Merge tag 'v7.0-rc6' into irq/core

to be able to merge the hyper-v patch related to randomness.

38 files changed, 305 insertions, 145 deletions

diff --git a/include/linux/auxvec.h b/include/linux/auxvec.h
index 407f7005e6d6..8bcb9b726262 100644
--- a/include/linux/auxvec.h
+++ b/include/linux/auxvec.h
@@ -4,6 +4,6 @@
 
 #include <uapi/linux/auxvec.h>
 
-#define AT_VECTOR_SIZE_BASE 22 /* NEW_AUX_ENT entries in auxiliary table */
+#define AT_VECTOR_SIZE_BASE 24 /* NEW_AUX_ENT entries in auxiliary table */
   /* number of "#define AT_.*" above, minus {AT_NULL, AT_IGNORE, AT_NOTELF} */
 #endif /* _LINUX_AUXVEC_H */
diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h
index 2cfbb4c65c78..d3dc5dc5f916 100644
--- a/include/linux/build_bug.h
+++ b/include/linux/build_bug.h
@@ -32,7 +32,8 @@
 /**
  * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied
  *		      error message.
- * @condition: the condition which the compiler should know is false.
+ * @cond: the condition which the compiler should know is false.
+ * @msg: build-time error message
  *
  * See BUILD_BUG_ON for description.
  */
@@ -60,6 +61,7 @@
 
 /**
  * static_assert - check integer constant expression at build time
+ * @expr: expression to be checked
  *
  * static_assert() is a wrapper for the C11 _Static_assert, with a
  * little macro magic to make the message optional (defaulting to the
diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h
index 13b35637bd5a..d5ca855116df 100644
--- a/include/linux/console_struct.h
+++ b/include/linux/console_struct.h
@@ -160,6 +160,7 @@ struct vc_data {
 	struct uni_pagedict **uni_pagedict_loc; /* [!] Location of uni_pagedict variable for this console */
 	u32 **vc_uni_lines;			/* unicode screen content */
 	u16		*vc_saved_screen;
+	u32		**vc_saved_uni_lines;
 	unsigned int	vc_saved_cols;
 	unsigned int	vc_saved_rows;
 	/* additional information is in vt_kern.h */
diff --git a/include/linux/damon.h b/include/linux/damon.h
index a4fea23da857..be3d198043ff 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -810,6 +810,12 @@ struct damon_ctx {
 	struct damos_walk_control *walk_control;
 	struct mutex walk_control_lock;
 
+	/*
+	 * indicate if this may be corrupted.  Currentonly this is set only for
+	 * damon_commit_ctx() failure.
+	 */
+	bool maybe_corrupted;
+
 	/* Working thread of the given DAMON context */
 	struct task_struct *kdamond;
 	/* Protects @kdamond field access */
diff --git a/include/linux/device.h b/include/linux/device.h
index 0be95294b6e6..e65d564f01cd 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -483,6 +483,8 @@ struct device_physical_location {
  * 		on.  This shrinks the "Board Support Packages" (BSPs) and
  * 		minimizes board-specific #ifdefs in drivers.
  * @driver_data: Private pointer for driver specific info.
+ * @driver_override: Driver name to force a match.  Do not touch directly; use
+ *		     device_set_driver_override() instead.
  * @links:	Links to suppliers and consumers of this device.
  * @power:	For device power management.
  *		See Documentation/driver-api/pm/devices.rst for details.
@@ -576,6 +578,10 @@ struct device {
 					   core doesn't touch it */
 	void		*driver_data;	/* Driver data, set and get with
 					   dev_set_drvdata/dev_get_drvdata */
+	struct {
+		const char	*name;
+		spinlock_t	lock;
+	} driver_override;
 	struct mutex		mutex;	/* mutex to synchronize calls to
 					 * its driver.
 					 */
@@ -701,6 +707,54 @@ struct device_link {
 
 #define kobj_to_dev(__kobj)	container_of_const(__kobj, struct device, kobj)
 
+int __device_set_driver_override(struct device *dev, const char *s, size_t len);
+
+/**
+ * device_set_driver_override() - Helper to set or clear driver override.
+ * @dev: Device to change
+ * @s: NUL-terminated string, new driver name to force a match, pass empty
+ *     string to clear it ("" or "\n", where the latter is only for sysfs
+ *     interface).
+ *
+ * Helper to set or clear driver override of a device.
+ *
+ * Returns: 0 on success or a negative error code on failure.
+ */
+static inline int device_set_driver_override(struct device *dev, const char *s)
+{
+	return __device_set_driver_override(dev, s, s ? strlen(s) : 0);
+}
+
+/**
+ * device_has_driver_override() - Check if a driver override has been set.
+ * @dev: device to check
+ *
+ * Returns true if a driver override has been set for this device.
+ */
+static inline bool device_has_driver_override(struct device *dev)
+{
+	guard(spinlock)(&dev->driver_override.lock);
+	return !!dev->driver_override.name;
+}
+
+/**
+ * device_match_driver_override() - Match a driver against the device's driver_override.
+ * @dev: device to check
+ * @drv: driver to match against
+ *
+ * Returns > 0 if a driver override is set and matches the given driver, 0 if a
+ * driver override is set but does not match, or < 0 if a driver override is not
+ * set at all.
+ */
+static inline int device_match_driver_override(struct device *dev,
+					       const struct device_driver *drv)
+{
+	guard(spinlock)(&dev->driver_override.lock);
+	if (dev->driver_override.name)
+		return !strcmp(dev->driver_override.name, drv->name);
+	return -1;
+}
+
 /**
  * device_iommu_mapped - Returns true when the device DMA is translated
  *			 by an IOMMU
diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h
index 63de5f053c33..c1b463cd6464 100644
--- a/include/linux/device/bus.h
+++ b/include/linux/device/bus.h
@@ -65,6 +65,9 @@ struct fwnode_handle;
  *			this bus.
  * @pm:		Power management operations of this bus, callback the specific
  *		device driver's pm-ops.
+ * @driver_override:	Set to true if this bus supports the driver_override
+ *			mechanism, which allows userspace to force a specific
+ *			driver to bind to a device via a sysfs attribute.
  * @need_parent_lock:	When probing or removing a device on this bus, the
  *			device core should lock the device's parent.
  *
@@ -106,6 +109,7 @@ struct bus_type {
 
 	const struct dev_pm_ops *pm;
 
+	bool driver_override;
 	bool need_parent_lock;
 };
 
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 29973baa0581..99ef042ecdb4 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -80,11 +80,18 @@
 #define DMA_ATTR_MMIO		(1UL << 10)
 
 /*
- * DMA_ATTR_CPU_CACHE_CLEAN: Indicates the CPU will not dirty any cacheline
- * overlapping this buffer while it is mapped for DMA. All mappings sharing
- * a cacheline must have this attribute for this to be considered safe.
+ * DMA_ATTR_DEBUGGING_IGNORE_CACHELINES: Indicates the CPU cache line can be
+ * overlapped. All mappings sharing a cacheline must have this attribute for
+ * this to be considered safe.
  */
-#define DMA_ATTR_CPU_CACHE_CLEAN	(1UL << 11)
+#define DMA_ATTR_DEBUGGING_IGNORE_CACHELINES	(1UL << 11)
+
+/*
+ * DMA_ATTR_REQUIRE_COHERENT: Indicates that DMA coherency is required.
+ * All mappings that carry this attribute can't work with SWIOTLB and cache
+ * flushing.
+ */
+#define DMA_ATTR_REQUIRE_COHERENT	(1UL << 12)
 
 /*
  * A dma_addr_t can hold any valid DMA or bus address for the platform.  It can
@@ -248,8 +255,8 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size,
 {
 	return NULL;
 }
-static void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
-		dma_addr_t dma_handle, unsigned long attrs)
+static inline void dma_free_attrs(struct device *dev, size_t size,
+		void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
 {
 }
 static inline void *dmam_alloc_attrs(struct device *dev, size_t size,
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 9a1eacf35d37..df8f88f63a70 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -42,7 +42,8 @@ extern const struct header_ops eth_header_ops;
 
 int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type,
 	       const void *daddr, const void *saddr, unsigned len);
-int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr);
+int eth_header_parse(const struct sk_buff *skb, const struct net_device *dev,
+		     unsigned char *haddr);
 int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh,
 		     __be16 type);
 void eth_header_cache_update(struct hh_cache *hh, const struct net_device *dev,
diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h
index d290060f4c73..91013161e9db 100644
--- a/include/linux/firmware/intel/stratix10-svc-client.h
+++ b/include/linux/firmware/intel/stratix10-svc-client.h
@@ -68,12 +68,12 @@
  * timeout value used in Stratix10 FPGA manager driver.
  * timeout value used in RSU driver
  */
-#define SVC_RECONFIG_REQUEST_TIMEOUT_MS         300
-#define SVC_RECONFIG_BUFFER_TIMEOUT_MS          720
-#define SVC_RSU_REQUEST_TIMEOUT_MS              300
+#define SVC_RECONFIG_REQUEST_TIMEOUT_MS         5000
+#define SVC_RECONFIG_BUFFER_TIMEOUT_MS          5000
+#define SVC_RSU_REQUEST_TIMEOUT_MS              2000
 #define SVC_FCS_REQUEST_TIMEOUT_MS		2000
 #define SVC_COMPLETED_TIMEOUT_MS		30000
-#define SVC_HWMON_REQUEST_TIMEOUT_MS		300
+#define SVC_HWMON_REQUEST_TIMEOUT_MS		2000
 
 struct stratix10_svc_chan;
 
diff --git a/include/linux/fs/super_types.h b/include/linux/fs/super_types.h
index fa7638b81246..383050e7fdf5 100644
--- a/include/linux/fs/super_types.h
+++ b/include/linux/fs/super_types.h
@@ -338,5 +338,6 @@ struct super_block {
 #define SB_I_NOUMASK	0x00001000	/* VFS does not apply umask */
 #define SB_I_NOIDMAP	0x00002000	/* No idmapped mounts on this superblock */
 #define SB_I_ALLOW_HSM	0x00004000	/* Allow HSM events on this superblock */
+#define SB_I_NO_DATA_INTEGRITY	0x00008000 /* fs cannot guarantee data persistence on sync */
 
 #endif /* _LINUX_FS_SUPER_TYPES_H */
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 2990b9f94cb5..31324609af4d 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -682,6 +682,7 @@ struct hid_device {
 	__s32 battery_charge_status;
 	enum hid_battery_status battery_status;
 	bool battery_avoid_query;
+	bool battery_present;
 	ktime_t battery_ratelimit_time;
 #endif
 
diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h
index 61b7335aa037..ca9afa824aa4 100644
--- a/include/linux/if_ether.h
+++ b/include/linux/if_ether.h
@@ -40,7 +40,8 @@ static inline struct ethhdr *inner_eth_hdr(const struct sk_buff *skb)
 	return (struct ethhdr *)skb_inner_mac_header(skb);
 }
 
-int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr);
+int eth_header_parse(const struct sk_buff *skb, const struct net_device *dev,
+		     unsigned char *haddr);
 
 extern ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len);
 
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 7a1516011ccf..e19872e37e06 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -53,7 +53,7 @@ struct iommu_flush_ops {
  *                 tables.
  * @ias:           Input address (iova) size, in bits.
  * @oas:           Output address (paddr) size, in bits.
- * @coherent_walk  A flag to indicate whether or not page table walks made
+ * @coherent_walk: A flag to indicate whether or not page table walks made
  *                 by the IOMMU are coherent with the CPU caches.
  * @tlb:           TLB management callbacks for this set of tables.
  * @iommu_dev:     The device representing the DMA configuration for the
@@ -136,6 +136,7 @@ struct io_pgtable_cfg {
 	void (*free)(void *cookie, void *pages, size_t size);
 
 	/* Low-level data specific to the table format */
+	/* private: */
 	union {
 		struct {
 			u64	ttbr;
@@ -203,6 +204,9 @@ struct arm_lpae_io_pgtable_walk_data {
  * @unmap_pages:  Unmap a range of virtually contiguous pages of the same size.
  * @iova_to_phys: Translate iova to physical address.
  * @pgtable_walk: (optional) Perform a page table walk for a given iova.
+ * @read_and_clear_dirty: Record dirty info per IOVA. If an IOVA is dirty,
+ *			  clear its dirty state from the PTE unless the
+ *			  IOMMU_DIRTY_NO_CLEAR flag is passed in.
  *
  * These functions map directly onto the iommu_ops member functions with
  * the same names.
@@ -231,7 +235,9 @@ struct io_pgtable_ops {
  *          the configuration actually provided by the allocator (e.g. the
  *          pgsize_bitmap may be restricted).
  * @cookie: An opaque token provided by the IOMMU driver and passed back to
- *          the callback routines in cfg->tlb.
+ *          the callback routines.
+ *
+ * Returns: Pointer to the &struct io_pgtable_ops for this set of page tables.
  */
 struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt,
 					    struct io_pgtable_cfg *cfg,
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 3e4a82a6f817..214fdbd49052 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -388,6 +388,7 @@ struct io_ring_ctx {
 	 * regularly bounce b/w CPUs.
 	 */
 	struct {
+		struct io_rings	__rcu	*rings_rcu;
 		struct llist_head	work_llist;
 		struct llist_head	retry_llist;
 		unsigned long		check_cq;
@@ -540,6 +541,7 @@ enum {
 	REQ_F_BL_NO_RECYCLE_BIT,
 	REQ_F_BUFFERS_COMMIT_BIT,
 	REQ_F_BUF_NODE_BIT,
+	REQ_F_BUF_MORE_BIT,
 	REQ_F_HAS_METADATA_BIT,
 	REQ_F_IMPORT_BUFFER_BIT,
 	REQ_F_SQE_COPIED_BIT,
@@ -625,6 +627,8 @@ enum {
 	REQ_F_BUFFERS_COMMIT	= IO_REQ_FLAG(REQ_F_BUFFERS_COMMIT_BIT),
 	/* buf node is valid */
 	REQ_F_BUF_NODE		= IO_REQ_FLAG(REQ_F_BUF_NODE_BIT),
+	/* incremental buffer consumption, more space available */
+	REQ_F_BUF_MORE		= IO_REQ_FLAG(REQ_F_BUF_MORE_BIT),
 	/* request has read/write metadata assigned */
 	REQ_F_HAS_METADATA	= IO_REQ_FLAG(REQ_F_HAS_METADATA_BIT),
 	/*
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 443053a76dcf..a7421382a916 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -333,7 +333,12 @@ struct tcp6_timewait_sock {
 };
 
 #if IS_ENABLED(CONFIG_IPV6)
-bool ipv6_mod_enabled(void);
+extern int disable_ipv6_mod;
+
+static inline bool ipv6_mod_enabled(void)
+{
+	return disable_ipv6_mod == 0;
+}
 
 static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk)
 {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 34759a262b28..6b76e7a6f4c2 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1940,56 +1940,43 @@ enum kvm_stat_kind {
 
 struct kvm_stat_data {
 	struct kvm *kvm;
-	const struct _kvm_stats_desc *desc;
+	const struct kvm_stats_desc *desc;
 	enum kvm_stat_kind kind;
 };
 
-struct _kvm_stats_desc {
-	struct kvm_stats_desc desc;
-	char name[KVM_STATS_NAME_SIZE];
-};
-
-#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz)		       \
-	.flags = type | unit | base |					       \
-		 BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) |	       \
-		 BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) |	       \
-		 BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK),	       \
-	.exponent = exp,						       \
-	.size = sz,							       \
+#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz)		\
+	.flags = type | unit | base |					\
+		 BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) |       \
+		 BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) |	\
+		 BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK),	\
+	.exponent = exp,						\
+	.size = sz,							\
 	.bucket_size = bsz
 
-#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz)	       \
-	{								       \
-		{							       \
-			STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),     \
-			.offset = offsetof(struct kvm_vm_stat, generic.stat)   \
-		},							       \
-		.name = #stat,						       \
-	}
-#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz)	       \
-	{								       \
-		{							       \
-			STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),     \
-			.offset = offsetof(struct kvm_vcpu_stat, generic.stat) \
-		},							       \
-		.name = #stat,						       \
-	}
-#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz)		       \
-	{								       \
-		{							       \
-			STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),     \
-			.offset = offsetof(struct kvm_vm_stat, stat)	       \
-		},							       \
-		.name = #stat,						       \
-	}
-#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz)		       \
-	{								       \
-		{							       \
-			STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),     \
-			.offset = offsetof(struct kvm_vcpu_stat, stat)	       \
-		},							       \
-		.name = #stat,						       \
-	}
+#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz)	\
+{									\
+	STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),		\
+	.offset = offsetof(struct kvm_vm_stat, generic.stat),		\
+	.name = #stat,							\
+}
+#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz)	\
+{									\
+	STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),		\
+	.offset = offsetof(struct kvm_vcpu_stat, generic.stat),		\
+	.name = #stat,							\
+}
+#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz)		\
+{									\
+	STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),		\
+	.offset = offsetof(struct kvm_vm_stat, stat),			\
+	.name = #stat,							\
+}
+#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz)		\
+{									\
+	STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),		\
+	.offset = offsetof(struct kvm_vcpu_stat, stat),			\
+	.name = #stat,							\
+}
 /* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */
 #define STATS_DESC(SCOPE, stat, type, unit, base, exp, sz, bsz)		       \
 	SCOPE##_STATS_DESC(stat, type, unit, base, exp, sz, bsz)
@@ -2066,7 +2053,7 @@ struct _kvm_stats_desc {
 	STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking)
 
 ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header,
-		       const struct _kvm_stats_desc *desc,
+		       const struct kvm_stats_desc *desc,
 		       void *stats, size_t size_stats,
 		       char __user *user_buffer, size_t size, loff_t *offset);
 
@@ -2111,9 +2098,9 @@ static inline void kvm_stats_log_hist_update(u64 *data, size_t size, u64 value)
 
 
 extern const struct kvm_stats_header kvm_vm_stats_header;
-extern const struct _kvm_stats_desc kvm_vm_stats_desc[];
+extern const struct kvm_stats_desc kvm_vm_stats_desc[];
 extern const struct kvm_stats_header kvm_vcpu_stats_header;
-extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[];
+extern const struct kvm_stats_desc kvm_vcpu_stats_desc[];
 
 static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
 {
diff --git a/include/linux/leafops.h b/include/linux/leafops.h
index a9ff94b744f2..05673d3529e7 100644
--- a/include/linux/leafops.h
+++ b/include/linux/leafops.h
@@ -363,6 +363,23 @@ static inline unsigned long softleaf_to_pfn(softleaf_t entry)
 	return swp_offset(entry) & SWP_PFN_MASK;
 }
 
+static inline void softleaf_migration_sync(softleaf_t entry,
+		struct folio *folio)
+{
+	/*
+	 * Ensure we do not race with split, which might alter tail pages into new
+	 * folios and thus result in observing an unlocked folio.
+	 * This matches the write barrier in __split_folio_to_order().
+	 */
+	smp_rmb();
+
+	/*
+	 * Any use of migration entries may only occur while the
+	 * corresponding page is locked
+	 */
+	VM_WARN_ON_ONCE(!folio_test_locked(folio));
+}
+
 /**
  * softleaf_to_page() - Obtains struct page for PFN encoded within leaf entry.
  * @entry: Leaf entry, softleaf_has_pfn(@entry) must return true.
@@ -374,11 +391,8 @@ static inline struct page *softleaf_to_page(softleaf_t entry)
 	struct page *page = pfn_to_page(softleaf_to_pfn(entry));
 
 	VM_WARN_ON_ONCE(!softleaf_has_pfn(entry));
-	/*
-	 * Any use of migration entries may only occur while the
-	 * corresponding page is locked
-	 */
-	VM_WARN_ON_ONCE(softleaf_is_migration(entry) && !PageLocked(page));
+	if (softleaf_is_migration(entry))
+		softleaf_migration_sync(entry, page_folio(page));
 
 	return page;
 }
@@ -394,12 +408,8 @@ static inline struct folio *softleaf_to_folio(softleaf_t entry)
 	struct folio *folio = pfn_folio(softleaf_to_pfn(entry));
 
 	VM_WARN_ON_ONCE(!softleaf_has_pfn(entry));
-	/*
-	 * Any use of migration entries may only occur while the
-	 * corresponding folio is locked.
-	 */
-	VM_WARN_ON_ONCE(softleaf_is_migration(entry) &&
-			!folio_test_locked(folio));
+	if (softleaf_is_migration(entry))
+		softleaf_migration_sync(entry, folio);
 
 	return folio;
 }
diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h
index eff711bf973f..234be7f12c15 100644
--- a/include/linux/local_lock_internal.h
+++ b/include/linux/local_lock_internal.h
@@ -315,7 +315,7 @@ do {								\
 
 #endif /* CONFIG_PREEMPT_RT */
 
-#if defined(WARN_CONTEXT_ANALYSIS)
+#if defined(WARN_CONTEXT_ANALYSIS) && !defined(__CHECKER__)
 /*
  * Because the compiler only knows about the base per-CPU variable, use this
  * helper function to make the compiler think we lock/unlock the @base variable,
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 0fe96f3ab3ef..65c732d440d2 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -55,6 +55,7 @@ struct mempolicy {
 		nodemask_t cpuset_mems_allowed;	/* relative to these nodes */
 		nodemask_t user_nodemask;	/* nodemask passed by user */
 	} w;
+	struct rcu_head rcu;
 };
 
 /*
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5be3d8a8f806..abb4963c1f06 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3514,26 +3514,21 @@ static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; }
 static inline void ptlock_free(struct ptdesc *ptdesc) {}
 #endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */
 
-static inline unsigned long ptdesc_nr_pages(const struct ptdesc *ptdesc)
-{
-	return compound_nr(ptdesc_page(ptdesc));
-}
-
 static inline void __pagetable_ctor(struct ptdesc *ptdesc)
 {
-	pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags));
+	struct folio *folio = ptdesc_folio(ptdesc);
 
-	__SetPageTable(ptdesc_page(ptdesc));
-	mod_node_page_state(pgdat, NR_PAGETABLE, ptdesc_nr_pages(ptdesc));
+	__folio_set_pgtable(folio);
+	lruvec_stat_add_folio(folio, NR_PAGETABLE);
 }
 
 static inline void pagetable_dtor(struct ptdesc *ptdesc)
 {
-	pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags));
+	struct folio *folio = ptdesc_folio(ptdesc);
 
 	ptlock_free(ptdesc);
-	__ClearPageTable(ptdesc_page(ptdesc));
-	mod_node_page_state(pgdat, NR_PAGETABLE, -ptdesc_nr_pages(ptdesc));
+	__folio_clear_pgtable(folio);
+	lruvec_stat_sub_folio(folio, NR_PAGETABLE);
 }
 
 static inline void pagetable_dtor_free(struct ptdesc *ptdesc)
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 07a2bbaf86e9..8450e18a87c2 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -234,7 +234,7 @@ struct mmu_notifier {
 };
 
 /**
- * struct mmu_interval_notifier_ops
+ * struct mmu_interval_notifier_ops - callback for range notification
  * @invalidate: Upon return the caller must stop using any SPTEs within this
  *              range. This function can sleep. Return false only if sleeping
  *              was required but mmu_notifier_range_blockable(range) is false.
@@ -309,8 +309,8 @@ void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub);
 
 /**
  * mmu_interval_set_seq - Save the invalidation sequence
- * @interval_sub - The subscription passed to invalidate
- * @cur_seq - The cur_seq passed to the invalidate() callback
+ * @interval_sub: The subscription passed to invalidate
+ * @cur_seq: The cur_seq passed to the invalidate() callback
  *
  * This must be called unconditionally from the invalidate callback of a
  * struct mmu_interval_notifier_ops under the same lock that is used to call
@@ -329,8 +329,8 @@ mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub,
 
 /**
  * mmu_interval_read_retry - End a read side critical section against a VA range
- * interval_sub: The subscription
- * seq: The return of the paired mmu_interval_read_begin()
+ * @interval_sub: The subscription
+ * @seq: The return of the paired mmu_interval_read_begin()
  *
  * This MUST be called under a user provided lock that is also held
  * unconditionally by op->invalidate() when it calls mmu_interval_set_seq().
@@ -338,7 +338,7 @@ mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub,
  * Each call should be paired with a single mmu_interval_read_begin() and
  * should be used to conclude the read side.
  *
- * Returns true if an invalidation collided with this critical section, and
+ * Returns: true if an invalidation collided with this critical section, and
  * the caller should retry.
  */
 static inline bool
@@ -350,20 +350,21 @@ mmu_interval_read_retry(struct mmu_interval_notifier *interval_sub,
 
 /**
  * mmu_interval_check_retry - Test if a collision has occurred
- * interval_su