Merge branch 'gfs2-iopen' into for-next

This commit is contained in:
Andreas Gruenbacher 2020-06-05 21:25:36 +02:00
commit 300e549b6e
10 changed files with 296 additions and 39 deletions

View File

@ -134,7 +134,9 @@ static struct dentry *gfs2_get_dentry(struct super_block *sb,
struct gfs2_sbd *sdp = sb->s_fs_info;
struct inode *inode;
inode = gfs2_lookup_by_inum(sdp, inum->no_addr, &inum->no_formal_ino,
if (!inum->no_formal_ino)
return ERR_PTR(-ESTALE);
inode = gfs2_lookup_by_inum(sdp, inum->no_addr, inum->no_formal_ino,
GFS2_BLKST_DINODE);
if (IS_ERR(inode))
return ERR_CAST(inode);

View File

@ -125,12 +125,11 @@ static void gfs2_glock_dealloc(struct rcu_head *rcu)
{
struct gfs2_glock *gl = container_of(rcu, struct gfs2_glock, gl_rcu);
if (gl->gl_ops->go_flags & GLOF_ASPACE) {
kfree(gl->gl_lksb.sb_lvbptr);
if (gl->gl_ops->go_flags & GLOF_ASPACE)
kmem_cache_free(gfs2_glock_aspace_cachep, gl);
} else {
kfree(gl->gl_lksb.sb_lvbptr);
else
kmem_cache_free(gfs2_glock_cachep, gl);
}
}
/**
@ -465,6 +464,15 @@ static void state_change(struct gfs2_glock *gl, unsigned int new_state)
gl->gl_tchange = jiffies;
}
static void gfs2_set_demote(struct gfs2_glock *gl)
{
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
set_bit(GLF_DEMOTE, &gl->gl_flags);
smp_mb();
wake_up(&sdp->sd_async_glock_wait);
}
static void gfs2_demote_wake(struct gfs2_glock *gl)
{
gl->gl_demote_state = LM_ST_EXCLUSIVE;
@ -757,20 +765,127 @@ out_unlock:
return;
}
void gfs2_inode_remember_delete(struct gfs2_glock *gl, u64 generation)
{
struct gfs2_inode_lvb *ri = (void *)gl->gl_lksb.sb_lvbptr;
if (ri->ri_magic == 0)
ri->ri_magic = cpu_to_be32(GFS2_MAGIC);
if (ri->ri_magic == cpu_to_be32(GFS2_MAGIC))
ri->ri_generation_deleted = cpu_to_be64(generation);
}
bool gfs2_inode_already_deleted(struct gfs2_glock *gl, u64 generation)
{
struct gfs2_inode_lvb *ri = (void *)gl->gl_lksb.sb_lvbptr;
if (ri->ri_magic != cpu_to_be32(GFS2_MAGIC))
return false;
return generation <= be64_to_cpu(ri->ri_generation_deleted);
}
static void gfs2_glock_poke(struct gfs2_glock *gl)
{
int flags = LM_FLAG_TRY_1CB | LM_FLAG_ANY | GL_SKIP;
struct gfs2_holder gh;
int error;
error = gfs2_glock_nq_init(gl, LM_ST_SHARED, flags, &gh);
if (!error)
gfs2_glock_dq(&gh);
}
static bool gfs2_try_evict(struct gfs2_glock *gl)
{
struct gfs2_inode *ip;
bool evicted = false;
/*
* If there is contention on the iopen glock and we have an inode, try
* to grab and release the inode so that it can be evicted. This will
* allow the remote node to go ahead and delete the inode without us
* having to do it, which will avoid rgrp glock thrashing.
*
* The remote node is likely still holding the corresponding inode
* glock, so it will run before we get to verify that the delete has
* happened below.
*/
spin_lock(&gl->gl_lockref.lock);
ip = gl->gl_object;
if (ip && !igrab(&ip->i_inode))
ip = NULL;
spin_unlock(&gl->gl_lockref.lock);
if (ip) {
struct gfs2_glock *inode_gl = NULL;
gl->gl_no_formal_ino = ip->i_no_formal_ino;
set_bit(GIF_DEFERRED_DELETE, &ip->i_flags);
d_prune_aliases(&ip->i_inode);
iput(&ip->i_inode);
/* If the inode was evicted, gl->gl_object will now be NULL. */
spin_lock(&gl->gl_lockref.lock);
ip = gl->gl_object;
if (ip) {
inode_gl = ip->i_gl;
lockref_get(&inode_gl->gl_lockref);
clear_bit(GIF_DEFERRED_DELETE, &ip->i_flags);
}
spin_unlock(&gl->gl_lockref.lock);
if (inode_gl) {
gfs2_glock_poke(inode_gl);
gfs2_glock_put(inode_gl);
}
evicted = !ip;
}
return evicted;
}
static void delete_work_func(struct work_struct *work)
{
struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_delete);
struct delayed_work *dwork = to_delayed_work(work);
