initialize(struct rmi_function *fn)
 	}
 
 	rc = f11_write_control_regs(fn, &f11->sens_query,
-			   &f11->dev_controls, fn->fd.query_base_addr);
+			   &f11->dev_controls, fn->fd.control_base_addr);
 	if (rc)
 		dev_warn(&fn->dev, "Failed to write control registers\n");
 
diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c
index f4e93f5fc204..ea90db3c7705 100644
--- a/drivers/net/slip/slhc.c
+++ b/drivers/net/slip/slhc.c
@@ -153,7 +153,7 @@ out_fail:
 void
 slhc_free(struct slcompress *comp)
 {
-	if ( comp == NULLSLCOMPR )
+	if ( IS_ERR_OR_NULL(comp) )
 		return;
 
 	if ( comp->tstate != NULLSLSTATE )
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 920bf3b4b0ef..cccc75d15970 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -7,6 +7,7 @@
 #include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
+#include <linux/sched/mm.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
@@ -427,9 +428,13 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
 	unsigned long this_sum_bytes = 0;
 	int i;
 	u64 offset;
+	unsigned nofs_flag;
+
+	nofs_flag = memalloc_nofs_save();
+	sums = kvzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size),
+		       GFP_KERNEL);
+	memalloc_nofs_restore(nofs_flag);
 
-	sums = kzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size),
-		       GFP_NOFS);
 	if (!sums)
 		return BLK_STS_RESOURCE;
 
@@ -472,8 +477,10 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
 
 				bytes_left = bio->bi_iter.bi_size - total_bytes;
 
-				sums = kzalloc(btrfs_ordered_sum_size(fs_info, bytes_left),
-					       GFP_NOFS);
+				nofs_flag = memalloc_nofs_save();
+				sums = kvzalloc(btrfs_ordered_sum_size(fs_info,
+						      bytes_left), GFP_KERNEL);
+				memalloc_nofs_restore(nofs_flag);
 				BUG_ON(!sums); /* -ENOMEM */
 				sums->len = bytes_left;
 				ordered = btrfs_lookup_ordered_extent(inode,
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 6fde2b2741ef..45e3cfd1198b 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -6,6 +6,7 @@
 #include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/writeback.h>
+#include <linux/sched/mm.h>
 #include "ctree.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
@@ -442,7 +443,7 @@ void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry)
 			cur = entry->list.next;
 			sum = list_entry(cur, struct btrfs_ordered_sum, list);
 			list_del(&sum->list);
-			kfree(sum);
+			kvfree(sum);
 		}
 		kmem_cache_free(btrfs_ordered_extent_cache, entry);
 	}
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 9c0ccc06d172..7037a137fa53 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2877,7 +2877,6 @@ static void collect_uncached_write_data(struct cifs_aio_ctx *ctx)
 	struct cifs_tcon *tcon;
 	struct cifs_sb_info *cifs_sb;
 	struct dentry *dentry = ctx->cfile->dentry;
-	unsigned int i;
 	int rc;
 
 	tcon = tlink_tcon(ctx->cfile->tlink);
@@ -2941,10 +2940,6 @@ restart_loop:
 		kref_put(&wdata->refcount, cifs_uncached_writedata_release);
 	}
 
-	if (!ctx->direct_io)
-		for (i = 0; i < ctx->npages; i++)
-			put_page(ctx->bv[i].bv_page);
-
 	cifs_stats_bytes_written(tcon, ctx->total_len);
 	set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(dentry->d_inode)->flags);
 
@@ -3582,7 +3577,6 @@ collect_uncached_read_data(struct cifs_aio_ctx *ctx)
 	struct iov_iter *to = &ctx->iter;
 	struct cifs_sb_info *cifs_sb;
 	struct cifs_tcon *tcon;
-	unsigned int i;
 	int rc;
 
 	tcon = tlink_tcon(ctx->cfile->tlink);
@@ -3666,15 +3660,8 @@ again:
 		kref_put(&rdata->refcount, cifs_uncached_readdata_release);
 	}
 
-	if (!ctx->direct_io) {
-		for (i = 0; i < ctx->npages; i++) {
-			if (ctx->should_dirty)
-				set_page_dirty(ctx->bv[i].bv_page);
-			put_page(ctx->bv[i].bv_page);
-		}
-
+	if (!ctx->direct_io)
 		ctx->total_len = ctx->len - iov_iter_count(to);
-	}
 
 	/* mask nodata case */
 	if (rc == -ENODATA)
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 53fdb5df0d2e..538fd7d807e4 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1735,6 +1735,10 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry,
 	if (rc == 0 || rc != -EBUSY)
 		goto do_rename_exit;
 
+	/* Don't fall back to using SMB on SMB 2+ mount */
+	if (server->vals->protocol_id != 0)
+		goto do_rename_exit;
+
 	/* open-file renames don't work across directories */
 	if (to_dentry->d_parent != from_dentry->d_parent)
 		goto do_rename_exit;
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 1e1626a2cfc3..0dc6f08020ac 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -789,6 +789,11 @@ cifs_aio_ctx_alloc(void)
 {
 	struct cifs_aio_ctx *ctx;
 
+	/*
+	 * Must use kzalloc to initialize ctx->bv to NULL and ctx->direct_io
+	 * to false so that we know when we have to unreference pages within
+	 * cifs_aio_ctx_release()
+	 */
 	ctx = kzalloc(sizeof(struct cifs_aio_ctx), GFP_KERNEL);
 	if (!ctx)
 		return NULL;
@@ -807,7 +812,23 @@ cifs_aio_ctx_release(struct kref *refcount)
 					struct cifs_aio_ctx, refcount);
 
 	cifsFileInfo_put(ctx->cfile);
-	kvfree(ctx->bv);
+
+	/*
+	 * ctx->bv is only set if setup_aio_ctx_iter() was call successfuly
+	 * which means that iov_iter_get_pages() was a success and thus that
+	 * we have taken reference on pages.
+	 */
+	if (ctx->bv) {
+		unsigned i;
+
+		for (i = 0; i < ctx->npages; i++) {
+			if (ctx->should_dirty)
+				set_page_dirty(ctx->bv[i].bv_page);
+			put_page(ctx->bv[i].bv_page);
+		}
+		kvfree(ctx->bv);
+	}
+
 	kfree(ctx);
 }
 
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index b8f7262ac354..a37774a55f3a 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -3466,6 +3466,7 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
 				    io_parms->tcon->tid, ses->Suid,
 				    io_parms->offset, 0);
 		free_rsp_buf(resp_buftype, rsp_iov.iov_base);
+		cifs_small_buf_release(req);
 		return rc == -ENODATA ? 0 : rc;
 	} else
 		trace_smb3_read_done(xid, req->PersistentFileId,
diff --git a/fs/io_uring.c b/fs/io_uring.c
index f65f85d89217..0e9fb2cb1984 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -740,7 +740,7 @@ static bool io_file_supports_async(struct file *file)
 }
 
 static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
-		      bool force_nonblock, struct io_submit_state *state)
+		      bool force_nonblock)
 {
 	const struct io_uring_sqe *sqe = s->sqe;
 	struct io_ring_ctx *ctx = req->ctx;
@@ -938,7 +938,7 @@ static void io_async_list_note(int rw, struct io_kiocb *req, size_t len)
 }
 
 static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
-		   bool force_nonblock, struct io_submit_state *state)
+		   bool force_nonblock)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct kiocb *kiocb = &req->rw;
@@ -947,7 +947,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
 	size_t iov_count;
 	int ret;
 
-	ret = io_prep_rw(req, s, force_nonblock, state);
+	ret = io_prep_rw(req, s, force_nonblock);
 	if (ret)
 		return ret;
 	file = kiocb->ki_filp;
@@ -985,7 +985,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
 }
 
 static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
-		    bool force_nonblock, struct io_submit_state *state)
+		    bool force_nonblock)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct kiocb *kiocb = &req->rw;
@@ -994,7 +994,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
 	size_t iov_count;
 	int ret;
 
-	ret = io_prep_rw(req, s, force_nonblock, state);
+	ret = io_prep_rw(req, s, force_nonblock);
 	if (ret)
 		return ret;
 
@@ -1336,8 +1336,7 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 }
 
 static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
-			   const struct sqe_submit *s, bool force_nonblock,
-			   struct io_submit_state *state)
+			   const struct sqe_submit *s, bool force_nonblock)
 {
 	int ret, opcode;
 
@@ -1353,18 +1352,18 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	case IORING_OP_READV:
 		if (unlikely(s->sqe->buf_index))
 			return -EINVAL;
-		ret = io_read(req, s, force_nonblock, state);
+		ret = io_read(req, s, force_nonblock);
 		break;
 	case IORING_OP_WRITEV:
 		if (unlikely(s->sqe->buf_index))
 			return -EINVAL;
-		ret = io_write(req, s, force_nonblock, state);
+		ret = io_write(req, s, force_nonblock);
 		break;
 	case IORING_OP_READ_FIXED:
-		ret = io_read(req, s, force_nonblock, state);
+		ret = io_read(req, s, force_nonblock);
 		break;
 	case IORING_OP_WRITE_FIXED:
-		ret = io_write(req, s, force_nonblock, state);
+		ret = io_write(req, s, force_nonblock);
 		break;
 	case IORING_OP_FSYNC:
 		ret = io_fsync(req, s->sqe, force_nonblock);
@@ -1457,7 +1456,7 @@ restart:
 			s->has_user = cur_mm != NULL;
 			s->needs_lock = true;
 			do {
-				ret = __io_submit_sqe(ctx, req, s, false, NULL);
+				ret = __io_submit_sqe(ctx, req, s, false);
 				/*
 				 * We can get EAGAIN for polled IO even though
 				 * we're forcing a sync submission from here,
@@ -1623,7 +1622,7 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
 	if (unlikely(ret))
 		goto out;
 
-	ret = __io_submit_sqe(ctx, req, s, true, state);
+	ret = __io_submit_sqe(ctx, req, s, true);
 	if (ret == -EAGAIN) {
 		struct io_uring_sqe *sqe_copy;
 
@@ -1739,7 +1738,8 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
 	head = ctx->cached_sq_head;
 	/* See comment at the top of this file */
 	smp_rmb();
-	if (head == READ_ONCE(ring->r.tail))
+	/* make sure SQ entry isn't read before tail */
+	if (head == smp_load_acquire(&ring->r.tail))
 		return false;
 
 	head = READ_ONCE(ring->array[head & ctx->sq_mask]);
@@ -1864,7 +1864,8 @@ static int io_sq_thread(void *data)
 
 			/* Tell userspace we may need a wakeup call */
 			ctx->sq_ring->flags |= IORING_SQ_NEED_WAKEUP;
-			smp_wmb();
+			/* make sure to read SQ tail after writing flags */
+			smp_mb();
 
 			if (!io_get_sqring(ctx, &sqes[0])) {
 				if (kthread_should_stop()) {
@@ -2574,7 +2575,8 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait)
 	poll_wait(file, &ctx->cq_wait, wait);
 	/* See comment at the top of this file */
 	smp_rmb();
-	if (READ_ONCE(ctx->sq_ring->r.tail) + 1 != ctx->cached_sq_head)
+	if (READ_ONCE(ctx->sq_ring->r.tail) - ctx->cached_sq_head !=
+	    ctx->sq_ring->ring_entries)
 		mask |= EPOLLOUT | EPOLLWRNORM;
 	if (READ_ONCE(ctx->cq_ring->r.head) != ctx->cached_cq_tail)
 		mask |= EPOLLIN | EPOLLRDNORM;
@@ -2934,6 +2936,14 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 {
 	int ret;
 
+	/*
+	 * We're inside the ring mutex, if the ref is already dying, then
+	 * someone else killed the ctx or is already going through
+	 * io_uring_register().
+	 */
+	if (percpu_ref_is_dying(&ctx->refs))
+		return -ENXIO;
+
 	percpu_ref_kill(&ctx->refs);
 
 	/*
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index d65390727541..7325baa8f9d4 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -1626,9 +1626,11 @@ static void drop_sysctl_table(struct ctl_table_header *header)
 	if (--header->nreg)
 		return;
 
-	if (parent)
+	if (parent) {
 		put_links(header);
-	start_unregistering(header);
+		start_unregistering(header);
+	}
+
 	if (!--header->count)
 		kfree_rcu(header, rcu);
 
diff --git a/fs/splice.c b/fs/splice.c
index 98943d9b219c..25212dcca2df 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -330,8 +330,8 @@ const struct pipe_buf_operations default_pipe_buf_ops = {
 	.get = generic_pipe_buf_get,
 };
 
-static int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe,
-				    struct pipe_buffer *buf)
+int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe,
+			     struct pipe_buffer *buf)
 {
 	return 1;
 }
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index cbf3180cb612..668ad971cd7b 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -420,7 +420,6 @@ extern struct ttm_bo_global {
 	/**
 	 * Protected by ttm_global_mutex.
 	 */
-	unsigned int use_count;
 	struct list_head device_list;
 
 	/**
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index abb2dac3da9b..5c626fdc10db 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -176,6 +176,7 @@ void free_pipe_info(struct pipe_inode_info *);
 bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);
+int generic_pipe_buf_nosteal(struct pipe_inode_info *, struct pipe_buffer *);
 void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *);
 void pipe_buf_mark_unmergeable(struct pipe_buffer *buf);
 
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index 87b3198f4b5d..f4d4010b7e3e 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -238,6 +238,7 @@ enum mlx5_ib_query_dev_resp_flags {
 	MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_COMP = 1 << 0,
 	MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_PAD  = 1 << 1,
 	MLX5_IB_QUERY_DEV_RESP_PACKET_BASED_CREDIT_MODE = 1 << 2,
+	MLX5_IB_QUERY_DEV_RESP_FLAGS_SCAT2CQE_DCT = 1 << 3,
 };
 
 enum mlx5_ib_tunnel_offloads {
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a4d9e14bf138..35f3ea375084 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2007,6 +2007,10 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
 	if (p->last_task_numa_placement) {
 		delta = runtime - p->last_sum_exec_runtime;
 		*period = now - p->last_task_numa_placement;
+
+		/* Avoid time going backwards, prevent potential divide error: */
+		if (unlikely((s64)*period < 0))
+			*period = 0;
 	} else {
 		delta = p->se.avg.load_sum;
 		*period = LOAD_AVG_MAX;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 41b6f96e5366..4ee8d8aa3d0f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -762,7 +762,7 @@ u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu)
 
 	preempt_disable_notrace();
 	time = rb_time_stamp(buffer);
-	preempt_enable_no_resched_notrace();
+	preempt_enable_notrace();
 
 	return time;
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 6c24755655c7..ca1ee656d6d8 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -496,8 +496,10 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 	 * not modified.
 	 */
 	pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL);
-	if (!pid_list)
+	if (!pid_list) {
+		trace_parser_put(&parser);
 		return -ENOMEM;
+	}
 
 	pid_list->pid_max = READ_ONCE(pid_max);
 
@@ -507,6 +509,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 
 	pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3);
 	if (!pid_list->pids) {
+		trace_parser_put(&parser);
 		kfree(pid_list);
 		return -ENOMEM;
 	}
@@ -7025,19 +7028,23 @@ struct buffer_ref {
 	struct ring_buffer	*buffer;
 	void			*page;
 	int			cpu;
-	int			ref;
+	refcount_t		refcount;
 };
 
+static void buffer_ref_release(struct buffer_ref *ref)
+{
+	if (!refcount_dec_and_test(&ref->refcount))
+		return;
+	ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
+	kfree(ref);
+}
+
 static void buffer_pipe_buf_release(struct pipe_inode_info *pipe,
 				    struct pipe_buffer *buf)
 {
 	struct buffer_ref *ref = (struct buffer_ref *)buf->private;
 
-	if (--ref->ref)
-		return;
-
-	ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
-	kfree(ref);
+	buffer_ref_release(ref);
 	buf->private = 0;
 }
 
@@ -7046,10 +7053,10 @@ static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe,
 {
 	struct buffer_ref *ref = (struct buffer_ref *)buf->private;
 
-	if (ref->ref > INT_MAX/2)
+	if (refcount_read(&ref->refcount) > INT_MAX/2)
 		return false;
 
-	ref->ref++;
+	refcount_inc(&ref->refcount);
 	return true;
 }
 
@@ -7057,7 +7064,7 @@ static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe,
 static const struct pipe_buf_operations buffer_pipe_buf_ops = {
 	.confirm		= generic_pipe_buf_confirm,
 	.release		= buffer_pipe_buf_release,
-	.steal			= generic_pipe_buf_steal,
+	.steal			= generic_pipe_buf_nosteal,
 	.get			= buffer_pipe_buf_get,
 };
 
@@ -7070,11 +7077,7 @@ static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i)
 	struct buffer_ref *ref =
 		(struct buffer_ref *)spd->partial[i].private;
 
-	if (--ref->ref)
-		return;
-
-	ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
-	kfree(ref);
+	buffer_ref_release(ref);
 	spd->partial[i].private = 0;
 }
 
@@ -7129,7 +7132,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			break;
 		}
 
-		ref->ref = 1;
+		refcount_set(&ref->refcount, 1);
 		ref->buffer = iter->trace_buffer->buffer;
 		ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file);
 		if (IS_ERR(ref->page)) {
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 00dbcdbc9a0d..d5a4a4036d2f 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1929,6 +1929,7 @@ config TEST_KMOD
 	depends on m
 	depends on BLOCK && (64BIT || LBDAF)	  # for XFS, BTRFS
 	depends on NETDEVICES && NET_CORE && INET # for TUN
+	depends on BLOCK
 	select TEST_LKM
 	select XFS_FS
 	select TUN
diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c
index 83cdcaa82bf6..f832b095afba 100644
--- a/lib/test_vmalloc.c
+++ b/lib/test_vmalloc.c
@@ -383,14 +383,14 @@ static void shuffle_array(int *arr, int n)
 static int test_func(void *private)
 {
 	struct test_driver *t = private;
-	cpumask_t newmask = CPU_MASK_NONE;
 	int random_array[ARRAY_SIZE(test_case_array)];
 	int index, i, j, ret;
 	ktime_t kt;
 	u64 delta;
 
-	cpumask_set_cpu(t->cpu, &newmask);
-	set_cpus_allowed_ptr(current, &newmask);
+	ret = set_cpus_allowed_ptr(current, cpumask_of(t->cpu));
+	if (ret < 0)
+		pr_err("Failed to set affinity to %d CPU\n", t->cpu);
 
 	for (i = 0; i < ARRAY_SIZE(test_case_array); i++)
 		random_array[i] = i;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 0082d699be94..b236069ff0d8 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -874,6 +874,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 	 */
 	mem = find_memory_block(__pfn_to_section(pfn));
 	nid = mem->nid;
+	put_device(&mem->dev);
 
 	/* associate pfn range with the zone */
 	zone = move_pfn_range(online_type, nid, pfn, nr_pages);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c6ce20aaf80b..c02cff1ed56e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -266,7 +266,20 @@ compound_page_dtor * const compound_page_dtors[] = {
 
 int min_free_kbytes = 1024;
 int user_min_free_kbytes = -1;
+#ifdef CONFIG_DISCONTIGMEM
+/*
+ * DiscontigMem defines memory ranges as separate pg_data_t even if the ranges
+ * are not on separate NUMA nodes. Functionally this works but with
+ * watermark_boost_factor, it can reclaim prematurely as the ranges can be
+ * quite small. By default, do not boost watermarks on discontigmem as in
+ * many cases very high-order allocations like THP are likely to be
+ * unsupported and the premature reclaim offsets the advantage of long-term
+ * fragmentation avoidance.
+ */
+int watermark_boost_factor __read_mostly;
+#else
 int watermark_boost_factor __read_mostly = 15000;
+#endif
 int watermark_scale_factor = 10;
 
 static unsigned long nr_kernel_pages __initdata;
@@ -3419,8 +3432,11 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
 		alloc_flags |= ALLOC_KSWAPD;
 
 #ifdef CONFIG_ZONE_DMA32
+	if (!zone)
+		return alloc_flags;
+
 	if (zone_idx(zone) != ZONE_NORMAL)
-		goto out;
+		return alloc_flags;
 
 	/*
 	 * If ZONE_DMA32 exists, assume it is the one after ZONE_NORMAL and
@@ -3429,9 +3445,9 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
 	 */
 	BUILD_BUG_ON(ZONE_NORMAL - ZONE_DMA32 != 1);
 	if (nr_online_nodes > 1 && !populated_zone(--zone))
-		goto out;
+		return alloc_flags;
 
-out:
+	alloc_flags |= ALLOC_NOFRAGMENT;
 #endif /* CONFIG_ZONE_DMA32 */
 	return alloc_flags;
 }
@@ -3773,11 +3789,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	memalloc_noreclaim_restore(noreclaim_flag);
 	psi_memstall_leave(&pflags);
 
-	if (*compact_result <= COMPACT_INACTIVE) {
-		WARN_ON_ONCE(page);
-		return NULL;
-	}
-
 	/*
 	 * At least in one zone compaction wasn't deferred or skipped, so let's
 	 * count a compaction stall