Commit 80914d97 authored by Greg Kroah-Hartman's avatar Greg Kroah-Hartman
parents 74361cb6 883d4cae
...@@ -2375,7 +2375,6 @@ int dlm_migrate_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res, ...@@ -2375,7 +2375,6 @@ int dlm_migrate_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
mlog(0, "returning %d\n", ret); mlog(0, "returning %d\n", ret);
return ret; return ret;
} }
EXPORT_SYMBOL_GPL(dlm_migrate_lockres);
int dlm_lock_basts_flushed(struct dlm_ctxt *dlm, struct dlm_lock *lock) int dlm_lock_basts_flushed(struct dlm_ctxt *dlm, struct dlm_lock *lock)
{ {
......
...@@ -155,7 +155,7 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm, ...@@ -155,7 +155,7 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm,
else else
status = dlm_get_unlock_actions(dlm, res, lock, lksb, &actions); status = dlm_get_unlock_actions(dlm, res, lock, lksb, &actions);
if (status != DLM_NORMAL) if (status != DLM_NORMAL && (status != DLM_CANCELGRANT || !master_node))
goto leave; goto leave;
/* By now this has been masked out of cancel requests. */ /* By now this has been masked out of cancel requests. */
...@@ -183,8 +183,7 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm, ...@@ -183,8 +183,7 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm,
spin_lock(&lock->spinlock); spin_lock(&lock->spinlock);
/* if the master told us the lock was already granted, /* if the master told us the lock was already granted,
* let the ast handle all of these actions */ * let the ast handle all of these actions */
if (status == DLM_NORMAL && if (status == DLM_CANCELGRANT) {
lksb->status == DLM_CANCELGRANT) {
actions &= ~(DLM_UNLOCK_REMOVE_LOCK| actions &= ~(DLM_UNLOCK_REMOVE_LOCK|
DLM_UNLOCK_REGRANT_LOCK| DLM_UNLOCK_REGRANT_LOCK|
DLM_UNLOCK_CLEAR_CONVERT_TYPE); DLM_UNLOCK_CLEAR_CONVERT_TYPE);
...@@ -349,14 +348,9 @@ static enum dlm_status dlm_send_remote_unlock_request(struct dlm_ctxt *dlm, ...@@ -349,14 +348,9 @@ static enum dlm_status dlm_send_remote_unlock_request(struct dlm_ctxt *dlm,
vec, veclen, owner, &status); vec, veclen, owner, &status);
if (tmpret >= 0) { if (tmpret >= 0) {
// successfully sent and received // successfully sent and received
if (status == DLM_CANCELGRANT) if (status == DLM_FORWARD)
ret = DLM_NORMAL;
else if (status == DLM_FORWARD) {
mlog(0, "master was in-progress. retry\n"); mlog(0, "master was in-progress. retry\n");
ret = DLM_FORWARD;
} else
ret = status; ret = status;
lksb->status = status;
} else { } else {
mlog_errno(tmpret); mlog_errno(tmpret);
if (dlm_is_host_down(tmpret)) { if (dlm_is_host_down(tmpret)) {
...@@ -372,7 +366,6 @@ static enum dlm_status dlm_send_remote_unlock_request(struct dlm_ctxt *dlm, ...@@ -372,7 +366,6 @@ static enum dlm_status dlm_send_remote_unlock_request(struct dlm_ctxt *dlm,
/* something bad. this will BUG in ocfs2 */ /* something bad. this will BUG in ocfs2 */
ret = dlm_err_to_dlm_status(tmpret); ret = dlm_err_to_dlm_status(tmpret);
} }
lksb->status = ret;
} }
return ret; return ret;
...@@ -483,6 +476,10 @@ int dlm_unlock_lock_handler(struct o2net_msg *msg, u32 len, void *data) ...@@ -483,6 +476,10 @@ int dlm_unlock_lock_handler(struct o2net_msg *msg, u32 len, void *data)
