summaryrefslogtreecommitdiffstats
path: root/fs/ceph
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ceph')
-rw-r--r--fs/ceph/acl.c6
-rw-r--r--fs/ceph/addr.c23
-rw-r--r--fs/ceph/caps.c246
-rw-r--r--fs/ceph/debugfs.c6
-rw-r--r--fs/ceph/export.c2
-rw-r--r--fs/ceph/file.c185
-rw-r--r--fs/ceph/inode.c249
-rw-r--r--fs/ceph/locks.c10
-rw-r--r--fs/ceph/mds_client.c15
-rw-r--r--fs/ceph/mds_client.h1
-rw-r--r--fs/ceph/mdsmap.c2
-rw-r--r--fs/ceph/super.h13
12 files changed, 395 insertions, 363 deletions
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index 21887d63dad..469f2e8657e 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -104,12 +104,6 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
umode_t new_mode = inode->i_mode, old_mode = inode->i_mode;
struct dentry *dentry;
- if (acl) {
- ret = posix_acl_valid(acl);
- if (ret < 0)
- goto out;
- }
-
switch (type) {
case ACL_TYPE_ACCESS:
name = POSIX_ACL_XATTR_ACCESS;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index b53278c9fd9..90b3954d48e 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -211,18 +211,15 @@ static int readpage_nounlock(struct file *filp, struct page *page)
SetPageError(page);
ceph_fscache_readpage_cancel(inode, page);
goto out;
- } else {
- if (err < PAGE_CACHE_SIZE) {
- /* zero fill remainder of page */
- zero_user_segment(page, err, PAGE_CACHE_SIZE);
- } else {
- flush_dcache_page(page);
- }
}
- SetPageUptodate(page);
+ if (err < PAGE_CACHE_SIZE)
+ /* zero fill remainder of page */
+ zero_user_segment(page, err, PAGE_CACHE_SIZE);
+ else
+ flush_dcache_page(page);
- if (err >= 0)
- ceph_readpage_to_fscache(inode, page);
+ SetPageUptodate(page);
+ ceph_readpage_to_fscache(inode, page);
out:
return err < 0 ? err : 0;
@@ -694,7 +691,7 @@ static int ceph_writepages_start(struct address_space *mapping,
(wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
if (fsc->mount_state == CEPH_MOUNT_SHUTDOWN) {
- pr_warning("writepage_start %p on forced umount\n", inode);
+ pr_warn("writepage_start %p on forced umount\n", inode);
return -EIO; /* we're in a forced umount, don't write! */
}
if (fsc->mount_options->wsize && fsc->mount_options->wsize < wsize)
@@ -1187,8 +1184,8 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
* never get called.
*/
static ssize_t ceph_direct_io(int rw, struct kiocb *iocb,
- const struct iovec *iov,
- loff_t pos, unsigned long nr_segs)
+ struct iov_iter *iter,
+ loff_t pos)
{
WARN_ON(1);
return -EINVAL;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index c561b628ebc..1fde164b74b 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -221,8 +221,8 @@ int ceph_unreserve_caps(struct ceph_mds_client *mdsc,
return 0;
}
-static struct ceph_cap *get_cap(struct ceph_mds_client *mdsc,
- struct ceph_cap_reservation *ctx)
+struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc,
+ struct ceph_cap_reservation *ctx)
{
struct ceph_cap *cap = NULL;
@@ -508,15 +508,14 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
* it is < 0. (This is so we can atomically add the cap and add an
* open file reference to it.)
*/
-int ceph_add_cap(struct inode *inode,
- struct ceph_mds_session *session, u64 cap_id,
- int fmode, unsigned issued, unsigned wanted,
- unsigned seq, unsigned mseq, u64 realmino, int flags,
- struct ceph_cap_reservation *caps_reservation)
+void ceph_add_cap(struct inode *inode,
+ struct ceph_mds_session *session, u64 cap_id,
+ int fmode, unsigned issued, unsigned wanted,
+ unsigned seq, unsigned mseq, u64 realmino, int flags,
+ struct ceph_cap **new_cap)
{
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_cap *new_cap = NULL;
struct ceph_cap *cap;
int mds = session->s_mds;
int actual_wanted;
@@ -531,20 +530,10 @@ int ceph_add_cap(struct inode *inode,
if (fmode >= 0)
wanted |= ceph_caps_for_mode(fmode);
-retry:
- spin_lock(&ci->i_ceph_lock);
cap = __get_cap_for_mds(ci, mds);
if (!cap) {
- if (new_cap) {
- cap = new_cap;
- new_cap = NULL;
- } else {
- spin_unlock(&ci->i_ceph_lock);
- new_cap = get_cap(mdsc, caps_reservation);
- if (new_cap == NULL)
- return -ENOMEM;
- goto retry;
- }
+ cap = *new_cap;
+ *new_cap = NULL;
cap->issued = 0;
cap->implemented = 0;
@@ -562,9 +551,6 @@ retry:
session->s_nr_caps++;
spin_unlock(&session->s_cap_lock);
} else {
- if (new_cap)
- ceph_put_cap(mdsc, new_cap);
-
/*
* auth mds of the inode changed. we received the cap export
* message, but still haven't received the cap import message.
@@ -626,7 +612,6 @@ retry:
ci->i_auth_cap = cap;
cap->mds_wanted = wanted;
}
- ci->i_cap_exporting_issued = 0;
} else {
WARN_ON(ci->i_auth_cap == cap);
}
@@ -648,9 +633,6 @@ retry:
if (fmode >= 0)
__ceph_get_fmode(ci, fmode);
- spin_unlock(&ci->i_ceph_lock);
- wake_up_all(&ci->i_cap_wq);
- return 0;
}
/*
@@ -685,7 +667,7 @@ static int __cap_is_valid(struct ceph_cap *cap)
*/
int __ceph_caps_issued(struct ceph_inode_info *ci, int *implemented)
{
- int have = ci->i_snap_caps | ci->i_cap_exporting_issued;
+ int have = ci->i_snap_caps;
struct ceph_cap *cap;
struct rb_node *p;
@@ -900,7 +882,7 @@ int __ceph_caps_mds_wanted(struct ceph_inode_info *ci)
*/
static int __ceph_is_any_caps(struct ceph_inode_info *ci)
{
- return !RB_EMPTY_ROOT(&ci->i_caps) || ci->i_cap_exporting_issued;
+ return !RB_EMPTY_ROOT(&ci->i_caps);
}
int ceph_is_any_caps(struct inode *inode)
@@ -2397,32 +2379,30 @@ static void invalidate_aliases(struct inode *inode)
* actually be a revocation if it specifies a smaller cap set.)
*
* caller holds s_mutex and i_ceph_lock, we drop both.
