Merge branch 'akpm/master'

56 files changed, 1375 insertions, 1283 deletions

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 960108560ab2..08c9e56c66ec 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -556,7 +556,7 @@ till "end_pgoff". ->map_pages() is called with page table locked and must
 not block.  If it's not possible to reach a page without blocking,
 filesystem should skip it. Filesystem should use do_set_pte() to setup
 page table entry. Pointer to entry associated with the page is passed in
-"pte" field in fault_env structure. Pointers to entries for other offsets
+"pte" field in vm_fault structure. Pointers to entries for other offsets
 should be calculated relative to "pte".
 
 	->page_mkwrite() is called when a previously read-only pte is
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index 06254467e4dd..3a147122bc98 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -236,7 +236,6 @@ static int
 spufs_mem_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct spu_context *ctx	= vma->vm_file->private_data;
-	unsigned long address = (unsigned long)vmf->virtual_address;
 	unsigned long pfn, offset;
 
 	offset = vmf->pgoff << PAGE_SHIFT;
@@ -244,7 +243,7 @@ spufs_mem_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		return VM_FAULT_SIGBUS;
 
 	pr_debug("spufs_mem_mmap_fault address=0x%lx, offset=0x%lx\n",
-			address, offset);
+			vmf->address, offset);
 
 	if (spu_acquire(ctx))
 		return VM_FAULT_NOPAGE;
@@ -256,7 +255,7 @@ spufs_mem_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		vma->vm_page_prot = pgprot_noncached_wc(vma->vm_page_prot);
 		pfn = (ctx->spu->local_store_phys + offset) >> PAGE_SHIFT;
 	}
-	vm_insert_pfn(vma, address, pfn);
+	vm_insert_pfn(vma, vmf->address, pfn);
 
 	spu_release(ctx);
 
@@ -355,8 +354,7 @@ static int spufs_ps_fault(struct vm_area_struct *vma,
 		down_read(&current->mm->mmap_sem);
 	} else {
 		area = ctx->spu->problem_phys + ps_offs;
-		vm_insert_pfn(vma, (unsigned long)vmf->virtual_address,
-					(area + offset) >> PAGE_SHIFT);
+		vm_insert_pfn(vma, vmf->address, (area + offset) >> PAGE_SHIFT);
 		spu_context_trace(spufs_ps_fault__insert, ctx, ctx->spu);
 	}
 
diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c
index a9973bb4a1b2..95e73c63c99d 100644
--- a/arch/sparc/kernel/nmi.c
+++ b/arch/sparc/kernel/nmi.c
@@ -42,7 +42,7 @@ static int panic_on_timeout;
  */
 atomic_t nmi_active = ATOMIC_INIT(0);		/* oprofile uses this */
 EXPORT_SYMBOL(nmi_active);
-
+static int nmi_init_done;
 static unsigned int nmi_hz = HZ;
 static DEFINE_PER_CPU(short, wd_enabled);
 static int endflag __initdata;
@@ -153,6 +153,8 @@ static void report_broken_nmi(int cpu, int *prev_nmi_count)
 
 void stop_nmi_watchdog(void *unused)
 {
+	if (!__this_cpu_read(wd_enabled))
+		return;
 	pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable);
 	__this_cpu_write(wd_enabled, 0);
 	atomic_dec(&nmi_active);
@@ -207,6 +209,9 @@ error:
 
 void start_nmi_watchdog(void *unused)
 {
+	if (__this_cpu_read(wd_enabled))
+		return;
+
 	__this_cpu_write(wd_enabled, 1);
 	atomic_inc(&nmi_active);
 
@@ -259,6 +264,8 @@ int __init nmi_init(void)
 		}
 	}
 
+	nmi_init_done = 1;
+
 	return err;
 }
 
@@ -270,3 +277,38 @@ static int __init setup_nmi_watchdog(char *str)
 	return 0;
 }
 __setup("nmi_watchdog=", setup_nmi_watchdog);
+
+/*
+ * sparc specific NMI watchdog enable function.
+ * Enables watchdog if it is not enabled already.
+ */
+int watchdog_nmi_enable(unsigned int cpu)
+{
+	if (atomic_read(&nmi_active) == -1) {
+		pr_warn("NMI watchdog cannot be enabled or disabled\n");
+		return -1;
+	}
+
+	/*
+	 * watchdog thread could start even before nmi_init is called.
+	 * Just Return in that case. Let nmi_init finish the init
+	 * process first.
+	 */
+	if (!nmi_init_done)
+		return 0;
+
+	smp_call_function_single(cpu, start_nmi_watchdog, NULL, 1);
+
+	return 0;
+}
+/*
+ * sparc specific NMI watchdog disable function.
+ * Disables watchdog if it is not disabled already.
+ */
+void watchdog_nmi_disable(unsigned int cpu)
+{
+	if (atomic_read(&nmi_active) == -1)
+		pr_warn_once("NMI watchdog cannot be enabled or disabled\n");
+	else
+		smp_call_function_single(cpu, stop_nmi_watchdog, NULL, 1);
+}
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index e739002427ed..40121d14d34d 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -109,7 +109,7 @@ static int vvar_fault(const struct vm_special_mapping *sm,
 		return VM_FAULT_SIGBUS;
 
 	if (sym_offset == image->sym_vvar_page) {
-		ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address,
+		ret = vm_insert_pfn(vma, vmf->address,
 				    __pa_symbol(&__vvar_page) >> PAGE_SHIFT);
 	} else if (sym_offset == image->sym_pvclock_page) {
 		struct pvclock_vsyscall_time_info *pvti =
@@ -117,7 +117,7 @@ static int vvar_fault(const struct vm_special_mapping *sm,
 		if (pvti && vclock_was_used(VCLOCK_PVCLOCK)) {
 			ret = vm_insert_pfn(
 				vma,
-				(unsigned long)vmf->virtual_address,
+				vmf->address,
 				__pa(pvti) >> PAGE_SHIFT);
 		}
 	}
diff --git a/drivers/char/agp/alpha-agp.c b/drivers/char/agp/alpha-agp.c
index 199b8e99f7d7..737187865269 100644
--- a/drivers/char/agp/alpha-agp.c
+++ b/drivers/char/agp/alpha-agp.c
@@ -19,8 +19,7 @@ static int alpha_core_agp_vm_fault(struct vm_area_struct *vma,
 	unsigned long pa;
 	struct page *page;
 
-	dma_addr = (unsigned long)vmf->virtual_address - vma->vm_start
-						+ agp->aperture.bus_base;
+	dma_addr = vmf->address - vma->vm_start + agp->aperture.bus_base;
 	pa = agp->ops->translate(agp, dma_addr);
 
 	if (pa == (unsigned long)-EINVAL)
diff --git a/drivers/char/mspec.c b/drivers/char/mspec.c
index f3f92d5fcda0..a697ca0cab1e 100644
--- a/drivers/char/mspec.c
+++ b/drivers/char/mspec.c
@@ -227,7 +227,7 @@ mspec_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	 * be because another thread has installed the pte first, so it
 	 * is no problem.
 	 */
-	vm_insert_pfn(vma, (unsigned long)vmf->virtual_address, pfn);
+	vm_insert_pfn(vma, vmf->address, pfn);
 
 	return VM_FAULT_NOPAGE;
 }
diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index 3d94ff20fdca..028b56ab9e31 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -328,7 +328,6 @@ static phys_addr_t pgoff_to_phys(struct dax_dev *dax_dev, pgoff_t pgoff,
 static int __dax_dev_fault(struct dax_dev *dax_dev, struct vm_area_struct *vma,
 		struct vm_fault *vmf)
 {
-	unsigned long vaddr = (unsigned long) vmf->virtual_address;
 	struct device *dev = &dax_dev->dev;
 	struct dax_region *dax_region;
 	int rc = VM_FAULT_SIGBUS;
@@ -353,7 +352,7 @@ static int __dax_dev_fault(struct dax_dev *dax_dev, struct vm_area_struct *vma,
 
 	pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
 
-	rc = vm_insert_mixed(vma, vaddr, pfn);
+	rc = vm_insert_mixed(vma, vmf->address, pfn);
 
 	if (rc == -ENOMEM)
 		return VM_FAULT_OOM;
diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c
index 768087ddb046..a293c8be232c 100644
--- a/drivers/gpu/drm/armada/armada_gem.c
+++ b/drivers/gpu/drm/armada/armada_gem.c
@@ -17,12 +17,11 @@
 static int armada_gem_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct armada_gem_object *obj = drm_to_armada_gem(vma->vm_private_data);
-	unsigned long addr = (unsigned long)vmf->virtual_address;
 	unsigned long pfn = obj->phys_addr >> PAGE_SHIFT;
 	int ret;
 
-	pfn += (addr - vma->vm_start) >> PAGE_SHIFT;
-	ret = vm_insert_pfn(vma, addr, pfn);
+	pfn += (vmf->address - vma->vm_start) >> PAGE_SHIFT;
+	ret = vm_insert_pfn(vma, vmf->address, pfn);
 
 	switch (ret) {
 	case 0:
diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
index caa4e4ca616d..bd311c77c254 100644
--- a/drivers/gpu/drm/drm_vm.c
+++ b/drivers/gpu/drm/drm_vm.c
@@ -124,8 +124,7 @@ static int drm_do_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		 * Using vm_pgoff as a selector forces us to use this unusual
 		 * addressing scheme.
 		 */
-		resource_size_t offset = (unsigned long)vmf->virtual_address -
-			vma->vm_start;
+		resource_size_t offset = vmf->address - vma->vm_start;
 		resource_size_t baddr = map->offset + offset;
 		struct drm_agp_mem *agpmem;
 		struct page *page;
@@ -195,7 +194,7 @@ static int drm_do_vm_shm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (!map)
 		return VM_FAULT_SIGBUS;	/* Nothing allocated */
 
-	offset = (unsigned long)vmf->virtual_address - vma->vm_start;
+	offset = vmf->address - vma->vm_start;
 	i = (unsigned long)map->handle + offset;
 	page = vmalloc_to_page((void *)i);
 	if (!page)
@@ -301,7 +300,8 @@ static int drm_do_vm_dma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (!dma->pagelist)
 		return VM_FAULT_SIGBUS;	/* Nothing allocated */
 
-	offset = (unsigned long)vmf->virtual_address - vma->vm_start;	/* vm_[pg]off[set] should be 0 */
+	offset = vmf->address - vma->vm_start;
+					/* vm_[pg]off[set] should be 0 */
 	page_nr = offset >> PAGE_SHIFT; /* page_nr could just be vmf->pgoff */
 	page = virt_to_page((void *)dma->pagelist[page_nr]);
 
@@ -337,7 +337,7 @@ static int drm_do_vm_sg_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (!entry->pagelist)
 		return VM_FAULT_SIGBUS;	/* Nothing allocated */
 
-	offset = (unsigned long)vmf->virtual_address - vma->vm_start;
+	offset = vmf->address - vma->vm_start;
 	map_offset = map->offset - (unsigned long)dev->sg->virtual;
 	page_offset = (offset >> PAGE_SHIFT) + (map_offset >> PAGE_SHIFT);
 	page = entry->pagelist[page_offset];
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index 7d066a91d778..114dddbd297b 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -202,15 +202,14 @@ int etnaviv_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	}
 
 	/* We don't use vmf->pgoff since that has the fake offset: */
-	pgoff = ((unsigned long)vmf->virtual_address -
-			vma->vm_start) >> PAGE_SHIFT;
+	pgoff = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
 
 	page = pages[pgoff];
 
-	VERB("Inserting %p pfn %lx, pa %lx", vmf->virtual_address,
+	VERB("Inserting %p pfn %lx, pa %lx", (void *)vmf->address,
 	     page_to_pfn(page), page_to_pfn(page) << PAGE_SHIFT);
 
-	ret = vm_insert_page(vma, (unsigned long)vmf->virtual_address, page);
+	ret = vm_insert_page(vma, vmf->address, page);
 
 out:
 	switch (ret) {
@@ -759,7 +758,7 @@ static struct page **etnaviv_gem_userptr_do_get_pages(
 	down_read(&mm->mmap_sem);
 	while (pinned < npages) {
 		ret = get_user_pages_remote(task, mm, ptr, npages - pinned,
-					    flags, pvec + pinned, NULL);
+					    flags, pvec + pinned, NULL, NULL);
 		if (ret < 0)
 			break;
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index f2ae72ba7d5a..5cfa5121e805 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -455,8 +455,7 @@ int exynos_drm_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	pgoff_t page_offset;
 	int ret;
 
-	page_offset = ((unsigned long)vmf->virtual_address -
-			vma->vm_start) >> PAGE_SHIFT;
+	page_offset = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
 
 	if (page_offset >= (exynos_gem->size >> PAGE_SHIFT)) {
 		DRM_ERROR("invalid page offset\n");
@@ -465,8 +464,7 @@ int exynos_drm_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	}
 
 	pfn = page_to_pfn(exynos_gem->pages[page_offset]);
-	ret = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address,
-			__pfn_to_pfn_t(pfn, PFN_DEV));
+	ret = vm_insert_mixed(vma, vmf->address, __pfn_to_pfn_t(pfn, PFN_DEV));
 
 out:
 	switch (ret) {
diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c
index 4071b2d1e8cf..8b44fa542562 100644
--- a/drivers/gpu/drm/gma500/framebuffer.c
+++ b/drivers/gpu/drm/gma500/framebuffer.c
@@ -125,7 +125,7 @@ static int psbfb_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 				  psbfb->gtt->offset;
 
 	page_num = vma_pages(vma);
-	address = (unsigned long)vmf->virtual_address - (vmf->pgoff << PAGE_SHIFT);
+	address = vmf->address - (vmf->pgoff << PAGE_SHIFT);
 
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
diff --git a/drivers/gpu/drm/gma500/gem.c b/drivers/gpu/drm/gma500/gem.c
index 6d1cb6b370b1..527c62917660 100644
--- a/drivers/gpu/drm/gma500/gem.c
+++ b/drivers/gpu/drm/gma500/gem.c
@@ -197,15 +197,14 @@ int psb_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 	/* Page relative to the VMA start - we must calculate this ourselves
 	   because vmf->pgoff is the fake GEM offset */
-	page_offset = ((unsigned long) vmf->virtual_address - vma->vm_start)
-				>> PAGE_SHIFT;
+	page_offset = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
 
 	/* CPU view of the page, don't go via the GART for CPU writes */
 	if (r->stolen)
 		pfn = (dev_priv->stolen_base + r->offset) >> PAGE_SHIFT;
 	else
 		pfn = page_to_pfn(r->pages[page_offset]);
-	ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address, pfn);
+	ret = vm_insert_pfn(vma, vmf->address, pfn);
 
 fail:
 	mutex_unlock(&dev_priv->mmap_mutex);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 902fa427c196..8f2d0eb66b81 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1796,8 +1796,7 @@ int i915_gem_fault(struct vm_area_struct *area, struct vm_fault *vmf)
 	int ret;
 
 	/* We don't use vmf->pgoff since that has the fake offset */
-	page_offset = ((unsigned long)vmf->virtual_address - area->vm_start) >>
-		PAGE_SHIFT;
+	page_offset = (vmf->address - area->vm_start) >> PAGE_SHIFT;
 
 	trace_i915_gem_object_fault(obj, page_offset, true, write);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 107ddf51065e..d068af2ec3a3 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -515,7 +515,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 					 obj->userptr.ptr + pinned * PAGE_SIZE,
 					 npages - pinned,
 					 flags,
-					 pvec + pinned, NULL);
+					 pvec + pinned, NULL, NULL);
 				if (ret < 0)
 					break;
 
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 57db7dbbb618..a40be13b519e 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -225,16 +225,14 @@ int msm_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	}
 
 	/* We don't use vmf->pgoff since that has the fake offset: */
-	pgoff = ((unsigned long)vmf->virtual_address -
-			vma->vm_start) >> PAGE_SHIFT;
+	pgoff = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
 
 	pfn = page_to_pfn(pages[pgoff]);
 
-	VERB("Inserting %p pfn %lx, pa %lx", vmf->virtual_address,
+	VERB("Inserting %p pfn %lx, pa %lx", (void *)vmf->address,
 			pfn, pfn << PAGE_SHIFT);
 
-	ret = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address,
-			__pfn_to_pfn_t(pfn, PFN_DEV));
+	ret = vm_insert_mixed(vma, vmf->address, __pfn_to_pfn_t(pfn, PFN_DEV));
 
 out_unlock:
 	mutex_unlock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index d4e1e11466f8..4a90c690f09e 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -398,8 +398,7 @@ static int fault_1d(struct drm_gem_object *obj,
 	pgoff_t pgoff;
 
 	/* We don't use vmf->pgoff since that has the fake offset: */
-	pgoff = ((unsigned long)vmf->virtual_address -
-			vma->vm_start) >> PAGE_SHIFT;
+	pgoff = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
 
 	if (omap_obj->pages) {
 		omap_gem_cpu_sync(obj, pgoff);
@@ -409,11 +408,10 @@ static int fault_1d(struct drm_gem_object *obj,
 		pfn = (omap_obj->paddr >> PAGE_SHIFT) + pgoff;
 	}
 
-	VERB("Inserting %p pfn %lx, pa %lx", vmf->virtual_address,
+	VERB("Inserting %p pfn %lx, pa %lx", (void *)vmf->address,
 			pfn, pfn << PAGE_SHIFT);
 
-	return vm_insert_mixed(vma, (unsigned long)vmf->virtual_address,
-			__pfn_to_pfn_t(pfn, PFN_DEV));
+	return vm_insert_mixed(vma, vmf->address, __pfn_to_pfn_t(pfn, PFN_DEV));
 }
 
 /* Special handling for the case of faulting in 2d tiled buffers */
@@ -427,7 +425,7 @@ static int fault_2d(struct drm_gem_object *obj,
 	struct page *pages[64];  /* XXX is this too much to have on stack? */
 	unsigned long pfn;
 	pgoff_t pgoff, base_pgoff;
-	void __user *vaddr;
+	unsigned long vaddr;
 	int i, ret, slots;
 
 	/*
@@ -447,8 +445,7 @@ static int fault_2d(struct drm_gem_object *obj,
 	const int m = 1 + ((omap_obj->width << fmt) / PAGE_SIZE);
 
 	/* We don't use vmf->pgoff since that has the fake offset: */
-	pgoff = ((unsigned long)vmf->virtual_address -
-			vma->vm_start) >> PAGE_SHIFT;
+	pgoff = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
 
 	/*
 	 * Actual address we start mapping at is rounded down to previous slot
@@ -459,7 +456,7 @@ static int fault_2d(struct drm_gem_object *obj,
 	/* figure out buffer width in slots */
 	slots = omap_obj->width >> priv->usergart[fmt].slot_shift;
 
-	vaddr = vmf->virtual_address - ((pgoff - base_pgoff) << PAGE_SHIFT);
+	vaddr = vmf->address - ((pgoff - base_pgoff) << PAGE_SHIFT);
 
 	entry = &priv->usergart[fmt].entry[priv->usergart[fmt].last];
 
@@ -503,12 +500,11 @@ static int fault_2d(struct drm_gem_object *obj,
 
 	pfn = entry->paddr >> PAGE_SHIFT;
 
-	VERB("Inserting %p pfn %lx, pa %lx", vmf->virtual_address,
+	VERB("Inserting %p pfn %lx, pa %lx", (void *)vmf->address,
 			pfn, pfn << PAGE_SHIFT);
 
 	for (i = n; i > 0; i--) {
-		vm_insert_mixed(vma, (unsigned long)vaddr,
-				__pfn_to_pfn_t(pfn, PFN_DEV));
+		vm_insert_mixed(vma, vaddr, __pfn_to_pfn_t(pfn, PFN_DEV));
 		pfn += priv->usergart[fmt].stride_pfn;
 		vaddr += PAGE_SIZE * m;
 	}
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index c08e5279eeac..7d853e6b5ff0 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -452,10 +452,10 @@ static int tegra_bo_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (!bo->pages)
 		return VM_FAULT_SIGBUS;
 
-	offset = ((unsigned long)vmf->virtual_address - vma->vm_start) >> PAGE_SHIFT;
+	offset = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
 	page = bo->pages[offset];
 
-	err = vm_insert_page(vma, (unsigned long)vmf->virtual_address, page);
+	err = vm_insert_page(vma, vmf->address, page);
 	switch (err) {
 	case -EAGAIN:
 	case 0:
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 4748aedc933a..68ef993ab431 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -101,7 +101,7 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct page *page;
 	int ret;
 	int i;
-	unsigned long address = (unsigned long)vmf->virtual_address;
+	unsigned long address = vmf->address;
 	int retval = VM_FAULT_NOPAGE;
 	struct ttm_mem_type_manager *man =
 		&bdev->man[bo->mem.mem_type];
diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c
index 818e70712b18..3c0c4bd3f750 100644
--- a/drivers/gpu/drm/udl/udl_gem.c
+++ b/drivers/gpu/drm/udl/udl_gem.c
@@ -107,14 +107,13 @@ int udl_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	unsigned int page_offset;
 	int ret = 0;
 
-	page_offset = ((unsigned long)vmf->virtual_address - vma->vm_start) >>
-		PAGE_SHIFT;
+	page_offset = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
 
 	if (!obj->pages)
 		return VM_FAULT_SIGBUS;
 
 	page = obj->pages[page_offset];
-	ret = vm_insert_page(vma, (unsigned long)vmf->virtual_address, page);
+	ret = vm_insert_page(vma, vmf->address, page);
 	switch (ret) {
 	case -EAGAIN:
 	case 0:
diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c
index f36c14729b55..477e07f0ecb6 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.c
+++ b/drivers/gpu/drm/vgem/vgem_drv.c
@@ -54,7 +54,7 @@ static int vgem_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct drm_vgem_gem_object *obj = vma->vm_private_data;
 	/* We don't use vmf->pgoff since that has the fake offset */
-	unsigned long vaddr = (unsigned long)vmf->virtual_address;
+	unsigned long vaddr = vmf->address;
 	struct page *page;
 
 	page = shmem_read_mapping_page(file_inode(obj->base.filp)->i_mapping,
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 1f0fe3217f23..6b079a31dced 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -578,7 +578,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 user_virt, u64 bcnt,
 		 */
 		npages = get_user_pages_remote(owning_process, owning_mm,
 				user_virt, gup_num_pages,
-				flags, local_page_list, NULL);
+				flags, local_page_list, NULL, NULL);
 		up_read(&owning_mm->mmap_sem);
 
 		if (npages < 0)
diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c
index 1db0af6c7f94..ba63ca57ed7e 100644
--- a/drivers/media/v4l2-core/videobuf-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf-dma-sg.c
@@ -439,13 +439,12 @@ static int videobuf_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct page *page;
 
 	dprintk(3, "fault: fault @ %08lx [vma %08lx-%08lx]\n",
-		(unsigned long)vmf->virtual_address,
-		vma->vm_start, vma->vm_end);
+		vmf->address, vma->vm_start, vma->vm_end);
 
 	page = alloc_page(GFP_USER | __GFP_DMA32);
 	if (!page)
 		return VM_FAULT_OOM;
-	clear_user_highpage(page, (unsigned long)vmf->virtual_address);
+	clear_user_highpage(page, vmf->address);
 	vmf->page = page;
 
 	return 0;
diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c
index ff5e7e8cb1d1..3907387b6d15 100644
--- a/drivers/misc/cxl/context.c
+++ b/drivers/misc/cxl/context.c
@@ -124,13 +124,12 @@ void cxl_context_set_mapping(struct cxl_context *ctx,
 static int cxl_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct cxl_context *ctx = vma->vm_file->private_data;
-	unsigned long address = (unsigned long)vmf->virtual_address;
 	u64 area, offset;
 
 	offset = vmf->pgoff << PAGE_SHIFT;
 
 	pr_devel("%s: pe: %i address: 0x%lx offset: 0x%llx\n",
-			__func__, ctx->pe, address, offset);
+			__func__, ctx->pe, vmf->address, offset);
 
 	if (ctx->afu->current_mode == CXL_MODE_DEDICATED) {
 		area = ctx->afu->psn_phys;
@@ -162,7 +161,7 @@ static int cxl_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		return VM_FAULT_SIGBUS;
 	}
 
-	vm_insert_pfn(vma, address, (area + offset) >> PAGE_SHIFT);
+	vm_insert_pfn(vma, vmf->address, (area + offset) >> PAGE_SHIFT);
 
 	mutex_unlock(&ctx->status_mutex);
 
diff --git a/drivers/misc/sgi-gru/grumain.c b/drivers/misc/sgi-gru/grumain.c
index 33741ad4a74a..af2e077da4b8 100644
--- a/drivers/misc/sgi-gru/grumain.c
+++ b/drivers/misc/sgi-gru/grumain.c
@@ -932,7 +932,7 @@ int gru_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	unsigned long paddr, vaddr;
 	unsigned long expires;
 
-	vaddr = (unsigned long)vmf->virtual_address;
+	vaddr = vmf->address;
 	gru_dbg(grudev, "vma %p, vaddr 0x%lx (0x%lx)\n",
 		vma, vaddr, GSEG_BASE(vaddr));
 	STAT(nopfn);
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/calib.c b/drivers/net/wireless/intel/iwlwifi/dvm/calib.c
index e9cef9de9ed8..c96f9b1d948a 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/calib.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/calib.c
@@ -900,8 +900,7 @@ static void iwlagn_gain_computation(struct iwl_priv *priv,
 