/* lock was found on queue */ /* lock was found on queue */
lksb = lock->lksb; lksb = lock->lksb;
if (flags & (LKM_VALBLK|LKM_PUT_LVB) &&
lock->ml.type != LKM_EXMODE)
flags &= ~(LKM_VALBLK|LKM_PUT_LVB);
/* unlockast only called on originating node */ /* unlockast only called on originating node */
if (flags & LKM_PUT_LVB) { if (flags & LKM_PUT_LVB) {
lksb->flags |= DLM_LKSB_PUT_LVB; lksb->flags |= DLM_LKSB_PUT_LVB;
...@@ -507,11 +504,8 @@ int dlm_unlock_lock_handler(struct o2net_msg *msg, u32 len, void *data) ...@@ -507,11 +504,8 @@ int dlm_unlock_lock_handler(struct o2net_msg *msg, u32 len, void *data)
"cookie=%u:%llu\n", "cookie=%u:%llu\n",
dlm_get_lock_cookie_node(unlock->cookie), dlm_get_lock_cookie_node(unlock->cookie),
dlm_get_lock_cookie_seq(unlock->cookie)); dlm_get_lock_cookie_seq(unlock->cookie));
else { else
/* send the lksb->status back to the other node */
status = lksb->status;
dlm_lock_put(lock); dlm_lock_put(lock);
}
leave: leave:
if (res) if (res)
...@@ -533,26 +527,22 @@ static enum dlm_status dlm_get_cancel_actions(struct dlm_ctxt *dlm, ...@@ -533,26 +527,22 @@ static enum dlm_status dlm_get_cancel_actions(struct dlm_ctxt *dlm,
if (dlm_lock_on_list(&res->blocked, lock)) { if (dlm_lock_on_list(&res->blocked, lock)) {
/* cancel this outright */ /* cancel this outright */
lksb->status = DLM_NORMAL;
status = DLM_NORMAL; status = DLM_NORMAL;
*actions = (DLM_UNLOCK_CALL_AST | *actions = (DLM_UNLOCK_CALL_AST |
DLM_UNLOCK_REMOVE_LOCK); DLM_UNLOCK_REMOVE_LOCK);
} else if (dlm_lock_on_list(&res->converting, lock)) { } else if (dlm_lock_on_list(&res->converting, lock)) {
/* cancel the request, put back on granted */ /* cancel the request, put back on granted */
lksb->status = DLM_NORMAL;
status = DLM_NORMAL; status = DLM_NORMAL;
*actions = (DLM_UNLOCK_CALL_AST | *actions = (DLM_UNLOCK_CALL_AST |
DLM_UNLOCK_REMOVE_LOCK | DLM_UNLOCK_REMOVE_LOCK |
DLM_UNLOCK_REGRANT_LOCK | DLM_UNLOCK_REGRANT_LOCK |
DLM_UNLOCK_CLEAR_CONVERT_TYPE); DLM_UNLOCK_CLEAR_CONVERT_TYPE);
} else if (dlm_lock_on_list(&res->granted, lock)) { } else if (dlm_lock_on_list(&res->granted, lock)) {
/* too late, already granted. DLM_CANCELGRANT */ /* too late, already granted. */
lksb->status = DLM_CANCELGRANT; status = DLM_CANCELGRANT;
status = DLM_NORMAL;
*actions = DLM_UNLOCK_CALL_AST; *actions = DLM_UNLOCK_CALL_AST;
} else { } else {
mlog(ML_ERROR, "lock to cancel is not on any list!\n"); mlog(ML_ERROR, "lock to cancel is not on any list!\n");
lksb->status = DLM_IVLOCKID;
status = DLM_IVLOCKID; status = DLM_IVLOCKID;
*actions = 0; *actions = 0;
} }
...@@ -569,13 +559,11 @@ static enum dlm_status dlm_get_unlock_actions(struct dlm_ctxt *dlm, ...@@ -569,13 +559,11 @@ static enum dlm_status dlm_get_unlock_actions(struct dlm_ctxt *dlm,
/* unlock request */ /* unlock request */
if (!dlm_lock_on_list(&res->granted, lock)) { if (!dlm_lock_on_list(&res->granted, lock)) {
lksb->status = DLM_DENIED;
status = DLM_DENIED; status = DLM_DENIED;
dlm_error(status); dlm_error(status);
*actions = 0; *actions = 0;
} else { } else {
/* unlock granted lock */ /* unlock granted lock */
lksb->status = DLM_NORMAL;
status = DLM_NORMAL; status = DLM_NORMAL;
*actions = (DLM_UNLOCK_FREE_LOCK | *actions = (DLM_UNLOCK_FREE_LOCK |
