From: Fred Isaman <iisaman@xxxxxxxxxxxxxx>
Replace a stub, so that extents underlying the layouts are properly
added, merged, or ignored as necessary.
Signed-off-by: Fred Isaman <iisaman@xxxxxxxxxxxxxx>
[pnfsblock: delete the new node before put it]
Signed-off-by: Mingyang Guo <guomingyang@xxxxxxxxxxxx>
Signed-off-by: Benny Halevy <bhalevy@xxxxxxxxxxx>
Signed-off-by: Peng Tao <peng_tao@xxxxxxx>
---
fs/nfs/blocklayout/blocklayout.h | 14 +++++-
fs/nfs/blocklayout/extents.c | 106 ++++++++++++++++++++++++++++++++++++++
2 files changed, 119 insertions(+), 1 deletions(-)
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index 5c1ccc1..6705b10 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -77,6 +77,14 @@ enum extentclass4 {
EXTENT_LISTS = 2,
};
+static inline int choose_list(enum exstate4 state)
+{
+ if (state == PNFS_BLOCK_READ_DATA || state == PNFS_BLOCK_NONE_DATA)
+ return RO_EXTENT;
+ else
+ return RW_EXTENT;
+}
+
struct pnfs_block_layout {
struct pnfs_layout_hdr bl_layout;
struct pnfs_inval_markings bl_inval; /* tracks INVAL->RW transition */
@@ -109,6 +117,11 @@ int nfs4_blk_process_layoutget(struct pnfs_layout_hdr *lo,
struct nfs4_layoutget_res *lgr, gfp_t gfp_flags);
/* blocklayoutdm.c */
void free_block_dev(struct pnfs_block_dev *bdev);
+/* extents.c */
+void put_extent(struct pnfs_block_extent *be);
+struct pnfs_block_extent *alloc_extent(void);
+int add_and_merge_extent(struct pnfs_block_layout *bl,
+ struct pnfs_block_extent *new);
#include <linux/sunrpc/simple_rpc_pipefs.h>
@@ -124,5 +137,4 @@ void bl_pipe_exit(void);
#define BL_DEVICE_REQUEST_PROC 0x1 /* User level process succeeds */
#define BL_DEVICE_REQUEST_ERR 0x2 /* User level process fails */
-void put_extent(struct pnfs_block_extent *be);
#endif /* FS_NFS_NFS4BLOCKLAYOUT_H */
diff --git a/fs/nfs/blocklayout/extents.c b/fs/nfs/blocklayout/extents.c
index 1283fa9..26c263f 100644
--- a/fs/nfs/blocklayout/extents.c
+++ b/fs/nfs/blocklayout/extents.c
@@ -95,3 +95,109 @@ void print_elist(struct list_head *list)
}
dprintk("****************\n");
}
+
+static inline int
+extents_consistent(struct pnfs_block_extent *old, struct pnfs_block_extent *new)
+{
+ /* Note this assumes new->be_f_offset >= old->be_f_offset */
+ return (new->be_state == old->be_state) &&
+ ((new->be_state == PNFS_BLOCK_NONE_DATA) ||
+ ((new->be_v_offset - old->be_v_offset ==
+ new->be_f_offset - old->be_f_offset) &&
+ new->be_mdev == old->be_mdev));
+}
+
+/* Adds new to appropriate list in bl, modifying new and removing existing
+ * extents as appropriate to deal with overlaps.
+ *
+ * See find_get_extent for list constraints.
+ *
+ * Refcount on new is already set. If end up not using it, or error out,
+ * need to put the reference.
+ *
+ * Lock is held by caller.
+ */
+int
+add_and_merge_extent(struct pnfs_block_layout *bl,
+ struct pnfs_block_extent *new)
+{
+ struct pnfs_block_extent *be, *tmp;
+ sector_t end = new->be_f_offset + new->be_length;
+ struct list_head *list;
+
+ dprintk("%s enter with be=%p\n", __func__, new);
+ print_bl_extent(new);
+ list = &bl->bl_extents[choose_list(new->be_state)];
+ print_elist(list);
+
+ /* Scan for proper place to insert, extending new to the left
+ * as much as possible.
+ */
+ list_for_each_entry_safe(be, tmp, list, be_node) {
+ if (new->be_f_offset < be->be_f_offset)
+ break;
+ if (end <= be->be_f_offset + be->be_length) {
+ /* new is a subset of existing be*/
+ if (extents_consistent(be, new)) {
+ dprintk("%s: new is subset, ignoring\n",
+ __func__);
+ put_extent(new);
+ return 0;
+ } else
+ goto out_err;
+ } else if (new->be_f_offset <=
+ be->be_f_offset + be->be_length) {
+ /* new overlaps or abuts existing be */
+ if (extents_consistent(be, new)) {
+ /* extend new to fully replace be */
+ new->be_length += new->be_f_offset -
+ be->be_f_offset;
+ new->be_f_offset = be->be_f_offset;
+ new->be_v_offset = be->be_v_offset;
+ dprintk("%s: removing %p\n", __func__, be);
+ list_del(&be->be_node);
+ put_extent(be);
+ } else if (new->be_f_offset !=
+ be->be_f_offset + be->be_length)
+ goto out_err;
+ }
+ }
+ /* Note that if we never hit the above break, be will not point to a
+ * valid extent. However, in that case &be->be_node==list.
+ */
+ list_add_tail(&new->be_node, &be->be_node);
+ dprintk("%s: inserting new\n", __func__);
+ print_elist(list);
+ /* Scan forward for overlaps. If we find any, extend new and
+ * remove the overlapped extent.
+ */
+ be = list_prepare_entry(new, list, be_node);
+ list_for_each_entry_safe_continue(be, tmp, list, be_node) {
+ if (end < be->be_f_offset)
+ break;
+ /* new overlaps or abuts existing be */
+ if (extents_consistent(be, new)) {
+ if (end < be->be_f_offset + be->be_length) {
+ /* extend new to fully cover be */
+ end = be->be_f_offset + be->be_length;
+ new->be_length = end - new->be_f_offset;
+ }
+ dprintk("%s: removing %p\n", __func__, be);
+ list_del(&be->be_node);
+ put_extent(be);
+ } else if (end != be->be_f_offset) {
+ list_del(&new->be_node);
+ goto out_err;
+ }
+ }
+ dprintk("%s: after merging\n", __func__);
+ print_elist(list);
+ /* STUB - The per-list consistency checks have all been done,
+ * should now check cross-list consistency.
+ */
+ return 0;
+
+ out_err:
+ put_extent(new);
+ return -EIO;
+}
--
1.7.4.1
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
