26 files changed, 414 insertions, 200 deletions

diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h
index 1109017499e5..e8275ea88e88 100644
--- a/arch/arm/include/asm/xen/page-coherent.h
+++ b/arch/arm/include/asm/xen/page-coherent.h
@@ -26,25 +26,14 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
 	__generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
 }
 
-static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir,
-		struct dma_attrs *attrs)
-{
-	if (__generic_dma_ops(hwdev)->unmap_page)
-		__generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
-}
+		struct dma_attrs *attrs);
 
-static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	if (__generic_dma_ops(hwdev)->sync_single_for_cpu)
-		__generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
-}
+void xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir);
+
+void xen_dma_sync_single_for_device(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir);
 
-static inline void xen_dma_sync_single_for_device(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	if (__generic_dma_ops(hwdev)->sync_single_for_device)
-		__generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
-}
 #endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */
diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h
index ded062f9b358..135c24a5ba26 100644
--- a/arch/arm/include/asm/xen/page.h
+++ b/arch/arm/include/asm/xen/page.h
@@ -33,7 +33,6 @@ typedef struct xpaddr {
 #define INVALID_P2M_ENTRY      (~0UL)
 
 unsigned long __pfn_to_mfn(unsigned long pfn);
-unsigned long __mfn_to_pfn(unsigned long mfn);
 extern struct rb_root phys_to_mach;
 
 static inline unsigned long pfn_to_mfn(unsigned long pfn)
@@ -51,14 +50,6 @@ static inline unsigned long pfn_to_mfn(unsigned long pfn)
 
 static inline unsigned long mfn_to_pfn(unsigned long mfn)
 {
-	unsigned long pfn;
-
-	if (phys_to_mach.rb_node != NULL) {
-		pfn = __mfn_to_pfn(mfn);
-		if (pfn != INVALID_P2M_ENTRY)
-			return pfn;
-	}
-
 	return mfn;
 }
 
diff --git a/arch/arm/xen/Makefile b/arch/arm/xen/Makefile
index 12969523414c..1f85bfe6b470 100644
--- a/arch/arm/xen/Makefile
+++ b/arch/arm/xen/Makefile
@@ -1 +1 @@
-obj-y		:= enlighten.o hypercall.o grant-table.o p2m.o mm.o
+obj-y		:= enlighten.o hypercall.o grant-table.o p2m.o mm.o mm32.o
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 98544c5f86e9..0e15f011f9c8 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -260,6 +260,12 @@ static int __init xen_guest_init(void)
 	xen_domain_type = XEN_HVM_DOMAIN;
 