DLM_UNLOCK_CALL_AST | DLM_UNLOCK_CALL_AST |
...@@ -632,6 +620,8 @@ enum dlm_status dlmunlock(struct dlm_ctxt *dlm, struct dlm_lockstatus *lksb, ...@@ -632,6 +620,8 @@ enum dlm_status dlmunlock(struct dlm_ctxt *dlm, struct dlm_lockstatus *lksb,
spin_lock(&res->spinlock); spin_lock(&res->spinlock);
is_master = (res->owner == dlm->node_num); is_master = (res->owner == dlm->node_num);
if (flags & LKM_VALBLK && lock->ml.type != LKM_EXMODE)
flags &= ~LKM_VALBLK;
spin_unlock(&res->spinlock); spin_unlock(&res->spinlock);
if (is_master) { if (is_master) {
...@@ -665,7 +655,7 @@ enum dlm_status dlmunlock(struct dlm_ctxt *dlm, struct dlm_lockstatus *lksb, ...@@ -665,7 +655,7 @@ enum dlm_status dlmunlock(struct dlm_ctxt *dlm, struct dlm_lockstatus *lksb,
} }
if (call_ast) { if (call_ast) {
mlog(0, "calling unlockast(%p, %d)\n", data, lksb->status); mlog(0, "calling unlockast(%p, %d)\n", data, status);
if (is_master) { if (is_master) {
/* it is possible that there is one last bast /* it is possible that there is one last bast
* pending. make sure it is flushed, then * pending. make sure it is flushed, then
...@@ -677,9 +667,12 @@ enum dlm_status dlmunlock(struct dlm_ctxt *dlm, struct dlm_lockstatus *lksb, ...@@ -677,9 +667,12 @@ enum dlm_status dlmunlock(struct dlm_ctxt *dlm, struct dlm_lockstatus *lksb,
wait_event(dlm->ast_wq, wait_event(dlm->ast_wq,
dlm_lock_basts_flushed(dlm, lock)); dlm_lock_basts_flushed(dlm, lock));
} }
(*unlockast)(data, lksb->status); (*unlockast)(data, status);
} }
if (status == DLM_CANCELGRANT)
status = DLM_NORMAL;
if (status == DLM_NORMAL) { if (status == DLM_NORMAL) {
mlog(0, "kicking the thread\n"); mlog(0, "kicking the thread\n");
dlm_kick_thread(dlm, res); dlm_kick_thread(dlm, res);
......
...@@ -840,6 +840,12 @@ static int ocfs2_local_alloc_new_window(struct ocfs2_super *osb, ...@@ -840,6 +840,12 @@ static int ocfs2_local_alloc_new_window(struct ocfs2_super *osb,
mlog(0, "Allocating %u clusters for a new window.\n", mlog(0, "Allocating %u clusters for a new window.\n",
ocfs2_local_alloc_window_bits(osb)); ocfs2_local_alloc_window_bits(osb));
/* Instruct the allocation code to try the most recently used
* cluster group. We'll re-record the group used this pass
* below. */
ac->ac_last_group = osb->la_last_gd;
/* we used the generic suballoc reserve function, but we set /* we used the generic suballoc reserve function, but we set
* everything up nicely, so there's no reason why we can't use * everything up nicely, so there's no reason why we can't use
* the more specific cluster api to claim bits. */ * the more specific cluster api to claim bits. */
...@@ -852,6 +858,8 @@ static int ocfs2_local_alloc_new_window(struct ocfs2_super *osb, ...@@ -852,6 +858,8 @@ static int ocfs2_local_alloc_new_window(struct ocfs2_super *osb,
goto bail; goto bail;
} }
osb->la_last_gd = ac->ac_last_group;
la->la_bm_off = cpu_to_le32(cluster_off); la->la_bm_off = cpu_to_le32(cluster_off);
alloc->id1.bitmap1.i_total = cpu_to_le32(cluster_count); alloc->id1.bitmap1.i_total = cpu_to_le32(cluster_count);
/* just in case... In the future when we find space ourselves, /* just in case... In the future when we find space ourselves,
......
