[Bcache v15 12/16] bcache: Bset code (lookups within a btree node)

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Signed-off-by: Kent Overstreet <koverstreet@xxxxxxxxxx>
---
 drivers/md/bcache/bset.c | 1165 ++++++++++++++++++++++++++++++++++++++++++++++
 drivers/md/bcache/bset.h |  372 +++++++++++++++
 2 files changed, 1537 insertions(+), 0 deletions(-)
 create mode 100644 drivers/md/bcache/bset.c
 create mode 100644 drivers/md/bcache/bset.h

diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
new file mode 100644
index 0000000..41d1de5
--- /dev/null
+++ b/drivers/md/bcache/bset.c
@@ -0,0 +1,1165 @@
+
+#include "bcache.h"
+#include "btree.h"
+#include "debug.h"
+
+#include <linux/random.h>
+
+/* Keylists */
+
+void bch_keylist_copy(struct keylist *dest, struct keylist *src)
+{
+	*dest = *src;
+
+	if (src->list == src->d) {
+		size_t n = (uint64_t *) src->top - src->d;
+		dest->top = (struct bkey *) &dest->d[n];
+		dest->list = dest->d;
+	}
+}
+
+int bch_keylist_realloc(struct keylist *l, int nptrs, struct cache_set *c)
+{
+	unsigned oldsize = (uint64_t *) l->top - l->list;
+	unsigned newsize = oldsize + 2 + nptrs;
+	uint64_t *new;
+
+	/* The journalling code doesn't handle the case where the keys to insert
+	 * is bigger than an empty write: If we just return -ENOMEM here,
+	 * bio_insert() and bio_invalidate() will insert the keys created so far
+	 * and finish the rest when the keylist is empty.
+	 */
+	if (newsize * sizeof(uint64_t) > block_bytes(c) - sizeof(struct jset))
+		return -ENOMEM;
+
+	newsize = roundup_pow_of_two(newsize);
+
+	if (newsize <= KEYLIST_INLINE ||
+	    roundup_pow_of_two(oldsize) == newsize)
+		return 0;
+
+	new = krealloc(l->list == l->d ? NULL : l->list,
+		       sizeof(uint64_t) * newsize, GFP_NOIO);
+
+	if (!new)
+		return -ENOMEM;
+
+	if (l->list == l->d)
+		memcpy(new, l->list, sizeof(uint64_t) * KEYLIST_INLINE);
+
+	l->list = new;
+	l->top = (struct bkey *) (&l->list[oldsize]);
+
+	return 0;
+}
+
+struct bkey *bch_keylist_pop(struct keylist *l)
+{
+	struct bkey *k = l->bottom;
+
+	if (k == l->top)
+		return NULL;
+
+	while (bkey_next(k) != l->top)
+		k = bkey_next(k);
+
+	return l->top = k;
+}
+
+/* Pointer validation */
+
+bool __bch_ptr_invalid(struct cache_set *c, int level, const struct bkey *k)
+{
+	if (level && (!KEY_PTRS(k) || !KEY_SIZE(k) || KEY_DIRTY(k)))
+		goto bad;
+
+	if (!level && KEY_SIZE(k) > KEY_OFFSET(k))
+		goto bad;
+
+	if (!KEY_SIZE(k))
+		return true;
+
+	for (unsigned i = 0; i < KEY_PTRS(k); i++)
+		if (ptr_available(c, k, i)) {
+			struct cache *ca = PTR_CACHE(c, k, i);
+			size_t bucket = PTR_BUCKET_NR(c, k, i);
+			size_t r = bucket_remainder(c, PTR_OFFSET(k, i));
+
+			if (KEY_SIZE(k) + r > c->sb.bucket_size ||
+			    bucket <  ca->sb.first_bucket ||
+			    bucket >= ca->sb.nbuckets)
+				goto bad;
+		}
+
+	return false;
+bad:
+	cache_bug(c, "spotted bad key %s: %s", pkey(k), bch_ptr_status(c, k));
+	return true;
+}
+
+bool bch_ptr_bad(struct btree *b, const struct bkey *k)
+{
+	struct bucket *g;
+	unsigned i, stale;
+
+	if (!bkey_cmp(k, &ZERO_KEY) ||
+	    !KEY_PTRS(k) ||
+	    bch_ptr_invalid(b, k))
+		return true;
+
+	if (KEY_PTRS(k) && PTR_DEV(k, 0) == PTR_CHECK_DEV)
+		return true;
+
+	for (i = 0; i < KEY_PTRS(k); i++)
+		if (ptr_available(b->c, k, i)) {
+			g = PTR_BUCKET(b->c, k, i);
+			stale = ptr_stale(b->c, k, i);
+
+			btree_bug_on(stale > 96, b,
+				     "key too stale: %i, need_gc %u",
+				     stale, b->c->need_gc);
+
+			btree_bug_on(stale && KEY_DIRTY(k) && KEY_SIZE(k),
+				     b, "stale dirty pointer");
+
+			if (stale)
+				return true;
+
+#ifdef CONFIG_BCACHE_EDEBUG
+			if (!mutex_trylock(&b->c->bucket_lock))
+				continue;
+
+			if (b->level) {
+				if (KEY_DIRTY(k) ||
+				    g->prio != BTREE_PRIO ||
+				    (b->c->gc_mark_valid &&
+				     GC_MARK(g) != GC_MARK_BTREE))
+					goto bug;
+
+			} else {
+				if (g->prio == BTREE_PRIO)
+					goto bug;
+
+				if (KEY_DIRTY(k) &&
+				    b->c->gc_mark_valid &&
+				    GC_MARK(g) != GC_MARK_DIRTY)
+					goto bug;
+			}
+			mutex_unlock(&b->c->bucket_lock);
+#endif
+		}
+
+	return false;
+#ifdef CONFIG_BCACHE_EDEBUG
+bug:
+	mutex_unlock(&b->c->bucket_lock);
+	btree_bug(b, "inconsistent pointer %s: bucket %li pin %i "
+		  "prio %i gen %i last_gc %i mark %llu gc_gen %i", pkey(k),
+		  PTR_BUCKET_NR(b->c, k, i), atomic_read(&g->pin),
+		  g->prio, g->gen, g->last_gc, GC_MARK(g), g->gc_gen);
+	return true;
+#endif
+}
+
+/* Key/pointer manipulation */
+
+void bch_bkey_copy_single_ptr(struct bkey *dest, const struct bkey *src, unsigned i)
+{
+	BUG_ON(i > KEY_PTRS(src));
+
+	/* Only copy the header, key, and one pointer. */
+	memcpy(dest, src, 2 * sizeof(uint64_t));
+	dest->ptr[0] = src->ptr[i];
+	SET_KEY_PTRS(dest, 1);
+	/* We didn't copy the checksum so clear that bit. */
+	SET_KEY_CSUM(dest, 0);
+}
+
+bool __bch_cut_front(const struct bkey *where, struct bkey *k)
+{
+	unsigned len = 0;
+
+	if (bkey_cmp(where, &START_KEY(k)) <= 0)
+		return false;
+
+	if (bkey_cmp(where, k) < 0)
+		len = KEY_OFFSET(k) - KEY_OFFSET(where);
+	else
+		bkey_copy_key(k, where);
+
+	for (unsigned i = 0; i < KEY_PTRS(k); i++)
+		SET_PTR_OFFSET(k, i, PTR_OFFSET(k, i) + KEY_SIZE(k) - len);
+
+	BUG_ON(len > KEY_SIZE(k));
+	SET_KEY_SIZE(k, len);
+	return true;
+}
+
+bool __bch_cut_back(const struct bkey *where, struct bkey *k)
+{
+	unsigned len = 0;
+
+	if (bkey_cmp(where, k) >= 0)
+		return false;
+
+	BUG_ON(KEY_INODE(where) != KEY_INODE(k));
+
+	if (bkey_cmp(where, &START_KEY(k)) > 0)
+		len = KEY_OFFSET(where) - KEY_START(k);
+
+	bkey_copy_key(k, where);
+
+	BUG_ON(len > KEY_SIZE(k));
+	SET_KEY_SIZE(k, len);
+	return true;
+}
+
+static uint64_t merge_chksums(struct bkey *l, struct bkey *r)
+{
+	return (l->ptr[KEY_PTRS(l)] + r->ptr[KEY_PTRS(r)]) &
+		~((uint64_t)1 << 63);
+}
+
+/* Tries to merge l and r: l should be lower than r
+ * Returns true if we were able to merge. If we did merge, l will be the merged
+ * key, r will be untouched.
+ */
+bool bch_bkey_try_merge(struct btree *b, struct bkey *l, struct bkey *r)
+{
+	if (key_merging_disabled(b->c))
+		return false;
+
+	if (KEY_PTRS(l) != KEY_PTRS(r) ||
+	    KEY_DIRTY(l) != KEY_DIRTY(r) ||
+	    bkey_cmp(l, &START_KEY(r)))
+		return false;
+
+	for (unsigned j = 0; j < KEY_PTRS(l); j++)
+		if (l->ptr[j] + PTR(0, KEY_SIZE(l), 0) != r->ptr[j] ||
+		    PTR_BUCKET_NR(b->c, l, j) != PTR_BUCKET_NR(b->c, r, j))
+			return false;
+
+	/* Keys with no pointers aren't restricted to one bucket and could
+	 * overflow KEY_SIZE
+	 */
+	if (KEY_SIZE(l) + KEY_SIZE(r) > USHRT_MAX) {
+		SET_KEY_OFFSET(l, KEY_OFFSET(l) + USHRT_MAX - KEY_SIZE(l));
+		SET_KEY_SIZE(l, USHRT_MAX);
+
+		bch_cut_front(l, r);
+		return false;
+	}
+
+	if (KEY_CSUM(l)) {
+		if (KEY_CSUM(r))
+			l->ptr[KEY_PTRS(l)] = merge_chksums(l, r);
+		else
+			SET_KEY_CSUM(l, 0);
+	}
+
+	SET_KEY_OFFSET(l, KEY_OFFSET(l) + KEY_SIZE(r));
+	SET_KEY_SIZE(l, KEY_SIZE(l) + KEY_SIZE(r));
+
+	return true;
+}
+
+/* Binary tree stuff for auxiliary search trees */
+
+static unsigned inorder_next(unsigned j, unsigned size)
+{
+	if (j * 2 + 1 < size) {
+		j = j * 2 + 1;
+
+		while (j * 2 < size)
+			j *= 2;
+	} else
+		j >>= ffz(j) + 1;
+
+	return j;
+}
+
+static unsigned inorder_prev(unsigned j, unsigned size)
+{
+	if (j * 2 < size) {
+		j = j * 2;
+
+		while (j * 2 + 1 < size)
+			j = j * 2 + 1;
+	} else
+		j >>= ffs(j);
+
+	return j;
+}
+
+/* I have no idea why this code works... and I'm the one who wrote it
+ *
+ * However, I do know what it does:
+ * Given a binary tree constructed in an array (i.e. how you normally implement
+ * a heap), it converts a node in the tree - referenced by array index - to the
+ * index it would have if you did an inorder traversal.
+ *
+ * Also tested for every j, size up to size somewhere around 6 million.
+ *
+ * The binary tree starts at array index 1, not 0
+ * extra is a function of size:
+ *   extra = (size - rounddown_pow_of_two(size - 1)) << 1;
+ */
+static unsigned __to_inorder(unsigned j, unsigned size, unsigned extra)
+{
+	unsigned b = fls(j);
+	unsigned shift = fls(size - 1) - b;
+
+	j  ^= 1U << (b - 1);
+	j <<= 1;
+	j  |= 1;
+	j <<= shift;
+
+	if (j > extra)
+		j -= (j - extra) >> 1;
+
+	return j;
+}
+
+static unsigned to_inorder(unsigned j, struct bset_tree *t)
+{
+	return __to_inorder(j, t->size, t->extra);
+}
+
+static unsigned __inorder_to_tree(unsigned j, unsigned size, unsigned extra)
+{
+	unsigned shift;
+
+	if (j > extra)
+		j += j - extra;
+
+	shift = ffs(j);
+
+	j >>= shift;
+	j  |= roundup_pow_of_two(size) >> shift;
+
+	return j;
+}
+
+static unsigned inorder_to_tree(unsigned j, struct bset_tree *t)
+{
+	return __inorder_to_tree(j, t->size, t->extra);
+}
+
+#if 0
+void inorder_test(void)
+{
+	unsigned long done = 0;
+	ktime_t start = ktime_get();
+
+	for (unsigned size = 2;
+	     size < 65536000;
+	     size++) {
+		unsigned extra = (size - rounddown_pow_of_two(size - 1)) << 1;
+		unsigned i = 1, j = rounddown_pow_of_two(size - 1);
+
+		if (!(size % 4096))
+			printk(KERN_NOTICE "loop %u, %llu per us\n", size,
+			       done / ktime_us_delta(ktime_get(), start));
+
+		while (1) {
+			if (__inorder_to_tree(i, size, extra) != j)
+				panic("size %10u j %10u i %10u", size, j, i);
+
+			if (__to_inorder(j, size, extra) != i)
+				panic("size %10u j %10u i %10u", size, j, i);
+
+			if (j == rounddown_pow_of_two(size) - 1)
+				break;
+
+			BUG_ON(inorder_prev(inorder_next(j, size), size) != j);
+
+			j = inorder_next(j, size);
+			i++;
+		}
+
+		done += size - 1;
+	}
+}
+#endif
+
+/*
+ * Cacheline/offset <-> bkey pointer arithmatic:
+ *
+ * t->tree is a binary search tree in an array; each node corresponds to a key
+ * in one cacheline in t->set (BSET_CACHELINE bytes).