- *
- * return value:
- * 0 - ok
- * 1 - check_caps on auth cap only (writeback)
- * 2 - check_caps (ack revoke)
*/
-static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
+static void handle_cap_grant(struct ceph_mds_client *mdsc,
+ struct inode *inode, struct ceph_mds_caps *grant,
+ void *snaptrace, int snaptrace_len,
+ struct ceph_buffer *xattr_buf,
struct ceph_mds_session *session,
- struct ceph_cap *cap,
- struct ceph_buffer *xattr_buf)
- __releases(ci->i_ceph_lock)
+ struct ceph_cap *cap, int issued)
+ __releases(ci->i_ceph_lock)
{
struct ceph_inode_info *ci = ceph_inode(inode);
int mds = session->s_mds;
int seq = le32_to_cpu(grant->seq);
int newcaps = le32_to_cpu(grant->caps);
- int issued, implemented, used, wanted, dirty;
+ int used, wanted, dirty;
u64 size = le64_to_cpu(grant->size);
u64 max_size = le64_to_cpu(grant->max_size);
struct timespec mtime, atime, ctime;
int check_caps = 0;
- int wake = 0;
- int writeback = 0;
- int queue_invalidate = 0;
- int deleted_inode = 0;
- int queue_revalidate = 0;
+ bool wake = 0;
+ bool writeback = 0;
+ bool queue_trunc = 0;
+ bool queue_invalidate = 0;
+ bool queue_revalidate = 0;
+ bool deleted_inode = 0;
dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
inode, cap, mds, seq, ceph_cap_string(newcaps));
@@ -2466,16 +2446,13 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
}
/* side effects now are allowed */
-
- issued = __ceph_caps_issued(ci, &implemented);
- issued |= implemented | __ceph_caps_dirty(ci);
-
cap->cap_gen = session->s_cap_gen;
cap->seq = seq;
__check_cap_issue(ci, cap, newcaps);
- if ((issued & CEPH_CAP_AUTH_EXCL) == 0) {
+ if ((newcaps & CEPH_CAP_AUTH_SHARED) &&
+ (issued & CEPH_CAP_AUTH_EXCL) == 0) {
inode->i_mode = le32_to_cpu(grant->mode);
inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(grant->uid));
inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(grant->gid));
@@ -2484,7 +2461,8 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
from_kgid(&init_user_ns, inode->i_gid));
}
- if ((issued & CEPH_CAP_LINK_EXCL) == 0) {
+ if ((newcaps & CEPH_CAP_AUTH_SHARED) &&
+ (issued & CEPH_CAP_LINK_EXCL) == 0) {
set_nlink(inode, le32_to_cpu(grant->nlink));
if (inode->i_nlink == 0 &&
(newcaps & (CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL)))
@@ -2511,30 +2489,35 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
if ((issued & CEPH_CAP_FILE_CACHE) && ci->i_rdcache_gen > 1)
queue_revalidate = 1;
- /* size/ctime/mtime/atime? */
- ceph_fill_file_size(inode, issued,
- le32_to_cpu(grant->truncate_seq),
- le64_to_cpu(grant->truncate_size), size);
- ceph_decode_timespec(&mtime, &grant->mtime);
- ceph_decode_timespec(&atime, &grant->atime);
- ceph_decode_timespec(&ctime, &grant->ctime);
- ceph_fill_file_time(inode, issued,
- le32_to_cpu(grant->time_warp_seq), &ctime, &mtime,
- &atime);
-
-
- /* file layout may have changed */
- ci->i_layout = grant->layout;
-
- /* max size increase? */
- if (ci->i_auth_cap == cap && max_size != ci->i_max_size) {
- dout("max_size %lld -> %llu\n", ci->i_max_size, max_size);
- ci->i_max_size = max_size;
- if (max_size >= ci->i_wanted_max_size) {
- ci->i_wanted_max_size = 0; /* reset */
- ci->i_requested_max_size = 0;
+ if (newcaps & CEPH_CAP_ANY_RD) {
+ /* ctime/mtime/atime? */
+ ceph_decode_timespec(&mtime, &grant->mtime);
+ ceph_decode_timespec(&atime, &grant->atime);
+ ceph_decode_timespec(&ctime, &grant->ctime);
+ ceph_fill_file_time(inode, issued,
+ le32_to_cpu(grant->time_warp_seq),
+ &ctime, &mtime, &atime);
+ }
+
+ if (newcaps & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR)) {
+ /* file layout may have changed */
+ ci->i_layout = grant->layout;
+ /* size/truncate_seq? */
+ queue_trunc = ceph_fill_file_size(inode, issued,
+ le32_to_cpu(grant->truncate_seq),
+ le64_to_cpu(grant->truncate_size),
+ size);
+ /* max size increase? */
+ if (ci->i_auth_cap == cap && max_size != ci->i_max_size) {
+ dout("max_size %lld -> %llu\n",
+ ci->i_max_size, max_size);
+ ci->i_max_size = max_size;
+ if (max_size >= ci->i_wanted_max_size) {
+ ci->i_wanted_max_size = 0; /* reset */
+ ci->i_requested_max_size = 0;
+ }
+ wake = 1;
}
- wake = 1;
}
/* check cap bits */
@@ -2595,6 +2578,23 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
spin_unlock(&ci->i_ceph_lock);
+ if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
+ down_write(&mdsc->snap_rwsem);
+ ceph_update_snap_trace(mdsc, snaptrace,
+ snaptrace + snaptrace_len, false);
+ downgrade_write(&mdsc->snap_rwsem);
+ kick_flushing_inode_caps(mdsc, session, inode);
+ up_read(&mdsc->snap_rwsem);
+ if (newcaps & ~issued)
+ wake = 1;
+ }
+
+ if (queue_trunc) {
+ ceph_queue_vmtruncate(inode);
+ ceph_queue_revalidate(inode);
+ } else if (queue_revalidate)
+ ceph_queue_revalidate(inode);
+
if (writeback)
/*
* queue inode for writeback: we can't actually call
@@ -2606,8 +2606,6 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
ceph_queue_invalidate(inode);
if (deleted_inode)
invalidate_aliases(inode);
- if (queue_revalidate)
- ceph_queue_revalidate(inode);
if (wake)
wake_up_all(&ci->i_cap_wq);
@@ -2784,7 +2782,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex,
{
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
struct ceph_mds_session *tsession = NULL;
- struct ceph_cap *cap, *tcap;
+ struct ceph_cap *cap, *tcap, *new_cap = NULL;
struct ceph_inode_info *ci = ceph_inode(inode);
u64 t_cap_id;
unsigned mseq = le32_to_cpu(ex->migrate_seq);
@@ -2807,7 +2805,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex,
retry:
spin_lock(&ci->i_ceph_lock);
cap = __get_cap_for_mds(ci, mds);
- if (!cap)
+ if (!cap || cap->cap_id != le64_to_cpu(ex->cap_id))
goto out_unlock;
if (target < 0) {
@@ -2846,15 +2844,14 @@ retry:
}
__ceph_remove_cap(cap, false);
goto out_unlock;
- }
-
- if (tsession) {
- int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0;
- spin_unlock(&ci->i_ceph_lock);
+ } else if (tsession) {
/* add placeholder for the export tagert */
+ int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0;
ceph_add_cap(inode, tsession, t_cap_id, -1, issued, 0,
- t_seq - 1, t_mseq, (u64)-1, flag, NULL);
- goto retry;
+ t_seq - 1, t_mseq, (u64)-1, flag, &new_cap);
+
+ __ceph_remove_cap(cap, false);
+ goto out_unlock;
}
spin_unlock(&ci->i_ceph_lock);
@@ -2873,6 +2870,7 @@ retry:
SINGLE_DEPTH_NESTING);
}
ceph_add_cap_releases(mdsc, tsession);
+ new_cap = ceph_get_cap(mdsc, NULL);
} else {
WARN_ON(1);
tsession = NULL;
@@ -2887,24 +2885,27 @@ out_unlock:
mutex_unlock(&tsession->s_mutex);
ceph_put_mds_session(tsession);
}
+ if (new_cap)
+ ceph_put_cap(mdsc, new_cap);
}
/*
- * Handle cap IMPORT. If there are temp bits from an older EXPORT,
- * clean them up.
+ * Handle cap IMPORT.
*
- * caller holds s_mutex.
+ * caller holds s_mutex. acquires i_ceph_lock
*/
static void handle_cap_import(struct ceph_mds_client *mdsc,
struct inode *inode, struct ceph_mds_caps *im,
struct ceph_mds_cap_peer *ph,
struct ceph_mds_session *session,
- void *snaptrace, int snaptrace_len)
+ struct ceph_cap **target_cap, int *old_issued)
+ __acquires(ci->i_ceph_lock)
{
struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_cap *cap;
+ struct ceph_cap *cap, *ocap, *new_cap = NULL;
int mds = session->s_mds;
- unsigned issued = le32_to_cpu(im->caps);
+ int issued;
+ unsigned caps = le32_to_cpu(im->caps);
unsigned wanted = le32_to_cpu(im->wanted);
unsigned seq = le32_to_cpu(im->seq);
unsigned mseq = le32_to_cpu(im->migrate_seq);
@@ -2924,40 +2925,52 @@ static void handle_cap_import(struct ceph_mds_client *mdsc,
dout("handle_cap_import inode %p ci %p mds%d mseq %d peer %d\n",
inode, ci, mds, mseq, peer);
+retry:
spin_lock(&ci->i_ceph_lock);
- cap = peer >= 0 ? __get_cap_for_mds(ci, peer) : NULL;
- if (cap && cap->cap_id == p_cap_id) {
+ cap = __get_cap_for_mds(ci, mds);
+ if (!cap) {
+ if (!new_cap) {
+ spin_unlock(&ci->i_ceph_lock);
+ new_cap = ceph_get_cap(mdsc, NULL);
+ goto retry;
+ }
+ cap = new_cap;
+ } else {
+ if (new_cap) {
+ ceph_put_cap(mdsc, new_cap);
+ new_cap = NULL;
+ }
+ }
+
+ __ceph_caps_issued(ci, &issued);
+ issued |= __ceph_caps_dirty(ci);
+
+ ceph_add_cap(inode, session, cap_id, -1, caps, wanted, seq, mseq,
+ realmino, CEPH_CAP_FLAG_AUTH, &new_cap);
+
+ ocap = peer >= 0 ? __get_cap_for_mds(ci, peer) : NULL;
+ if (ocap && ocap->cap_id == p_cap_id) {
dout(" remove export cap %p mds%d flags %d\n",
- cap, peer, ph->flags);
+ ocap, peer, ph->flags);
if ((ph->flags & CEPH_CAP_FLAG_AUTH) &&
- (cap->seq != le32_to_cpu(ph->seq) ||
- cap->mseq != le32_to_cpu(ph->mseq))) {
+ (ocap->seq != le32_to_cpu(ph->seq) ||
+ ocap->mseq != le32_to_cpu(ph->mseq))) {
pr_err("handle_cap_import: mismatched seq/mseq: "
"ino (%llx.%llx) mds%d seq %d mseq %d "
"importer mds%d has peer seq %d mseq %d\n",
- ceph_vinop(inode), peer, cap->seq,
- cap->mseq, mds, le32_to_cpu(ph->seq),
+ ceph_vinop(inode), peer, ocap->seq,
+ ocap->mseq, mds, le32_to_cpu(ph->seq),
le32_to_cpu(ph->mseq));
}
- ci->i_cap_exporting_issued = cap->issued;
- __ceph_remove_cap(cap, (ph->flags & CEPH_CAP_FLAG_RELEASE));
+ __ceph_remove_cap(ocap, (ph->flags & CEPH_CAP_FLAG_RELEASE));
}
/* make sure we re-request max_size, if necessary */
ci->i_wanted_max_size = 0;
ci->i_requested_max_size = 0;
- spin_unlock(&ci->i_ceph_lock);
-
- down_write(&mdsc->snap_rwsem);
- ceph_update_snap_trace(mdsc, snaptrace, snaptrace+snaptrace_len,
- false);
- downgrade_write(&mdsc->snap_rwsem);
- ceph_add_cap(inode, session, cap_id, -1,
- issued, wanted, seq, mseq, realmino, CEPH_CAP_FLAG_AUTH,
- NULL /* no caps context */);
- kick_flushing_inode_caps(mdsc, session, inode);
- up_read(&mdsc->snap_rwsem);
+ *old_issued = issued;
+ *target_cap = cap;
}
/*
@@ -2977,7 +2990,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
struct ceph_mds_caps *h;
struct ceph_mds_cap_peer *peer = NULL;
int mds = session->s_mds;
- int op;
+ int op, issued;
u32 seq, mseq;
struct ceph_vino vino;
u64 cap_id;
@@ -3069,7 +3082,10 @@ void ceph_handle_caps(struct ceph_mds_session *session,
case CEPH_CAP_OP_IMPORT:
handle_cap_import(mdsc, inode, h, peer, session,
- snaptrace, snaptrace_len);
+ &cap, &issued);
+ handle_cap_grant(mdsc, inode, h, snaptrace, snaptrace_len,
+ msg->middle, session, cap, issued);
+ goto done_unlocked;
}
/* the rest require a cap */
@@ -3086,8 +3102,10 @@ void ceph_handle_caps(struct ceph_mds_session *session,
switch (op) {
case CEPH_CAP_OP_REVOKE:
case CEPH_CAP_OP_GRANT:
- case CEPH_CAP_OP_IMPORT:
- handle_cap_grant(inode, h, session, cap, msg->middle);
+ __ceph_caps_issued(ci, &issued);
+ issued |= __ceph_caps_dirty(ci);
+ handle_cap_grant(mdsc, inode, h, NULL, 0, msg->middle,
+ session, cap, issued);
goto done_unlocked;
case CEPH_CAP_OP_FLUSH_ACK:
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 16b54aa31f0..5a743ac141a 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -71,9 +71,9 @@ static int mdsc_show(struct seq_file *s, void *p)
seq_printf(s, "%s", ceph_mds_op_name(req->r_op));
if (req->r_got_unsafe)
- seq_printf(s, "\t(unsafe)");
+ seq_puts(s, "\t(unsafe)");
else
- seq_printf(s, "\t");