...@@ -197,7 +197,6 @@ struct ocfs2_super ...@@ -197,7 +197,6 @@ struct ocfs2_super
struct ocfs2_node_map recovery_map; struct ocfs2_node_map recovery_map;
struct ocfs2_node_map umount_map; struct ocfs2_node_map umount_map;
u32 num_clusters;
u64 root_blkno; u64 root_blkno;
u64 system_dir_blkno; u64 system_dir_blkno;
u64 bitmap_blkno; u64 bitmap_blkno;
...@@ -237,6 +236,7 @@ struct ocfs2_super ...@@ -237,6 +236,7 @@ struct ocfs2_super
enum ocfs2_local_alloc_state local_alloc_state; enum ocfs2_local_alloc_state local_alloc_state;
struct buffer_head *local_alloc_bh; struct buffer_head *local_alloc_bh;
u64 la_last_gd;
/* Next two fields are for local node slot recovery during /* Next two fields are for local node slot recovery during
* mount. */ * mount. */
......
...@@ -70,12 +70,6 @@ static int ocfs2_block_group_search(struct inode *inode, ...@@ -70,12 +70,6 @@ static int ocfs2_block_group_search(struct inode *inode,
struct buffer_head *group_bh, struct buffer_head *group_bh,
u32 bits_wanted, u32 min_bits, u32 bits_wanted, u32 min_bits,
u16 *bit_off, u16 *bits_found); u16 *bit_off, u16 *bits_found);
static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
u32 bits_wanted,
u32 min_bits,
u16 *bit_off,
unsigned int *num_bits,
u64 *bg_blkno);
static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb, static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
struct ocfs2_alloc_context *ac, struct ocfs2_alloc_context *ac,
u32 bits_wanted, u32 bits_wanted,
...@@ -85,11 +79,6 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb, ...@@ -85,11 +79,6 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
u64 *bg_blkno); u64 *bg_blkno);
static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh, static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
int nr); int nr);
static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
struct buffer_head *bg_bh,
unsigned int bits_wanted,
u16 *bit_off,
u16 *bits_found);
static inline int ocfs2_block_group_set_bits(struct ocfs2_journal_handle *handle, static inline int ocfs2_block_group_set_bits(struct ocfs2_journal_handle *handle,
struct inode *alloc_inode, struct inode *alloc_inode,
struct ocfs2_group_desc *bg, struct ocfs2_group_desc *bg,
...@@ -143,6 +132,64 @@ static u32 ocfs2_bits_per_group(struct ocfs2_chain_list *cl) ...@@ -143,6 +132,64 @@ static u32 ocfs2_bits_per_group(struct ocfs2_chain_list *cl)
return (u32)le16_to_cpu(cl->cl_cpg) * (u32)le16_to_cpu(cl->cl_bpc); return (u32)le16_to_cpu(cl->cl_cpg) * (u32)le16_to_cpu(cl->cl_bpc);
} }
/* somewhat more expensive than our other checks, so use sparingly. */
static int ocfs2_check_group_descriptor(struct super_block *sb,
struct ocfs2_dinode *di,
struct ocfs2_group_desc *gd)
{
unsigned int max_bits;
if (!OCFS2_IS_VALID_GROUP_DESC(gd)) {
OCFS2_RO_ON_INVALID_GROUP_DESC(sb, gd);
return -EIO;
}
if (di->i_blkno != gd->bg_parent_dinode) {
ocfs2_error(sb, "Group descriptor # %llu has bad parent "
"pointer (%llu, expected %llu)",
(unsigned long long)le64_to_cpu(gd->bg_blkno),
(unsigned long long)le64_to_cpu(gd->bg_parent_dinode),
(unsigned long long)le64_to_cpu(di->i_blkno));
return -EIO;
}
max_bits = le16_to_cpu(di->id2.i_chain.cl_cpg) * le16_to_cpu(di->id2.i_chain.cl_bpc);
if (le16_to_cpu(gd->bg_bits) > max_bits) {
ocfs2_error(sb, "Group descriptor # %llu has bit count of %u",
(unsigned long long)le64_to_cpu(gd->bg_blkno),
le16_to_cpu(gd->bg_bits));
return -EIO;
}
if (le16_to_cpu(gd->bg_chain) >=
le16_to_cpu(di->id2.i_chain.cl_next_free_rec)) {
ocfs2_error(sb, "Group descriptor # %llu has bad chain %u",
(unsigned long long)le64_to_cpu(gd->bg_blkno),
le16_to_cpu(gd->bg_chain));
return -EIO;
}
if (le16_to_cpu(gd->bg_free_bits_count) > le16_to_cpu(gd->bg_bits)) {
ocfs2_error(sb, "Group descriptor # %llu has bit count %u but "
"claims that %u are free",
(unsigned long long)le64_to_cpu(gd->bg_blkno),
le16_to_cpu(gd->bg_bits),
le16_to_cpu(gd->bg_free_bits_count));
return -EIO;
}
if (le16_to_cpu(gd->bg_bits) > (8 * le16_to_cpu(gd->bg_size))) {
ocfs2_error(sb, "Group descriptor # %llu has bit count %u but "
"max bitmap bits of %u",
(unsigned long long)le64_to_cpu(gd->bg_blkno),
le16_to_cpu(gd->bg_bits),
8 * le16_to_cpu(gd->bg_size));
return -EIO;
}
return 0;
}
static int ocfs2_block_group_fill(struct ocfs2_journal_handle *handle, static int ocfs2_block_group_fill(struct ocfs2_journal_handle *handle,
struct inode *alloc_inode, struct inode *alloc_inode,
struct buffer_head *bg_bh, struct buffer_head *bg_bh,
...@@ -663,6 +710,7 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh, ...@@ -663,6 +710,7 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb, static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
struct buffer_head *bg_bh, struct buffer_head *bg_bh,
unsigned int bits_wanted, unsigned int bits_wanted,
unsigned int total_bits,
u16 *bit_off, u16 *bit_off,
u16 *bits_found) u16 *bits_found)
{ {
...@@ -679,10 +727,8 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb, ...@@ -679,10 +727,8 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
found = start = best_offset = best_size = 0; found = start = best_offset = best_size = 0;
bitmap = bg->bg_bitmap; bitmap = bg->bg_bitmap;
while((offset = ocfs2_find_next_zero_bit(bitmap, while((offset = ocfs2_find_next_zero_bit(bitmap, total_bits, start)) != -1) {
le16_to_cpu(bg->bg_bits), if (offset == total_bits)
start)) != -1) {
if (offset == le16_to_cpu(bg->bg_bits))
break; break;
if (!ocfs2_test_bg_bit_allocatable(bg_bh, offset)) { if (!ocfs2_test_bg_bit_allocatable(bg_bh, offset)) {
...@@ -911,14 +957,35 @@ static int ocfs2_cluster_group_search(struct inode *inode, ...@@ -911,14 +957,35 @@ static int ocfs2_cluster_group_search(struct inode *inode,
{ {
int search = -ENOSPC; int search = -ENOSPC;
int ret; int ret;
struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) group_bh->b_data; struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *) group_bh->b_data;
u16 tmp_off, tmp_found; u16 tmp_off, tmp_found;
unsigned int max_bits, gd_cluster_off;
BUG_ON(!ocfs2_is_cluster_bitmap(inode)); BUG_ON(!ocfs2_is_cluster_bitmap(inode));
if (bg->bg_free_bits_count) { if (gd->bg_free_bits_count) {
max_bits = le16_to_cpu(gd->bg_bits);
/* Tail groups in cluster bitmaps which aren't cpg
* aligned are prone to partial extention by a failed
* fs resize. If the file system resize never got to
* update the dinode cluster count, then we don't want
* to trust any clusters past it, regardless of what
* the group descriptor says. */
gd_cluster_off = ocfs2_blocks_to_clusters(inode->i_sb,
le64_to_cpu(gd->bg_blkno));
if ((gd_cluster_off + max_bits) >
OCFS2_I(inode)->ip_clusters) {
max_bits = OCFS2_I(inode)->ip_clusters - gd_cluster_off;
mlog(0, "Desc %llu, bg_bits %u, clusters %u, use %u\n",
(unsigned long long)le64_to_cpu(gd->bg_blkno),
le16_to_cpu(gd->bg_bits),
OCFS2_I(inode)->ip_clusters, max_bits);
}
ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb), ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb),