 	xen_setup_features();
+
+	if (!xen_feature(XENFEAT_grant_map_identity)) {
+		pr_warn("Please upgrade your Xen.\n"
+				"If your platform has any non-coherent DMA devices, they won't work properly.\n");
+	}
+
 	if (xen_feature(XENFEAT_dom0))
 		xen_start_info->flags |= SIF_INITDOMAIN|SIF_PRIVILEGED;
 	else
diff --git a/arch/arm/xen/mm32.c b/arch/arm/xen/mm32.c
new file mode 100644
index 000000000000..3b99860fd7ae
--- /dev/null
+++ b/arch/arm/xen/mm32.c
@@ -0,0 +1,202 @@
+#include <linux/cpu.h>
+#include <linux/dma-mapping.h>
+#include <linux/gfp.h>
+#include <linux/highmem.h>
+
+#include <xen/features.h>
+
+static DEFINE_PER_CPU(unsigned long, xen_mm32_scratch_virt);
+static DEFINE_PER_CPU(pte_t *, xen_mm32_scratch_ptep);
+
+static int alloc_xen_mm32_scratch_page(int cpu)
+{
+	struct page *page;
+	unsigned long virt;
+	pmd_t *pmdp;
+	pte_t *ptep;
+
+	if (per_cpu(xen_mm32_scratch_ptep, cpu) != NULL)
+		return 0;
+
+	page = alloc_page(GFP_KERNEL);
+	if (page == NULL) {
+		pr_warn("Failed to allocate xen_mm32_scratch_page for cpu %d\n", cpu);
+		return -ENOMEM;
+	}
+
+	virt = (unsigned long)__va(page_to_phys(page));
+	pmdp = pmd_offset(pud_offset(pgd_offset_k(virt), virt), virt);
+	ptep = pte_offset_kernel(pmdp, virt);
+
+	per_cpu(xen_mm32_scratch_virt, cpu) = virt;
+	per_cpu(xen_mm32_scratch_ptep, cpu) = ptep;
+
+	return 0;
+}
+
+static int xen_mm32_cpu_notify(struct notifier_block *self,
+				    unsigned long action, void *hcpu)
+{
+	int cpu = (long)hcpu;
+	switch (action) {
+	case CPU_UP_PREPARE:
+		if (alloc_xen_mm32_scratch_page(cpu))
+			return NOTIFY_BAD;
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block xen_mm32_cpu_notifier = {
+	.notifier_call	= xen_mm32_cpu_notify,
+};
+
+static void* xen_mm32_remap_page(dma_addr_t handle)
+{
+	unsigned long virt = get_cpu_var(xen_mm32_scratch_virt);
+	pte_t *ptep = __get_cpu_var(xen_mm32_scratch_ptep);
+
+	*ptep = pfn_pte(handle >> PAGE_SHIFT, PAGE_KERNEL);
+	local_flush_tlb_kernel_page(virt);
+
+	return (void*)virt;
+}
+
+static void xen_mm32_unmap(void *vaddr)
+{
+	put_cpu_var(xen_mm32_scratch_virt);
+}
+
+
+/* functions called by SWIOTLB */
+
+static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
+	size_t size, enum dma_data_direction dir,
+	void (*op)(const void *, size_t, int))
+{
+	unsigned long pfn;
+	size_t left = size;
+
+	pfn = (handle >> PAGE_SHIFT) + offset / PAGE_SIZE;
+	offset %= PAGE_SIZE;
+
+	do {
+		size_t len = left;
+		void *vaddr;
+	
+		if (!pfn_valid(pfn))
+		{
+			/* Cannot map the page, we don't know its physical address.
+			 * Return and hope for the best */
+			if (!xen_feature(XENFEAT_grant_map_identity))
+				return;
+			vaddr = xen_mm32_remap_page(handle) + offset;
+			op(vaddr, len, dir);
+			xen_mm32_unmap(vaddr - offset);
+		} else {
+			struct page *page = pfn_to_page(pfn);
+
+			if (PageHighMem(page)) {
+				if (len + offset > PAGE_SIZE)
+					len = PAGE_SIZE - offset;
+
+				if (cache_is_vipt_nonaliasing()) {
+					vaddr = kmap_atomic(page);
+					op(vaddr + offset, len, dir);
+					kunmap_atomic(vaddr);
+				} else {
+					vaddr = kmap_high_get(page);
+					if (vaddr) {
+						op(vaddr + offset, len, dir);
+						kunmap_high(page);
+					}
+				}
+			} else {
+				vaddr = page_address(page) + offset;
+				op(vaddr, len, dir);
+			}
+		}
+
+		offset = 0;
+		pfn++;
+		left -= len;
+	} while (left);
+}
+
+static void __xen_dma_page_dev_to_cpu(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir)
+{
+	/* Cannot use __dma_page_dev_to_cpu because we don't have a
+	 * struct page for handle */
+
+	if (dir != DMA_TO_DEVICE)
+		outer_inv_range(handle, handle + size);
+
+	dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, dmac_unmap_area);
+}
+
+static void __xen_dma_page_cpu_to_dev(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir)
+{
+
+	dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, dmac_map_area);
+
+	if (dir == DMA_FROM_DEVICE) {
+		outer_inv_range(handle, handle + size);
+	} else {
+		outer_clean_range(handle, handle + size);
+	}
+}
+
+void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir,
+		struct dma_attrs *attrs)
+
+{
+	if (!__generic_dma_ops(hwdev)->unmap_page)
+		return;
+	if (dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
+		return;
+
+	__xen_dma_page_dev_to_cpu(hwdev, handle, size, dir);
+}
+
+void xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	if (!__generic_dma_ops(hwdev)->sync_single_for_cpu)
+		return;
+	__xen_dma_page_dev_to_cpu(hwdev, handle, size, dir);
+}
+
+void xen_dma_sync_single_for_device(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	if (!__generic_dma_ops(hwdev)->sync_single_for_device)
+		return;
+	__xen_dma_page_cpu_to_dev(hwdev, handle, size, dir);
+}
+
+int __init xen_mm32_init(void)
+{
+	int cpu;
+
+	if (!xen_initial_domain())
+		return 0;
+
+	register_cpu_notifier(&xen_mm32_cpu_notifier);
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
+		if (alloc_xen_mm32_scratch_page(cpu)) {
+			put_online_cpus();
+			unregister_cpu_notifier(&xen_mm32_cpu_notifier);
+			return -ENOMEM;
+		}
+	}
+	put_online_cpus();
+
+	return 0;
+}
+arch_initcall(xen_mm32_init);
diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c
index 97baf4427817..054857776254 100644
--- a/arch/arm/xen/p2m.c
+++ b/arch/arm/xen/p2m.c
@@ -21,14 +21,12 @@ struct xen_p2m_entry {
 	unsigned long pfn;
 	unsigned long mfn;
 	unsigned long nr_pages;
-	struct rb_node rbnode_mach;
 	struct rb_node rbnode_phys;
 };
 
 static rwlock_t p2m_lock;
 struct rb_root phys_to_mach = RB_ROOT;
 EXPORT_SYMBOL_GPL(phys_to_mach);
-static struct rb_root mach_to_phys = RB_ROOT;
 
 static int xen_add_phys_to_mach_entry(struct xen_p2m_entry *new)
 {
@@ -41,8 +39,6 @@ static int xen_add_phys_to_mach_entry(struct xen_p2m_entry *new)
 		parent = *link;
 		entry = rb_entry(parent, struct xen_p2m_entry, rbnode_phys);
 
-		if (new->mfn == entry->mfn)
-			goto err_out;
 		if (new->pfn == entry->pfn)
 			goto err_out;
 
@@ -88,64 +84,6 @@ unsigned long __pfn_to_mfn(unsigned long pfn)
 }
 EXPORT_SYMBOL_GPL(__pfn_to_mfn);
 