+ seq_puts(s, "\t");
if (req->r_inode) {
seq_printf(s, " #%llx", ceph_ino(req->r_inode));
@@ -119,7 +119,7 @@ static int mdsc_show(struct seq_file *s, void *p)
seq_printf(s, " %s", req->r_path2);
}
- seq_printf(s, "\n");
+ seq_puts(s, "\n");
}
mutex_unlock(&mdsc->mutex);
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 00d6af6a32e..8d7d782f438 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -169,7 +169,7 @@ static struct dentry *__get_parent(struct super_block *sb,
return dentry;
}
-struct dentry *ceph_get_parent(struct dentry *child)
+static struct dentry *ceph_get_parent(struct dentry *child)
{
/* don't re-export snaps */
if (ceph_snap(child->d_inode) != CEPH_NOSNAP)
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 88a6df4cbe6..302085100c2 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -418,7 +418,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *i,
struct page **pages;
u64 off = iocb->ki_pos;
int num_pages, ret;
- size_t len = i->count;
+ size_t len = iov_iter_count(i);
dout("sync_read on file %p %llu~%u %s\n", file, off,
(unsigned)len,
@@ -436,25 +436,26 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *i,
if (file->f_flags & O_DIRECT) {
while (iov_iter_count(i)) {
- void __user *data = i->iov[0].iov_base + i->iov_offset;
- size_t len = i->iov[0].iov_len - i->iov_offset;
+ size_t start;
+ ssize_t n;
- num_pages = calc_pages_for((unsigned long)data, len);
- pages = ceph_get_direct_page_vector(data,
- num_pages, true);
- if (IS_ERR(pages))
- return PTR_ERR(pages);
+ n = iov_iter_get_pages_alloc(i, &pages, INT_MAX, &start);
+ if (n < 0)
+ return n;
- ret = striped_read(inode, off, len,
+ num_pages = (n + start + PAGE_SIZE - 1) / PAGE_SIZE;
+
+ ret = striped_read(inode, off, n,
pages, num_pages, checkeof,
- 1, (unsigned long)data & ~PAGE_MASK);
+ 1, start);
+
ceph_put_page_vector(pages, num_pages, true);
if (ret <= 0)
break;
off += ret;
iov_iter_advance(i, ret);
- if (ret < len)
+ if (ret < n)
break;
}
} else {
@@ -466,25 +467,14 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *i,
num_pages, checkeof, 0, 0);
if (ret > 0) {
int l, k = 0;
- size_t left = len = ret;
+ size_t left = ret;
while (left) {
- void __user *data = i->iov[0].iov_base
- + i->iov_offset;
- l = min(i->iov[0].iov_len - i->iov_offset,
- left);
-
- ret = ceph_copy_page_vector_to_user(&pages[k],
- data, off,
- l);
- if (ret > 0) {
- iov_iter_advance(i, ret);
- left -= ret;
- off += ret;
- k = calc_pages_for(iocb->ki_pos,
- len - left + 1) - 1;
- BUG_ON(k >= num_pages && left);
- } else
+ int copy = min_t(size_t, PAGE_SIZE, left);
+ l = copy_page_to_iter(pages[k++], 0, copy, i);
+ off += l;
+ left -= l;
+ if (l < copy)
break;
}
}
@@ -541,8 +531,7 @@ static void ceph_sync_write_unsafe(struct ceph_osd_request *req, bool unsafe)
* objects, rollback on failure, etc.)
*/
static ssize_t
-ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, size_t count)
+ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
@@ -556,11 +545,10 @@ ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov,
int written = 0;
int flags;
int check_caps = 0;
- int page_align;
int ret;
struct timespec mtime = CURRENT_TIME;
loff_t pos = iocb->ki_pos;
- struct iov_iter i;
+ size_t count = iov_iter_count(from);
if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
return -EROFS;
@@ -582,13 +570,10 @@ ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov,
CEPH_OSD_FLAG_ONDISK |
CEPH_OSD_FLAG_WRITE;
- iov_iter_init(&i, iov, nr_segs, count, 0);
-
- while (iov_iter_count(&i) > 0) {
- void __user *data = i.iov->iov_base + i.iov_offset;
- u64 len = i.iov->iov_len - i.iov_offset;
-
- page_align = (unsigned long)data & ~PAGE_MASK;
+ while (iov_iter_count(from) > 0) {
+ u64 len = iov_iter_single_seg_count(from);
+ size_t start;
+ ssize_t n;
snapc = ci->i_snap_realm->cached_context;
vino = ceph_vino(inode);
@@ -604,20 +589,21 @@ ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov,
break;
}
- num_pages = calc_pages_for(page_align, len);
- pages = ceph_get_direct_page_vector(data, num_pages, false);
- if (IS_ERR(pages)) {
- ret = PTR_ERR(pages);
- goto out;
+ n = iov_iter_get_pages_alloc(from, &pages, len, &start);
+ if (unlikely(n < 0)) {
+ ret = n;
+ ceph_osdc_put_request(req);
+ break;
}
+ num_pages = (n + start + PAGE_SIZE - 1) / PAGE_SIZE;
/*
* throw out any page cache pages in this range. this
* may block.
*/
truncate_inode_pages_range(inode->i_mapping, pos,
- (pos+len) | (PAGE_CACHE_SIZE-1));
- osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_align,
+ (pos+n) | (PAGE_CACHE_SIZE-1));
+ osd_req_op_extent_osd_data_pages(req, 0, pages, n, start,
false, false);
/* BUG_ON(vino.snap != CEPH_NOSNAP); */
@@ -629,22 +615,20 @@ ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov,
ceph_put_page_vector(pages, num_pages, false);
-out:
ceph_osdc_put_request(req);
- if (ret == 0) {
- pos += len;
- written += len;
- iov_iter_advance(&i, (size_t)len);
-
- if (pos > i_size_read(inode)) {
- check_caps = ceph_inode_set_size(inode, pos);
- if (check_caps)
- ceph_check_caps(ceph_inode(inode),
- CHECK_CAPS_AUTHONLY,
- NULL);
- }
- } else
+ if (ret)
break;
+ pos += n;
+ written += n;
+ iov_iter_advance(from, n);
+
+ if (pos > i_size_read(inode)) {
+ check_caps = ceph_inode_set_size(inode, pos);
+ if (check_caps)
+ ceph_check_caps(ceph_inode(inode),
+ CHECK_CAPS_AUTHONLY,
+ NULL);
+ }
}
if (ret != -EOLDSNAPC && written > 0) {
@@ -662,8 +646,7 @@ out:
* correct atomic write, we should e.g. take write locks on all
* objects, rollback on failure, etc.)
*/
-static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, size_t count)
+static ssize_t ceph_sync_write(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
@@ -681,7 +664,7 @@ static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov,
int ret;
struct timespec mtime = CURRENT_TIME;
loff_t pos = iocb->ki_pos;
- struct iov_iter i;
+ size_t count = iov_iter_count(from);
if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
return -EROFS;
@@ -703,9 +686,7 @@ static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov,
CEPH_OSD_FLAG_WRITE |
CEPH_OSD_FLAG_ACK;
- iov_iter_init(&i, iov, nr_segs, count, 0);
-
- while ((len = iov_iter_count(&i)) > 0) {
+ while ((len = iov_iter_count(from)) > 0) {
size_t left;
int n;
@@ -737,13 +718,12 @@ static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov,
left = len;
for (n = 0; n < num_pages; n++) {
size_t plen = min_t(size_t, left, PAGE_SIZE);
- ret = iov_iter_copy_from_user(pages[n], &i, 0, plen);
+ ret = copy_page_from_iter(pages[n], 0, plen, from);
if (ret != plen) {
ret = -EFAULT;
break;
}
left -= ret;
- iov_iter_advance(&i, ret);
}
if (ret < 0) {
@@ -796,8 +776,7 @@ out:
*
* Hmm, the sync read case isn't actually async... should it be?
*/
-static ssize_t ceph_aio_read(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *filp = iocb->ki_filp;
struct ceph_file_info *fi = filp->private_data;
@@ -823,40 +802,20 @@ again:
if ((got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0 ||
(iocb->ki_filp->f_flags & O_DIRECT) ||
(fi->flags & CEPH_F_SYNC)) {
- struct iov_iter i;
dout("aio_sync_read %p %llx.%llx %llu~%u got cap refs on %s\n",
inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
ceph_cap_string(got));
- if (!read) {
- ret = generic_segment_checks(iov, &nr_segs,
- &len, VERIFY_WRITE);
- if (ret)
- goto out;
- }
-
- iov_iter_init(&i, iov, nr_segs, len, read);
-
/* hmm, this isn't really async... */
- ret = ceph_sync_read(iocb, &i, &checkeof);
+ ret = ceph_sync_read(iocb, to, &checkeof);
} else {
- /*
- * We can't modify the content of iov,
- * so we only read from beginning.
- */
- if (read) {
- iocb->ki_pos = pos;
- len = iocb->ki_nbytes;
- read = 0;
- }
dout("aio_read %p %llx.%llx %llu~%u got cap refs on %s\n",
- inode, ceph_vinop(inode), pos, (unsigned)len,
+ inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
ceph_cap_string(got));
- ret = generic_file_aio_read(iocb, iov, nr_segs, pos);
+ ret = generic_file_read_iter(iocb, to);
}
-out:
dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n",
inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret);
ceph_put_cap_refs(ci, got);
@@ -872,6 +831,7 @@ out:
", reading more\n", iocb->ki_pos,
inode->i_size);
+ iov_iter_advance(to, ret);
read += ret;
len -= ret;
checkeof = 0;
@@ -895,8 +855,7 @@ out:
*
* If we are near ENOSPC, write synchronously.
*/
-static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct ceph_file_info *fi = file->private_data;
@@ -904,18 +863,15 @@ static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov,
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_osd_client *osdc =
&ceph_sb_to_client(inode->i_sb)->client->osdc;
- ssize_t count, written = 0;
+ ssize_t count = iov_iter_count(from), written = 0;
int err, want, got;
+ loff_t pos = iocb->ki_pos;
if (ceph_snap(inode) != CEPH_NOSNAP)
return -EROFS;
mutex_lock(&inode->i_mutex);
- err = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ);
- if (err)
- goto out;
-
/* We can write back this queue in page reclaim */
current->backing_dev_info = file->f_mapping->backing_dev_info;
@@ -925,6 +881,7 @@ static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov,
if (count == 0)
goto out;
+ iov_iter_truncate(from, count);
err = file_remove_suid(file);
if (err)
@@ -956,23 +913,26 @@ retry_snap:
if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 ||
(file->f_flags & O_DIRECT) || (fi->flags & CEPH_F_SYNC)) {
+ struct iov_iter data;
mutex_unlock(&inode->i_mutex);
+ /* we might need to revert back to that point */
+ data = *from;
if (file->f_flags & O_DIRECT)
- written = ceph_sync_direct_write(iocb, iov,
- nr_segs, count);
+ written = ceph_sync_direct_write(iocb, &data);
else
- written = ceph_sync_write(iocb, iov, nr_segs, count);
+ written = ceph_sync_write(iocb, &data);
if (written == -EOLDSNAPC) {
dout("aio_write %p %llx.%llx %llu~%u"
"got EOLDSNAPC, retrying\n",
inode, ceph_vinop(inode),
- pos, (unsigned)iov->iov_len);
+ pos, (unsigned)count);
mutex_lock(&inode->i_mutex);
goto retry_snap;
}
+ if (written > 0)
+ iov_iter_advance(from, written);
} else {
loff_t old_size = inode->i_size;
- struct iov_iter from;
/*
* No need to acquire the i_truncate_mutex. Because
* the MDS revokes Fwb caps before sending truncate
@@ -980,8 +940,7 @@ retry_snap:
* are pending vmtruncate. So write and vmtruncate
* can not run at the same time
*/
- iov_iter_init(&from, iov, nr_segs, count, 0);
- written = generic_perform_write(file, &from, pos);
+ written = generic_perform_write(file, from, pos);
if (likely(written >= 0))
iocb->ki_pos = pos + written;
if (inode->i_size > old_size)
@@ -999,7 +958,7 @@ retry_snap:
}
dout("aio_write %p %llx.%llx %llu~%u dropping cap refs on %s\n",
- inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
+ inode, ceph_vinop(inode), pos, (unsigned)count,
ceph_cap_string(got));
ceph_put_cap_refs(ci, got);
@@ -1276,16 +1235,16 @@ const struct file_operations ceph_file_fops = {
.open = ceph_open,
.release = ceph_release,
.llseek = ceph_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = ceph_aio_read,
- .aio_write = ceph_aio_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = ceph_read_iter,
+ .write_iter = ceph_write_iter,
.mmap = ceph_mmap,
.fsync = ceph_fsync,
.lock = ceph_lock,
.flock = ceph_flock,
.splice_read = generic_file_splice_read,
- .splice_write = generic_file_splice_write,
+ .splice_write = iter_file_splice_write,
.unlocked_ioctl = ceph_ioctl,
.compat_ioctl = ceph_ioctl,
.fallocate = ceph_fallocate,
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 233c6f96910..04c89c266ce 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -10,6 +10,7 @@
#include <linux/writeback.h>
#include <linux/vmalloc.h>
#include <linux/posix_acl.h>
+#include <linux/random.h>
#include "super.h"
#include "mds_client.h"
@@ -179,9 +180,8 @@ struct ceph_inode_frag *__ceph_find_frag(struct ceph_inode_info *ci, u32 f)
* specified, copy the frag delegation info to the caller if
* it is present.
*/
-u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
- struct ceph_inode_frag *pfrag,
- int *found)
+static u32 __ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
+ struct ceph_inode_frag *pfrag, int *found)
{
u32 t = ceph_frag_make(0, 0);
struct ceph_inode_frag *frag;
@@ -191,7 +191,6 @@ u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
if (found)
*found = 0;
- mutex_lock(&ci->i_fragtree_mutex);
while (1) {
WARN_ON(!ceph_frag_contains_value(t, v));
frag = __ceph_find_frag(ci, t);
@@ -220,10 +219,19 @@ u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
}
dout("choose_frag(%x) = %x\n", v, t);
- mutex_unlock(&ci->i_fragtree_mutex);
return t;
}
+u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
+ struct ceph_inode_frag *pfrag, int *found)
+{
+ u32 ret;
+ mutex_lock(&ci->i_fragtree_mutex);
+ ret = __ceph_choose_frag(ci, v, pfrag, found);
+ mutex_unlock(&ci->i_fragtree_mutex);
+ return ret;
+}
+
/*
* Process dirfrag (delegation) info from the mds. Include leaf
* fragment in tree ONLY if ndist > 0. Otherwise, only
@@ -237,11 +245,17 @@ static int ceph_fill_dirfrag(struct inode *inode,
u32 id = le32_to_cpu(dirinfo->frag);
int mds = le32_to_cpu(dirinfo->auth);
int ndist = le32_to_cpu(dirinfo->ndist);
+ int diri_auth = -1;
int i;
int err = 0;
+ spin_lock(&ci->i_ceph_lock);
+ if (ci->i_auth_cap)
+ diri_auth = ci->i_auth_cap->mds;
+ spin_unlock(&ci->i_ceph_lock);
+
mutex_lock(&ci->i_fragtree_mutex);
- if (ndist == 0) {
+ if (ndist == 0 && mds == diri_auth) {
/* no delegation info needed. */
frag = __ceph_find_frag(ci, id);
if (!frag)
@@ -286,6 +300,75 @@ out:
return err;
}
+static int ceph_fill_fragtree(struct inode *inode,
+ struct ceph_frag_tree_head *fragtree,
+ struct ceph_mds_reply_dirfrag *dirinfo)
+{
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ struct ceph_inode_frag *frag;
+ struct rb_node *rb_node;
+ int i;
+ u32 id, nsplits;
+ bool update = false;
+
+ mutex_lock(&ci->i_fragtree_mutex);
+ nsplits = le32_to_cpu(fragtree->nsplits);
+ if (nsplits) {
+ i = prandom_u32() % nsplits;
+ id = le32_to_cpu(fragtree->splits[i].frag);
+ if (!__ceph_find_frag(ci, id))
+ update = true;
+ } else if (!RB_EMPTY_ROOT(&ci->i_fragtree)) {
+ rb_node = rb_first(&ci->i_fragtree);
+ frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+ if (frag->frag != ceph_frag_make(0, 0) || rb_next(rb_node))
+ update = true;
+ }
+ if (!update && dirinfo) {
+ id = le32_to_cpu(dirinfo->frag);
+ if (id != __ceph_choose_frag(ci, id, NULL, NULL))
+ update = true;
+ }
+ if (!update)
+ goto out_unlock;
+
+ dout("fill_fragtree %llx.%llx\n", ceph_vinop(inode));
+ rb_node = rb_first(&ci->i_fragtree);
+ for (i = 0; i < nsplits; i++) {
+ id = le32_to_cpu(fragtree->splits[i].frag);
+ frag = NULL;
+ while (rb_node) {
+ frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+ if (ceph_frag_compare(frag->frag, id) >= 0) {
+ if (frag->frag != id)
+ frag = NULL;
+ else
+ rb_node = rb_next(rb_node);
+ break;
+ }
+ rb_node = rb_next(rb_node);
+ rb_erase(&frag->node, &ci->i_fragtree);
+ kfree(frag);
+ frag = NULL;
+ }
+ if (!frag) {
+ frag = __get_or_create_frag(ci, id);
+ if (IS_ERR(frag))
+ continue;
+ }
+ frag->split_by = le32_to_cpu(fragtree->splits[i].by);
+ dout(" frag %x split by %d\n", frag->frag, frag->split_by);
+ }
+ while (rb_node) {
+ frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+ rb_node = rb_next(rb_node);
+ rb_erase(&frag->node, &ci->i_fragtree);
+ kfree(frag);
+ }
+out_unlock:
+ mutex_unlock(&ci->i_fragtree_mutex);
+ return 0;
+}
/*
* initialize a newly allocated inode.
@@ -341,7 +424,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
INIT_LIST_HEAD(&ci->i_cap_snaps);
ci->i_head_snapc = NULL;
ci->i_snap_caps = 0;
- ci->i_cap_exporting_issued = 0;
for (i = 0; i < CEPH_FILE_MODE_NUM; i++)
ci->i_nr_by_mode[i] = 0;
@@ -407,7 +489,7 @@ void ceph_destroy_inode(struct inode *inode)
/*
* we may still have a snap_realm reference if there are stray
- * caps in i_cap_exporting_issued or i_snap_caps.
+ * caps in i_snap_caps.
*/
if (ci->i_snap_realm) {
struct ceph_mds_client *mdsc =
@@ -582,22 +664,26 @@ static int fill_inode(struct inode *inode,
unsigned long ttl_from, 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;
struct ceph_inode_info *ci = ceph_inode(inode);
- int i;
- int issued = 0, implemented;
+ int issued = 0, implemented, new_issued;
struct timespec mtime, atime, ctime;
- u32 nsplits;
- struct ceph_inode_frag *frag;
- struct rb_node *rb_node;
struct ceph_buffer *xattr_blob = NULL;
+ struct ceph_cap *new_cap = NULL;
int err = 0;
- int queue_trunc = 0;
+ bool wake = false;
+ bool queue_trunc = false;
+ bool new_version = false;
dout("fill_inode %p ino %llx.%llx v %llu had %llu\n",
inode, ceph_vinop(inode), le64_to_cpu(info->version),
ci->i_version);
+ /* prealloc new cap struct */
+ if (info->cap.caps && ceph_snap(inode) == CEPH_NOSNAP)
+ new_cap = ceph_get_cap(mdsc, caps_reservation);
+
/*
* prealloc xattr data, if it looks like we'll need it. only
* if len > 4 (meaning there are actually xattrs; the first 4
@@ -623,19 +709,23 @@ static int fill_inode(struct inode *inode,
* 3 2 skip
* 3 3 update
*/
- if (le64_to_cpu(info->version) > 0 &&
- (ci->i_version & ~1) >= le64_to_cpu(info->version))
- goto no_change;
-
+ if (ci->i_version == 0 ||
+ ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
+ le64_to_cpu(info->version) > (ci->i_version & ~1)))
+ new_version = true;
+
issued = __ceph_caps_issued(ci, &implemented);
issued |= implemented | __ceph_caps_dirty(ci);
+ new_issued = ~issued & le32_to_cpu(info->cap.caps);
/* update inode */
ci->i_version = le64_to_cpu(info->version);
inode->i_version++;
inode->i_rdev = le32_to_cpu(info->rdev);
+ inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
- if ((issued & CEPH_CAP_AUTH_EXCL) == 0) {
+ if ((new_version || (new_issued & CEPH_CAP_AUTH_SHARED)) &&
+ (issued & CEPH_CAP_AUTH_EXCL) == 0) {
inode->i_mode = le32_to_cpu(info->mode);
inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(info->uid));
inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(info->gid));
@@ -644,23 +734,35 @@ static int fill_inode(struct inode *inode,
from_kgid(&init_user_ns, inode->i_gid));
}
- if ((issued & CEPH_CAP_LINK_EXCL) == 0)
+ if ((new_version || (new_issued & CEPH_CAP_LINK_SHARED)) &&
+ (issued & CEPH_CAP_LINK_EXCL) == 0)
set_nlink(inode, le32_to_cpu(info->nlink));
- /* be careful with mtime, atime, size */
- ceph_decode_timespec(&atime, &info->atime);
- ceph_decode_timespec(&mtime, &info->mtime);
- ceph_decode_timespec(&ctime, &info->ctime);
- queue_trunc = ceph_fill_file_size(inode, issued,
- le32_to_cpu(info->truncate_seq),
- le64_to_cpu(info->truncate_size),
- le64_to_cpu(info->size));
- ceph_fill_file_time(inode, issued,
- le32_to_cpu(info->time_warp_seq),
- &ctime, &mtime, &atime);
-
- ci->i_layout = info->layout;
- inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
+ if (new_version || (new_issued & CEPH_CAP_ANY_RD)) {
+ /* be careful with mtime, atime, size */
+ ceph_decode_timespec(&atime, &info->atime);
+ ceph_decode_timespec(&mtime, &info->mtime);
+ ceph_decode_timespec(&ctime, &info->ctime);
+ ceph_fill_file_time(inode, issued,
+ le32_to_cpu(info->time_warp_seq),
+ &ctime, &mtime, &atime);
+ }
+
+ if (new_version ||
+ (new_issued & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR))) {
+ ci->i_layout = info->layout;
+ queue_trunc = ceph_fill_file_size(inode, issued,
+ le32_to_cpu(info->truncate_seq),
+ le64_to_cpu(info->truncate_size),
+ le64_to_cpu(info->size));
+ /* only update max_size on auth cap */
+ if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
+ ci->i_max_size != le64_to_cpu(info->max_size)) {
+ dout("max_size %lld -> %llu\n", ci->i_max_size,
+ le64_to_cpu(info->max_size));
+ ci->i_max_size = le64_to_cpu(info->max_size);
+ }
+ }
/* xattrs */
/* note that if i_xattrs.len <= 4, i_xattrs.data will still be NULL. */
@@ -745,58 +847,6 @@ static int fill_inode(struct inode *inode,
dout(" marking %p complete (empty)\n", inode);
__ceph_dir_set_complete(ci, atomic_read(&ci->i_release_count));
}
-no_change:
- /* only update max_size on auth cap */
- if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
- ci->i_max_size != le64_to_cpu(info->max_size)) {
- dout("max_size %lld -> %llu\n", ci->i_max_size,
- le64_to_cpu(info->max_size));
- ci->i_max_size = le64_to_cpu(info->max_size);
- }
-
- spin_unlock(&ci->i_ceph_lock);
-
- /* queue truncate if we saw i_size decrease */
- if (queue_trunc)
- ceph_queue_vmtruncate(inode);
-
- /* populate frag tree */
- /* FIXME: move me up, if/when version reflects fragtree changes */
- nsplits = le32_to_cpu(info->fragtree.nsplits);
- mutex_lock(&ci->i_fragtree_mutex);
- rb_node = rb_first(&ci->i_fragtree);
- for (i = 0; i < nsplits; i++) {
- u32 id = le32_to_cpu(info->fragtree.splits[i].frag);
- frag = NULL;
- while (rb_node) {
- frag = rb_entry(rb_node, struct ceph_inode_frag, node);
- if (ceph_frag_compare(frag->frag, id) >= 0) {
- if (frag->frag != id)
- frag = NULL;
- else
- rb_node = rb_next(rb_node);
- break;
- }
- rb_node = rb_next(rb_node);
- rb_erase(&frag->node, &ci->i_fragtree);
- kfree(frag);
- frag = NULL;
- }
- if (!frag) {
- frag = __get_or_create_frag(ci, id);
- if (IS_ERR(frag))
- continue;
- }
- frag->split_by = le32_to_cpu(info->fragtree.splits[i].by);
- dout(" frag %x split by %d\n", frag->frag, frag->split_by);
- }
- while (rb_node) {
- frag = rb_entry(rb_node, struct ceph_inode_frag, node);
- rb_node = rb_next(rb_node);
- rb_erase(&frag->node, &ci->i_fragtree);
- kfree(frag);
- }
- mutex_unlock(&ci->i_fragtree_mutex);
/* were we issued a capability? */
if (info->cap.caps) {
@@ -809,30 +859,41 @@ no_change:
le32_to_cpu(info->cap.seq),
le32_to_cpu(info->cap.mseq),
le64_to_cpu(info->cap.realm),
- info->cap.flags,
- caps_reservation);
+ info->cap.flags, &new_cap);
+ wake = true;
} else {