group_bh, bits_wanted, group_bh, bits_wanted,
max_bits,
&tmp_off, &tmp_found); &tmp_off, &tmp_found);
if (ret) if (ret)
return ret; return ret;
...@@ -951,17 +1018,109 @@ static int ocfs2_block_group_search(struct inode *inode, ...@@ -951,17 +1018,109 @@ static int ocfs2_block_group_search(struct inode *inode,
if (bg->bg_free_bits_count) if (bg->bg_free_bits_count)
ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb), ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb),
group_bh, bits_wanted, group_bh, bits_wanted,
le16_to_cpu(bg->bg_bits),
bit_off, bits_found); bit_off, bits_found);
return ret; return ret;
} }
static int ocfs2_alloc_dinode_update_counts(struct inode *inode,
struct ocfs2_journal_handle *handle,
struct buffer_head *di_bh,
u32 num_bits,
u16 chain)
{
int ret;
u32 tmp_used;
struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data;
struct ocfs2_chain_list *cl = (struct ocfs2_chain_list *) &di->id2.i_chain;
ret = ocfs2_journal_access(handle, inode, di_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret < 0) {
mlog_errno(ret);
goto out;
}
tmp_used = le32_to_cpu(di->id1.bitmap1.i_used);
di->id1.bitmap1.i_used = cpu_to_le32(num_bits + tmp_used);
le32_add_cpu(&cl->cl_recs[chain].c_free, -num_bits);
ret = ocfs2_journal_dirty(handle, di_bh);
if (ret < 0)
mlog_errno(ret);
out:
return ret;
}
static int ocfs2_search_one_group(struct ocfs2_alloc_context *ac,
u32 bits_wanted,
u32 min_bits,
u16 *bit_off,
unsigned int *num_bits,
u64 gd_blkno,
u16 *bits_left)
{
int ret;
u16 found;
struct buffer_head *group_bh = NULL;
struct ocfs2_group_desc *gd;
struct inode *alloc_inode = ac->ac_inode;
struct ocfs2_journal_handle *handle = ac->ac_handle;
ret = ocfs2_read_block(OCFS2_SB(alloc_inode->i_sb), gd_blkno,
&group_bh, OCFS2_BH_CACHED, alloc_inode);
if (ret < 0) {
mlog_errno(ret);
return ret;
}
gd = (struct ocfs2_group_desc *) group_bh->b_data;
if (!OCFS2_IS_VALID_GROUP_DESC(gd)) {
OCFS2_RO_ON_INVALID_GROUP_DESC(alloc_inode->i_sb, gd);
ret = -EIO;
goto out;
}
ret = ac->ac_group_search(alloc_inode, group_bh, bits_wanted, min_bits,
bit_off, &found);
if (ret < 0) {
if (ret != -ENOSPC)
mlog_errno(ret);
goto out;
}
*num_bits = found;
ret = ocfs2_alloc_dinode_update_counts(alloc_inode, handle, ac->ac_bh,
*num_bits,
le16_to_cpu(gd->bg_chain));
if (ret < 0) {
mlog_errno(ret);
goto out;
}
ret = ocfs2_block_group_set_bits(handle, alloc_inode, gd, group_bh,
*bit_off, *num_bits);
if (ret < 0)
mlog_errno(ret);
*bits_left = le16_to_cpu(gd->bg_free_bits_count);
out:
brelse(group_bh);
return ret;
}
static int ocfs2_search_chain(struct ocfs2_alloc_context *ac, static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
u32 bits_wanted, u32 bits_wanted,
u32 min_bits, u32 min_bits,
u16 *bit_off, u16 *bit_off,
unsigned int *num_bits, unsigned int *num_bits,
u64 *bg_blkno) u64 *bg_blkno,
u16 *bits_left)
{ {
int status; int status;
u16 chain, tmp_bits; u16 chain, tmp_bits;
...@@ -988,9 +1147,9 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac, ...@@ -988,9 +1147,9 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
goto bail; goto bail;
} }
bg = (struct ocfs2_group_desc *) group_bh->b_data; bg = (struct ocfs2_group_desc *) group_bh->b_data;
if (!OCFS2_IS_VALID_GROUP_DESC(bg)) { status = ocfs2_check_group_descriptor(alloc_inode->i_sb, fe, bg);
OCFS2_RO_ON_INVALID_GROUP_DESC(alloc_inode->i_sb, bg); if (status) {
status = -EIO; mlog_errno(status);
goto bail; goto bail;