 		/* bound gain by 2 bits value max, 3rd bit is sign */
 		data->delta_gain_code[i] =
-			min(abs(delta_g),
-			(s32) CHAIN_NOISE_MAX_DELTA_GAIN_CODE);
+			min(abs(delta_g), CHAIN_NOISE_MAX_DELTA_GAIN_CODE);
 
 		if (delta_g < 0)
 			/*
diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c
index d5cc3070e83f..b653451843c8 100644
--- a/drivers/staging/android/ion/ion.c
+++ b/drivers/staging/android/ion/ion.c
@@ -882,7 +882,7 @@ static int ion_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	BUG_ON(!buffer->pages || !buffer->pages[vmf->pgoff]);
 
 	pfn = page_to_pfn(ion_buffer_page(buffer->pages[vmf->pgoff]));
-	ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address, pfn);
+	ret = vm_insert_pfn(vma, vmf->address, pfn);
 	mutex_unlock(&buffer->lock);
 	if (ret)
 		return VM_FAULT_ERROR;
diff --git a/drivers/staging/lustre/lustre/llite/vvp_io.c b/drivers/staging/lustre/lustre/llite/vvp_io.c
index 33b38bda8319..d102ba0b629c 100644
--- a/drivers/staging/lustre/lustre/llite/vvp_io.c
+++ b/drivers/staging/lustre/lustre/llite/vvp_io.c
@@ -1018,7 +1018,7 @@ static int vvp_io_kernel_fault(struct vvp_fault_io *cfio)
 		       "page %p map %p index %lu flags %lx count %u priv %0lx: got addr %p type NOPAGE\n",
 		       vmf->page, vmf->page->mapping, vmf->page->index,
 		       (long)vmf->page->flags, page_count(vmf->page),
-		       page_private(vmf->page), vmf->virtual_address);
+		       page_private(vmf->page), (void *)vmf->address);
 		if (unlikely(!(cfio->ft_flags & VM_FAULT_LOCKED))) {
 			lock_page(vmf->page);
 			cfio->ft_flags |= VM_FAULT_LOCKED;
@@ -1029,12 +1029,12 @@ static int vvp_io_kernel_fault(struct vvp_fault_io *cfio)
 	}
 
 	if (cfio->ft_flags & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) {
-		CDEBUG(D_PAGE, "got addr %p - SIGBUS\n", vmf->virtual_address);
+		CDEBUG(D_PAGE, "got addr %p - SIGBUS\n", (void *)vmf->address);
 		return -EFAULT;
 	}
 
 	if (cfio->ft_flags & VM_FAULT_OOM) {
-		CDEBUG(D_PAGE, "got addr %p - OOM\n", vmf->virtual_address);
+		CDEBUG(D_PAGE, "got addr %p - OOM\n", (void *)vmf->address);
 		return -ENOMEM;
 	}
 
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 51810a95416e..cae2e9121e48 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -362,7 +362,7 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 
 		down_read(&mm->mmap_sem);
 		ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags, page,
-					    NULL);
+					    NULL, NULL);
 		up_read(&mm->mmap_sem);
 	}
 
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 702040fe2001..6e3306f4a525 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -602,7 +602,7 @@ static int privcmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	printk(KERN_DEBUG "privcmd_fault: vma=%p %lx-%lx, pgoff=%lx, uv=%p\n",
 	       vma, vma->vm_start, vma->vm_end,
-	       vmf->pgoff, vmf->virtual_address);
+	       vmf->pgoff, (void *)vmf->address);
 
 	return VM_FAULT_SIGBUS;
 }
diff --git a/fs/dax.c b/fs/dax.c
index 92bfe98662f9..b1fe228cd609 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -31,6 +31,7 @@
 #include <linux/vmstat.h>
 #include <linux/pfn_t.h>
 #include <linux/sizes.h>
+#include <linux/mmu_notifier.h>
 #include <linux/iomap.h>
 #include "internal.h"
 
@@ -240,6 +241,23 @@ static void *get_unlocked_mapping_entry(struct address_space *mapping,
 	}
 }
 
+static void dax_unlock_mapping_entry(struct address_space *mapping,
+				     pgoff_t index)
+{
+	void *entry, **slot;
+
+	spin_lock_irq(&mapping->tree_lock);
+	entry = __radix_tree_lookup(&mapping->page_tree, index, NULL, &slot);
+	if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry) ||
+			 !slot_locked(mapping, slot))) {
+		spin_unlock_irq(&mapping->tree_lock);
+		return;
+	}
+	unlock_slot(mapping, slot);
+	spin_unlock_irq(&mapping->tree_lock);
+	dax_wake_mapping_entry_waiter(mapping, index, entry, false);
+}
+
 static void put_locked_mapping_entry(struct address_space *mapping,
 				     pgoff_t index, void *entry)
 {
@@ -434,22 +452,6 @@ void dax_wake_mapping_entry_waiter(struct address_space *mapping,
 		__wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key);
 }
 
-void dax_unlock_mapping_entry(struct address_space *mapping, pgoff_t index)
-{
-	void *entry, **slot;
-
-	spin_lock_irq(&mapping->tree_lock);
-	entry = __radix_tree_lookup(&mapping->page_tree, index, NULL, &slot);
-	if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry) ||
-			 !slot_locked(mapping, slot))) {
-		spin_unlock_irq(&mapping->tree_lock);
-		return;
-	}
-	unlock_slot(mapping, slot);
-	spin_unlock_irq(&mapping->tree_lock);
-	dax_wake_mapping_entry_waiter(mapping, index, entry, false);
-}
-
 /*
  * Delete exceptional DAX entry at @index from @mapping. Wait for radix tree
  * entry to get unlocked before deleting it.
@@ -501,10 +503,8 @@ static int dax_load_hole(struct address_space *mapping, void *entry,
 	/* This will replace locked radix tree entry with a hole page */
 	page = find_or_create_page(mapping, vmf->pgoff,
 				   vmf->gfp_mask | __GFP_ZERO);
-	if (!page) {
-		put_locked_mapping_entry(mapping, vmf->pgoff, entry);
+	if (!page)
 		return VM_FAULT_OOM;
-	}
 	vmf->page = page;
 	return VM_FAULT_LOCKED;
 }
@@ -616,36 +616,107 @@ static void *dax_insert_mapping_entry(struct address_space *mapping,
 	return new_entry;
 }
 
+static inline unsigned long
+pgoff_address(pgoff_t pgoff, struct vm_area_struct *vma)
+{
+	unsigned long address;
+
+	address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
+	return address;
+}
+
+/* Walk all mappings of a given index of a file and writeprotect them */
+static void dax_mapping_entry_mkclean(struct address_space *mapping,
+				      pgoff_t index, unsigned long pfn)
+{
+	struct vm_area_struct *vma;
+	pte_t *ptep;
+	pte_t pte;
+	spinlock_t *ptl;
+	bool changed;
+
+	i_mmap_lock_read(mapping);
+	vma_interval_tree_foreach(vma, &mapping->i_mmap, index, index) {
+		unsigned long address;
+
+		cond_resched();
+
+		if (!(vma->vm_flags & VM_SHARED))
+			continue;
+
+		address = pgoff_address(index, vma);
+		changed = false;
+		if (follow_pte(vma->vm_mm, address, &ptep, &ptl))
+			continue;
+		if (pfn != pte_pfn(*ptep))
+			goto unlock;
+		if (!pte_dirty(*ptep) && !pte_write(*ptep))
+			goto unlock;
+
+		flush_cache_page(vma, address, pfn);
+		pte = ptep_clear_flush(vma, address, ptep);
+		pte = pte_wrprotect(pte);
+		pte = pte_mkclean(pte);
+		set_pte_at(vma->vm_mm, address, ptep, pte);
+		changed = true;
+unlock:
+		pte_unmap_unlock(ptep, ptl);
+
+		if (changed)
+			mmu_notifier_invalidate_page(vma->vm_mm, address);
+	}
+	i_mmap_unlock_read(mapping);
+}
+
 static int dax_writeback_one(struct block_device *bdev,
 		struct address_space *mapping, pgoff_t index, void *entry)
 {
 	struct radix_tree_root *page_tree = &mapping->page_tree;
-	struct radix_tree_node *node;
 	struct blk_dax_ctl dax;
-	void **slot;
+	void *entry2, **slot;
 	int ret = 0;
 
-	spin_lock_irq(&mapping->tree_lock);
 	/*
-	 * Regular page slots are stabilized by the page lock even
-	 * without the tree itself locked.  These unlocked entries
-	 * need verification under the tree lock.
+	 * A page got tagged dirty in DAX mapping? Something is seriously
+	 * wrong.
 	 */
-	if (!__radix_tree_lookup(page_tree, index, &node, &slot))
-		goto unlock;
-	if (*slot != entry)
-		goto unlock;
-
-	/* another fsync thread may have already written back this entry */
-	if (!radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
-		goto unlock;
+	if (WARN_ON(!radix_tree_exceptional_entry(entry)))
+		return -EIO;
 
+	spin_lock_irq(&mapping->tree_lock);
+	entry2 = get_unlocked_mapping_entry(mapping, index, &slot);
+	/* Entry got punched out / reallocated? */
+	if (!entry2 || !radix_tree_exceptional_entry(entry2))
+		goto put_unlocked;
+	/*
+	 * Entry got reallocated elsewhere? No need to writeback. We have to
+	 * compare sectors as we must not bail out due to difference in lockbit
+	 * or entry type.
+	 */
+	if (dax_radix_sector(entry2) != dax_radix_sector(entry))
+		goto put_unlocked;
 	if (WARN_ON_ONCE(dax_is_empty_entry(entry) ||
 				dax_is_zero_entry(entry))) {
 		ret = -EIO;
-		goto unlock;
+		goto put_unlocked;
 	}
 
+	/* Another fsync thread may have already written back this entry */
+	if (!radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
+		goto put_unlocked;
+	/* Lock the entry to serialize with page faults */
+	entry = lock_slot(mapping, slot);
+	/*
+	 * We can clear the tag now but we have to be careful so that concurrent
+	 * dax_writeback_one() calls for the same index cannot finish before we
+	 * actually flush the caches. This is achieved as the calls will look
+	 * at the entry only under tree_lock and once they do that they will
+	 * see the entry locked and wait for it to unlock.
+	 */
+	radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_TOWRITE);
+	spin_unlock_irq(&mapping->tree_lock);
+
 	/*
 	 * Even if dax_writeback_mapping_range() was given a wbc->range_start
 	 * in the middle of a PMD, the 'index' we are given will be aligned to
@@ -655,31 +726,40 @@ static int dax_writeback_one(struct block_device *bdev,
 	 */
 	dax.sector = dax_radix_sector(entry);
 	dax.size = PAGE_SIZE << dax_radix_order(entry);
-	spin_unlock_irq(&mapping->tree_lock);
 
 	/*
 	 * We cannot hold tree_lock while calling dax_map_atomic() because it
 	 * eventually calls cond_resched().
 	 */
 	ret = dax_map_atomic(bdev, &dax);
-	if (ret < 0)
+	if (ret < 0) {
+		put_locked_mapping_entry(mapping, index, entry);
 		return ret;
+	}
 
 	if (WARN_ON_ONCE(ret < dax.size)) {
 		ret = -EIO;
 		goto unmap;
 	}
 
+	dax_mapping_entry_mkclean(mapping, index, pfn_t_to_pfn(dax.pfn));
 	wb_cache_pmem(dax.addr, dax.size);
-
+	/*
+	 * After we have flushed the cache, we can clear the dirty tag. There
+	 * cannot be new dirty data in the pfn after the flush has completed as
+	 * the pfn mappings are writeprotected and fault waits for mapping
+	 * entry lock.
+	 */
 	spin_lock_irq(&mapping->tree_lock);
-	radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_TOWRITE);
+	radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_DIRTY);
 	spin_unlock_irq(&mapping->tree_lock);
  unmap:
 	dax_unmap_atomic(bdev, &dax);
+	put_locked_mapping_entry(mapping, index, entry);
 	return ret;
 
- unlock:
+ put_unlocked:
+	put_unlocked_mapping_entry(mapping, index, entry2);
 	spin_unlock_irq(&mapping->tree_lock);
 	return ret;
 }
@@ -739,7 +819,7 @@ static int dax_insert_mapping(struct address_space *mapping,
 		struct block_device *bdev, sector_t sector, size_t size,
 		void **entryp, struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	unsigned long vaddr = (unsigned long)vmf->virtual_address;
+	unsigned long vaddr = vmf->address;
 	struct blk_dax_ctl dax = {
 		.sector = sector,
 		.size = size,
@@ -768,17 +848,27 @@ int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct file *file = vma->vm_file;
 	struct address_space *mapping = file->f_mapping;
-	void *entry;
+	void *entry, **slot;
 	pgoff_t index = vmf->pgoff;
 
 	spin_lock_irq(&mapping->tree_lock);
-	entry = get_unlocked_mapping_entry(mapping, index, NULL);
-	if (!entry || !radix_tree_exceptional_entry(entry))
-		goto out;
+	entry = get_unlocked_mapping_entry(mapping, index, &slot);
+	if (!entry || !radix_tree_exceptional_entry(entry)) {
+		if (entry)
+			put_unlocked_mapping_entry(mapping, index, entry);
+		spin_unlock_irq(&mapping->tree_lock);
+		return VM_FAULT_NOPAGE;
+	}
 	radix_tree_tag_set(&mapping->page_tree, index, PAGECACHE_TAG_DIRTY);
-	put_unlocked_mapping_entry(mapping, index, entry);
-out:
+	entry = lock_slot(mapping, slot);
 	spin_unlock_irq(&mapping->tree_lock);
+	/*
+	 * If we race with somebody updating the PTE and finish_mkwrite_fault()
+	 * fails, we don't care. We need to return VM_FAULT_NOPAGE and retry
+	 * the fault in either case.
+	 */
+	finish_mkwrite_fault(vmf);
+	put_locked_mapping_entry(mapping, index, entry);
 	return VM_FAULT_NOPAGE;
 }
 EXPORT_SYMBOL_GPL(dax_pfn_mkwrite);
@@ -949,13 +1039,13 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 {
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	struct inode *inode = mapping->host;
-	unsigned long vaddr = (unsigned long)vmf->virtual_address;
+	unsigned long vaddr = vmf->address;
 	loff_t pos = (loff_t)vmf->pgoff << PAGE_SHIFT;
 	sector_t sector;
 	struct iomap iomap = { 0 };
 	unsigned flags = IOMAP_FAULT;
 	int error, major = 0;
-	int locked_status = 0;
+	int vmf_ret = 0;
 	void *entry;
 
 	/*
@@ -1008,13 +1098,11 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 
 		if (error)
 			goto finish_iomap;
-		if (!radix_tree_exceptional_entry(entry)) {
-			vmf->page = entry;
-			locked_status = VM_FAULT_LOCKED;
-		} else {
-			vmf->entry = entry;
-			locked_status = VM_FAULT_DAX_LOCKED;
-		}
+
+		__SetPageUptodate(vmf->cow_page);
+		vmf_ret = finish_fault(vmf);
+		if (!vmf_ret)
+			vmf_ret = VM_FAULT_DONE_COW;
 		goto finish_iomap;
 	}
 
@@ -1031,7 +1119,7 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
 		if (!(vmf->flags & FAULT_FLAG_WRITE)) {
-			locked_status = dax_load_hole(mapping, entry, vmf);
+			vmf_ret = dax_load_hole(mapping, entry, vmf);
 			break;
 		}
 		/*FALLTHRU*/
@@ -1043,7 +1131,7 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 
  finish_iomap:
 	if (ops->iomap_end) {
-		if (error) {
+		if (error || (vmf_ret & VM_FAULT_ERROR)) {
 			/* keep previous error */
 			ops->iomap_end(inode, pos, PAGE_SIZE, 0, flags,
 					&iomap);
@@ -1053,7 +1141,7 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		}
 	}
  unlock_entry:
-	if (!locked_status || error)
+	if (vmf_ret != VM_FAULT_LOCKED || error)
 		put_locked_mapping_entry(mapping, vmf->pgoff, entry);
  out:
 	if (error == -ENOMEM)
@@ -1061,9 +1149,9 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	/* -EBUSY is fine, somebody else faulted on the same PTE */
 	if (error < 0 && error != -EBUSY)
 		return VM_FAULT_SIGBUS | major;
-	if (locked_status) {
+	if (vmf_ret) {
 		WARN_ON_ONCE(error); /* -EBUSY from ops->iomap_end? */
-		return locked_status;
+		return vmf_ret;
 	}
 	return VM_FAULT_NOPAGE | major;
 }
diff --git a/fs/exec.c b/fs/exec.c
index 88b5e1efdbd6..8112eacf10f3 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -209,7 +209,7 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 	 * doing the exec and bprm->mm is the new process's mm.
 	 */
 	ret = get_user_pages_remote(current, bprm->mm, pos, 1, gup_flags,
-			&page, NULL);
+			&page, NULL, NULL);
 	if (ret <= 0)
 		return NULL;
 
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 85959d8324df..d96e2f30084b 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -257,9 +257,9 @@ out:
  * fatal_signal_pending()s, and the mmap_sem must be released before
  * returning it.
  */
-int handle_userfault(struct fault_env *fe, unsigned long reason)
+int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 {
-	struct mm_struct *mm = fe->vma->vm_mm;
+	struct mm_struct *mm = vmf->vma->vm_mm;
 	struct userfaultfd_ctx *ctx;
 	struct userfaultfd_wait_queue uwq;
 	int ret;
@@ -268,7 +268,7 @@ int handle_userfault(struct fault_env *fe, unsigned long reason)
 	BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
 
 	ret = VM_FAULT_SIGBUS;
-	ctx = fe->vma->vm_userfaultfd_ctx.ctx;
+	ctx = vmf->vma->vm_userfaultfd_ctx.ctx;
 	if (!ctx)
 		goto out;
 
@@ -301,17 +301,18 @@ int handle_userfault(struct fault_env *fe, unsigned long reason)
 	 * without first stopping userland access to the memory. For
 	 * VM_UFFD_MISSING userfaults this is enough for now.
 	 */
-	if (unlikely(!(fe->flags & FAULT_FLAG_ALLOW_RETRY))) {
+	if (unlikely(!(vmf->flags & FAULT_FLAG_ALLOW_RETRY))) {
 		/*
 		 * Validate the invariant that nowait must allow retry
 		 * to be sure not to return SIGBUS erroneously on
 		 * nowait invocations.
 		 */
-		BUG_ON(fe->flags & FAULT_FLAG_RETRY_NOWAIT);
+		BUG_ON(vmf->flags & FAULT_FLAG_RETRY_NOWAIT);
 #ifdef CONFIG_DEBUG_VM
 		if (printk_ratelimit()) {
 			printk(KERN_WARNING
-			       "FAULT_FLAG_ALLOW_RETRY missing %x\n", fe->flags);
+			       "FAULT_FLAG_ALLOW_RETRY missing %x\n",
+			       vmf->flags);
 			dump_stack();
 		}
 #endif
@@ -323,7 +324,7 @@ int handle_userfault(struct fault_env *fe, unsigned long reason)
 	 * and wait.
 	 */
 	ret = VM_FAULT_RETRY;
-	if (fe->flags & FAULT_FLAG_RETRY_NOWAIT)
+	if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
 		goto out;
 
 	/* take the reference before dropping the mmap_sem */
@@ -331,11 +332,11 @@ int handle_userfault(struct fault_env *fe, unsigned long reason)
 
 	init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
 	uwq.wq.private = current;
-	uwq.msg = userfault_msg(fe->address, fe->flags, reason);
+	uwq.msg = userfault_msg(vmf->address, vmf->flags, reason);
 	uwq.ctx = ctx;
 
 	return_to_userland =
-		(fe->flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) ==
+		(vmf->flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) ==
 		(FAULT_FLAG_USER|FAULT_FLAG_KILLABLE);
 
 	spin_lock(&ctx->fault_pending_wqh.lock);
@@ -353,7 +354,8 @@ int handle_userfault(struct fault_env *fe, unsigned long reason)
 			  TASK_KILLABLE);
 	spin_unlock(&ctx->fault_pending_wqh.lock);
 
-	must_wait = userfaultfd_must_wait(ctx, fe->address, fe->flags, reason);
+	must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags,
+					  reason);
 	up_read(&mm->mmap_sem);
 
 	if (likely(must_wait && !ACCESS_ONCE(ctx->released) &&
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 0afade8bd3d7..f97bcfe79472 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -46,7 +46,6 @@ void dax_wake_mapping_entry_waiter(struct address_space *mapping,
 
 #ifdef CONFIG_FS_DAX
 struct page *read_dax_sector(struct block_device *bdev, sector_t n);
-void dax_unlock_mapping_entry(struct address_space *mapping, pgoff_t index);
 int __dax_zero_page_range(struct block_device *bdev, sector_t sector,
 		unsigned int offset, unsigned int length);
 #else
@@ -55,12 +54,6 @@ static inline struct page *read_dax_sector(struct block_device *bdev,
 {
 	return ERR_PTR(-ENXIO);
 }
-/* Shouldn't ever be called when dax is disabled. */
-static inline void dax_unlock_mapping_entry(struct address_space *mapping,
-					    pgoff_t index)
-{
-	BUG();
-}
 static inline int __dax_zero_page_range(struct block_device *bdev,
 		sector_t sector, unsigned int offset, unsigned int length)
 {
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 1f782aa1d8e6..97e478d6b690 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -1,12 +1,12 @@
 #ifndef _LINUX_HUGE_MM_H
 #define _LINUX_HUGE_MM_H
 
-extern int do_huge_pmd_anonymous_page(struct fault_env *fe);
+extern int do_huge_pmd_anonymous_page(struct vm_fault *vmf);
 extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 			 pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
 			 struct vm_area_struct *vma);
-extern void huge_pmd_set_accessed(struct fault_env *fe, pmd_t orig_pmd);
-extern int do_huge_pmd_wp_page(struct fault_env *fe, pmd_t orig_pmd);
+extern void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd);
+extern int do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd);
 extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 					  unsigned long addr,
 					  pmd_t *pmd,
@@ -142,7 +142,7 @@ static inline int hpage_nr_pages(struct page *page)
 	return 1;
 }
 
-extern int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t orig_pmd);
+extern int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd);
 
 extern struct page *huge_zero_page;
 
@@ -212,7 +212,7 @@ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
 	return NULL;
 }
 
-static inline int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t orig_pmd)
+static inline int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd)
 {
 	return 0;
 }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0b5b2e4df14e..4424784ac374 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -292,36 +292,23 @@ extern pgprot_t protection_map[16];
  * pgoff should be used in favour of virtual_address, if possible.
  */
 struct vm_fault {
+	struct vm_area_struct *vma;	/* Target VMA */
 	unsigned int flags;		/* FAULT_FLAG_xxx flags */
 	gfp_t gfp_mask;			/* gfp mask to be used for allocations */
 	pgoff_t pgoff;			/* Logical page offset based on vma */
-	void __user *virtual_address;	/* Faulting virtual address */
+	unsigned long address;		/* Faulting virtual address */
+	pmd_t *pmd;			/* Pointer to pmd entry matching
+					 * the 'address' */
+	pte_t orig_pte;			/* Value of PTE at the time of fault */
 
-	struct page *cow_page;		/* Handler may choose to COW */
+	struct page *cow_page;		/* Page handler may use for COW fault */
+	struct mem_cgroup *memcg;	/* Cgroup cow_page belongs to */
 	struct page *page;		/* ->fault handlers should return a
 					 * page here, unless VM_FAULT_NOPAGE
 					 * is set (which is also implied by
 					 * VM_FAULT_ERROR).
 					 */
-	void *entry;			/* ->fault handler can alternatively
-					 * return locked DAX entry. In that
-					 * case handler should return
-					 * VM_FAULT_DAX_LOCKED and fill in
-					 * entry here.
-					 */
-};
-
-/*
- * Page fault context: passes though page fault handler instead of endless list
- * of function arguments.
- */
-struct fault_env {
-	struct vm_area_struct *vma;	/* Target VMA */
-	unsigned long address;		/* Faulting virtual address */
-	unsigned int flags;		/* FAULT_FLAG_xxx flags */
-	pmd_t *pmd;			/* Pointer to pmd entry matching
-					 * the 'address'
-					 */
+	/* These three entries are valid only while holding ptl lock */
 	pte_t *pte;			/* Pointer to pte entry matching
 					 * the 'address'. NULL if the page
 					 * table hasn't been allocated.
@@ -351,7 +338,7 @@ struct vm_operations_struct {
 	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
 	int (*pmd_fault)(struct vm_area_struct *, unsigned long address,
 						pmd_t *, unsigned int flags);
-	void (*map_pages)(struct fault_env *fe,
+	void (*map_pages)(struct vm_fault *vmf,
 			pgoff_t start_pgoff, pgoff_t end_pgoff);
 
 	/* notification that a previously read-only page is about to become
@@ -625,8 +612,10 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 	return pte;
 }
 
-int alloc_set_pte(struct fault_env *fe, struct mem_cgroup *memcg,
+int alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
 		struct page *page);
+int finish_fault(struct vm_fault *vmf);
+int finish_mkwrite_fault(struct vm_fault *vmf);
 #endif
 
 /*
@@ -1110,7 +1099,7 @@ static inline void clear_page_pfmemalloc(struct page *page)
 #define VM_FAULT_LOCKED	0x0200	/* ->fault locked the returned page */
 #define VM_FAULT_RETRY	0x0400	/* ->fault blocked, must retry */
 #define VM_FAULT_FALLBACK 0x0800	/* huge page fault failed, fall back to small */
-#define VM_FAULT_DAX_LOCKED 0x1000	/* ->fault has locked DAX entry */
+#define VM_FAULT_DONE_COW   0x1000	/* ->fault has fully handled COW */
 