+ *
+ * This means we don't have to store the full index of the key that a node in
+ * the binary tree points to; to_inorder() gives us the cacheline, and then
+ * bkey_float->m gives us the offset within that cacheline, in units of 8 bytes.
+ *
+ * cacheline_to_bkey() and friends abstract out all the pointer arithmatic to
+ * make this work.
+ *
+ * To construct the bfloat for an arbitrary key we need to know what the key
+ * immediately preceding it is: we have to check if the two keys differ in the
+ * bits we're going to store in bkey_float->mantissa. t->prev[j] stores the size
+ * of the previous key so we can walk backwards to it from t->tree[j]'s key.
+ */
+
+static struct bkey *cacheline_to_bkey(struct bset_tree *t, unsigned cacheline,
+				      unsigned offset)
+{
+	return ((void *) t->data) + cacheline * BSET_CACHELINE + offset * 8;
+}
+
+static unsigned bkey_to_cacheline(struct bset_tree *t, struct bkey *k)
+{
+	return ((void *) k - (void *) t->data) / BSET_CACHELINE;
+}
+
+static unsigned bkey_to_cacheline_offset(struct bkey *k)
+{
+	return ((size_t) k & (BSET_CACHELINE - 1)) / sizeof(uint64_t);
+}
+
+static struct bkey *tree_to_bkey(struct bset_tree *t, unsigned j)
+{
+	return cacheline_to_bkey(t, to_inorder(j, t), t->tree[j].m);
+}
+
+static struct bkey *tree_to_prev_bkey(struct bset_tree *t, unsigned j)
+{
+	return (void *) (((uint64_t *) tree_to_bkey(t, j)) - t->prev[j]);
+}
+
+/*
+ * For the write set - the one we're currently inserting keys into - we don't
+ * maintain a full search tree, we just keep a simple lookup table in t->prev.
+ */
+static struct bkey *table_to_bkey(struct bset_tree *t, unsigned cacheline)
+{
+	return cacheline_to_bkey(t, cacheline, t->prev[cacheline]);
+}
+
+static inline uint64_t shrd128(uint64_t high, uint64_t low, uint8_t shift)
+{
+#ifdef CONFIG_X86_64
+	asm("shrd %[shift],%[high],%[low]"
+	    : [low] "+Rm" (low)
+	    : [high] "R" (high),
+	    [shift] "ci" (shift)
+	    : "cc");
+#else
+	low >>= shift;
+	low  |= (high << 1) << (63U - shift);
+#endif
+	return low;
+}
+
+static inline unsigned bfloat_mantissa(const struct bkey *k,
+				       struct bkey_float *f)
+{
+	const uint64_t *p = &k->low - (f->exponent >> 6);
+	return shrd128(p[-1], p[0], f->exponent & 63) & BKEY_MANTISSA_MASK;
+}
+
+static void make_bfloat(struct bset_tree *t, unsigned j)
+{
+	struct bkey_float *f = &t->tree[j];
+	struct bkey *m = tree_to_bkey(t, j);
+	struct bkey *p = tree_to_prev_bkey(t, j);
+
+	struct bkey *l = is_power_of_2(j)
+		? t->data->start
+		: tree_to_prev_bkey(t, j >> ffs(j));
+
+	struct bkey *r = is_power_of_2(j + 1)
+		? node(t->data, t->data->keys - bkey_u64s(&t->end))
+		: tree_to_bkey(t, j >> (ffz(j) + 1));
+
+	BUG_ON(m < l || m > r);
+	BUG_ON(bkey_next(p) != m);
+
+	if (KEY_INODE(l) != KEY_INODE(r))
+		f->exponent = fls64(KEY_INODE(r) ^ KEY_INODE(l)) + 64;
+	else
+		f->exponent = fls64(r->low ^ l->low);
+
+	f->exponent = max_t(int, f->exponent - BKEY_MANTISSA_BITS, 0);
+
+	/*
+	 * Setting f->exponent = 127 flags this node as failed, and causes the
+	 * lookup code to fall back to comparing against the original key.
+	 */
+
+	if (bfloat_mantissa(m, f) != bfloat_mantissa(p, f))
+		f->mantissa = bfloat_mantissa(m, f) - 1;
+	else
+		f->exponent = 127;
+}
+
+static void bset_alloc_tree(struct btree *b, struct bset_tree *t)
+{
+	if (t != b->sets) {
+		unsigned j = roundup(t[-1].size,
+				     64 / sizeof(struct bkey_float));
+
+		t->tree = t[-1].tree + j;
+		t->prev = t[-1].prev + j;
+	}
+
+	while (t < b->sets + MAX_BSETS)
+		t++->size = 0;
+}
+
+static void bset_build_unwritten_tree(struct btree *b)
+{
+	struct bset_tree *t = b->sets + b->nsets;
+
+	bset_alloc_tree(b, t);
+
+	if (t->tree != b->sets->tree + bset_tree_space(b)) {
+		t->prev[0] = bkey_to_cacheline_offset(t->data->start);
+		t->size = 1;
+	}
+}
+
+static void bset_build_written_tree(struct btree *b)
+{
+	struct bset_tree *t = b->sets + b->nsets;
+	struct bkey *k = t->data->start;
+	unsigned j, cacheline = 1;
+
+	bset_alloc_tree(b, t);
+
+	t->size = min_t(unsigned,
+			bkey_to_cacheline(t, end(t->data)),
+			b->sets->tree + bset_tree_space(b) - t->tree);
+
+	if (t->size < 2) {
+		t->size = 0;
+		return;
+	}
+
+	t->extra = (t->size - rounddown_pow_of_two(t->size - 1)) << 1;
+
+	/* First we figure out where the first key in each cacheline is */
+	for (j = inorder_next(0, t->size);
+	     j;
+	     j = inorder_next(j, t->size)) {
+		while (bkey_to_cacheline(t, k) != cacheline)
+			k = bkey_next(k);
+
+		t->prev[j] = bkey_u64s(k);
+		k = bkey_next(k);
+		cacheline++;
+		t->tree[j].m = bkey_to_cacheline_offset(k);
+	}
+
+	while (bkey_next(k) != end(t->data))
+		k = bkey_next(k);
+
+	t->end = *k;
+
+	/* Then we build the tree */
+	for (j = inorder_next(0, t->size);
+	     j;
+	     j = inorder_next(j, t->size))
+		make_bfloat(t, j);
+}
+
+void bch_bset_fix_invalidated_key(struct btree *b, struct bkey *k)
+{
+	struct bset_tree *t;
+	unsigned inorder, j = 1;
+
+	for (t = b->sets; t <= &b->sets[b->nsets]; t++)
+		if (k < end(t->data))
+			goto found_set;
+
+	BUG();
+found_set:
+	if (!t->size || !bset_written(b, t))
+		return;
+
+	inorder = bkey_to_cacheline(t, k);
+
+	if (k == t->data->start)
+		goto fix_left;
+
+	if (bkey_next(k) == end(t->data)) {
+		t->end = *k;
+		goto fix_right;
+	}
+
+	j = inorder_to_tree(inorder, t);
+
+	if (j &&
+	    j < t->size &&
+	    k == tree_to_bkey(t, j))
+fix_left:	do {
+			make_bfloat(t, j);
+			j = j * 2;
+		} while (j < t->size);
+
+	j = inorder_to_tree(inorder + 1, t);
+
+	if (j &&
+	    j < t->size &&
+	    k == tree_to_prev_bkey(t, j))
+fix_right:	do {
+			make_bfloat(t, j);
+			j = j * 2 + 1;
+		} while (j < t->size);
+}
+
+void bch_bset_fix_lookup_table(struct btree *b, struct bkey *k)
+{
+	struct bset_tree *t = &b->sets[b->nsets];
+	unsigned shift = bkey_u64s(k);
+	unsigned j = bkey_to_cacheline(t, k);
+
+	/* We're getting called from btree_split() or btree_gc, just bail out */
+	if (!t->size)
+		return;
+
+	/* k is the key we just inserted; we need to find the entry in the
+	 * lookup table for the first key that is strictly greater than k:
+	 * it's either k's cacheline or the next one
+	 */
+	if (j < t->size &&
+	    table_to_bkey(t, j) <= k)
+		j++;
+
+	/* Adjust all the lookup table entries, and find a new key for any that
+	 * have gotten too big
+	 */
+	for (; j < t->size; j++) {
+		t->prev[j] += shift;
+
+		if (t->prev[j] > 7) {
+			k = table_to_bkey(t, j - 1);
+
+			while (k < cacheline_to_bkey(t, j, 0))
+				k = bkey_next(k);
+
+			t->prev[j] = bkey_to_cacheline_offset(k);
+		}
+	}
+
+	if (t->size == b->sets->tree + bset_tree_space(b) - t->tree)
+		return;
+
+	/* Possibly add a new entry to the end of the lookup table */
+
+	for (k = table_to_bkey(t, t->size - 1);
+	     k != end(t->data);
+	     k = bkey_next(k))
+		if (t->size == bkey_to_cacheline(t, k)) {
+			t->prev[t->size] = bkey_to_cacheline_offset(k);
+			t->size++;
+		}
+}
+
+void bch_bset_init_next(struct btree *b)
+{
+	struct bset *i = write_block(b);
+
+	if (i != b->sets[0].data) {
+		b->sets[++b->nsets].data = i;
+		i->seq = b->sets[0].data->seq;
+	} else
+		get_random_bytes(&i->seq, sizeof(uint64_t));
+
+	i->magic	= bset_magic(b->c);
+	i->version	= 0;
+	i->keys		= 0;
+
+	bset_build_unwritten_tree(b);
+}
+
+struct bset_search_iter {
+	struct bkey *l, *r;
+};
+
+static struct bset_search_iter bset_search_write_set(struct btree *b,
+						     struct bset_tree *t,
+						     const struct bkey *search)
+{
+	unsigned li = 0, ri = t->size;
+
+	BUG_ON(!b->nsets &&
+	       t->size < bkey_to_cacheline(t, end(t->data)));
+
+	while (li + 1 != ri) {
+		unsigned m = (li + ri) >> 1;
+
+		if (bkey_cmp(table_to_bkey(t, m), search) > 0)
+			ri = m;
+		else
+			li = m;
+	}
+
+	return (struct bset_search_iter) {
+		table_to_bkey(t, li),
+		ri < t->size ? table_to_bkey(t, ri) : end(t->data)
+	};
+}
+
+static struct bset_search_iter bset_search_tree(struct btree *b,
+						struct bset_tree *t,
+						const struct bkey *search)
+{
+	struct bkey *l, *r;
+	struct bkey_float *f;
+	unsigned inorder, j, n = 1;
+
+	do {
+		unsigned p = n << 4;
+		p &= ((int) (p - t->size)) >> 31;
+
+		prefetch(&t->tree[p]);
+
+		j = n;
+		f = &t->tree[j];
+
+		/*
+		 * n = (f->mantissa > bfloat_mantissa())
+		 *	? j * 2
+		 *	: j * 2 + 1;
+		 *
+		 * We need to subtract 1 from f->mantissa for the sign bit trick
+		 * to work  - that's done in make_bfloat()
+		 */
+		if (likely(f->exponent != 127))
+			n = j * 2 + (((unsigned)
+				      (f->mantissa -
+				       bfloat_mantissa(search, f))) >> 31);
+		else
+			n = (bkey_cmp(tree_to_bkey(t, j), search) > 0)
+				? j * 2
+				: j * 2 + 1;
+	} while (n < t->size);
+
+	inorder = to_inorder(j, t);
+
+	/*
+	 * n would have been the node we recursed to - the low bit tells us if
+	 * we recursed left or recursed right.
+	 */
+	if (n & 1) {
+		l = cacheline_to_bkey(t, inorder, f->m);
+
+		if (++inorder != t->size) {
+			f = &t->tree[inorder_next(j, t->size)];
+			r = cacheline_to_bkey(t, inorder, f->m);
+		} else
+			r = end(t->data);
+	} else {
+		r = cacheline_to_bkey(t, inorder, f->m);
+
+		if (--inorder) {
+			f = &t->tree[inorder_prev(j, t->size)];
+			l = cacheline_to_bkey(t, inorder, f->m);
+		} else
+			l = t->data->start;
+	}
+
+	return (struct bset_search_iter) {l, r};
+}
+
+struct bkey *__bch_bset_search(struct btree *b, struct bset_tree *t,
+			       const struct bkey *search)
+{
+	struct bset_search_iter i;
+
+	/*
+	 * First, we search for a cacheline, then lastly we do a linear search
+	 * within that cacheline.
+	 *
+	 * To search for the cacheline, there's three different possibilities:
+	 *  * The set is too small to have a search tree, so we just do a linear
+	 *    search over the whole set.
+	 *  * The set is the one we're currently inserting into; keeping a full
+	 *    auxiliary search tree up to date would be too expensive, so we
+	 *    use a much simpler lookup table to do a binary search -
+	 *    bset_search_write_set().
+	 *  * Or we use the auxiliary search tree we constructed earlier -
+	 *    bset_search_tree()
+	 */
+
+	if (unlikely(!t->size)) {
+		i.l = t->data->start;
+		i.r = end(t->data);
+	} else if (bset_written(b, t)) {
+		/*
+		 * Each node in the auxiliary search tree covers a certain range
+		 * of bits, and keys above and below the set it covers might
+		 * differ outside those bits - so we have to special case the
+		 * start and end - handle that here:
+		 */
+
+		if (unlikely(bkey_cmp(search, &t->end) >= 0))
+			return end(t->data);
+
+		if (unlikely(bkey_cmp(search, t->data->start) < 0))
+			return t->data->start;
+
+		i = bset_search_tree(b, t, search);
+	} else
+		i = bset_search_write_set(b, t, search);
+
+#ifdef CONFIG_BCACHE_EDEBUG
+	BUG_ON(bset_written(b, t) &&
+	       i.l != t->data->start &&
+	       bkey_cmp(tree_to_prev_bkey(t,
+		  inorder_to_tree(bkey_to_cacheline(t, i.l), t)),
+			search) > 0);
+
+	BUG_ON(i.r != end(t->data) &&
+	       bkey_cmp(i.r, search) <= 0);
+#endif
+
+	while (likely(i.l != i.r) &&
+	       bkey_cmp(i.l, search) <= 0)
+		i.l = bkey_next(i.l);
+
+	return i.l;
+}
+
+/* Btree iterator */
+
+static inline bool btree_iter_cmp(struct btree_iter_set l,
+				  struct btree_iter_set r)
+{
+	int64_t c = bkey_cmp(&START_KEY(l.k), &START_KEY(r.k));
+
+	return c ? c > 0 : l.k < r.k;
+}
+
+static inline bool btree_iter_end(struct btree_iter *iter)
+{
+	return !iter->used;
+}
+
+void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k, struct bkey *end)
+{
+	if (k != end)
+		BUG_ON(!heap_add(iter,
+				 ((struct btree_iter_set) { k, end }),
+				 btree_iter_cmp));
+}
+
+struct bkey *__bch_btree_iter_init(struct btree *b, struct btree_iter *iter,
+			       struct bkey *search, struct bset_tree *start)
+{
+	struct bkey *ret = NULL;
+	iter->size = ARRAY_SIZE(iter->data);
+	iter->used = 0;
+
+	for (; start <= &b->sets[b->nsets]; start++) {
+		ret = bch_bset_search(b, start, search);
+		bch_btree_iter_push(iter, ret, end(start->data));
+	}
+
+	return ret;
+}
+
+struct bkey *bch_btree_iter_next(struct btree_iter *iter)
+{
+	struct btree_iter_set unused;
+	struct bkey *ret = NULL;
+
+	if (!btree_iter_end(iter)) {
+		ret = iter->data->k;
+		iter->data->k = bkey_next(iter->data->k);
+
+		if (iter->data->k > iter->data->end) {
+			__WARN();
+			iter->data->k = iter->data->end;
+		}
+
+		if (iter->data->k == iter->data->end)
+			heap_pop(iter, unused, btree_iter_cmp);
+		else
+			heap_sift(iter, 0, btree_iter_cmp);
+	}
+
+	return ret;
+}
+
+struct bkey *bch_next_recurse_key(struct btree *b, struct bkey *search)
+{
+	struct bkey *ret;
+	struct btree_iter iter;
+	bch_btree_iter_init(b, &iter, search);
+
+	do
+		ret = bch_btree_iter_next(&iter);
+	while (ret && bch_ptr_bad(b, ret));
+
+	return ret;
+}
+
+/* Mergesort */
+
+static void btree_sort_fixup(struct btree_iter *iter)
+{
+	while (iter->used > 1) {
+		struct btree_iter_set *top = iter->data, *i = top + 1;
+		struct bkey *k;
+
+		if (iter->used > 2 &&
+		    btree_iter_cmp(i[0], i[1]))
+			i++;
+
+		for (k = i->k;
+		     k != i->end && bkey_cmp(top->k, &START_KEY(k)) > 0;
+		     k = bkey_next(k))
+			if (top->k > i->k)
+				__bch_cut_front(top->k, k);
+			else if (KEY_SIZE(k))
+				bch_cut_back(&START_KEY(k), top->k);
+
+		if (top->k < i->k || k == i->k)
+			break;
+
+		heap_sift(iter, i - top, btree_iter_cmp);
+	}
+}
+
+static void btree_mergesort(struct btree *b, struct bset *out,
+			    struct btree_iter *iter,
+			    bool fixup, bool remove_stale)
+{
+	struct bkey *k, *last = NULL;
+	bool (*bad)(struct btree *, const struct bkey *) = remove_stale
+		? bch_ptr_bad
+		: bch_ptr_invalid;
+
+	while (!btree_iter_end(iter)) {
+		if (fixup && !b->level)
+			btree_sort_fixup(iter);
+
+		k = bch_btree_iter_next(iter);
+		if (bad(b, k))
+			continue;
+
+		if (!last) {
+			last = out->start;
+			bkey_copy(last, k);
+		} else if (b->level ||
+			   !bch_bkey_try_merge(b, last, k)) {
+			last = bkey_next(last);
+			bkey_copy(last, k);
+		}
+	}
+
+	out->keys = last ? (uint64_t *) bkey_next(last) - out->d : 0;
+
+	pr_debug("sorted %i keys", out->keys);
+	bch_check_key_order(b, out);
+}
+
+static void __btree_sort(struct btree *b, struct btree_iter *iter,
+			 unsigned start, unsigned order, bool fixup)
+{
+	uint64_t start_time;
+	bool remove_stale = !b->written;
+	struct bset *out = (void *) __get_free_pages(__GFP_NOWARN|GFP_NOIO,
+						     order);
+	if (!out) {
+		mutex_lock(&b->c->sort_lock);
+		out = b->c->sort;
+		order = ilog2(bucket_pages(b->c));
+	}
+
+	start_time = local_clock();
+
+	btree_mergesort(b, out, iter, fixup, remove_stale);
+	b->nsets = start;
+
+	if (!fixup && !start && b->written)
+		bch_btree_verify(b, out);
+
+	if (!start && order == b->page_order) {
+		/*
+		 * Our temporary buffer is the same size as the btree node's
+		 * buffer, we can just swap buffers instead of doing a big
+		 * memcpy()
+		 */
+
+		out->magic	= bset_magic(b->c);
+		out->seq	= b->sets[0].data->seq;
+		out->version	= b->sets[0].data->version;
+		swap(out, b->sets[0].data);
+
+		if (b->c->sort == b->sets[0].data)
+			b->c->sort = out;
+	} else {
+		b->sets[start].data->keys = out->keys;
+		memcpy(b->sets[start].data->start, out->start,
+		       (void *) end(out) - (void *) out->start);
+	}
+
+	if (out == b->c->sort)
+		mutex_unlock(&b->c->sort_lock);
+	else
+		free_pages((unsigned long) out, order);
+
+	if (b->written)
+		bset_build_written_tree(b);
+
+	if (!start) {
+		spin_lock(&b->c->sort_time_lock);
+		time_stats_update(&b->c->sort_time, start_time);
+		spin_unlock(&b->c->sort_time_lock);
+	}
+}
+
+void bch_btree_sort_partial(struct btree *b, unsigned start)
+{
+	size_t oldsize = 0, order = b->page_order, keys = 0;
+	struct btree_iter iter;
+	__bch_btree_iter_init(b, &iter, NULL, &b->sets[start]);
+
+	BUG_ON(b->sets[b->nsets].data == write_block(b) &&
+	       (b->sets[b->nsets].size || b->nsets));
+
+	if (b->written)
+		oldsize = bch_count_data(b);
+
+	if (start) {
+		struct bset *i;
+		for_each_sorted_set_start(b, i, start)
+			keys += i->keys;
+
+		order = roundup_pow_of_two(__set_bytes(i, keys)) / PAGE_SIZE;
+		if (order)
+			order = ilog2(order);
+	}
+
+	__btree_sort(b, &iter, start, order, false);
+
+	EBUG_ON(b->written && bch_count_data(b) != oldsize);
+}
+
+void bch_btree_sort_and_fix_extents(struct btree *b, struct btree_iter *iter)
+{
+	BUG_ON(!b->written);
+	__btree_sort(b, iter, 0, b->page_order, true);
+}
+
+void bch_btree_sort_into(struct btree *b, struct btree *new)
+{
+	uint64_t start_time = local_clock();
+
+	struct btree_iter iter;
+	bch_btree_iter_init(b, &iter, NULL);
+
+	btree_mergesort(b, new->sets->data, &iter, false, true);
+
+	spin_lock(&b->c->sort_time_lock);
+	time_stats_update(&b->c->sort_time, start_time);
+	spin_unlock(&b->c->sort_time_lock);
+
+	bkey_copy_key(&new->key, &b->key);
+	new->sets->size = 0;
+}
+
+void bch_btree_sort_lazy(struct btree *b)
+{
+	if (b->nsets) {
+		struct bset *i;
+		unsigned keys = 0, total;
+
+		for_each_sorted_set(b, i)
+			keys += i->keys;
+		total = keys;
+
+		for (unsigned j = 0; j < b->nsets; j++) {
+			if (keys * 2 < total ||
+			    keys < 1000) {
+				bch_btree_sort_partial(b, j);
+				return;
+			}
+
+			keys -= b->sets[j].data->keys;
+		}
+
+		/* Must sort if b->nsets == 3 or we'll overflow */
+		if (b->nsets >= (MAX_BSETS - 1) - b->level) {
+			bch_btree_sort(b);
+			return;
+		}
+	}
+
+	bset_build_written_tree(b);
+}
+
+/* Sysfs stuff */
+
+struct bset_stats {
+	size_t nodes;
+	size_t sets_written, sets_unwritten;
+	size_t bytes_written, bytes_unwritten;
+	size_t floats, failed;
+};
+
+static int bch_btree_bset_stats(struct btree *b, struct btree_op *op,
+			    struct bset_stats *stats)
+{
+	struct bkey *k;
+
+	stats->nodes++;
+
+	for (int i = 0; i <= b->nsets; i++) {
+		struct bset_tree *t = &b->sets[i];
+		size_t bytes = t->data->keys * sizeof(uint64_t);
+
+		if (bset_written(b, t)) {
+			stats->sets_written++;
+			stats->bytes_written += bytes;
+
+			stats->floats += t->size - 1;
+
+			for (size_t j = 1; j < t->size; j++)
+				if (t->tree[j].exponent == 127)
+					stats->failed++;
+		} else {
+			stats->sets_unwritten++;
+			stats->bytes_unwritten += bytes;
+		}
+	}
+
+	if (b->level)
+		for_each_key_filter(b, k, bch_ptr_bad) {
+			int ret = btree(bset_stats, k, b, op, stats);
+			if (ret)
+				return ret;
+		}
+
+	return 0;
+}
+
+int bch_bset_print_stats(struct cache_set *c, char *buf)
+{
+	struct btree_op op;
+	struct bset_stats t;
+	int ret;
+
+	bch_btree_op_init_stack(&op);
+	memset(&t, 0, sizeof(struct bset_stats));
+
+	ret = btree_root(bset_stats, c, &op, &t);
+	if (ret)
+		return ret;
+
+	return snprintf(buf, PAGE_SIZE,
+			"btree nodes:		%zu\n"
+			"written sets:		%zu\n"
+			"unwritten sets:		%zu\n"
+			"written key bytes:	%zu\n"
+			"unwritten key bytes:	%zu\n"
+			"floats:			%zu\n"
+			"failed:			%zu\n",
+			t.nodes,
+			t.sets_written, t.sets_unwritten,
+			t.bytes_written, t.bytes_unwritten,
+			t.floats, t.failed);
+}
diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h
new file mode 100644
index 0000000..39fe22b
--- /dev/null
+++ b/drivers/md/bcache/bset.h
@@ -0,0 +1,372 @@
+#ifndef _BCACHE_BSET_H
+#define _BCACHE_BSET_H
+
+/*
+ * BKEYS:
+ *
+ * A bkey contains a key, a size field, a variable number of pointers, and some
+ * ancillary flag bits.
+ *
+ * We use two different functions for validating bkeys, bch_ptr_invalid and
+ * bch_ptr_bad().
+ *
+ * bch_ptr_invalid() primarily filters out keys and pointers that would be
+ * invalid due to some sort of bug, whereas bch_ptr_bad() filters out keys and
+ * pointer that occur in normal practice but don't point to real data.
+ *
+ * The one exception to the rule that ptr_invalid() filters out invalid keys is
+ * that it also filters out keys of size 0 - these are keys that have been
+ * completely overwritten. It'd be safe to delete these in memory while leaving
+ * them on disk, just unnecessary work - so we filter them out when resorting
+ * instead.
+ *
+ * We can't filter out stale keys when we're resorting, because garbage
+ * collection needs to find them to ensure bucket gens don't wrap around -
+ * unless we're rewriting the btree node those stale keys still exist on disk.
+ *
+ * We also implement functions here for removing some number of sectors from the
+ * front or the back of a bkey - this is mainly used for fixing overlapping
+ * extents, by removing the overlapping sectors from the older key.
+ *
+ * BSETS:
+ *
+ * A bset is an array of bkeys laid out contiguously in memory in sorted order,
+ * along with a header. A btree node is made up of a number of these, written at
+ * different times.
+ *
+ * There could be many of them on disk, but we never allow there to be more than
+ * 4 in memory - we lazily resort as needed.
+ *
+ * We implement code here for creating and maintaining auxiliary search trees
+ * (described below) for searching an individial bset, and on top of that we
+ * implement a btree iterator.
+ *
+ * BTREE ITERATOR:
+ *
+ * Most of the code in bcache doesn't care about an individual bset - it needs
+ * to search entire btree nodes and iterate over them in sorted order.
+ *
+ * The btree iterator code serves both functions; it iterates through the keys
+ * in a btree node in sorted order, starting from either keys after a specific
+ * point (if you pass it a search key) or the start of the btree node.
+ *
+ * AUXILIARY SEARCH TREES:
+ *
+ * Since keys are variable length, we can't use a binary search on a bset - we
+ * wouldn't be able to find the start of the next key. But binary searches are
+ * slow anyways, due to terrible cache behaviour; bcache originally used binary
+ * searches and that code topped out at under 50k lookups/second.
+ *
+ * So we need to construct some sort of lookup table. Since we only insert keys
+ * into the last (unwritten) set, most of the keys within a given btree node are
+ * usually in sets that are mostly constant. We use two different types of
+ * lookup tables to take advantage of this.
+ *
+ * Both lookup tables share in common that they don't index every key in the
+ * set; they index one key every BSET_CACHELINE bytes, and then a linear search
+ * is used for the rest.
+ *
+ * For sets that have been written to disk and are no longer being inserted
+ * into, we construct a binary search tree in an array - traversing a binary
+ * search tree in an array gives excellent locality of reference and is very
+ * fast, since both children of any node are adjacent to each other in memory
+ * (and their grandchildren, and great grandchildren...) - this means
+ * prefetching can be used to great effect.
+ *
+ * It's quite useful performance wise to keep these nodes small - not just
+ * because they're more likely to be in L2, but also because we can prefetch
+ * more nodes on a single cacheline and thus prefetch more iterations in advance
+ * when traversing this tree.
+ *
+ * Nodes in the auxiliary search tree must contain both a key to compare against
+ * (we don't want to fetch the key from the set, that would defeat the purpose),
+ * and a pointer to the key. We use a few tricks to compress both of these.
+ *
+ * To compress the pointer, we take advantage of the fact that one node in the
+ * search tree corresponds to precisely BSET_CACHELINE bytes in the set. We have
+ * a function (to_inorder()) that takes the index of a node in a binary tree and
+ * returns what its index would be in an inorder traversal, so we only have to
+ * store the low bits of the offset.
+ *
+ * The key is 84 bits (KEY_DEV + key->key, the offset on the device). To
+ * compress that,  we take advantage of the fact that when we're traversing the
+ * search tree at every iteration we know that both our search key and the key
+ * we're looking for lie within some range - bounded by our previous
+ * comparisons. (We special case the start of a search so that this is true even
+ * at the root of the tree).
+ *
+ * So we know the key we're looking for is between a and b, and a and b don't
+ * differ higher than bit 50, we don't need to check anything higher than bit
+ * 50.
+ *
+ * We don't usually need the rest of the bits, either; we only need enough bits
+ * to partition the key range we're currently checking.  Consider key n - the
+ * key our auxiliary search tree node corresponds to, and key p, the key
+ * immediately preceding n.  The lowest bit we need to store in the auxiliary
+ * search tree is the highest bit that differs between n and p.
+ *
+ * Note that this could be bit 0 - we might sometimes need all 80 bits to do the
+ * comparison. But we'd really like our nodes in the auxiliary search tree to be
+ * of fixed size.
+ *
+ * The solution is to make them fixed size, and when we're constructing a node
+ * check if p and n differed in the bits we needed them to. If they don't we
+ * flag that node, and when doing lookups we fallback to comparing against the
+ * real key. As long as this doesn't happen to often (and it seems to reliably
+ * happen a bit less than 1% of the time), we win - even on failures, that key
+ * is then more likely to be in cache than if we were doing binary searches all
+ * the way, since we're touching so much less memory.
+ *
+ * The keys in the auxiliary search tree are stored in (software) floating
+ * point, with an exponent and a mantissa. The exponent needs to be big enough
+ * to address all the bits in the original key, but the number of bits in the
+ * mantissa is somewhat arbitrary; more bits just gets us fewer failures.
+ *
+ * We need 7 bits for the exponent and 3 bits for the key's offset (since keys
+ * are 8 byte aligned); using 22 bits for the mantissa means a node is 4 bytes.
+ * We need one node per 128 bytes in the btree node, which means the auxiliary
+ * search trees take up 3% as much memory as the btree itself.
+ *
+ * Constructing these auxiliary search trees is moderately expensive, and we
+ * don't want to be constantly rebuilding the search tree for the last set
+ * whenever we insert another key into it. For the unwritten set, we use a much
+ * simpler lookup table - it's just a flat array, so index i in the lookup table
+ * corresponds to the i range of BSET_CACHELINE bytes in the set. Indexing
+ * within each byte range works the same as with the auxiliary search trees.
+ *
+ * These are much easier to keep up to date when we insert a key - we do it
+ * somewhat lazily; when we shift a key up we usually just increment the pointer
+ * to it, only when it would overflow do we go to the trouble of finding the
+ * first key in that range of bytes again.
+ */
+
+/* Btree key comparison/iteration */
+
+struct btree_iter {
+	size_t size, used;
+	struct btree_iter_set {
+		struct bkey *k, *end;
+	} data[MAX_BSETS];
+};
+
+struct bset_tree {
+	/*
+	 * We construct a binary tree in an array as if the array
+	 * started at 1, so that things line up on the same cachelines
+	 * better: see comments in bset.c at cacheline_to_bkey() for
+	 * details
+	 */
+
+	/* size of the binary tree and prev array */
+	unsigned	size;
+
+	/* function of size - precalculated for to_inorder() */
+	unsigned	extra;
+
+	/* copy of the last key in the set */
+	struct bkey	end;
+	struct bkey_float *tree;
+
+	/*
+	 * The nodes in the bset tree point to specific keys - this
+	 * array holds the sizes of the previous key.
+	 *
+	 * Conceptually it's a member of struct bkey_float, but we want
+	 * to keep bkey_float to 4 bytes and prev isn't used in the fast
+	 * path.
+	 */
+	uint8_t		*prev;
+
+	/* The actual btree node, with pointers to each sorted set */
+	struct bset	*data;
+};
+
+static __always_inline int64_t bkey_cmp(const struct bkey *l,
+					const struct bkey *r)
+{
+	return unlikely(KEY_INODE(l) != KEY_INODE(r))
+		? (int64_t) KEY_INODE(l) - (int64_t) KEY_INODE(r)
+		: (int64_t) KEY_OFFSET(l) - (int64_t) KEY_OFFSET(r);
+}
+
+static inline size_t bkey_u64s(const struct bkey *k)
+{
+	BUG_ON(KEY_CSUM(k) > 1);
+	return 2 + KEY_PTRS(k) + (KEY_CSUM(k) ? 1 : 0);
+}
+
+static inline size_t bkey_bytes(const struct bkey *k)
+{
+	return bkey_u64s(k) * sizeof(uint64_t);
+}
+
+static inline void bkey_copy(struct bkey *dest, const struct bkey *src)
+{
+	memcpy(dest, src, bkey_bytes(src));
+}
+
+static inline void bkey_copy_key(struct bkey *dest, const struct bkey *src)
+{
+	if (!src)
+		src = &KEY(0, 0, 0);
+
+	SET_KEY_INODE(dest, KEY_INODE(src));
+	SET_KEY_OFFSET(dest, KEY_OFFSET(src));
+}
+
+static inline struct bkey *bkey_next(const struct bkey *k)
+{
+	uint64_t *d = (void *) k;
+	return (struct bkey *) (d + bkey_u64s(k));
+}
+
+/* Keylists */
+
+struct keylist {
+	struct bkey		*top;
+	union {
+		uint64_t		*list;
+		struct bkey		*bottom;
+	};
+
+	/* Enough room for btree_split's keys without realloc */
+#define KEYLIST_INLINE		16
+	uint64_t		d[KEYLIST_INLINE];
+};
+
+static inline void bch_keylist_init(struct keylist *l)
+{
+	l->top = (void *) (l->list = l->d);
+}
+
+static inline void bch_keylist_push(struct keylist *l)
+{
+	l->top = bkey_next(l->top);
+}
+
+static inline void bch_keylist_add(struct keylist *l, struct bkey *k)
+{
+	bkey_copy(l->top, k);
+	bch_keylist_push(l);
+}
+
+static inline bool bch_keylist_empty(struct keylist *l)
+{
+	return l->top == (void *) l->list;
+}
+
+static inline void bch_keylist_free(struct keylist *l)
+{
+	if (l->list != l->d)
+		kfree(l->list);
+}
+
+void bch_keylist_copy(struct keylist *, struct keylist *);
+struct bkey *bch_keylist_pop(struct keylist *);
+int bch_keylist_realloc(struct keylist *, int, struct cache_set *);
+
+void bch_bkey_copy_single_ptr(struct bkey *, const struct bkey *, unsigned);
+bool __bch_cut_front(const struct bkey *, struct bkey *);
+bool __bch_cut_back(const struct bkey *, struct bkey *);
+
+static inline bool bch_cut_front(const struct bkey *where, struct bkey *k)
+{
+	BUG_ON(bkey_cmp(where, k) > 0);
+	return __bch_cut_front(where, k);
+}
+
+static inline bool bch_cut_back(const struct bkey *where, struct bkey *k)
+{
+	BUG_ON(bkey_cmp(where, &START_KEY(k)) < 0);
+	return __bch_cut_back(where, k);
+}
+
+const char *bch_ptr_status(struct cache_set *, const struct bkey *);
+bool __bch_ptr_invalid(struct cache_set *, int level, const struct bkey *);
+bool bch_ptr_bad(struct btree *, const struct bkey *);
+
+static inline uint8_t gen_after(uint8_t a, uint8_t b)
+{
+	uint8_t r = a - b;
+	return r > 128U ? 0 : r;
+}
+
+static inline uint8_t ptr_stale(struct cache_set *c, const struct bkey *k,
+				unsigned i)
+{
+	return gen_after(PTR_BUCKET(c, k, i)->gen, PTR_GEN(k, i));
+}
+
+static inline bool ptr_available(struct cache_set *c, const struct bkey *k,
+				 unsigned i)
+{
+	return (PTR_DEV(k, i) < MAX_CACHES_PER_SET) && PTR_CACHE(c, k, i);
+}
+
+struct bkey *bch_next_recurse_key(struct btree *, struct bkey *);
+struct bkey *bch_btree_iter_next(struct btree_iter *);
+void bch_btree_iter_push(struct btree_iter *, struct bkey *, struct bkey *);
+struct bkey *__bch_btree_iter_init(struct btree *, struct btree_iter *,
+				   struct bkey *, struct bset_tree *);
+
+/* 32 bits total: */
+#define BKEY_MID_BITS		3
+#define BKEY_EXPONENT_BITS	7
+#define BKEY_MANTISSA_BITS	22
+#define BKEY_MANTISSA_MASK	((1 << BKEY_MANTISSA_BITS) - 1)
+
+struct bkey_float {
+	unsigned	exponent:BKEY_EXPONENT_BITS;
+	unsigned	m:BKEY_MID_BITS;
+	unsigned	mantissa:BKEY_MANTISSA_BITS;
+} __packed;
+
+/*
+ * BSET_CACHELINE was originally intended to match the hardware cacheline size -
+ * it used to be 64, but I realized the lookup code would touch slightly less
+ * memory if it was 128.
+ *
+ * It definites the number of bytes (in struct bset) per struct bkey_float in
+ * the auxiliar search tree - when we're done searching the bset_float tree we
+ * have this many bytes left that we do a linear search over.
+ *
+ * Since (after level 5) every level of the bset_tree is on a new cacheline,
+ * we're touching one fewer cacheline in the bset tree in exchange for one more
+ * cacheline in the linear search - but the linear search might stop before it
+ * gets to the second cacheline.
+ */
+
+#define BSET_CACHELINE		128
+#define bset_tree_space(b)	(btree_data_space(b) / BSET_CACHELINE)
+
+#define bset_tree_bytes(b)	(bset_tree_space(b) * sizeof(struct bkey_float))
+#define bset_prev_bytes(b)	(bset_tree_space(b) * sizeof(uint8_t))
+
+void bch_bset_init_next(struct btree *);
+
+void bch_bset_fix_invalidated_key(struct btree *, struct bkey *);
+void bch_bset_fix_lookup_table(struct btree *, struct bkey *);
+
+struct bkey *__bch_bset_search(struct btree *, struct bset_tree *,
+			   const struct bkey *);
+
+static inline struct bkey *bch_bset_search(struct btree *b, struct bset_tree *t,
+					   const struct bkey *search)
+{
+	return search ? __bch_bset_search(b, t, search) : t->data->start;
+}
+
+bool bch_bkey_try_merge(struct btree *, struct bkey *, struct bkey *);
+void bch_btree_sort_lazy(struct btree *);
+void bch_btree_sort_into(struct btree *, struct btree *);
+void bch_btree_sort_and_fix_extents(struct btree *, struct btree_iter *);
+void bch_btree_sort_partial(struct btree *, unsigned);
+
+static inline void bch_btree_sort(struct btree *b)
+{
+	bch_btree_sort_partial(b, 0);
+}
+
+int bch_bset_print_stats(struct cache_set *, char *);
+
+#endif
-- 
1.7.7.3

--
dm-devel mailing list
dm-devel@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/dm-devel


[Index of Archives]     [DM Crypt]     [Fedora Desktop]     [ATA RAID]     [Fedora Marketing]     [Fedora Packaging]     [Fedora SELinux]     [Yosemite Discussion]     [KDE Users]     [Fedora Docs]

  Powered by Linux