} }
...@@ -1018,9 +1177,9 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac, ...@@ -1018,9 +1177,9 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
goto bail; goto bail;
} }
bg = (struct ocfs2_group_desc *) group_bh->b_data; bg = (struct ocfs2_group_desc *) group_bh->b_data;
if (!OCFS2_IS_VALID_GROUP_DESC(bg)) { status = ocfs2_check_group_descriptor(alloc_inode->i_sb, fe, bg);
OCFS2_RO_ON_INVALID_GROUP_DESC(alloc_inode->i_sb, bg); if (status) {
status = -EIO; mlog_errno(status);
goto bail; goto bail;
} }
} }
...@@ -1099,6 +1258,7 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac, ...@@ -1099,6 +1258,7 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
(unsigned long long)fe->i_blkno); (unsigned long long)fe->i_blkno);
*bg_blkno = le64_to_cpu(bg->bg_blkno); *bg_blkno = le64_to_cpu(bg->bg_blkno);
*bits_left = le16_to_cpu(bg->bg_free_bits_count);
bail: bail:
if (group_bh) if (group_bh)
brelse(group_bh); brelse(group_bh);
...@@ -1120,6 +1280,8 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb, ...@@ -1120,6 +1280,8 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
{ {
int status; int status;
u16 victim, i; u16 victim, i;
u16 bits_left = 0;
u64 hint_blkno = ac->ac_last_group;
struct ocfs2_chain_list *cl; struct ocfs2_chain_list *cl;
struct ocfs2_dinode *fe; struct ocfs2_dinode *fe;
...@@ -1146,6 +1308,28 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb, ...@@ -1146,6 +1308,28 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
goto bail; goto bail;
} }
if (hint_blkno) {
/* Attempt to short-circuit the usual search mechanism
* by jumping straight to the most recently used
* allocation group. This helps us mantain some
* contiguousness across allocations. */
status = ocfs2_search_one_group(ac, bits_wanted, min_bits,
bit_off, num_bits,
hint_blkno, &bits_left);
if (!status) {
/* Be careful to update *bg_blkno here as the
* caller is expecting it to be filled in, and
* ocfs2_search_one_group() won't do that for
* us. */
*bg_blkno = hint_blkno;
goto set_hint;
}
if (status < 0 && status != -ENOSPC) {
mlog_errno(status);
goto bail;
}
}
cl = (struct ocfs2_chain_list *) &fe->id2.i_chain; cl = (struct ocfs2_chain_list *) &fe->id2.i_chain;
victim = ocfs2_find_victim_chain(cl); victim = ocfs2_find_victim_chain(cl);
...@@ -1153,9 +1337,9 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb, ...@@ -1153,9 +1337,9 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
ac->ac_allow_chain_relink = 1; ac->ac_allow_chain_relink = 1;
status = ocfs2_search_chain(ac, bits_wanted, min_bits, bit_off, status = ocfs2_search_chain(ac, bits_wanted, min_bits, bit_off,
num_bits, bg_blkno); num_bits, bg_blkno, &bits_left);
if (!status) if (!status)
goto bail; goto set_hint;
if (status < 0 && status != -ENOSPC) { if (status < 0 && status != -ENOSPC) {
mlog_errno(status); mlog_errno(status);
goto bail; goto bail;
...@@ -1177,8 +1361,8 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb, ...@@ -1177,8 +1361,8 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
ac->ac_chain = i; ac->ac_chain = i;
status = ocfs2_search_chain(ac, bits_wanted, min_bits, status = ocfs2_search_chain(ac, bits_wanted, min_bits,
bit_off, num_bits, bit_off, num_bits, bg_blkno,
bg_blkno); &bits_left);
if (!status) if (!status)
break; break;
if (status < 0 && status != -ENOSPC) { if (status < 0 && status != -ENOSPC) {
...@@ -1186,8 +1370,19 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb, ...@@ -1186,8 +1370,19 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
