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

drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
 - keep the ZC code, drop the code related to reinit
net/bridge/netfilter/ebtables.c
 - fix build after move to net_generic

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

5 files changed, 57 insertions, 27 deletions

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 1f972b75a9ab..eeb3ebe11d7a 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -21,9 +21,30 @@
 /* Pseudo write pointer value for conventional zone */
 #define WP_CONVENTIONAL ((u64)-2)
 
+/*
+ * Location of the first zone of superblock logging zone pairs.
+ *
+ * - primary superblock:    0B (zone 0)
+ * - first copy:          512G (zone starting at that offset)
+ * - second copy:           4T (zone starting at that offset)
+ */
+#define BTRFS_SB_LOG_PRIMARY_OFFSET	(0ULL)
+#define BTRFS_SB_LOG_FIRST_OFFSET	(512ULL * SZ_1G)
+#define BTRFS_SB_LOG_SECOND_OFFSET	(4096ULL * SZ_1G)
+
+#define BTRFS_SB_LOG_FIRST_SHIFT	const_ilog2(BTRFS_SB_LOG_FIRST_OFFSET)
+#define BTRFS_SB_LOG_SECOND_SHIFT	const_ilog2(BTRFS_SB_LOG_SECOND_OFFSET)
+
 /* Number of superblock log zones */
 #define BTRFS_NR_SB_LOG_ZONES 2
 
+/*
+ * Maximum supported zone size. Currently, SMR disks have a zone size of
+ * 256MiB, and we are expecting ZNS drives to be in the 1-4GiB range. We do not
+ * expect the zone size to become larger than 8GiB in the near future.
+ */
+#define BTRFS_MAX_ZONE_SIZE		SZ_8G
+
 static int copy_zone_info_cb(struct blk_zone *zone, unsigned int idx, void *data)
 {
 	struct blk_zone *zones = data;
@@ -111,23 +132,22 @@ static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones,
 }
 
 /*
- * The following zones are reserved as the circular buffer on ZONED btrfs.
- *  - The primary superblock: zones 0 and 1
- *  - The first copy: zones 16 and 17
- *  - The second copy: zones 1024 or zone at 256GB which is minimum, and
- *                     the following one
+ * Get the first zone number of the superblock mirror
  */
 static inline u32 sb_zone_number(int shift, int mirror)
 {
-	ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX);
+	u64 zone;
 
+	ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX);
 	switch (mirror) {
-	case 0: return 0;
-	case 1: return 16;
-	case 2: return min_t(u64, btrfs_sb_offset(mirror) >> shift, 1024);
+	case 0: zone = 0; break;
+	case 1: zone = 1ULL << (BTRFS_SB_LOG_FIRST_SHIFT - shift); break;
+	case 2: zone = 1ULL << (BTRFS_SB_LOG_SECOND_SHIFT - shift); break;
 	}
 
-	return 0;
+	ASSERT(zone <= U32_MAX);
+
+	return (u32)zone;
 }
 
 /*
@@ -300,10 +320,21 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device)
 		zone_sectors = bdev_zone_sectors(bdev);
 	}
 
-	nr_sectors = bdev_nr_sectors(bdev);
 	/* Check if it's power of 2 (see is_power_of_2) */
 	ASSERT(zone_sectors != 0 && (zone_sectors & (zone_sectors - 1)) == 0);
 	zone_info->zone_size = zone_sectors << SECTOR_SHIFT;
+
+	/* We reject devices with a zone size larger than 8GB */
+	if (zone_info->zone_size > BTRFS_MAX_ZONE_SIZE) {
+		btrfs_err_in_rcu(fs_info,
+		"zoned: %s: zone size %llu larger than supported maximum %llu",
+				 rcu_str_deref(device->name),
+				 zone_info->zone_size, BTRFS_MAX_ZONE_SIZE);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	nr_sectors = bdev_nr_sectors(bdev);
 	zone_info->zone_size_shift = ilog2(zone_info->zone_size);
 	zone_info->max_zone_append_size =
 		(u64)queue_max_zone_append_sectors(queue) << SECTOR_SHIFT;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index b61491bf3166..b2e86e739d7a 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -812,6 +812,7 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
 		    struct buffer_head *map_bh)
 {
 	int ret = 0;
+	int boundary = sdio->boundary;	/* dio_send_cur_page may clear it */
 