-static int xen_add_mach_to_phys_entry(struct xen_p2m_entry *new)
-{
-	struct rb_node **link = &mach_to_phys.rb_node;
-	struct rb_node *parent = NULL;
-	struct xen_p2m_entry *entry;
-	int rc = 0;
-
-	while (*link) {
-		parent = *link;
-		entry = rb_entry(parent, struct xen_p2m_entry, rbnode_mach);
-
-		if (new->mfn == entry->mfn)
-			goto err_out;
-		if (new->pfn == entry->pfn)
-			goto err_out;
-
-		if (new->mfn < entry->mfn)
-			link = &(*link)->rb_left;
-		else
-			link = &(*link)->rb_right;
-	}
-	rb_link_node(&new->rbnode_mach, parent, link);
-	rb_insert_color(&new->rbnode_mach, &mach_to_phys);
-	goto out;
-
-err_out:
-	rc = -EINVAL;
-	pr_warn("%s: cannot add pfn=%pa -> mfn=%pa: pfn=%pa -> mfn=%pa already exists\n",
-			__func__, &new->pfn, &new->mfn, &entry->pfn, &entry->mfn);
-out:
-	return rc;
-}
-
-unsigned long __mfn_to_pfn(unsigned long mfn)
-{
-	struct rb_node *n = mach_to_phys.rb_node;
-	struct xen_p2m_entry *entry;
-	unsigned long irqflags;
-
-	read_lock_irqsave(&p2m_lock, irqflags);
-	while (n) {
-		entry = rb_entry(n, struct xen_p2m_entry, rbnode_mach);
-		if (entry->mfn <= mfn &&
-				entry->mfn + entry->nr_pages > mfn) {
-			read_unlock_irqrestore(&p2m_lock, irqflags);
-			return entry->pfn + (mfn - entry->mfn);
-		}
-		if (mfn < entry->mfn)
-			n = n->rb_left;
-		else
-			n = n->rb_right;
-	}
-	read_unlock_irqrestore(&p2m_lock, irqflags);
-
-	return INVALID_P2M_ENTRY;
-}
-EXPORT_SYMBOL_GPL(__mfn_to_pfn);
-
 int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 			    struct gnttab_map_grant_ref *kmap_ops,
 			    struct page **pages, unsigned int count)
@@ -192,7 +130,6 @@ bool __set_phys_to_machine_multi(unsigned long pfn,
 			p2m_entry = rb_entry(n, struct xen_p2m_entry, rbnode_phys);
 			if (p2m_entry->pfn <= pfn &&
 					p2m_entry->pfn + p2m_entry->nr_pages > pfn) {
-				rb_erase(&p2m_entry->rbnode_mach, &mach_to_phys);
 				rb_erase(&p2m_entry->rbnode_phys, &phys_to_mach);
 				write_unlock_irqrestore(&p2m_lock, irqflags);
 				kfree(p2m_entry);
@@ -217,8 +154,7 @@ bool __set_phys_to_machine_multi(unsigned long pfn,
 	p2m_entry->mfn = mfn;
 
 	write_lock_irqsave(&p2m_lock, irqflags);
-	if ((rc = xen_add_phys_to_mach_entry(p2m_entry) < 0) ||
-		(rc = xen_add_mach_to_phys_entry(p2m_entry) < 0)) {
+	if ((rc = xen_add_phys_to_mach_entry(p2m_entry)) < 0) {
 		write_unlock_irqrestore(&p2m_lock, irqflags);
 		return false;
 	}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 778178f4c7d1..36327438caf0 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -23,6 +23,7 @@ config X86
 	def_bool y
 	select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
 	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
+	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select HAVE_AOUT if X86_32
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index afcd35d331de..cfe3b954d5e4 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -497,8 +497,6 @@ static __always_inline int fls64(__u64 x)
 
 #include <asm-generic/bitops/sched.h>
 
-#define ARCH_HAS_FAST_MULTIPLIER 1
-
 #include <asm/arch_hweight.h>
 
 #include <asm-generic/bitops/const_hweight.h>
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 54535831f1e1..77881798f793 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -10,10 +10,11 @@
 #include "blk.h"
 
 static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
-					     struct bio *bio)
+					     struct bio *bio,
+					     bool no_sg_merge)
 {
 	struct bio_vec bv, bvprv = { NULL };
-	int cluster, high, highprv = 1, no_sg_merge;
+	int cluster, high, highprv = 1;
 	unsigned int seg_size, nr_phys_segs;
 	struct bio *fbio, *bbio;
 	struct bvec_iter iter;
@@ -35,7 +36,6 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	cluster = blk_queue_cluster(q);
 	seg_size = 0;
 	nr_phys_segs = 0;
-	no_sg_merge = test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags);
 	high = 0;
 	for_each_bio(bio) {
 		bio_for_each_segment(bv, bio, iter) {
@@ -88,18 +88,23 @@ new_segment:
 
 void blk_recalc_rq_segments(struct request *rq)
 {
-	rq->nr_phys_segments = __blk_recalc_rq_segments(rq->q, rq->bio);
+	bool no_sg_merge = !!test_bit(QUEUE_FLAG_NO_SG_MERGE,
+			&rq->q->queue_flags);
+
+	rq->nr_phys_segments = __blk_recalc_rq_segments(rq->q, rq->bio,
+			no_sg_merge);
 }
 
