From f85122afeb230b4ad0b90ac40aba0fe6532baeea Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Tue, 2 Apr 2019 08:04:30 -0400
Subject: ceph: add refcounting for Fx caps
In future patches we'll be taking and relying on Fx caps. Add proper
refcounting for them.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
fs/ceph/inode.c | 1 +
1 file changed, 1 insertion(+)
(limited to 'fs/ceph/inode.c')
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index d01710a16a4a..094b8fc37787 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -496,6 +496,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
ci->i_rdcache_ref = 0;
ci->i_wr_ref = 0;
ci->i_wb_ref = 0;
+ ci->i_fx_ref = 0;
ci->i_wrbuffer_ref = 0;
ci->i_wrbuffer_ref_head = 0;
atomic_set(&ci->i_filelock_ref, 0);
--
cgit v1.2.3
From 3bb48b4142bbf72045af5ebe72e65ccff6d02680 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Mon, 2 Dec 2019 13:47:57 -0500
Subject: ceph: add flag to designate that a request is asynchronous
...and ensure that such requests are never queued. The MDS has need to
know that a request is asynchronous so add flags and proper
infrastructure for that.
Also, delegated inode numbers and directory caps are associated with the
session, so ensure that async requests are always transmitted on the
first attempt and are never queued to wait for session reestablishment.
If it does end up looking like we'll need to queue the request, then
have it return -EJUKEBOX so the caller can reattempt with a synchronous
request.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
fs/ceph/inode.c | 1 +
fs/ceph/mds_client.c | 15 +++++++++++++++
fs/ceph/mds_client.h | 1 +
include/linux/ceph/ceph_fs.h | 5 +++--
4 files changed, 20 insertions(+), 2 deletions(-)
(limited to 'fs/ceph/inode.c')
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 094b8fc37787..9869ec101e88 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1311,6 +1311,7 @@ retry_lookup:
err = fill_inode(in, req->r_locked_page, &rinfo->targeti, NULL,
session,
(!test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags) &&
+ !test_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags) &&
rinfo->head->result == 0) ? req->r_fmode : -1,
&req->r_caps_reservation);
if (err < 0) {
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 2da98b6cc064..9e8b2099e63f 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2528,6 +2528,8 @@ static int __prepare_send_request(struct ceph_mds_client *mdsc,
rhead->oldest_client_tid = cpu_to_le64(__get_oldest_tid(mdsc));
if (test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags))
flags |= CEPH_MDS_FLAG_REPLAY;
+ if (test_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags))
+ flags |= CEPH_MDS_FLAG_ASYNC;
if (req->r_parent)
flags |= CEPH_MDS_FLAG_WANT_DENTRY;
rhead->flags = cpu_to_le32(flags);
@@ -2611,6 +2613,10 @@ static void __do_request(struct ceph_mds_client *mdsc,
mds = __choose_mds(mdsc, req, &random);
if (mds < 0 ||
ceph_mdsmap_get_state(mdsc->mdsmap, mds) < CEPH_MDS_STATE_ACTIVE) {
+ if (test_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags)) {
+ err = -EJUKEBOX;
+ goto finish;
+ }
dout("do_request no mds or not active, waiting for map\n");
list_add(&req->r_wait, &mdsc->waiting_for_map);
return;
@@ -2635,6 +2641,15 @@ static void __do_request(struct ceph_mds_client *mdsc,
err = -EACCES;
goto out_session;
}
+ /*
+ * We cannot queue async requests since the caps and delegated
+ * inodes are bound to the session. Just return -EJUKEBOX and
+ * let the caller retry a sync request in that case.
+ */
+ if (test_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags)) {
+ err = -EJUKEBOX;
+ goto out_session;
+ }
if (session->s_state == CEPH_MDS_SESSION_NEW ||
session->s_state == CEPH_MDS_SESSION_CLOSING) {
__open_session(mdsc, session);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index a0918d00117c..95ac00e59e66 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -255,6 +255,7 @@ struct ceph_mds_request {
#define CEPH_MDS_R_GOT_RESULT (5) /* got a result */
#define CEPH_MDS_R_DID_PREPOPULATE (6) /* prepopulated readdir */
#define CEPH_MDS_R_PARENT_LOCKED (7) /* is r_parent->i_rwsem wlocked? */
+#define CEPH_MDS_R_ASYNC (8) /* async request */
unsigned long r_req_flags;
struct mutex r_fill_mutex;
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index cb21c5cf12c3..9f747a1b8788 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -444,8 +444,9 @@ union ceph_mds_request_args {
} __attribute__ ((packed)) lookupino;
} __attribute__ ((packed));
-#define CEPH_MDS_FLAG_REPLAY 1 /* this is a replayed op */
-#define CEPH_MDS_FLAG_WANT_DENTRY 2 /* want dentry in reply */
+#define CEPH_MDS_FLAG_REPLAY 1 /* this is a replayed op */
+#define CEPH_MDS_FLAG_WANT_DENTRY 2 /* want dentry in reply */
+#define CEPH_MDS_FLAG_ASYNC 4 /* request is asynchronous */
struct ceph_mds_request_head {
__le64 oldest_client_tid;
--
cgit v1.2.3
From f5e17aed3accb406f51ae528d657c275efc1edfc Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Tue, 18 Feb 2020 14:12:32 -0500
Subject: ceph: track primary dentry link
Newer versions of the MDS will flag a dentry as "primary". In later
patches, we'll need to consult this info, so track it in di->flags.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
fs/ceph/dir.c | 1 +
fs/ceph/inode.c | 8 +++++++-
fs/ceph/super.h | 1 +
include/linux/ceph/ceph_fs.h | 3 +++
4 files changed, 12 insertions(+), 1 deletion(-)
(limited to 'fs/ceph/inode.c')
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index d0cd0aba5843..a87274935a09 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1411,6 +1411,7 @@ void ceph_invalidate_dentry_lease(struct dentry *dentry)
spin_lock(&dentry->d_lock);
di->time = jiffies;
di->lease_shared_gen = 0;
+ di->flags &= ~CEPH_DENTRY_PRIMARY_LINK;
__dentry_lease_unlist(di);
spin_unlock(&dentry->d_lock);
}
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 9869ec101e88..7478bd0283c1 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1051,6 +1051,7 @@ static void __update_dentry_lease(struct inode *dir, struct dentry *dentry,
struct ceph_mds_session **old_lease_session)
{
struct ceph_dentry_info *di = ceph_dentry(dentry);
+ unsigned mask = le16_to_cpu(lease->mask);
long unsigned duration = le32_to_cpu(lease->duration_ms);
long unsigned ttl = from_time + (duration * HZ) / 1000;
long unsigned half_ttl = from_time + (duration * HZ / 2) / 1000;
@@ -1062,8 +1063,13 @@ static void __update_dentry_lease(struct inode *dir, struct dentry *dentry,
if (ceph_snap(dir) != CEPH_NOSNAP)
return;
+ if (mask & CEPH_LEASE_PRIMARY_LINK)
+ di->flags |= CEPH_DENTRY_PRIMARY_LINK;
+ else
+ di->flags &= ~CEPH_DENTRY_PRIMARY_LINK;
+
di->lease_shared_gen = atomic_read(&ceph_inode(dir)->i_shared_gen);
- if (duration == 0) {
+ if (!(mask & CEPH_LEASE_VALID)) {
__ceph_dentry_dir_lease_touch(di);
return;
}
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index b2711ee56b09..7a93f37e7708 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -284,6 +284,7 @@ struct ceph_dentry_info {
#define CEPH_DENTRY_REFERENCED 1
#define CEPH_DENTRY_LEASE_LIST 2
#define CEPH_DENTRY_SHRINK_LIST 4
+#define CEPH_DENTRY_PRIMARY_LINK 8
struct ceph_inode_xattrs_info {
/*
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 9f747a1b8788..94cc4b047987 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -531,6 +531,9 @@ struct ceph_mds_reply_lease {
__le32 seq;
} __attribute__ ((packed));
+#define CEPH_LEASE_VALID (1 | 2) /* old and new bit values */
+#define CEPH_LEASE_PRIMARY_LINK 4 /* primary linkage */
+
struct ceph_mds_reply_dirfrag {
__le32 frag; /* fragment */
__le32 auth; /* auth mds, if this is a delegation point */
--
cgit v1.2.3
From 966c716018de1c0860b3cfa65e316394d84723d2 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 5 Dec 2019 09:09:25 -0500
Subject: ceph: make ceph_fill_inode non-static
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
fs/ceph/inode.c | 47 ++++++++++++++++++++++++-----------------------
fs/ceph/super.h | 8 ++++++++
2 files changed, 32 insertions(+), 23 deletions(-)
(limited to 'fs/ceph/inode.c')
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 7478bd0283c1..4056c7968b86 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -728,11 +728,11 @@ void ceph_fill_file_time(struct inode *inode, int issued,
* Populate an inode based on info from mds. May be called on new or
* existing inodes.
*/
-static int fill_inode(struct inode *inode, struct page *locked_page,
- struct ceph_mds_reply_info_in *iinfo,
- struct ceph_mds_reply_dirfrag *dirinfo,
- struct ceph_mds_session *session, int cap_fmode,
- struct ceph_cap_reservation *caps_reservation)
+int ceph_fill_inode(struct inode *inode, struct page *locked_page,
+ struct ceph_mds_reply_info_in *iinfo,
+ struct ceph_mds_reply_dirfrag *dirinfo,
+ struct ceph_mds_session *session, int cap_fmode,
+ struct ceph_cap_reservation *caps_reservation)
{
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
struct ceph_mds_reply_inode *info = iinfo->in;
@@ -749,7 +749,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
bool new_version = false;
bool fill_inline = false;
- dout("fill_inode %p ino %llx.%llx v %llu had %llu\n",
+ dout("%s %p ino %llx.%llx v %llu had %llu\n", __func__,
inode, ceph_vinop(inode), le64_to_cpu(info->version),
ci->i_version);
@@ -770,7 +770,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
if (iinfo->xattr_len > 4) {
xattr_blob = ceph_buffer_new(iinfo->xattr_len, GFP_NOFS);
if (!xattr_blob)
- pr_err("fill_inode ENOMEM xattr blob %d bytes\n",
+ pr_err("%s ENOMEM xattr blob %d bytes\n", __func__,
iinfo->xattr_len);
}
@@ -933,8 +933,9 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
spin_unlock(&ci->i_ceph_lock);
if (symlen != i_size_read(inode)) {
- pr_err("fill_inode %llx.%llx BAD symlink "
- "size %lld\n", ceph_vinop(inode),
+ pr_err("%s %llx.%llx BAD symlink "
+ "size %lld\n", __func__,
+ ceph_vinop(inode),
i_size_read(inode));
i_size_write(inode, symlen);
inode->i_blocks = calc_inode_blocks(symlen);
@@ -958,7 +959,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
inode->i_fop = &ceph_dir_fops;
break;
default:
- pr_err("fill_inode %llx.%llx BAD mode 0%o\n",
+ pr_err("%s %llx.%llx BAD mode 0%o\n", __func__,
ceph_vinop(inode), inode->i_mode);
}
@@ -1246,10 +1247,9 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
struct inode *dir = req->r_parent;
if (dir) {
- err = fill_inode(dir, NULL,
- &rinfo->diri, rinfo->dirfrag,
- session, -1,
- &req->r_caps_reservation);
+ err = ceph_fill_inode(dir, NULL, &rinfo->diri,
+ rinfo->dirfrag, session, -1,
+ &req->r_caps_reservation);
if (err < 0)
goto done;
} else {
@@ -1314,14 +1314,14 @@ retry_lookup:
goto done;
}
- err = fill_inode(in, req->r_locked_page, &rinfo->targeti, NULL,
- session,
+ err = ceph_fill_inode(in, req->r_locked_page, &rinfo->targeti,
+ NULL, session,
(!test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags) &&
!test_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags) &&
rinfo->head->result == 0) ? req->r_fmode : -1,
&req->r_caps_reservation);
if (err < 0) {
- pr_err("fill_inode badness %p %llx.%llx\n",
+ pr_err("ceph_fill_inode badness %p %llx.%llx\n",
in, ceph_vinop(in));
if (in->i_state & I_NEW)
discard_new_inode(in);
@@ -1508,10 +1508,11 @@ static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req,
dout("new_inode badness got %d\n", err);
continue;
}
- rc = fill_inode(in, NULL, &rde->inode, NULL, session,
- -1, &req->r_caps_reservation);
+ rc = ceph_fill_inode(in, NULL, &rde->inode, NULL, session,
+ -1, &req->r_caps_reservation);
if (rc < 0) {
- pr_err("fill_inode badness on %p got %d\n", in, rc);
+ pr_err("ceph_fill_inode badness on %p got %d\n",
+ in, rc);
err = rc;
if (in->i_state & I_NEW) {
ihold(in);
@@ -1715,10 +1716,10 @@ retry_lookup:
}
}
- ret = fill_inode(in, NULL, &rde->inode, NULL, session,
- -1, &req->r_caps_reservation);
+ ret = ceph_fill_inode(in, NULL, &rde->inode, NULL, session,
+ -1, &req->r_caps_reservation);
if (ret < 0) {
- pr_err("fill_inode badness on %p\n", in);
+ pr_err("ceph_fill_inode badness on %p\n", in);
if (d_really_is_negative(dn)) {
/* avoid calling iput_final() in mds
* dispatch threads */
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index f5313d79ae27..2c479d761d32 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -895,6 +895,9 @@ static inline bool __ceph_have_pending_cap_snap(struct ceph_inode_info *ci)
}
/* inode.c */
+struct ceph_mds_reply_info_in;
+struct ceph_mds_reply_dirfrag;
+
extern const struct inode_operations ceph_file_iops;
extern struct inode *ceph_alloc_inode(struct super_block *sb);
@@ -910,6 +913,11 @@ extern void ceph_fill_file_time(struct inode *inode, int issued,
u64 time_warp_seq, struct timespec64 *ctime,
struct timespec64 *mtime,
struct timespec64 *atime);
+extern int ceph_fill_inode(struct inode *inode, struct page *locked_page,
+ struct ceph_mds_reply_info_in *iinfo,
+ struct ceph_mds_reply_dirfrag *dirinfo,
+ struct ceph_mds_session *session, int cap_fmode,
+ struct ceph_cap_reservation *caps_reservation);
extern int ceph_fill_trace(struct super_block *sb,
struct ceph_mds_request *req);
extern int ceph_readdir_prepopulate(struct ceph_mds_request *req,
--
cgit v1.2.3
From 785892fe88f693028a996d1cb363d60609848e5e Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 2 Jan 2020 07:11:38 -0500
Subject: ceph: cache layout in parent dir on first sync create
If a create is done, then typically we'll end up writing to the file
soon afterward. We don't want to wait for the reply before doing that
when doing an async create, so that means we need the layout for the
new file before we've gotten the response from the MDS.
All files created in a directory will initially inherit the same layout,
so copy off the requisite info from the first synchronous create in the
directory, and save it in a new i_cached_layout field. Zero out the
layout when we lose Dc caps in the dir.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
fs/ceph/caps.c | 13 ++++++++++---
fs/ceph/file.c | 22 +++++++++++++++++++++-
fs/ceph/inode.c | 2 ++
fs/ceph/mds_client.c | 7 ++++++-
fs/ceph/super.h | 1 +
5 files changed, 40 insertions(+), 5 deletions(-)
(limited to 'fs/ceph/inode.c')
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index d09b9d91cf4f..be85225b962c 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -561,14 +561,14 @@ static void __cap_delay_cancel(struct ceph_mds_client *mdsc,
spin_unlock(&mdsc->cap_delay_lock);
}
-/*
- * Common issue checks for add_cap, handle_cap_grant.
- */
+/* Common issue checks for add_cap, handle_cap_grant. */
static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
unsigned issued)
{
unsigned had = __ceph_caps_issued(ci, NULL);
+ lockdep_assert_held(&ci->i_ceph_lock);
+
/*
* Each time we receive FILE_CACHE anew, we increment
* i_rdcache_gen.
@@ -593,6 +593,13 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
__ceph_dir_clear_complete(ci);
}
}
+
+ /* Wipe saved layout if we're losing DIR_CREATE caps */
+ if (S_ISDIR(ci->vfs_inode.i_mode) && (had & CEPH_CAP_DIR_CREATE) &&
+ !(issued & CEPH_CAP_DIR_CREATE)) {
+ ceph_put_string(rcu_dereference_raw(ci->i_cached_layout.pool_ns));
+ memset(&ci->i_cached_layout, 0, sizeof(ci->i_cached_layout));
+ }
}
/*
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 7f8c4e308301..b6ad64b8863a 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -430,6 +430,23 @@ out:
return err;
}
+/* Clone the layout from a synchronous create, if the dir now has Dc caps */
+static void
+cache_file_layout(struct inode *dst, struct inode *src)
+{
+ struct ceph_inode_info *cdst = ceph_inode(dst);
+ struct ceph_inode_info *csrc = ceph_inode(src);
+
+ spin_lock(&cdst->i_ceph_lock);
+ if ((__ceph_caps_issued(cdst, NULL) & CEPH_CAP_DIR_CREATE) &&
+ !ceph_file_layout_is_valid(&cdst->i_cached_layout)) {
+ memcpy(&cdst->i_cached_layout, &csrc->i_layout,
+ sizeof(cdst->i_cached_layout));
+ rcu_assign_pointer(cdst->i_cached_layout.pool_ns,
+ ceph_try_get_string(csrc->i_layout.pool_ns));
+ }
+ spin_unlock(&cdst->i_ceph_lock);
+}
/*
* Do a lookup + open with a single request. If we get a non-existent
@@ -518,7 +535,10 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
} else {
dout("atomic_open finish_open on dn %p\n", dn);
if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
- ceph_init_inode_acls(d_inode(dentry), &as_ctx);
+ struct inode *newino = d_inode(dentry);
+
+ cache_file_layout(dir, newino);
+ ceph_init_inode_acls(newino, &as_ctx);
file->f_mode |= FMODE_CREATED;
}
err = finish_open(file, dentry, ceph_open);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 4056c7968b86..73f986efb1fd 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -447,6 +447,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
ci->i_max_files = 0;
memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout));
+ memset(&ci->i_cached_layout, 0, sizeof(ci->i_cached_layout));
RCU_INIT_POINTER(ci->i_layout.pool_ns, NULL);
ci->i_fragtree = RB_ROOT;
@@ -587,6 +588,7 @@ void ceph_evict_inode(struct inode *inode)
ceph_buffer_put(ci->i_xattrs.prealloc_blob);
ceph_put_string(rcu_dereference_raw(ci->i_layout.pool_ns));
+ ceph_put_string(rcu_dereference_raw(ci->i_cached_layout.pool_ns));
}
static inline blkcnt_t calc_inode_blocks(u64 size)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index a0ad9bd56b7f..177acb9f456b 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -3535,8 +3535,13 @@ static int reconnect_caps_cb(struct inode *inode, struct ceph_cap *cap,
cap->cap_gen = cap->session->s_cap_gen;
/* These are lost when the session goes away */
- if (S_ISDIR(inode->i_mode))
+ if (S_ISDIR(inode->i_mode)) {
+ if (cap->issued & CEPH_CAP_DIR_CREATE) {
+ ceph_put_string(rcu_dereference_raw(ci->i_cached_layout.pool_ns));
+ memset(&ci->i_cached_layout, 0, sizeof(ci->i_cached_layout));
+ }
cap->issued &= ~CEPH_CAP_ANY_DIR_OPS;
+ }
if (recon_state->msg_version >= 2) {
rec.v2.cap_id = cpu_to_le64(cap->cap_id);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 2c479d761d32..22b89eaeaad4 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -326,6 +326,7 @@ struct ceph_inode_info {
struct ceph_dir_layout i_dir_layout;
struct ceph_file_layout i_layout;
+ struct ceph_file_layout i_cached_layout; // for async creates
char *i_symlink;
/* for dirs */
--
cgit v1.2.3
From 719a2514e9bf313c3627078926d56bc2a8b290d1 Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zyan@redhat.com>
Date: Thu, 5 Mar 2020 20:21:00 +0800
Subject: ceph: consider inode's last read/write when calculating wanted caps
Add i_last_rd and i_last_wr to ceph_inode_info. These fields are
used to track the last time the client acquired read/write caps for
the inode.
If there is no read/write on an inode for 'caps_wanted_delay_max'
seconds, __ceph_caps_file_wanted() does not request caps for read/write
even there are open files.
Call __ceph_touch_fmode() for dir operations. __ceph_caps_file_wanted()
calculates dir's wanted caps according to last dir read/modification. If
there is recent dir read, dir inode wants CEPH_CAP_ANY_SHARED caps. If
there is recent dir modification, also wants CEPH_CAP_FILE_EXCL.
Readdir is a special case. Dir inode wants CEPH_CAP_FILE_EXCL after
readdir, as with that, modifications do not need to release
CEPH_CAP_FILE_SHARED or invalidate all dentry leases issued by readdir.
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
fs/ceph/caps.c | 183 ++++++++++++++++++++++++++++++-------------
fs/ceph/dir.c | 21 +++--
fs/ceph/file.c | 21 ++---
fs/ceph/inode.c | 10 ++-
fs/ceph/ioctl.c | 2 +
fs/ceph/mds_client.c | 11 ++-
fs/ceph/super.h | 13 ++-
include/linux/ceph/ceph_fs.h | 1 +
8 files changed, 188 insertions(+), 74 deletions(-)
(limited to 'fs/ceph/inode.c')
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index a75e5eb3740e..aa5bb5a4de46 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -978,19 +978,67 @@ int __ceph_caps_used(struct ceph_inode_info *ci)
return used;
}
+#define FMODE_WAIT_BIAS 1000
+
/*
* wanted, by virtue of open file modes
*/
int __ceph_caps_file_wanted(struct ceph_inode_info *ci)
{
- int i, bits = 0;
- for (i = 0; i < CEPH_FILE_MODE_BITS; i++) {
- if (ci->i_nr_by_mode[i])
- bits |= 1 << i;
+ const int PIN_SHIFT = ffs(CEPH_FILE_MODE_PIN);
+ const int RD_SHIFT = ffs(CEPH_FILE_MODE_RD);
+ const int WR_SHIFT = ffs(CEPH_FILE_MODE_WR);
+ const int LAZY_SHIFT = ffs(CEPH_FILE_MODE_LAZY);
+ struct ceph_mount_options *opt =
+ ceph_inode_to_client(&ci->vfs_inode)->mount_options;
+ unsigned long used_cutoff = jiffies - opt->caps_wanted_delay_max * HZ;
+ unsigned long idle_cutoff = jiffies - opt->caps_wanted_delay_min * HZ;
+
+ if (S_ISDIR(ci->vfs_inode.i_mode)) {
+ int want = 0;
+
+ /* use used_cutoff here, to keep dir's wanted caps longer */
+ if (ci->i_nr_by_mode[RD_SHIFT] > 0 ||
+ time_after(ci->i_last_rd, used_cutoff))
+ want |= CEPH_CAP_ANY_SHARED;
+
+ if (ci->i_nr_by_mode[WR_SHIFT] > 0 ||
+ time_after(ci->i_last_wr, used_cutoff)) {
+ want |= CEPH_CAP_ANY_SHARED | CEPH_CAP_FILE_EXCL;
+ if (opt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS)
+ want |= CEPH_CAP_ANY_DIR_OPS;
+ }
+
+ if (want || ci->i_nr_by_mode[PIN_SHIFT] > 0)
+ want |= CEPH_CAP_PIN;
+
+ return want;
+ } else {
+ int bits = 0;
+
+ if (ci->i_nr_by_mode[RD_SHIFT] > 0) {
+ if (ci->i_nr_by_mode[RD_SHIFT] >= FMODE_WAIT_BIAS ||
+ time_after(ci->i_last_rd, used_cutoff))
+ bits |= 1 << RD_SHIFT;
+ } else if (time_after(ci->i_last_rd, idle_cutoff)) {
+ bits |= 1 << RD_SHIFT;
+ }
+
+ if (ci->i_nr_by_mode[WR_SHIFT] > 0) {
+ if (ci->i_nr_by_mode[WR_SHIFT] >= FMODE_WAIT_BIAS ||
+ time_after(ci->i_last_wr, used_cutoff))
+ bits |= 1 << WR_SHIFT;
+ } else if (time_after(ci->i_last_wr, idle_cutoff)) {
+ bits |= 1 << WR_SHIFT;
+ }
+
+ /* check lazyio only when read/write is wanted */
+ if ((bits & (CEPH_FILE_MODE_RDWR << 1)) &&
+ ci->i_nr_by_mode[LAZY_SHIFT] > 0)
+ bits |= 1 << LAZY_SHIFT;
+
+ return bits ? ceph_caps_for_mode(bits >> 1) : 0;
}
- if (bits == 0)
- return 0;
- return ceph_caps_for_mode(bits >> 1);
}
/*
@@ -1032,14 +1080,6 @@ int __ceph_caps_mds_wanted(struct ceph_inode_info *ci, bool check)
return mds_wanted;
}
-/*
- * called under i_ceph_lock
- */
-static int __ceph_is_single_caps(struct ceph_inode_info *ci)
-{
- return rb_first(&ci->i_caps) == rb_last(&ci->i_caps);
-}
-
int ceph_is_any_caps(struct inode *inode)
{
struct ceph_inode_info *ci = ceph_inode(inode);
@@ -1877,10 +1917,6 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
if (ci->i_ceph_flags & CEPH_I_FLUSH)
flags |= CHECK_CAPS_FLUSH;
- if (!(flags & CHECK_CAPS_AUTHONLY) ||
- (ci->i_auth_cap && __ceph_is_single_caps(ci)))
- __cap_delay_cancel(mdsc, ci);
-
goto retry_locked;
retry:
spin_lock(&ci->i_ceph_lock);
@@ -1907,9 +1943,7 @@ retry_locked:
if (IS_RDONLY(inode)) {
want = CEPH_CAP_ANY_SHARED;
} else {
- want = CEPH_CAP_ANY_SHARED |
- CEPH_CAP_FILE_EXCL |
- CEPH_CAP_ANY_DIR_OPS;
+ want |= CEPH_CAP_ANY_SHARED | CEPH_CAP_FILE_EXCL;
}
retain |= want;
} else {
@@ -2105,9 +2139,17 @@ ack:
goto retry; /* retake i_ceph_lock and restart our cap scan. */
}
- /* Reschedule delayed caps release if we delayed anything */
- if (delayed)
- __cap_delay_requeue(mdsc, ci, false);
+ if (list_empty(&ci->i_cap_delay_list)) {
+ if (delayed) {
+ /* Reschedule delayed caps release if we delayed anything */
+ __cap_delay_requeue(mdsc, ci, false);
+ } else if (__ceph_is_any_real_caps(ci) &&
+ (file_wanted & ~CEPH_CAP_PIN) &&
+ !(used & (CEPH_CAP_FILE_RD | CEPH_CAP_ANY_FILE_WR))) {
+ /* periodically re-calculate caps wanted by open files */
+ __cap_delay_requeue(mdsc, ci, true);
+ }
+ }
spin_unlock(&ci->i_ceph_lock);
@@ -2573,8 +2615,9 @@ void ceph_take_cap_refs(struct ceph_inode_info *ci, int got,
* FIXME: how does a 0 return differ from -EAGAIN?
*/
enum {
- NON_BLOCKING = 1,
- CHECK_FILELOCK = 2,
+ /* first 8 bits are reserved for CEPH_FILE_MODE_FOO */
+ NON_BLOCKING = (1 << 8),
+ CHECK_FILELOCK = (1 << 9),
};
static int try_get_cap_refs(struct inode *inode, int need, int want,
@@ -2584,7 +2627,6 @@ static int try_get_cap_refs(struct inode *inode, int need, int want,
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
int ret = 0;
int have, implemented;
- int file_wanted;
bool snap_rwsem_locked = false;
dout("get_cap_refs %p need %s want %s\n", inode,
@@ -2600,15 +2642,6 @@ again:
goto out_unlock;
}
- /* make sure file is actually open */
- file_wanted = __ceph_caps_file_wanted(ci);
- if ((file_wanted & need) != need) {
- dout("try_get_cap_refs need %s file_wanted %s, EBADF\n",
- ceph_cap_string(need), ceph_cap_string(file_wanted));
- ret = -EBADF;
- goto out_unlock;
- }
-
/* finish pending truncate */
while (ci->i_truncate_pending) {
spin_unlock(&ci->i_ceph_lock);
@@ -2719,6 +2752,9 @@ again:
ceph_cap_string(have), ceph_cap_string(need));
}
out_unlock:
+
+ __ceph_touch_fmode(ci, mdsc, flags);
+
spin_unlock(&ci->i_ceph_lock);
if (snap_rwsem_locked)
up_read(&mdsc->snap_rwsem);
@@ -2756,10 +2792,20 @@ static void check_max_size(struct inode *inode, loff_t endoff)
ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
}
+static inline int get_used_fmode(int caps)
+{
+ int fmode = 0;
+ if (caps & CEPH_CAP_FILE_RD)
+ fmode |= CEPH_FILE_MODE_RD;
+ if (caps & CEPH_CAP_FILE_WR)
+ fmode |= CEPH_FILE_MODE_WR;
+ return fmode;
+}
+
int ceph_try_get_caps(struct inode *inode, int need, int want,
bool nonblock, int *got)
{
- int ret;
+ int ret, flags;
BUG_ON(need & ~CEPH_CAP_FILE_RD);
BUG_ON(want & ~(CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO |
@@ -2771,8 +2817,11 @@ int ceph_try_get_caps(struct inode *inode, int need, int want,
return ret;
}
- ret = try_get_cap_refs(inode, need, want, 0,
- (nonblock ? NON_BLOCKING : 0), got);
+ flags = get_used_fmode(need | want);
+ if (nonblock)
+ flags |= NON_BLOCKING;
+
+ ret = try_get_cap_refs(inode, need, want, 0, flags, got);
return ret == -EAGAIN ? 0 : ret;
}
@@ -2798,11 +2847,15 @@ int ceph_get_caps(struct file *filp, int need, int want,
fi->filp_gen != READ_ONCE(fsc->filp_gen))
return -EBADF;
+ flags = get_used_fmode(need | want);
+
while (true) {
if (endoff > 0)
check_max_size(inode, endoff);
- flags = atomic_read(&fi->num_locks) ? CHECK_FILELOCK : 0;
+ flags &= CEPH_FILE_MODE_MASK;
+ if (atomic_read(&fi->num_locks))
+ flags |= CHECK_FILELOCK;
_got = 0;
ret = try_get_cap_refs(inode, need, want, endoff,
flags, &_got);
@@ -2822,6 +2875,8 @@ int ceph_get_caps(struct file *filp, int need, int want,
list_add(&cw.list, &mdsc->cap_wait_list);
spin_unlock(&mdsc->caps_list_lock);
+ /* make sure used fmode not timeout */
+ ceph_get_fmode(ci, flags, FMODE_WAIT_BIAS);
add_wait_queue(&ci->i_cap_wq, &wait);
flags |= NON_BLOCKING;
@@ -2835,6 +2890,7 @@ int ceph_get_caps(struct file *filp, int need, int want,
}
remove_wait_queue(&ci->i_cap_wq, &wait);
+ ceph_put_fmode(ci, flags, FMODE_WAIT_BIAS);
spin_lock(&mdsc->caps_list_lock);
list_del(&cw.list);
@@ -2854,7 +2910,7 @@ int ceph_get_caps(struct file *filp, int need, int want,
if (ret < 0) {
if (ret == -ESTALE) {
/* session was killed, try renew caps */
- ret = ceph_renew_caps(inode);
+ ret = ceph_renew_caps(inode, flags);
if (ret == 0)
continue;
}
@@ -4153,6 +4209,33 @@ void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc)
dout("flush_dirty_caps done\n");
}
+void __ceph_touch_fmode(struct ceph_inode_info *ci,
+ struct ceph_mds_client *mdsc, int fmode)
+{
+ unsigned long now = jiffies;
+ if (fmode & CEPH_FILE_MODE_RD)
+ ci->i_last_rd = now;
+ if (fmode & CEPH_FILE_MODE_WR)
+ ci->i_last_wr = now;
+ /* queue periodic check */
+ if (fmode &&
+ __ceph_is_any_real_caps(ci) &&
+ list_empty(&ci->i_cap_delay_list))
+ __cap_delay_requeue(mdsc, ci, true);
+}
+
+void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count)
+{
+ int i;
+ int bits = (fmode << 1) | 1;
+ spin_lock(&ci->i_ceph_lock);
+ for (i = 0; i < CEPH_FILE_MODE_BITS; i++) {
+ if (bits & (1 << i))
+ ci->i_nr_by_mode[i] += count;
+ }
+ spin_unlock(&ci->i_ceph_lock);
+}
+
void __ceph_get_fmode(struct ceph_inode_info *ci, int fmode)
{
int i;
@@ -4168,26 +4251,18 @@ void __ceph_get_fmode(struct ceph_inode_info *ci, int fmode)
* we may need to release capabilities to the MDS (or schedule
* their delayed release).
*/
-void ceph_put_fmode(struct ceph_inode_info *ci, int fmode)
+void ceph_put_fmode(struct ceph_inode_info *ci, int fmode, int count)
{
- int i, last = 0;
+ int i;
int bits = (fmode << 1) | 1;
spin_lock(&ci->i_ceph_lock);
for (i = 0; i < CEPH_FILE_MODE_BITS; i++) {
if (bits & (1 << i)) {
- BUG_ON(ci->i_nr_by_mode[i] == 0);
- if (--ci->i_nr_by_mode[i] == 0)
- last++;
+ BUG_ON(ci->i_nr_by_mode[i] < count);
+ ci->i_nr_by_mode[i] -= count;
}
}
- dout("put_fmode %p fmode %d {%d,%d,%d,%d}\n",
- &ci->vfs_inode, fmode,
- ci->i_nr_by_mode[0], ci->i_nr_by_mode[1],
- ci->i_nr_by_mode[2], ci->i_nr_by_mode[3]);
spin_unlock(&ci->i_ceph_lock);
-
- if (last && ci->i_vino.snap == CEPH_NOSNAP)
- ceph_check_caps(ci, 0, NULL);
}
/*
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index ee6b319e5481..d594c2627430 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -335,8 +335,11 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
ctx->pos = 2;
}
- /* can we use the dcache? */
spin_lock(&ci->i_ceph_lock);
+ /* request Fx cap. if have Fx, we don't need to release Fs cap
+ * for later create/unlink. */
+ __ceph_touch_fmode(ci, mdsc, CEPH_FILE_MODE_WR);
+ /* can we use the dcache? */
if (ceph_test_mount_opt(fsc, DCACHE) &&
!ceph_test_mount_opt(fsc, NOASYNCREADDIR) &&
ceph_snap(inode) != CEPH_SNAPDIR &&
@@ -760,6 +763,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
ceph_test_mount_opt(fsc, DCACHE) &&
__ceph_dir_is_complete(ci) &&
(__ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1))) {
+ __ceph_touch_fmode(ci, mdsc, CEPH_FILE_MODE_RD);
spin_unlock(&ci->i_ceph_lock);
dout(" dir %p complete, -ENOENT\n", dir);
d_add(dentry, NULL);
@@ -1621,7 +1625,8 @@ static int __dir_lease_try_check(const struct dentry *dentry)
/*
* Check if directory-wide content lease/cap is valid.
*/
-static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry)
+static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry,
+ struct ceph_mds_client *mdsc)
{
struct ceph_inode_info *ci = ceph_inode(dir);
int valid;
@@ -1629,7 +1634,10 @@ static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry)
spin_lock(&ci->i_ceph_lock);
valid = __ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1);
- shared_gen = atomic_read(&ci->i_shared_gen);
+ if (valid) {
+ __ceph_touch_fmode(ci, mdsc, CEPH_FILE_MODE_RD);
+ shared_gen = atomic_read(&ci->i_shared_gen);
+ }
spin_unlock(&ci->i_ceph_lock);
if (valid) {
struct ceph_dentry_info *di;
@@ -1655,6 +1663,7 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
int valid = 0;
struct dentry *parent;
struct inode *dir, *inode;
+ struct ceph_mds_client *mdsc;
if (flags & LOOKUP_RCU) {
parent = READ_ONCE(dentry->d_parent);
@@ -1671,6 +1680,8 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
dout("d_revalidate %p '%pd' inode %p offset 0x%llx\n", dentry,
dentry, inode, ceph_dentry(dentry)->offset);
+ mdsc = ceph_sb_to_client(dir->i_sb)->mdsc;
+
/* always trust cached snapped dentries, snapdir dentry */
if (ceph_snap(dir) != CEPH_NOSNAP) {
dout("d_revalidate %p '%pd' inode %p is SNAPPED\n", dentry,
@@ -1682,7 +1693,7 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
valid = dentry_lease_is_valid(dentry, flags);
if (valid == -ECHILD)
return valid;
- if (valid || dir_lease_is_valid(dir, dentry)) {
+ if (valid || dir_lease_is_valid(dir, dentry, mdsc)) {
if (inode)
valid = ceph_is_any_caps(inode);
else
@@ -1691,8 +1702,6 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
}
if (!valid) {
- struct ceph_mds_client *mdsc =
- ceph_sb_to_client(dir->i_sb)->mdsc;
struct ceph_mds_request *req;
int op, err;
u32 mask;
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index a6c484123d98..6239cff491e2 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -213,7 +213,7 @@ static int ceph_init_file_info(struct inode *inode, struct file *file,
struct ceph_dir_file_info *dfi =
kmem_cache_zalloc(ceph_dir_file_cachep, GFP_KERNEL);
if (!dfi) {
- ceph_put_fmode(ci, fmode); /* clean up */
+ ceph_put_fmode(ci, fmode, 1); /* clean up */
return -ENOMEM;
}
@@ -224,7 +224,7 @@ static int ceph_init_file_info(struct inode *inode, struct file *file,
} else {
fi = kmem_cache_zalloc(ceph_file_cachep, GFP_KERNEL);
if (!fi) {
- ceph_put_fmode(ci, fmode); /* clean up */
+ ceph_put_fmode(ci, fmode, 1); /* clean up */
return -ENOMEM;
}
@@ -263,7 +263,7 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
case S_IFLNK:
dout("init_file %p %p 0%o (symlink)\n", inode, file,
inode->i_mode);
- ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
+ ceph_put_fmode(ceph_inode(inode), fmode, 1); /* clean up */
break;
default:
@@ -273,7 +273,7 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
* we need to drop the open ref now, since we don't
* have .release set to ceph_release.
*/
- ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
+ ceph_put_fmode(ceph_inode(inode), fmode, 1); /* clean up */
BUG_ON(inode->i_fop->release == ceph_release);
/* call the proper open fop */
@@ -285,14 +285,15 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
/*
* try renew caps after session gets killed.
*/
-int ceph_renew_caps(struct inode *inode)
+int ceph_renew_caps(struct inode *inode, int fmode)
{
- struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+ struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_mds_request *req;
int err, flags, wanted;
spin_lock(&ci->i_ceph_lock);
+ __ceph_touch_fmode(ci, mdsc, fmode);
wanted = __ceph_caps_file_wanted(ci);
if (__ceph_is_any_real_caps(ci) &&
(!(wanted & CEPH_CAP_ANY_WR) || ci->i_auth_cap)) {
@@ -405,6 +406,7 @@ int ceph_open(struct inode *inode, struct file *file)
} else if (ceph_snap(inode) != CEPH_NOSNAP &&
(ci->i_snap_caps & wanted) == wanted) {
__ceph_get_fmode(ci, fmode);
+ __ceph_touch_fmode(ci, mdsc, fmode);
spin_unlock(&ci->i_ceph_lock);
return ceph_init_file(inode, file, fmode);
}
@@ -781,7 +783,7 @@ retry:
}
out_req:
if (!req->r_err && req->r_target_inode)
- ceph_put_fmode(ceph_inode(req->r_target_inode), req->r_fmode);
+ ceph_put_fmode(ceph_inode(req->r_target_inode), req->r_fmode, 1);
ceph_mdsc_put_request(req);
out_ctx:
ceph_release_acl_sec_ctx(&as_ctx);
@@ -798,7 +800,7 @@ int ceph_release(struct inode *inode, struct file *file)
dout("release inode %p dir file %p\n", inode, file);
WARN_ON(!list_empty(&dfi->file_info.rw_contexts));
- ceph_put_fmode(ci, dfi->file_info.fmode);
+ ceph_put_fmode(ci, dfi->file_info.fmode, 1);
if (dfi->last_readdir)
ceph_mdsc_put_request(dfi->last_readdir);
@@ -810,7 +812,8 @@ int ceph_release(struct inode *inode, struct file *file)
dout("release inode %p regular file %p\n", inode, file);
WARN_ON(!list_empty(&fi->rw_contexts));
- ceph_put_fmode(ci, fi->fmode);
+ ceph_put_fmode(ci, fi->fmode, 1);
+
kmem_cache_free(ceph_file_cachep, fi);
}
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 73f986efb1fd..a618e8ae9d0f 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -479,6 +479,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
ci->i_head_snapc = NULL;
ci->i_snap_caps = 0;
+ ci->i_last_rd = ci->i_last_wr = jiffies - 3600 * HZ;
for (i = 0; i < CEPH_FILE_MODE_BITS; i++)
ci->i_nr_by_mode[i] = 0;
@@ -639,7 +640,7 @@ int ceph_fill_file_size(struct inode *inode, int issued,
if ((issued & (CEPH_CAP_FILE_CACHE|
CEPH_CAP_FILE_BUFFER)) ||
mapping_mapped(inode->i_mapping) ||
- __ceph_caps_file_wanted(ci)) {
+ __ceph_is_file_opened(ci)) {
ci->i_truncate_pending++;
queue_trunc = 1;
}
@@ -1013,6 +1014,13 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
fill_inline = true;
}
+ if (cap_fmode >= 0) {
+ if (!info_caps)
+ pr_warn("mds issued no caps on %llx.%llx\n",
+ ceph_vinop(inode));
+ __ceph_touch_fmode(ci, mdsc, cap_fmode);
+ }
+
spin_unlock(&ci->i_ceph_lock);
if (fill_inline)
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index c90f03beb15d..6e061bf62ad4 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -243,11 +243,13 @@ static long ceph_ioctl_lazyio(struct file *file)
struct ceph_file_info *fi = file->private_data;
struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
+ struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
if ((fi->fmode & CEPH_FILE_MODE_LAZY) == 0) {
spin_lock(&ci->i_ceph_lock);
fi->fmode |= CEPH_FILE_MODE_LAZY;
ci->i_nr_by_mode[ffs(CEPH_FILE_MODE_LAZY)]++;
+ __ceph_touch_fmode(ci, mdsc, fi->fmode);
spin_unlock(&ci->i_ceph_lock);
dout("ioctl_layzio: file %p marked lazy\n", file);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 68b8afded466..486f91f9685b 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2486,7 +2486,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
if (req->r_inode_drop)
releases += ceph_encode_inode_release(&p,
req->r_inode ? req->r_inode : d_inode(req->r_dentry),
- mds, req->r_inode_drop, req->r_inode_unless, 0);
+ mds, req->r_inode_drop, req->r_inode_unless,
+ req->r_op == CEPH_MDS_OP_READDIR);
if (req->r_dentry_drop)
releases += ceph_encode_dentry_release(&p, req->r_dentry,
req->r_parent, mds, req->r_dentry_drop,
@@ -2833,7 +2834,13 @@ int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, struct inode *dir,
if (req->r_inode)
ceph_get_cap_refs(ceph_inode(req->r_inode), CEPH_CAP_PIN);
if (req->r_parent) {
- ceph_get_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN);
+ struct ceph_inode_info *ci = ceph_inode(req->r_parent);
+ int fmode = (req->r_op & CEPH_MDS_OP_WRITE) ?
+ CEPH_FILE_MODE_WR : CEPH_FILE_MODE_RD;
+ spin_lock(&ci->i_ceph_lock);
+ ceph_take_cap_refs(ci, CEPH_CAP_PIN, false);
+ __ceph_touch_fmode(ci, mdsc, fmode);
+ spin_unlock(&ci->i_ceph_lock);
ihold(req->r_parent);
}
if (req->r_old_dentry_dir)
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 356ad7b46b85..63dd8e61ba88 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -366,6 +366,8 @@ struct ceph_inode_info {
dirty|flushing caps */
unsigned i_snap_caps; /* cap bits for snapped files */
+ unsigned long i_last_rd;
+ unsigned long i_last_wr;
int i_nr_by_mode[CEPH_FILE_MODE_BITS]; /* open file counts */
struct mutex i_truncate_mutex;
@@ -680,6 +682,10 @@ extern int __ceph_caps_revoking_other(struct ceph_inode_info *ci,
extern int ceph_caps_revoking(struct ceph_inode_info *ci, int mask);
extern int __ceph_caps_used(struct ceph_inode_info *ci);
+static inline bool __ceph_is_file_opened(struct ceph_inode_info *ci)
+{
+ return ci->i_nr_by_mode[0];
+}
extern int __ceph_caps_file_wanted(struct ceph_inode_info *ci);
extern int __ceph_caps_wanted(struct ceph_inode_info *ci);
@@ -1093,7 +1099,10 @@ extern int ceph_try_get_caps(struct inode *inode,
/* for counting open files by mode */
extern void __ceph_get_fmode(struct ceph_inode_info *ci, int mode);
-extern void ceph_put_fmode(struct ceph_inode_info *ci, int mode);
+extern void ceph_get_fmode(struct ceph_inode_info *ci, int mode, int count);
+extern void ceph_put_fmode(struct ceph_inode_info *ci, int mode, int count);
+extern void __ceph_touch_fmode(struct ceph_inode_info *ci,
+ struct ceph_mds_client *mdsc, int fmode);
/* addr.c */
extern const struct address_space_operations ceph_aops;
@@ -1105,7 +1114,7 @@ extern void ceph_pool_perm_destroy(struct ceph_mds_client* mdsc);
/* file.c */
extern const struct file_operations ceph_file_fops;
-extern int ceph_renew_caps(struct inode *inode);
+extern int ceph_renew_caps(struct inode *inode, int fmode);
extern int ceph_open(struct inode *inode, struct file *file);
extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
struct file *file, unsigned flags, umode_t mode);
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index e035c5194005..ebf5ba62b772 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -568,6 +568,7 @@ struct ceph_filelock {
#define CEPH_FILE_MODE_RDWR 3 /* RD | WR */
#define CEPH_FILE_MODE_LAZY 4 /* lazy io */
#define CEPH_FILE_MODE_BITS 4
+#define CEPH_FILE_MODE_MASK ((1 << CEPH_FILE_MODE_BITS) - 1)
int ceph_flags_to_mode(int flags);
--
cgit v1.2.3
From a0d93e327fc424b94e78a1b25287bb4e632ee054 Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zyan@redhat.com>
Date: Thu, 5 Mar 2020 20:21:01 +0800
Subject: ceph: remove delay check logic from ceph_check_caps()
__ceph_caps_file_wanted() already checks 'caps_wanted_delay_min' and
'caps_wanted_delay_max'. There is no need to duplicate the logic in
ceph_check_caps() and __send_cap()
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
fs/ceph/caps.c | 148 ++++++++++++++------------------------------------------
fs/ceph/file.c | 13 ++---
fs/ceph/inode.c | 1 -
fs/ceph/super.h | 8 ++-
4 files changed, 44 insertions(+), 126 deletions(-)
(limited to 'fs/ceph/inode.c')
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index aa5bb5a4de46..fe0f724d27e9 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -490,13 +490,10 @@ static void __cap_set_timeouts(struct ceph_mds_client *mdsc,
struct ceph_inode_info *ci)
{
struct ceph_mount_options *opt = mdsc->fsc->mount_options;
-
- ci->i_hold_caps_min = round_jiffies(jiffies +
- opt->caps_wanted_delay_min * HZ);
ci->i_hold_caps_max = round_jiffies(jiffies +
opt->caps_wanted_delay_max * HZ);
- dout("__cap_set_timeouts %p min %lu max %lu\n", &ci->vfs_inode,
- ci->i_hold_caps_min - jiffies, ci->i_hold_caps_max - jiffies);
+ dout("__cap_set_timeouts %p %lu\n", &ci->vfs_inode,
+ ci->i_hold_caps_max - jiffies);
}
/*
@@ -508,8 +505,7 @@ static void __cap_set_timeouts(struct ceph_mds_client *mdsc,
* -> we take mdsc->cap_delay_lock
*/
static void __cap_delay_requeue(struct ceph_mds_client *mdsc,
- struct ceph_inode_info *ci,
- bool set_timeout)
+ struct ceph_inode_info *ci)
{
dout("__cap_delay_requeue %p flags 0x%lx at %lu\n", &ci->vfs_inode,
ci->i_ceph_flags, ci->i_hold_caps_max);
@@ -520,8 +516,7 @@ static void __cap_delay_requeue(struct ceph_mds_client *mdsc,
goto no_change;
list_del_init(&ci->i_cap_delay_list);
}
- if (set_timeout)
- __cap_set_timeouts(mdsc, ci);
+ __cap_set_timeouts(mdsc, ci);
list_add_tail(&ci->i_cap_delay_list, &mdsc->cap_delay_list);
no_change:
spin_unlock(&mdsc->cap_delay_lock);
@@ -733,7 +728,7 @@ void ceph_add_cap(struct inode *inode,
dout(" issued %s, mds wanted %s, actual %s, queueing\n",
ceph_cap_string(issued), ceph_cap_string(wanted),
ceph_cap_string(actual_wanted));
- __cap_delay_requeue(mdsc, ci, true);
+ __cap_delay_requeue(mdsc, ci);
}
if (flags & CEPH_CAP_FLAG_AUTH) {
@@ -1342,7 +1337,6 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
struct cap_msg_args arg;
int held, revoking;
int wake = 0;
- int delayed = 0;
int ret;
/* Don't send anything if it's still being created. Return delayed */
@@ -1362,28 +1356,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
ceph_cap_string(revoking));
BUG_ON((retain & CEPH_CAP_PIN) == 0);
- arg.session = cap->session;
-
- /* don't release wanted unless we've waited a bit. */
- if ((ci->i_ceph_flags & CEPH_I_NODELAY) == 0 &&
- time_before(jiffies, ci->i_hold_caps_min)) {
- dout(" delaying issued %s -> %s, wanted %s -> %s on send\n",
- ceph_cap_string(cap->issued),
- ceph_cap_string(cap->issued & retain),
- ceph_cap_string(cap->mds_wanted),
- ceph_cap_string(want));
- want |= cap->mds_wanted;
- retain |= cap->issued;
- delayed = 1;
- }
- ci->i_ceph_flags &= ~(CEPH_I_NODELAY | CEPH_I_FLUSH);
- if (want & ~cap->mds_wanted) {
- /* user space may open/close single file frequently.
- * This avoids droping mds_wanted immediately after
- * requesting new mds_wanted.
- */
- __cap_set_timeouts(mdsc, ci);
- }
+ ci->i_ceph_flags &= ~CEPH_I_FLUSH;
cap->issued &= retain; /* drop bits we don't want */
if (cap->implemented & ~cap->issued) {
@@ -1398,6 +1371,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
cap->implemented &= cap->issued | used;
cap->mds_wanted = want;
+ arg.session = cap->session;
arg.ino = ceph_vino(inode).ino;
arg.cid = cap->cap_id;
arg.follows = flushing ? ci->i_head_snapc->seq : 0;
@@ -1458,14 +1432,19 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
ret = send_cap_msg(&arg);
if (ret < 0) {
- dout("error sending cap msg, must requeue %p\n", inode);
- delayed = 1;
+ pr_err("error sending cap msg, ino (%llx.%llx) "
+ "flushing %s tid %llu, requeue\n",
+ ceph_vinop(inode), ceph_cap_string(flushing),
+ flush_tid);
+ spin_lock(&ci->i_ceph_lock);
+ __cap_delay_requeue(mdsc, ci);
+ spin_unlock(&ci->i_ceph_lock);
}
if (wake)
wake_up_all(&ci->i_cap_wq);
- return delayed;
+ return ret;
}
static inline int __send_flush_snap(struct inode *inode,
@@ -1731,7 +1710,7 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
if (((was | ci->i_flushing_caps) & CEPH_CAP_FILE_BUFFER) &&
(mask & CEPH_CAP_FILE_BUFFER))
dirty |= I_DIRTY_DATASYNC;
- __cap_delay_requeue(mdsc, ci, true);
+ __cap_delay_requeue(mdsc, ci);
return dirty;
}
@@ -1883,8 +1862,6 @@ bool __ceph_should_report_size(struct ceph_inode_info *ci)
* versus held caps. Release, flush, ack revoked caps to mds as
* appropriate.
*
- * CHECK_CAPS_NODELAY - caller is delayed work and we should not delay
- * cap release further.
* CHECK_CAPS_AUTHONLY - we should only check the auth cap
* CHECK_CAPS_FLUSH - we should flush any dirty caps immediately, without
* further delay.
@@ -1903,17 +1880,10 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
int mds = -1; /* keep track of how far we've gone through i_caps list
to avoid an infinite loop on retry */
struct rb_node *p;
- int delayed = 0, sent = 0;
- bool no_delay = flags & CHECK_CAPS_NODELAY;
bool queue_invalidate = false;
bool tried_invalidate = false;
- /* if we are unmounting, flush any unused caps immediately. */
- if (mdsc->stopping)
- no_delay = true;
-
spin_lock(&ci->i_ceph_lock);
-
if (ci->i_ceph_flags & CEPH_I_FLUSH)
flags |= CHECK_CAPS_FLUSH;
@@ -1960,14 +1930,13 @@ retry_locked:
}
dout("check_caps %p file_want %s used %s dirty %s flushing %s"
- " issued %s revoking %s retain %s %s%s%s\n", inode,
+ " issued %s revoking %s retain %s %s%s\n", inode,
ceph_cap_string(file_wanted),
ceph_cap_string(used), ceph_cap_string(ci->i_dirty_caps),
ceph_cap_string(ci->i_flushing_caps),
ceph_cap_string(issued), ceph_cap_string(revoking),
ceph_cap_string(retain),
(flags & CHECK_CAPS_AUTHONLY) ? " AUTHONLY" : "",
- (flags & CHECK_CAPS_NODELAY) ? " NODELAY" : "",
(flags & CHECK_CAPS_FLUSH) ? " FLUSH" : "");
/*
@@ -1975,7 +1944,7 @@ retry_locked:
* have cached pages, but don't want them, then try to invalidate.
* If we fail, it's because pages are locked.... try again later.
*/
- if ((!no_delay || mdsc->stopping) &&
+ if ((!(flags & CHECK_CAPS_NOINVAL) || mdsc->stopping) &&
S_ISREG(inode->i_mode) &&
!(ci->i_wb_ref || ci->i_wrbuffer_ref) && /* no dirty pages... */
inode->i_data.nrpages && /* have cached pages */
@@ -2055,21 +2024,6 @@ retry_locked:
if ((cap->issued & ~retain) == 0)
continue; /* nope, all good */
- if (no_delay)
- goto ack;
-
- /* delay? */
- if ((ci->i_ceph_flags & CEPH_I_NODELAY) == 0 &&
- time_before(jiffies, ci->i_hold_caps_max)) {
- dout(" delaying issued %s -> %s, wanted %s -> %s\n",
- ceph_cap_string(cap->issued),
- ceph_cap_string(cap->issued & retain),
- ceph_cap_string(cap->mds_wanted),
- ceph_cap_string(want));
- delayed++;
- continue;
- }
-
ack:
if (session && session != cap->session) {
dout("oops, wrong session %p mutex\n", session);
@@ -2130,25 +2084,19 @@ ack:
}
mds = cap->mds; /* remember mds, so we don't repeat */
- sent++;
/* __send_cap drops i_ceph_lock */
- delayed += __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, 0,
- cap_used, want, retain, flushing,
- flush_tid, oldest_flush_tid);
+ __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, 0, cap_used, want,
+ retain, flushing, flush_tid, oldest_flush_tid);
goto retry; /* retake i_ceph_lock and restart our cap scan. */
}
- if (list_empty(&ci->i_cap_delay_list)) {
- if (delayed) {
- /* Reschedule delayed caps release if we delayed anything */
- __cap_delay_requeue(mdsc, ci, false);
- } else if (__ceph_is_any_real_caps(ci) &&
- (file_wanted & ~CEPH_CAP_PIN) &&
- !(used & (CEPH_CAP_FILE_RD | CEPH_CAP_ANY_FILE_WR))) {
- /* periodically re-calculate caps wanted by open files */
- __cap_delay_requeue(mdsc, ci, true);
- }
+ /* periodically re-calculate caps wanted by open files */
+ if (__ceph_is_any_real_caps(ci) &&
+ list_empty(&ci->i_cap_delay_list) &&
+ (file_wanted & ~CEPH_CAP_PIN) &&
+ !(used & (CEPH_CAP_FILE_RD | CEPH_CAP_ANY_FILE_WR))) {
+ __cap_delay_requeue(mdsc, ci);
}
spin_unlock(&ci->i_ceph_lock);
@@ -2178,7 +2126,6 @@ retry:
retry_locked:
if (ci->i_dirty_caps && ci->i_auth_cap) {
struct ceph_cap *cap = ci->i_auth_cap;
- int delayed;
if (session != cap->session) {
spin_unlock(&ci->i_ceph_lock);
@@ -2207,18 +2154,10 @@ retry_locked:
&oldest_flush_tid);
/* __send_cap drops i_ceph_lock */
- delayed = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH,
- CEPH_CLIENT_CAPS_SYNC,
- __ceph_caps_used(ci),
- __ceph_caps_wanted(ci),
- (cap->issued | cap->implemented),
- flushing, flush_tid, oldest_flush_tid);
-
- if (delayed) {
- spin_lock(&ci->i_ceph_lock);
- __cap_delay_requeue(mdsc, ci, true);
- spin_unlock(&ci->i_ceph_lock);
- }
+ __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH, CEPH_CLIENT_CAPS_SYNC,
+ __ceph_caps_used(ci), __ceph_caps_wanted(ci),
+ (cap->issued | cap->implemented),
+ flushing, flush_tid, oldest_flush_tid);
} else {
if (!list_empty(&ci->i_cap_flush_list)) {
struct ceph_cap_flush *cf =
@@ -2422,22 +2361,13 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
if (cf->caps) {
dout("kick_flushing_caps %p cap %p tid %llu %s\n",
inode, cap, cf->tid, ceph_cap_string(cf->caps));
- ci->i_ceph_flags |= CEPH_I_NODELAY;
-
- ret = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH,
+ __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH,
(cf->tid < last_snap_flush ?
CEPH_CLIENT_CAPS_PENDING_CAPSNAP : 0),
__ceph_caps_used(ci),
__ceph_caps_wanted(ci),
(cap->issued | cap->implemented),
cf->caps, cf->tid, oldest_flush_tid);
- if (ret) {
- pr_err("kick_flushing_caps: error sending "
- "cap flush, ino (%llx.%llx) "
- "tid %llu flushing %s\n",
- ceph_vinop(inode), cf->tid,
- ceph_cap_string(cf->caps));
- }
} else {
struct ceph_cap_snap *capsnap =
container_of(cf, struct ceph_cap_snap,
@@ -3059,7 +2989,7 @@ void ceph_put_cap_refs(struct ceph_inode_info *ci, int had)
dout("put_cap_refs %p had %s%s%s\n", inode, ceph_cap_string(had),
last ? " last" : "", put ? " put" : "");
- if (last && !flushsnaps)
+ if (last)
ceph_check_caps(ci, 0, NULL);
else if (flushsnaps)
ceph_flush_snaps(ci, NULL);
@@ -3478,10 +3408,10 @@ static void handle_cap_grant(struct inode *inode,
wake_up_all(&ci->i_cap_wq);
if (check_caps == 1)
- ceph_check_caps(ci, CHECK_CAPS_NODELAY|CHECK_CAPS_AUTHONLY,
+ ceph_check_caps(ci, CHECK_CAPS_AUTHONLY | CHECK_CAPS_NOINVAL,
session);
else if (check_caps == 2)
- ceph_check_caps(ci, CHECK_CAPS_NODELAY, session);
+ ceph_check_caps(ci, CHECK_CAPS_NOINVAL, session);
else
mutex_unlock(&session->s_mutex);
}
@@ -4156,7 +4086,6 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
{
struct inode *inode;
struct ceph_inode_info *ci;
- int flags = CHECK_CAPS_NODELAY;
dout("check_delayed_caps\n");
while (1) {
@@ -4176,7 +4105,7 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
if (inode) {
dout("check_delayed_caps on %p\n", inode);
- ceph_check_caps(ci, flags, NULL);
+ ceph_check_caps(ci, 0, NULL);
/* avoid calling iput_final() in tick thread */
ceph_async_iput(inode);
}
@@ -4201,7 +4130,7 @@ void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc)
ihold(inode);
dout("flush_dirty_caps %p\n", inode);
spin_unlock(&mdsc->cap_dirty_lock);
- ceph_check_caps(ci, CHECK_CAPS_NODELAY|CHECK_CAPS_FLUSH, NULL);
+ ceph_check_caps(ci, CHECK_CAPS_FLUSH, NULL);
iput(inode);
spin_lock(&mdsc->cap_dirty_lock);
}
@@ -4221,7 +4150,7 @@ void __ceph_touch_fmode(struct ceph_inode_info *ci,
if (fmode &&
__ceph_is_any_real_caps(ci) &&
list_empty(&ci->i_cap_delay_list))
- __cap_delay_requeue(mdsc, ci, true);
+ __cap_delay_requeue(mdsc, ci);
}
void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count)
@@ -4280,7 +4209,6 @@ int ceph_drop_caps_for_unlink(struct inode *inode)
if (inode->i_nlink == 1) {
drop |= ~(__ceph_caps_wanted(ci) | CEPH_CAP_PIN);
- ci->i_ceph_flags |= CEPH_I_NODELAY;
if (__ceph_caps_dirty(ci)) {
struct ceph_mds_client *mdsc =
ceph_inode_to_client(inode)->mdsc;
@@ -4336,8 +4264,6 @@ int ceph_encode_inode_release(void **p, struct inode *inode,
if (force || (cap->issued & drop)) {
if (cap->issued & drop) {
int wanted = __ceph_caps_wanted(ci);
- if ((ci->i_ceph_flags & CEPH_I_NODELAY) == 0)
- wanted |= cap->mds_wanted;
dout("encode_inode_release %p cap %p "
"%s -> %s, wanted %s -> %s\n", inode, cap,
ceph_cap_string(cap->issued),
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 6239cff491e2..39b364a51c17 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1826,7 +1826,7 @@ retry_snap:
if (dirty)
__mark_inode_dirty(inode, dirty);
if (ceph_quota_is_max_bytes_approaching(inode, iocb->ki_pos))
- ceph_check_caps(ci, CHECK_CAPS_NODELAY, NULL);
+ ceph_check_caps(ci, 0, NULL);
}
dout("aio_write %p %llx.%llx %llu~%u dropping cap refs on %s\n",
@@ -2427,15 +2427,10 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
inode_inc_iversion_raw(dst_inode);
if (dst_off > size) {
- int caps_flags = 0;
-
/* Let the MDS know about dst file size change */
- if (ceph_quota_is_max_bytes_approaching(dst_inode, dst_off))
- caps_flags |= CHECK_CAPS_NODELAY;
- if (ceph_inode_set_size(dst_inode, dst_off))
- caps_flags |= CHECK_CAPS_AUTHONLY;
- if (caps_flags)
- ceph_check_caps(dst_ci, caps_flags, NULL);
+ if (ceph_inode_set_size(dst_inode, dst_off) ||
+ ceph_quota_is_max_bytes_approaching(dst_inode, dst_off))
+ ceph_check_caps(dst_ci, CHECK_CAPS_AUTHONLY, NULL);
}
/* Mark Fw dirty */
spin_lock(&dst_ci->i_ceph_lock);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index a618e8ae9d0f..c4dd534aaec3 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -472,7 +472,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
ci->i_prealloc_cap_flush = NULL;
INIT_LIST_HEAD(&ci->i_cap_flush_list);
init_waitqueue_head(&ci->i_cap_wq);
- ci->i_hold_caps_min = 0;
ci->i_hold_caps_max = 0;
INIT_LIST_HEAD(&ci->i_cap_delay_list);
INIT_LIST_HEAD(&ci->i_cap_snaps);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 63dd8e61ba88..edceedfee00a 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -173,9 +173,9 @@ struct ceph_cap {
struct list_head caps_item;
};
-#define CHECK_CAPS_NODELAY 1 /* do not delay any further */
-#define CHECK_CAPS_AUTHONLY 2 /* only check auth cap */
-#define CHECK_CAPS_FLUSH 4 /* flush any dirty caps */
+#define CHECK_CAPS_AUTHONLY 1 /* only check auth cap */
+#define CHECK_CAPS_FLUSH 2 /* flush any dirty caps */
+#define CHECK_CAPS_NOINVAL 4 /* don't invalidate pagecache */
struct ceph_cap_flush {
u64 tid;
@@ -357,7 +357,6 @@ struct ceph_inode_info {
struct ceph_cap_flush *i_prealloc_cap_flush;
struct list_head i_cap_flush_list;
wait_queue_head_t i_cap_wq; /* threads waiting on a capability */
- unsigned long i_hold_caps_min; /* jiffies */
unsigned long i_hold_caps_max; /* jiffies */
struct list_head i_cap_delay_list; /* for delayed cap release to mds */
struct ceph_cap_reservation i_cap_migration_resv;
@@ -518,7 +517,6 @@ static inline struct inode *ceph_find_inode(struct super_block *sb,
* Ceph inode.
*/
#define CEPH_I_DIR_ORDERED (1 << 0) /* dentries in dir are ordered */
-#define CEPH_I_NODELAY (1 << 1) /* do not delay cap release */
#define CEPH_I_FLUSH (1 << 2) /* do not delay flush of dirty metadata */
#define CEPH_I_POOL_PERM (1 << 3) /* pool rd/wr bits are valid */
#define CEPH_I_POOL_RD (1 << 4) /* can read from pool */
--
cgit v1.2.3
From 135e671e54fcb46cb4f8b7be9673d3ea7b8ac315 Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zyan@redhat.com>
Date: Thu, 5 Mar 2020 20:21:02 +0800
Subject: ceph: simplify calling of ceph_get_fmode()
Originally, calling ceph_get_fmode() for open files is by thread that
handles request reply. There is a small window between updating caps and
and waking the request initiator. We need to prevent ceph_check_caps()
from releasing wanted caps in the window.
Previous patches made fill_inode() call __ceph_touch_fmode() for open file
requests. This prevented ceph_check_caps() from releasing wanted caps for
'caps_wanted_delay_min' seconds, enough for request initiator to get
woken up and call ceph_get_fmode().
This allows us to now call ceph_get_fmode() in ceph_open() instead.
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
fs/ceph/caps.c | 26 +++-----------------------
fs/ceph/file.c | 21 +++++----------------
fs/ceph/inode.c | 8 +-------
fs/ceph/super.h | 3 +--
4 files changed, 10 insertions(+), 48 deletions(-)
(limited to 'fs/ceph/inode.c')
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index fe0f724d27e9..02dd2a9bd252 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -608,7 +608,7 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
*/
void ceph_add_cap(struct inode *inode,
struct ceph_mds_session *session, u64 cap_id,
- int fmode, unsigned issued, unsigned wanted,
+ unsigned issued, unsigned wanted,
unsigned seq, unsigned mseq, u64 realmino, int flags,
struct ceph_cap **new_cap)
{
@@ -624,13 +624,6 @@ void ceph_add_cap(struct inode *inode,
dout("add_cap %p mds%d cap %llx %s seq %d\n", inode,
session->s_mds, cap_id, ceph_cap_string(issued), seq);
- /*
- * If we are opening the file, include file mode wanted bits
- * in wanted.
- */
- if (fmode >= 0)
- wanted |= ceph_caps_for_mode(fmode);
-
spin_lock(&session->s_gen_ttl_lock);
gen = session->s_cap_gen;
spin_unlock(&session->s_gen_ttl_lock);
@@ -755,9 +748,6 @@ void ceph_add_cap(struct inode *inode,
cap->issue_seq = seq;
cap->mseq = mseq;
cap->cap_gen = gen;
-
- if (fmode >= 0)
- __ceph_get_fmode(ci, fmode);
}
/*
@@ -3707,7 +3697,7 @@ retry:
/* add placeholder for the export tagert */
int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0;
tcap = new_cap;
- ceph_add_cap(inode, tsession, t_cap_id, -1, issued, 0,
+ ceph_add_cap(inode, tsession, t_cap_id, issued, 0,
t_seq - 1, t_mseq, (u64)-1, flag, &new_cap);
if (!list_empty(&ci->i_cap_flush_list) &&
@@ -3812,7 +3802,7 @@ retry:
__ceph_caps_issued(ci, &issued);
issued |= __ceph_caps_dirty(ci);
- ceph_add_cap(inode, session, cap_id, -1, caps, wanted, seq, mseq,
+ ceph_add_cap(inode, session, cap_id, caps, wanted, seq, mseq,
realmino, CEPH_CAP_FLAG_AUTH, &new_cap);
ocap = peer >= 0 ? __get_cap_for_mds(ci, peer) : NULL;
@@ -4165,16 +4155,6 @@ void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count)
spin_unlock(&ci->i_ceph_lock);
}
-void __ceph_get_fmode(struct ceph_inode_info *ci, int fmode)
-{
- int i;
- int bits = (fmode << 1) | 1;
- for (i = 0; i < CEPH_FILE_MODE_BITS; i++) {
- if (bits & (1 << i))
- ci->i_nr_by_mode[i]++;
- }
-}
-
/*
* Drop open file reference. If we were the last open file,
* we may need to release capabilities to the MDS (or schedule
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 39b364a51c17..4a5ccbb7e808 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -212,10 +212,8 @@ static int ceph_init_file_info(struct inode *inode, struct file *file,
if (isdir) {
struct ceph_dir_file_info *dfi =
kmem_cache_zalloc(ceph_dir_file_cachep, GFP_KERNEL);
- if (!dfi) {
- ceph_put_fmode(ci, fmode, 1); /* clean up */
+ if (!dfi)
return -ENOMEM;
- }
file->private_data = dfi;
fi = &dfi->file_info;
@@ -223,15 +221,15 @@ static int ceph_init_file_info(struct inode *inode, struct file *file,
dfi->readdir_cache_idx = -1;
} else {
fi = kmem_cache_zalloc(ceph_file_cachep, GFP_KERNEL);
- if (!fi) {
- ceph_put_fmode(ci, fmode, 1); /* clean up */
+ if (!fi)
return -ENOMEM;
- }
file->private_data = fi;
}
+ ceph_get_fmode(ci, fmode, 1);
fi->fmode = fmode;
+
spin_lock_init(&fi->rw_contexts_lock);
INIT_LIST_HEAD(&fi->rw_contexts);
fi->meta_err = errseq_sample(&ci->i_meta_err);
@@ -263,7 +261,6 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
case S_IFLNK:
dout("init_file %p %p 0%o (symlink)\n", inode, file,
inode->i_mode);
- ceph_put_fmode(ceph_inode(inode), fmode, 1); /* clean up */
break;
default:
@@ -273,7 +270,6 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
* we need to drop the open ref now, since we don't
* have .release set to ceph_release.
*/
- ceph_put_fmode(ceph_inode(inode), fmode, 1); /* clean up */
BUG_ON(inode->i_fop->release == ceph_release);
/* call the proper open fop */
@@ -327,7 +323,6 @@ int ceph_renew_caps(struct inode *inode, int fmode)
req->r_inode = inode;
ihold(inode);
req->r_num_caps = 1;
- req->r_fmode = -1;
err = ceph_mdsc_do_request(mdsc, NULL, req);
ceph_mdsc_put_request(req);
@@ -373,9 +368,6 @@ int ceph_open(struct inode *inode, struct file *file)
/* trivially open snapdir */
if (ceph_snap(inode) == CEPH_SNAPDIR) {
- spin_lock(&ci->i_ceph_lock);
- __ceph_get_fmode(ci, fmode);
- spin_unlock(&ci->i_ceph_lock);
return ceph_init_file(inode, file, fmode);
}
@@ -393,7 +385,7 @@ int ceph_open(struct inode *inode, struct file *file)
dout("open %p fmode %d want %s issued %s using existing\n",
inode, fmode, ceph_cap_string(wanted),
ceph_cap_string(issued));
- __ceph_get_fmode(ci, fmode);
+ __ceph_touch_fmode(ci, mdsc, fmode);
spin_unlock(&ci->i_ceph_lock);
/* adjust wanted? */
@@ -405,7 +397,6 @@ int ceph_open(struct inode *inode, struct file *file)
return ceph_init_file(inode, file, fmode);
} else if (ceph_snap(inode) != CEPH_NOSNAP &&
(ci->i_snap_caps & wanted) == wanted) {
- __ceph_get_fmode(ci, fmode);
__ceph_touch_fmode(ci, mdsc, fmode);
spin_unlock(&ci->i_ceph_lock);
return ceph_init_file(inode, file, fmode);
@@ -782,8 +773,6 @@ retry:
err = finish_open(file, dentry, ceph_open);
}
out_req:
- if (!req->r_err && req->r_target_inode)
- ceph_put_fmode(ceph_inode(req->r_target_inode), req->r_fmode, 1);
ceph_mdsc_put_request(req);
out_ctx:
ceph_release_acl_sec_ctx(&as_ctx);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index c4dd534aaec3..c7ff9f7067f6 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -970,7 +970,7 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
if (ceph_snap(inode) == CEPH_NOSNAP) {
ceph_add_cap(inode, session,
le64_to_cpu(info->cap.cap_id),
- cap_fmode, info_caps,
+ info_caps,
le32_to_cpu(info->cap.wanted),
le32_to_cpu(info->cap.seq),
le32_to_cpu(info->cap.mseq),
@@ -995,13 +995,7 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
dout(" %p got snap_caps %s\n", inode,
ceph_cap_string(info_caps));
ci->i_snap_caps |= info_caps;
- if (cap_fmode >= 0)
- __ceph_get_fmode(ci, cap_fmode);
}
- } else if (cap_fmode >= 0) {
- pr_warn("mds issued no caps on %llx.%llx\n",
- ceph_vinop(inode));
- __ceph_get_fmode(ci, cap_fmode);
}
if (iinfo->inline_version > 0 &&
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index edceedfee00a..60aac3aee055 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -1050,7 +1050,7 @@ extern struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc,
struct ceph_cap_reservation *ctx);
extern void ceph_add_cap(struct inode *inode,
struct ceph_mds_session *session, u64 cap_id,
- int fmode, unsigned issued, unsigned wanted,
+ unsigned issued, unsigned wanted,
unsigned cap, unsigned seq, u64 realmino, int flags,
struct ceph_cap **new_cap);
extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release);
@@ -1096,7 +1096,6 @@ extern int ceph_try_get_caps(struct inode *inode,
int need, int want, bool nonblock, int *got);
/* for counting open files by mode */
-extern void __ceph_get_fmode(struct ceph_inode_info *ci, int mode);
extern void ceph_get_fmode(struct ceph_inode_info *ci, int mode, int count);
extern void ceph_put_fmode(struct ceph_inode_info *ci, int mode, int count);
extern void __ceph_touch_fmode(struct ceph_inode_info *ci,
--
cgit v1.2.3
From bf73c62e7ff8dc220f3f57df4e42f9947320c447 Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zyan@redhat.com>
Date: Thu, 5 Mar 2020 20:21:04 +0800
Subject: ceph: check all mds' caps after page writeback
If an inode has caps from multiple mds's, the following can happen:
- non-auth mds revokes Fsc. Fcb is used, so page writeback is queued.
- when writeback finishes, ceph_check_caps() is called with auth only
flag. ceph_check_caps() invalidates pagecache, but skips checking any
non-auth caps.
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
fs/ceph/caps.c | 2 +-
fs/ceph/inode.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
(limited to 'fs/ceph/inode.c')
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 0b3a36310033..342a32c74c64 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -3062,7 +3062,7 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
spin_unlock(&ci->i_ceph_lock);
if (last) {
- ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
+ ceph_check_caps(ci, 0, NULL);
} else if (flush_snaps) {
ceph_flush_snaps(ci, NULL);
}
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index c7ff9f7067f6..ee40ba7e0e77 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1984,7 +1984,7 @@ retry:
mutex_unlock(&ci->i_truncate_mutex);
if (wrbuffer_refs == 0)
- ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
+ ceph_check_caps(ci, 0, NULL);
wake_up_all(&ci->i_cap_wq);
}
--
cgit v1.2.3
From ef9157259fb7bb3bc2c61df227e36f1b861a4753 Mon Sep 17 00:00:00 2001
From: Luis Henriques <lhenriques@suse.com>
Date: Wed, 11 Mar 2020 11:05:38 +0000
Subject: ceph: fix snapshot directory timestamps
The .snap directory timestamps are kept at 0 (1970-01-01 00:00), which
isn't consistent with what the fuse client does. This patch makes the
behaviour consistent, by setting these timestamps (atime, btime, ctime,
mtime) to those of the parent directory.
Cc: Marc Roos <M.Roos@f1-outsourcing.eu>
Signed-off-by: Luis Henriques <lhenriques@suse.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
fs/ceph/inode.c | 4 ++++
1 file changed, 4 insertions(+)
(limited to 'fs/ceph/inode.c')
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index ee40ba7e0e77..7fef94fd1e55 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -82,10 +82,14 @@ struct inode *ceph_get_snapdir(struct inode *parent)
inode->i_mode = parent->i_mode;
inode->i_uid = parent->i_uid;
inode->i_gid = parent->i_gid;
+ inode->i_mtime = parent->i_mtime;
+ inode->i_ctime = parent->i_ctime;
+ inode->i_atime = parent->i_atime;
inode->i_op = &ceph_snapdir_iops;
inode->i_fop = &ceph_snapdir_fops;
ci->i_snap_caps = CEPH_CAP_PIN; /* so we can open */
ci->i_rbytes = 0;
+ ci->i_btime = ceph_inode(parent)->i_btime;
if (inode->i_state & I_NEW)
unlock_new_inode(inode);
--
cgit v1.2.3