diff --git a/Documentation/virt/kvm/mmu.rst b/Documentation/virt/kvm/mmu.rst
index 1c030dbac7c4..5bfe28b0728e 100644
--- a/Documentation/virt/kvm/mmu.rst
+++ b/Documentation/virt/kvm/mmu.rst
@@ -455,7 +455,7 @@ If the generation number of the spte does not equal the global generation
 number, it will ignore the cached MMIO information and handle the page
 fault through the slow path.
 
-Since only 19 bits are used to store generation-number on mmio spte, all
+Since only 18 bits are used to store generation-number on mmio spte, all
 pages are zapped when there is an overflow.
 
 Unfortunately, a single memory access might access kvm_memslots(kvm) multiple
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 22c81f1edda2..85a3e49f92f4 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -104,6 +104,7 @@
 /* Shared ISS fault status code(IFSC/DFSC) for Data/Instruction aborts */
 #define ESR_ELx_FSC		(0x3F)
 #define ESR_ELx_FSC_TYPE	(0x3C)
+#define ESR_ELx_FSC_LEVEL	(0x03)
 #define ESR_ELx_FSC_EXTABT	(0x10)
 #define ESR_ELx_FSC_SERROR	(0x11)
 #define ESR_ELx_FSC_ACCESS	(0x08)
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 5ef2669ccd6c..00bc6f1234ba 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -350,6 +350,11 @@ static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vc
 	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_TYPE;
 }
 
+static __always_inline u8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_LEVEL;
+}
+
 static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
 {
 	switch (kvm_vcpu_trap_get_fault(vcpu)) {
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 0271b4a3b9fe..bdf8e55ed308 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -470,6 +470,15 @@ static bool stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level,
 	if (!kvm_block_mapping_supported(addr, end, phys, level))
 		return false;
 
+	/*
+	 * If the PTE was already valid, drop the refcount on the table
+	 * early, as it will be bumped-up again in stage2_map_walk_leaf().
+	 * This ensures that the refcount stays constant across a valid to
+	 * valid PTE update.
+	 */
+	if (kvm_pte_valid(*ptep))
+		put_page(virt_to_page(ptep));
+
 	if (kvm_set_valid_leaf_pte(ptep, phys, data->attr, level))
 		goto out;
 
@@ -493,7 +502,13 @@ static int stage2_map_walk_table_pre(u64 addr, u64 end, u32 level,
 		return 0;
 
 	kvm_set_invalid_pte(ptep);
-	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, data->mmu, addr, 0);
+
+	/*
+	 * Invalidate the whole stage-2, as we may have numerous leaf
+	 * entries below us which would otherwise need invalidating
+	 * individually.
+	 */
+	kvm_call_hyp(__kvm_tlb_flush_vmid, data->mmu);
 	data->anchor = ptep;
 	return 0;
 }
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 1a01da9fdc99..75814a02d189 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -754,10 +754,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	gfn_t gfn;
 	kvm_pfn_t pfn;
 	bool logging_active = memslot_is_logging(memslot);
-	unsigned long vma_pagesize;
+	unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu);
+	unsigned long vma_pagesize, fault_granule;
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
 	struct kvm_pgtable *pgt;
 
+	fault_granule = 1UL << ARM64_HW_PGTABLE_LEVEL_SHIFT(fault_level);
 	write_fault = kvm_is_write_fault(vcpu);
 	exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
 	VM_BUG_ON(write_fault && exec_fault);
@@ -896,7 +898,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	else if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC))
 		prot |= KVM_PGTABLE_PROT_X;
 
-	if (fault_status == FSC_PERM && !(logging_active && writable)) {
+	/*
+	 * Under the premise of getting a FSC_PERM fault, we just need to relax
+	 * permissions only if vma_pagesize equals fault_granule. Otherwise,
+	 * kvm_pgtable_stage2_map() should be called to change block size.
+	 */
+	if (fault_status == FSC_PERM && vma_pagesize == fault_granule) {
 		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
 	} else {
 		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h
index ab104905d4db..81de51e6aa32 100644
--- a/arch/riscv/include/asm/timex.h
+++ b/arch/riscv/include/asm/timex.h
@@ -60,6 +60,8 @@ static inline u32 get_cycles_hi(void)
 }
 #define get_cycles_hi get_cycles_hi
 
+#endif /* !CONFIG_RISCV_M_MODE */
+
 #ifdef CONFIG_64BIT
 static inline u64 get_cycles64(void)
 {
@@ -79,8 +81,6 @@ static inline u64 get_cycles64(void)
 }
 #endif /* CONFIG_64BIT */
 
-#endif /* !CONFIG_RISCV_M_MODE */
-
 #define ARCH_HAS_READ_CURRENT_TIMER
 static inline int read_current_timer(unsigned long *timer_val)
 {
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index fcac2cac78fe..c51ad544f25b 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -40,8 +40,8 @@ static u64 generation_mmio_spte_mask(u64 gen)
 	WARN_ON(gen & ~MMIO_SPTE_GEN_MASK);
 	BUILD_BUG_ON((MMIO_SPTE_GEN_HIGH_MASK | MMIO_SPTE_GEN_LOW_MASK) & SPTE_SPECIAL_MASK);
 
-	mask = (gen << MMIO_SPTE_GEN_LOW_START) & MMIO_SPTE_GEN_LOW_MASK;
-	mask |= (gen << MMIO_SPTE_GEN_HIGH_START) & MMIO_SPTE_GEN_HIGH_MASK;
+	mask = (gen << MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_SPTE_GEN_LOW_MASK;
+	mask |= (gen << MMIO_SPTE_GEN_HIGH_SHIFT) & MMIO_SPTE_GEN_HIGH_MASK;
 	return mask;
 }
 
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 5c75a451c000..2b3a30bd38b0 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -56,11 +56,11 @@
 #define SPTE_MMU_WRITEABLE	(1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1))
 
 /*
- * Due to limited space in PTEs, the MMIO generation is a 19 bit subset of
+ * Due to limited space in PTEs, the MMIO generation is a 18 bit subset of
  * the memslots generation and is derived as follows:
  *
  * Bits 0-8 of the MMIO generation are propagated to spte bits 3-11
- * Bits 9-18 of the MMIO generation are propagated to spte bits 52-61
+ * Bits 9-17 of the MMIO generation are propagated to spte bits 54-62
  *
  * The KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS flag is intentionally not included in
  * the MMIO generation number, as doing so would require stealing a bit from
@@ -69,18 +69,29 @@
  * requires a full MMU zap).  The flag is instead explicitly queried when
  * checking for MMIO spte cache hits.
  */
-#define MMIO_SPTE_GEN_MASK		GENMASK_ULL(17, 0)
 