 void blk_recount_segments(struct request_queue *q, struct bio *bio)
 {
-	if (test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags))
+	if (test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags) &&
+			bio->bi_vcnt < queue_max_segments(q))
 		bio->bi_phys_segments = bio->bi_vcnt;
 	else {
 		struct bio *nxt = bio->bi_next;
 
 		bio->bi_next = NULL;
-		bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio);
+		bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio, false);
 		bio->bi_next = nxt;
 	}
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4aac82615a46..383ea0cb1f0a 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1321,6 +1321,7 @@ static void blk_mq_free_rq_map(struct blk_mq_tag_set *set,
 				continue;
 			set->ops->exit_request(set->driver_data, tags->rqs[i],
 						hctx_idx, i);
+			tags->rqs[i] = NULL;
 		}
 	}
 
@@ -1354,8 +1355,9 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 
 	INIT_LIST_HEAD(&tags->page_list);
 
-	tags->rqs = kmalloc_node(set->queue_depth * sizeof(struct request *),
-					GFP_KERNEL, set->numa_node);
+	tags->rqs = kzalloc_node(set->queue_depth * sizeof(struct request *),
+				 GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY,
+				 set->numa_node);
 	if (!tags->rqs) {
 		blk_mq_free_tags(tags);
 		return NULL;
@@ -1379,8 +1381,9 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 			this_order--;
 
 		do {
-			page = alloc_pages_node(set->numa_node, GFP_KERNEL,
-						this_order);
+			page = alloc_pages_node(set->numa_node,
+				GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY,
+				this_order);
 			if (page)
 				break;
 			if (!this_order--)
@@ -1404,8 +1407,10 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 			if (set->ops->init_request) {
 				if (set->ops->init_request(set->driver_data,
 						tags->rqs[i], hctx_idx, i,
-						set->numa_node))
+						set->numa_node)) {
+					tags->rqs[i] = NULL;
 					goto fail;
+				}
 			}
 
 			p += rq_size;
@@ -1416,7 +1421,6 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 	return tags;
 
 fail:
-	pr_warn("%s: failed to allocate requests\n", __func__);
 	blk_mq_free_rq_map(set, tags, hctx_idx);
 	return NULL;
 }
@@ -1936,6 +1940,61 @@ static int blk_mq_queue_reinit_notify(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
+static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
+{
+	int i;
+
+	for (i = 0; i < set->nr_hw_queues; i++) {
+		set->tags[i] = blk_mq_init_rq_map(set, i);
+		if (!set->tags[i])
+			goto out_unwind;
+	}
+
+	return 0;
+
+out_unwind:
+	while (--i >= 0)
+		blk_mq_free_rq_map(set, set->tags[i], i);
+
+	set->tags = NULL;
+	return -ENOMEM;
+}
+
+/*
+ * Allocate the request maps associated with this tag_set. Note that this
+ * may reduce the depth asked for, if memory is tight. set->queue_depth
+ * will be updated to reflect the allocated depth.
+ */
+static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
+{
+	unsigned int depth;
+	int err;
+
+	depth = set->queue_depth;
+	do {
+		err = __blk_mq_alloc_rq_maps(set);
+		if (!err)
+			break;
+
+		set->queue_depth >>= 1;
+		if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN) {
+			err = -ENOMEM;
+			break;
+		}
+	} while (set->queue_depth);
+
+	if (!set->queue_depth || err) {
+		pr_err("blk-mq: failed to allocate request map\n");
+		return -ENOMEM;
+	}
+
+	if (depth != set->queue_depth)
+		pr_info("blk-mq: reduced tag depth (%u -> %u)\n",
+						depth, set->queue_depth);
+
+	return 0;
+}
+
 /*
  * Alloc a tag set to be associated with one or more request queues.
  * May fail with EINVAL for various error conditions. May adjust the
@@ -1944,8 +2003,6 @@ static int blk_mq_queue_reinit_notify(struct notifier_block *nb,
  */
 int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 {
-	int i;
-
 	if (!set->nr_hw_queues)
 		return -EINVAL;
 	if (!set->queue_depth)
@@ -1966,23 +2023,18 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 				 sizeof(struct blk_mq_tags *),
 				 GFP_KERNEL, set->numa_node);
 	if (!set->tags)
-		goto out;
+		return -ENOMEM;
 
-	for (i = 0; i < set->nr_hw_queues; i++) {
-		set->tags[i] = blk_mq_init_rq_map(set, i);
-		if (!set->tags[i])
-			goto out_unwind;
-	}
+	if (blk_mq_alloc_rq_maps(set))
+		goto enomem;
 
 	mutex_init(&set->tag_list_lock);
 	INIT_LIST_HEAD(&set->tag_list);
 
 	return 0;
-
-out_unwind:
-	while (--i >= 0)
-		blk_mq_free_rq_map(set, set->tags[i], i);
-out:
+enomem:
+	kfree(set->tags);
+	set->tags = NULL;
 	return -ENOMEM;
 }
 EXPORT_SYMBOL(blk_mq_alloc_tag_set);
@@ -1997,6 +2049,7 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 	}
 
 	kfree(set->tags);
+	set->tags = NULL;
 }
 EXPORT_SYMBOL(blk_mq_free_tag_set);
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 4db5abf96b9e..17f5c84ce7bf 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -554,8 +554,10 @@ int blk_register_queue(struct gendisk *disk)
 	 * Initialization must be complete by now.  Finish the initial
 	 * bypass from queue allocation.
 	 */
-	queue_flag_set_unlocked(QUEUE_FLAG_INIT_DONE, q);
-	blk_queue_bypass_end(q);
+	if (!blk_queue_init_done(q)) {
+		queue_flag_set_unlocked(QUEUE_FLAG_INIT_DONE, q);
+		blk_queue_bypass_end(q);
+	}
 
 	ret = blk_trace_init_sysfs(dev);
 	if (ret)
diff --git a/block/genhd.c b/block/genhd.c
index 791f41943132..09da5e4a8e03 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -28,10 +28,10 @@ struct kobject *block_depr;
 /* for extended dynamic devt allocation, currently only one major is used */
 #define NR_EXT_DEVT		(1 << MINORBITS)
 
-/* For extended devt allocation.  ext_devt_mutex prevents look up
+/* For extended devt allocation.  ext_devt_lock prevents look up
  * results from going away underneath its user.
  */
-static DEFINE_MUTEX(ext_devt_mutex);
+static DEFINE_SPINLOCK(ext_devt_lock);
 static DEFINE_IDR(ext_devt_idr);
 
 static struct device_type disk_type;
@@ -420,9 +420,13 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt)
 	}
 
 	/* allocate ext devt */
-	mutex_lock(&ext_devt_mutex);
-	idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_KERNEL);
-	mutex_unlock(&ext_devt_mutex);
+	idr_preload(GFP_KERNEL);
+
+	spin_lock(&ext_devt_lock);
+	idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_NOWAIT);
+	spin_unlock(&ext_devt_lock);
+
+	idr_preload_end();
 	if (idx < 0)
 		return idx == -ENOSPC ? -EBUSY : idx;
 
@@ -447,9 +451,9 @@ void blk_free_devt(dev_t devt)
 		return;
 
 	if (MAJOR(devt) == BLOCK_EXT_MAJOR) {
-		mutex_lock(&ext_devt_mutex);
+		spin_lock(&ext_devt_lock);
 		idr_remove(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
-		mutex_unlock(&ext_devt_mutex);
+		spin_unlock(&ext_devt_lock);
 	}
 }
 
@@ -665,7 +669,6 @@ void del_gendisk(struct gendisk *disk)
 		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
 	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
 	device_del(disk_to_dev(disk));
-	blk_free_devt(disk_to_dev(disk)->devt);
 }
 EXPORT_SYMBOL(del_gendisk);
 
@@ -690,13 +693,13 @@ struct gendisk *get_gendisk(dev_t devt, int *partno)
 	} else {
 		struct hd_struct *part;
 
-		mutex_lock(&ext_devt_mutex);
+		spin_lock(&ext_devt_lock);
 		part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
 		if (part && get_disk(part_to_disk(part))) {
 			*partno = part->partno;
 			disk = part_to_disk(part);
 		}
-		mutex_unlock(&ext_devt_mutex);
+		spin_unlock(&ext_devt_lock);
 	}
 
 	return disk;
@@ -1098,6 +1101,7 @@ static void disk_release(struct device *dev)
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
+	blk_free_devt(dev->devt);
 	disk_release_events(disk);
 	kfree(disk->random);
 	disk_replace_part_tbl(disk, NULL);
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 789cdea05893..0d9e5f97f0a8 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -211,6 +211,7 @@ static const struct attribute_group *part_attr_groups[] = {
 static void part_release(struct device *dev)
 {
 	struct hd_struct *p = dev_to_part(dev);
+	blk_free_devt(dev->devt);
 	free_part_stats(p);
 	free_part_info(p);
 	kfree(p);
@@ -253,7 +254,6 @@ void delete_partition(struct gendisk *disk, int partno)
 	rcu_assign_pointer(ptbl->last_lookup, NULL);
 	kobject_put(part->holder_dir);
 	device_del(part_to_dev(part));
-	blk_free_devt(part_devt(part));
 
 	hd_struct_put(part);
 }
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index db1e9560d8a7..5c8e7fe07745 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3918,7 +3918,6 @@ skip_create_disk:
 	if (rv) {
 		dev_err(&dd->pdev->dev,
 			"Unable to allocate request queue\n");
-		rv = -ENOMEM;
 		goto block_queue_alloc_init_error;
 	}
 
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index a3b042c4d448..00d469c7f9f7 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -462,17 +462,21 @@ static int null_add_dev(void)
 	struct gendisk *disk;
 	struct nullb *nullb;
 	sector_t size;
+	int rv;
 
 	nullb = kzalloc_node(sizeof(*nullb), GFP_KERNEL, home_node);
-	if (!nullb)
+	if (!nullb) {
+		rv = -ENOMEM;
 		goto out;
+	}
 
 	spin_lock_init(&nullb->lock);
 
 	if (queue_mode == NULL_Q_MQ && use_per_node_hctx)
 		submit_queues = nr_online_nodes;
 
-	if (setup_queues(nullb))
+	rv = setup_queues(nullb);
+	if (rv)
 		goto out_free_nullb;
 
 	if (queue_mode == NULL_Q_MQ) {
@@ -484,22 +488,29 @@ static int null_add_dev(void)
 		nullb->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
 		nullb->tag_set.driver_data = nullb;
 