 #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
 
@@ -1221,6 +1210,8 @@ int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
 			struct vm_area_struct *vma);
 void unmap_mapping_range(struct address_space *mapping,
 		loff_t const holebegin, loff_t const holelen, int even_cows);
+int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp,
+	       spinlock_t **ptlp);
 int follow_pfn(struct vm_area_struct *vma, unsigned long address,
 	unsigned long *pfn);
 int follow_phys(struct vm_area_struct *vma, unsigned long address,
@@ -1276,15 +1267,12 @@ extern int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
 long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
 			    unsigned long start, unsigned long nr_pages,
 			    unsigned int gup_flags, struct page **pages,
-			    struct vm_area_struct **vmas);
+			    struct vm_area_struct **vmas, int *locked);
 long get_user_pages(unsigned long start, unsigned long nr_pages,
 			    unsigned int gup_flags, struct page **pages,
 			    struct vm_area_struct **vmas);
 long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
 		    unsigned int gup_flags, struct page **pages, int *locked);
-long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
-			       unsigned long start, unsigned long nr_pages,
-			       struct page **pages, unsigned int gup_flags);
 long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 		    struct page **pages, unsigned int gup_flags);
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
@@ -2099,7 +2087,7 @@ extern void truncate_inode_pages_final(struct address_space *);
 
 /* generic vm_area_ops exported for stackable file systems */
 extern int filemap_fault(struct vm_area_struct *, struct vm_fault *);
-extern void filemap_map_pages(struct fault_env *fe,
+extern void filemap_map_pages(struct vm_fault *vmf,
 		pgoff_t start_pgoff, pgoff_t end_pgoff);
 extern int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
 
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index a78c35cff1ae..aacca824a6ae 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -7,6 +7,23 @@
 #include <linux/sched.h>
 #include <asm/irq.h>
 
+/*
+ * The run state of the lockup detectors is controlled by the content of the
+ * 'watchdog_enabled' variable. Each lockup detector has its dedicated bit -
+ * bit 0 for the hard lockup detector and bit 1 for the soft lockup detector.
+ *
+ * 'watchdog_user_enabled', 'nmi_watchdog_enabled' and 'soft_watchdog_enabled'
+ * are variables that are only used as an 'interface' between the parameters
+ * in /proc/sys/kernel and the internal state bits in 'watchdog_enabled'. The
+ * 'watchdog_thresh' variable is handled differently because its value is not
+ * boolean, and the lockup detectors are 'suspended' while 'watchdog_thresh'
+ * is equal zero.
+ */
+#define NMI_WATCHDOG_ENABLED_BIT   0
+#define SOFT_WATCHDOG_ENABLED_BIT  1
+#define NMI_WATCHDOG_ENABLED      (1 << NMI_WATCHDOG_ENABLED_BIT)
+#define SOFT_WATCHDOG_ENABLED     (1 << SOFT_WATCHDOG_ENABLED_BIT)
+
 /**
  * touch_nmi_watchdog - restart NMI watchdog timeout.
  * 
@@ -91,9 +108,16 @@ extern int nmi_watchdog_enabled;
 extern int soft_watchdog_enabled;
 extern int watchdog_user_enabled;
 extern int watchdog_thresh;
+extern unsigned long watchdog_enabled;
 extern unsigned long *watchdog_cpumask_bits;
+#ifdef CONFIG_SMP
 extern int sysctl_softlockup_all_cpu_backtrace;
 extern int sysctl_hardlockup_all_cpu_backtrace;
+#else
+#define sysctl_softlockup_all_cpu_backtrace 0
+#define sysctl_hardlockup_all_cpu_backtrace 0
+#endif
+extern bool is_hardlockup(void);
 struct ctl_table;
 extern int proc_watchdog(struct ctl_table *, int ,
 			 void __user *, size_t *, loff_t *);
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index dd66a952e8cd..11b92b047a1e 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -27,7 +27,7 @@
 #define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK)
 #define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS)
 
-extern int handle_userfault(struct fault_env *fe, unsigned long reason);
+extern int handle_userfault(struct vm_fault *vmf, unsigned long reason);
 
 extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
 			    unsigned long src_start, unsigned long len);
@@ -55,7 +55,7 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma)
 #else /* CONFIG_USERFAULTFD */
 
 /* mm helpers */
-static inline int handle_userfault(struct fault_env *fe, unsigned long reason)
+static inline int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 {
 	return VM_FAULT_SIGBUS;
 }
diff --git a/ipc/sem.c b/ipc/sem.c
index e84703d5024e..31eaa87ecba4 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -11,6 +11,7 @@
  * (c) 2001 Red Hat Inc
  * Lockless wakeup
  * (c) 2003 Manfred Spraul <manfred@colorfullife.com>
+ * (c) 2016 Davidlohr Bueso <dave@stgolabs.net>
  * Further wakeup optimizations, documentation
  * (c) 2010 Manfred Spraul <manfred@colorfullife.com>
  *
@@ -53,15 +54,11 @@
  *   Semaphores are actively given to waiting tasks (necessary for FIFO).
  *   (see update_queue())
  * - To improve the scalability, the actual wake-up calls are performed after
- *   dropping all locks. (see wake_up_sem_queue_prepare(),
- *   wake_up_sem_queue_do())
+ *   dropping all locks. (see wake_up_sem_queue_prepare())
  * - All work is done by the waker, the woken up task does not have to do
  *   anything - not even acquiring a lock or dropping a refcount.
  * - A woken up task may not even touch the semaphore array anymore, it may
  *   have been destroyed already by a semctl(RMID).
- * - The synchronizations between wake-ups due to a timeout/signal and a
- *   wake-up due to a completed semaphore operation is achieved by using an
- *   intermediate state (IN_WAKEUP).
  * - UNDO values are stored in an array (one per process and per
  *   semaphore array, lazily allocated). For backwards compatibility, multiple
  *   modes for the UNDO variables are supported (per process, per thread)
@@ -118,7 +115,8 @@ struct sem_queue {
 	struct sembuf		*sops;	 /* array of pending operations */
 	struct sembuf		*blocking; /* the operation that blocked */
 	int			nsops;	 /* number of operations */
-	int			alter;	 /* does *sops alter the array? */
+	bool			alter;	 /* does *sops alter the array? */
+	bool                    dupsop;	 /* sops on more than one sem_num */
 };
 
 /* Each task has a list of undo requests. They are executed automatically
@@ -433,29 +431,6 @@ static inline void sem_unlock(struct sem_array *sma, int locknum)
  *
  * The caller holds the RCU read lock.
  */
-static inline struct sem_array *sem_obtain_lock(struct ipc_namespace *ns,
-			int id, struct sembuf *sops, int nsops, int *locknum)
-{
-	struct kern_ipc_perm *ipcp;
-	struct sem_array *sma;
-
-	ipcp = ipc_obtain_object_idr(&sem_ids(ns), id);
-	if (IS_ERR(ipcp))
-		return ERR_CAST(ipcp);
-
-	sma = container_of(ipcp, struct sem_array, sem_perm);
-	*locknum = sem_lock(sma, sops, nsops);
-
-	/* ipc_rmid() may have already freed the ID while sem_lock
-	 * was spinning: verify that the structure is still valid
-	 */
-	if (ipc_valid_object(ipcp))
-		return container_of(ipcp, struct sem_array, sem_perm);
-
-	sem_unlock(sma, *locknum);
-	return ERR_PTR(-EINVAL);
-}
-
 static inline struct sem_array *sem_obtain_object(struct ipc_namespace *ns, int id)
 {
 	struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&sem_ids(ns), id);
@@ -488,40 +463,6 @@ static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
 	ipc_rmid(&sem_ids(ns), &s->sem_perm);
 }
 
-/*
- * Lockless wakeup algorithm:
- * Without the check/retry algorithm a lockless wakeup is possible:
- * - queue.status is initialized to -EINTR before blocking.
- * - wakeup is performed by
- *	* unlinking the queue entry from the pending list
- *	* setting queue.status to IN_WAKEUP
- *	  This is the notification for the blocked thread that a
- *	  result value is imminent.
- *	* call wake_up_process
- *	* set queue.status to the final value.
- * - the previously blocked thread checks queue.status:
- *	* if it's IN_WAKEUP, then it must wait until the value changes
- *	* if it's not -EINTR, then the operation was completed by
- *	  update_queue. semtimedop can return queue.status without
- *	  performing any operation on the sem array.
- *	* otherwise it must acquire the spinlock and check what's up.
- *
- * The two-stage algorithm is necessary to protect against the following
- * races:
- * - if queue.status is set after wake_up_process, then the woken up idle
- *   thread could race forward and try (and fail) to acquire sma->lock
- *   before update_queue had a chance to set queue.status
- * - if queue.status is written before wake_up_process and if the
- *   blocked process is woken up by a signal between writing
- *   queue.status and the wake_up_process, then the woken up
- *   process could return from semtimedop and die by calling
- *   sys_exit before wake_up_process is called. Then wake_up_process
- *   will oops, because the task structure is already invalid.
- *   (yes, this happened on s390 with sysv msg).
- *
- */
-#define IN_WAKEUP	1
-
 /**
  * newary - Create a new semaphore set
  * @ns: namespace
@@ -641,15 +582,23 @@ SYSCALL_DEFINE3(semget, key_t, key, int, nsems, int, semflg)
 }
 
 /**
- * perform_atomic_semop - Perform (if possible) a semaphore operation
+ * perform_atomic_semop[_slow] - Attempt to perform semaphore
+ *                               operations on a given array.
  * @sma: semaphore array
  * @q: struct sem_queue that describes the operation
  *
+ * Caller blocking are as follows, based the value
+ * indicated by the semaphore operation (sem_op):
+ *
+ *  (1) >0 never blocks.
+ *  (2)  0 (wait-for-zero operation): semval is non-zero.
+ *  (3) <0 attempting to decrement semval to a value smaller than zero.
+ *
  * Returns 0 if the operation was possible.
  * Returns 1 if the operation is impossible, the caller must sleep.
- * Negative values are error codes.
+ * Returns <0 for error codes.
  */
-static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q)
+static int perform_atomic_semop_slow(struct sem_array *sma, struct sem_queue *q)
 {
 	int result, sem_op, nsops, pid;
 	struct sembuf *sop;
@@ -720,51 +669,84 @@ undo:
 	return result;
 }
 
-/** wake_up_sem_queue_prepare(q, error): Prepare wake-up
- * @q: queue entry that must be signaled
- * @error: Error value for the signal
- *
- * Prepare the wake-up of the queue entry q.
- */
-static void wake_up_sem_queue_prepare(struct list_head *pt,
-				struct sem_queue *q, int error)
+static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q)
 {
-	if (list_empty(pt)) {
-		/*
-		 * Hold preempt off so that we don't get preempted and have the
-		 * wakee busy-wait until we're scheduled back on.
-		 */
-		preempt_disable();
+	int result, sem_op, nsops;
+	struct sembuf *sop;
+	struct sem *curr;
+	struct sembuf *sops;
+	struct sem_undo *un;
+
+	sops = q->sops;
+	nsops = q->nsops;
+	un = q->undo;
+
+	if (unlikely(q->dupsop))
+		return perform_atomic_semop_slow(sma, q);
+
+	/*
+	 * We scan the semaphore set twice, first to ensure that the entire
+	 * operation can succeed, therefore avoiding any pointless writes
+	 * to shared memory and having to undo such changes in order to block
+	 * until the operations can go through.
+	 */
+	for (sop = sops; sop < sops + nsops; sop++) {
+		curr = sma->sem_base + sop->sem_num;
+		sem_op = sop->sem_op;
+		result = curr->semval;
+
+		if (!sem_op && result)
+			goto would_block; /* wait-for-zero */
+
+		result += sem_op;
+		if (result < 0)
+			goto would_block;
+
+		if (result > SEMVMX)
+			return -ERANGE;
+
+		if (sop->sem_flg & SEM_UNDO) {
+			int undo = un->semadj[sop->sem_num] - sem_op;
+
+			/* Exceeding the undo range is an error. */
+			if (undo < (-SEMAEM - 1) || undo > SEMAEM)
+				return -ERANGE;
+		}
+	}
+
+	for (sop = sops; sop < sops + nsops; sop++) {
+		curr = sma->sem_base + sop->sem_num;
+		sem_op = sop->sem_op;
+		result = curr->semval;
+
+		if (sop->sem_flg & SEM_UNDO) {
+			int undo = un->semadj[sop->sem_num] - sem_op;
+
+			un->semadj[sop->sem_num] = undo;
+		}
+		curr->semval += sem_op;
+		curr->sempid = q->pid;
 	}
-	q->status = IN_WAKEUP;
-	q->pid = error;
 
-	list_add_tail(&q->list, pt);
+	return 0;
+
+would_block:
+	q->blocking = sop;
+	return sop->sem_flg & IPC_NOWAIT ? -EAGAIN : 1;
 }
 
-/**
- * wake_up_sem_queue_do - do the actual wake-up
- * @pt: list of tasks to be woken up
- *
- * Do the actual wake-up.
- * The function is called without any locks held, thus the semaphore array
- * could be destroyed already and the tasks can disappear as soon as the
- * status is set to the actual return code.
- */
-static void wake_up_sem_queue_do(struct list_head *pt)
+static inline void wake_up_sem_queue_prepare(struct sem_queue *q, int error,
+					     struct wake_q_head *wake_q)
 {
-	struct sem_queue *q, *t;
-	int did_something;
-
-	did_something = !list_empty(pt);
-	list_for_each_entry_safe(q, t, pt, list) {
-		wake_up_process(q->sleeper);
-		/* q can disappear immediately after writing q->status. */
-		smp_wmb();
-		q->status = q->pid;
-	}
-	if (did_something)
-		preempt_enable();
+	wake_q_add(wake_q, q->sleeper);
+	/*
+	 * Rely on the above implicit barrier, such that we can
+	 * ensure that we hold reference to the task before setting
+	 * q->status. Otherwise we could race with do_exit if the
+	 * task is awoken by an external event before calling
+	 * wake_up_process().
+	 */
+	WRITE_ONCE(q->status, error);
 }
 
 static void unlink_queue(struct sem_array *sma, struct sem_queue *q)
@@ -784,7 +766,7 @@ static void unlink_queue(struct sem_array *sma, struct sem_queue *q)
  * modified the array.
  * Note that wait-for-zero operations are handled without restart.
  */
-static int check_restart(struct sem_array *sma, struct sem_queue *q)
+static inline int check_restart(struct sem_array *sma, struct sem_queue *q)
 {
 	/* pending complex alter operations are too difficult to analyse */
 	if (!list_empty(&sma->pending_alter))
@@ -812,21 +794,20 @@ static int check_restart(struct sem_array *sma, struct sem_queue *q)
  * wake_const_ops - wake up non-alter tasks
  * @sma: semaphore array.
  * @semnum: semaphore that was modified.
- * @pt: list head for the tasks that must be woken up.
+ * @wake_q: lockless wake-queue head.
  *
  * wake_const_ops must be called after a semaphore in a semaphore array
  * was set to 0. If complex const operations are pending, wake_const_ops must
  * be called with semnum = -1, as well as with the number of each modified
  * semaphore.
- * The tasks that must be woken up are added to @pt. The return code
+ * The tasks that must be woken up are added to @wake_q. The return code
  * is stored in q->pid.
  * The function returns 1 if at least one operation was completed successfully.
  */
 static int wake_const_ops(struct sem_array *sma, int semnum,
-				struct list_head *pt)
+			  struct wake_q_head *wake_q)
 {
-	struct sem_queue *q;
-	struct list_head *walk;
+	struct sem_queue *q, *tmp;
 	struct list_head *pending_list;
 	int semop_completed = 0;
 
@@ -835,25 +816,19 @@ static int wake_const_ops(struct sem_array *sma, int semnum,
 	else
 		pending_list = &sma->sem_base[semnum].pending_const;
 
-	walk = pending_list->next;
-	while (walk != pending_list) {
-		int error;
-
-		q = container_of(walk, struct sem_queue, list);
-		walk = walk->next;
-
-		error = perform_atomic_semop(sma, q);
-
-		if (error <= 0) {
-			/* operation completed, remove from queue & wakeup */
+	list_for_each_entry_safe(q, tmp, pending_list, list) {
+		int error = perform_atomic_semop(sma, q);
 
-			unlink_queue(sma, q);
+		if (error > 0)
+			continue;
+		/* operation completed, remove from queue & wakeup */
+		unlink_queue(sma, q);
 
-			wake_up_sem_queue_prepare(pt, q, error);
-			if (error == 0)
-				semop_completed = 1;
-		}
+		wake_up_sem_queue_prepare(q, error, wake_q);
+		if (error == 0)
+			semop_completed = 1;
 	}
+
 	return semop_completed;
 }
 
@@ -862,14 +837,14 @@ static int wake_const_ops(struct sem_array *sma, int semnum,
  * @sma: semaphore array
  * @sops: operations that were performed
  * @nsops: number of operations
- * @pt: list head of the tasks that must be woken up.
+ * @wake_q: lockless wake-queue head
  *
  * Checks all required queue for wait-for-zero operations, based
  * on the actual changes that were performed on the semaphore array.
  * The function returns 1 if at least one operation was completed successfully.
  */
 static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops,
-					int nsops, struct list_head *pt)
+				int nsops, struct wake_q_head *wake_q)
 {
 	int i;
 	int semop_completed = 0;
@@ -882,7 +857,7 @@ static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops,
 
 			if (sma->sem_base[num].semval == 0) {
 				got_zero = 1;
-				semop_completed |= wake_const_ops(sma, num, pt);
+				semop_completed |= wake_const_ops(sma, num, wake_q);
 			}
 		}
 	} else {
@@ -893,7 +868,7 @@ static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops,
 		for (i = 0; i < sma->sem_nsems; i++) {
 			if (sma->sem_base[i].semval == 0) {
 				got_zero = 1;
-				semop_completed |= wake_const_ops(sma, i, pt);
+				semop_completed |= wake_const_ops(sma, i, wake_q);
 			}
 		}
 	}
@@ -902,7 +877,7 @@ static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops,
 	 * then check the global queue, too.
 	 */
 	if (got_zero)
-		semop_completed |= wake_const_ops(sma, -1, pt);
+		semop_completed |= wake_const_ops(sma, -1, wake_q);
 
 	return semop_completed;
 }
@@ -912,22 +887,21 @@ static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops,
  * update_queue - look for tasks that can be completed.
  * @sma: semaphore array.
  * @semnum: semaphore that was modified.
- * @pt: list head for the tasks that must be woken up.
+ * @wake_q: lockless wake-queue head.
  *
  * update_queue must be called after a semaphore in a semaphore array
  * was modified. If multiple semaphores were modified, update_queue must
  * be called with semnum = -1, as well as with the number of each modified
  * semaphore.
- * The tasks that must be woken up are added to @pt. The return code
+ * The tasks that must be woken up are added to @wake_q. The return code
  * is stored in q->pid.
  * The function internally checks if const operations can now succeed.
  *
  * The function return 1 if at least one semop was completed successfully.
  */
-static int update_queue(struct sem_array *sma, int semnum, struct list_head *pt)
+static int update_queue(struct sem_array *sma, int semnum, struct wake_q_head *wake_q)
 {
-	struct sem_queue *q;
-	struct list_head *walk;
+	struct sem_queue *q, *tmp;
 	struct list_head *pending_list;
 	int semop_completed = 0;
 
@@ -937,13 +911,9 @@ static int update_queue(struct sem_array *sma, int semnum, struct list_head *pt)
 		pending_list = &sma->sem_base[semnum].pending_alter;
 
 again:
-	walk = pending_list->next;
-	while (walk != pending_list) {
+	list_for_each_entry_safe(q, tmp, pending_list, list) {
 		int error, restart;
 
-		q = container_of(walk, struct sem_queue, list);
-		walk = walk->next;
-
 		/* If we are scanning the single sop, per-semaphore list of
 		 * one semaphore and that semaphore is 0, then it is not
 		 * necessary to scan further: simple increments
@@ -966,11 +936,11 @@ again:
 			restart = 0;
 		} else {
 			semop_completed = 1;
-			do_smart_wakeup_zero(sma, q->sops, q->nsops, pt);
+			do_smart_wakeup_zero(sma, q->sops, q->nsops, wake_q);
 			restart = check_restart(sma, q);
 		}
 
-		wake_up_sem_queue_prepare(pt, q, error);
+		wake_up_sem_queue_prepare(q, error, wake_q);
 		if (restart)
 			goto again;
 	}
@@ -1001,24 +971,24 @@ static void set_semotime(struct sem_array *sma, struct sembuf *sops)
  * @sops: operations that were performed
  * @nsops: number of operations
  * @otime: force setting otime
- * @pt: list head of the tasks that must be woken up.
+ * @wake_q: lockless wake-queue head
  *
  * do_smart_update() does the required calls to update_queue and wakeup_zero,
  * based on the actual changes that were performed on the semaphore array.
  * Note that the function does not do the actual wake-up: the caller is
- * responsible for calling wake_up_sem_queue_do(@pt).
+ * responsible for calling wake_up_q().
  * It is safe to perform this call after dropping all locks.
  */
 static void do_smart_update(struct sem_array *sma, struct sembuf *sops, int nsops,
-			int otime, struct list_head *pt)
+			    int otime, struct wake_q_head *wake_q)
 {
 	int i;
 
-	otime |= do_smart_wakeup_zero(sma, sops, nsops, pt);
+	otime |= do_smart_wakeup_zero(sma, sops, nsops, wake_q);
 
 	if (!list_empty(&sma->pending_alter)) {
 		/* semaphore array uses the global queue - just process it. */
-		otime |= update_queue(sma, -1, pt);
+		otime |= update_queue(sma, -1, wake_q);
 	} else {
 		if (!sops) {
 			/*
@@ -1026,7 +996,7 @@ static void do_smart_update(struct sem_array *sma, struct sembuf *sops, int nsop
 			 * known. Check all.
 			 */
 			for (i = 0; i < sma->sem_nsems; i++)
-				otime |= update_queue(sma, i, pt);
+				otime |= update_queue(sma, i, wake_q);
 		} else {
 			/*
 			 * Check the semaphores that were increased:
@@ -1040,7 +1010,7 @@ static void do_smart_update(struct sem_array *sma, struct sembuf *sops, int nsop
 			for (i = 0; i < nsops; i++) {
 				if (sops[i].sem_op > 0) {
 					otime |= update_queue(sma,
-							sops[i].sem_num, pt);
+							      sops[i].sem_num, wake_q);
 				}
 			}
 		}
@@ -1128,8 +1098,8 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 	struct sem_undo *un, *tu;
 	struct sem_queue *q, *tq;
 	struct sem_array *sma = container_of(ipcp, struct sem_array, sem_perm);
-	struct list_head tasks;
 	int i;
+	DEFINE_WAKE_Q(wake_q);
 
 	/* Free the existing undo structures for this semaphore set.  */
 	ipc_assert_locked_object(&sma->sem_perm);
@@ -1143,25 +1113,24 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 	}
 
 	/* Wake up all pending processes and let them fail with EIDRM. */
-	INIT_LIST_HEAD(&tasks);
 	list_for_each_entry_safe(q, tq, &sma->pending_const, list) {
 		unlink_queue(sma, q);
-		wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
+		wake_up_sem_queue_prepare(q, -EIDRM, &wake_q);
 	}
 
 	list_for_each_entry_safe(q, tq, &sma->pending_alter, list) {
 		unlink_queue(sma, q);
-		wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
+		wake_up_sem_queue_prepare(q, -EIDRM, &wake_q);
 	}
 	for (i = 0; i < sma->sem_nsems; i++) {
 		struct sem *sem = sma->sem_base + i;
 		list_for_each_entry_safe(q, tq, &sem->pending_const, list) {
 			unlink_queue(sma, q);
-			wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
+			wake_up_sem_queue_prepare(q, -EIDRM, &wake_q);
 		}
 		list_for_each_entry_safe(q, tq, &sem->pending_alter, list) {
 			unlink_queue(sma, q);
-			wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
+			wake_up_sem_queue_prepare(q, -EIDRM, &wake_q);
 		}
 	}
 
@@ -1170,7 +1139,7 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 	sem_unlock(sma, -1);
 	rcu_read_unlock();
 
-	wake_up_sem_queue_do(&tasks);
+	wake_up_q(&wake_q);
 	ns->used_sems -= sma->sem_nsems;
 	ipc_rcu_putref(sma, sem_rcu_free);
 }
@@ -1309,9 +1278,9 @@ static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum,
 	struct sem_undo *un;
 	struct sem_array *sma;
 	struct sem *curr;
-	int err;
-	struct list_head tasks;
-	int val;
+	int err, val;
+	DEFINE_WAKE_Q(wake_q);
+
 #if defined(CONFIG_64BIT) && defined(__BIG_ENDIAN)
 	/* big-endian 64bit */
 	val = arg >> 32;
@@ -1323,8 +1292,6 @@ static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum,
 	if (val > SEMVMX || val < 0)
 		return -ERANGE;
 
-	INIT_LIST_HEAD(&tasks);
-
 	rcu_read_lock();
 	sma = sem_obtain_object_check(ns, semid);
 	if (IS_ERR(sma)) {
@@ -1367,10 +1334,10 @@ static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum,
 	curr->sempid = task_tgid_vnr(current);
 	sma->sem_ctime = get_seconds();
 	/* maybe some queued-up processes were waiting for this */
-	do_smart_update(sma, NULL, 0, 0, &tasks);
+	do_smart_update(sma, NULL, 0, 0, &wake_q);
 	sem_unlock(sma, -1);
 	rcu_read_unlock();
-	wake_up_sem_queue_do(&tasks);
+	wake_up_q(&wake_q);
 	return 0;
 }
 
