summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-11-15 16:33:41 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2013-11-15 16:33:41 -0800
commitf412f2c60b480fa5140a4b4cb321cd48c64e1812 (patch)
treeaafd5a5922b43daca4abdfa9bb723fc1f334108d /include
parentcd1177f25069cb494680eedd718e7c6d8fd85d10 (diff)
parent1cf7e9c68fe84248174e998922b39e508375e7c1 (diff)
Merge branch 'for-linus' of git://git.kernel.dk/linux-block
Pull second round of block driver updates from Jens Axboe: "As mentioned in the original pull request, the bcache bits were pulled because of their dependency on the immutable bio vecs. Kent re-did this part and resubmitted it, so here's the 2nd round of (mostly) driver updates for 3.13. It contains: - The bcache work from Kent. - Conversion of virtio-blk to blk-mq. This removes the bio and request path, and substitutes with the blk-mq path instead. The end result almost 200 deleted lines. Patch is acked by Asias and Christoph, who both did a bunch of testing. - A removal of bootmem.h include from Grygorii Strashko, part of a larger series of his killing the dependency on that header file. - Removal of __cpuinit from blk-mq from Paul Gortmaker" * 'for-linus' of git://git.kernel.dk/linux-block: (56 commits) virtio_blk: blk-mq support blk-mq: remove newly added instances of __cpuinit bcache: defensively handle format strings bcache: Bypass torture test bcache: Delete some slower inline asm bcache: Use ida for bcache block dev minor bcache: Fix sysfs splat on shutdown with flash only devs bcache: Better full stripe scanning bcache: Have btree_split() insert into parent directly bcache: Move spinlock into struct time_stats bcache: Kill sequential_merge option bcache: Kill bch_next_recurse_key() bcache: Avoid deadlocking in garbage collection bcache: Incremental gc bcache: Add make_btree_freeing_key() bcache: Add btree_node_write_sync() bcache: PRECEDING_KEY() bcache: bch_(btree|extent)_ptr_invalid() bcache: Don't bother with bucket refcount for btree node allocations bcache: Debug code improvements ...
Diffstat (limited to 'include')
-rw-r--r--include/trace/events/bcache.h47
-rw-r--r--include/uapi/linux/bcache.h373
2 files changed, 410 insertions, 10 deletions
diff --git a/include/trace/events/bcache.h b/include/trace/events/bcache.h
index 5ebda976ea93..e2b9576d00e2 100644
--- a/include/trace/events/bcache.h
+++ b/include/trace/events/bcache.h
@@ -6,11 +6,9 @@
#include <linux/tracepoint.h>
-struct search;
-
DECLARE_EVENT_CLASS(bcache_request,
- TP_PROTO(struct search *s, struct bio *bio),
- TP_ARGS(s, bio),
+ TP_PROTO(struct bcache_device *d, struct bio *bio),
+ TP_ARGS(d, bio),
TP_STRUCT__entry(
__field(dev_t, dev )
@@ -24,8 +22,8 @@ DECLARE_EVENT_CLASS(bcache_request,
TP_fast_assign(
__entry->dev = bio->bi_bdev->bd_dev;
- __entry->orig_major = s->d->disk->major;
- __entry->orig_minor = s->d->disk->first_minor;
+ __entry->orig_major = d->disk->major;
+ __entry->orig_minor = d->disk->first_minor;
__entry->sector = bio->bi_sector;
__entry->orig_sector = bio->bi_sector - 16;
__entry->nr_sector = bio->bi_size >> 9;
@@ -79,13 +77,13 @@ DECLARE_EVENT_CLASS(btree_node,
/* request.c */
DEFINE_EVENT(bcache_request, bcache_request_start,
- TP_PROTO(struct search *s, struct bio *bio),
- TP_ARGS(s, bio)
+ TP_PROTO(struct bcache_device *d, struct bio *bio),
+ TP_ARGS(d, bio)
);
DEFINE_EVENT(bcache_request, bcache_request_end,
- TP_PROTO(struct search *s, struct bio *bio),
- TP_ARGS(s, bio)
+ TP_PROTO(struct bcache_device *d, struct bio *bio),
+ TP_ARGS(d, bio)
);
DECLARE_EVENT_CLASS(bcache_bio,
@@ -370,6 +368,35 @@ DEFINE_EVENT(btree_node, bcache_btree_set_root,
TP_ARGS(b)
);
+TRACE_EVENT(bcache_keyscan,
+ TP_PROTO(unsigned nr_found,
+ unsigned start_inode, uint64_t start_offset,
+ unsigned end_inode, uint64_t end_offset),
+ TP_ARGS(nr_found,
+ start_inode, start_offset,
+ end_inode, end_offset),
+
+ TP_STRUCT__entry(
+ __field(__u32, nr_found )
+ __field(__u32, start_inode )
+ __field(__u64, start_offset )
+ __field(__u32, end_inode )
+ __field(__u64, end_offset )
+ ),
+
+ TP_fast_assign(
+ __entry->nr_found = nr_found;
+ __entry->start_inode = start_inode;
+ __entry->start_offset = start_offset;
+ __entry->end_inode = end_inode;
+ __entry->end_offset = end_offset;
+ ),
+
+ TP_printk("found %u keys from %u:%llu to %u:%llu", __entry->nr_found,
+ __entry->start_inode, __entry->start_offset,
+ __entry->end_inode, __entry->end_offset)
+);
+
/* Allocator */
TRACE_EVENT(bcache_alloc_invalidate,
diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h
new file mode 100644
index 000000000000..164a7e263988
--- /dev/null
+++ b/include/uapi/linux/bcache.h
@@ -0,0 +1,373 @@
+#ifndef _LINUX_BCACHE_H
+#define _LINUX_BCACHE_H
+
+/*
+ * Bcache on disk data structures
+ */
+
+#include <asm/types.h>
+
+#define BITMASK(name, type, field, offset, size) \
+static inline __u64 name(const type *k) \
+{ return (k->field >> offset) & ~(~0ULL << size); } \
+ \
+static inline void SET_##name(type *k, __u64 v) \
+{ \
+ k->field &= ~(~(~0ULL << size) << offset); \
+ k->field |= (v & ~(~0ULL << size)) << offset; \
+}
+
+/* Btree keys - all units are in sectors */
+
+struct bkey {
+ __u64 high;
+ __u64 low;
+ __u64 ptr[];
+};
+
+#define KEY_FIELD(name, field, offset, size) \
+ BITMASK(name, struct bkey, field, offset, size)
+
+#define PTR_FIELD(name, offset, size) \
+static inline __u64 name(const struct bkey *k, unsigned i) \
+{ return (k->ptr[i] >> offset) & ~(~0ULL << size); } \
+ \
+static inline void SET_##name(struct bkey *k, unsigned i, __u64 v) \
+{ \
+ k->ptr[i] &= ~(~(~0ULL << size) << offset); \
+ k->ptr[i] |= (v & ~(~0ULL << size)) << offset; \
+}
+
+#define KEY_SIZE_BITS 16
+
+KEY_FIELD(KEY_PTRS, high, 60, 3)
+KEY_FIELD(HEADER_SIZE, high, 58, 2)
+KEY_FIELD(KEY_CSUM, high, 56, 2)
+KEY_FIELD(KEY_PINNED, high, 55, 1)
+KEY_FIELD(KEY_DIRTY, high, 36, 1)
+
+KEY_FIELD(KEY_SIZE, high, 20, KEY_SIZE_BITS)
+KEY_FIELD(KEY_INODE, high, 0, 20)
+
+/* Next time I change the on disk format, KEY_OFFSET() won't be 64 bits */
+
+static inline __u64 KEY_OFFSET(const struct bkey *k)
+{
+ return k->low;
+}
+
+static inline void SET_KEY_OFFSET(struct bkey *k, __u64 v)
+{
+ k->low = v;
+}
+
+/*
+ * The high bit being set is a relic from when we used it to do binary
+ * searches - it told you where a key started. It's not used anymore,
+ * and can probably be safely dropped.
+ */
+#define KEY(inode, offset, size) \
+((struct bkey) { \
+ .high = (1ULL << 63) | ((__u64) (size) << 20) | (inode), \
+ .low = (offset) \
+})
+
+#define ZERO_KEY KEY(0, 0, 0)
+
+#define MAX_KEY_INODE (~(~0 << 20))
+#define MAX_KEY_OFFSET (~0ULL >> 1)
+#define MAX_KEY KEY(MAX_KEY_INODE, MAX_KEY_OFFSET, 0)
+
+#define KEY_START(k) (KEY_OFFSET(k) - KEY_SIZE(k))
+#define START_KEY(k) KEY(KEY_INODE(k), KEY_START(k), 0)
+
+#define PTR_DEV_BITS 12
+
+PTR_FIELD(PTR_DEV, 51, PTR_DEV_BITS)
+PTR_FIELD(PTR_OFFSET, 8, 43)
+PTR_FIELD(PTR_GEN, 0, 8)
+
+#define PTR_CHECK_DEV ((1 << PTR_DEV_BITS) - 1)
+
+#define PTR(gen, offset, dev) \
+ ((((__u64) dev) << 51) | ((__u64) offset) << 8 | gen)
+
+/* Bkey utility code */
+
+static inline unsigned long bkey_u64s(const struct bkey *k)
+{
+ return (sizeof(struct bkey) / sizeof(__u64)) + KEY_PTRS(k);
+}
+
+static inline unsigned long bkey_bytes(const struct bkey *k)
+{
+ return bkey_u64s(k) * sizeof(__u64);
+}
+
+#define bkey_copy(_dest, _src) memcpy(_dest, _src, bkey_bytes(_src))
+
+static inline void bkey_copy_key(struct bkey *dest, const struct bkey *src)
+{
+ SET_KEY_INODE(dest, KEY_INODE(src));
+ SET_KEY_OFFSET(dest, KEY_OFFSET(src));
+}
+
+static inline struct bkey *bkey_next(const struct bkey *k)
+{
+ __u64 *d = (void *) k;
+ return (struct bkey *) (d + bkey_u64s(k));
+}
+
+static inline struct bkey *bkey_last(const struct bkey *k, unsigned nr_keys)
+{
+ __u64 *d = (void *) k;
+ return (struct bkey *) (d + nr_keys);
+}
+/* Enough for a key with 6 pointers */
+#define BKEY_PAD 8
+
+#define BKEY_PADDED(key) \
+ union { struct bkey key; __u64 key ## _pad[BKEY_PAD]; }
+
+/* Superblock */
+
+/* Version 0: Cache device
+ * Version 1: Backing device
+ * Version 2: Seed pointer into btree node checksum
+ * Version 3: Cache device with new UUID format
+ * Version 4: Backing device with data offset
+ */
+#define BCACHE_SB_VERSION_CDEV 0
+#define BCACHE_SB_VERSION_BDEV 1
+#define BCACHE_SB_VERSION_CDEV_WITH_UUID 3
+#define BCACHE_SB_VERSION_BDEV_WITH_OFFSET 4
+#define BCACHE_SB_MAX_VERSION 4
+
+#define SB_SECTOR 8
+#define SB_SIZE 4096
+#define SB_LABEL_SIZE 32
+#define SB_JOURNAL_BUCKETS 256U
+/* SB_JOURNAL_BUCKETS must be divisible by BITS_PER_LONG */
+#define MAX_CACHES_PER_SET 8
+
+#define BDEV_DATA_START_DEFAULT 16 /* sectors */
+
+struct cache_sb {
+ __u64 csum;
+ __u64 offset; /* sector where this sb was written */
+ __u64 version;
+
+ __u8 magic[16];
+
+ __u8 uuid[16];
+ union {
+ __u8 set_uuid[16];
+ __u64 set_magic;
+ };
+ __u8 label[SB_LABEL_SIZE];
+
+ __u64 flags;
+ __u64 seq;
+ __u64 pad[8];
+
+ union {
+ struct {
+ /* Cache devices */
+ __u64 nbuckets; /* device size */
+
+ __u16 block_size; /* sectors */
+ __u16 bucket_size; /* sectors */
+
+ __u16 nr_in_set;
+ __u16 nr_this_dev;
+ };
+ struct {
+ /* Backing devices */
+ __u64 data_offset;
+
+ /*
+ * block_size from the cache device section is still used by
+ * backing devices, so don't add anything here until we fix
+ * things to not need it for backing devices anymore
+ */
+ };
+ };
+
+ __u32 last_mount; /* time_t */
+
+ __u16 first_bucket;
+ union {
+ __u16 njournal_buckets;
+ __u16 keys;
+ };
+ __u64 d[SB_JOURNAL_BUCKETS]; /* journal buckets */
+};
+
+static inline _Bool SB_IS_BDEV(const struct cache_sb *sb)
+{
+ return sb->version == BCACHE_SB_VERSION_BDEV
+ || sb->version == BCACHE_SB_VERSION_BDEV_WITH_OFFSET;
+}
+
+BITMASK(CACHE_SYNC, struct cache_sb, flags, 0, 1);
+BITMASK(CACHE_DISCARD, struct cache_sb, flags, 1, 1);
+BITMASK(CACHE_REPLACEMENT, struct cache_sb, flags, 2, 3);
+#define CACHE_REPLACEMENT_LRU 0U
+#define CACHE_REPLACEMENT_FIFO 1U
+#define CACHE_REPLACEMENT_RANDOM 2U
+
+BITMASK(BDEV_CACHE_MODE, struct cache_sb, flags, 0, 4);
+#define CACHE_MODE_WRITETHROUGH 0U
+#define CACHE_MODE_WRITEBACK 1U
+#define CACHE_MODE_WRITEAROUND 2U
+#define CACHE_MODE_NONE 3U
+BITMASK(BDEV_STATE, struct cache_sb, flags, 61, 2);
+#define BDEV_STATE_NONE 0U
+#define BDEV_STATE_CLEAN 1U
+#define BDEV_STATE_DIRTY 2U
+#define BDEV_STATE_STALE 3U
+
+/*
+ * Magic numbers
+ *
+ * The various other data structures have their own magic numbers, which are
+ * xored with the first part of the cache set's UUID
+ */
+
+#define JSET_MAGIC 0x245235c1a3625032ULL
+#define PSET_MAGIC 0x6750e15f87337f91ULL
+#define BSET_MAGIC 0x90135c78b99e07f5ULL
+
+static inline __u64 jset_magic(struct cache_sb *sb)
+{
+ return sb->set_magic ^ JSET_MAGIC;
+}
+
+static inline __u64 pset_magic(struct cache_sb *sb)
+{
+ return sb->set_magic ^ PSET_MAGIC;
+}
+
+static inline __u64 bset_magic(struct cache_sb *sb)
+{
+ return sb->set_magic ^ BSET_MAGIC;
+}
+
+/*
+ * Journal
+ *
+ * On disk format for a journal entry:
+ * seq is monotonically increasing; every journal entry has its own unique
+ * sequence number.
+ *
+ * last_seq is the oldest journal entry that still has keys the btree hasn't
+ * flushed to disk yet.
+ *
+ * version is for on disk format changes.
+ */
+
+#define BCACHE_JSET_VERSION_UUIDv1 1
+#define BCACHE_JSET_VERSION_UUID 1 /* Always latest UUID format */
+#define BCACHE_JSET_VERSION 1
+
+struct jset {
+ __u64 csum;
+ __u64 magic;
+ __u64 seq;
+ __u32 version;
+ __u32 keys;
+
+ __u64 last_seq;
+
+ BKEY_PADDED(uuid_bucket);
+ BKEY_PADDED(btree_root);
+ __u16 btree_level;
+ __u16 pad[3];
+
+ __u64 prio_bucket[MAX_CACHES_PER_SET];
+
+ union {
+ struct bkey start[0];
+ __u64 d[0];
+ };
+};
+
+/* Bucket prios/gens */
+
+struct prio_set {
+ __u64 csum;
+ __u64 magic;
+ __u64 seq;
+ __u32 version;
+ __u32 pad;
+
+ __u64 next_bucket;
+
+ struct bucket_disk {
+ __u16 prio;
+ __u8 gen;
+ } __attribute((packed)) data[];
+};
+
+/* UUIDS - per backing device/flash only volume metadata */
+
+struct uuid_entry {
+ union {
+ struct {
+ __u8 uuid[16];
+ __u8 label[32];
+ __u32 first_reg;
+ __u32 last_reg;
+ __u32 invalidated;
+
+ __u32 flags;
+ /* Size of flash only volumes */
+ __u64 sectors;
+ };
+
+ __u8 pad[128];
+ };
+};
+
+BITMASK(UUID_FLASH_ONLY, struct uuid_entry, flags, 0, 1);
+
+/* Btree nodes */
+
+/* Version 1: Seed pointer into btree node checksum
+ */
+#define BCACHE_BSET_CSUM 1
+#define BCACHE_BSET_VERSION 1
+
+/*
+ * Btree nodes
+ *
+ * On disk a btree node is a list/log of these; within each set the keys are
+ * sorted
+ */
+struct bset {
+ __u64 csum;
+ __u64 magic;
+ __u64 seq;
+ __u32 version;
+ __u32 keys;
+
+ union {
+ struct bkey start[0];
+ __u64 d[0];
+ };
+};
+
+/* OBSOLETE */
+
+/* UUIDS - per backing device/flash only volume metadata */
+
+struct uuid_entry_v0 {
+ __u8 uuid[16];
+ __u8 label[32];
+ __u32 first_reg;
+ __u32 last_reg;
+ __u32 invalidated;
+ __u32 pad;
+};
+
+#endif /* _LINUX_BCACHE_H */