-		if (blk_mq_alloc_tag_set(&nullb->tag_set))
+		rv = blk_mq_alloc_tag_set(&nullb->tag_set);
+		if (rv)
 			goto out_cleanup_queues;
 
 		nullb->q = blk_mq_init_queue(&nullb->tag_set);
-		if (!nullb->q)
+		if (!nullb->q) {
+			rv = -ENOMEM;
 			goto out_cleanup_tags;
+		}
 	} else if (queue_mode == NULL_Q_BIO) {
 		nullb->q = blk_alloc_queue_node(GFP_KERNEL, home_node);
-		if (!nullb->q)
+		if (!nullb->q) {
+			rv = -ENOMEM;
 			goto out_cleanup_queues;
+		}
 		blk_queue_make_request(nullb->q, null_queue_bio);
 		init_driver_queues(nullb);
 	} else {
 		nullb->q = blk_init_queue_node(null_request_fn, &nullb->lock, home_node);
-		if (!nullb->q)
+		if (!nullb->q) {
+			rv = -ENOMEM;
 			goto out_cleanup_queues;
+		}
 		blk_queue_prep_rq(nullb->q, null_rq_prep_fn);
 		blk_queue_softirq_done(nullb->q, null_softirq_done_fn);
 		init_driver_queues(nullb);
@@ -509,8 +520,10 @@ static int null_add_dev(void)
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, nullb->q);
 
 	disk = nullb->disk = alloc_disk_node(1, home_node);
-	if (!disk)
+	if (!disk) {
+		rv = -ENOMEM;
 		goto out_cleanup_blk_queue;
+	}
 
 	mutex_lock(&lock);
 	list_add_tail(&nullb->list, &nullb_list);
@@ -544,7 +557,7 @@ out_cleanup_queues:
 out_free_nullb:
 	kfree(nullb);
 out:
-	return -ENOMEM;
+	return rv;
 }
 
 static int __init null_init(void)
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 1af40ee209e2..7130505c2425 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -895,8 +895,8 @@ static void migration_success_pre_commit(struct dm_cache_migration *mg)
 	struct cache *cache = mg->cache;
 
 	if (mg->writeback) {
-		cell_defer(cache, mg->old_ocell, false);
 		clear_dirty(cache, mg->old_oblock, mg->cblock);
+		cell_defer(cache, mg->old_ocell, false);
 		cleanup_migration(mg);
 		return;
 
@@ -951,13 +951,13 @@ static void migration_success_post_commit(struct dm_cache_migration *mg)
 		}
 
 	} else {
+		clear_dirty(cache, mg->new_oblock, mg->cblock);
 		if (mg->requeue_holder)
 			cell_defer(cache, mg->new_ocell, true);
 		else {
 			bio_endio(mg->new_ocell->holder, 0);
 			cell_defer(cache, mg->new_ocell, false);
 		}
-		clear_dirty(cache, mg->new_oblock, mg->cblock);
 		cleanup_migration(mg);
 	}
 }
diff --git a/fs/dcache.c b/fs/dcache.c
index d30ce699ae4b..4023e77b800e 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -106,8 +106,7 @@ static inline struct hlist_bl_head *d_hash(const struct dentry *parent,
 					unsigned int hash)
 {
 	hash += (unsigned long) parent / L1_CACHE_BYTES;
-	hash = hash + (hash >> d_hash_shift);
-	return dentry_hashtable + (hash & d_hash_mask);
+	return dentry_hashtable + hash_32(hash, d_hash_shift);
 }
 
 /* Statistics gathering. */
diff --git a/fs/namei.c b/fs/namei.c
index a996bb48dfab..229235862e50 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -34,6 +34,7 @@
 #include <linux/device_cgroup.h>
 #include <linux/fs_struct.h>
 #include <linux/posix_acl.h>
+#include <linux/hash.h>
 #include <asm/uaccess.h>
 
 #include "internal.h"
@@ -1634,8 +1635,7 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd)
 
 static inline unsigned int fold_hash(unsigned long hash)
 {
-	hash += hash >> (8*sizeof(int));
-	return hash;
+	return hash_64(hash, 32);
 }
 
 #else	/* 32-bit case */
diff --git a/include/linux/hash.h b/include/linux/hash.h
index bd1754c7ecef..d0494c399392 100644
--- a/include/linux/hash.h
+++ b/include/linux/hash.h
@@ -37,6 +37,9 @@ static __always_inline u64 hash_64(u64 val, unsigned int bits)
 {
 	u64 hash = val;
 
+#if defined(CONFIG_ARCH_HAS_FAST_MULTIPLIER) && BITS_PER_LONG == 64
+	hash = hash * GOLDEN_RATIO_PRIME_64;
+#else
 	/*  Sigh, gcc can't optimise this alone like it does for 32 bits. */
 	u64 n = hash;
 	n <<= 18;
@@ -51,6 +54,7 @@ static __always_inline u64 hash_64(u64 val, unsigned int bits)
 	hash += n;
 	n <<= 2;
 	hash += n;
+#endif
 