@@ -1382,9 +1349,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 	int err, nsems;
 	ushort fast_sem_io[SEMMSL_FAST];
 	ushort *sem_io = fast_sem_io;
-	struct list_head tasks;
-
-	INIT_LIST_HEAD(&tasks);
+	DEFINE_WAKE_Q(wake_q);
 
 	rcu_read_lock();
 	sma = sem_obtain_object_check(ns, semid);
@@ -1495,7 +1460,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		}
 		sma->sem_ctime = get_seconds();
 		/* maybe some queued-up processes were waiting for this */
-		do_smart_update(sma, NULL, 0, 0, &tasks);
+		do_smart_update(sma, NULL, 0, 0, &wake_q);
 		err = 0;
 		goto out_unlock;
 	}
@@ -1531,7 +1496,7 @@ out_unlock:
 	sem_unlock(sma, -1);
 out_rcu_wakeup:
 	rcu_read_unlock();
-	wake_up_sem_queue_do(&tasks);
+	wake_up_q(&wake_q);
 out_free:
 	if (sem_io != fast_sem_io)
 		ipc_free(sem_io);
@@ -1804,32 +1769,6 @@ out:
 	return un;
 }
 
-
-/**
- * get_queue_result - retrieve the result code from sem_queue
- * @q: Pointer to queue structure
- *
- * Retrieve the return code from the pending queue. If IN_WAKEUP is found in
- * q->status, then we must loop until the value is replaced with the final
- * value: This may happen if a task is woken up by an unrelated event (e.g.
- * signal) and in parallel the task is woken up by another task because it got
- * the requested semaphores.
- *
- * The function can be called with or without holding the semaphore spinlock.
- */
-static int get_queue_result(struct sem_queue *q)
-{
-	int error;
-
-	error = q->status;
-	while (unlikely(error == IN_WAKEUP)) {
-		cpu_relax();
-		error = q->status;
-	}
-
-	return error;
-}
-
 SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 		unsigned, nsops, const struct timespec __user *, timeout)
 {
@@ -1838,11 +1777,11 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 	struct sembuf fast_sops[SEMOPM_FAST];
 	struct sembuf *sops = fast_sops, *sop;
 	struct sem_undo *un;
-	int undos = 0, alter = 0, max, locknum;
+	int max, locknum;
+	bool undos = false, alter = false, dupsop = false;
 	struct sem_queue queue;
-	unsigned long jiffies_left = 0;
+	unsigned long dup = 0, jiffies_left = 0;
 	struct ipc_namespace *ns;
-	struct list_head tasks;
 
 	ns = current->nsproxy->ipc_ns;
 
@@ -1855,10 +1794,12 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 		if (sops == NULL)
 			return -ENOMEM;
 	}
+
 	if (copy_from_user(sops, tsops, nsops * sizeof(*tsops))) {
 		error =  -EFAULT;
 		goto out_free;
 	}
+
 	if (timeout) {
 		struct timespec _timeout;
 		if (copy_from_user(&_timeout, timeout, sizeof(*timeout))) {
@@ -1872,18 +1813,30 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 		}
 		jiffies_left = timespec_to_jiffies(&_timeout);
 	}
+
 	max = 0;
 	for (sop = sops; sop < sops + nsops; sop++) {
+		unsigned long mask = 1ULL << ((sop->sem_num) % BITS_PER_LONG);
+
 		if (sop->sem_num >= max)
 			max = sop->sem_num;
 		if (sop->sem_flg & SEM_UNDO)
-			undos = 1;
-		if (sop->sem_op != 0)
-			alter = 1;
+			undos = true;
+		if (dup & mask) {
+			/*
+			 * There was a previous alter access that appears
+			 * to have accessed the same semaphore, thus use
+			 * the dupsop logic. "appears", because the detection
+			 * can only check % BITS_PER_LONG.
+			 */
+			dupsop = true;
+		}
+		if (sop->sem_op != 0) {
+			alter = true;
+			dup |= mask;
+		}
 	}
 
-	INIT_LIST_HEAD(&tasks);
-
 	if (undos) {
 		/* On success, find_alloc_undo takes the rcu_read_lock */
 		un = find_alloc_undo(ns, semid);
@@ -1904,16 +1857,22 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 	}
 
 	error = -EFBIG;
-	if (max >= sma->sem_nsems)
-		goto out_rcu_wakeup;
+	if (max >= sma->sem_nsems) {
+		rcu_read_unlock();
+		goto out_free;
+	}
 
 	error = -EACCES;
-	if (ipcperms(ns, &sma->sem_perm, alter ? S_IWUGO : S_IRUGO))
-		goto out_rcu_wakeup;
+	if (ipcperms(ns, &sma->sem_perm, alter ? S_IWUGO : S_IRUGO)) {
+		rcu_read_unlock();
+		goto out_free;
+	}
 
 	error = security_sem_semop(sma, sops, nsops, alter);
-	if (error)
-		goto out_rcu_wakeup;
+	if (error) {
+		rcu_read_unlock();
+		goto out_free;
+	}
 
 	error = -EIDRM;
 	locknum = sem_lock(sma, sops, nsops);
@@ -1942,24 +1901,34 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 	queue.undo = un;
 	queue.pid = task_tgid_vnr(current);
 	queue.alter = alter;
+	queue.dupsop = dupsop;
 
 	error = perform_atomic_semop(sma, &queue);
-	if (error == 0) {
-		/* If the operation was successful, then do
+	if (error == 0) { /* non-blocking succesfull path */
+		DEFINE_WAKE_Q(wake_q);
+
+		/*
+		 * If the operation was successful, then do
 		 * the required updates.
 		 */
 		if (alter)
-			do_smart_update(sma, sops, nsops, 1, &tasks);
+			do_smart_update(sma, sops, nsops, 1, &wake_q);
 		else
 			set_semotime(sma, sops);
+
+		sem_unlock(sma, locknum);
+		rcu_read_unlock();
+		wake_up_q(&wake_q);
+
+		goto out_free;
 	}
-	if (error <= 0)
+	if (error < 0) /* non-blocking error path */
 		goto out_unlock_free;
 
-	/* We need to sleep on this operation, so we put the current
+	/*
+	 * We need to sleep on this operation, so we put the current
 	 * task into the pending queue and go to sleep.
 	 */
-
 	if (nsops == 1) {
 		struct sem *curr;
 		curr = &sma->sem_base[sops->sem_num];
@@ -1988,77 +1957,69 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 		sma->complex_count++;
 	}
 
-	queue.status = -EINTR;
-	queue.sleeper = current;
+	do {
+		queue.status = -EINTR;
+		queue.sleeper = current;
 
-sleep_again:
-	__set_current_state(TASK_INTERRUPTIBLE);
-	sem_unlock(sma, locknum);
-	rcu_read_unlock();
-
-	if (timeout)
-		jiffies_left = schedule_timeout(jiffies_left);
-	else
-		schedule();
+		__set_current_state(TASK_INTERRUPTIBLE);
+		sem_unlock(sma, locknum);
+		rcu_read_unlock();
 
-	error = get_queue_result(&queue);
+		if (timeout)
+			jiffies_left = schedule_timeout(jiffies_left);
+		else
+			schedule();
 
-	if (error != -EINTR) {
-		/* fast path: update_queue already obtained all requested
-		 * resources.
-		 * Perform a smp_mb(): User space could assume that semop()
-		 * is a memory barrier: Without the mb(), the cpu could
-		 * speculatively read in user space stale data that was
-		 * overwritten by the previous owner of the semaphore.
+		/*
+		 * fastpath: the semop has completed, either successfully or
+		 * not, from the syscall pov, is quite irrelevant to us at this
+		 * point; we're done.
+		 *
+		 * We _do_ care, nonetheless, about being awoken by a signal or
+		 * spuriously.  The queue.status is checked again in the
+		 * slowpath (aka after taking sem_lock), such that we can detect
+		 * scenarios where we were awakened externally, during the
+		 * window between wake_q_add() and wake_up_q().
 		 */
-		smp_mb();
-
-		goto out_free;
-	}
-
-	rcu_read_lock();
-	sma = sem_obtain_lock(ns, semid, sops, nsops, &locknum);
-
-	/*
-	 * Wait until it's guaranteed that no wakeup_sem_queue_do() is ongoing.
-	 */
-	error = get_queue_result(&queue);
+		error = READ_ONCE(queue.status);
+		if (error != -EINTR) {
+			/*
+			 * User space could assume that semop() is a memory
+			 * barrier: Without the mb(), the cpu could
+			 * speculatively read in userspace stale data that was
+			 * overwritten by the previous owner of the semaphore.
+			 */
+			smp_mb();
+			goto out_free;
+		}
 
-	/*
-	 * Array removed? If yes, leave without sem_unlock().
-	 */
-	if (IS_ERR(sma)) {
-		rcu_read_unlock();
-		goto out_free;
-	}
+		rcu_read_lock();
+		sem_lock(sma, sops, nsops);
 
+		if (!ipc_valid_object(&sma->sem_perm))
+			goto out_unlock_free;
 
-	/*
-	 * If queue.status != -EINTR we are woken up by another process.
-	 * Leave without unlink_queue(), but with sem_unlock().
-	 */
-	if (error != -EINTR)
-		goto out_unlock_free;
+		error = READ_ONCE(queue.status);
 
-	/*
-	 * If an interrupt occurred we have to clean up the queue
-	 */
-	if (timeout && jiffies_left == 0)
-		error = -EAGAIN;
+		/*
+		 * If queue.status != -EINTR we are woken up by another process.
+		 * Leave without unlink_queue(), but with sem_unlock().
+		 */
+		if (error != -EINTR)
+			goto out_unlock_free;
 
-	/*
-	 * If the wakeup was spurious, just retry
-	 */
-	if (error == -EINTR && !signal_pending(current))
-		goto sleep_again;
+		/*
+		 * If an interrupt occurred we have to clean up the queue.
+		 */
+		if (timeout && jiffies_left == 0)
+			error = -EAGAIN;
+	} while (error == -EINTR && !signal_pending(current)); /* spurious */
 
 	unlink_queue(sma, &queue);
 
 out_unlock_free:
 	sem_unlock(sma, locknum);
-out_rcu_wakeup:
 	rcu_read_unlock();
-	wake_up_sem_queue_do(&tasks);
 out_free:
 	if (sops != fast_sops)
 		kfree(sops);
@@ -2119,8 +2080,8 @@ void exit_sem(struct task_struct *tsk)
 	for (;;) {
 		struct sem_array *sma;
 		struct sem_undo *un;
-		struct list_head tasks;
 		int semid, i;
+		DEFINE_WAKE_Q(wake_q);
 
 		cond_resched();
 
@@ -2208,11 +2169,10 @@ void exit_sem(struct task_struct *tsk)
 			}
 		}
 		/* maybe some queued-up processes were waiting for this */
-		INIT_LIST_HEAD(&tasks);
-		do_smart_update(sma, NULL, 0, 1, &tasks);
+		do_smart_update(sma, NULL, 0, 1, &wake_q);
 		sem_unlock(sma, -1);
 		rcu_read_unlock();
-		wake_up_sem_queue_do(&tasks);
+		wake_up_q(&wake_q);
 
 		kfree_rcu(un, rcu);
 	}
diff --git a/kernel/Makefile b/kernel/Makefile
index eb26e12c6c2a..314e7d62f5f0 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -84,6 +84,7 @@ obj-$(CONFIG_KPROBES) += kprobes.o
 obj-$(CONFIG_KGDB) += debug/
 obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
 obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o
+obj-$(CONFIG_HARDLOCKUP_DETECTOR) += watchdog_hld.o
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index f9ec9add2164..215871bda3a2 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -301,7 +301,7 @@ int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr,
 retry:
 	/* Read the page with vaddr into memory */
 	ret = get_user_pages_remote(NULL, mm, vaddr, 1, FOLL_FORCE, &old_page,
-			&vma);
+			&vma, NULL);
 	if (ret <= 0)
 		return ret;
 
@@ -1712,7 +1712,7 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr)
 	 * essentially a kernel access to the memory.
 	 */
 	result = get_user_pages_remote(NULL, mm, vaddr, 1, FOLL_FORCE, &page,
-			NULL);
+			NULL, NULL);
 	if (result < 0)
 		return result;
 
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index cd6716e115e8..3c8bb6571128 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -121,3 +121,8 @@ long clock_nanosleep_restart(struct restart_block *restart_block)
 	return hrtimer_nanosleep_restart(restart_block);
 }
 #endif
+
+int posix_timer_event(struct k_itimer *timr, int si_private)
+{
+	return 0;
+}
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 6d1020c03d41..d4b0fa01cae3 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -24,32 +24,14 @@
 
 #include <asm/irq_regs.h>
 #include <linux/kvm_para.h>
-#include <linux/perf_event.h>
 #include <linux/kthread.h>
 
-/*
- * The run state of the lockup detectors is controlled by the content of the
- * 'watchdog_enabled' variable. Each lockup detector has its dedicated bit -
- * bit 0 for the hard lockup detector and bit 1 for the soft lockup detector.
- *
- * 'watchdog_user_enabled', 'nmi_watchdog_enabled' and 'soft_watchdog_enabled'
- * are variables that are only used as an 'interface' between the parameters
- * in /proc/sys/kernel and the internal state bits in 'watchdog_enabled'. The
- * 'watchdog_thresh' variable is handled differently because its value is not
- * boolean, and the lockup detectors are 'suspended' while 'watchdog_thresh'
- * is equal zero.
- */
-#define NMI_WATCHDOG_ENABLED_BIT   0
-#define SOFT_WATCHDOG_ENABLED_BIT  1
-#define NMI_WATCHDOG_ENABLED      (1 << NMI_WATCHDOG_ENABLED_BIT)
-#define SOFT_WATCHDOG_ENABLED     (1 << SOFT_WATCHDOG_ENABLED_BIT)
-
 static DEFINE_MUTEX(watchdog_proc_mutex);
 
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
-static unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED|NMI_WATCHDOG_ENABLED;
+#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
+unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED|NMI_WATCHDOG_ENABLED;
 #else
-static unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED;
+unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED;
 #endif
 int __read_mostly nmi_watchdog_enabled;
 int __read_mostly soft_watchdog_enabled;
@@ -59,9 +41,6 @@ int __read_mostly watchdog_thresh = 10;
 #ifdef CONFIG_SMP
 int __read_mostly sysctl_softlockup_all_cpu_backtrace;
 int __read_mostly sysctl_hardlockup_all_cpu_backtrace;
-#else
-#define sysctl_softlockup_all_cpu_backtrace 0
-#define sysctl_hardlockup_all_cpu_backtrace 0
 #endif
 static struct cpumask watchdog_cpumask __read_mostly;
 unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
@@ -100,50 +79,9 @@ static DEFINE_PER_CPU(bool, soft_watchdog_warn);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
 static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt);
 static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved);
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
-static DEFINE_PER_CPU(bool, hard_watchdog_warn);
-static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
-static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
-#endif
 static unsigned long soft_lockup_nmi_warn;
 
-/* boot commands */
-/*
- * Should we panic when a soft-lockup or hard-lockup occurs:
- */
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
-unsigned int __read_mostly hardlockup_panic =
-			CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE;
-static unsigned long hardlockup_allcpu_dumped;
-/*
- * We may not want to enable hard lockup detection by default in all cases,
- * for example when running the kernel as a guest on a hypervisor. In these
- * cases this function can be called to disable hard lockup detection. This
- * function should only be executed once by the boot processor before the
- * kernel command line parameters are parsed, because otherwise it is not
- * possible to override this in hardlockup_panic_setup().
- */
-void hardlockup_detector_disable(void)
-{
-	watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
-}
-
-static int __init hardlockup_panic_setup(char *str)
-{
-	if (!strncmp(str, "panic", 5))
-		hardlockup_panic = 1;
-	else if (!strncmp(str, "nopanic", 7))
-		hardlockup_panic = 0;
-	else if (!strncmp(str, "0", 1))
-		watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
-	else if (!strncmp(str, "1", 1))
-		watchdog_enabled |= NMI_WATCHDOG_ENABLED;
-	return 1;
-}
-__setup("nmi_watchdog=", hardlockup_panic_setup);
-#endif
-
 unsigned int __read_mostly softlockup_panic =
 			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
 
@@ -264,32 +202,14 @@ void touch_all_softlockup_watchdogs(void)
 	wq_watchdog_touch(-1);
 }
 
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
-void touch_nmi_watchdog(void)
-{
-	/*
-	 * Using __raw here because some code paths have
-	 * preemption enabled.  If preemption is enabled
-	 * then interrupts should be enabled too, in which
-	 * case we shouldn't have to worry about the watchdog
-	 * going off.
-	 */
-	raw_cpu_write(watchdog_nmi_touch, true);
-	touch_softlockup_watchdog();
-}
-EXPORT_SYMBOL(touch_nmi_watchdog);
-
-#endif
-
 void touch_softlockup_watchdog_sync(void)
 {
 	__this_cpu_write(softlockup_touch_sync, true);
 	__this_cpu_write(watchdog_touch_ts, 0);
 }
 
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
 /* watchdog detector functions */
-static bool is_hardlockup(void)
+bool is_hardlockup(void)
 {
 	unsigned long hrint = __this_cpu_read(hrtimer_interrupts);
 
@@ -299,7 +219,6 @@ static bool is_hardlockup(void)
 	__this_cpu_write(hrtimer_interrupts_saved, hrint);
 	return false;
 }
-#endif
 
 static int is_softlockup(unsigned long touch_ts)
 {
@@ -313,77 +232,22 @@ static int is_softlockup(unsigned long touch_ts)
 	return 0;
 }
 
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
-
-static struct perf_event_attr wd_hw_attr = {
-	.type		= PERF_TYPE_HARDWARE,
-	.config		= PERF_COUNT_HW_CPU_CYCLES,
-	.size		= sizeof(struct perf_event_attr),
-	.pinned		= 1,
-	.disabled	= 1,
-};
-
-/* Callback function for perf event subsystem */
-static void watchdog_overflow_callback(struct perf_event *event,
-		 struct perf_sample_data *data,
-		 struct pt_regs *regs)
-{
-	/* Ensure the watchdog never gets throttled */
-	event->hw.interrupts = 0;
-
-	if (__this_cpu_read(watchdog_nmi_touch) == true) {
-		__this_cpu_write(watchdog_nmi_touch, false);
-		return;
-	}
-
-	/* check for a hardlockup
-	 * This is done by making sure our timer interrupt
-	 * is incrementing.  The timer interrupt should have
-	 * fired multiple times before we overflow'd.  If it hasn't
-	 * then this is a good indication the cpu is stuck
-	 */
-	if (is_hardlockup()) {
-		int this_cpu = smp_processor_id();
-
-		/* only print hardlockups once */
-		if (__this_cpu_read(hard_watchdog_warn) == true)
-			return;
-
-		pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu);
-		print_modules();
-		print_irqtrace_events(current);
-		if (regs)
-			show_regs(regs);
-		else
-			dump_stack();
-
-		/*
-		 * Perform all-CPU dump only once to avoid multiple hardlockups
-		 * generating interleaving traces
-		 */
-		if (sysctl_hardlockup_all_cpu_backtrace &&
-				!test_and_set_bit(0, &hardlockup_allcpu_dumped))
-			trigger_allbutself_cpu_backtrace();
-
-		if (hardlockup_panic)
-			nmi_panic(regs, "Hard LOCKUP");
-
-		__this_cpu_write(hard_watchdog_warn, true);
-		return;
-	}
-
-	__this_cpu_write(hard_watchdog_warn, false);
-	return;
-}
-#endif /* CONFIG_HARDLOCKUP_DETECTOR */
-
 static void watchdog_interrupt_count(void)
 {
 	__this_cpu_inc(hrtimer_interrupts);
 }
 
-static int watchdog_nmi_enable(unsigned int cpu);
-static void watchdog_nmi_disable(unsigned int cpu);
+/*
+ * These two functions are mostly architecture specific
+ * defining them as weak here.
+ */
+int __weak watchdog_nmi_enable(unsigned int cpu)
+{
+	return 0;
+}
+void __weak watchdog_nmi_disable(unsigned int cpu)
+{
+}
 
 static int watchdog_enable_all_cpus(void);
 static void watchdog_disable_all_cpus(void);
@@ -576,109 +440,6 @@ static void watchdog(unsigned int cpu)
 		watchdog_nmi_disable(cpu);
 }
 
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
-/*
- * People like the simple clean cpu node info on boot.
- * Reduce the watchdog noise by only printing messages
- * that are different from what cpu0 displayed.
- */
-static unsigned long cpu0_err;
-
-static int watchdog_nmi_enable(unsigned int cpu)
-{
-	struct perf_event_attr *wd_attr;
-	struct perf_event *event = per_cpu(watchdog_ev, cpu);
-
-	/* nothing to do if the hard lockup detector is disabled */
-	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
-		goto out;
-
-	/* is it already setup and enabled? */
-	if (event && event->state > PERF_EVENT_STATE_OFF)
-		goto out;
-
-	/* it is setup but not enabled */
-	if (event != NULL)
-		goto out_enable;
-
-	wd_attr = &wd_hw_attr;
-	wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh);
-
-	/* Try to register using hardware perf events */
-	event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL);
-
-	/* save cpu0 error for future comparision */
-	if (cpu == 0 && IS_ERR(event))
-		cpu0_err = PTR_ERR(event);
-
-	if (!IS_ERR(event)) {
-		/* only print for cpu0 or different than cpu0 */
-		if (cpu == 0 || cpu0_err)
-			pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n");
-		goto out_save;
-	}
-
-	/*
-	 * Disable the hard lockup detector if _any_ CPU fails to set up
-	 * set up the hardware perf event. The watchdog() function checks
-	 * the NMI_WATCHDOG_ENABLED bit periodically.
-	 *
-	 * The barriers are for syncing up watchdog_enabled across all the
-	 * cpus, as clear_bit() does not use barriers.
-	 */
-	smp_mb__before_atomic();
-	clear_bit(NMI_WATCHDOG_ENABLED_BIT, &watchdog_enabled);
-	smp_mb__after_atomic();
-
-	/* skip displaying the same error again */
-	if (cpu > 0 && (PTR_ERR(event) == cpu0_err))
-		return PTR_ERR(event);
-
-	/* vary the KERN level based on the returned errno */
-	if (PTR_ERR(event) == -EOPNOTSUPP)
-		pr_info("disabled (cpu%i): not supported (no LAPIC?)\n", cpu);
-	else if (PTR_ERR(event) == -ENOENT)
-		pr_warn("disabled (cpu%i): hardware events not enabled\n",
-			 cpu);
-	else
-		pr_err("disabled (cpu%i): unable to create perf event: %ld\n",
-			cpu, PTR_ERR(event));
-
-	pr_info("Shutting down hard lockup detector on all cpus\n");
-
-	return PTR_ERR(event);
-
-	/* success path */
-out_save:
-	per_cpu(watchdog_ev, cpu) = event;
-out_enable:
-	perf_event_enable(per_cpu(watchdog_ev, cpu));
-out:
-	return 0;
-}
-
-static void watchdog_nmi_disable(unsigned int cpu)
-{
-	struct perf_event *event = per_cpu(watchdog_ev, cpu);
-
-	if (event) {
-		perf_event_disable(event);
-		per_cpu(watchdog_ev, cpu) = NULL;
-
-		/* should be in cleanup, but blocks oprofile */
-		perf_event_release_kernel(event);
-	}
-	if (cpu == 0) {
-		/* watchdog_nmi_enable() expects this to be zero initially. */
-		cpu0_err = 0;
-	}
-}
-
-#else
-static int watchdog_nmi_enable(unsigned int cpu) { return 0; }
-static void watchdog_nmi_disable(unsigned int cpu) { return; }
-#endif /* CONFIG_HARDLOCKUP_DETECTOR */
-
 static struct smp_hotplug_thread watchdog_threads = {
 	.store			= &softlockup_watchdog,
 	.thread_should_run	= watchdog_should_run,
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
new file mode 100644
index 000000000000..84016c8aee6b
--- /dev/null
+++ b/kernel/watchdog_hld.c
@@ -0,0 +1,227 @@
+/*
+ * Detect hard lockups on a system
+ *
+ * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
+ *
+ * Note: Most of this code is borrowed heavily from the original softlockup
+ * detector, so thanks to Ingo for the initial implementation.
+ * Some chunks also taken from the old x86-specific nmi watchdog code, thanks
+ * to those contributors as well.
+ */
+
+#define pr_fmt(fmt) "NMI watchdog: " fmt
+
+#include <linux/nmi.h>
+#include <linux/module.h>
+#include <asm/irq_regs.h>
+#include <linux/perf_event.h>
+
+static DEFINE_PER_CPU(bool, hard_watchdog_warn);
+static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
+static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
+
+/* boot commands */
+/*
+ * Should we panic when a soft-lockup or hard-lockup occurs:
+ */
+unsigned int __read_mostly hardlockup_panic =
+			CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE;
+static unsigned long hardlockup_allcpu_dumped;
+/*
+ * We may not want to enable hard lockup detection by default in all cases,
+ * for example when running the kernel as a guest on a hypervisor. In these
+ * cases this function can be called to disable hard lockup detection. This
+ * function should only be executed once by the boot processor before the
+ * kernel command line parameters are parsed, because otherwise it is not
+ * possible to override this in hardlockup_panic_setup().
+ */
+void hardlockup_detector_disable(void)
+{
+	watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
+}
+
+static int __init hardlockup_panic_setup(char *str)
+{
+	if (!strncmp(str, "panic", 5))
+		hardlockup_panic = 1;
+	else if (!strncmp(str, "nopanic", 7))
+		hardlockup_panic = 0;
+	else if (!strncmp(str, "0", 1))
+		watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
+	else if (!strncmp(str, "1", 1))
+		watchdog_enabled |= NMI_WATCHDOG_ENABLED;
+	return 1;
+}
+__setup("nmi_watchdog=", hardlockup_panic_setup);
+
+void touch_nmi_watchdog(void)
+{
+	/*
+	 * Using __raw here because some code paths have
+	 * preemption enabled.  If preemption is enabled
+	 * then interrupts should be enabled too, in which
+	 * case we shouldn't have to worry about the watchdog
+	 * going off.
+	 */
+	raw_cpu_write(watchdog_nmi_touch, true);
+	touch_softlockup_watchdog();
+}
+EXPORT_SYMBOL(touch_nmi_watchdog);
+
+static struct perf_event_attr wd_hw_attr = {
+	.type		= PERF_TYPE_HARDWARE,
+	.config		= PERF_COUNT_HW_CPU_CYCLES,
+	.size		= sizeof(struct perf_event_attr),
+	.pinned		= 1,
+	.disabled	= 1,
+};
+
+/* Callback function for perf event subsystem */
+static void watchdog_overflow_callback(struct perf_event *event,
+		 struct perf_sample_data *data,
+		 struct pt_regs *regs)
+{
+	/* Ensure the watchdog never gets throttled */
+	event->hw.interrupts = 0;
+
+	if (__this_cpu_read(watchdog_nmi_touch) == true) {
+		__this_cpu_write(watchdog_nmi_touch, false);
+		return;
+	}
+
+	/* check for a hardlockup
+	 * This is done by making sure our timer interrupt
+	 * is incrementing.  The timer interrupt should have
+	 * fired multiple times before we overflow'd.  If it hasn't
+	 * then this is a good indication the cpu is stuck
+	 */
+	if (is_hardlockup()) {
+		int this_cpu = smp_processor_id();
+
+		/* only print hardlockups once */
+		if (__this_cpu_read(hard_watchdog_warn) == true)
+			return;
+
+		pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu);
+		print_modules();
+		print_irqtrace_events(current);
+		if (regs)
+			show_regs(regs);
+		else
+			dump_stack();
+
+		/*
+		 * Perform all-CPU dump only once to avoid multiple hardlockups
+		 * generating interleaving traces
+		 */
+		if (sysctl_hardlockup_all_cpu_backtrace &&
+				!test_and_set_bit(0, &hardlockup_allcpu_dumped))
+			trigger_allbutself_cpu_backtrace();
+
+		if (hardlockup_panic)
+			nmi_panic(regs, "Hard LOCKUP");
+
+		__this_cpu_write(hard_watchdog_warn, true);
+		return;
+	}
+
+	__this_cpu_write(hard_watchdog_warn, false);
+	return;
+}
+
+/*
+ * People like the simple clean cpu node info on boot.
+ * Reduce the watchdog noise by only printing messages
+ * that are different from what cpu0 displayed.
+ */
+static unsigned long cpu0_err;
+
+int watchdog_nmi_enable(unsigned int cpu)
+{
+	struct perf_event_attr *wd_attr;
+	struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+	/* nothing to do if the hard lockup detector is disabled */
+	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
+		goto out;
+
+	/* is it already setup and enabled? */
+	if (event && event->state > PERF_EVENT_STATE_OFF)
+		goto out;
+
+	/* it is setup but not enabled */
+	if (event != NULL)
+		goto out_enable;
+
+	wd_attr = &wd_hw_attr;
+	wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh);
+
+	/* Try to register using hardware perf events */
+	event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL);
+
+	/* save cpu0 error for future comparision */
+	if (cpu == 0 && IS_ERR(event))
+		cpu0_err = PTR_ERR(event);
+
+	if (!IS_ERR(event)) {
+		/* only print for cpu0 or different than cpu0 */
+		if (cpu == 0 || cpu0_err)
+			pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n");
+		goto out_save;
+	}
+
+	/*
+	 * Disable the hard lockup detector if _any_ CPU fails to set up
+	 * set up the hardware perf event. The watchdog() function checks
+	 * the NMI_WATCHDOG_ENABLED bit periodically.
+	 *
+	 * The barriers are for syncing up watchdog_enabled across all the
+	 * cpus, as clear_bit() does not use barriers.
+	 */
+	smp_mb__before_atomic();
+	clear_bit(NMI_WATCHDOG_ENABLED_BIT, &watchdog_enabled);
+	smp_mb__after_atomic();
+
+	/* skip displaying the same error again */
+	if (cpu > 0 && (PTR_ERR(event) == cpu0_err))
+		return PTR_ERR(event);
+
+	/* vary the KERN level based on the returned errno */
+	if (PTR_ERR(event) == -EOPNOTSUPP)
+		pr_info("disabled (cpu%i): not supported (no LAPIC?)\n", cpu);
+	else if (PTR_ERR(event) == -ENOENT)
+		pr_warn("disabled (cpu%i): hardware events not enabled\n",
+			 cpu);
+	else
+		pr_err("disabled (cpu%i): unable to create perf event: %ld\n",
+			cpu, PTR_ERR(event));
+
+	pr_info("Shutting down hard lockup detector on all cpus\n");
+
+	return PTR_ERR(event);
+
+	/* success path */
+out_save:
+	per_cpu(watchdog_ev, cpu) = event;
+out_enable:
+	perf_event_enable(per_cpu(watchdog_ev, cpu));
+out:
+	return 0;
+}
+
+void watchdog_nmi_disable(unsigned int cpu)
+{
+	struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+	if (event) {
+		perf_event_disable(event);
+		per_cpu(watchdog_ev, cpu) = NULL;
+
+		/* should be in cleanup, but blocks oprofile */
+		perf_event_release_kernel(event);
+	}
+	if (cpu == 0) {
+		/* watchdog_nmi_enable() expects this to be zero initially. */
+		cpu0_err = 0;
+	}
+}
diff --git a/mm/filemap.c b/mm/filemap.c
index 69568388c699..235021e361eb 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2164,12 +2164,12 @@ page_not_uptodate:
 }
 EXPORT_SYMBOL(filemap_fault);
 
-void filemap_map_pages(struct fault_env *fe,
+void filemap_map_pages(struct vm_fault *vmf,
 		pgoff_t start_pgoff, pgoff_t end_pgoff)
 {
 	struct radix_tree_iter iter;
 	void **slot;
-	struct file *file = fe->vma->vm_file;
+	struct file *file = vmf->vma->vm_file;
 	struct address_space *mapping = file->f_mapping;
 	pgoff_t last_pgoff = start_pgoff;
 	loff_t size;
@@ -2225,11 +2225,11 @@ repeat:
 		if (file->f_ra.mmap_miss > 0)
 			file->f_ra.mmap_miss--;
 
-		fe->address += (iter.index - last_pgoff) << PAGE_SHIFT;
-		if (fe->pte)
-			fe->pte += iter.index - last_pgoff;
+		vmf->address += (iter.index - last_pgoff) << PAGE_SHIFT;
+		if (vmf->pte)
+			vmf->pte += iter.index - last_pgoff;
 		last_pgoff = iter.index;
-		if (alloc_set_pte(fe, NULL, page))
+		if (alloc_set_pte(vmf, NULL, page))
 			goto unlock;
 		unlock_page(page);
 		goto next;
@@ -2239,7 +2239,7 @@ skip:
 		put_page(page);
 next:
 		/* Huge page is mapped? No need to proceed. */
-		if (pmd_trans_huge(*fe->pmd))
+		if (pmd_trans_huge(*vmf->pmd))
 			break;
 		if (iter.index == end_pgoff)
 			break;
diff --git a/mm/gup.c b/mm/gup.c
index e50178c58b97..55315555489d 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -865,9 +865,10 @@ EXPORT_SYMBOL(get_user_pages_locked);
  * caller if required (just like with __get_user_pages). "FOLL_GET"
  * is set implicitly if "pages" is non-NULL.
  */
-__always_inline long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
-					       unsigned long start, unsigned long nr_pages,
-					       struct page **pages, unsigned int gup_flags)
+static __always_inline long __get_user_pages_unlocked(struct task_struct *tsk,
+		struct mm_struct *mm, unsigned long start,
+		unsigned long nr_pages, struct page **pages,
+		unsigned int gup_flags)
 {
 	long ret;
 	int locked = 1;
@@ -879,7 +880,6 @@ __always_inline long __get_user_pages_unlocked(struct task_struct *tsk, struct m
 		up_read(&mm->mmap_sem);
 	return ret;
 }
-EXPORT_SYMBOL(__get_user_pages_unlocked);
 
 /*
  * get_user_pages_unlocked() is suitable to replace the form:
@@ -917,6 +917,9 @@ EXPORT_SYMBOL(get_user_pages_unlocked);
  *		only intends to ensure the pages are faulted in.
  * @vmas:	array of pointers to vmas corresponding to each page.
  *		Or NULL if the caller does not require them.
+ * @locked:	pointer to lock flag indicating whether lock is held and
+ *		subsequently whether VM_FAULT_RETRY functionality can be
+ *		utilised. Lock must initially be held.
  *
  * Returns number of pages pinned. This may be fewer than the number
  * requested. If nr_pages is 0 or negative, returns 0. If no pages
@@ -960,10 +963,10 @@ EXPORT_SYMBOL(get_user_pages_unlocked);
 long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
 		unsigned long start, unsigned long nr_pages,
 		unsigned int gup_flags, struct page **pages,
-		struct vm_area_struct **vmas)
+		struct vm_area_struct **vmas, int *locked)
 {
 	return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
-				       NULL, false,
+				       locked, true,
 				       gup_flags | FOLL_TOUCH | FOLL_REMOTE);
 }
 EXPORT_SYMBOL(get_user_pages_remote);
@@ -971,8 +974,9 @@ EXPORT_SYMBOL(get_user_pages_remote);
 /*
  * This is the same as get_user_pages_remote(), just with a
  * less-flexible calling convention where we assume that the task
- * and mm being operated on are the current task's.  We also
- * obviously don't pass FOLL_REMOTE in here.
+ * and mm being operated on are the current task's and don't allow
+ * passing of a locked parameter.  We also obviously don't pass
+ * FOLL_REMOTE in here.
  */
 long get_user_pages(unsigned long start, unsigned long nr_pages,
 		unsigned int gup_flags, struct page **pages,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e96c670fe8b7..0957e654b3c9 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -532,13 +532,13 @@ unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
 }
 EXPORT_SYMBOL_GPL(thp_get_unmapped_area);
 
-static int __do_huge_pmd_anonymous_page(struct fault_env *fe, struct page *page,
+static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
 		gfp_t gfp)
 {
-	struct vm_area_struct *vma = fe->vma;
+	struct vm_area_struct *vma = vmf->vma;
 	struct mem_cgroup *memcg;
 	pgtable_t pgtable;
-	unsigned long haddr = fe->address & HPAGE_PMD_MASK;
+	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
 
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 
@@ -563,9 +563,9 @@ static int __do_huge_pmd_anonymous_page(struct fault_env *fe, struct page *page,
 	 */
 	__SetPageUptodate(page);
 
-	fe->ptl = pmd_lock(vma->vm_mm, fe->pmd);
-	if (unlikely(!pmd_none(*fe->pmd))) {
-		spin_unlock(fe->ptl);
+	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
+	if (unlikely(!pmd_none(*vmf->pmd))) {
+		spin_unlock(vmf->ptl);
 		mem_cgroup_cancel_charge(page, memcg, true);
 		put_page(page);
 		pte_free(vma->vm_mm, pgtable);
@@ -576,11 +576,11 @@ static int __do_huge_pmd_anonymous_page(struct fault_env *fe, struct page *page,
 		if (userfaultfd_missing(vma)) {
 			int ret;
 
-			spin_unlock(fe->ptl);
+			spin_unlock(vmf->ptl);
 			mem_cgroup_cancel_charge(page, memcg, true);
 			put_page(page);
 			pte_free(vma->vm_mm, pgtable);
-			ret = handle_userfault(fe, VM_UFFD_MISSING);
+			ret = handle_userfault(vmf, VM_UFFD_MISSING);
 			VM_BUG_ON(ret & VM_FAULT_FALLBACK);
 			return ret;
 		}
@@ -590,11 +590,11 @@ static int __do_huge_pmd_anonymous_page(struct fault_env *fe, struct page *page,
 		page_add_new_anon_rmap(page, vma, haddr, true);
 		mem_cgroup_commit_charge(page, memcg, false, true);
 		lru_cache_add_active_or_unevictable(page, vma);
-		pgtable_trans_huge_deposit(vma->vm_mm, fe->pmd, pgtable);
-		set_pmd_at(vma->vm_mm, haddr, fe->pmd, entry);
+		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
+		set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
 		add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
 		atomic_long_inc(&vma->vm_mm->nr_ptes);
-		spin_unlock(fe->ptl);
+		spin_unlock(vmf->ptl);
 		count_vm_event(THP_FAULT_ALLOC);
 	}
 
@@ -641,12 +641,12 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
 	return true;
 }
 
-int do_huge_pmd_anonymous_page(struct fault_env *fe)
+int do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = fe->vma;
+	struct vm_area_struct *vma = vmf->vma;
 	gfp_t gfp;
 	struct page *page;
-	unsigned long haddr = fe->address & HPAGE_PMD_MASK;
+	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
 
 	if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)
 		return VM_FAULT_FALLBACK;
@@ -654,7 +654,7 @@ int do_huge_pmd_anonymous_page(struct fault_env *fe)
 		return VM_FAULT_OOM;
 	if (unlikely(khugepaged_enter(vma, vma->vm_flags)))
 		return VM_FAULT_OOM;
-	if (!(fe->flags & FAULT_FLAG_WRITE) &&
+	if (!(vmf->flags & FAULT_FLAG_WRITE) &&
 			!mm_forbids_zeropage(vma->vm_mm) &&
 			transparent_hugepage_use_zero_page()) {
 		pgtable_t pgtable;
@@ -670,22 +670,22 @@ int do_huge_pmd_anonymous_page(struct fault_env *fe)
 			count_vm_event(THP_FAULT_FALLBACK);
 			return VM_FAULT_FALLBACK;
 		}
-		fe->ptl = pmd_lock(vma->vm_mm, fe->pmd);
+		vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
 		ret = 0;
 		set = false;
-		if (pmd_none(*fe->pmd)) {
+		if (pmd_none(*vmf->pmd)) {
 			if (userfaultfd_missing(vma)) {
-				spin_unlock(fe->ptl);
-				ret = handle_userfault(fe, VM_UFFD_MISSING);
+				spin_unlock(vmf->ptl);
+				ret = handle_userfault(vmf, VM_UFFD_MISSING);
 				VM_BUG_ON(ret & VM_FAULT_FALLBACK);
 			} else {
 				set_huge_zero_page(pgtable, vma->vm_mm, vma,
-						   haddr, fe->pmd, zero_page);
-				spin_unlock(fe->ptl);
+						   haddr, vmf->pmd, zero_page);
+				spin_unlock(vmf->ptl);
 				set = true;
 			}
 		} else
-			spin_unlock(fe->ptl);
+			spin_unlock(vmf->ptl);
 		if (!set)
 			pte_free(vma->vm_mm, pgtable);
 		return ret;
@@ -697,7 +697,7 @@ int do_huge_pmd_anonymous_page(struct fault_env *fe)
 		return VM_FAULT_FALLBACK;
 	}
 	prep_transhuge_page(page);
-	return __do_huge_pmd_anonymous_page(fe, page, gfp);
+	return __do_huge_pmd_anonymous_page(vmf, page, gfp);
 }
 
 static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
@@ -869,30 +869,30 @@ out:
 	return ret;
 }
 
-void huge_pmd_set_accessed(struct fault_env *fe, pmd_t orig_pmd)
+void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd)
 {
 	pmd_t entry;
 	unsigned long haddr;
 
-	fe->ptl = pmd_lock(fe->vma->vm_mm, fe->pmd);
-	if (unlikely(!pmd_same(*fe->pmd, orig_pmd)))
+	vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
+	if (unlikely(!pmd_same(*vmf->pmd, orig_pmd)))
 		goto unlock;
 
 	entry = pmd_mkyoung(orig_pmd);
-	haddr = fe->address & HPAGE_PMD_MASK;
-	if (pmdp_set_access_flags(fe->vma, haddr, fe->pmd, entry,
-				fe->flags & FAULT_FLAG_WRITE))
-		update_mmu_cache_pmd(fe->vma, fe->address, fe->pmd);
+	haddr = vmf->address & HPAGE_PMD_MASK;
+	if (pmdp_set_access_flags(vmf->vma, haddr, vmf->pmd, entry,
+				vmf->flags & FAULT_FLAG_WRITE))
+		update_mmu_cache_pmd(vmf->vma, vmf->address, vmf->pmd);
 
 unlock:
-	spin_unlock(fe->ptl);
+	spin_unlock(vmf->ptl);
 }
 
-static int do_huge_pmd_wp_page_fallback(struct fault_env *fe, pmd_t orig_pmd,
+static int do_huge_pmd_wp_page_fallback(struct vm_fault *vmf, pmd_t orig_pmd,
 		struct page *page)
 {
-	struct vm_area_struct *vma = fe->vma;
-	unsigned long haddr = fe->address & HPAGE_PMD_MASK;
+	struct vm_area_struct *vma = vmf->vma;
+	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
 	struct mem_cgroup *memcg;
 	pgtable_t pgtable;
 	pmd_t _pmd;
@@ -911,7 +911,7 @@ static int do_huge_pmd_wp_page_fallback(struct fault_env *fe, pmd_t orig_pmd,
 	for (i = 0; i < HPAGE_PMD_NR; i++) {
 		pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE |
 					       __GFP_OTHER_NODE, vma,
-					       fe->address, page_to_nid(page));
+					       vmf->address, page_to_nid(page));
 		if (unlikely(!pages[i] ||
 			     mem_cgroup_try_charge(pages[i], vma->vm_mm,
 				     GFP_KERNEL, &memcg, false))) {
@@ -942,15 +942,15 @@ static int do_huge_pmd_wp_page_fallback(struct fault_env *fe, pmd_t orig_pmd,
 	mmun_end   = haddr + HPAGE_PMD_SIZE;
 	mmu_notifier_invalidate_range_start(vma->vm_mm, mmun_start, mmun_end);
 
-	fe->ptl = pmd_lock(vma->vm_mm, fe->pmd);
-	if (unlikely(!pmd_same(*fe->pmd, orig_pmd)))
+	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
+	if (unlikely(!pmd_same(*vmf->pmd, orig_pmd)))
 		goto out_free_pages;
 	VM_BUG_ON_PAGE(!PageHead(page), page);
 
-	pmdp_huge_clear_flush_notify(vma, haddr, fe->pmd);
+	pmdp_huge_clear_flush_notify(vma, haddr, vmf->pmd);
 	/* leave pmd empty until pte is filled */
 
-	pgtable = pgtable_trans_huge_withdraw(vma->vm_mm, fe->pmd);
+	pgtable = pgtable_trans_huge_withdraw(vma->vm_mm, vmf->pmd);
 	pmd_populate(vma->vm_mm, &_pmd, pgtable);
 
 	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
@@ -959,20 +959,20 @@ static int do_huge_pmd_wp_page_fallback(struct fault_env *fe, pmd_t orig_pmd,
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 		memcg = (void *)page_private(pages[i]);
 		set_page_private(pages[i], 0);
-		page_add_new_anon_rmap(pages[i], fe->vma, haddr, false);
+		page_add_new_anon_rmap(pages[i], vmf->vma, haddr, false);
 		mem_cgroup_commit_charge(pages[i], memcg, false, false);
 		lru_cache_add_active_or_unevictable(pages[i], vma);
-		fe->pte = pte_offset_map(&_pmd, haddr);
-		VM_BUG_ON(!pte_none(*fe->pte));
-		set_pte_at(vma->vm_mm, haddr, fe->pte, entry);
-		pte_unmap(fe->pte);
+		vmf->pte = pte_offset_map(&_pmd, haddr);
+		VM_BUG_ON(!pte_none(*vmf->pte));
+		set_pte_at(vma->vm_mm, haddr, vmf->pte, entry);
+		pte_unmap(vmf->pte);
 	}
 	kfree(pages);
 
 	smp_wmb(); /* make pte visible before pmd */
-	pmd_populate(vma->vm_mm, fe->pmd, pgtable);
+	pmd_populate(vma->vm_mm, vmf->pmd, pgtable);
 	page_remove_rmap(page, true);
-	spin_unlock(fe->ptl);
+	spin_unlock(vmf->ptl);
 
 	mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end);
 
@@ -983,7 +983,7 @@ out:
 	return ret;
 
 out_free_pages:
-	spin_unlock(fe->ptl);
+	spin_unlock(vmf->ptl);
 	mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end);
 	for (i = 0; i < HPAGE_PMD_NR; i++) {
 		memcg = (void *)page_private(pages[i]);
@@ -995,23 +995,23 @@ out_free_pages:
 	goto out;
 }
 
-int do_huge_pmd_wp_page(struct fault_env *fe, pmd_t orig_pmd)
+int do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
 {
-	struct vm_area_struct *vma = fe->vma;
+	struct vm_area_struct *vma = vmf->vma;
 	struct page *page = NULL, *new_page;
 	struct mem_cgroup *memcg;
-	unsigned long haddr = fe->address & HPAGE_PMD_MASK;
+	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
 	unsigned long mmun_start;	/* For mmu_notifiers */
 	unsigned long mmun_end;		/* For mmu_notifiers */
 	gfp_t huge_gfp;			/* for allocation and charge */
 	int ret = 0;
 
-	fe->ptl = pmd_lockptr(vma->vm_mm, fe->pmd);
+	vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd);
 	VM_BUG_ON_VMA(!vma->anon_vma, vma);
 	if (is_huge_zero_pmd(orig_pmd))
 		goto alloc;
-	spin_lock(fe->ptl);
-	if (unlikely(!pmd_same(*fe->pmd, orig_pmd)))
+	spin_lock(vmf->ptl);
+	if (unlikely(!pmd_same(*vmf->pmd, orig_pmd)))
 		goto out_unlock;
 
 	page = pmd_page(orig_pmd);
@@ -1024,13 +1024,13 @@ int do_huge_pmd_wp_page(struct fault_env *fe, pmd_t orig_pmd)
 		pmd_t entry;
 		entry = pmd_mkyoung(orig_pmd);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
-		if (pmdp_set_access_flags(vma, haddr, fe->pmd, entry,  1))
-			update_mmu_cache_pmd(vma, fe->address, fe->pmd);
+		if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry,  1))
+			update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
 		ret |= VM_FAULT_WRITE;
 		goto out_unlock;
 	}
 	get_page(page);
-	spin_unlock(fe->ptl);
+	spin_unlock(vmf->ptl);
 alloc:
 	if (transparent_hugepage_enabled(vma) &&
 	    !transparent_hugepage_debug_cow()) {
@@ -1043,12 +1043,12 @@ alloc:
 		prep_transhuge_page(new_page);
 	} else {
 		if (!page) {
-			split_huge_pmd(vma, fe->pmd, fe->address);
+			split_huge_pmd(vma, vmf->pmd, vmf->address);
 			ret |= VM_FAULT_FALLBACK;
 		} else {
-			ret = do_huge_pmd_wp_page_fallback(fe, orig_pmd, page);
+			ret = do_huge_pmd_wp_page_fallback(vmf, orig_pmd, page);
 			if (ret & VM_FAULT_OOM) {
-				split_huge_pmd(vma, fe->pmd, fe->address);
+				split_huge_pmd(vma, vmf->pmd, vmf->address);
 				ret |= VM_FAULT_FALLBACK;
 			}
 			put_page(page);
@@ -1060,7 +1060,7 @@ alloc:
 	if (unlikely(mem_cgroup_try_charge(new_page, vma->vm_mm,
 					huge_gfp, &memcg, true))) {
 		put_page(new_page);
-		split_huge_pmd(vma, fe->pmd, fe->address);
+		split_huge_pmd(vma, vmf->pmd, vmf->address);
 		if (page)
 			put_page(page);
 		ret |= VM_FAULT_FALLBACK;
@@ -1080,11 +1080,11 @@ alloc:
 	mmun_end   = haddr + HPAGE_PMD_SIZE;
 	mmu_notifier_invalidate_range_start(vma->vm_mm, mmun_start, mmun_end);
 
-	spin_lock(fe->ptl);
+	spin_lock(vmf->ptl);
 	if (page)
 		put_page(page);
-	if (unlikely(!pmd_same(*fe->pmd, orig_pmd))) {
-		spin_unlock(fe->ptl);
+	if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) {
+		spin_unlock(vmf->ptl);
 		mem_cgroup_cancel_charge(new_page, memcg, true);
 		put_page(new_page);
 		goto out_mn;
@@ -1092,12 +1092,12 @@ alloc:
 		pmd_t entry;
 		entry = mk_huge_pmd(new_page, vma->vm_page_prot);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
-		pmdp_huge_clear_flush_notify(vma, haddr, fe->pmd);
+		pmdp_huge_clear_flush_notify(vma, haddr, vmf->pmd);
 		page_add_new_anon_rmap(new_page, vma, haddr, true);
 		mem_cgroup_commit_charge(new_page, memcg, false, true);
 		lru_cache_add_active_or_unevictable(new_page, vma);
-		set_pmd_at(vma->vm_mm, haddr, fe->pmd, entry);
-		update_mmu_cache_pmd(vma, fe->address, fe->pmd);
+		set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
+		update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
 		if (!page) {
 			add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
 		} else {
@@ -1107,13 +1107,13 @@ alloc:
 		}
 		ret |= VM_FAULT_WRITE;
 	}
-	spin_unlock(fe->ptl);
+	spin_unlock(vmf->ptl);
 out_mn:
 	mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end);
 out:
 	return ret;
 out_unlock:
-	spin_unlock(fe->ptl);
+	spin_unlock(vmf->ptl);
 	return ret;
 }
 
