Merge branch 'linus/master' into rdma.git for-next

rdma.git merge resolution for the 4.19 merge window

Conflicts:
 drivers/infiniband/core/rdma_core.c
   - Use the rdma code and revise with the new spelling for
     atomic_fetch_add_unless
 drivers/nvme/host/rdma.c
   - Replace max_sge with max_send_sge in new blk code
 drivers/nvme/target/rdma.c
   - Use the blk code and revise to use NULL for ib_post_recv when
     appropriate
   - Replace max_sge with max_recv_sge in new blk code
 net/rds/ib_send.c
   - Use the net code and revise to use NULL for ib_post_recv when
     appropriate

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

1 files changed, 21 insertions, 107 deletions

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 51e77d72068a..2be00e873e92 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -5,14 +5,11 @@
 
 #include <linux/fs.h>
 #include <linux/pagemap.h>
-#include <linux/highmem.h>
 #include <linux/time.h>
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/backing-dev.h>
-#include <linux/mpage.h>
 #include <linux/falloc.h>
-#include <linux/swap.h>
 #include <linux/writeback.h>
 #include <linux/compat.h>
 #include <linux/slab.h>
@@ -83,7 +80,7 @@ static int __compare_inode_defrag(struct inode_defrag *defrag1,
 static int __btrfs_add_inode_defrag(struct btrfs_inode *inode,
 				    struct inode_defrag *defrag)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct inode_defrag *entry;
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
@@ -135,8 +132,8 @@ static inline int __need_auto_defrag(struct btrfs_fs_info *fs_info)
 int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
 			   struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	struct btrfs_root *root = inode->root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct inode_defrag *defrag;
 	u64 transid;
 	int ret;
@@ -185,7 +182,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
 static void btrfs_requeue_inode_defrag(struct btrfs_inode *inode,
 				       struct inode_defrag *defrag)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	int ret;
 
 	if (!__need_auto_defrag(fs_info))
@@ -833,8 +830,7 @@ next_slot:
 				btrfs_file_extent_num_bytes(leaf, fi);
 		} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
 			extent_end = key.offset +
-				btrfs_file_extent_inline_len(leaf,
-						     path->slots[0], fi);
+				btrfs_file_extent_ram_bytes(leaf, fi);
 		} else {
 			/* can't happen */
 			BUG();
@@ -1133,7 +1129,7 @@ static int extent_mergeable(struct extent_buffer *leaf, int slot,
 int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 			      struct btrfs_inode *inode, u64 start, u64 end)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf;
 	struct btrfs_path *path;
@@ -1470,7 +1466,7 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
 				u64 *lockstart, u64 *lockend,
 				struct extent_state **cached_state)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	u64 start_pos;
 	u64 last_pos;
 	int i;
@@ -1526,7 +1522,7 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
 static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos,
 				    size_t *write_bytes)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_root *root = inode->root;
 	struct btrfs_ordered_extent *ordered;
 	u64 lockstart, lockend;
@@ -1569,10 +1565,11 @@ static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos,
 	return ret;
 }
 
-static noinline ssize_t __btrfs_buffered_write(struct file *file,
-					       struct iov_iter *i,
-					       loff_t pos)
+static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
+					       struct iov_iter *i)
 {
+	struct file *file = iocb->ki_filp;
+	loff_t pos = iocb->ki_pos;
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -1804,7 +1801,7 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
-	loff_t pos = iocb->ki_pos;
+	loff_t pos;
 	ssize_t written;
 	ssize_t written_buffered;
 	loff_t endbyte;
@@ -1815,8 +1812,8 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	if (written < 0 || !iov_iter_count(from))
 		return written;
 
-	pos += written;
-	written_buffered = __btrfs_buffered_write(file, from, pos);
+	pos = iocb->ki_pos;
+	written_buffered = btrfs_buffered_write(iocb, from);
 	if (written_buffered < 0) {
 		err = written_buffered;
 		goto out;
@@ -1953,7 +1950,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	if (iocb->ki_flags & IOCB_DIRECT) {
 		num_written = __btrfs_direct_write(iocb, from);
 	} else {
-		num_written = __btrfs_buffered_write(file, from, pos);
+		num_written = btrfs_buffered_write(iocb, from);
 		if (num_written > 0)
 			iocb->ki_pos = pos + num_written;
 		if (clean_page)
@@ -2042,7 +2039,6 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	struct btrfs_trans_handle *trans;
 	struct btrfs_log_ctx ctx;
 	int ret = 0, err;
-	bool full_sync = false;
 	u64 len;
 
 	/*
@@ -2066,96 +2062,21 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
 	inode_lock(inode);
 	atomic_inc(&root->log_batch);
-	full_sync = test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-			     &BTRFS_I(inode)->runtime_flags);
+
 	/*
-	 * We might have have had more pages made dirty after calling
-	 * start_ordered_ops and before acquiring the inode's i_mutex.
+	 * We have to do this here to avoid the priority inversion of waiting on
+	 * IO of a lower priority task while holding a transaciton open.
 	 */
-	if (full_sync) {
-		/*
-		 * For a full sync, we need to make sure any ordered operations
-		 * start and finish before we start logging the inode, so that
-		 * all extents are persisted and the respective file extent
-		 * items are in the fs/subvol btree.
-		 */
-		ret = btrfs_wait_ordered_range(inode, start, len);
-	} else {
-		/*
-		 * Start any new ordered operations before starting to log the
-		 * inode. We will wait for them to finish in btrfs_sync_log().
-		 *
-		 * Right before acquiring the inode's mutex, we might have new
-		 * writes dirtying pages, which won't immediately start the
-		 * respective ordered operations - that is done through the
-		 * fill_delalloc callbacks invoked from the writepage and
-		 * writepages address space operations. So make sure we start
-		 * all ordered operations before starting to log our inode. Not
-		 * doing this means that while logging the inode, writeback
-		 * could start and invoke writepage/writepages, which would call
-		 * the fill_delalloc callbacks (cow_file_range,
-		 * submit_compressed_extents). These callbacks add first an
-		 * extent map to the modified list of extents and then create
-		 * the respective ordered operation, which means in
-		 * tree-log.c:btrfs_log_inode() we might capture all existing
-		 * ordered operations (with btrfs_get_logged_extents()) before
-		 * the fill_delalloc callback adds its ordered operation, and by
-		 * the time we visit the modified list of extent maps (with
-		 * btrfs_log_changed_extents()), we see and process the extent
-		 * map they created. We then use the extent map to construct a
-		 * file extent item for logging without waiting for the
-		 * respective ordered operation to finish - this file extent
-		 * item points to a disk location that might not have yet been
-		 * written to, containing random data - so after a crash a log
-		 * replay will make our inode have file extent items that point
-		 * to disk locations containing invalid data, as we returned
-		 * success to userspace without waiting for the respective
-		 * ordered operation to finish, because it wasn't captured by
-		 * btrfs_get_logged_extents().
-		 */
-		ret = start_ordered_ops(inode, start, end);
-	}
+	ret = btrfs_wait_ordered_range(inode, start, len);
 	if (ret) {
 		inode_unlock(inode);
 		goto out;
 	}
 	atomic_inc(&root->log_batch);
 
-	/*
-	 * If the last transaction that changed this file was before the current
-	 * transaction and we have the full sync flag set in our inode, we can
-	 * bail out now without any syncing.
-	 *
-	 * Note that we can't bail out if the full sync flag isn't set. This is
-	 * because when the full sync flag is set we start all ordered extents
-	 * and wait for them to fully complete - when they complete they update
-	 * the inode's last_trans field through:
-	 *
-	 *     btrfs_finish_ordered_io() ->
-	 *         btrfs_update_inode_fallback() ->
-	 *             btrfs_update_inode() ->
-	 *                 btrfs_set_inode_last_trans()
-	 *
-	 * So we are sure that last_trans is up to date and can do this check to
-	 * bail out safely. For the fast path, when the full sync flag is not
-	 * set in our inode, we can not do it because we start only our ordered
-	 * extents and don't wait for them to complete (that is when
-	 * btrfs_finish_ordered_io runs), so here at this point their last_trans
-	 * value might be less than or equals to fs_info->last_trans_committed,
-	 * and setting a speculative last_trans for an inode when a buffered
-	 * write is made (such as fs_info->generation + 1 for example) would not
-	 * be reliable since after setting the value and before fsync is called
-	 * any number of transactions can start and commit (transaction kthread
-	 * commits the current transaction periodically), and a transaction
-	 * commit does not start nor waits for ordered extents to complete.
-	 */
 	smp_mb();
 	if (btrfs_inode_in_log(BTRFS_I(inode), fs_info->generation) ||
-	    (full_sync && BTRFS_I(inode)->last_trans <=
-	     fs_info->last_trans_committed) ||
-	    (!btrfs_have_ordered_extents_in_range(inode, start, len) &&
-	     BTRFS_I(inode)->last_trans
-	     <= fs_info->last_trans_committed)) {
+	    BTRFS_I(inode)->last_trans <= fs_info->last_trans_committed) {
 		/*
 		 * We've had everything committed since the last time we were
 		 * modified so clear this flag in case it was set for whatever
@@ -2239,13 +2160,6 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 				goto out;
 			}
 		}
-		if (!full_sync) {
-			ret = btrfs_wait_ordered_range(inode, start, len);
-			if (ret) {
-				btrfs_end_transaction(trans);
-				goto out;
-			}
-		}
 		ret = btrfs_commit_transaction(trans);
 	} else {
 		ret = btrfs_end_transaction(trans);
@@ -2310,7 +2224,7 @@ static int fill_holes(struct btrfs_trans_handle *trans,
 		struct btrfs_inode *inode,
 		struct btrfs_path *path, u64 offset, u64 end)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf;
 	struct btrfs_file_extent_item *fi;