1 files changed, 65 insertions, 52 deletions

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index fd03e689a6be..32611a4edd6b 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -17,6 +17,7 @@
 #include <linux/uio.h>
 #include <linux/iversion.h>
 #include <linux/fsverity.h>
+#include <linux/iomap.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
@@ -368,12 +369,13 @@ next_slot:
 			btrfs_set_file_extent_offset(leaf, fi, extent_offset);
 			btrfs_set_file_extent_num_bytes(leaf, fi,
 							extent_end - args->start);
-			btrfs_mark_buffer_dirty(leaf);
+			btrfs_mark_buffer_dirty(trans, leaf);
 
 			if (update_refs && disk_bytenr > 0) {
 				btrfs_init_generic_ref(&ref,
 						BTRFS_ADD_DELAYED_REF,
-						disk_bytenr, num_bytes, 0);
+						disk_bytenr, num_bytes, 0,
+						root->root_key.objectid);
 				btrfs_init_data_ref(&ref,
 						root->root_key.objectid,
 						new_key.objectid,
@@ -405,13 +407,13 @@ next_slot:
 
 			memcpy(&new_key, &key, sizeof(new_key));
 			new_key.offset = args->end;
-			btrfs_set_item_key_safe(fs_info, path, &new_key);
+			btrfs_set_item_key_safe(trans, path, &new_key);
 
 			extent_offset += args->end - key.offset;
 			btrfs_set_file_extent_offset(leaf, fi, extent_offset);
 			btrfs_set_file_extent_num_bytes(leaf, fi,
 							extent_end - args->end);
-			btrfs_mark_buffer_dirty(leaf);
+			btrfs_mark_buffer_dirty(trans, leaf);
 			if (update_refs && disk_bytenr > 0)
 				args->bytes_found += args->end - key.offset;
 			break;
@@ -431,7 +433,7 @@ next_slot:
 
 			btrfs_set_file_extent_num_bytes(leaf, fi,
 							args->start - key.offset);
-			btrfs_mark_buffer_dirty(leaf);
+			btrfs_mark_buffer_dirty(trans, leaf);
 			if (update_refs && disk_bytenr > 0)
 				args->bytes_found += extent_end - args->start;
 			if (args->end == extent_end)
@@ -463,7 +465,8 @@ delete_extent_item:
 			} else if (update_refs && disk_bytenr > 0) {
 				btrfs_init_generic_ref(&ref,
 						BTRFS_DROP_DELAYED_REF,
-						disk_bytenr, num_bytes, 0);
+						disk_bytenr, num_bytes, 0,
+						root->root_key.objectid);
 				btrfs_init_data_ref(&ref,
 						root->root_key.objectid,
 						key.objectid,
@@ -536,7 +539,8 @@ delete_extent_item:
 			if (btrfs_comp_cpu_keys(&key, &slot_key) > 0)
 				path->slots[0]++;
 		}
-		btrfs_setup_item_for_insert(root, path, &key, args->extent_item_size);
+		btrfs_setup_item_for_insert(trans, root, path, &key,
+					    args->extent_item_size);
 		args->extent_inserted = true;
 	}
 
@@ -593,7 +597,6 @@ 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 = trans->fs_info;
 	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf;
 	struct btrfs_path *path;
@@ -664,7 +667,7 @@ again:
 				     ino, bytenr, orig_offset,
 				     &other_start, &other_end)) {
 			new_key.offset = end;
-			btrfs_set_item_key_safe(fs_info, path, &new_key);
+			btrfs_set_item_key_safe(trans, path, &new_key);
 			fi = btrfs_item_ptr(leaf, path->slots[0],
 					    struct btrfs_file_extent_item);
 			btrfs_set_file_extent_generation(leaf, fi,
@@ -679,7 +682,7 @@ again:
 							 trans->transid);
 			btrfs_set_file_extent_num_bytes(leaf, fi,
 							end - other_start);
-			btrfs_mark_buffer_dirty(leaf);
+			btrfs_mark_buffer_dirty(trans, leaf);
 			goto out;
 		}
 	}
@@ -698,7 +701,7 @@ again:
 							 trans->transid);
 			path->slots[0]++;
 			new_key.offset = start;
-			btrfs_set_item_key_safe(fs_info, path, &new_key);
+			btrfs_set_item_key_safe(trans, path, &new_key);
 
 			fi = btrfs_item_ptr(leaf, path->slots[0],
 					    struct btrfs_file_extent_item);
@@ -708,7 +711,7 @@ again:
 							other_end - start);
 			btrfs_set_file_extent_offset(leaf, fi,
 						     start - orig_offset);
-			btrfs_mark_buffer_dirty(leaf);
+			btrfs_mark_buffer_dirty(trans, leaf);
 			goto out;
 		}
 	}
@@ -742,10 +745,10 @@ again:
 		btrfs_set_file_extent_offset(leaf, fi, split - orig_offset);
 		btrfs_set_file_extent_num_bytes(leaf, fi,
 						extent_end - split);
-		btrfs_mark_buffer_dirty(leaf);
+		btrfs_mark_buffer_dirty(trans, leaf);
 
 		btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, bytenr,
-				       num_bytes, 0);
+				       num_bytes, 0, root->root_key.objectid);
 		btrfs_init_data_ref(&ref, root->root_key.objectid, ino,
 				    orig_offset, 0, false);
 		ret = btrfs_inc_extent_ref(trans, &ref);
@@ -771,7 +774,7 @@ again:
 	other_start = end;
 	other_end = 0;
 	btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, bytenr,
-			       num_bytes, 0);
+			       num_bytes, 0, root->root_key.objectid);
 	btrfs_init_data_ref(&ref, root->root_key.objectid, ino, orig_offset,
 			    0, false);
 	if (extent_mergeable(leaf, path->slots[0] + 1,
@@ -814,7 +817,7 @@ again:
 		btrfs_set_file_extent_type(leaf, fi,
 					   BTRFS_FILE_EXTENT_REG);
 		btrfs_set_file_extent_generation(leaf, fi, trans->transid);
-		btrfs_mark_buffer_dirty(leaf);
+		btrfs_mark_buffer_dirty(trans, leaf);
 	} else {
 		fi = btrfs_item_ptr(leaf, del_slot - 1,
 			   struct btrfs_file_extent_item);
@@ -823,7 +826,7 @@ again:
 		btrfs_set_file_extent_generation(leaf, fi, trans->transid);
 		btrfs_set_file_extent_num_bytes(leaf, fi,
 						extent_end - key.offset);
-		btrfs_mark_buffer_dirty(leaf);
+		btrfs_mark_buffer_dirty(trans, leaf);
 
 		ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
 		if (ret < 0) {
@@ -876,9 +879,9 @@ static int prepare_uptodate_page(struct inode *inode,
 	return 0;
 }
 
-static unsigned int get_prepare_fgp_flags(bool nowait)
+static fgf_t get_prepare_fgp_flags(bool nowait)
 {
-	unsigned int fgp_flags = FGP_LOCK | FGP_ACCESSED | FGP_CREAT;
+	fgf_t fgp_flags = FGP_LOCK | FGP_ACCESSED | FGP_CREAT;
 
 	if (nowait)
 		fgp_flags |= FGP_NOWAIT;
@@ -910,7 +913,7 @@ static noinline int prepare_pages(struct inode *inode, struct page **pages,
 	int i;
 	unsigned long index = pos >> PAGE_SHIFT;
 	gfp_t mask = get_prepare_gfp_flags(inode, nowait);
-	unsigned int fgp_flags = get_prepare_fgp_flags(nowait);
+	fgf_t fgp_flags = get_prepare_fgp_flags(nowait);
 	int err = 0;
 	int faili;
 
@@ -1108,17 +1111,19 @@ void btrfs_check_nocow_unlock(struct btrfs_inode *inode)
 
 static void update_time_for_write(struct inode *inode)
 {
-	struct timespec64 now;
+	struct timespec64 now, ts;
 
 	if (IS_NOCMTIME(inode))
 		return;
 
 	now = current_time(inode);
-	if (!timespec64_equal(&inode->i_mtime, &now))
-		inode->i_mtime = now;
+	ts = inode_get_mtime(inode);
+	if (!timespec64_equal(&ts, &now))
+		inode_set_mtime_to_ts(inode, now);
 
-	if (!timespec64_equal(&inode->i_ctime, &now))
-		inode->i_ctime = now;
+	ts = inode_get_ctime(inode);
+	if (!timespec64_equal(&ts, &now))
+		inode_set_ctime_to_ts(inode, now);
 
 	if (IS_I_VERSION(inode))
 		inode_inc_iversion(inode);
@@ -1466,8 +1471,13 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	if (iocb->ki_flags & IOCB_NOWAIT)
 		ilock_flags |= BTRFS_ILOCK_TRY;
 
-	/* If the write DIO is within EOF, use a shared lock */
-	if (iocb->ki_pos + iov_iter_count(from) <= i_size_read(inode))
+	/*
+	 * If the write DIO is within EOF, use a shared lock and also only if
+	 * security bits will likely not be dropped by file_remove_privs() called
+	 * from btrfs_write_check(). Either will need to be rechecked after the
+	 * lock was acquired.
+	 */
+	if (iocb->ki_pos + iov_iter_count(from) <= i_size_read(inode) && IS_NOSEC(inode))
 		ilock_flags |= BTRFS_ILOCK_SHARED;
 
 relock:
@@ -1475,6 +1485,13 @@ relock:
 	if (err < 0)
 		return err;
 
+	/* Shared lock cannot be used with security bits set. */
+	if ((ilock_flags & BTRFS_ILOCK_SHARED) && !IS_NOSEC(inode)) {
+		btrfs_inode_unlock(BTRFS_I(inode), ilock_flags);
+		ilock_flags &= ~BTRFS_ILOCK_SHARED;
+		goto relock;
+	}
+
 	err = generic_write_checks(iocb, from);
 	if (err <= 0) {
 		btrfs_inode_unlock(BTRFS_I(inode), ilock_flags);
@@ -1733,7 +1750,7 @@ static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx)
 	struct btrfs_inode *inode = BTRFS_I(ctx->inode);
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 
-	if (btrfs_inode_in_log(inode, fs_info->generation) &&
+	if (btrfs_inode_in_log(inode, btrfs_get_fs_generation(fs_info)) &&
 	    list_empty(&ctx->ordered_extents))
 		return true;
 
@@ -1744,7 +1761,7 @@ static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx)
 	 * and for a fast fsync we don't wait for that, we only wait for the
 	 * writeback to complete.
 	 */
-	if (inode->last_trans <= fs_info->last_trans_committed &&
+	if (inode->last_trans <= btrfs_get_last_trans_committed(fs_info) &&
 	    (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) ||
 	     list_empty(&ctx->ordered_extents)))
 		return true;
@@ -1873,7 +1890,6 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
 	atomic_inc(&root->log_batch);
 
-	smp_mb();
 	if (skip_inode_logging(&ctx)) {
 		/*
 		 * We've had everything committed since the last time we were
@@ -2091,7 +2107,7 @@ static int fill_holes(struct btrfs_trans_handle *trans,
 		btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes);
 		btrfs_set_file_extent_offset(leaf, fi, 0);
 		btrfs_set_file_extent_generation(leaf, fi, trans->transid);
-		btrfs_mark_buffer_dirty(leaf);
+		btrfs_mark_buffer_dirty(trans, leaf);
 		goto out;
 	}
 
@@ -2099,7 +2115,7 @@ static int fill_holes(struct btrfs_trans_handle *trans,
 		u64 num_bytes;
 
 		key.offset = offset;
-		btrfs_set_item_key_safe(fs_info, path, &key);
+		btrfs_set_item_key_safe(trans, path, &key);
 		fi = btrfs_item_ptr(leaf, path->slots[0],
 				    struct btrfs_file_extent_item);
 		num_bytes = btrfs_file_extent_num_bytes(leaf, fi) + end -
@@ -2108,7 +2124,7 @@ static int fill_holes(struct btrfs_trans_handle *trans,
 		btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes);
 		btrfs_set_file_extent_offset(leaf, fi, 0);
 		btrfs_set_file_extent_generation(leaf, fi, trans->transid);
-		btrfs_mark_buffer_dirty(leaf);
+		btrfs_mark_buffer_dirty(trans, leaf);
 		goto out;
 	}
 	btrfs_release_path(path);
@@ -2260,7 +2276,7 @@ static int btrfs_insert_replace_extent(struct btrfs_trans_handle *trans,
 	btrfs_set_file_extent_num_bytes(leaf, extent, replace_len);
 	if (extent_info->is_new_extent)
 		btrfs_set_file_extent_generation(leaf, extent, trans->transid);
-	btrfs_mark_buffer_dirty(leaf);
+	btrfs_mark_buffer_dirty(trans, leaf);
 	btrfs_release_path(path);
 
 	ret = btrfs_inode_set_file_extent_range(inode, extent_info->file_offset,
@@ -2290,7 +2306,8 @@ static int btrfs_insert_replace_extent(struct btrfs_trans_handle *trans,
 
 		btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF,
 				       extent_info->disk_offset,
-				       extent_info->disk_len, 0);
+				       extent_info->disk_len, 0,
+				       root->root_key.objectid);
 		ref_offset = extent_info->file_offset - extent_info->data_offset;
 		btrfs_init_data_ref(&ref, root->root_key.objectid,
 				    btrfs_ino(inode), ref_offset, 0, false);
@@ -2459,12 +2476,11 @@ int btrfs_replace_file_extents(struct btrfs_inode *inode,
 		 */
 		inode_inc_iversion(&inode->vfs_inode);
 
-		if (!extent_info || extent_info->update_times) {
-			inode->vfs_inode.i_mtime = current_time(&inode->vfs_inode);
-			inode->vfs_inode.i_ctime = inode->vfs_inode.i_mtime;
-		}
+		if (!extent_info || extent_info->update_times)
+			inode_set_mtime_to_ts(&inode->vfs_inode,
+					      inode_set_ctime_current(&inode->vfs_inode));
 
-		ret = btrfs_update_inode(trans, root, inode);
+		ret = btrfs_update_inode(trans, inode);
 		if (ret)
 			break;
 
@@ -2703,9 +2719,8 @@ static int btrfs_punch_hole(struct file *file, loff_t offset, loff_t len)
 
 	ASSERT(trans != NULL);
 	inode_inc_iversion(inode);
-	inode->i_mtime = current_time(inode);
-	inode->i_ctime = inode->i_mtime;
-	ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
+	inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
+	ret = btrfs_update_inode(trans, BTRFS_I(inode));
 	updated_inode = true;
 	btrfs_end_transaction(trans);
 	btrfs_btree_balance_dirty(fs_info);
@@ -2721,18 +2736,17 @@ out_only_mutex:
 		 * for detecting, at fsync time, if the inode isn't yet in the
 		 * log tree or it's there but not up to date.
 		 */
-		struct timespec64 now = current_time(inode);
+		struct timespec64 now = inode_set_ctime_current(inode);
 
 		inode_inc_iversion(inode);
-		inode->i_mtime = now;
-		inode->i_ctime = now;
+		inode_set_mtime_to_ts(inode, now);
 		trans = btrfs_start_transaction(root, 1);
 		if (IS_ERR(trans)) {
 			ret = PTR_ERR(trans);
 		} else {
 			int ret2;
 
-			ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
+			ret = btrfs_update_inode(trans, BTRFS_I(inode));
 			ret2 = btrfs_end_transaction(trans);
 			if (!ret)
 				ret = ret2;
@@ -2796,10 +2810,10 @@ static int btrfs_fallocate_update_isize(struct inode *inode,
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
-	inode->i_ctime = current_time(inode);
+	inode_set_ctime_current(inode);
 	i_size_write(inode, end);
 	btrfs_inode_safe_disk_i_size_write(BTRFS_I(inode), 0);
-	ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
+	ret = btrfs_update_inode(trans, BTRFS_I(inode));
 	ret2 = btrfs_end_transaction(trans);
 
 	return ret ? ret : ret2;
@@ -3018,7 +3032,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 	struct extent_changeset *data_reserved = NULL;
 	struct falloc_range *range;
 	struct falloc_range *tmp;
-	struct list_head reserve_list;
+	LIST_HEAD(reserve_list);
 	u64 cur_offset;
 	u64 last_byte;
 	u64 alloc_start;
@@ -3110,7 +3124,6 @@ static long btrfs_fallocate(struct file *file, int mode,
 	btrfs_assert_inode_range_clean(BTRFS_I(inode), alloc_start, locked_end);
 
 	/* First, check if we exceed the qgroup limit */
-	INIT_LIST_HEAD(&reserve_list);
 	while (cur_offset < alloc_end) {
 		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, cur_offset,
 				      alloc_end - cur_offset);
@@ -3179,7 +3192,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 			qgroup_reserved -= range->len;
 		} else if (qgroup_reserved > 0) {
 			btrfs_qgroup_free_data(BTRFS_I(inode), data_reserved,
-					       range->start, range->len);
+					       range->start, range->len, NULL);
 			qgroup_reserved -= range->len;
 		}
 		list_del(&range->list);