20 files changed, 125 insertions, 30 deletions

diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h
index 1f0a9ff23a2c..941deffc590d 100644
--- a/include/linux/alloc_tag.h
+++ b/include/linux/alloc_tag.h
@@ -135,18 +135,21 @@ static inline void alloc_tag_sub_check(union codetag_ref *ref) {}
 #endif
 
 /* Caller should verify both ref and tag to be valid */
-static inline void __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag)
+static inline bool __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag)
 {
 	alloc_tag_add_check(ref, tag);
 	if (!ref || !tag)
-		return;
+		return false;
 
 	ref->ct = &tag->ct;
+	return true;
 }
 
-static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag)
+static inline bool alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag)
 {
-	__alloc_tag_ref_set(ref, tag);
+	if (unlikely(!__alloc_tag_ref_set(ref, tag)))
+		return false;
+
 	/*
 	 * We need in increment the call counter every time we have a new
 	 * allocation or when we split a large allocation into smaller ones.
@@ -154,12 +157,13 @@ static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *t
 	 * counter because when we free each part the counter will be decremented.
 	 */
 	this_cpu_inc(tag->counters->calls);
+	return true;
 }
 
 static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes)
 {
-	alloc_tag_ref_set(ref, tag);
-	this_cpu_add(tag->counters->bytes, bytes);
+	if (likely(alloc_tag_ref_set(ref, tag)))
+		this_cpu_add(tag->counters->bytes, bytes);
 }
 
 static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes)
diff --git a/include/linux/backing-file.h b/include/linux/backing-file.h
index 4b61b0e57720..2eed0ffb5e8f 100644
--- a/include/linux/backing-file.h
+++ b/include/linux/backing-file.h
@@ -16,7 +16,7 @@ struct backing_file_ctx {
 	const struct cred *cred;
 	struct file *user_file;
 	void (*accessed)(struct file *);
-	void (*end_write)(struct file *);
+	void (*end_write)(struct file *, loff_t, ssize_t);
 };
 
 struct file *backing_file_open(const struct path *user_path, int flags,
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 19d8ca8ac960..bdadb0bb6cec 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -635,6 +635,7 @@ enum bpf_type_flag {
 	 */
 	PTR_UNTRUSTED		= BIT(6 + BPF_BASE_TYPE_BITS),
 
+	/* MEM can be uninitialized. */
 	MEM_UNINIT		= BIT(7 + BPF_BASE_TYPE_BITS),
 
 	/* DYNPTR points to memory local to the bpf program. */
@@ -700,6 +701,13 @@ enum bpf_type_flag {
 	 */
 	MEM_ALIGNED		= BIT(17 + BPF_BASE_TYPE_BITS),
 
+	/* MEM is being written to, often combined with MEM_UNINIT. Non-presence
+	 * of MEM_WRITE means that MEM is only being read. MEM_WRITE without the
+	 * MEM_UNINIT means that memory needs to be initialized since it is also
+	 * read.
+	 */
+	MEM_WRITE		= BIT(18 + BPF_BASE_TYPE_BITS),
+
 	__BPF_TYPE_FLAG_MAX,
 	__BPF_TYPE_LAST_FLAG	= __BPF_TYPE_FLAG_MAX - 1,
 };
@@ -758,10 +766,10 @@ enum bpf_arg_type {
 	ARG_PTR_TO_SOCKET_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET,
 	ARG_PTR_TO_STACK_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_STACK,
 	ARG_PTR_TO_BTF_ID_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID,
-	/* pointer to memory does not need to be initialized, helper function must fill
-	 * all bytes or clear them in error case.
+	/* Pointer to memory does not need to be initialized, since helper function
+	 * fills all bytes or clears them in error case.
 	 */
-	ARG_PTR_TO_UNINIT_MEM		= MEM_UNINIT | ARG_PTR_TO_MEM,
+	ARG_PTR_TO_UNINIT_MEM		= MEM_UNINIT | MEM_WRITE | ARG_PTR_TO_MEM,
 	/* Pointer to valid memory of size known at compile time. */
 	ARG_PTR_TO_FIXED_SIZE_MEM	= MEM_FIXED_SIZE | ARG_PTR_TO_MEM,
 
diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h
index aaf004d94322..e45162ef59bb 100644
--- a/include/linux/bpf_mem_alloc.h
+++ b/include/linux/bpf_mem_alloc.h
@@ -33,6 +33,9 @@ int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg
 int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size);
 void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma);
 
