Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR (net-6.13-rc7).

Conflicts:
  a42d71e322a8 ("net_sched: sch_cake: Add drop reasons")
  737d4d91d35b ("sched: sch_cake: add bounds checks to host bulk flow fairness counts")

Adjacent changes:

drivers/net/ethernet/meta/fbnic/fbnic.h
  3a856ab34726 ("eth: fbnic: add IRQ reuse support")
  95978931d55f ("eth: fbnic: Revert "eth: fbnic: Add hardware monitoring support via HWMON interface"")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

9 files changed, 101 insertions, 30 deletions

diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h
index 0d5448c0b86c..a3ce553413de 100644
--- a/include/linux/io_uring/cmd.h
+++ b/include/linux/io_uring/cmd.h
@@ -18,6 +18,11 @@ struct io_uring_cmd {
 	u8		pdu[32]; /* available inline for free use */
 };
 
+struct io_uring_cmd_data {
+	struct io_uring_sqe	sqes[2];
+	void			*op_data;
+};
+
 static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe)
 {
 	return sqe->cmd;
@@ -113,4 +118,9 @@ static inline struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd
 	return cmd_to_io_kiocb(cmd)->tctx->task;
 }
 
+static inline struct io_uring_cmd_data *io_uring_cmd_get_async_data(struct io_uring_cmd *cmd)
+{
+	return cmd_to_io_kiocb(cmd)->async_data;
+}
+
 #endif /* _LINUX_IO_URING_CMD_H */
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 5675af6b740c..75bf54e76f3b 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -335,7 +335,7 @@ struct iomap_ioend {
 	u16			io_type;
 	u16			io_flags;	/* IOMAP_F_* */
 	struct inode		*io_inode;	/* file being written to */
-	size_t			io_size;	/* size of the extent */
+	size_t			io_size;	/* size of data within eof */
 	loff_t			io_offset;	/* offset in the file */
 	sector_t		io_sector;	/* start sector of ioend */
 	struct bio		io_bio;		/* MUST BE LAST! */
diff --git a/include/linux/memfd.h b/include/linux/memfd.h
index 3f2cf339ceaf..d437e3070850 100644
--- a/include/linux/memfd.h
+++ b/include/linux/memfd.h
@@ -7,6 +7,7 @@
 #ifdef CONFIG_MEMFD_CREATE
 extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg);
 struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx);
+unsigned int *memfd_file_seals_ptr(struct file *file);
 #else
 static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a)
 {
@@ -16,6 +17,19 @@ static inline struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx)
 {
 	return ERR_PTR(-EINVAL);
 }
+
+static inline unsigned int *memfd_file_seals_ptr(struct file *file)
+{
+	return NULL;
+}
 #endif
 
+/* Retrieve memfd seals associated with the file, if any. */
+static inline unsigned int memfd_file_seals(struct file *file)
+{
+	unsigned int *sealsp = memfd_file_seals_ptr(file);
+
+	return sealsp ? *sealsp : 0;
+}
+
 #endif /* __LINUX_MEMFD_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 338a76ce9083..b1c3db9cf355 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3125,6 +3125,7 @@ static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc)
 	if (!pmd_ptlock_init(ptdesc))
 		return false;
 	__folio_set_pgtable(folio);
+	ptdesc_pmd_pts_init(ptdesc);
 	lruvec_stat_add_folio(folio, NR_PAGETABLE);
 	return true;
 }
@@ -4101,6 +4102,37 @@ void mem_dump_obj(void *object);
 static inline void mem_dump_obj(void *object) {}
 #endif
 
+static inline bool is_write_sealed(int seals)
+{
+	return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE);
+}
+
+/**
+ * is_readonly_sealed - Checks whether write-sealed but mapped read-only,
+ *                      in which case writes should be disallowing moving
+ *                      forwards.
+ * @seals: the seals to check
+ * @vm_flags: the VMA flags to check
+ *
+ * Returns whether readonly sealed, in which case writess should be disallowed
+ * going forward.
+ */
+static inline bool is_readonly_sealed(int seals, vm_flags_t vm_flags)
+{
+	/*
+	 * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as
+	 * MAP_SHARED and read-only, take care to not allow mprotect to
+	 * revert protections on such mappings. Do this only for shared
+	 * mappings. For private mappings, don't need to mask
+	 * VM_MAYWRITE as we still want them to be COW-writable.
+	 */
+	if (is_write_sealed(seals) &&
+	    ((vm_flags & (VM_SHARED | VM_WRITE)) == VM_SHARED))
+		return true;
+
+	return false;
+}
+
 /**
  * seal_check_write - Check for F_SEAL_WRITE or F_SEAL_FUTURE_WRITE flags and
  *                    handle them.
@@ -4112,24 +4144,15 @@ static inline void mem_dump_obj(void *object) {}
  */
 static inline int seal_check_write(int seals, struct vm_area_struct *vma)
 {
-	if (seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) {
-		/*
-		 * New PROT_WRITE and MAP_SHARED mmaps are not allowed when
-		 * write seals are active.
-		 */
-		if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE))
-			return -EPERM;
-
-		/*
-		 * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as
-		 * MAP_SHARED and read-only, take care to not allow mprotect to
-		 * revert protections on such mappings. Do this only for shared
-		 * mappings. For private mappings, don't need to mask
-		 * VM_MAYWRITE as we still want them to be COW-writable.
-		 */
-		if (vma->vm_flags & VM_SHARED)
-			vm_flags_clear(vma, VM_MAYWRITE);
-	}
+	if (!is_write_sealed(seals))
+		return 0;
+
+	/*
+	 * New PROT_WRITE and MAP_SHARED mmaps are not allowed when
+	 * write seals are active.
+	 */
+	if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE))
+		return -EPERM;
 
 	return 0;
 }
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 7361a8f3ab68..332cee285662 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -445,6 +445,7 @@ FOLIO_MATCH(compound_head, _head_2a);
  * @pt_index:         Used for s390 gmap.
  * @pt_mm:            Used for x86 pgds.
  * @pt_frag_refcount: For fragmented page table tracking. Powerpc only.
+ * @pt_share_count:   Used for HugeTLB PMD page table share count.
  * @_pt_pad_2:        Padding to ensure proper alignment.
  * @ptl:              Lock for the page table.
  * @__page_type:      Same as page->page_type. Unused for page tables.
@@ -471,6 +472,9 @@ struct ptdesc {
 		pgoff_t pt_index;
 		struct mm_struct *pt_mm;
 		atomic_t pt_frag_refcount;
+#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING
+		atomic_t pt_share_count;
+#endif
 	};
 
 	union {
@@ -516,6 +520,32 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page));
 	const struct page *:		(const struct ptdesc *)(p),	\
 	struct page *:			(struct ptdesc *)(p)))
 
