xfs: support logging EFIs for realtime extents
Teach the EFI mechanism how to free realtime extents. We're going to
need this to enforce proper ordering of operations when we enable
realtime rmap.
Declare a new log intent item type (XFS_LI_EFI_RT) and a separate defer
ops for rt extents. This keeps the ondisk artifacts and processing code
completely separate between the rt and non-rt cases. Hopefully this
will make it easier to debug filesystem problems.
Previous versions of this patch accomplished this by setting the high
bit in each rt EFI extent. This was found to be less transparent by
reviewers.
[Contains a bug fix and cleanups from hch]
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
diff --git a/libxfs/defer_item.c b/libxfs/defer_item.c
index 98a291c..b3c835d 100644
--- a/libxfs/defer_item.c
+++ b/libxfs/defer_item.c
@@ -85,6 +85,12 @@
{
struct xfs_mount *mp = tp->t_mountp;
+ if (xfs_efi_is_realtime(xefi)) {
+ *dfpp = xfs_defer_add(tp, &xefi->xefi_list,
+ &xfs_rtextent_free_defer_type);
+ return;
+ }
+
xefi->xefi_pag = xfs_perag_intent_get(mp, xefi->xefi_startblock);
if (xefi->xefi_agresv == XFS_AG_RESV_AGFL)
*dfpp = xfs_defer_add(tp, &xefi->xefi_list,
@@ -157,6 +163,52 @@
.cancel_item = xfs_extent_free_cancel_item,
};
+static struct xfs_log_item *
+xfs_rtextent_free_create_intent(
+ struct xfs_trans *tp,
+ struct list_head *items,
+ unsigned int count,
+ bool sort)
+{
+ return NULL;
+}
+
+/* Cancel a free extent. */
+STATIC void
+xfs_rtextent_free_cancel_item(
+ struct list_head *item)
+{
+ struct xfs_extent_free_item *xefi = xefi_entry(item);
+
+ kmem_cache_free(xfs_extfree_item_cache, xefi);
+}
+
+STATIC int
+xfs_rtextent_free_finish_item(
+ struct xfs_trans *tp,
+ struct xfs_log_item *done,
+ struct list_head *item,
+ struct xfs_btree_cur **state)
+{
+ struct xfs_extent_free_item *xefi = xefi_entry(item);
+ int error;
+
+ error = xfs_rtfree_blocks(tp, xefi->xefi_startblock,
+ xefi->xefi_blockcount);
+ if (error != -EAGAIN)
+ xfs_rtextent_free_cancel_item(item);
+ return error;
+}
+
+const struct xfs_defer_op_type xfs_rtextent_free_defer_type = {
+ .name = "rtextent_free",
+ .create_intent = xfs_rtextent_free_create_intent,
+ .abort_intent = xfs_extent_free_abort_intent,
+ .create_done = xfs_extent_free_create_done,
+ .finish_item = xfs_rtextent_free_finish_item,
+ .cancel_item = xfs_rtextent_free_cancel_item,
+};
+
/*
* AGFL blocks are accounted differently in the reserve pools and are not
* inserted into the busy extent list.
diff --git a/libxfs/xfs_alloc.c b/libxfs/xfs_alloc.c
index 3806a6b..3dc656e 100644
--- a/libxfs/xfs_alloc.c
+++ b/libxfs/xfs_alloc.c
@@ -2641,8 +2641,17 @@
ASSERT(!isnullstartblock(bno));
ASSERT(!(free_flags & ~XFS_FREE_EXTENT_ALL_FLAGS));
- if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbext(mp, bno, len)))
- return -EFSCORRUPTED;
+ if (free_flags & XFS_FREE_EXTENT_REALTIME) {
+ if (type != XFS_AG_RESV_NONE) {
+ ASSERT(type == XFS_AG_RESV_NONE);
+ return -EFSCORRUPTED;
+ }
+ if (XFS_IS_CORRUPT(mp, !xfs_verify_rtbext(mp, bno, len)))
+ return -EFSCORRUPTED;
+ } else {
+ if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbext(mp, bno, len)))
+ return -EFSCORRUPTED;
+ }
xefi = kmem_cache_zalloc(xfs_extfree_item_cache,
GFP_KERNEL | __GFP_NOFAIL);
@@ -2651,6 +2660,8 @@
xefi->xefi_agresv = type;
if (free_flags & XFS_FREE_EXTENT_SKIP_DISCARD)
xefi->xefi_flags |= XFS_EFI_SKIP_DISCARD;
+ if (free_flags & XFS_FREE_EXTENT_REALTIME)
+ xefi->xefi_flags |= XFS_EFI_REALTIME;
if (oinfo) {
ASSERT(oinfo->oi_offset == 0);
diff --git a/libxfs/xfs_alloc.h b/libxfs/xfs_alloc.h
index fae1708..c6f3515 100644
--- a/libxfs/xfs_alloc.h
+++ b/libxfs/xfs_alloc.h
@@ -240,7 +240,11 @@
/* Don't issue a discard for the blocks freed. */
#define XFS_FREE_EXTENT_SKIP_DISCARD (1U << 0)
-#define XFS_FREE_EXTENT_ALL_FLAGS (XFS_FREE_EXTENT_SKIP_DISCARD)
+/* Free blocks on the realtime device. */
+#define XFS_FREE_EXTENT_REALTIME (1U << 1)
+
+#define XFS_FREE_EXTENT_ALL_FLAGS (XFS_FREE_EXTENT_SKIP_DISCARD | \
+ XFS_FREE_EXTENT_REALTIME)
/*
* List of extents to be free "later".
@@ -260,6 +264,12 @@
#define XFS_EFI_ATTR_FORK (1U << 1) /* freeing attr fork block */
#define XFS_EFI_BMBT_BLOCK (1U << 2) /* freeing bmap btree block */
#define XFS_EFI_CANCELLED (1U << 3) /* dont actually free the space */
+#define XFS_EFI_REALTIME (1U << 4) /* freeing realtime extent */
+
+static inline bool xfs_efi_is_realtime(const struct xfs_extent_free_item *xefi)
+{
+ return xefi->xefi_flags & XFS_EFI_REALTIME;
+}
struct xfs_alloc_autoreap {
struct xfs_defer_pending *dfp;
diff --git a/libxfs/xfs_defer.c b/libxfs/xfs_defer.c
index e3a608f..8f6708c 100644
--- a/libxfs/xfs_defer.c
+++ b/libxfs/xfs_defer.c
@@ -839,6 +839,12 @@
ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
+ if (!ops->finish_item) {
+ ASSERT(ops->finish_item != NULL);
+ xfs_force_shutdown(tp->t_mountp, SHUTDOWN_CORRUPT_INCORE);
+ return NULL;
+ }
+
dfp = xfs_defer_find_last(tp, ops);
if (!dfp || !xfs_defer_can_append(dfp, ops))
dfp = xfs_defer_alloc(&tp->t_dfops, ops);
diff --git a/libxfs/xfs_defer.h b/libxfs/xfs_defer.h
index 8b33803..ec51b84 100644
--- a/libxfs/xfs_defer.h
+++ b/libxfs/xfs_defer.h
@@ -71,6 +71,7 @@
extern const struct xfs_defer_op_type xfs_rmap_update_defer_type;
extern const struct xfs_defer_op_type xfs_extent_free_defer_type;
extern const struct xfs_defer_op_type xfs_agfl_free_defer_type;
+extern const struct xfs_defer_op_type xfs_rtextent_free_defer_type;
extern const struct xfs_defer_op_type xfs_attr_defer_type;
extern const struct xfs_defer_op_type xfs_exchmaps_defer_type;
diff --git a/libxfs/xfs_log_format.h b/libxfs/xfs_log_format.h
index 3e6682e..b81f369 100644
--- a/libxfs/xfs_log_format.h
+++ b/libxfs/xfs_log_format.h
@@ -248,6 +248,8 @@
#define XFS_LI_ATTRD 0x1247 /* attr set/remove done */
#define XFS_LI_XMI 0x1248 /* mapping exchange intent */
#define XFS_LI_XMD 0x1249 /* mapping exchange done */
+#define XFS_LI_EFI_RT 0x124a /* realtime extent free intent */
+#define XFS_LI_EFD_RT 0x124b /* realtime extent free done */
#define XFS_LI_TYPE_DESC \
{ XFS_LI_EFI, "XFS_LI_EFI" }, \
@@ -267,7 +269,9 @@
{ XFS_LI_ATTRI, "XFS_LI_ATTRI" }, \
{ XFS_LI_ATTRD, "XFS_LI_ATTRD" }, \
{ XFS_LI_XMI, "XFS_LI_XMI" }, \
- { XFS_LI_XMD, "XFS_LI_XMD" }
+ { XFS_LI_XMD, "XFS_LI_XMD" }, \
+ { XFS_LI_EFI_RT, "XFS_LI_EFI_RT" }, \
+ { XFS_LI_EFD_RT, "XFS_LI_EFD_RT" }
/*
* Inode Log Item Format definitions.
