summaryrefslogtreecommitdiff
path: root/fs/gfs2/glops.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/gfs2/glops.c')
-rw-r--r--fs/gfs2/glops.c311
1 files changed, 105 insertions, 206 deletions
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index d78b61ecc1cd..2173ccf5034b 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -11,6 +11,7 @@
#include <linux/bio.h>
#include <linux/posix_acl.h>
#include <linux/security.h>
+#include <linux/log2.h>
#include "gfs2.h"
#include "incore.h"
@@ -29,8 +30,6 @@
struct workqueue_struct *gfs2_freeze_wq;
-extern struct workqueue_struct *gfs2_control_wq;
-
static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh)
{
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
@@ -39,12 +38,12 @@ static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh)
"AIL buffer %p: blocknr %llu state 0x%08lx mapping %p page "
"state 0x%lx\n",
bh, (unsigned long long)bh->b_blocknr, bh->b_state,
- bh->b_page->mapping, bh->b_page->flags);
+ bh->b_folio->mapping, bh->b_folio->flags.f);
fs_err(sdp, "AIL glock %u:%llu mapping %p\n",
gl->gl_name.ln_type, gl->gl_name.ln_number,
gfs2_glock2aspace(gl));
gfs2_lm(sdp, "AIL error\n");
- gfs2_withdraw_delayed(sdp);
+ gfs2_withdraw(sdp);
}
/**
@@ -90,7 +89,7 @@ static int gfs2_ail_empty_gl(struct gfs2_glock *gl)
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
struct gfs2_trans tr;
unsigned int revokes;
- int ret;
+ int ret = 0;
revokes = atomic_read(&gl->gl_ail_count);
@@ -124,15 +123,18 @@ static int gfs2_ail_empty_gl(struct gfs2_glock *gl)
memset(&tr, 0, sizeof(tr));
set_bit(TR_ONSTACK, &tr.tr_flags);
ret = __gfs2_trans_begin(&tr, sdp, 0, revokes, _RET_IP_);
- if (ret)
+ if (ret) {
+ fs_err(sdp, "Transaction error %d: Unable to write revokes.", ret);
goto flush;
+ }
__gfs2_ail_flush(gl, 0, revokes);
gfs2_trans_end(sdp);
flush:
- gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
- GFS2_LFC_AIL_EMPTY_GL);
- return 0;
+ if (!ret)
+ gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
+ GFS2_LFC_AIL_EMPTY_GL);
+ return ret;
}
void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
@@ -162,7 +164,7 @@ void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
static int gfs2_rgrp_metasync(struct gfs2_glock *gl)
{
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
- struct address_space *metamapping = &sdp->sd_aspace;
+ struct address_space *metamapping = gfs2_aspace(sdp);
struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
const unsigned bsize = sdp->sd_sb.sb_bsize;
loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK;
@@ -193,7 +195,7 @@ static int rgrp_go_sync(struct gfs2_glock *gl)
struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
int error;
- if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
+ if (!rgd || !test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
return 0;
GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE);
@@ -219,18 +221,22 @@ static int rgrp_go_sync(struct gfs2_glock *gl)
static void rgrp_go_inval(struct gfs2_glock *gl, int flags)
{
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
- struct address_space *mapping = &sdp->sd_aspace;
+ struct address_space *mapping = gfs2_aspace(sdp);
struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
const unsigned bsize = sdp->sd_sb.sb_bsize;
- loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK;
- loff_t end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1;
+ loff_t start, end;
+ if (!rgd)
+ return;
+ start = (rgd->rd_addr * bsize) & PAGE_MASK;
+ end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1;
gfs2_rgrp_brelse(rgd);
WARN_ON_ONCE(!(flags & DIO_METADATA));
+ gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
truncate_inode_pages_range(mapping, start, end);
}
-static void gfs2_rgrp_go_dump(struct seq_file *seq, struct gfs2_glock *gl,
+static void gfs2_rgrp_go_dump(struct seq_file *seq, const struct gfs2_glock *gl,
const char *fs_id_buf)
{
struct gfs2_rgrpd *rgd = gl->gl_object;
@@ -323,7 +329,9 @@ static int inode_go_sync(struct gfs2_glock *gl)
ret = gfs2_inode_metasync(gl);
if (!error)
error = ret;
- gfs2_ail_empty_gl(gl);
+ ret = gfs2_ail_empty_gl(gl);
+ if (!error)
+ error = ret;
/*
* Writeback of the data mapping may cause the dirty flag to be set
* so we have to clear it again here.
@@ -351,6 +359,8 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags)
{
struct gfs2_inode *ip = gfs2_glock2inode(gl);
+ gfs2_assert_withdraw(gl->gl_name.ln_sbd, !atomic_read(&gl->gl_ail_count));
+
if (flags & DIO_METADATA) {
struct address_space *mapping = gfs2_glock2aspace(gl);
truncate_inode_pages(mapping, 0);
@@ -374,36 +384,24 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags)
gfs2_clear_glop_pending(ip);
}
-/**
- * inode_go_demote_ok - Check to see if it's ok to unlock an inode glock
- * @gl: the glock
- *
- * Returns: 1 if it's ok
- */
-
-static int inode_go_demote_ok(const struct gfs2_glock *gl)
-{
- struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
-
- if (sdp->sd_jindex == gl->gl_object || sdp->sd_rindex == gl->gl_object)
- return 0;
-
- return 1;
-}
-
static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
{
+ struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
const struct gfs2_dinode *str = buf;
- struct timespec64 atime;
+ struct timespec64 atime, iatime;
u16 height, depth;
umode_t mode = be32_to_cpu(str->di_mode);
struct inode *inode = &ip->i_inode;
- bool is_new = inode->i_state & I_NEW;
+ bool is_new = inode_state_read_once(inode) & I_NEW;
- if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)))
- goto corrupt;
- if (unlikely(!is_new && inode_wrong_type(inode, mode)))
- goto corrupt;
+ if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr))) {
+ gfs2_consist_inode(ip);
+ return -EIO;
+ }
+ if (unlikely(!is_new && inode_wrong_type(inode, mode))) {
+ gfs2_consist_inode(ip);
+ return -EIO;
+ }
ip->i_no_formal_ino = be64_to_cpu(str->di_num.no_formal_ino);
inode->i_mode = mode;
if (is_new) {
@@ -424,12 +422,13 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
gfs2_set_inode_blocks(inode, be64_to_cpu(str->di_blocks));
atime.tv_sec = be64_to_cpu(str->di_atime);
atime.tv_nsec = be32_to_cpu(str->di_atime_nsec);
- if (timespec64_compare(&inode->i_atime, &atime) < 0)
- inode->i_atime = atime;
- inode->i_mtime.tv_sec = be64_to_cpu(str->di_mtime);
- inode->i_mtime.tv_nsec = be32_to_cpu(str->di_mtime_nsec);
- inode->i_ctime.tv_sec = be64_to_cpu(str->di_ctime);
- inode->i_ctime.tv_nsec = be32_to_cpu(str->di_ctime_nsec);
+ iatime = inode_get_atime(inode);
+ if (timespec64_compare(&iatime, &atime) < 0)
+ inode_set_atime_to_ts(inode, atime);
+ inode_set_mtime(inode, be64_to_cpu(str->di_mtime),
+ be32_to_cpu(str->di_mtime_nsec));
+ inode_set_ctime(inode, be64_to_cpu(str->di_ctime),
+ be32_to_cpu(str->di_ctime_nsec));
ip->i_goal = be64_to_cpu(str->di_goal_meta);
ip->i_generation = be64_to_cpu(str->di_generation);
@@ -439,26 +438,33 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
/* i_diskflags and i_eattr must be set before gfs2_set_inode_flags() */
gfs2_set_inode_flags(inode);
height = be16_to_cpu(str->di_height);
- if (unlikely(height > GFS2_MAX_META_HEIGHT))
- goto corrupt;
+ if (unlikely(height > sdp->sd_max_height)) {
+ gfs2_consist_inode(ip);
+ return -EIO;
+ }
ip->i_height = (u8)height;
depth = be16_to_cpu(str->di_depth);
- if (unlikely(depth > GFS2_DIR_MAX_DEPTH))
- goto corrupt;
+ if (unlikely(depth > GFS2_DIR_MAX_DEPTH)) {
+ gfs2_consist_inode(ip);
+ return -EIO;
+ }
+ if ((ip->i_diskflags & GFS2_DIF_EXHASH) &&
+ depth < ilog2(sdp->sd_hash_ptrs)) {
+ gfs2_consist_inode(ip);
+ return -EIO;
+ }
ip->i_depth = (u8)depth;
ip->i_entries = be32_to_cpu(str->di_entries);
- if (gfs2_is_stuffed(ip) && inode->i_size > gfs2_max_stuffed_size(ip))
- goto corrupt;
-
+ if (gfs2_is_stuffed(ip) && inode->i_size > gfs2_max_stuffed_size(ip)) {
+ gfs2_consist_inode(ip);
+ return -EIO;
+ }
if (S_ISREG(inode->i_mode))
gfs2_set_aops(inode);
return 0;
-corrupt:
- gfs2_consist_inode(ip);
- return -EIO;
}
/**
@@ -468,7 +474,7 @@ corrupt:
* Returns: errno
*/
-int gfs2_inode_refresh(struct gfs2_inode *ip)
+static int gfs2_inode_refresh(struct gfs2_inode *ip)
{
struct buffer_head *dibh;
int error;
@@ -484,7 +490,7 @@ int gfs2_inode_refresh(struct gfs2_inode *ip)
/**
* inode_go_instantiate - read in an inode if necessary
- * @gh: The glock holder
+ * @gl: The glock
*
* Returns: errno
*/
@@ -492,11 +498,18 @@ int gfs2_inode_refresh(struct gfs2_inode *ip)
static int inode_go_instantiate(struct gfs2_glock *gl)
{
struct gfs2_inode *ip = gl->gl_object;
+ struct gfs2_glock *io_gl;
+ int error;
if (!ip) /* no inode to populate - read it in later */
return 0;
- return gfs2_inode_refresh(ip);
+ error = gfs2_inode_refresh(ip);
+ if (error)
+ return error;
+ io_gl = ip->i_iopen_gh.gh_gl;
+ io_gl->gl_no_formal_ino = ip->i_no_formal_ino;
+ return 0;
}
static int inode_go_held(struct gfs2_holder *gh)
@@ -527,71 +540,54 @@ static int inode_go_held(struct gfs2_holder *gh)
*
*/
-static void inode_go_dump(struct seq_file *seq, struct gfs2_glock *gl,
+static void inode_go_dump(struct seq_file *seq, const struct gfs2_glock *gl,
const char *fs_id_buf)
{
struct gfs2_inode *ip = gl->gl_object;
- struct inode *inode = &ip->i_inode;
- unsigned long nrpages;
+ const struct inode *inode = &ip->i_inode;
if (ip == NULL)
return;
- xa_lock_irq(&inode->i_data.i_pages);
- nrpages = inode->i_data.nrpages;
- xa_unlock_irq(&inode->i_data.i_pages);
-
gfs2_print_dbg(seq, "%s I: n:%llu/%llu t:%u f:0x%02lx d:0x%08x s:%llu "
"p:%lu\n", fs_id_buf,
(unsigned long long)ip->i_no_formal_ino,
(unsigned long long)ip->i_no_addr,
- IF2DT(ip->i_inode.i_mode), ip->i_flags,
+ IF2DT(inode->i_mode), ip->i_flags,
(unsigned int)ip->i_diskflags,
- (unsigned long long)i_size_read(inode), nrpages);
+ (unsigned long long)i_size_read(inode),
+ inode->i_data.nrpages);
}
/**
- * freeze_go_sync - promote/demote the freeze glock
+ * freeze_go_callback - A cluster node is requesting a freeze
* @gl: the glock
+ * @remote: true if this came from a different cluster node
*/
-static int freeze_go_sync(struct gfs2_glock *gl)
+static void freeze_go_callback(struct gfs2_glock *gl, bool remote)
{
- int error = 0;
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+ struct super_block *sb = sdp->sd_vfs;
+
+ if (!remote ||
+ (gl->gl_state != LM_ST_SHARED &&
+ gl->gl_state != LM_ST_UNLOCKED) ||
+ gl->gl_demote_state != LM_ST_UNLOCKED)
+ return;
/*
- * We need to check gl_state == LM_ST_SHARED here and not gl_req ==
- * LM_ST_EXCLUSIVE. That's because when any node does a freeze,
- * all the nodes should have the freeze glock in SH mode and they all
- * call do_xmote: One for EX and the others for UN. They ALL must
- * freeze locally, and they ALL must queue freeze work. The freeze_work
- * calls freeze_func, which tries to reacquire the freeze glock in SH,
- * effectively waiting for the thaw on the node who holds it in EX.
- * Once thawed, the work func acquires the freeze glock in
- * SH and everybody goes back to thawed.
+ * Try to get an active super block reference to prevent racing with
+ * unmount (see super_trylock_shared()). But note that unmount isn't
+ * the only place where a write lock on s_umount is taken, and we can
+ * fail here because of things like remount as well.
*/
- if (gl->gl_state == LM_ST_SHARED && !gfs2_withdrawn(sdp) &&
- !test_bit(SDF_NORECOVERY, &sdp->sd_flags)) {
- atomic_set(&sdp->sd_freeze_state, SFS_STARTING_FREEZE);
- error = freeze_super(sdp->sd_vfs);
- if (error) {
- fs_info(sdp, "GFS2: couldn't freeze filesystem: %d\n",
- error);
- if (gfs2_withdrawn(sdp)) {
- atomic_set(&sdp->sd_freeze_state, SFS_UNFROZEN);
- return 0;
- }
- gfs2_assert_withdraw(sdp, 0);
- }
- queue_work(gfs2_freeze_wq, &sdp->sd_freeze_work);
- if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
- gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_FREEZE |
- GFS2_LFC_FREEZE_GO_SYNC);
- else /* read-only mounts */
- atomic_set(&sdp->sd_freeze_state, SFS_FROZEN);
+ if (down_read_trylock(&sb->s_umount)) {
+ atomic_inc(&sb->s_active);
+ up_read(&sb->s_umount);
+ if (!queue_work(gfs2_freeze_wq, &sdp->sd_freeze_work))
+ deactivate_super(sb);
}
- return 0;
}
/**
@@ -609,31 +605,18 @@ static int freeze_go_xmote_bh(struct gfs2_glock *gl)
if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
- error = gfs2_find_jhead(sdp->sd_jdesc, &head, false);
- if (gfs2_assert_withdraw_delayed(sdp, !error))
+ error = gfs2_find_jhead(sdp->sd_jdesc, &head);
+ if (gfs2_assert_withdraw(sdp, !error))
return error;
- if (gfs2_assert_withdraw_delayed(sdp, head.lh_flags &
- GFS2_LOG_HEAD_UNMOUNT))
+ if (gfs2_assert_withdraw(sdp, head.lh_flags &
+ GFS2_LOG_HEAD_UNMOUNT))
return -EIO;
- sdp->sd_log_sequence = head.lh_sequence + 1;
- gfs2_log_pointers_init(sdp, head.lh_blkno);
+ gfs2_log_pointers_init(sdp, &head);
}
return 0;
}
/**
- * freeze_go_demote_ok
- * @gl: the glock
- *
- * Always returns 0
- */
-
-static int freeze_go_demote_ok(const struct gfs2_glock *gl)
-{
- return 0;
-}
-
-/**
* iopen_go_callback - schedule the dcache entry for the inode to be deleted
* @gl: the glock
* @remote: true if this came from a different cluster node
@@ -645,105 +628,29 @@ static void iopen_go_callback(struct gfs2_glock *gl, bool remote)
struct gfs2_inode *ip = gl->gl_object;
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
- if (!remote || sb_rdonly(sdp->sd_vfs))
+ if (!remote || test_bit(SDF_KILL, &sdp->sd_flags))
return;
if (gl->gl_demote_state == LM_ST_UNLOCKED &&
gl->gl_state == LM_ST_SHARED && ip) {
gl->gl_lockref.count++;
- if (!queue_delayed_work(gfs2_delete_workqueue,
- &gl->gl_delete, 0))
+ if (!gfs2_queue_try_to_evict(gl))
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
- *
- * For now, this is only used for the journal inode glock. In withdraw
- * situations, we need to wait for the glock to be freed so that we know
- * other nodes may proceed with recovery / journal replay.
- */
-static void inode_go_free(struct gfs2_glock *gl)
-{
- /* Note that we cannot reference gl_object because it's already set
- * to NULL by this point in its lifecycle. */
- if (!test_bit(GLF_FREEING, &gl->gl_flags))
- return;
- clear_bit_unlock(GLF_FREEING, &gl->gl_flags);
- wake_up_bit(&gl->gl_flags, GLF_FREEING);
-}
-
-/**
- * nondisk_go_callback - used to signal when a node did a withdraw
- * @gl: the nondisk glock
- * @remote: true if this came from a different cluster node
- *
- */
-static void nondisk_go_callback(struct gfs2_glock *gl, bool remote)
-{
- struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
-
- /* Ignore the callback unless it's from another node, and it's the
- live lock. */
- if (!remote || gl->gl_name.ln_number != GFS2_LIVE_LOCK)
- return;
-
- /* First order of business is to cancel the demote request. We don't
- * really want to demote a nondisk glock. At best it's just to inform
- * us of another node's withdraw. We'll keep it in SH mode. */
- clear_bit(GLF_DEMOTE, &gl->gl_flags);
- clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags);
-
- /* Ignore the unlock if we're withdrawn, unmounting, or in recovery. */
- if (test_bit(SDF_NORECOVERY, &sdp->sd_flags) ||
- test_bit(SDF_WITHDRAWN, &sdp->sd_flags) ||
- test_bit(SDF_REMOTE_WITHDRAW, &sdp->sd_flags))
- return;
-
- /* We only care when a node wants us to unlock, because that means
- * they want a journal recovered. */
- if (gl->gl_demote_state != LM_ST_UNLOCKED)
- return;
-
- if (sdp->sd_args.ar_spectator) {
- fs_warn(sdp, "Spectator node cannot recover journals.\n");
- return;
- }
-
- fs_warn(sdp, "Some node has withdrawn; checking for recovery.\n");
- set_bit(SDF_REMOTE_WITHDRAW, &sdp->sd_flags);
- /*
- * We can't call remote_withdraw directly here or gfs2_recover_journal
- * because this is called from the glock unlock function and the
- * remote_withdraw needs to enqueue and dequeue the same "live" glock
- * we were called from. So we queue it to the control work queue in
- * lock_dlm.
- */
- queue_delayed_work(gfs2_control_wq, &sdp->sd_control_work, 0);
-}
-
const struct gfs2_glock_operations gfs2_meta_glops = {
.go_type = LM_TYPE_META,
- .go_flags = GLOF_NONDISK,
};
const struct gfs2_glock_operations gfs2_inode_glops = {
.go_sync = inode_go_sync,
.go_inval = inode_go_inval,
- .go_demote_ok = inode_go_demote_ok,
.go_instantiate = inode_go_instantiate,
.go_held = inode_go_held,
.go_dump = inode_go_dump,
.go_type = LM_TYPE_INODE,
- .go_flags = GLOF_ASPACE | GLOF_LRU | GLOF_LVB,
- .go_free = inode_go_free,
+ .go_flags = GLOF_ASPACE | GLOF_LVB,
};
const struct gfs2_glock_operations gfs2_rgrp_glops = {
@@ -756,41 +663,33 @@ const struct gfs2_glock_operations gfs2_rgrp_glops = {
};
const struct gfs2_glock_operations gfs2_freeze_glops = {
- .go_sync = freeze_go_sync,
.go_xmote_bh = freeze_go_xmote_bh,
- .go_demote_ok = freeze_go_demote_ok,
+ .go_callback = freeze_go_callback,
.go_type = LM_TYPE_NONDISK,
- .go_flags = GLOF_NONDISK,
};
const struct gfs2_glock_operations gfs2_iopen_glops = {
.go_type = LM_TYPE_IOPEN,
.go_callback = iopen_go_callback,
.go_dump = inode_go_dump,
- .go_demote_ok = iopen_go_demote_ok,
- .go_flags = GLOF_LRU | GLOF_NONDISK,
.go_subclass = 1,
};
const struct gfs2_glock_operations gfs2_flock_glops = {
.go_type = LM_TYPE_FLOCK,
- .go_flags = GLOF_LRU | GLOF_NONDISK,
};
const struct gfs2_glock_operations gfs2_nondisk_glops = {
.go_type = LM_TYPE_NONDISK,
- .go_flags = GLOF_NONDISK,
- .go_callback = nondisk_go_callback,
};
const struct gfs2_glock_operations gfs2_quota_glops = {
.go_type = LM_TYPE_QUOTA,
- .go_flags = GLOF_LVB | GLOF_LRU | GLOF_NONDISK,
+ .go_flags = GLOF_LVB,
};
const struct gfs2_glock_operations gfs2_journal_glops = {
.go_type = LM_TYPE_JOURNAL,
- .go_flags = GLOF_NONDISK,
};
const struct gfs2_glock_operations *gfs2_glops_list[] = {