+#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING
+static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc)
+{
+	atomic_set(&ptdesc->pt_share_count, 0);
+}
+
+static inline void ptdesc_pmd_pts_inc(struct ptdesc *ptdesc)
+{
+	atomic_inc(&ptdesc->pt_share_count);
+}
+
+static inline void ptdesc_pmd_pts_dec(struct ptdesc *ptdesc)
+{
+	atomic_dec(&ptdesc->pt_share_count);
+}
+
+static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc)
+{
+	return atomic_read(&ptdesc->pt_share_count);
+}
+#else
+static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc)
+{
+}
+#endif
+
 /*
  * Used for sizing the vmemmap region on some architectures
  */
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 5eaceef41e6c..ecdd5ced16a8 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -185,6 +185,7 @@ struct netfs_io_subrequest {
 	short			error;		/* 0 or error that occurred */
 	unsigned short		debug_index;	/* Index in list (for debugging output) */
 	unsigned int		nr_segs;	/* Number of segs in io_iter */
+	u8			retry_count;	/* The number of retries (0 on initial pass) */
 	enum netfs_io_source	source;		/* Where to read from/write to */
 	unsigned char		stream_nr;	/* I/O stream this belongs to */
 	unsigned char		curr_folioq_slot; /* Folio currently being read */
@@ -194,14 +195,13 @@ struct netfs_io_subrequest {
 #define NETFS_SREQ_COPY_TO_CACHE	0	/* Set if should copy the data to the cache */
 #define NETFS_SREQ_CLEAR_TAIL		1	/* Set if the rest of the read should be cleared */
 #define NETFS_SREQ_SEEK_DATA_READ	3	/* Set if ->read() should SEEK_DATA first */
-#define NETFS_SREQ_NO_PROGRESS		4	/* Set if we didn't manage to read any data */
+#define NETFS_SREQ_MADE_PROGRESS	4	/* Set if we transferred at least some data */
 #define NETFS_SREQ_ONDEMAND		5	/* Set if it's from on-demand read mode */
 #define NETFS_SREQ_BOUNDARY		6	/* Set if ends on hard boundary (eg. ceph object) */
 #define NETFS_SREQ_HIT_EOF		7	/* Set if short due to EOF */
 #define NETFS_SREQ_IN_PROGRESS		8	/* Unlocked when the subrequest completes */
 #define NETFS_SREQ_NEED_RETRY		9	/* Set if the filesystem requests a retry */
-#define NETFS_SREQ_RETRYING		10	/* Set if we're retrying */
-#define NETFS_SREQ_FAILED		11	/* Set if the subreq failed unretryably */
+#define NETFS_SREQ_FAILED		10	/* Set if the subreq failed unretryably */
 };
 
 enum netfs_io_origin {
@@ -269,7 +269,6 @@ struct netfs_io_request {
 	size_t			prev_donated;	/* Fallback for subreq->prev_donated */
 	refcount_t		ref;
 	unsigned long		flags;
-#define NETFS_RREQ_COPY_TO_CACHE	1	/* Need to write to the cache */
 #define NETFS_RREQ_NO_UNLOCK_FOLIO	2	/* Don't unlock no_unlock_folio on completion */
 #define NETFS_RREQ_DONT_UNLOCK_FOLIOS	3	/* Don't unlock the folios on completion */
 #define NETFS_RREQ_FAILED		4	/* The request failed */
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 35842d1e3879..5b520fe86b60 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -221,10 +221,7 @@ do {									\
 } while (0)
 
 #define PERCPU_PTR(__p)							\
-({									\
-	unsigned long __pcpu_ptr = (__force unsigned long)(__p);	\
-	(typeof(*(__p)) __force __kernel *)(__pcpu_ptr);		\
-})
+	(typeof(*(__p)) __force __kernel *)((__force unsigned long)(__p))
 
 #ifdef CONFIG_SMP
 
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 3c82fad904d4..c7f42844c79a 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -282,7 +282,7 @@ static inline int inet_csk_reqsk_queue_len(const struct sock *sk)
 
 static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk)
 {
-	return inet_csk_reqsk_queue_len(sk) >= READ_ONCE(sk->sk_max_ack_backlog);
+	return inet_csk_reqsk_queue_len(sk) > READ_ONCE(sk->sk_max_ack_backlog);
 }
 
 bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req);
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index d650ae6b58d3..74e5b9960c54 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -329,7 +329,6 @@ struct ufs_pwr_mode_info {
  * @program_key: program or evict an inline encryption key
  * @fill_crypto_prdt: initialize crypto-related fields in the PRDT
  * @event_notify: called to notify important events
- * @reinit_notify: called to notify reinit of UFSHCD during max gear switch
  * @mcq_config_resource: called to configure MCQ platform resources
  * @get_hba_mac: reports maximum number of outstanding commands supported by
  *	the controller. Should be implemented for UFSHCI 4.0 or later
@@ -381,7 +380,6 @@ struct ufs_hba_variant_ops {
 				    void *prdt, unsigned int num_segments);
 	void	(*event_notify)(struct ufs_hba *hba,
 				enum ufs_event_type evt, void *data);
-	void	(*reinit_notify)(struct ufs_hba *);
 	int	(*mcq_config_resource)(struct ufs_hba *hba);
 	int	(*get_hba_mac)(struct ufs_hba *hba);
 	int	(*op_runtime_config)(struct ufs_hba *hba);