struct gfs2_glock *gl = container_of(dwork, struct gfs2_glock, gl_delete);
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
struct inode *inode;
u64 no_addr = gl->gl_name.ln_number;
spin_lock(&gl->gl_lockref.lock);
clear_bit(GLF_PENDING_DELETE, &gl->gl_flags);
spin_unlock(&gl->gl_lockref.lock);
/* If someone's using this glock to create a new dinode, the block must
have been freed by another node, then re-used, in which case our
iopen callback is too late after the fact. Ignore it. */
if (test_bit(GLF_INODE_CREATING, &gl->gl_flags))
goto out;
inode = gfs2_lookup_by_inum(sdp, no_addr, NULL, GFS2_BLKST_UNLINKED);
if (test_bit(GLF_DEMOTE, &gl->gl_flags)) {
/*
* If we can evict the inode, give the remote node trying to
* delete the inode some time before verifying that the delete
* has happened. Otherwise, if we cause contention on the inode glock
* immediately, the remote node will think that we still have
* the inode in use, and so it will give up waiting.
*
* If we can't evict the inode, signal to the remote node that
* the inode is still in use. We'll later try to delete the
* inode locally in gfs2_evict_inode.
*
* FIXME: We only need to verify that the remote node has
* deleted the inode because nodes before this remote delete
* rework won't cooperate. At a later time, when we no longer
* care about compatibility with such nodes, we can skip this
* step entirely.
*/
if (gfs2_try_evict(gl)) {
if (gfs2_queue_delete_work(gl, 5 * HZ))
return;
}
goto out;
}
inode = gfs2_lookup_by_inum(sdp, no_addr, gl->gl_no_formal_ino,
GFS2_BLKST_UNLINKED);
if (!IS_ERR_OR_NULL(inode)) {
d_prune_aliases(inode);
iput(inode);
@ -801,7 +916,7 @@ static void glock_work_func(struct work_struct *work)
if (!delay) {
clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags);
set_bit(GLF_DEMOTE, &gl->gl_flags);
gfs2_set_demote(gl);
}
}
run_queue(gl, 0);
@ -932,7 +1047,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
gl->gl_object = NULL;
gl->gl_hold_time = GL_GLOCK_DFT_HOLD;
INIT_DELAYED_WORK(&gl->gl_work, glock_work_func);
INIT_WORK(&gl->gl_delete, delete_work_func);
INIT_DELAYED_WORK(&gl->gl_delete, delete_work_func);
mapping = gfs2_glock2aspace(gl);
if (mapping) {
@ -1146,9 +1261,10 @@ wait_for_dlm:
static void handle_callback(struct gfs2_glock *gl, unsigned int state,
unsigned long delay, bool remote)
{
int bit = delay ? GLF_PENDING_DEMOTE : GLF_DEMOTE;
set_bit(bit, &gl->gl_flags);
if (delay)
set_bit(GLF_PENDING_DEMOTE, &gl->gl_flags);
else
gfs2_set_demote(gl);
if (gl->gl_demote_state == LM_ST_EXCLUSIVE) {
gl->gl_demote_state = state;
gl->gl_demote_time = jiffies;
@ -1755,6 +1871,44 @@ static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp)
rhashtable_walk_exit(&iter);
}
bool gfs2_queue_delete_work(struct gfs2_glock *gl, unsigned long delay)
{
bool queued;
spin_lock(&gl->gl_lockref.lock);
queued = queue_delayed_work(gfs2_delete_workqueue,
&gl->gl_delete, delay);
if (queued)
set_bit(GLF_PENDING_DELETE, &gl->gl_flags);
spin_unlock(&gl->gl_lockref.lock);
return queued;
}
void gfs2_cancel_delete_work(struct gfs2_glock *gl)
{
if (cancel_delayed_work_sync(&gl->gl_delete)) {
clear_bit(GLF_PENDING_DELETE, &gl->gl_flags);
gfs2_glock_put(gl);
}
}
bool gfs2_delete_work_queued(const struct gfs2_glock *gl)
{
return test_bit(GLF_PENDING_DELETE, &gl->gl_flags);
}
static void flush_delete_work(struct gfs2_glock *gl)
{
flush_delayed_work(&gl->gl_delete);
gfs2_glock_queue_work(gl, 0);
}
void gfs2_flush_delete_work(struct gfs2_sbd *sdp)
{
glock_hash_walk(flush_delete_work, sdp);
flush_workqueue(gfs2_delete_workqueue);
}
/**
* thaw_glock - thaw out a glock which has an unprocessed reply waiting
* @gl: The glock to thaw