 	if (dio->op == REQ_OP_WRITE) {
 		/*
@@ -850,10 +851,10 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
 	sdio->cur_page_fs_offset = sdio->block_in_file << sdio->blkbits;
 out:
 	/*
-	 * If sdio->boundary then we want to schedule the IO now to
+	 * If boundary then we want to schedule the IO now to
 	 * avoid metadata seeks.
 	 */
-	if (sdio->boundary) {
+	if (boundary) {
 		ret = dio_send_cur_page(dio, sdio, map_bh);
 		if (sdio->bio)
 			dio_bio_submit(dio, sdio);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index bd14327c8e7e..dff34975d86b 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -6754,6 +6754,9 @@ static int io_sq_thread(void *data)
 	current->flags |= PF_NO_SETAFFINITY;
 
 	mutex_lock(&sqd->lock);
+	/* a user may had exited before the thread started */
+	io_run_task_work_head(&sqd->park_task_work);
+
 	while (!test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state)) {
 		int ret;
 		bool cap_entries, sqt_spin, needs_sched;
@@ -6770,10 +6773,10 @@ static int io_sq_thread(void *data)
 			}
 			cond_resched();
 			mutex_lock(&sqd->lock);
-			if (did_sig)
-				break;
 			io_run_task_work();
 			io_run_task_work_head(&sqd->park_task_work);
+			if (did_sig)
+				break;
 			timeout = jiffies + sqd->sq_thread_idle;
 			continue;
 		}
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 3bfb4147895a..ad20403b383f 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -2295,7 +2295,7 @@ static int ocfs2_dio_end_io_write(struct inode *inode,
 	struct ocfs2_alloc_context *meta_ac = NULL;
 	handle_t *handle = NULL;
 	loff_t end = offset + bytes;
-	int ret = 0, credits = 0, locked = 0;
+	int ret = 0, credits = 0;
 
 	ocfs2_init_dealloc_ctxt(&dealloc);
 
@@ -2306,13 +2306,6 @@ static int ocfs2_dio_end_io_write(struct inode *inode,
 	    !dwc->dw_orphaned)
 		goto out;
 
-	/* ocfs2_file_write_iter will get i_mutex, so we need not lock if we
-	 * are in that context. */
-	if (dwc->dw_writer_pid != task_pid_nr(current)) {
-		inode_lock(inode);
-		locked = 1;
-	}
-
 	ret = ocfs2_inode_lock(inode, &di_bh, 1);
 	if (ret < 0) {
 		mlog_errno(ret);
@@ -2393,8 +2386,6 @@ out:
 	if (meta_ac)
 		ocfs2_free_alloc_context(meta_ac);
 	ocfs2_run_deallocs(osb, &dealloc);
-	if (locked)
-		inode_unlock(inode);
 	ocfs2_dio_free_write_ctx(inode, dwc);
 
 	return ret;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 6611c64ca0be..5edc1d0cf115 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1245,22 +1245,24 @@ int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 				goto bail_unlock;
 			}
 		}
+		down_write(&OCFS2_I(inode)->ip_alloc_sem);
 		handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS +
 					   2 * ocfs2_quota_trans_credits(sb));
 		if (IS_ERR(handle)) {
 			status = PTR_ERR(handle);
 			mlog_errno(status);
-			goto bail_unlock;
+			goto bail_unlock_alloc;
 		}
 		status = __dquot_transfer(inode, transfer_to);
 		if (status < 0)
 			goto bail_commit;
 	} else {
+		down_write(&OCFS2_I(inode)->ip_alloc_sem);
 		handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
 		if (IS_ERR(handle)) {
 			status = PTR_ERR(handle);
 			mlog_errno(status);
-			goto bail_unlock;
+			goto bail_unlock_alloc;
 		}
 	}
 
@@ -1273,6 +1275,8 @@ int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 
 bail_commit:
 	ocfs2_commit_trans(osb, handle);
+bail_unlock_alloc:
+	up_write(&OCFS2_I(inode)->ip_alloc_sem);
 bail_unlock:
 	if (status && inode_locked) {
 		ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock);