#define PAGE_CACHE_SECTOR_SHIFT (PAGE_CACHE_SHIFT - SECTOR_SHIFT)
#define SECTOR_SIZE (1 << SECTOR_SHIFT)
-struct block_mount_id {
- spinlock_t bm_lock; /* protects list */
- struct list_head bm_devlist; /* holds pnfs_block_dev */
-};
+struct pnfs_block_dev;
-struct pnfs_block_dev {
- struct list_head bm_node;
- struct nfs4_deviceid bm_mdevid; /* associated devid */
- struct block_device *bm_mdev; /* meta device itself */
- struct net *net;
+enum pnfs_block_volume_type {
+ PNFS_BLOCK_VOLUME_SIMPLE = 0,
+ PNFS_BLOCK_VOLUME_SLICE = 1,
+ PNFS_BLOCK_VOLUME_CONCAT = 2,
+ PNFS_BLOCK_VOLUME_STRIPE = 3,
};
-enum exstate4 {
- PNFS_BLOCK_READWRITE_DATA = 0,
- PNFS_BLOCK_READ_DATA = 1,
- PNFS_BLOCK_INVALID_DATA = 2, /* mapped, but data is invalid */
- PNFS_BLOCK_NONE_DATA = 3 /* unmapped, it's a hole */
+#define PNFS_BLOCK_MAX_UUIDS 4
+#define PNFS_BLOCK_MAX_DEVICES 64
+
+/*
+ * Random upper cap for the uuid length to avoid unbounded allocation.
+ * Not actually limited by the protocol.
+ */
+#define PNFS_BLOCK_UUID_LEN 128
+
+
+struct pnfs_block_volume {
+ enum pnfs_block_volume_type type;
+ union {
+ struct {
+ int len;
+ int nr_sigs;
+ struct {
+ u64 offset;
+ u32 sig_len;
+ u8 sig[PNFS_BLOCK_UUID_LEN];
+ } sigs[PNFS_BLOCK_MAX_UUIDS];
+ } simple;
+ struct {
+ u64 start;
+ u64 len;
+ u32 volume;
+ } slice;
+ struct {
+ u32 volumes_count;
+ u32 volumes[PNFS_BLOCK_MAX_DEVICES];
+ } concat;
+ struct {
+ u64 chunk_size;
+ u32 volumes_count;
+ u32 volumes[PNFS_BLOCK_MAX_DEVICES];
+ } stripe;
+ };
};
-#define MY_MAX_TAGS (15) /* tag bitnums used must be less than this */
+struct pnfs_block_dev_map {
+ sector_t start;
+ sector_t len;
-struct my_tree {
- sector_t mtt_step_size; /* Internal sector alignment */
- struct list_head mtt_stub; /* Should be a radix tree */
+ sector_t disk_offset;
+ struct block_device *bdev;
};
-struct pnfs_inval_markings {
- spinlock_t im_lock;
- struct my_tree im_tree; /* Sectors that need LAYOUTCOMMIT */
- sector_t im_block_size; /* Server blocksize in sectors */
- struct list_head im_extents; /* Short extents for INVAL->RW conversion */
+struct pnfs_block_dev {
+ struct nfs4_deviceid_node node;
+
+ u64 start;
+ u64 len;
+
+ u32 nr_children;
+ struct pnfs_block_dev *children;
+ u64 chunk_size;
+
+ struct block_device *bdev;
+ u64 disk_offset;
+
+ bool (*map)(struct pnfs_block_dev *dev, u64 offset,
+ struct pnfs_block_dev_map *map);
};
-struct pnfs_inval_tracking {
- struct list_head it_link;
- int it_sector;
- int it_tags;
+enum exstate4 {
+ PNFS_BLOCK_READWRITE_DATA = 0,
+ PNFS_BLOCK_READ_DATA = 1,
+ PNFS_BLOCK_INVALID_DATA = 2, /* mapped, but data is invalid */
+ PNFS_BLOCK_NONE_DATA = 3 /* unmapped, it's a hole */
};
/* sector_t fields are all in 512-byte sectors */
struct pnfs_block_extent {
- struct kref be_refcnt;
- struct list_head be_node; /* link into lseg list */
- struct nfs4_deviceid be_devid; /* FIXME: could use device cache instead */
- struct block_device *be_mdev;
+ union {
+ struct rb_node be_node;
+ struct list_head be_list;
+ };
+ struct nfs4_deviceid_node *be_device;
sector_t be_f_offset; /* the starting offset in the file */
sector_t be_length; /* the size of the extent */
sector_t be_v_offset; /* the starting offset in the volume */
enum exstate4 be_state; /* the state of this extent */
- struct pnfs_inval_markings *be_inval; /* tracks INVAL->RW transition */
+#define EXTENT_WRITTEN 1
+#define EXTENT_COMMITTING 2
+ unsigned int be_tag;
};
-/* Shortened extent used by LAYOUTCOMMIT */
-struct pnfs_block_short_extent {
- struct list_head bse_node;
- struct nfs4_deviceid bse_devid;
- struct block_device *bse_mdev;
- sector_t bse_f_offset; /* the starting offset in the file */
- sector_t bse_length; /* the size of the extent */
-};
-
-static inline void
-BL_INIT_INVAL_MARKS(struct pnfs_inval_markings *marks, sector_t blocksize)
-{
- spin_lock_init(&marks->im_lock);
- INIT_LIST_HEAD(&marks->im_tree.mtt_stub);
- INIT_LIST_HEAD(&marks->im_extents);
- marks->im_block_size = blocksize;
- marks->im_tree.mtt_step_size = min((sector_t)PAGE_CACHE_SECTORS,
- blocksize);
-}
-
-enum extentclass4 {
- RW_EXTENT = 0, /* READWRTE and INVAL */
- RO_EXTENT = 1, /* READ and NONE */
- EXTENT_LISTS = 2,
-};
-
-static inline int bl_choose_list(enum exstate4 state)
-{
- if (state == PNFS_BLOCK_READ_DATA || state == PNFS_BLOCK_NONE_DATA)
- return RO_EXTENT;
- else
- return RW_EXTENT;
-}
+/* on the wire size of the extent */
+#define BL_EXTENT_SIZE (7 * sizeof(__be32) + NFS4_DEVICEID4_SIZE)
struct pnfs_block_layout {
- struct pnfs_layout_hdr bl_layout;
- struct pnfs_inval_markings bl_inval; /* tracks INVAL->RW transition */
+ struct pnfs_layout_hdr bl_layout;
+ struct rb_root bl_ext_rw;
+ struct rb_root bl_ext_ro;
spinlock_t bl_ext_lock; /* Protects list manipulation */
- struct list_head bl_extents[EXTENT_LISTS]; /* R and RW extents */
- struct list_head bl_commit; /* Needs layout commit */
- struct list_head bl_committing; /* Layout committing */
- unsigned int bl_count; /* entries in bl_commit */
- sector_t bl_blocksize; /* Server blocksize in sectors */
};
-#define BLK_ID(lo) ((struct block_mount_id *)(NFS_SERVER(lo->plh_inode)->pnfs_ld_data))
-
static inline struct pnfs_block_layout *
BLK_LO2EXT(struct pnfs_layout_hdr *lo)
{
#define BL_DEVICE_REQUEST_PROC 0x1 /* User level process succeeds */
#define BL_DEVICE_REQUEST_ERR 0x2 /* User level process fails */
-/* blocklayoutdev.c */
-ssize_t bl_pipe_downcall(struct file *, const char __user *, size_t);
-void bl_pipe_destroy_msg(struct rpc_pipe_msg *);
-void nfs4_blkdev_put(struct block_device *bdev);
-struct pnfs_block_dev *nfs4_blk_decode_device(struct nfs_server *server,
- struct pnfs_device *dev);
-int nfs4_blk_process_layoutget(struct pnfs_layout_hdr *lo,
- struct nfs4_layoutget_res *lgr, gfp_t gfp_flags);
-
-/* blocklayoutdm.c */
-void bl_free_block_dev(struct pnfs_block_dev *bdev);
-
-/* extents.c */
-struct pnfs_block_extent *
-bl_find_get_extent(struct pnfs_block_layout *bl, sector_t isect,
- struct pnfs_block_extent **cow_read);
-int bl_mark_sectors_init(struct pnfs_inval_markings *marks,
- sector_t offset, sector_t length);
-void bl_put_extent(struct pnfs_block_extent *be);
-struct pnfs_block_extent *bl_alloc_extent(void);
-int bl_is_sector_init(struct pnfs_inval_markings *marks, sector_t isect);
-int encode_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
- struct xdr_stream *xdr,
- const struct nfs4_layoutcommit_args *arg);
-void clean_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
- const struct nfs4_layoutcommit_args *arg,
- int status);
-int bl_add_merge_extent(struct pnfs_block_layout *bl,
- struct pnfs_block_extent *new);
-int bl_mark_for_commit(struct pnfs_block_extent *be,
- sector_t offset, sector_t length,
- struct pnfs_block_short_extent *new);
-int bl_push_one_short_extent(struct pnfs_inval_markings *marks);
-struct pnfs_block_short_extent *
-bl_pop_one_short_extent(struct pnfs_inval_markings *marks);
-void bl_free_short_extents(struct pnfs_inval_markings *marks, int num_to_free);
+/* dev.c */
+struct nfs4_deviceid_node *bl_alloc_deviceid_node(struct nfs_server *server,
+ struct pnfs_device *pdev, gfp_t gfp_mask);
+void bl_free_deviceid_node(struct nfs4_deviceid_node *d);
+
+/* extent_tree.c */
+int ext_tree_insert(struct pnfs_block_layout *bl,
+ struct pnfs_block_extent *new);
+int ext_tree_remove(struct pnfs_block_layout *bl, bool rw, sector_t start,
+ sector_t end);
+int ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start,
+ sector_t len);
+bool ext_tree_lookup(struct pnfs_block_layout *bl, sector_t isect,
+ struct pnfs_block_extent *ret, bool rw);
+int ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg);
+void ext_tree_mark_committed(struct nfs4_layoutcommit_args *arg, int status);
+
+/* rpc_pipefs.c */
+dev_t bl_resolve_deviceid(struct nfs_server *server,
+ struct pnfs_block_volume *b, gfp_t gfp_mask);
+int __init bl_init_pipefs(void);
+void __exit bl_cleanup_pipefs(void);
#endif /* FS_NFS_NFS4BLOCKLAYOUT_H */
projects / karo-tx-linux.git / blobdiff