 #define MMIO_SPTE_GEN_LOW_START		3
 #define MMIO_SPTE_GEN_LOW_END		11
-#define MMIO_SPTE_GEN_LOW_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \
-						    MMIO_SPTE_GEN_LOW_START)
 
 #define MMIO_SPTE_GEN_HIGH_START	PT64_SECOND_AVAIL_BITS_SHIFT
 #define MMIO_SPTE_GEN_HIGH_END		62
+
+#define MMIO_SPTE_GEN_LOW_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \
+						    MMIO_SPTE_GEN_LOW_START)
 #define MMIO_SPTE_GEN_HIGH_MASK		GENMASK_ULL(MMIO_SPTE_GEN_HIGH_END, \
 						    MMIO_SPTE_GEN_HIGH_START)
 
+#define MMIO_SPTE_GEN_LOW_BITS		(MMIO_SPTE_GEN_LOW_END - MMIO_SPTE_GEN_LOW_START + 1)
+#define MMIO_SPTE_GEN_HIGH_BITS		(MMIO_SPTE_GEN_HIGH_END - MMIO_SPTE_GEN_HIGH_START + 1)
+
+/* remember to adjust the comment above as well if you change these */
+static_assert(MMIO_SPTE_GEN_LOW_BITS == 9 && MMIO_SPTE_GEN_HIGH_BITS == 9);
+
+#define MMIO_SPTE_GEN_LOW_SHIFT		(MMIO_SPTE_GEN_LOW_START - 0)
+#define MMIO_SPTE_GEN_HIGH_SHIFT	(MMIO_SPTE_GEN_HIGH_START - MMIO_SPTE_GEN_LOW_BITS)
+
+#define MMIO_SPTE_GEN_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_BITS + MMIO_SPTE_GEN_HIGH_BITS - 1, 0)
+
 extern u64 __read_mostly shadow_nx_mask;
 extern u64 __read_mostly shadow_x_mask; /* mutual exclusive with nx_mask */
 extern u64 __read_mostly shadow_user_mask;
@@ -228,8 +239,8 @@ static inline u64 get_mmio_spte_generation(u64 spte)
 {
 	u64 gen;
 
-	gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_START;
-	gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_START;
+	gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_SHIFT;
+	gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_SHIFT;
 	return gen;
 }
 
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index ff28a5c6abd6..84c8f06bec26 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -66,7 +66,7 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 
 void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root)
 {
-	gfn_t max_gfn = 1ULL << (boot_cpu_data.x86_phys_bits - PAGE_SHIFT);
+	gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
 
 	lockdep_assert_held(&kvm->mmu_lock);
 
@@ -456,7 +456,7 @@ bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end)
 
 void kvm_tdp_mmu_zap_all(struct kvm *kvm)
 {
-	gfn_t max_gfn = 1ULL << (boot_cpu_data.x86_phys_bits - PAGE_SHIFT);
+	gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
 	bool flush;
 
 	flush = kvm_tdp_mmu_zap_gfn_range(kvm, 0, max_gfn);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 79b3a564f1c9..da7eb4aaf44f 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -530,12 +530,12 @@ static int svm_hardware_enable(void)
 
 static void svm_cpu_uninit(int cpu)
 {
-	struct svm_cpu_data *sd = per_cpu(svm_data, raw_smp_processor_id());
+	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
 
 	if (!sd)
 		return;
 
-	per_cpu(svm_data, raw_smp_processor_id()) = NULL;
+	per_cpu(svm_data, cpu) = NULL;
 	kfree(sd->sev_vmcbs);
 	__free_page(sd->save_area);
 	kfree(sd);
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 501e9dacfff9..9ebf53903d7b 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -132,73 +132,12 @@ module_param(log_stats, int, 0644);
 
 #define BLKBACK_INVALID_HANDLE (~0)
 
-/* Number of free pages to remove on each call to gnttab_free_pages */
-#define NUM_BATCH_FREE_PAGES 10
-
 static inline bool persistent_gnt_timeout(struct persistent_gnt *persistent_gnt)
 {
 	return pgrant_timeout && (jiffies - persistent_gnt->last_used >=
 			HZ * pgrant_timeout);
 }
 
-static inline int get_free_page(struct xen_blkif_ring *ring, struct page **page)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&ring->free_pages_lock, flags);
-	if (list_empty(&ring->free_pages)) {
-		BUG_ON(ring->free_pages_num != 0);
-		spin_unlock_irqrestore(&ring->free_pages_lock, flags);
-		return gnttab_alloc_pages(1, page);
-	}
-	BUG_ON(ring->free_pages_num == 0);
-	page[0] = list_first_entry(&ring->free_pages, struct page, lru);
-	list_del(&page[0]->lru);
-	ring->free_pages_num--;
-	spin_unlock_irqrestore(&ring->free_pages_lock, flags);
-
-	return 0;
-}
-
-static inline void put_free_pages(struct xen_blkif_ring *ring, struct page **page,
-                                  int num)
-{
-	unsigned long flags;
-	int i;
-
-	spin_lock_irqsave(&ring->free_pages_lock, flags);
-	for (i = 0; i < num; i++)
-		list_add(&page[i]->lru, &ring->free_pages);
-	ring->free_pages_num += num;
-	spin_unlock_irqrestore(&ring->free_pages_lock, flags);
-}
-
-static inline void shrink_free_pagepool(struct xen_blkif_ring *ring, int num)
-{
-	/* Remove requested pages in batches of NUM_BATCH_FREE_PAGES */
-	struct page *page[NUM_BATCH_FREE_PAGES];
-	unsigned int num_pages = 0;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ring->free_pages_lock, flags);
-	while (ring->free_pages_num > num) {
-		BUG_ON(list_empty(&ring->free_pages));
-		page[num_pages] = list_first_entry(&ring->free_pages,
-		                                   struct page, lru);
-		list_del(&page[num_pages]->lru);
-		ring->free_pages_num--;
-		if (++num_pages == NUM_BATCH_FREE_PAGES) {
-			spin_unlock_irqrestore(&ring->free_pages_lock, flags);
-			gnttab_free_pages(num_pages, page);
-			spin_lock_irqsave(&ring->free_pages_lock, flags);
-			num_pages = 0;
-		}
-	}
-	spin_unlock_irqrestore(&ring->free_pages_lock, flags);
-	if (num_pages != 0)
-		gnttab_free_pages(num_pages, page);
-}
-
 #define vaddr(page) ((unsigned long)pfn_to_kaddr(page_to_pfn(page)))
 
 static int do_block_io_op(struct xen_blkif_ring *ring, unsigned int *eoi_flags);
@@ -331,7 +270,8 @@ static void free_persistent_gnts(struct xen_blkif_ring *ring, struct rb_root *ro
 			unmap_data.count = segs_to_unmap;
 			BUG_ON(gnttab_unmap_refs_sync(&unmap_data));
 
-			put_free_pages(ring, pages, segs_to_unmap);
+			gnttab_page_cache_put(&ring->free_pages, pages,
+					      segs_to_unmap);
 			segs_to_unmap = 0;
 		}
 
@@ -371,7 +311,8 @@ void xen_blkbk_unmap_purged_grants(struct work_struct *work)
 		if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST) {
 			unmap_data.count = segs_to_unmap;
 			BUG_ON(gnttab_unmap_refs_sync(&unmap_data));
-			put_free_pages(ring, pages, segs_to_unmap);
+			gnttab_page_cache_put(&ring->free_pages, pages,
+					      segs_to_unmap);
 			segs_to_unmap = 0;
 		}
 		kfree(persistent_gnt);
@@ -379,7 +320,7 @@ void xen_blkbk_unmap_purged_grants(struct work_struct *work)
 	if (segs_to_unmap > 0) {
 		unmap_data.count = segs_to_unmap;
 		BUG_ON(gnttab_unmap_refs_sync(&unmap_data));
-		put_free_pages(ring, pages, segs_to_unmap);
+		gnttab_page_cache_put(&ring->free_pages, pages, segs_to_unmap);
 	}
 }
 
@@ -664,9 +605,10 @@ int xen_blkif_schedule(void *arg)
 
 		/* Shrink the free pages pool if it is too large. */
 		if (time_before(jiffies, blkif->buffer_squeeze_end))
-			shrink_free_pagepool(ring, 0);
+			gnttab_page_cache_shrink(&ring->free_pages, 0);
 		else
-			shrink_free_pagepool(ring, max_buffer_pages);
+			gnttab_page_cache_shrink(&ring->free_pages,
+						 max_buffer_pages);
 
 		if (log_stats && time_after(jiffies, ring->st_print))
 			print_stats(ring);
@@ -697,7 +639,7 @@ void xen_blkbk_free_caches(struct xen_blkif_ring *ring)
 	ring->persistent_gnt_c = 0;
 
 	/* Since we are shutting down remove all pages from the buffer */
-	shrink_free_pagepool(ring, 0 /* All */);
+	gnttab_page_cache_shrink(&ring->free_pages, 0 /* All */);
 }
 
 static unsigned int xen_blkbk_unmap_prepare(
@@ -736,7 +678,7 @@ static void xen_blkbk_unmap_and_respond_callback(int result, struct gntab_unmap_
 	   but is this the best way to deal with this? */
 	BUG_ON(result);
 
-	put_free_pages(ring, data->pages, data->count);
+	gnttab_page_cache_put(&ring->free_pages, data->pages, data->count);
 	make_response(ring, pending_req->id,
 		      pending_req->operation, pending_req->status);
 	free_req(ring, pending_req);
@@ -803,7 +745,8 @@ static void xen_blkbk_unmap(struct xen_blkif_ring *ring,
 		if (invcount) {
 			ret = gnttab_unmap_refs(unmap, NULL, unmap_pages, invcount);
 			BUG_ON(ret);
-			put_free_pages(ring, unmap_pages, invcount);
+			gnttab_page_cache_put(&ring->free_pages, unmap_pages,
+					      invcount);
 		}
 		pages += batch;
 		num -= batch;
@@ -850,7 +793,8 @@ static int xen_blkbk_map(struct xen_blkif_ring *ring,
 			pages[i]->page = persistent_gnt->page;
 			pages[i]->persistent_gnt = persistent_gnt;
 		} else {
-			if (get_free_page(ring, &pages[i]->page))
+			if (gnttab_page_cache_get(&ring->free_pages,
+						  &pages[i]->page))
 				goto out_of_memory;
 			addr = vaddr(pages[i]->page);
 			pages_to_gnt[segs_to_map] = pages[i]->page;
@@ -883,7 +827,8 @@ static int xen_blkbk_map(struct xen_blkif_ring *ring,
 			BUG_ON(new_map_idx >= segs_to_map);
 			if (unlikely(map[new_map_idx].status != 0)) {
 				pr_debug("invalid buffer -- could not remap it\n");
-				put_free_pages(ring, &pages[seg_idx]->page, 1);
+				gnttab_page_cache_put(&ring->free_pages,
+						      &pages[seg_idx]->page, 1);
 				pages[seg_idx]->handle = BLKBACK_INVALID_HANDLE;
 				ret |= 1;
 				goto next;
@@ -944,7 +889,7 @@ static int xen_blkbk_map(struct xen_blkif_ring *ring,
 
 out_of_memory:
 	pr_alert("%s: out of memory\n", __func__);
-	put_free_pages(ring, pages_to_gnt, segs_to_map);
+	gnttab_page_cache_put(&ring->free_pages, pages_to_gnt, segs_to_map);
 	for (i = last_map; i < num; i++)
 		pages[i]->handle = BLKBACK_INVALID_HANDLE;
 	return -ENOMEM;
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index c6ea5d38c509..a1b9df2c4ef1 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -288,9 +288,7 @@ struct xen_blkif_ring {
 	struct work_struct	persistent_purge_work;
 
 	/* Buffer of free pages to map grant refs. */
-	spinlock_t		free_pages_lock;
-	int			free_pages_num;
-	struct list_head	free_pages;
+	struct gnttab_page_cache free_pages;
 
 	struct work_struct	free_work;
 	/* Thread shutdown wait queue. */
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index f5705569e2a7..76912c584a76 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -144,8 +144,7 @@ static int xen_blkif_alloc_rings(struct xen_blkif *blkif)
 		INIT_LIST_HEAD(&ring->pending_free);
 		INIT_LIST_HEAD(&ring->persistent_purge_list);
 		INIT_WORK(&ring->persistent_purge_work, xen_blkbk_unmap_purged_grants);
-		spin_lock_init(&ring->free_pages_lock);
-		INIT_LIST_HEAD(&ring->free_pages);
+		gnttab_page_cache_init(&ring->free_pages);
 
 		spin_lock_init(&ring->pending_free_lock);
 		init_waitqueue_head(&ring->pending_free_wq);
@@ -317,8 +316,7 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif)
 		BUG_ON(atomic_read(&ring->persistent_gnt_in_use) != 0);
 		BUG_ON(!list_empty(&ring->persistent_purge_list));
 		BUG_ON(!RB_EMPTY_ROOT(&ring->persistent_gnts));
-		BUG_ON(!list_empty(&ring->free_pages));
-		BUG_ON(ring->free_pages_num != 0);
+		BUG_ON(ring->free_pages.num_pages != 0);
 		BUG_ON(ring->persistent_gnt_c != 0);
 		WARN_ON(i != (XEN_BLKIF_REQS_PER_PAGE * blkif->nr_ring_pages));
 		ring->active = false;
diff --git a/drivers/input/keyboard/cros_ec_keyb.c b/drivers/input/keyboard/cros_ec_keyb.c
index 15d17c717081..1f0d61b3c213 100644
--- a/drivers/input/keyboard/cros_ec_keyb.c
+++ b/drivers/input/keyboard/cros_ec_keyb.c
@@ -183,6 +183,7 @@ static void cros_ec_keyb_process(struct cros_ec_keyb *ckdev,
 					"changed: [r%d c%d]: byte %02x\n",
 					row, col, new_state);
 
+				input_event(idev, EV_MSC, MSC_SCAN, pos);
 				input_report_key(idev, keycodes[pos],
 						 new_state);
 			}
diff --git a/drivers/input/misc/cm109.c b/drivers/input/misc/cm109.c
index e413801f0491..f515fae465c3 100644
--- a/drivers/input/misc/cm109.c
+++ b/drivers/input/misc/cm109.c
@@ -568,12 +568,15 @@ static int cm109_input_open(struct input_dev *idev)
 	dev->ctl_data->byte[HID_OR2] = dev->keybit;
 	dev->ctl_data->byte[HID_OR3] = 0x00;
 
+	dev->ctl_urb_pending = 1;
 	error = usb_submit_urb(dev->urb_ctl, GFP_KERNEL);
-	if (error)
+	if (error) {
+		dev->ctl_urb_pending = 0;
 		dev_err(&dev->intf->dev, "%s: usb_submit_urb (urb_ctl) failed %d\n",
 			__func__, error);
-	else
+	} else {
 		dev->open = 1;
+	}
 
 	mutex_unlock(&dev->pm_mutex);
 
diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c
index d14a65683c5e..cb6ec59a045d 100644
--- a/drivers/input/misc/soc_button_array.c
+++ b/drivers/input/misc/soc_button_array.c
@@ -83,6 +83,17 @@ static const struct dmi_system_id dmi_use_low_level_irq[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "One S1003"),
 		},
 	},
+	{
+		/*
+		 * Lenovo Yoga Tab2 1051L, something messes with the home-button
+		 * IRQ settings, leading to a non working home-button.
+		 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "60073"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "1051L"),
+		},
+	},
 	{} /* Terminating entry */
 };
 
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 7ecb65176c1a..3a2dcf0805f1 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -611,6 +611,48 @@ static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "AOA150"),
 		},
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A114-31"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A314-31"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A315-31"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-132"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-332"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire ES1-432"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate Spin B118-RN"),
+		},
+	},
 	{
 		/* Advent 4211 */
 		.matches = {
diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c
index 02c75ea385e0..6612f9e2d7e8 100644
--- a/drivers/input/touchscreen/goodix.c
+++ b/drivers/input/touchscreen/goodix.c
@@ -192,6 +192,18 @@ static const struct dmi_system_id rotated_screen[] = {
 			DMI_MATCH(DMI_BIOS_DATE, "12/19/2014"),
 		},
 	},
+	{
+		.ident = "Teclast X98 Pro",
+		.matches = {
+			/*
+			 * Only match BIOS date, because the manufacturers
+			 * BIOS does not report the board name at all
+			 * (sometimes)...
+			 */
+			DMI_MATCH(DMI_BOARD_VENDOR, "TECLAST"),
+			DMI_MATCH(DMI_BIOS_DATE, "10/28/2015"),
+		},
+	},
 	{
 		.ident = "WinBook TW100",
 		.matches = {
diff --git a/drivers/input/touchscreen/raydium_i2c_ts.c b/drivers/input/touchscreen/raydium_i2c_ts.c
index e694a9b2b1e5..603a948460d6 100644
--- a/drivers/input/touchscreen/raydium_i2c_ts.c
+++ b/drivers/input/touchscreen/raydium_i2c_ts.c
@@ -137,45 +137,25 @@ struct raydium_data {
 	bool wake_irq_enabled;
 };
 
-static int raydium_i2c_xfer(struct i2c_client *client,
-			    u32 addr, void *data, size_t len, bool is_read)
+/*
+ * Header to be sent for RM_CMD_BANK_SWITCH command. This is used by
+ * raydium_i2c_{read|send} below.
+ */
+struct __packed raydium_bank_switch_header {
+	u8 cmd;
+	__be32 be_addr;
+};
+
+static int raydium_i2c_xfer(struct i2c_client *client, u32 addr,
+			    struct i2c_msg *xfer, size_t xfer_count)
 {
-	struct raydium_bank_switch_header {
-		u8 cmd;
-		__be32 be_addr;
-	} __packed header = {
-		.cmd = RM_CMD_BANK_SWITCH,
-		.be_addr = cpu_to_be32(addr),
-	};
-
-	u8 reg_addr = addr & 0xff;
-
-	struct i2c_msg xfer[] = {
-		{
-			.addr = client->addr,
-			.len = sizeof(header),
-			.buf = (u8 *)&header,
-		},
-		{
-			.addr = client->addr,
-			.len = 1,
-			.buf = &reg_addr,
-		},
-		{
-			.addr = client->addr,
-			.len = len,
-			.buf = data,
-			.flags = is_read ? I2C_M_RD : 0,
-		}
-	};
-
+	int ret;
 	/*
 	 * If address is greater than 255, then RM_CMD_BANK_SWITCH needs to be
 	 * sent first. Else, skip the header i.e. xfer[0].
 	 */
 	int xfer_start_idx = (addr > 0xff) ? 0 : 1;
-	size_t xfer_count = ARRAY_SIZE(xfer) - xfer_start_idx;
-	int ret;
+	xfer_count -= xfer_start_idx;
 
 	ret = i2c_transfer(client->adapter, &xfer[xfer_start_idx], xfer_count);
 	if (likely(ret == xfer_count))
@@ -189,10 +169,46 @@ static int raydium_i2c_send(struct i2c_client *client,
 {
 	int tries = 0;
 	int error;
+	u8 *tx_buf;
+	u8 reg_addr = addr & 0xff;
+
+	tx_buf = kmalloc(len + 1, GFP_KERNEL);
+	if (!tx_buf)
+		return -ENOMEM;
+
+	tx_buf[0] = reg_addr;
+	memcpy(tx_buf + 1, data, len);
 
 	do {
-		error = raydium_i2c_xfer(client, addr, (void *)data, len,
-					 false);
+		struct raydium_bank_switch_header header = {
+			.cmd = RM_CMD_BANK_SWITCH,
+			.be_addr = cpu_to_be32(addr),
+		};
+
+		/*
+		 * Perform as a single i2c_transfer transaction to ensure that
+		 * no other I2C transactions are initiated on the bus to any
+		 * other device in between. Initiating transacations to other
+		 * devices after RM_CMD_BANK_SWITCH is sent is known to cause
+		 * issues. This is also why regmap infrastructure cannot be used
+		 * for this driver. Regmap handles page(bank) switch and reads
+		 * as separate i2c_transfer() operations. This can result in
+		 * problems if the Raydium device is on a shared I2C bus.
+		 */
+		struct i2c_msg xfer[] = {
+			{
+				.addr = client->addr,
+				.len = sizeof(header),
+				.buf = (u8 *)&header,
+			},
+			{
+				.addr = client->addr,
+				.len = len + 1,
+				.buf = tx_buf,
+			},
+		};
+
+		error = raydium_i2c_xfer(client, addr, xfer, ARRAY_SIZE(xfer));
 		if (likely(!error))
 			return 0;
 
@@ -206,12 +222,46 @@ static int raydium_i2c_send(struct i2c_client *client,
 static int raydium_i2c_read(struct i2c_client *client,
 			    u32 addr, void *data, size_t len)
 {
-	size_t xfer_len;
 	int error;
 
 	while (len) {
-		xfer_len = min_t(size_t, len, RM_MAX_READ_SIZE);
-		error = raydium_i2c_xfer(client, addr, data, xfer_len, true);
+		u8 reg_addr = addr & 0xff;
+		struct raydium_bank_switch_header header = {
+			.cmd = RM_CMD_BANK_SWITCH,
+			.be_addr = cpu_to_be32(addr),
+		};
+		size_t xfer_len = min_t(size_t, len, RM_MAX_READ_SIZE);
+
+		/*
+		 * Perform as a single i2c_transfer transaction to ensure that
+		 * no other I2C transactions are initiated on the bus to any
+		 * other device in between. Initiating transacations to other
+		 * devices after RM_CMD_BANK_SWITCH is sent is known to cause
+		 * issues. This is also why regmap infrastructure cannot be used
+		 * for this driver. Regmap handles page(bank) switch and writes
+		 * as separate i2c_transfer() operations. This can result in
+		 * problems if the Raydium device is on a shared I2C bus.
+		 */
+		struct i2c_msg xfer[] = {
+			{
+				.addr = client->addr,
+				.len = sizeof(header),
+				.buf = (u8 *)&header,
+			},
+			{
+				.addr = client->addr,
+				.len = 1,
+				.buf = &reg_addr,
+			},
+			{
+				.addr = client->addr,
+				.len = xfer_len,
+				.buf = data,
+				.flags = I2C_M_RD,
+			}
+		};
+
+		error = raydium_i2c_xfer(client, addr, xfer, ARRAY_SIZE(xfer));
 		if (unlikely(error))
 			return error;
 
diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c
index 1c0a41803bb6..926408b41270 100644
--- a/drivers/misc/eeprom/at24.c
+++ b/drivers/misc/eeprom/at24.c
@@ -736,7 +736,6 @@ static int at24_probe(struct i2c_client *client)
 
 	nvmem_config.type = NVMEM_TYPE_EEPROM;
 	nvmem_config.dev = dev;
-	nvmem_config.id = NVMEM_DEVID_AUTO;
 	nvmem_config.read_only = !writable;
 	nvmem_config.root_only = !(flags & AT24_FLAG_IRUGO);
 	nvmem_config.owner = THIS_MODULE;
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index 202ba925c494..5c3513a4b450 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -3020,7 +3020,6 @@ static int beiscsi_create_eqs(struct beiscsi_hba *phba,
 			goto create_eq_error;
 		}
 
-		mem->dma = paddr;
 		mem->va = eq_vaddress;
 		ret = be_fill_queue(eq, phba->params.num_eq_entries,
 				    sizeof(struct be_eq_entry), eq_vaddress);
@@ -3030,6 +3029,7 @@ static int beiscsi_create_eqs(struct beiscsi_hba *phba,
 			goto create_eq_error;
 		}
 
+		mem->dma = paddr;
 		ret = beiscsi_cmd_eq_create(&phba->ctrl, eq,
 					    BEISCSI_EQ_DELAY_DEF);
 		if (ret) {
@@ -3086,7 +3086,6 @@ static int beiscsi_create_cqs(struct beiscsi_hba *phba,
 			goto create_cq_error;
 		}
 
-		mem->dma = paddr;
 		ret = be_fill_queue(cq, phba->params.num_cq_entries,
 				    sizeof(struct sol_cqe), cq_vaddress);
 		if (ret) {
@@ -3096,6 +3095,7 @@ static int beiscsi_create_cqs(struct beiscsi_hba *phba,
 			goto create_cq_error;
 		}
 
+		mem->dma = paddr;
 		ret = beiscsi_cmd_cq_create(&phba->ctrl, cq, eq, false,
 					    false, 0);
 		if (ret) {
diff --git a/drivers/scsi/bnx2i/Kconfig b/drivers/scsi/bnx2i/Kconfig
index 75ace2302fed..0cc06c2ce0b8 100644
--- a/drivers/scsi/bnx2i/Kconfig
+++ b/drivers/scsi/bnx2i/Kconfig
@@ -4,6 +4,7 @@ config SCSI_BNX2_ISCSI
 	depends on NET
 	depends on PCI
 	depends on (IPV6 || IPV6=n)
+	depends on MMU
 	select SCSI_ISCSI_ATTRS
 	select NETDEVICES
 	select ETHERNET
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index c8dd8588f800..274ccf18ce2d 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -452,6 +452,12 @@ static int hisi_sas_task_prep(struct sas_task *task,
 		blk_tag = blk_mq_unique_tag(scmd->request);
 		dq_index = blk_mq_unique_tag_to_hwq(blk_tag);
 		*dq_pointer = dq = &hisi_hba->dq[dq_index];
+	} else if (hisi_hba->shost->nr_hw_queues)  {
+		struct Scsi_Host *shost = hisi_hba->shost;
+		struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT];
+		int queue = qmap->mq_map[raw_smp_processor_id()];
+
+		*dq_pointer = dq = &hisi_hba->dq[queue];
 	} else {
 		*dq_pointer = dq = sas_dev->dq;
 	}
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 7133ca859b5e..960de375ce69 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -2452,6 +2452,11 @@ static int interrupt_init_v3_hw(struct hisi_hba *hisi_hba)
 			rc = -ENOENT;
 			goto free_irq_vectors;
 		}
+		cq->irq_mask = pci_irq_get_affinity(pdev, i + BASE_VECTORS_V3_HW);
+		if (!cq->irq_mask) {
+			dev_err(dev, "could not get cq%d irq affinity!\n", i);
+			return -ENOENT;
+		}
 	}
 
 	return 0;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 60c7a7d74852..03c6d0620bfd 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1703,8 +1703,7 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
 		break;
 	case BLK_STS_RESOURCE:
 	case BLK_STS_ZONE_RESOURCE:
-		if (atomic_read(&sdev->device_busy) ||
-		    scsi_device_blocked(sdev))
+		if (scsi_device_blocked(sdev))
 			ret = BLK_STS_DEV_RESOURCE;
 		break;
 	default:
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 99c8ff81de74..ded00a89bfc4 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1246,11 +1246,6 @@ static void storvsc_on_channel_callback(void *context)
 		request = (struct storvsc_cmd_request *)
 			((unsigned long)desc->trans_id);
 
-		if (hv_pkt_datalen(desc) < sizeof(struct vstor_packet) - vmscsi_size_delta) {
-			dev_err(&device->device, "Invalid packet len\n");
-			continue;
-		}
-
 		if (request == &stor_device->init_request ||
 		    request == &stor_device->reset_request) {
 			memcpy(&request->vstor_packet, packet,
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 523dcdf39cc9..3729bea0c989 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -813,6 +813,129 @@ int gnttab_alloc_pages(int nr_pages, struct page **pages)
 }
 EXPORT_SYMBOL_GPL(gnttab_alloc_pages);
 
+#ifdef CONFIG_XEN_UNPOPULATED_ALLOC
+static inline void cache_init(struct gnttab_page_cache *cache)
+{
+	cache->pages = NULL;
+}
+
+static inline bool cache_empty(struct gnttab_page_cache *cache)
+{
+	return !cache->pages;
+}
+
+static inline struct page *cache_deq(struct gnttab_page_cache *cache)
+{
+	struct page *page;
+
+	page = cache->pages;
+	cache->pages = page->zone_device_data;
+
+	return page;
+}
+
+static inline void cache_enq(struct gnttab_page_cache *cache, struct page *page)
+{
+	page->zone_device_data = cache->pages;
+	cache->pages = page;
+}
+#else
+static inline void cache_init(struct gnttab_page_cache *cache)
+{
+	INIT_LIST_HEAD(&cache->pages);
+}
+
+static inline bool cache_empty(struct gnttab_page_cache *cache)
+{
+	return list_empty(&cache->pages);
+}
+
+static inline struct page *cache_deq(struct gnttab_page_cache *cache)
+{
+	struct page *page;
+
+	page = list_first_entry(&cache->pages, struct page, lru);
+	list_del(&page->lru);
+
+	return page;
+}
+
+static inline void cache_enq(struct gnttab_page_cache *cache, struct page *page)
+{
+	list_add(&page->lru, &cache->pages);
+}
+#endif
+
+void gnttab_page_cache_init(struct gnttab_page_cache *cache)
+{
+	spin_lock_init(&cache->lock);
+	cache_init(cache);
+	cache->num_pages = 0;
+}
+EXPORT_SYMBOL_GPL(gnttab_page_cache_init);
+
+int gnttab_page_cache_get(struct gnttab_page_cache *cache, struct page **page)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cache->lock, flags);
+
+	if (cache_empty(cache)) {
+		spin_unlock_irqrestore(&cache->lock, flags);
+		return gnttab_alloc_pages(1, page);
+	}
+
+	page[0] = cache_deq(cache);
+	cache->num_pages--;
+
+	spin_unlock_irqrestore(&cache->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(gnttab_page_cache_get);
+
+void gnttab_page_cache_put(struct gnttab_page_cache *cache, struct page **page,
+			   unsigned int num)
+{
+	unsigned long flags;
+	unsigned int i;
+
+	spin_lock_irqsave(&cache->lock, flags);
+
+	for (i = 0; i < num; i++)
+		cache_enq(cache, page[i]);
+	cache->num_pages += num;
+
+	spin_unlock_irqrestore(&cache->lock, flags);
+}
+EXPORT_SYMBOL_GPL(gnttab_page_cache_put);
+
+void gnttab_page_cache_shrink(struct gnttab_page_cache *cache, unsigned int num)
+{
+	struct page *page[10];
+	unsigned int i = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cache->lock, flags);
+
+	while (cache->num_pages > num) {
+		page[i] = cache_deq(cache);
+		cache->num_pages--;
+		if (++i == ARRAY_SIZE(page)) {
+			spin_unlock_irqrestore(&cache->lock, flags);
+			gnttab_free_pages(i, page);
+			i = 0;
+			spin_lock_irqsave(&cache->lock, flags);
+		}
+	}
+
+	spin_unlock_irqrestore(&cache->lock, flags);
+
+	if (i != 0)
+		gnttab_free_pages(i, page);
+}
+EXPORT_SYMBOL_GPL(gnttab_page_cache_shrink);
+
 void gnttab_pages_clear_private(int nr_pages, struct page **pages)
 {
 	int i;
diff --git a/drivers/xen/unpopulated-alloc.c b/drivers/xen/unpopulated-alloc.c
index 8c512ea550bb..7762c1bb23cb 100644
--- a/drivers/xen/unpopulated-alloc.c
+++ b/drivers/xen/unpopulated-alloc.c
@@ -12,7 +12,7 @@
 #include <xen/xen.h>
 
 static DEFINE_MUTEX(list_lock);
-static LIST_HEAD(page_list);
+static struct page *page_list;
 static unsigned int list_count;
 
 static int fill_list(unsigned int nr_pages)
@@ -84,7 +84,8 @@ static int fill_list(unsigned int nr_pages)
 		struct page *pg = virt_to_page(vaddr + PAGE_SIZE * i);
 
 		BUG_ON(!virt_addr_valid(vaddr + PAGE_SIZE * i));
-		list_add(&pg->lru, &page_list);
+		pg->zone_device_data = page_list;
+		page_list = pg;
 		list_count++;
 	}
 
@@ -118,12 +119,10 @@ int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages)
 	}
 
 	for (i = 0; i < nr_pages; i++) {
-		struct page *pg = list_first_entry_or_null(&page_list,
-							   struct page,
-							   lru);
+		struct page *pg = page_list;
 
 		BUG_ON(!pg);
-		list_del(&pg->lru);
+		page_list = pg->zone_device_data;
 		list_count--;
 		pages[i] = pg;
 
@@ -134,7 +133,8 @@ int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages)
 				unsigned int j;
 
 				for (j = 0; j <= i; j++) {
-					list_add(&pages[j]->lru, &page_list);
+					pages[j]->zone_device_data = page_list;
+					page_list = pages[j];
 					list_count++;
 				}
 				goto out;
@@ -160,7 +160,8 @@ void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages)
 
 	mutex_lock(&list_lock);
 	for (i = 0; i < nr_pages; i++) {
-		list_add(&pages[i]->lru, &page_list);
+		pages[i]->zone_device_data = page_list;
+		page_list = pages[i];
 		list_count++;
 	}
 	mutex_unlock(&list_lock);
@@ -189,7 +190,8 @@ static int __init init(void)
 			struct page *pg =
 				pfn_to_page(xen_extra_mem[i].start_pfn + j);
 
-			list_add(&pg->lru, &page_list);
+			pg->zone_device_data = page_list;
+			page_list = pg;
 			list_count++;
 		}
 	}
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index 4acc4e899600..862162dca33c 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -99,6 +99,8 @@ struct vscsibk_info {
 	struct list_head v2p_entry_lists;
 
 	wait_queue_head_t waiting_to_free;
+
+	struct gnttab_page_cache free_pages;
 };
 
 /* theoretical maximum of grants for one request */
@@ -188,10 +190,6 @@ module_param_named(max_buffer_pages, scsiback_max_buffer_pages, int, 0644);
 MODULE_PARM_DESC(max_buffer_pages,
 "Maximum number of free pages to keep in backend buffer");
 
-static DEFINE_SPINLOCK(free_pages_lock);
-static int free_pages_num;
-static LIST_HEAD(scsiback_free_pages);
-
 /* Global spinlock to protect scsiback TPG list */
 static DEFINE_MUTEX(scsiback_mutex);
 static LIST_HEAD(scsiback_list);
@@ -207,41 +205,6 @@ static void scsiback_put(struct vscsibk_info *info)
 		wake_up(&info->waiting_to_free);
 }
 
-static void put_free_pages(struct page **page, int num)
-{
-	unsigned long flags;
-	int i = free_pages_num + num, n = num;
-
-	if (num == 0)
-		return;
-	if (i > scsiback_max_buffer_pages) {
-		n = min(num, i - scsiback_max_buffer_pages);
-		gnttab_free_pages(n, page + num - n);
-		n = num - n;
-	}
-	spin_lock_irqsave(&free_pages_lock, flags);
-	for (i = 0; i < n; i++)
-		list_add(&page[i]->lru, &scsiback_free_pages);
-	free_pages_num += n;
-	spin_unlock_irqrestore(&free_pages_lock, flags);
-}
-
-static int get_free_page(struct page **page)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&free_pages_lock, flags);
-	if (list_empty(&scsiback_free_pages)) {
-		spin_unlock_irqrestore(&free_pages_lock, flags);
-		return gnttab_alloc_pages(1, page);
-	}
-	page[0] = list_first_entry(&scsiback_free_pages, struct page, lru);
-	list_del(&page[0]->lru);
-	free_pages_num--;
-	spin_unlock_irqrestore(&free_pages_lock, flags);
-	return 0;
-}
-
 static unsigned long vaddr_page(struct page *page)
 {
 	unsigned long pfn = page_to_pfn(page);
@@ -302,7 +265,8 @@ static void scsiback_fast_flush_area(struct vscsibk_pend *req)
 		BUG_ON(err);
 	}
 
-	put_free_pages(req->pages, req->n_grants);
+	gnttab_page_cache_put(&req->info->free_pages, req->pages,
+			      req->n_grants);
 	req->n_grants = 0;
 }
 
@@ -445,8 +409,8 @@ static int scsiback_gnttab_data_map_list(struct vscsibk_pend *pending_req,
 	struct vscsibk_info *info = pending_req->info;
 
 	for (i = 0; i < cnt; i++) {
-		if (get_free_page(pg + mapcount)) {
-			put_free_pages(pg, mapcount);
+		if (gnttab_page_cache_get(&info->free_pages, pg + mapcount)) {
+			gnttab_page_cache_put(&info->free_pages, pg, mapcount);
 			pr_err("no grant page\n");
 			return -ENOMEM;
 		}
@@ -796,6 +760,8 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info,
 		cond_resched();
 	}
 
+	gnttab_page_cache_shrink(&info->free_pages, scsiback_max_buffer_pages);
+
 	RING_FINAL_CHECK_FOR_REQUESTS(&info->ring, more_to_do);
 	return more_to_do;
 }
@@ -1233,6 +1199,8 @@ static int scsiback_remove(struct xenbus_device *dev)
 
 	scsiback_release_translation_entry(info);
 
+	gnttab_page_cache_shrink(&info->free_pages, 0);
+
 	dev_set_drvdata(&dev->dev, NULL);
 
 	return 0;
@@ -1263,6 +1231,7 @@ static int scsiback_probe(struct xenbus_device *dev,
 	info->irq = 0;
 	INIT_LIST_HEAD(&info->v2p_entry_lists);
 	spin_lock_init(&info->v2p_lock);
+	gnttab_page_cache_init(&info->free_pages);
 
 	err = xenbus_printf(XBT_NIL, dev->nodename, "feature-sg-grant", "%u",
 			    SG_ALL);
@@ -1879,13 +1848,6 @@ static int __init scsiback_init(void)
 
 static void __exit scsiback_exit(void)
 {
-	struct page *page;
-
-	while (free_pages_num) {
-		if (get_free_page(&page))
-			BUG();
-		gnttab_free_pages(1, &page);
-	}
 	target_unregister_template(&scsiback_ops);
 	xenbus_unregister_driver(&scsiback_driver);
 }
diff --git a/fs/io_uring.c b/fs/io_uring.c
index a2a7c65a77aa..86dac2b2e276 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1284,7 +1284,7 @@ static bool io_identity_cow(struct io_kiocb *req)
 	 */
 	io_init_identity(id);
 	if (creds)
-		req->work.identity->creds = creds;
+		id->creds = creds;
 
 	/* add one for this request */
 	refcount_inc(&id->count);
@@ -9183,6 +9183,7 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx)
 {
 	struct file *file;
 	int ret;
+	int fd;
 
 #if defined(CONFIG_UNIX)
 	ret = sock_create_kern(&init_net, PF_UNIX, SOCK_RAW, IPPROTO_IP,
@@ -9194,12 +9195,12 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx)
 	ret = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
 	if (ret < 0)
 		goto err;
+	fd = ret;
 
 	file = anon_inode_getfile("[io_uring]", &io_uring_fops, ctx,
 					O_RDWR | O_CLOEXEC);
 	if (IS_ERR(file)) {
-err_fd:
-		put_unused_fd(ret);
+		put_unused_fd(fd);
 		ret = PTR_ERR(file);
 		goto err;
 	}
@@ -9207,12 +9208,14 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx)
 #if defined(CONFIG_UNIX)
 	ctx->ring_sock->file = file;
 #endif
-	if (unlikely(io_uring_add_task_file(ctx, file))) {
-		file = ERR_PTR(-ENOMEM);
-		goto err_fd;
+	ret = io_uring_add_task_file(ctx, file);
+	if (ret) {
+		fput(file);
+		put_unused_fd(fd);
+		goto err;
 	}
-	fd_install(ret, file);
-	return ret;
+	fd_install(fd, file);
+	return fd;
 err:
 #if defined(CONFIG_UNIX)
 	sock_release(ctx->ring_sock);
diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h
index 9bc5bc07d4d3..b9c937b3a149 100644
--- a/include/xen/grant_table.h
+++ b/include/xen/grant_table.h
@@ -198,6 +198,23 @@ void gnttab_free_auto_xlat_frames(void);
 int gnttab_alloc_pages(int nr_pages, struct page **pages);
 void gnttab_free_pages(int nr_pages, struct page **pages);
 
+struct gnttab_page_cache {
+	spinlock_t		lock;
+#ifdef CONFIG_XEN_UNPOPULATED_ALLOC
+	struct page		*pages;
+#else
+	struct list_head	pages;
+#endif
+	unsigned int		num_pages;
+};
+
+void gnttab_page_cache_init(struct gnttab_page_cache *cache);
+int gnttab_page_cache_get(struct gnttab_page_cache *cache, struct page **page);
+void gnttab_page_cache_put(struct gnttab_page_cache *cache, struct page **page,
+			   unsigned int num);
+void gnttab_page_cache_shrink(struct gnttab_page_cache *cache,
+			      unsigned int num);
+
 #ifdef CONFIG_XEN_GRANT_DMA_ALLOC
 struct gnttab_dma_alloc_args {
 	/* Device for which DMA memory will be/was allocated. */
diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat
index d199a3694be8..b0bf56c5f120 100755
--- a/tools/kvm/kvm_stat/kvm_stat
+++ b/tools/kvm/kvm_stat/kvm_stat
@@ -742,7 +742,11 @@ class DebugfsProvider(Provider):
         The fields are all available KVM debugfs files
 
         """
-        return self.walkdir(PATH_DEBUGFS_KVM)[2]
+        exempt_list = ['halt_poll_fail_ns', 'halt_poll_success_ns']
+        fields = [field for field in self.walkdir(PATH_DEBUGFS_KVM)[2]
+                  if field not in exempt_list]
+
+        return fields
 
     def update_fields(self, fields_filter):
         """Refresh fields, applying fields_filter"""
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index b3ece55a2da6..6f441dd9f33c 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -156,14 +156,23 @@ static void guest_code_move_memory_region(void)
 	GUEST_SYNC(0);
 
 	/*
-	 * Spin until the memory region is moved to a misaligned address.  This
-	 * may or may not trigger MMIO, as the window where the memslot is
-	 * invalid is quite small.
+	 * Spin until the memory region starts getting moved to a
+	 * misaligned address.
+	 * Every region move may or may not trigger MMIO, as the
+	 * window where the memslot is invalid is usually quite small.
 	 */
 	val = guest_spin_on_val(0);
 	GUEST_ASSERT_1(val == 1 || val == MMIO_VAL, val);
 
-	/* Spin until the memory region is realigned. */
+	/* Spin until the misaligning memory region move completes. */
+	val = guest_spin_on_val(MMIO_VAL);
+	GUEST_ASSERT_1(val == 1 || val == 0, val);
+
+	/* Spin until the memory region starts to get re-aligned. */
+	val = guest_spin_on_val(0);
+	GUEST_ASSERT_1(val == 1 || val == MMIO_VAL, val);
+
+	/* Spin until the re-aligning memory region move completes. */
 	val = guest_spin_on_val(MMIO_VAL);
 	GUEST_ASSERT_1(val == 1, val);