@@ -1186,12 +1186,12 @@ out:
 }
 
 /* NUMA hinting page fault entry point for trans huge pmds */
-int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t pmd)
+int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
 {
-	struct vm_area_struct *vma = fe->vma;
+	struct vm_area_struct *vma = vmf->vma;
 	struct anon_vma *anon_vma = NULL;
 	struct page *page;
-	unsigned long haddr = fe->address & HPAGE_PMD_MASK;
+	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
 	int page_nid = -1, this_nid = numa_node_id();
 	int target_nid, last_cpupid = -1;
 	bool page_locked;
@@ -1199,8 +1199,8 @@ int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t pmd)
 	bool was_writable;
 	int flags = 0;
 
-	fe->ptl = pmd_lock(vma->vm_mm, fe->pmd);
-	if (unlikely(!pmd_same(pmd, *fe->pmd)))
+	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
+	if (unlikely(!pmd_same(pmd, *vmf->pmd)))
 		goto out_unlock;
 
 	/*
@@ -1208,9 +1208,9 @@ int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t pmd)
 	 * without disrupting NUMA hinting information. Do not relock and
 	 * check_same as the page may no longer be mapped.
 	 */
-	if (unlikely(pmd_trans_migrating(*fe->pmd))) {
-		page = pmd_page(*fe->pmd);
-		spin_unlock(fe->ptl);
+	if (unlikely(pmd_trans_migrating(*vmf->pmd))) {
+		page = pmd_page(*vmf->pmd);
+		spin_unlock(vmf->ptl);
 		wait_on_page_locked(page);
 		goto out;
 	}
@@ -1243,7 +1243,7 @@ int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t pmd)
 
 	/* Migration could have started since the pmd_trans_migrating check */
 	if (!page_locked) {
-		spin_unlock(fe->ptl);
+		spin_unlock(vmf->ptl);
 		wait_on_page_locked(page);
 		page_nid = -1;
 		goto out;
@@ -1254,12 +1254,12 @@ int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t pmd)
 	 * to serialises splits
 	 */
 	get_page(page);
-	spin_unlock(fe->ptl);
+	spin_unlock(vmf->ptl);
 	anon_vma = page_lock_anon_vma_read(page);
 
 	/* Confirm the PMD did not change while page_table_lock was released */
-	spin_lock(fe->ptl);
-	if (unlikely(!pmd_same(pmd, *fe->pmd))) {
+	spin_lock(vmf->ptl);
+	if (unlikely(!pmd_same(pmd, *vmf->pmd))) {
 		unlock_page(page);
 		put_page(page);
 		page_nid = -1;
@@ -1277,9 +1277,9 @@ int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t pmd)
 	 * Migrate the THP to the requested node, returns with page unlocked
 	 * and access rights restored.
 	 */
-	spin_unlock(fe->ptl);
+	spin_unlock(vmf->ptl);
 	migrated = migrate_misplaced_transhuge_page(vma->vm_mm, vma,
-				fe->pmd, pmd, fe->address, page, target_nid);
+				vmf->pmd, pmd, vmf->address, page, target_nid);
 	if (migrated) {
 		flags |= TNF_MIGRATED;
 		page_nid = target_nid;
@@ -1294,18 +1294,19 @@ clear_pmdnuma:
 	pmd = pmd_mkyoung(pmd);
 	if (was_writable)
 		pmd = pmd_mkwrite(pmd);
-	set_pmd_at(vma->vm_mm, haddr, fe->pmd, pmd);
-	update_mmu_cache_pmd(vma, fe->address, fe->pmd);
+	set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd);
+	update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
 	unlock_page(page);
 out_unlock:
-	spin_unlock(fe->ptl);
+	spin_unlock(vmf->ptl);
 
 out:
 	if (anon_vma)
 		page_unlock_anon_vma_read(anon_vma);
 
 	if (page_nid != -1)
-		task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, fe->flags);
+		task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR,
+				vmf->flags);
 
 	return 0;
 }
diff --git a/mm/internal.h b/mm/internal.h
index 537ac9951f5f..44d68895a9b9 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -36,7 +36,7 @@
 /* Do not use these with a slab allocator */
 #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK)
 
-int do_swap_page(struct fault_env *fe, pte_t orig_pte);
+int do_swap_page(struct vm_fault *vmf);
 
 void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
 		unsigned long floor, unsigned long ceiling);
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 09460955e818..7434a63cac94 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -875,13 +875,13 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 					unsigned long address, pmd_t *pmd,
 					int referenced)
 {
-	pte_t pteval;
 	int swapped_in = 0, ret = 0;
-	struct fault_env fe = {
+	struct vm_fault vmf = {
 		.vma = vma,
 		.address = address,
 		.flags = FAULT_FLAG_ALLOW_RETRY,
 		.pmd = pmd,
+		.pgoff = linear_page_index(vma, address),
 	};
 
 	/* we only decide to swapin, if there is enough young ptes */
@@ -889,19 +889,19 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 		trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
 		return false;
 	}
-	fe.pte = pte_offset_map(pmd, address);
-	for (; fe.address < address + HPAGE_PMD_NR*PAGE_SIZE;
-			fe.pte++, fe.address += PAGE_SIZE) {
-		pteval = *fe.pte;
-		if (!is_swap_pte(pteval))
+	vmf.pte = pte_offset_map(pmd, address);
+	for (; vmf.address < address + HPAGE_PMD_NR*PAGE_SIZE;
+			vmf.pte++, vmf.address += PAGE_SIZE) {
+		vmf.orig_pte = *vmf.pte;
+		if (!is_swap_pte(vmf.orig_pte))
 			continue;
 		swapped_in++;
-		ret = do_swap_page(&fe, pteval);
+		ret = do_swap_page(&vmf);
 
 		/* do_swap_page returns VM_FAULT_RETRY with released mmap_sem */
 		if (ret & VM_FAULT_RETRY) {
 			down_read(&mm->mmap_sem);
-			if (hugepage_vma_revalidate(mm, address, &fe.vma)) {
+			if (hugepage_vma_revalidate(mm, address, &vmf.vma)) {
 				/* vma is no longer available, don't continue to swapin */
 				trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
 				return false;
@@ -915,10 +915,10 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 			return false;
 		}
 		/* pte is unmapped now, we need to map it */
-		fe.pte = pte_offset_map(pmd, fe.address);
+		vmf.pte = pte_offset_map(pmd, vmf.address);
 	}
-	fe.pte--;
-	pte_unmap(fe.pte);
+	vmf.pte--;
+	pte_unmap(vmf.pte);
 	trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 1);
 	return true;
 }
diff --git a/mm/memory.c b/mm/memory.c
index 08d8da39de28..455c3e628d52 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2034,20 +2034,17 @@ static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma)
  *
  * We do this without the lock held, so that it can sleep if it needs to.
  */
-static int do_page_mkwrite(struct vm_area_struct *vma, struct page *page,
-	       unsigned long address)
+static int do_page_mkwrite(struct vm_fault *vmf)
 {
-	struct vm_fault vmf;
 	int ret;
+	struct page *page = vmf->page;
+	unsigned int old_flags = vmf->flags;
 
-	vmf.virtual_address = (void __user *)(address & PAGE_MASK);
-	vmf.pgoff = page->index;
-	vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
-	vmf.gfp_mask = __get_fault_gfp_mask(vma);
-	vmf.page = page;
-	vmf.cow_page = NULL;
+	vmf->flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
 
-	ret = vma->vm_ops->page_mkwrite(vma, &vmf);
+	ret = vmf->vma->vm_ops->page_mkwrite(vmf->vma, vmf);
+	/* Restore original flags so that caller is not surprised */
+	vmf->flags = old_flags;
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
 		return ret;
 	if (unlikely(!(ret & VM_FAULT_LOCKED))) {
@@ -2063,6 +2060,41 @@ static int do_page_mkwrite(struct vm_area_struct *vma, struct page *page,
 }
 
 /*
+ * Handle dirtying of a page in shared file mapping on a write fault.
+ *
+ * The function expects the page to be locked and unlocks it.
+ */
+static void fault_dirty_shared_page(struct vm_area_struct *vma,
+				    struct page *page)
+{
+	struct address_space *mapping;
+	bool dirtied;
+	bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite;
+
+	dirtied = set_page_dirty(page);
+	VM_BUG_ON_PAGE(PageAnon(page), page);
+	/*
+	 * Take a local copy of the address_space - page.mapping may be zeroed
+	 * by truncate after unlock_page().   The address_space itself remains
+	 * pinned by vma->vm_file's reference.  We rely on unlock_page()'s
+	 * release semantics to prevent the compiler from undoing this copying.
+	 */
+	mapping = page_rmapping(page);
+	unlock_page(page);
+
+	if ((dirtied || page_mkwrite) && mapping) {
+		/*
+		 * Some device drivers do not set page.mapping
+		 * but still dirty their pages
+		 */
+		balance_dirty_pages_ratelimited(mapping);
+	}
+
+	if (!page_mkwrite)
+		file_update_time(vma->vm_file);
+}
+
+/*
  * Handle write page faults for pages that can be reused in the current vma
  *
  * This can happen either due to the mapping being with the VM_SHARED flag,
@@ -2070,11 +2102,11 @@ static int do_page_mkwrite(struct vm_area_struct *vma, struct page *page,
  * case, all we need to do here is to mark the page as writable and update
  * any related book-keeping.
  */
-static inline int wp_page_reuse(struct fault_env *fe, pte_t orig_pte,
-			struct page *page, int page_mkwrite, int dirty_shared)
-	__releases(fe->ptl)
+static inline void wp_page_reuse(struct vm_fault *vmf)
+	__releases(vmf->ptl)
 {
-	struct vm_area_struct *vma = fe->vma;
+	struct vm_area_struct *vma = vmf->vma;
+	struct page *page = vmf->page;
 	pte_t entry;
 	/*
 	 * Clear the pages cpupid information as the existing
@@ -2084,39 +2116,12 @@ static inline int wp_page_reuse(struct fault_env *fe, pte_t orig_pte,
 	if (page)
 		page_cpupid_xchg_last(page, (1 << LAST_CPUPID_SHIFT) - 1);
 
-	flush_cache_page(vma, fe->address, pte_pfn(orig_pte));
-	entry = pte_mkyoung(orig_pte);
+	flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
+	entry = pte_mkyoung(vmf->orig_pte);
 	entry = maybe_mkwrite(pte_mkdirty(entry), vma);
-	if (ptep_set_access_flags(vma, fe->address, fe->pte, entry, 1))
-		update_mmu_cache(vma, fe->address, fe->pte);
-	pte_unmap_unlock(fe->pte, fe->ptl);
-
-	if (dirty_shared) {
-		struct address_space *mapping;
-		int dirtied;
-
-		if (!page_mkwrite)
-			lock_page(page);
-
-		dirtied = set_page_dirty(page);
-		VM_BUG_ON_PAGE(PageAnon(page), page);
-		mapping = page->mapping;
-		unlock_page(page);
-		put_page(page);
-
-		if ((dirtied || page_mkwrite) && mapping) {
-			/*
-			 * Some device drivers do not set page.mapping
-			 * but still dirty their pages
-			 */
-			balance_dirty_pages_ratelimited(mapping);
-		}
-
-		if (!page_mkwrite)
-			file_update_time(vma->vm_file);
-	}
-
-	return VM_FAULT_WRITE;
+	if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1))
+		update_mmu_cache(vma, vmf->address, vmf->pte);
+	pte_unmap_unlock(vmf->pte, vmf->ptl);
 }
 
 /*
@@ -2135,31 +2140,32 @@ static inline int wp_page_reuse(struct fault_env *fe, pte_t orig_pte,
  *   held to the old page, as well as updating the rmap.
  * - In any case, unlock the PTL and drop the reference we took to the old page.
  */
-static int wp_page_copy(struct fault_env *fe, pte_t orig_pte,
-		struct page *old_page)
+static int wp_page_copy(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = fe->vma;
+	struct vm_area_struct *vma = vmf->vma;
 	struct mm_struct *mm = vma->vm_mm;
+	struct page *old_page = vmf->page;
 	struct page *new_page = NULL;
 	pte_t entry;
 	int page_copied = 0;
-	const unsigned long mmun_start = fe->address & PAGE_MASK;
+	const unsigned long mmun_start = vmf->address & PAGE_MASK;
 	const unsigned long mmun_end = mmun_start + PAGE_SIZE;
 	struct mem_cgroup *memcg;
 
 	if (unlikely(anon_vma_prepare(vma)))
 		goto oom;
 
-	if (is_zero_pfn(pte_pfn(orig_pte))) {
-		new_page = alloc_zeroed_user_highpage_movable(vma, fe->address);
+	if (is_zero_pfn(pte_pfn(vmf->orig_pte))) {
+		new_page = alloc_zeroed_user_highpage_movable(vma,
+							      vmf->address);
 		if (!new_page)
 			goto oom;
 	} else {
 		new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma,
-				fe->address);
+				vmf->address);
 		if (!new_page)
 			goto oom;
-		cow_user_page(new_page, old_page, fe->address, vma);
+		cow_user_page(new_page, old_page, vmf->address, vma);
 	}
 
 	if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false))
@@ -2172,8 +2178,8 @@ static int wp_page_copy(struct fault_env *fe, pte_t orig_pte,
 	/*
 	 * Re-check the pte - we dropped the lock
 	 */
-	fe->pte = pte_offset_map_lock(mm, fe->pmd, fe->address, &fe->ptl);
-	if (likely(pte_same(*fe->pte, orig_pte))) {
+	vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl);
+	if (likely(pte_same(*vmf->pte, vmf->orig_pte))) {
 		if (old_page) {
 			if (!PageAnon(old_page)) {
 				dec_mm_counter_fast(mm,
@@ -2183,7 +2189,7 @@ static int wp_page_copy(struct fault_env *fe, pte_t orig_pte,
 		} else {
 			inc_mm_counter_fast(mm, MM_ANONPAGES);
 		}
-		flush_cache_page(vma, fe->address, pte_pfn(orig_pte));
+		flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
 		entry = mk_pte(new_page, vma->vm_page_prot);
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 		/*
@@ -2192,8 +2198,8 @@ static int wp_page_copy(struct fault_env *fe, pte_t orig_pte,
 		 * seen in the presence of one thread doing SMC and another
 		 * thread doing COW.
 		 */
-		ptep_clear_flush_notify(vma, fe->address, fe->pte);
-		page_add_new_anon_rmap(new_page, vma, fe->address, false);
+		ptep_clear_flush_notify(vma, vmf->address, vmf->pte);
+		page_add_new_anon_rmap(new_page, vma, vmf->address, false);
 		mem_cgroup_commit_charge(new_page, memcg, false, false);
 		lru_cache_add_active_or_unevictable(new_page, vma);
 		/*
@@ -2201,8 +2207,8 @@ static int wp_page_copy(struct fault_env *fe, pte_t orig_pte,
 		 * mmu page tables (such as kvm shadow page tables), we want the
 		 * new page to be mapped directly into the secondary page table.
 		 */
-		set_pte_at_notify(mm, fe->address, fe->pte, entry);
-		update_mmu_cache(vma, fe->address, fe->pte);
+		set_pte_at_notify(mm, vmf->address, vmf->pte, entry);
+		update_mmu_cache(vma, vmf->address, vmf->pte);
 		if (old_page) {
 			/*
 			 * Only after switching the pte to the new page may
@@ -2239,7 +2245,7 @@ static int wp_page_copy(struct fault_env *fe, pte_t orig_pte,
 	if (new_page)
 		put_page(new_page);
 
-	pte_unmap_unlock(fe->pte, fe->ptl);
+	pte_unmap_unlock(vmf->pte, vmf->ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	if (old_page) {
 		/*
@@ -2263,79 +2269,91 @@ oom:
 	return VM_FAULT_OOM;
 }
 
+/**
+ * finish_mkwrite_fault - finish page fault for a shared mapping, making PTE
+ *			  writeable once the page is prepared
+ *
+ * @vmf: structure describing the fault
+ *
+ * This function handles all that is needed to finish a write page fault in a
+ * shared mapping due to PTE being read-only once the mapped page is prepared.
+ * It handles locking of PTE and modifying it. The function returns
+ * VM_FAULT_WRITE on success, 0 when PTE got changed before we acquired PTE
+ * lock.
+ *
+ * The function expects the page to be locked or other protection against
+ * concurrent faults / writeback (such as DAX radix tree locks).
+ */
+int finish_mkwrite_fault(struct vm_fault *vmf)
+{
+	WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED));
+	vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address,
+				       &vmf->ptl);
+	/*
+	 * We might have raced with another page fault while we released the
+	 * pte_offset_map_lock.
+	 */
+	if (!pte_same(*vmf->pte, vmf->orig_pte)) {
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
+		return VM_FAULT_NOPAGE;
+	}
+	wp_page_reuse(vmf);
+	return 0;
+}
+
 /*
  * Handle write page faults for VM_MIXEDMAP or VM_PFNMAP for a VM_SHARED
  * mapping
  */
-static int wp_pfn_shared(struct fault_env *fe,  pte_t orig_pte)
+static int wp_pfn_shared(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = fe->vma;
+	struct vm_area_struct *vma = vmf->vma;
 
 	if (vma->vm_ops && vma->vm_ops->pfn_mkwrite) {
-		struct vm_fault vmf = {
-			.page = NULL,
-			.pgoff = linear_page_index(vma, fe->address),
-			.virtual_address =
-				(void __user *)(fe->address & PAGE_MASK),
-			.flags = FAULT_FLAG_WRITE | FAULT_FLAG_MKWRITE,
-		};
 		int ret;
 
-		pte_unmap_unlock(fe->pte, fe->ptl);
-		ret = vma->vm_ops->pfn_mkwrite(vma, &vmf);
-		if (ret & VM_FAULT_ERROR)
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
+		vmf->flags |= FAULT_FLAG_MKWRITE;
+		ret = vma->vm_ops->pfn_mkwrite(vma, vmf);
+		if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))
 			return ret;
-		fe->pte = pte_offset_map_lock(vma->vm_mm, fe->pmd, fe->address,
-				&fe->ptl);
-		/*
-		 * We might have raced with another page fault while we
-		 * released the pte_offset_map_lock.
-		 */
-		if (!pte_same(*fe->pte, orig_pte)) {
-			pte_unmap_unlock(fe->pte, fe->ptl);
-			return 0;
-		}
+		return finish_mkwrite_fault(vmf);
 	}
-	return wp_page_reuse(fe, orig_pte, NULL, 0, 0);
+	wp_page_reuse(vmf);
+	return VM_FAULT_WRITE;
 }
 
-static int wp_page_shared(struct fault_env *fe, pte_t orig_pte,
-		struct page *old_page)
-	__releases(fe->ptl)
+static int wp_page_shared(struct vm_fault *vmf)
+	__releases(vmf->ptl)
 {
-	struct vm_area_struct *vma = fe->vma;
-	int page_mkwrite = 0;
+	struct vm_area_struct *vma = vmf->vma;
 
-	get_page(old_page);
+	get_page(vmf->page);
 
 	if (vma->vm_ops && vma->vm_ops->page_mkwrite) {
 		int tmp;
 
-		pte_unmap_unlock(fe->pte, fe->ptl);
-		tmp = do_page_mkwrite(vma, old_page, fe->address);
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
+		tmp = do_page_mkwrite(vmf);
 		if (unlikely(!tmp || (tmp &
 				      (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) {
-			put_page(old_page);
+			put_page(vmf->page);
 			return tmp;
 		}
-		/*
-		 * Since we dropped the lock we need to revalidate
-		 * the PTE as someone else may have changed it.  If
-		 * they did, we just return, as we can count on the
-		 * MMU to tell us if they didn't also make it writable.
-		 */
-		fe->pte = pte_offset_map_lock(vma->vm_mm, fe->pmd, fe->address,
-						 &fe->ptl);
-		if (!pte_same(*fe->pte, orig_pte)) {
-			unlock_page(old_page);
-			pte_unmap_unlock(fe->pte, fe->ptl);
-			put_page(old_page);
-			return 0;
+		tmp = finish_mkwrite_fault(vmf);
+		if (unlikely(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) {
+			unlock_page(vmf->page);
+			put_page(vmf->page);
+			return tmp;
 		}
-		page_mkwrite = 1;
+	} else {
+		wp_page_reuse(vmf);
+		lock_page(vmf->page);
 	}
+	fault_dirty_shared_page(vma, vmf->page);
+	put_page(vmf->page);
 
-	return wp_page_reuse(fe, orig_pte, old_page, page_mkwrite, 1);
+	return VM_FAULT_WRITE;
 }
 
 /*
@@ -2356,14 +2374,13 @@ static int wp_page_shared(struct fault_env *fe, pte_t orig_pte,
  * but allow concurrent faults), with pte both mapped and locked.
  * We return with mmap_sem still held, but pte unmapped and unlocked.
  */
-static int do_wp_page(struct fault_env *fe, pte_t orig_pte)
-	__releases(fe->ptl)
+static int do_wp_page(struct vm_fault *vmf)
+	__releases(vmf->ptl)
 {
-	struct vm_area_struct *vma = fe->vma;
-	struct page *old_page;
+	struct vm_area_struct *vma = vmf->vma;
 
-	old_page = vm_normal_page(vma, fe->address, orig_pte);
-	if (!old_page) {
+	vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte);
+	if (!vmf->page) {
 		/*
 		 * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a
 		 * VM_PFNMAP VMA.
@@ -2373,33 +2390,33 @@ static int do_wp_page(struct fault_env *fe, pte_t orig_pte)
 		 */
 		if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
 				     (VM_WRITE|VM_SHARED))
-			return wp_pfn_shared(fe, orig_pte);
+			return wp_pfn_shared(vmf);
 
-		pte_unmap_unlock(fe->pte, fe->ptl);
-		return wp_page_copy(fe, orig_pte, old_page);
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
+		return wp_page_copy(vmf);
 	}
 
 	/*
 	 * Take out anonymous pages first, anonymous shared vmas are
 	 * not dirty accountable.
 	 */
-	if (PageAnon(old_page) && !PageKsm(old_page)) {
+	if (PageAnon(vmf->page) && !PageKsm(vmf->page)) {
 		int total_mapcount;
-		if (!trylock_page(old_page)) {
-			get_page(old_page);
-			pte_unmap_unlock(fe->pte, fe->ptl);
-			lock_page(old_page);
-			fe->pte = pte_offset_map_lock(vma->vm_mm, fe->pmd,
-					fe->address, &fe->ptl);
-			if (!pte_same(*fe->pte, orig_pte)) {
-				unlock_page(old_page);
-				pte_unmap_unlock(fe->pte, fe->ptl);
-				put_page(old_page);
+		if (!trylock_page(vmf->page)) {
+			get_page(vmf->page);
+			pte_unmap_unlock(vmf->pte, vmf->ptl);
+			lock_page(vmf->page);
+			vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
+					vmf->address, &vmf->ptl);
+			if (!pte_same(*vmf->pte, vmf->orig_pte)) {
+				unlock_page(vmf->page);
+				pte_unmap_unlock(vmf->pte, vmf->ptl);
+				put_page(vmf->page);
 				return 0;
 			}
-			put_page(old_page);
+			put_page(vmf->page);
 		}
-		if (reuse_swap_page(old_page, &total_mapcount)) {
+		if (reuse_swap_page(vmf->page, &total_mapcount)) {
 			if (total_mapcount == 1) {
 				/*
 				 * The page is all ours. Move it to
@@ -2408,24 +2425,25 @@ static int do_wp_page(struct fault_env *fe, pte_t orig_pte)
 				 * Protected against the rmap code by
 				 * the page lock.
 				 */
-				page_move_anon_rmap(old_page, vma);
+				page_move_anon_rmap(vmf->page, vma);
 			}
-			unlock_page(old_page);
-			return wp_page_reuse(fe, orig_pte, old_page, 0, 0);
+			unlock_page(vmf->page);
+			wp_page_reuse(vmf);
+			return VM_FAULT_WRITE;
 		}
-		unlock_page(old_page);
+		unlock_page(vmf->page);
 	} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
 					(VM_WRITE|VM_SHARED))) {
-		return wp_page_shared(fe, orig_pte, old_page);
+		return wp_page_shared(vmf);
 	}
 
 	/*
 	 * Ok, we need to copy. Oh, well..
 	 */
-	get_page(old_page);
+	get_page(vmf->page);
 
-	pte_unmap_unlock(fe->pte, fe->ptl);
-	return wp_page_copy(fe, orig_pte, old_page);
+	pte_unmap_unlock(vmf->pte, vmf->ptl);
+	return wp_page_copy(vmf);
 }
 
 static void unmap_mapping_range_vma(struct vm_area_struct *vma,
@@ -2513,9 +2531,9 @@ EXPORT_SYMBOL(unmap_mapping_range);
  * We return with the mmap_sem locked or unlocked in the same cases
  * as does filemap_fault().
  */
-int do_swap_page(struct fault_env *fe, pte_t orig_pte)
+int do_swap_page(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = fe->vma;
+	struct vm_area_struct *vma = vmf->vma;
 	struct page *page, *swapcache;
 	struct mem_cgroup *memcg;
 	swp_entry_t entry;
@@ -2524,17 +2542,18 @@ int do_swap_page(struct fault_env *fe, pte_t orig_pte)
 	int exclusive = 0;
 	int ret = 0;
 
-	if (!pte_unmap_same(vma->vm_mm, fe->pmd, fe->pte, orig_pte))
+	if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte))
 		goto out;
 
-	entry = pte_to_swp_entry(orig_pte);
+	entry = pte_to_swp_entry(vmf->orig_pte);
 	if (unlikely(non_swap_entry(entry))) {
 		if (is_migration_entry(entry)) {
-			migration_entry_wait(vma->vm_mm, fe->pmd, fe->address);
+			migration_entry_wait(vma->vm_mm, vmf->pmd,
+					     vmf->address);
 		} else if (is_hwpoison_entry(entry)) {
 			ret = VM_FAULT_HWPOISON;
 		} else {
-			print_bad_pte(vma, fe->address, orig_pte, NULL);
+			print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL);
 			ret = VM_FAULT_SIGBUS;
 		}
 		goto out;
@@ -2542,16 +2561,16 @@ int do_swap_page(struct fault_env *fe, pte_t orig_pte)
 	delayacct_set_flag(DELAYACCT_PF_SWAPIN);
 	page = lookup_swap_cache(entry);
 	if (!page) {
-		page = swapin_readahead(entry,
-					GFP_HIGHUSER_MOVABLE, vma, fe->address);
+		page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, vma,
+					vmf->address);
 		if (!page) {
 			/*
 			 * Back out if somebody else faulted in this pte
 			 * while we released the pte lock.
 			 */
-			fe->pte = pte_offset_map_lock(vma->vm_mm, fe->pmd,
-					fe->address, &fe->ptl);
-			if (likely(pte_same(*fe->pte, orig_pte)))
+			vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
+					vmf->address, &vmf->ptl);
+			if (likely(pte_same(*vmf->pte, vmf->orig_pte)))
 				ret = VM_FAULT_OOM;
 			delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
 			goto unlock;
@@ -2573,7 +2592,7 @@ int do_swap_page(struct fault_env *fe, pte_t orig_pte)
 	}
 
 	swapcache = page;
-	locked = lock_page_or_retry(page, vma->vm_mm, fe->flags);
+	locked = lock_page_or_retry(page, vma->vm_mm, vmf->flags);
 
 	delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
 	if (!locked) {
@@ -2590,7 +2609,7 @@ int do_swap_page(struct fault_env *fe, pte_t orig_pte)
 	if (unlikely(!PageSwapCache(page) || page_private(page) != entry.val))
 		goto out_page;
 
-	page = ksm_might_need_to_copy(page, vma, fe->address);
+	page = ksm_might_need_to_copy(page, vma, vmf->address);
 	if (unlikely(!page)) {
 		ret = VM_FAULT_OOM;
 		page = swapcache;
@@ -2606,9 +2625,9 @@ int do_swap_page(struct fault_env *fe, pte_t orig_pte)
 	/*
 	 * Back out if somebody else already faulted in this pte.
 	 */
-	fe->pte = pte_offset_map_lock(vma->vm_mm, fe->pmd, fe->address,
-			&fe->ptl);
-	if (unlikely(!pte_same(*fe->pte, orig_pte)))
+	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
+			&vmf->ptl);
+	if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte)))
 		goto out_nomap;
 
 	if (unlikely(!PageUptodate(page))) {
@@ -2629,22 +2648,23 @@ int do_swap_page(struct fault_env *fe, pte_t orig_pte)
 	inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
 	dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS);
 	pte = mk_pte(page, vma->vm_page_prot);
-	if ((fe->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) {
+	if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) {
 		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
-		fe->flags &= ~FAULT_FLAG_WRITE;
+		vmf->flags &= ~FAULT_FLAG_WRITE;
 		ret |= VM_FAULT_WRITE;
 		exclusive = RMAP_EXCLUSIVE;
 	}
 	flush_icache_page(vma, page);
-	if (pte_swp_soft_dirty(orig_pte))
+	if (pte_swp_soft_dirty(vmf->orig_pte))
 		pte = pte_mksoft_dirty(pte);
-	set_pte_at(vma->vm_mm, fe->address, fe->pte, pte);
+	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
+	vmf->orig_pte = pte;
 	if (page == swapcache) {
-		do_page_add_anon_rmap(page, vma, fe->address, exclusive);
+		do_page_add_anon_rmap(page, vma, vmf->address, exclusive);
 		mem_cgroup_commit_charge(page, memcg, true, false);
 		activate_page(page);
 	} else { /* ksm created a completely new copy */
-		page_add_new_anon_rmap(page, vma, fe->address, false);
+		page_add_new_anon_rmap(page, vma, vmf->address, false);
 		mem_cgroup_commit_charge(page, memcg, false, false);
 		lru_cache_add_active_or_unevictable(page, vma);
 	}
@@ -2667,22 +2687,22 @@ int do_swap_page(struct fault_env *fe, pte_t orig_pte)
 		put_page(swapcache);
 	}
 
-	if (fe->flags & FAULT_FLAG_WRITE) {
-		ret |= do_wp_page(fe, pte);
+	if (vmf->flags & FAULT_FLAG_WRITE) {
+		ret |= do_wp_page(vmf);
 		if (ret & VM_FAULT_ERROR)
 			ret &= VM_FAULT_ERROR;
 		goto out;
 	}
 
 	/* No need to invalidate - it was non-present before */
-	update_mmu_cache(vma, fe->address, fe->pte);
+	update_mmu_cache(vma, vmf->address, vmf->pte);
 unlock:
-	pte_unmap_unlock(fe->pte, fe->ptl);
+	pte_unmap_unlock(vmf->pte, vmf->ptl);
 out:
 	return ret;
 out_nomap:
 	mem_cgroup_cancel_charge(page, memcg, false);
-	pte_unmap_unlock(fe->pte, fe->ptl);
+	pte_unmap_unlock(vmf->pte, vmf->ptl);
 out_page:
 	unlock_page(page);
 out_release:
@@ -2733,9 +2753,9 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo
  * but allow concurrent faults), and pte mapped but not yet locked.
  * We return with mmap_sem still held, but pte unmapped and unlocked.
  */
-static int do_anonymous_page(struct fault_env *fe)
+static int do_anonymous_page(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = fe->vma;
+	struct vm_area_struct *vma = vmf->vma;
 	struct mem_cgroup *memcg;
 	struct page *page;
 	pte_t entry;
@@ -2745,7 +2765,7 @@ static int do_anonymous_page(struct fault_env *fe)
 		return VM_FAULT_SIGBUS;
 
 	/* Check if we need to add a guard page to the stack */
-	if (check_stack_guard_page(vma, fe->address) < 0)
+	if (check_stack_guard_page(vma, vmf->address) < 0)
 		return VM_FAULT_SIGSEGV;
 
 	/*
@@ -2758,26 +2778,26 @@ static int do_anonymous_page(struct fault_env *fe)
 	 *
 	 * Here we only have down_read(mmap_sem).
 	 */
-	if (pte_alloc(vma->vm_mm, fe->pmd, fe->address))
+	if (pte_alloc(vma->vm_mm, vmf->pmd, vmf->address))
 		return VM_FAULT_OOM;
 
 	/* See the comment in pte_alloc_one_map() */
-	if (unlikely(pmd_trans_unstable(fe->pmd)))
+	if (unlikely(pmd_trans_unstable(vmf->pmd)))
 		return 0;
 
 	/* Use the zero-page for reads */
-	if (!(fe->flags & FAULT_FLAG_WRITE) &&
+	if (!(vmf->flags & FAULT_FLAG_WRITE) &&
 			!mm_forbids_zeropage(vma->vm_mm)) {
-		entry = pte_mkspecial(pfn_pte(my_zero_pfn(fe->address),
+		entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address),
 						vma->vm_page_prot));
-		fe->pte = pte_offset_map_lock(vma->vm_mm, fe->pmd, fe->address,
-				&fe->ptl);
-		if (!pte_none(*fe->pte))
+		vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
+				vmf->address, &vmf->ptl);
+		if (!pte_none(*vmf->pte))
 			goto unlock;
 		/* Deliver the page fault to userland, check inside PT lock */
 		if (userfaultfd_missing(vma)) {
-			pte_unmap_unlock(fe->pte, fe->ptl);
-			return handle_userfault(fe, VM_UFFD_MISSING);
+			pte_unmap_unlock(vmf->pte, vmf->ptl);
+			return handle_userfault(vmf, VM_UFFD_MISSING);
 		}
 		goto setpte;
 	}
@@ -2785,7 +2805,7 @@ static int do_anonymous_page(struct fault_env *fe)
 	/* Allocate our own private page. */
 	if (unlikely(anon_vma_prepare(vma)))
 		goto oom;
-	page = alloc_zeroed_user_highpage_movable(vma, fe->address);
+	page = alloc_zeroed_user_highpage_movable(vma, vmf->address);
 	if (!page)
 		goto oom;
 
@@ -2803,30 +2823,30 @@ static int do_anonymous_page(struct fault_env *fe)
 	if (vma->vm_flags & VM_WRITE)
 		entry = pte_mkwrite(pte_mkdirty(entry));
 
-	fe->pte = pte_offset_map_lock(vma->vm_mm, fe->pmd, fe->address,
-			&fe->ptl);
-	if (!pte_none(*fe->pte))
+	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
+			&vmf->ptl);
+	if (!pte_none(*vmf->pte))
 		goto release;
 
 	/* Deliver the page fault to userland, check inside PT lock */
 	if (userfaultfd_missing(vma)) {
-		pte_unmap_unlock(fe->pte, fe->ptl);
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
 		mem_cgroup_cancel_charge(page, memcg, false);
 		put_page(page);
-		return handle_userfault(fe, VM_UFFD_MISSING);
+		return handle_userfault(vmf, VM_UFFD_MISSING);
 	}
 
 	inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
-	page_add_new_anon_rmap(page, vma, fe->address, false);
+	page_add_new_anon_rmap(page, vma, vmf->address, false);
 	mem_cgroup_commit_charge(page, memcg, false, false);
 	lru_cache_add_active_or_unevictable(page, vma);
 setpte:
-	set_pte_at(vma->vm_mm, fe->address, fe->pte, entry);
+	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry);
 
 	/* No need to invalidate - it was non-present before */
-	update_mmu_cache(vma, fe->address, fe->pte);
+	update_mmu_cache(vma, vmf->address, vmf->pte);
 unlock:
-	pte_unmap_unlock(fe->pte, fe->ptl);
+	pte_unmap_unlock(vmf->pte, vmf->ptl);
 	return 0;
 release:
 	mem_cgroup_cancel_charge(page, memcg, false);
@@ -2843,62 +2863,50 @@ oom:
  * released depending on flags and vma->vm_ops->fault() return value.
  * See filemap_fault() and __lock_page_retry().
  */
-static int __do_fault(struct fault_env *fe, pgoff_t pgoff,
-		struct page *cow_page, struct page **page, void **entry)
+static int __do_fault(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = fe->vma;
-	struct vm_fault vmf;
+	struct vm_area_struct *vma = vmf->vma;
 	int ret;
 
-	vmf.virtual_address = (void __user *)(fe->address & PAGE_MASK);
-	vmf.pgoff = pgoff;
-	vmf.flags = fe->flags;
-	vmf.page = NULL;
-	vmf.gfp_mask = __get_fault_gfp_mask(vma);
-	vmf.cow_page = cow_page;
-
-	ret = vma->vm_ops->fault(vma, &vmf);
-	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
-		return ret;
-	if (ret & VM_FAULT_DAX_LOCKED) {
-		*entry = vmf.entry;
+	ret = vma->vm_ops->fault(vma, vmf);
+	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY |
+			    VM_FAULT_DONE_COW)))
 		return ret;
-	}
 
-	if (unlikely(PageHWPoison(vmf.page))) {
+	if (unlikely(PageHWPoison(vmf->page))) {
 		if (ret & VM_FAULT_LOCKED)
-			unlock_page(vmf.page);
-		put_page(vmf.page);
+			unlock_page(vmf->page);
+		put_page(vmf->page);
+		vmf->page = NULL;
 		return VM_FAULT_HWPOISON;
 	}
 
 	if (unlikely(!(ret & VM_FAULT_LOCKED)))
-		lock_page(vmf.page);
+		lock_page(vmf->page);
 	else
-		VM_BUG_ON_PAGE(!PageLocked(vmf.page), vmf.page);
+		VM_BUG_ON_PAGE(!PageLocked(vmf->page), vmf->page);
 
-	*page = vmf.page;
 	return ret;
 }
 
-static int pte_alloc_one_map(struct fault_env *fe)
+static int pte_alloc_one_map(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = fe->vma;
+	struct vm_area_struct *vma = vmf->vma;
 
-	if (!pmd_none(*fe->pmd))
+	if (!pmd_none(*vmf->pmd))
 		goto map_pte;
-	if (fe->prealloc_pte) {
-		fe->ptl = pmd_lock(vma->vm_mm, fe->pmd);
-		if (unlikely(!pmd_none(*fe->pmd))) {
-			spin_unlock(fe->ptl);
+	if (vmf->prealloc_pte) {
+		vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
+		if (unlikely(!pmd_none(*vmf->pmd))) {
+			spin_unlock(vmf->ptl);
 			goto map_pte;
 		}
 
 		atomic_long_inc(&vma->vm_mm->nr_ptes);
-		pmd_populate(vma->vm_mm, fe->pmd, fe->prealloc_pte);
-		spin_unlock(fe->ptl);
-		fe->prealloc_pte = 0;
-	} else if (unlikely(pte_alloc(vma->vm_mm, fe->pmd, fe->address))) {
+		pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte);
+		spin_unlock(vmf->ptl);
+		vmf->prealloc_pte = 0;
+	} else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd, vmf->address))) {
 		return VM_FAULT_OOM;
 	}
 map_pte:
@@ -2913,11 +2921,11 @@ map_pte:
 	 * through an atomic read in C, which is what pmd_trans_unstable()
 	 * provides.
 	 */
-	if (pmd_trans_unstable(fe->pmd) || pmd_devmap(*fe->pmd))
+	if (pmd_trans_unstable(vmf->pmd) || pmd_devmap(*vmf->pmd))
 		return VM_FAULT_NOPAGE;
 
-	fe->pte = pte_offset_map_lock(vma->vm_mm, fe->pmd, fe->address,
-			&fe->ptl);
+	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
+			&vmf->ptl);
 	return 0;
 }
 
@@ -2935,24 +2943,24 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
 	return true;
 }
 
-static void deposit_prealloc_pte(struct fault_env *fe)
+static void deposit_prealloc_pte(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = fe->vma;
+	struct vm_area_struct *vma = vmf->vma;
 
-	pgtable_trans_huge_deposit(vma->vm_mm, fe->pmd, fe->prealloc_pte);
+	pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, vmf->prealloc_pte);
 	/*
 	 * We are going to consume the prealloc table,
 	 * count that as nr_ptes.
 	 */
 	atomic_long_inc(&vma->vm_mm->nr_ptes);
-	fe->prealloc_pte = 0;
+	vmf->prealloc_pte = 0;
 }
 
-static int do_set_pmd(struct fault_env *fe, struct page *page)
+static int do_set_pmd(struct vm_fault *vmf, struct page *page)
 {
-	struct vm_area_struct *vma = fe->vma;
-	bool write = fe->flags & FAULT_FLAG_WRITE;
-	unsigned long haddr = fe->address & HPAGE_PMD_MASK;
+	struct vm_area_struct *vma = vmf->vma;
+	bool write = vmf->flags & FAULT_FLAG_WRITE;
+	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
 	pmd_t entry;
 	int i, ret;
 
@@ -2966,15 +2974,15 @@ static int do_set_pmd(struct fault_env *fe, struct page *page)
 	 * Archs like ppc64 need additonal space to store information
 	 * related to pte entry. Use the preallocated table for that.
 	 */
-	if (arch_needs_pgtable_deposit() && !fe->prealloc_pte) {
-		fe->prealloc_pte = pte_alloc_one(vma->vm_mm, fe->address);
-		if (!fe->prealloc_pte)
+	if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) {
+		vmf->prealloc_pte = pte_alloc_one(vma->vm_mm, vmf->address);
+		if (!vmf->prealloc_pte)
 			return VM_FAULT_OOM;
 		smp_wmb(); /* See comment in __pte_alloc() */
 	}
 
-	fe->ptl = pmd_lock(vma->vm_mm, fe->pmd);
-	if (unlikely(!pmd_none(*fe->pmd)))
+	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
+	if (unlikely(!pmd_none(*vmf->pmd)))
 		goto out;
 
 	for (i = 0; i < HPAGE_PMD_NR; i++)
@@ -2990,11 +2998,11 @@ static int do_set_pmd(struct fault_env *fe, struct page *page)
 	 * deposit and withdraw with pmd lock held
 	 */
 	if (arch_needs_pgtable_deposit())
-		deposit_prealloc_pte(fe);
+		deposit_prealloc_pte(vmf);
 
-	set_pmd_at(vma->vm_mm, haddr, fe->pmd, entry);
+	set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
 
-	update_mmu_cache_pmd(vma, haddr, fe->pmd);
+	update_mmu_cache_pmd(vma, haddr, vmf->pmd);
 
 	/* fault is handled */
 	ret = 0;
@@ -3005,13 +3013,13 @@ out:
 	 * withdraw with pmd lock held.
 	 */
 	if (arch_needs_pgtable_deposit() && ret == VM_FAULT_FALLBACK)
-		fe->prealloc_pte = pgtable_trans_huge_withdraw(vma->vm_mm,
-							       fe->pmd);
-	spin_unlock(fe->ptl);
+		vmf->prealloc_pte = pgtable_trans_huge_withdraw(vma->vm_mm,
+								vmf->pmd);
+	spin_unlock(vmf->ptl);
 	return ret;
 }
 #else
-static int do_set_pmd(struct fault_env *fe, struct page *page)
+static int do_set_pmd(struct vm_fault *vmf, struct page *page)
 {
 	BUILD_BUG();
 	return 0;
@@ -3022,41 +3030,42 @@ static int do_set_pmd(struct fault_env *fe, struct page *page)
  * alloc_set_pte - setup new PTE entry for given page and add reverse page
  * mapping. If needed, the fucntion allocates page table or use pre-allocated.
  *
- * @fe: fault environment
+ * @vmf: fault environment
  * @memcg: memcg to charge page (only for private mappings)
  * @page: page to map
  *
- * Caller must take care of unlocking fe->ptl, if fe->pte is non-NULL on return.
+ * Caller must take care of unlocking vmf->ptl, if vmf->pte is non-NULL on
+ * return.
  *
  * Target users are page handler itself and implementations of
  * vm_ops->map_pages.
  */
-int alloc_set_pte(struct fault_env *fe, struct mem_cgroup *memcg,
+int alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
 		struct page *page)
 {
-	struct vm_area_struct *vma = fe->vma;
-	bool write = fe->flags & FAULT_FLAG_WRITE;
+	struct vm_area_struct *vma = vmf->vma;
+	bool write = vmf->flags & FAULT_FLAG_WRITE;
 	pte_t entry;
 	int ret;
 
-	if (pmd_none(*fe->pmd) && PageTransCompound(page) &&
+	if (pmd_none(*vmf->pmd) && PageTransCompound(page) &&
 			IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) {
 		/* THP on COW? */
 		VM_BUG_ON_PAGE(memcg, page);
 
-		ret = do_set_pmd(fe, page);
+		ret = do_set_pmd(vmf, page);
 		if (ret != VM_FAULT_FALLBACK)
 			goto fault_handled;
 	}
 
-	if (!fe->pte) {
-		ret = pte_alloc_one_map(fe);
+	if (!vmf->pte) {
+		ret = pte_alloc_one_map(vmf);
 		if (ret)
 			goto fault_handled;
 	}
 
 	/* Re-check under ptl */
-	if (unlikely(!pte_none(*fe->pte))) {
+	if (unlikely(!pte_none(*vmf->pte))) {
 		ret = VM_FAULT_NOPAGE;
 		goto fault_handled;
 	}
@@ -3068,28 +3077,60 @@ int alloc_set_pte(struct fault_env *fe, struct mem_cgroup *memcg,
 	/* copy-on-write page */
 	if (write && !(vma->vm_flags & VM_SHARED)) {
 		inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
-		page_add_new_anon_rmap(page, vma, fe->address, false);
+		page_add_new_anon_rmap(page, vma, vmf->address, false);
 		mem_cgroup_commit_charge(page, memcg, false, false);
 		lru_cache_add_active_or_unevictable(page, vma);
 	} else {
 		inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
 		page_add_file_rmap(page, false);
 	}
-	set_pte_at(vma->vm_mm, fe->address, fe->pte, entry);
+	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry);
 
 	/* no need to invalidate: a not-present page won't be cached */
-	update_mmu_cache(vma, fe->address, fe->pte);
+	update_mmu_cache(vma, vmf->address, vmf->pte);
 	ret = 0;
 
 fault_handled:
 	/* preallocated pagetable is unused: free it */
-	if (fe->prealloc_pte) {
-		pte_free(fe->vma->vm_mm, fe->prealloc_pte);
-		fe->prealloc_pte = 0;
+	if (vmf->prealloc_pte) {
+		pte_free(vmf->vma->vm_mm, vmf->prealloc_pte);
+		vmf->prealloc_pte = 0;
 	}
 	return ret;
 }
 
+
+/**
+ * finish_fault - finish page fault once we have prepared the page to fault
+ *
+ * @vmf: structure describing the fault
+ *
+ * This function handles all that is needed to finish a page fault once the
+ * page to fault in is prepared. It handles locking of PTEs, inserts PTE for
+ * given page, adds reverse page mapping, handles memcg charges and LRU
+ * addition. The function returns 0 on success, VM_FAULT_ code in case of
+ * error.
+ *
+ * The function expects the page to be locked and on success it consumes a
+ * reference of a page being mapped (for the PTE which maps it).
+ */
+int finish_fault(struct vm_fault *vmf)
+{
+	struct page *page;
+	int ret;
+
+	/* Did we COW the page? */
+	if ((vmf->flags & FAULT_FLAG_WRITE) &&
+	    !(vmf->vma->vm_flags & VM_SHARED))
+		page = vmf->cow_page;
+	else
+		page = vmf->page;
+	ret = alloc_set_pte(vmf, vmf->memcg, page);
+	if (vmf->pte)
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
+	return ret;
+}
+
 static unsigned long fault_around_bytes __read_mostly =
 	rounddown_pow_of_two(65536);
 
@@ -3154,17 +3195,18 @@ late_initcall(fault_around_debugfs);
  * fault_around_pages() value (and therefore to page order).  This way it's
  * easier to guarantee that we don't cross page table boundaries.
  */
-static int do_fault_around(struct fault_env *fe, pgoff_t start_pgoff)
+static int do_fault_around(struct vm_fault *vmf)
 {
-	unsigned long address = fe->address, nr_pages, mask;
+	unsigned long address = vmf->address, nr_pages, mask;
+	pgoff_t start_pgoff = vmf->pgoff;
 	pgoff_t end_pgoff;
 	int off, ret = 0;
 
 	nr_pages = READ_ONCE(fault_around_bytes) >> PAGE_SHIFT;
 	mask = ~(nr_pages * PAGE_SIZE - 1) & PAGE_MASK;
 
-	fe->address = max(address & mask, fe->vma->vm_start);
-	off = ((address - fe->address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
+	vmf->address = max(address & mask, vmf->vma->vm_start);
+	off = ((address - vmf->address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
 	start_pgoff -= off;
 
 	/*
@@ -3172,45 +3214,45 @@ static int do_fault_around(struct fault_env *fe, pgoff_t start_pgoff)
 	 *  or fault_around_pages() from start_pgoff, depending what is nearest.
 	 */
 	end_pgoff = start_pgoff -
-		((fe->address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) +
+		((vmf->address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) +
 		PTRS_PER_PTE - 1;
-	end_pgoff = min3(end_pgoff, vma_pages(fe->vma) + fe->vma->vm_pgoff - 1,
+	end_pgoff = min3(end_pgoff, vma_pages(vmf->vma) + vmf->vma->vm_pgoff - 1,
 			start_pgoff + nr_pages - 1);
 
-	if (pmd_none(*fe->pmd)) {
-		fe->prealloc_pte = pte_alloc_one(fe->vma->vm_mm, fe->address);
-		if (!fe->prealloc_pte)
+	if (pmd_none(*vmf->pmd)) {
+		vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm,
+						  vmf->address);
+		if (!vmf->prealloc_pte)
 			goto out;
 		smp_wmb(); /* See comment in __pte_alloc() */
 	}
 
-	fe->vma->vm_ops->map_pages(fe, start_pgoff, end_pgoff);
+	vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff);
 
 	/* Huge page is mapped? Page fault is solved */
-	if (pmd_trans_huge(*fe->pmd)) {
+	if (pmd_trans_huge(*vmf->pmd)) {
 		ret = VM_FAULT_NOPAGE;
 		goto out;
 	}
 
 	/* ->map_pages() haven't done anything useful. Cold page cache? */
-	if (!fe->pte)
+	if (!vmf->pte)
 		goto out;
 
 	/* check if the page fault is solved */
-	fe->pte -= (fe->address >> PAGE_SHIFT) - (address >> PAGE_SHIFT);
-	if (!pte_none(*fe->pte))
+	vmf->pte -= (vmf->address >> PAGE_SHIFT) - (address >> PAGE_SHIFT);
+	if (!pte_none(*vmf->pte))
 		ret = VM_FAULT_NOPAGE;
-	pte_unmap_unlock(fe->pte, fe->ptl);
+	pte_unmap_unlock(vmf->pte, vmf->ptl);
 out:
-	fe->address = address;
-	fe->pte = NULL;
+	vmf->address = address;
+	vmf->pte = NULL;
 	return ret;
 }
 
-static int do_read_fault(struct fault_env *fe, pgoff_t pgoff)
+static int do_read_fault(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = fe->vma;
-	struct page *fault_page;
+	struct vm_area_struct *vma = vmf->vma;
 	int ret = 0;
 
 	/*
@@ -3219,80 +3261,67 @@ static int do_read_fault(struct fault_env *fe, pgoff_t pgoff)
 	 * something).
 	 */
 	if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) {
-		ret = do_fault_around(fe, pgoff);
+		ret = do_fault_around(vmf);
 		if (ret)
 			return ret;
 	}
 
-	ret = __do_fault(fe, pgoff, NULL, &fault_page, NULL);
+	ret = __do_fault(vmf);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
 		return ret;
 
-	ret |= alloc_set_pte(fe, NULL, fault_page);
-	if (fe->pte)
-		pte_unmap_unlock(fe->pte, fe->ptl);
-	unlock_page(fault_page);
+	ret |= finish_fault(vmf);
+	unlock_page(vmf->page);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
-		put_page(fault_page);
+		put_page(vmf->page);
 	return ret;
 }
 
-static int do_cow_fault(struct fault_env *fe, pgoff_t pgoff)
+static int do_cow_fault(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = fe->vma;
-	struct page *fault_page, *new_page;
-	void *fault_entry;
-	struct mem_cgroup *memcg;
+	struct vm_area_struct *vma = vmf->vma;
 	int ret;
 
 	if (unlikely(anon_vma_prepare(vma)))
 		return VM_FAULT_OOM;
 
-	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, fe->address);
-	if (!new_page)
+	vmf->cow_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address);
+	if (!vmf->cow_page)
 		return VM_FAULT_OOM;
 
-	if (mem_cgroup_try_charge(new_page, vma->vm_mm, GFP_KERNEL,
-				&memcg, false)) {
-		put_page(new_page);
+	if (mem_cgroup_try_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL,
+				&vmf->memcg, false)) {
+		put_page(vmf->cow_page);
 		return VM_FAULT_OOM;
 	}
 
-	ret = __do_fault(fe, pgoff, new_page, &fault_page, &fault_entry);
+	ret = __do_fault(vmf);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
 		goto uncharge_out;
+	if (ret & VM_FAULT_DONE_COW)
+		return ret;
 
-	if (!(ret & VM_FAULT_DAX_LOCKED))
-		copy_user_highpage(new_page, fault_page, fe->address, vma);
-	__SetPageUptodate(new_page);
+	copy_user_highpage(vmf->cow_page, vmf->page, vmf->address, vma);
+	__SetPageUptodate(vmf->cow_page);
 
-	ret |= alloc_set_pte(fe, memcg, new_page);
-	if (fe->pte)
-		pte_unmap_unlock(fe->pte, fe->ptl);
-	if (!(ret & VM_FAULT_DAX_LOCKED)) {
-		unlock_page(fault_page);
-		put_page(fault_page);
-	} else {
-		dax_unlock_mapping_entry(vma->vm_file->f_mapping, pgoff);
-	}
+	ret |= finish_fault(vmf);
+	unlock_page(vmf->page);
+	put_page(vmf->page);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
 		goto uncharge_out;
 	return ret;
 uncharge_out:
-	mem_cgroup_cancel_charge(new_page, memcg, false);
-	put_page(new_page);
+	mem_cgroup_cancel_charge(vmf->cow_page, vmf->memcg, false);
+	put_page(vmf->cow_page);
 	return ret;
 }
 
-static int do_shared_fault(struct fault_env *fe, pgoff_t pgoff)
+static int do_shared_fault(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = fe->vma;
-	struct page *fault_page;
-	struct address_space *mapping;
-	int dirtied = 0;
+	struct vm_area_struct *vma = vmf->vma;
 	int ret, tmp;
 
-	ret = __do_fault(fe, pgoff, NULL, &fault_page, NULL);
+	ret = __do_fault(vmf);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
 		return ret;
 
@@ -3301,46 +3330,24 @@ static int do_shared_fault(struct fault_env *fe, pgoff_t pgoff)
 	 * about to become writable
 	 */
 	if (vma->vm_ops->page_mkwrite) {
-		unlock_page(fault_page);
-		tmp = do_page_mkwrite(vma, fault_page, fe->address);
+		unlock_page(vmf->page);
+		tmp = do_page_mkwrite(vmf);
 		if (unlikely(!tmp ||
 				(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) {
-			put_page(fault_page);
+			put_page(vmf->page);
 			return tmp;
 		}
 	}
 
-	ret |= alloc_set_pte(fe, NULL, fault_page);
-	if (fe->pte)
-		pte_unmap_unlock(fe->pte, fe->ptl);
+	ret |= finish_fault(vmf);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE |
 					VM_FAULT_RETRY))) {
-		unlock_page(fault_page);
-		put_page(fault_page);
+		unlock_page(vmf->page);
+		put_page(vmf->page);
 		return ret;
 	}
 
-	if (set_page_dirty(fault_page))
-		dirtied = 1;
-	/*
-	 * Take a local copy of the address_space - page.mapping may be zeroed
-	 * by truncate after unlock_page().   The address_space itself remains
-	 * pinned by vma->vm_file's reference.  We rely on unlock_page()'s
-	 * release semantics to prevent the compiler from undoing this copying.
-	 */
-	mapping = page_rmapping(fault_page);
-	unlock_page(fault_page);
-	if ((dirtied || vma->vm_ops->page_mkwrite) && mapping) {
-		/*
-		 * Some device drivers do not set page.mapping but still
-		 * dirty their pages
-		 */
-		balance_dirty_pages_ratelimited(mapping);
-	}
-
-	if (!vma->vm_ops->page_mkwrite)
-		file_update_time(vma->vm_file);
-
+	fault_dirty_shared_page(vma, vmf->page);
 	return ret;
 }
 
@@ -3350,19 +3357,18 @@ static int do_shared_fault(struct fault_env *fe, pgoff_t pgoff)
  * The mmap_sem may have been released depending on flags and our
  * return value.  See filemap_fault() and __lock_page_or_retry().
  */
-static int do_fault(struct fault_env *fe)
+static int do_fault(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = fe->vma;
-	pgoff_t pgoff = linear_page_index(vma, fe->address);
+	struct vm_area_struct *vma = vmf->vma;
 
 	/* The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */
 	if (!vma->vm_ops->fault)
 		return VM_FAULT_SIGBUS;
-	if (!(fe->flags & FAULT_FLAG_WRITE))
-		return do_read_fault(fe, pgoff);
+	if (!(vmf->flags & FAULT_FLAG_WRITE))
+		return do_read_fault(vmf);
 	if (!(vma->vm_flags & VM_SHARED))
-		return do_cow_fault(fe, pgoff);
-	return do_shared_fault(fe, pgoff);
+		return do_cow_fault(vmf);
+	return do_shared_fault(vmf);
 }
 
 static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
@@ -3380,14 +3386,15 @@ static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
 	return mpol_misplaced(page, vma, addr);
 }
 
-static int do_numa_page(struct fault_env *fe, pte_t pte)
+static int do_numa_page(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = fe->vma;
+	struct vm_area_struct *vma = vmf->vma;
 	struct page *page = NULL;
 	int page_nid = -1;
 	int last_cpupid;
 	int target_nid;
 	bool migrated = false;
+	pte_t pte = vmf->orig_pte;
 	bool was_writable = pte_write(pte);
 	int flags = 0;
 
@@ -3400,10 +3407,10 @@ static int do_numa_page(struct fault_env *fe, pte_t pte)
 	* page table entry is not accessible, so there would be no
 	* concurrent hardware modifications to the PTE.
 	*/
-	fe->ptl = pte_lockptr(vma->vm_mm, fe->pmd);
-	spin_lock(fe->ptl);
-	if (unlikely(!pte_same(*fe->pte, pte))) {
-		pte_unmap_unlock(fe->pte, fe->ptl);
+	vmf->ptl = pte_lockptr(vma->vm_mm, vmf->pmd);
+	spin_lock(vmf->ptl);
+	if (unlikely(!pte_same(*vmf->pte, pte))) {
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
 		goto out;
 	}
 
@@ -3412,18 +3419,18 @@ static int do_numa_page(struct fault_env *fe, pte_t pte)
 	pte = pte_mkyoung(pte);
 	if (was_writable)
 		pte = pte_mkwrite(pte);
-	set_pte_at(vma->vm_mm, fe->address, fe->pte, pte);
-	update_mmu_cache(vma, fe->address, fe->pte);
+	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
+	update_mmu_cache(vma, vmf->address, vmf->pte);
 
-	page = vm_normal_page(vma, fe->address, pte);
+	page = vm_normal_page(vma, vmf->address, pte);
 	if (!page) {
-		pte_unmap_unlock(fe->pte, fe->ptl);
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
 		return 0;
 	}
 
 	/* TODO: handle PTE-mapped THP */
 	if (PageCompound(page)) {
-		pte_unmap_unlock(fe->pte, fe->ptl);
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
 		return 0;
 	}
 
@@ -3447,9 +3454,9 @@ static int do_numa_page(struct fault_env *fe, pte_t pte)
 
 	last_cpupid = page_cpupid_last(page);
 	page_nid = page_to_nid(page);
-	target_nid = numa_migrate_prep(page, vma, fe->address, page_nid,
+	target_nid = numa_migrate_prep(page, vma, vmf->address, page_nid,
 			&flags);
-	pte_unmap_unlock(fe->pte, fe->ptl);
+	pte_unmap_unlock(vmf->pte, vmf->ptl);
 	if (target_nid == -1) {
 		put_page(page);
 		goto out;
@@ -3469,28 +3476,28 @@ out:
 	return 0;
 }
 
-static int create_huge_pmd(struct fault_env *fe)
+static int create_huge_pmd(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = fe->vma;
+	struct vm_area_struct *vma = vmf->vma;
 	if (vma_is_anonymous(vma))
-		return do_huge_pmd_anonymous_page(fe);
+		return do_huge_pmd_anonymous_page(vmf);
 	if (vma->vm_ops->pmd_fault)
-		return vma->vm_ops->pmd_fault(vma, fe->address, fe->pmd,
-				fe->flags);
+		return vma->vm_ops->pmd_fault(vma, vmf->address, vmf->pmd,
+				vmf->flags);
 	return VM_FAULT_FALLBACK;
 }
 
-static int wp_huge_pmd(struct fault_env *fe, pmd_t orig_pmd)
+static int wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
 {
-	if (vma_is_anonymous(fe->vma))
-		return do_huge_pmd_wp_page(fe, orig_pmd);
-	if (fe->vma->vm_ops->pmd_fault)
-		return fe->vma->vm_ops->pmd_fault(fe->vma, fe->address, fe->pmd,
-				fe->flags);
+	if (vma_is_anonymous(vmf->vma))
+		return do_huge_pmd_wp_page(vmf, orig_pmd);
+	if (vmf->vma->vm_ops->pmd_fault)
+		return vmf->vma->vm_ops->pmd_fault(vmf->vma, vmf->address,
+						   vmf->pmd, vmf->flags);
 
 	/* COW handled on pte level: split pmd */
-	VM_BUG_ON_VMA(fe->vma->vm_flags & VM_SHARED, fe->vma);
-	__split_huge_pmd(fe->vma, fe->pmd, fe->address, false, NULL);
+	VM_BUG_ON_VMA(vmf->vma->vm_flags & VM_SHARED, vmf->vma);
+	__split_huge_pmd(vmf->vma, vmf->pmd, vmf->address, false, NULL);
 
 	return VM_FAULT_FALLBACK;
 }
@@ -3515,21 +3522,21 @@ static inline bool vma_is_accessible(struct vm_area_struct *vma)
  * The mmap_sem may have been released depending on flags and our return value.
  * See filemap_fault() and __lock_page_or_retry().
  */
-static int handle_pte_fault(struct fault_env *fe)
+static int handle_pte_fault(struct vm_fault *vmf)
 {
 	pte_t entry;
 
-	if (unlikely(pmd_none(*fe->pmd))) {
+	if (unlikely(pmd_none(*vmf->pmd))) {
 		/*
 		 * Leave __pte_alloc() until later: because vm_ops->fault may
 		 * want to allocate huge page, and if we expose page table
 		 * for an instant, it will be difficult to retract from
 		 * concurrent faults and from rmap lookups.
 		 */
-		fe->pte = NULL;
+		vmf->pte = NULL;
 	} else {
 		/* See comment in pte_alloc_one_map() */
-		if (pmd_trans_unstable(fe->pmd) || pmd_devmap(*fe->pmd))
+		if (pmd_trans_unstable(vmf->pmd) || pmd_devmap(*vmf->pmd))
 			return 0;
 		/*
 		 * A regular pmd is established and it can't morph into a huge
@@ -3537,9 +3544,8 @@ static int handle_pte_fault(struct fault_env *fe)
 		 * mmap_sem read mode and khugepaged takes it in write mode.
 		 * So now it's safe to run pte_offset_map().
 		 */
-		fe->pte = pte_offset_map(fe->pmd, fe->address);
-
-		entry = *fe->pte;
+		vmf->pte = pte_offset_map(vmf->pmd, vmf->address);
+		vmf->orig_pte = *vmf->pte;
 
 		/*
 		 * some architectures can have larger ptes than wordsize,
@@ -3550,38 +3556,39 @@ static int handle_pte_fault(struct fault_env *fe)
 		 * ptl lock held. So here a barrier will do.
 		 */
 		barrier();
-		if (pte_none(entry)) {
-			pte_unmap(fe->pte);
-			fe->pte = NULL;
+		if (pte_none(vmf->orig_pte)) {
+			pte_unmap(vmf->pte);
+			vmf->pte = NULL;
 		}
 	}
 
-	if (!fe->pte) {
-		if (vma_is_anonymous(fe->vma))
-			return do_anonymous_page(fe);
+	if (!vmf->pte) {
+		if (vma_is_anonymous(vmf->vma))
+			return do_anonymous_page(vmf);
 		else
-			return do_fault(fe);
+			return do_fault(vmf);
 	}
 
-	if (!pte_present(entry))
-		return do_swap_page(fe, entry);
+	if (!pte_present(vmf->orig_pte))
+		return do_swap_page(vmf);
 
-	if (pte_protnone(entry) && vma_is_accessible(fe->vma))
-		return do_numa_page(fe, entry);
+	if (pte_protnone(vmf->orig_pte) && vma_is_accessible(vmf->vma))
+		return do_numa_page(vmf);
 
-	fe->ptl = pte_lockptr(fe->vma->vm_mm, fe->pmd);
-	spin_lock(fe->ptl);
-	if (unlikely(!pte_same(*fe->pte, entry)))
+	vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd);
+	spin_lock(vmf->ptl);
+	entry = vmf->orig_pte;
+	if (unlikely(!pte_same(*vmf->pte, entry)))
 		goto unlock;
-	if (fe->flags & FAULT_FLAG_WRITE) {
+	if (vmf->flags & FAULT_FLAG_WRITE) {
 		if (!pte_write(entry))
-			return do_wp_page(fe, entry);
+			return do_wp_page(vmf);
 		entry = pte_mkdirty(entry);
 	}
 	entry = pte_mkyoung(entry);
-	if (ptep_set_access_flags(fe->vma, fe->address, fe->pte, entry,
-				fe->flags & FAULT_FLAG_WRITE)) {
-		update_mmu_cache(fe->vma, fe->address, fe->pte);
+	if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry,
+				vmf->flags & FAULT_FLAG_WRITE)) {
+		update_mmu_cache(vmf->vma, vmf->address, vmf->pte);
 	} else {
 		/*
 		 * This is needed only for protection faults but the arch code
@@ -3589,11 +3596,11 @@ static int handle_pte_fault(struct fault_env *fe)
 		 * This still avoids useless tlb flushes for .text page faults
 		 * with threads.
 		 */
-		if (fe->flags & FAULT_FLAG_WRITE)
-			flush_tlb_fix_spurious_fault(fe->vma, fe->address);
+		if (vmf->flags & FAULT_FLAG_WRITE)
+			flush_tlb_fix_spurious_fault(vmf->vma, vmf->address);
 	}
 unlock:
-	pte_unmap_unlock(fe->pte, fe->ptl);
+	pte_unmap_unlock(vmf->pte, vmf->ptl);
 	return 0;
 }
 
@@ -3606,10 +3613,12 @@ unlock:
 static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 		unsigned int flags)
 {
-	struct fault_env fe = {
+	struct vm_fault vmf = {
 		.vma = vma,
-		.address = address,
+		.address = address & PAGE_MASK,
 		.flags = flags,
+		.pgoff = linear_page_index(vma, address),
+		.gfp_mask = __get_fault_gfp_mask(vma),
 	};
 	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgd;
@@ -3619,35 +3628,35 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 	pud = pud_alloc(mm, pgd, address);
 	if (!pud)
 		return VM_FAULT_OOM;
-	fe.pmd = pmd_alloc(mm, pud, address);
-	if (!fe.pmd)
+	vmf.pmd = pmd_alloc(mm, pud, address);
+	if (!vmf.pmd)
 		return VM_FAULT_OOM;
-	if (pmd_none(*fe.pmd) && transparent_hugepage_enabled(vma)) {
-		int ret = create_huge_pmd(&fe);
+	if (pmd_none(*vmf.pmd) && transparent_hugepage_enabled(vma)) {
+		int ret = create_huge_pmd(&vmf);
 		if (!(ret & VM_FAULT_FALLBACK))
 			return ret;
 	} else {
-		pmd_t orig_pmd = *fe.pmd;
+		pmd_t orig_pmd = *vmf.pmd;
 		int ret;
 
 		barrier();
 		if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) {
 			if (pmd_protnone(orig_pmd) && vma_is_accessible(vma))
-				return do_huge_pmd_numa_page(&fe, orig_pmd);
+				return do_huge_pmd_numa_page(&vmf, orig_pmd);
 
-			if ((fe.flags & FAULT_FLAG_WRITE) &&
+			if ((vmf.flags & FAULT_FLAG_WRITE) &&
 					!pmd_write(orig_pmd)) {
-				ret = wp_huge_pmd(&fe, orig_pmd);
+				ret = wp_huge_pmd(&vmf, orig_pmd);
 				if (!(ret & VM_FAULT_FALLBACK))
 					return ret;
 			} else {
-				huge_pmd_set_accessed(&fe, orig_pmd);
+				huge_pmd_set_accessed(&vmf, orig_pmd);
 				return 0;
 			}
 		}
 	}
 
-	return handle_pte_fault(&fe);
+	return handle_pte_fault(&vmf);
 }
 
 /*
@@ -3808,8 +3817,8 @@ out:
 	return -EINVAL;
 }
 
-static inline int follow_pte(struct mm_struct *mm, unsigned long address,
-			     pte_t **ptepp, spinlock_t **ptlp)
+int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp,
+	       spinlock_t **ptlp)
 {
 	int res;
 
@@ -3919,7 +3928,7 @@ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
 		struct page *page = NULL;
 
 		ret = get_user_pages_remote(tsk, mm, addr, 1,
-				gup_flags, &page, &vma);
+				gup_flags, &page, &vma, NULL);
 		if (ret <= 0) {
 #ifndef CONFIG_HAVE_IOREMAP_PROT
 			break;
diff --git a/mm/nommu.c b/mm/nommu.c
index 27bc543128e5..210d7ec2843c 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -176,9 +176,10 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
 }
 EXPORT_SYMBOL(get_user_pages_locked);
 
-long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
-			       unsigned long start, unsigned long nr_pages,
-			       struct page **pages, unsigned int gup_flags)
+static long __get_user_pages_unlocked(struct task_struct *tsk,
+			struct mm_struct *mm, unsigned long start,
+			unsigned long nr_pages, struct page **pages,
+			unsigned int gup_flags)
 {
 	long ret;
 	down_read(&mm->mmap_sem);
@@ -187,7 +188,6 @@ long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
 	up_read(&mm->mmap_sem);
 	return ret;
 }
-EXPORT_SYMBOL(__get_user_pages_unlocked);
 
 long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 			     struct page **pages, unsigned int gup_flags)
@@ -1801,7 +1801,7 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 }
 EXPORT_SYMBOL(filemap_fault);
 
-void filemap_map_pages(struct fault_env *fe,
+void filemap_map_pages(struct vm_fault *vmf,
 		pgoff_t start_pgoff, pgoff_t end_pgoff)
 {
 	BUG();
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index be8dc8d1edb9..84d0c7eada2b 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -88,7 +88,7 @@ static int process_vm_rw_single_vec(unsigned long addr,
 	ssize_t rc = 0;
 	unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES
 		/ sizeof(struct pages *);
-	unsigned int flags = FOLL_REMOTE;
+	unsigned int flags = 0;
 
 	/* Work out address and page range required */
 	if (len == 0)
@@ -100,15 +100,19 @@ static int process_vm_rw_single_vec(unsigned long addr,
 
 	while (!rc && nr_pages && iov_iter_count(iter)) {
 		int pages = min(nr_pages, max_pages_per_loop);
+		int locked = 1;
 		size_t bytes;
 
 		/*
 		 * Get the pages we're interested in.  We must
-		 * add FOLL_REMOTE because task/mm might not
+		 * access remotely because task/mm might not
 		 * current/current->mm
 		 */
-		pages = __get_user_pages_unlocked(task, mm, pa, pages,
-						  process_pages, flags);
+		down_read(&mm->mmap_sem);
+		pages = get_user_pages_remote(task, mm, pa, pages, flags,
+					      process_pages, NULL, &locked);
+		if (locked)
+			up_read(&mm->mmap_sem);
 		if (pages <= 0)
 			return -EFAULT;
 
diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c
index 682b73af7766..838ffa78cfda 100644
--- a/security/tomoyo/domain.c
+++ b/security/tomoyo/domain.c
@@ -881,7 +881,7 @@ bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos,
 	 * the execve().
 	 */
 	if (get_user_pages_remote(current, bprm->mm, pos, 1,
-				FOLL_FORCE, &page, NULL) <= 0)
+				FOLL_FORCE, &page, NULL, NULL) <= 0)
 		return false;
 #else
 	page = bprm->page[pos / PAGE_SIZE];
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index d08e214ec6e7..be93ab02b490 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -719,14 +719,14 @@ sub set_value {
 
     if ($buildonly && $lvalue =~ /^TEST_TYPE(\[.*\])?$/ && $prvalue ne "build") {
 	# Note if a test is something other than build, then we
-	# will need other manditory options.
+	# will need other mandatory options.
 	if ($prvalue ne "install") {
 	    # for bisect, we need to check BISECT_TYPE
 	    if ($prvalue ne "bisect") {
 		$buildonly = 0;
 	    }
 	} else {
-	    # install still limits some manditory options.
+	    # install still limits some mandatory options.
 	    $buildonly = 2;
 	}
     }
@@ -735,7 +735,7 @@ sub set_value {
 	if ($prvalue ne "install") {
 	    $buildonly = 0;
 	} else {
-	    # install still limits some manditory options.
+	    # install still limits some mandatory options.
 	    $buildonly = 2;
 	}
     }
@@ -3989,7 +3989,7 @@ sub make_min_config {
 		}
 	    }
 
-	    # Save off all the current mandidory configs
+	    # Save off all the current mandatory configs
 	    open (OUT, ">$temp_config")
 		or die "Can't write to $temp_config";
 	    foreach my $config (keys %keep_configs) {
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index efeceb0a222d..3815e940fbea 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -76,16 +76,20 @@ static void async_pf_execute(struct work_struct *work)
 	struct kvm_vcpu *vcpu = apf->vcpu;
 	unsigned long addr = apf->addr;
 	gva_t gva = apf->gva;
+	int locked = 1;
 
 	might_sleep();
 
 	/*
 	 * This work is run asynchromously to the task which owns
 	 * mm and might be done in another context, so we must
-	 * use FOLL_REMOTE.
+	 * access remotely.
 	 */
-	__get_user_pages_unlocked(NULL, mm, addr, 1, NULL,
-			FOLL_WRITE | FOLL_REMOTE);
+	down_read(&mm->mmap_sem);
+	get_user_pages_remote(NULL, mm, addr, 1, FOLL_WRITE, NULL, NULL,
+			&locked);
+	if (locked)
+		up_read(&mm->mmap_sem);
 
 	kvm_async_page_present_sync(vcpu, apf);
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 9e81531e85f5..a52ac3440b7b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1415,13 +1415,12 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
 		npages = get_user_page_nowait(addr, write_fault, page);
 		up_read(&current->mm->mmap_sem);
 	} else {
-		unsigned int flags = FOLL_TOUCH | FOLL_HWPOISON;
+		unsigned int flags = FOLL_HWPOISON;
 
 		if (write_fault)
 			flags |= FOLL_WRITE;
 
-		npages = __get_user_pages_unlocked(current, current->mm, addr, 1,
-						   page, flags);
+		npages = get_user_pages_unlocked(addr, 1, page, flags);
 	}
 	if (npages != 1)
 		return npages;