View File

@ -244,6 +244,10 @@ static inline int gfs2_glock_nq_init(struct gfs2_glock *gl,
extern void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state);
extern void gfs2_glock_complete(struct gfs2_glock *gl, int ret);
extern bool gfs2_queue_delete_work(struct gfs2_glock *gl, unsigned long delay);
extern void gfs2_cancel_delete_work(struct gfs2_glock *gl);
extern bool gfs2_delete_work_queued(const struct gfs2_glock *gl);
extern void gfs2_flush_delete_work(struct gfs2_sbd *sdp);
extern void gfs2_gl_hash_clear(struct gfs2_sbd *sdp);
extern void gfs2_glock_finish_truncate(struct gfs2_inode *ip);
extern void gfs2_glock_thaw(struct gfs2_sbd *sdp);
@ -315,4 +319,7 @@ static inline void glock_clear_object(struct gfs2_glock *gl, void *object)
spin_unlock(&gl->gl_lockref.lock);
}
extern void gfs2_inode_remember_delete(struct gfs2_glock *gl, u64 generation);
extern bool gfs2_inode_already_deleted(struct gfs2_glock *gl, u64 generation);
#endif /* __GLOCK_DOT_H__ */

View File

@ -612,11 +612,17 @@ static void iopen_go_callback(struct gfs2_glock *gl, bool remote)
if (gl->gl_demote_state == LM_ST_UNLOCKED &&
gl->gl_state == LM_ST_SHARED && ip) {
gl->gl_lockref.count++;
if (queue_work(gfs2_delete_workqueue, &gl->gl_delete) == 0)
if (!queue_delayed_work(gfs2_delete_workqueue,
&gl->gl_delete, 0))
gl->gl_lockref.count--;
}
}
static int iopen_go_demote_ok(const struct gfs2_glock *gl)
{
return !gfs2_delete_work_queued(gl);
}
/**
* inode_go_free - wake up anyone waiting for dlm's unlock ast to free it
* @gl: glock being freed
@ -696,7 +702,7 @@ const struct gfs2_glock_operations gfs2_inode_glops = {
.go_lock = inode_go_lock,
.go_dump = inode_go_dump,
.go_type = LM_TYPE_INODE,
.go_flags = GLOF_ASPACE | GLOF_LRU,
.go_flags = GLOF_ASPACE | GLOF_LRU | GLOF_LVB,
.go_free = inode_go_free,
};
@ -720,6 +726,7 @@ const struct gfs2_glock_operations gfs2_freeze_glops = {
const struct gfs2_glock_operations gfs2_iopen_glops = {
.go_type = LM_TYPE_IOPEN,
.go_callback = iopen_go_callback,
.go_demote_ok = iopen_go_demote_ok,
.go_flags = GLOF_LRU | GLOF_NONDISK,
};

View File

@ -345,6 +345,7 @@ enum {
GLF_OBJECT = 14, /* Used only for tracing */
GLF_BLOCKING = 15,
GLF_INODE_CREATING = 16, /* Inode creation occurring */
GLF_PENDING_DELETE = 17,
GLF_FREEING = 18, /* Wait for glock to be freed */
};
@ -378,8 +379,11 @@ struct gfs2_glock {
atomic_t gl_revokes;
struct delayed_work gl_work;
union {
/* For inode and iopen glocks only */
struct work_struct gl_delete;
/* For iopen glocks only */
struct {
struct delayed_work gl_delete;
u64 gl_no_formal_ino;
};
/* For rgrp glocks only */
struct {
loff_t start;
@ -398,6 +402,7 @@ enum {
GIF_ORDERED = 4,
GIF_FREE_VFS_INODE = 5,
GIF_GLOP_PENDING = 6,
GIF_DEFERRED_DELETE = 7,
};
struct gfs2_inode {

View File

@ -114,6 +114,10 @@ static void gfs2_set_iop(struct inode *inode)
* placeholder because it doesn't otherwise make sense), the on-disk block type
* is verified to be @blktype.
*
* When @no_formal_ino is non-zero, this function will return ERR_PTR(-ESTALE)
* if it detects that @no_formal_ino doesn't match the actual inode generation
* number. However, it doesn't always know unless @type is DT_UNKNOWN.
*
* Returns: A VFS inode, or an error
*/
@ -157,6 +161,11 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
if (error)
goto fail;
error = -ESTALE;
if (no_formal_ino &&
gfs2_inode_already_deleted(ip->i_gl, no_formal_ino))
goto fail;
if (blktype != GFS2_BLKST_FREE) {
error = gfs2_check_blk_type(sdp, no_addr,
blktype);
@ -170,6 +179,7 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
if (unlikely(error))
goto fail;
gfs2_cancel_delete_work(ip->i_iopen_gh.gh_gl);
glock_set_object(ip->i_iopen_gh.gh_gl, ip);
gfs2_glock_put(io_gl);
io_gl = NULL;
@ -188,13 +198,23 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
inode->i_mode = DT2IF(type);
}
gfs2_set_iop(inode);
if (gfs2_holder_initialized(&i_gh))
gfs2_glock_dq_uninit(&i_gh);
unlock_new_inode(inode);
gfs2_set_iop(inode);
}
if (gfs2_holder_initialized(&i_gh))
gfs2_glock_dq_uninit(&i_gh);
if (no_formal_ino && ip->i_no_formal_ino &&
no_formal_ino != ip->i_no_formal_ino) {
if (inode->i_state & I_NEW)
goto fail;
iput(inode);
return ERR_PTR(-ESTALE);
}
if (inode->i_state & I_NEW)
unlock_new_inode(inode);
return inode;
fail:
@ -206,23 +226,26 @@ fail:
return ERR_PTR(error);
}
/**
* gfs2_lookup_by_inum - look up an inode by inode number
* @sdp: The super block
* @no_addr: The inode number
* @no_formal_ino: The inode generation number (0 for any)
* @blktype: Requested block type (see gfs2_inode_lookup)
*/
struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
u64 *no_formal_ino, unsigned int blktype)
u64 no_formal_ino, unsigned int blktype)
{
struct super_block *sb = sdp->sd_vfs;
struct inode *inode;
int error;
inode = gfs2_inode_lookup(sb, DT_UNKNOWN, no_addr, 0, blktype);
inode = gfs2_inode_lookup(sb, DT_UNKNOWN, no_addr, no_formal_ino,
blktype);
if (IS_ERR(inode))
return inode;
/* Two extra checks for NFS only */
if (no_formal_ino) {
error = -ESTALE;
if (GFS2_I(inode)->i_no_formal_ino != *no_formal_ino)
goto fail_iput;
error = -EIO;
if (GFS2_I(inode)->i_diskflags & GFS2_DIF_SYSTEM)
goto fail_iput;
@ -724,6 +747,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
if (error)
goto fail_gunlock2;
gfs2_cancel_delete_work(ip->i_iopen_gh.gh_gl);
glock_set_object(ip->i_iopen_gh.gh_gl, ip);
gfs2_set_iop(inode);
insert_inode_hash(inode);

View File

@ -92,7 +92,7 @@ extern struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type,
u64 no_addr, u64 no_formal_ino,
unsigned int blktype);
extern struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
u64 *no_formal_ino,
u64 no_formal_ino,
unsigned int blktype);
extern int gfs2_inode_refresh(struct gfs2_inode *ip);

View File

@ -1835,7 +1835,7 @@ static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip
*/
ip = gl->gl_object;
if (ip || queue_work(gfs2_delete_workqueue, &gl->gl_delete) == 0)
if (ip || !gfs2_queue_delete_work(gl, 0))
gfs2_glock_put(gl);
else
found++;

View File

@ -626,7 +626,7 @@ int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
}
}
flush_workqueue(gfs2_delete_workqueue);
gfs2_flush_delete_work(sdp);
if (!log_write_allowed && current == sdp->sd_quotad_process)
fs_warn(sdp, "The quotad daemon is withdrawing.\n");
else if (sdp->sd_quotad_process)
@ -1054,7 +1054,7 @@ static int gfs2_drop_inode(struct inode *inode)
struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
gfs2_glock_hold(gl);
if (queue_work(gfs2_delete_workqueue, &gl->gl_delete) == 0)
if (!gfs2_queue_delete_work(gl, 0))
gfs2_glock_queue_put(gl);
return false;
}
@ -1258,6 +1258,55 @@ static void gfs2_glock_put_eventually(struct gfs2_glock *gl)
gfs2_glock_put(gl);
}
static bool gfs2_upgrade_iopen_glock(struct inode *inode)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_holder *gh = &ip->i_iopen_gh;
long timeout = 5 * HZ;
int error;
gh->gh_flags |= GL_NOCACHE;
gfs2_glock_dq_wait(gh);
/*
* If there are no other lock holders, we'll get the lock immediately.
* Otherwise, the other nodes holding the lock will be notified about
* our locking request. If they don't have the inode open, they'll
* evict the cached inode and release the lock. Otherwise, if they
* poke the inode glock, we'll take this as an indication that they
* still need the iopen glock and that they'll take care of deleting
* the inode when they're done. As a last resort, if another node
* keeps holding the iopen glock without showing any activity on the
* inode glock, we'll eventually time out.
*
* Note that we're passing the LM_FLAG_TRY_1CB flag to the first
* locking request as an optimization to notify lock holders as soon as
* possible. Without that flag, they'd be notified implicitly by the
* second locking request.
*/
gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, gh);
error = gfs2_glock_nq(gh);
if (error != GLR_TRYFAILED)
return !error;
gfs2_holder_reinit(LM_ST_EXCLUSIVE, GL_ASYNC | GL_NOCACHE, gh);
error = gfs2_glock_nq(gh);
if (error)
return false;
timeout = wait_event_interruptible_timeout(sdp->sd_async_glock_wait,
!test_bit(HIF_WAIT, &gh->gh_iflags) ||
test_bit(GLF_DEMOTE, &ip->i_gl->gl_flags),
timeout);
if (!test_bit(HIF_HOLDER, &gh->gh_iflags)) {
gfs2_glock_dq(gh);
return false;
}
return true;
}
/**
* gfs2_evict_inode - Remove an inode from cache
* @inode: The inode to evict
@ -1299,9 +1348,12 @@ static void gfs2_evict_inode(struct inode *inode)
if (test_bit(GIF_ALLOC_FAILED, &ip->i_flags)) {
BUG_ON(!gfs2_glock_is_locked_by_me(ip->i_gl));
gfs2_holder_mark_uninitialized(&gh);
goto alloc_failed;
goto out_delete;
}
if (test_bit(GIF_DEFERRED_DELETE, &ip->i_flags))
goto out;
/* Deletes should never happen under memory pressure anymore. */
if (WARN_ON_ONCE(current->flags & PF_MEMALLOC))
goto out;
@ -1315,6 +1367,8 @@ static void gfs2_evict_inode(struct inode *inode)
goto out;
}
if (gfs2_inode_already_deleted(ip->i_gl, ip->i_no_formal_ino))
goto out_truncate;
error = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED);
if (error)
goto out_truncate;
@ -1331,16 +1385,13 @@ static void gfs2_evict_inode(struct inode *inode)
if (inode->i_nlink)
goto out_truncate;
alloc_failed:
out_delete:
if (gfs2_holder_initialized(&ip->i_iopen_gh) &&
test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) {
ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
gfs2_glock_dq_wait(&ip->i_iopen_gh);
gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE,
&ip->i_iopen_gh);
error = gfs2_glock_nq(&ip->i_iopen_gh);
if (error)
if (!gfs2_upgrade_iopen_glock(inode)) {
gfs2_holder_uninit(&ip->i_iopen_gh);
goto out_truncate;
}
}
if (S_ISDIR(inode->i_mode) &&
@ -1368,6 +1419,7 @@ alloc_failed:
that subsequent inode creates don't see an old gl_object. */
glock_clear_object(ip->i_gl, ip);
error = gfs2_dinode_dealloc(ip);
gfs2_inode_remember_delete(ip->i_gl, ip->i_no_formal_ino);
goto out_unlock;
out_truncate:

View File

@ -171,6 +171,12 @@ struct gfs2_rindex {
#define GFS2_RGF_NOALLOC 0x00000008
#define GFS2_RGF_TRIMMED 0x00000010
struct gfs2_inode_lvb {
__be32 ri_magic;
__be32 __pad;
__be64 ri_generation_deleted;
};
struct gfs2_rgrp_lvb {
__be32 rl_magic;
__be32 rl_flags;