goto bail; goto bail;
} }
} }
bail:
set_hint:
if (status != -ENOSPC) {
/* If the next search of this group is not likely to
* yield a suitable extent, then we reset the last
* group hint so as to not waste a disk read */
if (bits_left < min_bits)
ac->ac_last_group = 0;
else
ac->ac_last_group = *bg_blkno;
}
bail:
mlog_exit(status); mlog_exit(status);
return status; return status;
} }
...@@ -1341,7 +1536,7 @@ int ocfs2_claim_clusters(struct ocfs2_super *osb, ...@@ -1341,7 +1536,7 @@ int ocfs2_claim_clusters(struct ocfs2_super *osb,
{ {
int status; int status;
unsigned int bits_wanted = ac->ac_bits_wanted - ac->ac_bits_given; unsigned int bits_wanted = ac->ac_bits_wanted - ac->ac_bits_given;
u64 bg_blkno; u64 bg_blkno = 0;
u16 bg_bit_off; u16 bg_bit_off;
mlog_entry_void(); mlog_entry_void();
...@@ -1494,9 +1689,9 @@ static int ocfs2_free_suballoc_bits(struct ocfs2_journal_handle *handle, ...@@ -1494,9 +1689,9 @@ static int ocfs2_free_suballoc_bits(struct ocfs2_journal_handle *handle,
} }
group = (struct ocfs2_group_desc *) group_bh->b_data; group = (struct ocfs2_group_desc *) group_bh->b_data;
if (!OCFS2_IS_VALID_GROUP_DESC(group)) { status = ocfs2_check_group_descriptor(alloc_inode->i_sb, fe, group);
OCFS2_RO_ON_INVALID_GROUP_DESC(alloc_inode->i_sb, group); if (status) {
status = -EIO; mlog_errno(status);
goto bail; goto bail;
} }
BUG_ON((count + start_bit) > le16_to_cpu(group->bg_bits)); BUG_ON((count + start_bit) > le16_to_cpu(group->bg_bits));
......
...@@ -49,6 +49,8 @@ struct ocfs2_alloc_context { ...@@ -49,6 +49,8 @@ struct ocfs2_alloc_context {
u16 ac_chain; u16 ac_chain;
int ac_allow_chain_relink; int ac_allow_chain_relink;
group_search_t *ac_group_search; group_search_t *ac_group_search;
u64 ac_last_group;
}; };
void ocfs2_free_alloc_context(struct ocfs2_alloc_context *ac); void ocfs2_free_alloc_context(struct ocfs2_alloc_context *ac);
......
...@@ -1442,8 +1442,13 @@ static int ocfs2_initialize_super(struct super_block *sb, ...@@ -1442,8 +1442,13 @@ static int ocfs2_initialize_super(struct super_block *sb,
osb->bitmap_blkno = OCFS2_I(inode)->ip_blkno; osb->bitmap_blkno = OCFS2_I(inode)->ip_blkno;
/* We don't have a cluster lock on the bitmap here because
* we're only interested in static information and the extra
* complexity at mount time isn't worht it. Don't pass the
* inode in to the read function though as we don't want it to
* be put in the cache. */
status = ocfs2_read_block(osb, osb->bitmap_blkno, &bitmap_bh, 0, status = ocfs2_read_block(osb, osb->bitmap_blkno, &bitmap_bh, 0,
inode); NULL);
iput(inode); iput(inode);
if (status < 0) { if (status < 0) {
mlog_errno(status); mlog_errno(status);
...@@ -1452,7 +1457,6 @@ static int ocfs2_initialize_super(struct super_block *sb, ...@@ -1452,7 +1457,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
di = (struct ocfs2_dinode *) bitmap_bh->b_data; di = (struct ocfs2_dinode *) bitmap_bh->b_data;
osb->bitmap_cpg = le16_to_cpu(di->id2.i_chain.cl_cpg); osb->bitmap_cpg = le16_to_cpu(di->id2.i_chain.cl_cpg);
osb->num_clusters = le32_to_cpu(di->id1.bitmap1.i_total);
brelse(bitmap_bh); brelse(bitmap_bh);
mlog(0, "cluster bitmap inode: %llu, clusters per group: %u\n", mlog(0, "cluster bitmap inode: %llu, clusters per group: %u\n",
(unsigned long long)osb->bitmap_blkno, osb->bitmap_cpg); (unsigned long long)osb->bitmap_blkno, osb->bitmap_cpg);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment