Merge tag 'for-6.9-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "Mostly stabilization, refactoring and cleanup changes. There rest are
  minor performance optimizations due to caching or lock contention
  reduction and a few notable fixes.

  Performance improvements:

   - minor speedup in logging when repeatedly allocated structure is
     preallocated only once, improves latency and decreases lock
     contention

   - minor throughput increase (+6%), reduced lock contention after
     clearing delayed allocation bits, applies to several common
     workload types

   - skip full quota rescan if a new relation is added in the same
     transaction

  Fixes:

   - zstd fix for inline compressed file in subpage mode, updated
     version from the 6.8 time

   - proper qgroup inheritance ioctl parameter validation

   - more fiemap followup fixes after reduced locking done in 6.8:
      - fix race when detecting delalloc ranges

  Core changes:

   - more debugging code:
      - added assertions for a very rare crash in raid56 calculation
      - tree-checker dumps page state to give more insights into
        possible reference counting issues

   - add checksum calculation offloading sysfs knob, for now enabled
     under DEBUG only to determine a good heuristic for deciding the
     offload or synchronous, depends on various factors (block group
     profile, device speed) and is not as clear as initially thought
     (checksum type)

   - error handling improvements, added assertions

   - more page to folio conversion (defrag, truncate), cached size and
     shift

   - preparation for more fine grained locking of sectors in subpage
     mode

   - cleanups and refactoring:
      - include cleanups, forward declarations
      - pointer-to-structure helpers
      - redundant argument removals
      - removed unused code
      - slab cache updates, last use of SLAB_MEM_SPREAD removed"

* tag 'for-6.9-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (114 commits)
  btrfs: reuse cloned extent buffer during fiemap to avoid re-allocations
  btrfs: fix race when detecting delalloc ranges during fiemap
  btrfs: fix off-by-one chunk length calculation at contains_pending_extent()
  btrfs: qgroup: allow quick inherit if snapshot is created and added to the same parent
  btrfs: qgroup: validate btrfs_qgroup_inherit parameter
  btrfs: include device major and minor numbers in the device scan notice
  btrfs: mark btrfs_put_caching_control() static
  btrfs: remove SLAB_MEM_SPREAD flag use
  btrfs: qgroup: always free reserved space for extent records
  btrfs: tree-checker: dump the page status if hit something wrong
  btrfs: compression: remove dead comments in btrfs_compress_heuristic()
  btrfs: subpage: make writer lock utilize bitmap
  btrfs: subpage: make reader lock utilize bitmap
  btrfs: unexport btrfs_subpage_start_writer() and btrfs_subpage_end_and_test_writer()
  btrfs: pass a valid extent map cache pointer to __get_extent_map()
  btrfs: merge btrfs_del_delalloc_inode() helpers
  btrfs: pass btrfs_device to btrfs_scratch_superblocks()
  btrfs: handle transaction commit errors in flush_reservations()
  btrfs: use KMEM_CACHE() to create btrfs_free_space cache
  btrfs: use KMEM_CACHE() to create delayed ref caches
  ...

1 files changed, 73 insertions, 25 deletions

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index e180da4cc227..a2d07fa3cfdf 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -14,10 +14,8 @@
 #include <linux/namei.h>
 #include "misc.h"
 #include "ctree.h"
-#include "extent_map.h"
 #include "disk-io.h"
 #include "transaction.h"
-#include "print-tree.h"
 #include "volumes.h"
 #include "raid56.h"
 #include "rcu-string.h"
@@ -769,8 +767,9 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		if (same_fsid_diff_dev) {
 			generate_random_uuid(fs_devices->fsid);
 			fs_devices->temp_fsid = true;
-			pr_info("BTRFS: device %s using temp-fsid %pU\n",
-				path, fs_devices->fsid);
+		pr_info("BTRFS: device %s (%d:%d) using temp-fsid %pU\n",
+				path, MAJOR(path_devt), MINOR(path_devt),
+				fs_devices->fsid);
 		}
 
 		mutex_lock(&fs_devices->device_list_mutex);
@@ -799,8 +798,9 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 
 		if (fs_devices->opened) {
 			btrfs_err(NULL,
-"device %s belongs to fsid %pU, and the fs is already mounted, scanned by %s (%d)",
-				  path, fs_devices->fsid, current->comm,
+"device %s (%d:%d) belongs to fsid %pU, and the fs is already mounted, scanned by %s (%d)",
+				  path, MAJOR(path_devt), MINOR(path_devt),
+				  fs_devices->fsid, current->comm,
 				  task_pid_nr(current));
 			mutex_unlock(&fs_devices->device_list_mutex);
 			return ERR_PTR(-EBUSY);
@@ -826,13 +826,15 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 
 		if (disk_super->label[0])
 			pr_info(
-	"BTRFS: device label %s devid %llu transid %llu %s scanned by %s (%d)\n",
+"BTRFS: device label %s devid %llu transid %llu %s (%d:%d) scanned by %s (%d)\n",
 				disk_super->label, devid, found_transid, path,
+				MAJOR(path_devt), MINOR(path_devt),
 				current->comm, task_pid_nr(current));
 		else
 			pr_info(
-	"BTRFS: device fsid %pU devid %llu transid %llu %s scanned by %s (%d)\n",
+"BTRFS: device fsid %pU devid %llu transid %llu %s (%d:%d) scanned by %s (%d)\n",
 				disk_super->fsid, devid, found_transid, path,
+				MAJOR(path_devt), MINOR(path_devt),
 				current->comm, task_pid_nr(current));
 
 	} else if (!device->name || strcmp(device->name->str, path)) {
@@ -1368,7 +1370,8 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags,
 		else
 			btrfs_free_stale_devices(devt, NULL);
 
-		pr_debug("BTRFS: skip registering single non-seed device %s\n", path);
+	pr_debug("BTRFS: skip registering single non-seed device %s (%d:%d)\n",
+			path, MAJOR(devt), MINOR(devt));
 		device = NULL;
 		goto free_disk_super;
 	}
@@ -1403,7 +1406,7 @@ static bool contains_pending_extent(struct btrfs_device *device, u64 *start,
 
 		if (in_range(physical_start, *start, len) ||
 		    in_range(*start, physical_start,
-			     physical_end - physical_start)) {
+			     physical_end + 1 - physical_start)) {
 			*start = physical_end + 1;
 			return true;
 		}
@@ -2032,11 +2035,10 @@ static void btrfs_scratch_superblock(struct btrfs_fs_info *fs_info,
 			copy_num, ret);
 }
 
-void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
-			       struct block_device *bdev,
-			       const char *device_path)
+void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, struct btrfs_device *device)
 {
 	int copy_num;
+	struct block_device *bdev = device->bdev;
 
 	if (!bdev)
 		return;
@@ -2052,7 +2054,7 @@ void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
 	btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
 
 	/* Update ctime/mtime for device path for libblkid */
-	update_dev_time(device_path);
+	update_dev_time(device->name->str);
 }
 
 int btrfs_rm_device(struct btrfs_fs_info *fs_info,
@@ -2187,8 +2189,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 	 *  just flush the device and let the caller do the final bdev_release.
 	 */
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
-		btrfs_scratch_superblocks(fs_info, device->bdev,
-					  device->name->str);
+		btrfs_scratch_superblocks(fs_info, device);
 		if (device->bdev) {
 			sync_blockdev(device->bdev);
 			invalidate_bdev(device->bdev);
@@ -2301,8 +2302,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev)
 
 	mutex_unlock(&fs_devices->device_list_mutex);
 
-	btrfs_scratch_superblocks(tgtdev->fs_info, tgtdev->bdev,
-				  tgtdev->name->str);
+	btrfs_scratch_superblocks(tgtdev->fs_info, tgtdev);
 
 	btrfs_close_bdev(tgtdev);
 	synchronize_rcu();
@@ -3393,7 +3393,17 @@ again:
 			mutex_unlock(&fs_info->reclaim_bgs_lock);
 			goto error;
 		}
-		BUG_ON(ret == 0); /* Corruption */
+		if (ret == 0) {
+			/*
+			 * On the first search we would find chunk tree with
+			 * offset -1, which is not possible. On subsequent
+			 * loops this would find an existing item on an invalid
+			 * offset (one less than the previous one, wrong
+			 * alignment and size).
+			 */
+			ret = -EUCLEAN;
+			goto error;
+		}
 
 		ret = btrfs_previous_item(chunk_root, path, key.objectid,
 					  key.type);
@@ -3480,6 +3490,44 @@ static int btrfs_may_alloc_data_chunk(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
+static void btrfs_disk_balance_args_to_cpu(struct btrfs_balance_args *cpu,
+					   const struct btrfs_disk_balance_args *disk)
+{
+	memset(cpu, 0, sizeof(*cpu));
+
+	cpu->profiles = le64_to_cpu(disk->profiles);
+	cpu->usage = le64_to_cpu(disk->usage);
+	cpu->devid = le64_to_cpu(disk->devid);
+	cpu->pstart = le64_to_cpu(disk->pstart);
+	cpu->pend = le64_to_cpu(disk->pend);
+	cpu->vstart = le64_to_cpu(disk->vstart);
+	cpu->vend = le64_to_cpu(disk->vend);
+	cpu->target = le64_to_cpu(disk->target);
+	cpu->flags = le64_to_cpu(disk->flags);
+	cpu->limit = le64_to_cpu(disk->limit);
+	cpu->stripes_min = le32_to_cpu(disk->stripes_min);
+	cpu->stripes_max = le32_to_cpu(disk->stripes_max);
+}
+
+static void btrfs_cpu_balance_args_to_disk(struct btrfs_disk_balance_args *disk,
+					   const struct btrfs_balance_args *cpu)
+{
+	memset(disk, 0, sizeof(*disk));
+
+	disk->profiles = cpu_to_le64(cpu->profiles);
+	disk->usage = cpu_to_le64(cpu->usage);
+	disk->devid = cpu_to_le64(cpu->devid);
+	disk->pstart = cpu_to_le64(cpu->pstart);
+	disk->pend = cpu_to_le64(cpu->pend);
+	disk->vstart = cpu_to_le64(cpu->vstart);
+	disk->vend = cpu_to_le64(cpu->vend);
+	disk->target = cpu_to_le64(cpu->target);
+	disk->flags = cpu_to_le64(cpu->flags);
+	disk->limit = cpu_to_le64(cpu->limit);
+	disk->stripes_min = cpu_to_le32(cpu->stripes_min);
+	disk->stripes_max = cpu_to_le32(cpu->stripes_max);
+}
+
 static int insert_balance_item(struct btrfs_fs_info *fs_info,
 			       struct btrfs_balance_control *bctl)
 {
@@ -3624,7 +3672,7 @@ static void reset_balance_state(struct btrfs_fs_info *fs_info)
 	struct btrfs_balance_control *bctl = fs_info->balance_ctl;
 	int ret;
 
-	BUG_ON(!fs_info->balance_ctl);
+	ASSERT(fs_info->balance_ctl);
 
 	spin_lock(&fs_info->balance_lock);
 	fs_info->balance_ctl = NULL;
@@ -5944,6 +5992,7 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info,
 			    struct btrfs_chunk_map *map, int first,
 			    int dev_replace_is_ongoing)
 {
+	const enum btrfs_read_policy policy = READ_ONCE(fs_info->fs_devices->read_policy);
 	int i;
 	int num_stripes;
 	int preferred_mirror;
@@ -5958,13 +6007,12 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info,
 	else
 		num_stripes = map->num_stripes;
 
-	switch (fs_info->fs_devices->read_policy) {
+	switch (policy) {
 	default:
 		/* Shouldn't happen, just warn and use pid instead of failing */
-		btrfs_warn_rl(fs_info,
-			      "unknown read_policy type %u, reset to pid",
-			      fs_info->fs_devices->read_policy);
-		fs_info->fs_devices->read_policy = BTRFS_READ_POLICY_PID;
+		btrfs_warn_rl(fs_info, "unknown read_policy type %u, reset to pid",
+			      policy);
+		WRITE_ONCE(fs_info->fs_devices->read_policy, BTRFS_READ_POLICY_PID);
 		fallthrough;
 	case BTRFS_READ_POLICY_PID:
 		preferred_mirror = first + (current->pid % num_stripes);