 	/* High bits are more random, so use them. */
 	return hash >> (64 - bits);
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index 1f44466c1e9d..c367cbdf73ab 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -258,23 +258,11 @@ extern unsigned long preset_lpj;
 #define SEC_JIFFIE_SC (32 - SHIFT_HZ)
 #endif
 #define NSEC_JIFFIE_SC (SEC_JIFFIE_SC + 29)
-#define USEC_JIFFIE_SC (SEC_JIFFIE_SC + 19)
 #define SEC_CONVERSION ((unsigned long)((((u64)NSEC_PER_SEC << SEC_JIFFIE_SC) +\
                                 TICK_NSEC -1) / (u64)TICK_NSEC))
 
 #define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\
                                         TICK_NSEC -1) / (u64)TICK_NSEC))
-#define USEC_CONVERSION  \
-                    ((unsigned long)((((u64)NSEC_PER_USEC << USEC_JIFFIE_SC) +\
-                                        TICK_NSEC -1) / (u64)TICK_NSEC))
-/*
- * USEC_ROUND is used in the timeval to jiffie conversion.  See there
- * for more details.  It is the scaled resolution rounding value.  Note
- * that it is a 64-bit value.  Since, when it is applied, we are already
- * in jiffies (albit scaled), it is nothing but the bits we will shift
- * off.
- */
-#define USEC_ROUND (u64)(((u64)1 << USEC_JIFFIE_SC) - 1)
 /*
  * The maximum jiffie value is (MAX_INT >> 1).  Here we translate that
  * into seconds.  The 64-bit case will overflow if we are not careful,
diff --git a/include/xen/interface/features.h b/include/xen/interface/features.h
index 131a6ccdba25..14334d0161d5 100644
--- a/include/xen/interface/features.h
+++ b/include/xen/interface/features.h
@@ -53,6 +53,9 @@
 /* operation as Dom0 is supported */
 #define XENFEAT_dom0                      11
 
+/* Xen also maps grant references at pfn = mfn */
+#define XENFEAT_grant_map_identity        12
+
 #define XENFEAT_NR_SUBMAPS 1
 
 #endif /* __XEN_PUBLIC_FEATURES_H__ */
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 4aec4a457431..a7077d3ae52f 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -464,18 +464,26 @@ static enum alarmtimer_type clock2alarm(clockid_t clockid)
 static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm,
 							ktime_t now)
 {
+	unsigned long flags;
 	struct k_itimer *ptr = container_of(alarm, struct k_itimer,
 						it.alarm.alarmtimer);
-	if (posix_timer_event(ptr, 0) != 0)
-		ptr->it_overrun++;
+	enum alarmtimer_restart result = ALARMTIMER_NORESTART;
+
+	spin_lock_irqsave(&ptr->it_lock, flags);
+	if ((ptr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) {
+		if (posix_timer_event(ptr, 0) != 0)
+			ptr->it_overrun++;
+	}
 
 	/* Re-add periodic timers */
 	if (ptr->it.alarm.interval.tv64) {
 		ptr->it_overrun += alarm_forward(alarm, now,
 						ptr->it.alarm.interval);
-		return ALARMTIMER_RESTART;
+		result = ALARMTIMER_RESTART;
 	}
-	return ALARMTIMER_NORESTART;
+	spin_unlock_irqrestore(&ptr->it_lock, flags);
+
+	return result;
 }
 
 /**
@@ -541,18 +549,22 @@ static int alarm_timer_create(struct k_itimer *new_timer)
  * @new_timer: k_itimer pointer
  * @cur_setting: itimerspec data to fill
  *
- * Copies the itimerspec data out from the k_itimer
+ * Copies out the current itimerspec data
  */
 static void alarm_timer_get(struct k_itimer *timr,
 				struct itimerspec *cur_setting)
 {
-	memset(cur_setting, 0, sizeof(struct itimerspec));
+	ktime_t relative_expiry_time =
+		alarm_expires_remaining(&(timr->it.alarm.alarmtimer));
+
+	if (ktime_to_ns(relative_expiry_time) > 0) {
+		cur_setting->it_value = ktime_to_timespec(relative_expiry_time);
+	} else {
+		cur_setting->it_value.tv_sec = 0;
+		cur_setting->it_value.tv_nsec = 0;
+	}
 
-	cur_setting->it_interval =
-			ktime_to_timespec(timr->it.alarm.interval);
-	cur_setting->it_value =
-		ktime_to_timespec(timr->it.alarm.alarmtimer.node.expires);
-	return;
+	cur_setting->it_interval = ktime_to_timespec(timr->it.alarm.interval);
 }
 
 /**
diff --git a/kernel/time/time.c b/kernel/time/time.c
index f0294ba14634..a9ae20fb0b11 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -559,17 +559,20 @@ EXPORT_SYMBOL(usecs_to_jiffies);
  * that a remainder subtract here would not do the right thing as the
  * resolution values don't fall on second boundries.  I.e. the line:
  * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding.
+ * Note that due to the small error in the multiplier here, this
+ * rounding is incorrect for sufficiently large values of tv_nsec, but
+ * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're
+ * OK.
  *
  * Rather, we just shift the bits off the right.
  *
  * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec
  * value to a scaled second value.
  */
-unsigned long
-timespec_to_jiffies(const struct timespec *value)
+static unsigned long
+__timespec_to_jiffies(unsigned long sec, long nsec)
 {
-	unsigned long sec = value->tv_sec;
-	long nsec = value->tv_nsec + TICK_NSEC - 1;
+	nsec = nsec + TICK_NSEC - 1;
 
 	if (sec >= MAX_SEC_IN_JIFFIES){
 		sec = MAX_SEC_IN_JIFFIES;
@@ -580,6 +583,13 @@ timespec_to_jiffies(const struct timespec *value)
 		 (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
 
 }
+
+unsigned long
+timespec_to_jiffies(const struct timespec *value)
+{
+	return __timespec_to_jiffies(value->tv_sec, value->tv_nsec);
+}
+
 EXPORT_SYMBOL(timespec_to_jiffies);
 
 void
@@ -596,31 +606,27 @@ jiffies_to_timespec(const unsigned long jiffies, struct timespec *value)
 }
 EXPORT_SYMBOL(jiffies_to_timespec);
 
-/* Same for "timeval"
- *
- * Well, almost.  The problem here is that the real system resolution is
- * in nanoseconds and the value being converted is in micro seconds.
- * Also for some machines (those that use HZ = 1024, in-particular),
- * there is a LARGE error in the tick size in microseconds.
-
- * The solution we use is to do the rounding AFTER we convert the
- * microsecond part.  Thus the USEC_ROUND, the bits to be shifted off.
- * Instruction wise, this should cost only an additional add with carry
- * instruction above the way it was done above.
+/*
+ * We could use a similar algorithm to timespec_to_jiffies (with a
+ * different multiplier for usec instead of nsec). But this has a
+ * problem with rounding: we can't exactly add TICK_NSEC - 1 to the
+ * usec value, since it's not necessarily integral.
+ *
+ * We could instead round in the intermediate scaled representation
+ * (i.e. in units of 1/2^(large scale) jiffies) but that's also
+ * perilous: the scaling introduces a small positive error, which
+ * combined with a division-rounding-upward (i.e. adding 2^(scale) - 1
+ * units to the intermediate before shifting) leads to accidental
+ * overflow and overestimates.
+ *
+ * At the cost of one additional multiplication by a constant, just
+ * use the timespec implementation.
  */
 unsigned long
 timeval_to_jiffies(const struct timeval *value)
 {
-	unsigned long sec = value->tv_sec;
-	long usec = value->tv_usec;
-
-	if (sec >= MAX_SEC_IN_JIFFIES){
-		sec = MAX_SEC_IN_JIFFIES;
-		usec = 0;
-	}
-	return (((u64)sec * SEC_CONVERSION) +
-		(((u64)usec * USEC_CONVERSION + USEC_ROUND) >>
-		 (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
+	return __timespec_to_jiffies(value->tv_sec,
+				     value->tv_usec * NSEC_PER_USEC);
 }
 EXPORT_SYMBOL(timeval_to_jiffies);
 
diff --git a/lib/Kconfig b/lib/Kconfig
index a5ce0c7f6c30..54cf309a92a5 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -51,6 +51,9 @@ config PERCPU_RWSEM
 config ARCH_USE_CMPXCHG_LOCKREF
 	bool
 
+config ARCH_HAS_FAST_MULTIPLIER
+	bool
+
 config CRC_CCITT
 	tristate "CRC-CCITT functions"
 	help
diff --git a/lib/hweight.c b/lib/hweight.c
index b7d81ba143d1..9a5c1f221558 100644
--- a/lib/hweight.c
+++ b/lib/hweight.c
@@ -11,7 +11,7 @@
 
 unsigned int __sw_hweight32(unsigned int w)
 {
-#ifdef ARCH_HAS_FAST_MULTIPLIER
+#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
 	w -= (w >> 1) & 0x55555555;
 	w =  (w & 0x33333333) + ((w >> 2) & 0x33333333);
 	w =  (w + (w >> 4)) & 0x0f0f0f0f;
@@ -49,7 +49,7 @@ unsigned long __sw_hweight64(__u64 w)
 	return __sw_hweight32((unsigned int)(w >> 32)) +
 	       __sw_hweight32((unsigned int)w);
 #elif BITS_PER_LONG == 64
-#ifdef ARCH_HAS_FAST_MULTIPLIER
+#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
 	w -= (w >> 1) & 0x5555555555555555ul;
 	w =  (w & 0x3333333333333333ul) + ((w >> 2) & 0x3333333333333333ul);
 	w =  (w + (w >> 4)) & 0x0f0f0f0f0f0f0f0ful;
diff --git a/lib/string.c b/lib/string.c
index 992bf30af759..f3c6ff596414 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -807,9 +807,9 @@ void *memchr_inv(const void *start, int c, size_t bytes)
 		return check_bytes8(start, value, bytes);
 
 	value64 = value;
-#if defined(ARCH_HAS_FAST_MULTIPLIER) && BITS_PER_LONG == 64
+#if defined(CONFIG_ARCH_HAS_FAST_MULTIPLIER) && BITS_PER_LONG == 64
 	value64 *= 0x0101010101010101;
-#elif defined(ARCH_HAS_FAST_MULTIPLIER)
+#elif defined(CONFIG_ARCH_HAS_FAST_MULTIPLIER)
 	value64 *= 0x01010101;
 	value64 |= value64 << 32;
 #else