+/* Check the allocation size for kmalloc equivalent allocator */
+int bpf_mem_alloc_check_size(bool percpu, size_t size);
+
 /* kmalloc/kfree equivalent: */
 void *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size);
 void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr);
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 9f2a6b83b49e..fa78f49d4a9a 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -146,6 +146,7 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp)
 BPF_LINK_TYPE(BPF_LINK_TYPE_NETFILTER, netfilter)
 BPF_LINK_TYPE(BPF_LINK_TYPE_TCX, tcx)
 BPF_LINK_TYPE(BPF_LINK_TYPE_NETKIT, netkit)
+BPF_LINK_TYPE(BPF_LINK_TYPE_SOCKMAP, sockmap)
 #endif
 #ifdef CONFIG_PERF_EVENTS
 BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf)
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index f805adaa316e..cd6f9aae311f 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -80,7 +80,11 @@
 #define __noscs __attribute__((__no_sanitize__("shadow-call-stack")))
 #endif
 
+#ifdef __SANITIZE_HWADDRESS__
+#define __no_sanitize_address __attribute__((__no_sanitize__("hwaddress")))
+#else
 #define __no_sanitize_address __attribute__((__no_sanitize_address__))
+#endif
 
 #if defined(__SANITIZE_THREAD__)
 #define __no_sanitize_thread __attribute__((__no_sanitize_thread__))
diff --git a/include/linux/device.h b/include/linux/device.h
index b4bde8d22697..667cb6db9019 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1078,6 +1078,9 @@ int device_for_each_child(struct device *dev, void *data,
 			  int (*fn)(struct device *dev, void *data));
 int device_for_each_child_reverse(struct device *dev, void *data,
 				  int (*fn)(struct device *dev, void *data));
+int device_for_each_child_reverse_from(struct device *parent,
+				       struct device *from, const void *data,
+				       int (*fn)(struct device *, const void *));
 struct device *device_find_child(struct device *dev, void *data,
 				 int (*match)(struct device *dev, void *data));
 struct device *device_find_child_by_name(struct device *parent,
diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h
index c13e99cbbf81..4b4bfef6f053 100644
--- a/include/linux/fs_context.h
+++ b/include/linux/fs_context.h
@@ -160,6 +160,12 @@ extern int get_tree_keyed(struct fs_context *fc,
 
 int setup_bdev_super(struct super_block *sb, int sb_flags,
 		struct fs_context *fc);
+
+#define GET_TREE_BDEV_QUIET_LOOKUP		0x0001
+int get_tree_bdev_flags(struct fs_context *fc,
+		int (*fill_super)(struct super_block *sb,
+				  struct fs_context *fc), unsigned int flags);
+
 extern int get_tree_bdev(struct fs_context *fc,
 			       int (*fill_super)(struct super_block *sb,
 						 struct fs_context *fc));
diff --git a/include/linux/input.h b/include/linux/input.h
index 89a0be6ee0e2..cd866b020a01 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -339,12 +339,16 @@ struct input_handler {
  * @name: name given to the handle by handler that created it
  * @dev: input device the handle is attached to
  * @handler: handler that works with the device through this handle
+ * @handle_events: event sequence handler. It is set up by the input core
+ *	according to event handling method specified in the @handler. See
+ *	input_handle_setup_event_handler().
+ *	This method is being called by the input core with interrupts disabled
+ *	and dev->event_lock spinlock held and so it may not sleep.
  * @d_node: used to put the handle on device's list of attached handles
  * @h_node: used to put the handle on handler's list of handles from which
  *	it gets events
  */
 struct input_handle {
-
 	void *private;
 
 	int open;
@@ -353,6 +357,10 @@ struct input_handle {
 	struct input_dev *dev;
 	struct input_handler *handler;
 
+	unsigned int (*handle_events)(struct input_handle *handle,
+				      struct input_value *vals,
+				      unsigned int count);
+
 	struct list_head	d_node;
 	struct list_head	h_node;
 };
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index d0420e962ffd..f61407e3b121 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -270,6 +270,25 @@ static inline loff_t iomap_last_written_block(struct inode *inode, loff_t pos,
 	return round_up(pos + written, i_blocksize(inode));
 }
 
+/*
+ * Check if the range needs to be unshared for a FALLOC_FL_UNSHARE_RANGE
+ * operation.
+ *
+ * Don't bother with blocks that are not shared to start with; or mappings that
+ * cannot be shared, such as inline data, delalloc reservations, holes or
+ * unwritten extents.
+ *
+ * Note that we use srcmap directly instead of iomap_iter_srcmap as unsharing
+ * requires providing a separate source map, and the presence of one is a good
+ * indicator that unsharing is needed, unlike IOMAP_F_SHARED which can be set
+ * for any data that goes into the COW fork for XFS.
+ */
+static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter)
+{
+	return (iter->iomap.flags & IOMAP_F_SHARED) &&
+		iter->srcmap.type == IOMAP_MAPPED;
+}
+
 ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
 		const struct iomap_ops *ops, void *private);
 int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops);
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 11690dacd986..ec9c05044d4f 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -54,12 +54,11 @@ static inline long mm_ksm_zero_pages(struct mm_struct *mm)
 	return atomic_long_read(&mm->ksm_zero_pages);
 }
 
-static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
 {
+	/* Adding mm to ksm is best effort on fork. */
 	if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags))
-		return __ksm_enter(mm);
-
-	return 0;
+		__ksm_enter(mm);
 }
 
 static inline int ksm_execve(struct mm_struct *mm)
@@ -107,9 +106,8 @@ static inline int ksm_disable(struct mm_struct *mm)
 	return 0;
 }
 
-static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
 {
-	return 0;
 }
 
 static inline int ksm_execve(struct mm_struct *mm)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index db567d26f7b9..45be36e5285f 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1313,8 +1313,6 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 
 struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
 struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn);
-kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn);
-kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map);
 void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty);
 unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ecf63d2b0582..61fff5d34ed5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3818,8 +3818,9 @@ void *sparse_buffer_alloc(unsigned long size);
 struct page * __populate_section_memmap(unsigned long pfn,
 		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
 		struct dev_pagemap *pgmap);
-void pmd_init(void *addr);
 void pud_init(void *addr);
+void pmd_init(void *addr);
+void kernel_pte_init(void *addr);
 pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
 p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node);
 pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 17506e4a2835..5b1c984daf45 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -458,9 +458,7 @@ struct lru_gen_folio {
 
 enum {
 	MM_LEAF_TOTAL,		/* total leaf entries */
-	MM_LEAF_OLD,		/* old leaf entries */
 	MM_LEAF_YOUNG,		/* young leaf entries */
-	MM_NONLEAF_TOTAL,	/* total non-leaf entries */
 	MM_NONLEAF_FOUND,	/* non-leaf entries found in Bloom filters */
 	MM_NONLEAF_ADDED,	/* non-leaf entries added to Bloom filters */
 	NR_MM_STATS
@@ -557,7 +555,7 @@ struct lru_gen_memcg {
 
 void lru_gen_init_pgdat(struct pglist_data *pgdat);
 void lru_gen_init_lruvec(struct lruvec *lruvec);
-void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
+bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
 
 void lru_gen_init_memcg(struct mem_cgroup *memcg);
 void lru_gen_exit_memcg(struct mem_cgroup *memcg);
@@ -576,8 +574,9 @@ static inline void lru_gen_init_lruvec(struct lruvec *lruvec)
 {
 }
 
-static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
+static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 {
+	return false;
 }
 
 static inline void lru_gen_init_memcg(struct mem_cgroup *memcg)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4d20c776a4ff..8896705ccd63 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3325,6 +3325,12 @@ static inline void netif_tx_wake_all_queues(struct net_device *dev)
 
 static __always_inline void netif_tx_stop_queue(struct netdev_queue *dev_queue)
 {
+	/* Paired with READ_ONCE() from dev_watchdog() */
+	WRITE_ONCE(dev_queue->trans_start, jiffies);
+
+	/* This barrier is paired with smp_mb() from dev_watchdog() */
+	smp_mb__before_atomic();
+
 	/* Must be an atomic op see netif_txq_try_stop() */
 	set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
 }
@@ -3451,6 +3457,12 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue,
 	if (likely(dql_avail(&dev_queue->dql) >= 0))
 		return;
 
+	/* Paired with READ_ONCE() from dev_watchdog() */
+	WRITE_ONCE(dev_queue->trans_start, jiffies);
+
+	/* This barrier is paired with smp_mb() from dev_watchdog() */
+	smp_mb__before_atomic();
+
 	set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state);
 
 	/*
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 1b3a76710487..cc839e4365c1 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -975,12 +975,16 @@ static __always_inline bool folio_test_##fname(const struct folio *folio) \
 }									\
 static __always_inline void __folio_set_##fname(struct folio *folio)	\
 {									\
+	if (folio_test_##fname(folio))					\
+		return;							\
 	VM_BUG_ON_FOLIO(data_race(folio->page.page_type) != UINT_MAX,	\
 			folio);						\
 	folio->page.page_type = (unsigned int)PGTY_##lname << 24;	\
 }									\
 static __always_inline void __folio_clear_##fname(struct folio *folio)	\
 {									\
+	if (folio->page.page_type == UINT_MAX)				\
+		return;							\
 	VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio);		\
 	folio->page.page_type = UINT_MAX;				\
 }
@@ -993,11 +997,15 @@ static __always_inline int Page##uname(const struct page *page)		\
 }									\
 static __always_inline void __SetPage##uname(struct page *page)		\
 {									\
+	if (Page##uname(page))						\
+		return;							\
 	VM_BUG_ON_PAGE(data_race(page->page_type) != UINT_MAX, page);	\
 	page->page_type = (unsigned int)PGTY_##lname << 24;		\
 }									\
 static __always_inline void __ClearPage##uname(struct page *page)	\
 {									\
+	if (page->page_type == UINT_MAX)				\
+		return;							\
 	VM_BUG_ON_PAGE(!Page##uname(page), page);			\
 	page->page_type = UINT_MAX;					\
 }
diff --git a/include/linux/swap.h b/include/linux/swap.h
index ca533b478c21..f3e0ac20c2e8 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -335,6 +335,7 @@ struct swap_info_struct {
 					 * list.
 					 */
 	struct work_struct discard_work; /* discard worker */
+	struct work_struct reclaim_work; /* reclaim worker */
 	struct list_head discard_clusters; /* discard clusters list */
 	struct plist_node avail_lists[]; /*
 					   * entries in swap_avail_heads, one
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 72744638c5b0..99c9c5a7252a 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -251,12 +251,19 @@ static inline void tick_dep_set_task(struct task_struct *tsk,
 	if (tick_nohz_full_enabled())
 		tick_nohz_dep_set_task(tsk, bit);
 }
+
 static inline void tick_dep_clear_task(struct task_struct *tsk,
 				       enum tick_dep_bits bit)
 {
 	if (tick_nohz_full_enabled())
 		tick_nohz_dep_clear_task(tsk, bit);
 }
+
+static inline void tick_dep_init_task(struct task_struct *tsk)
+{
+	atomic_set(&tsk->tick_dep_mask, 0);
+}
+
 static inline void tick_dep_set_signal(struct task_struct *tsk,
 				       enum tick_dep_bits bit)
 {
@@ -290,6 +297,7 @@ static inline void tick_dep_set_task(struct task_struct *tsk,
 				     enum tick_dep_bits bit) { }
 static inline void tick_dep_clear_task(struct task_struct *tsk,
 				       enum tick_dep_bits bit) { }
+static inline void tick_dep_init_task(struct task_struct *tsk) { }
 static inline void tick_dep_set_signal(struct task_struct *tsk,
 				       enum tick_dep_bits bit) { }
 static inline void tick_dep_clear_signal(struct signal_struct *signal,
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 39c7cf82b0c2..43844510d5d0 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -38,6 +38,7 @@
 #else
  #define can_do_masked_user_access() 0
  #define masked_user_access_begin(src) NULL
+ #define mask_user_address(src) (src)
 #endif
 
 /*
@@ -159,19 +160,27 @@ _inline_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	unsigned long res = n;
 	might_fault();
-	if (!should_fail_usercopy() && likely(access_ok(from, n))) {
+	if (should_fail_usercopy())
+		goto fail;
+	if (can_do_masked_user_access())
+		from = mask_user_address(from);
+	else {
+		if (!access_ok(from, n))
+			goto fail;
 		/*
 		 * Ensure that bad access_ok() speculation will not
 		 * lead to nasty side effects *after* the copy is
 		 * finished:
 		 */
 		barrier_nospec();
-		instrument_copy_from_user_before(to, from, n);
-		res = raw_copy_from_user(to, from, n);
-		instrument_copy_from_user_after(to, from, n, res);
 	}
-	if (unlikely(res))
-		memset(to + (n - res), 0, res);
+	instrument_copy_from_user_before(to, from, n);
+	res = raw_copy_from_user(to, from, n);
+	instrument_copy_from_user_after(to, from, n, res);
+	if (likely(!res))
+		return 0;
+fail:
+	memset(to + (n - res), 0, res);
 	return res;
 }
 extern __must_check unsigned long
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 9fc6ce15c499..cb40f1a1d081 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -249,6 +249,7 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
 
 extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *);
 extern void dup_userfaultfd_complete(struct list_head *);
+void dup_userfaultfd_fail(struct list_head *);
 
 extern void mremap_userfaultfd_prep(struct vm_area_struct *,
 				    struct vm_userfaultfd_ctx *);
@@ -351,6 +352,10 @@ static inline void dup_userfaultfd_complete(struct list_head *l)
 {
 }
 
+static inline void dup_userfaultfd_fail(struct list_head *l)
+{
+}
+
 static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma,
 					   struct vm_userfaultfd_ctx *ctx)
 {