- spin_lock(&ci->i_ceph_lock);
dout(" %p got snap_caps %s\n", inode,
ceph_cap_string(le32_to_cpu(info->cap.caps)));
ci->i_snap_caps |= le32_to_cpu(info->cap.caps);
if (cap_fmode >= 0)
__ceph_get_fmode(ci, cap_fmode);
- spin_unlock(&ci->i_ceph_lock);
}
} else if (cap_fmode >= 0) {
- pr_warning("mds issued no caps on %llx.%llx\n",
+ pr_warn("mds issued no caps on %llx.%llx\n",
ceph_vinop(inode));
__ceph_get_fmode(ci, cap_fmode);
}
+ spin_unlock(&ci->i_ceph_lock);
+
+ if (wake)
+ wake_up_all(&ci->i_cap_wq);
+
+ /* queue truncate if we saw i_size decrease */
+ if (queue_trunc)
+ ceph_queue_vmtruncate(inode);
+
+ /* populate frag tree */
+ if (S_ISDIR(inode->i_mode))
+ ceph_fill_fragtree(inode, &info->fragtree, dirinfo);
/* update delegation info? */
if (dirinfo)
ceph_fill_dirfrag(inode, dirinfo);
err = 0;
-
out:
+ if (new_cap)
+ ceph_put_cap(mdsc, new_cap);
if (xattr_blob)
ceph_buffer_put(xattr_blob);
return err;
@@ -1485,7 +1546,7 @@ static void ceph_invalidate_work(struct work_struct *work)
orig_gen = ci->i_rdcache_gen;
spin_unlock(&ci->i_ceph_lock);
- truncate_inode_pages(inode->i_mapping, 0);
+ truncate_pagecache(inode, 0);
spin_lock(&ci->i_ceph_lock);
if (orig_gen == ci->i_rdcache_gen &&
@@ -1588,7 +1649,7 @@ retry:
ci->i_truncate_pending, to);
spin_unlock(&ci->i_ceph_lock);
- truncate_inode_pages(inode->i_mapping, to);
+ truncate_pagecache(inode, to);
spin_lock(&ci->i_ceph_lock);
if (to == ci->i_truncate_size) {
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index 191398852a2..fbc39c47bac 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -53,10 +53,7 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
else
length = fl->fl_end - fl->fl_start + 1;
- if (lock_type == CEPH_LOCK_FCNTL)
- owner = secure_addr(fl->fl_owner);
- else
- owner = secure_addr(fl->fl_file);
+ owner = secure_addr(fl->fl_owner);
dout("ceph_lock_message: rule: %d, op: %d, owner: %llx, pid: %llu, "
"start: %llu, length: %llu, wait: %d, type: %d", (int)lock_type,
@@ -314,10 +311,7 @@ int lock_to_ceph_filelock(struct file_lock *lock,
cephlock->length = cpu_to_le64(lock->fl_end - lock->fl_start + 1);
cephlock->client = cpu_to_le64(0);
cephlock->pid = cpu_to_le64((u64)lock->fl_pid);
- if (lock->fl_flags & FL_POSIX)
- cephlock->owner = cpu_to_le64(secure_addr(lock->fl_owner));
- else
- cephlock->owner = cpu_to_le64(secure_addr(lock->fl_file));
+ cephlock->owner = cpu_to_le64(secure_addr(lock->fl_owner));
switch (lock->fl_type) {
case F_RDLCK:
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 2b4d093d056..92a2548278f 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1558,6 +1558,8 @@ ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode)
init_completion(&req->r_safe_completion);
INIT_LIST_HEAD(&req->r_unsafe_item);
+ req->r_stamp = CURRENT_TIME;
+
req->r_op = op;
req->r_direct_mode = mode;
return req;
@@ -1783,7 +1785,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
}
len = sizeof(*head) +
- pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64));
+ pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)) +
+ sizeof(struct timespec);
/* calculate (max) length for cap releases */
len += sizeof(struct ceph_mds_request_release) *
@@ -1800,6 +1803,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
goto out_free2;
}
+ msg->hdr.version = 2;
msg->hdr.tid = cpu_to_le64(req->r_tid);
head = msg->front.iov_base;
@@ -1836,6 +1840,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
mds, req->r_old_inode_drop, req->r_old_inode_unless, 0);
head->num_releases = cpu_to_le16(releases);
+ /* time stamp */
+ ceph_encode_copy(&p, &req->r_stamp, sizeof(req->r_stamp));
+
BUG_ON(p > end);
msg->front.iov_len = p - msg->front.iov_base;
msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
@@ -2218,13 +2225,13 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
/* dup? */
if ((req->r_got_unsafe && !head->safe) ||
(req->r_got_safe && head->safe)) {
- pr_warning("got a dup %s reply on %llu from mds%d\n",
+ pr_warn("got a dup %s reply on %llu from mds%d\n",
head->safe ? "safe" : "unsafe", tid, mds);
mutex_unlock(&mdsc->mutex);
goto out;
}
if (req->r_got_safe && !head->safe) {
- pr_warning("got unsafe after safe on %llu from mds%d\n",
+ pr_warn("got unsafe after safe on %llu from mds%d\n",
tid, mds);
mutex_unlock(&mdsc->mutex);
goto out;
@@ -3525,7 +3532,7 @@ static void peer_reset(struct ceph_connection *con)
struct ceph_mds_session *s = con->private;
struct ceph_mds_client *mdsc = s->s_mdsc;
- pr_warning("mds%d closed our session\n", s->s_mds);
+ pr_warn("mds%d closed our session\n", s->s_mds);
send_mds_reconnect(mdsc, s);
}
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index e90cfccf93b..e00737cf523 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -194,6 +194,7 @@ struct ceph_mds_request {
int r_fmode; /* file mode, if expecting cap */
kuid_t r_uid;
kgid_t r_gid;
+ struct timespec r_stamp;
/* for choosing which mds to send this request to */
int r_direct_mode;
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 132b64eeecd..261531e55e9 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -62,7 +62,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
ceph_decode_16_safe(p, end, version, bad);
if (version > 3) {
- pr_warning("got mdsmap version %d > 3, failing", version);
+ pr_warn("got mdsmap version %d > 3, failing", version);
goto bad;
}
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index ead05cc1f44..12b20744e38 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -292,7 +292,6 @@ struct ceph_inode_info {
struct ceph_snap_context *i_head_snapc; /* set if wr_buffer_head > 0 or
dirty|flushing caps */
unsigned i_snap_caps; /* cap bits for snapped files */
- unsigned i_cap_exporting_issued;
int i_nr_by_mode[CEPH_FILE_MODE_NUM]; /* open file counts */
@@ -775,11 +774,13 @@ static inline void ceph_forget_all_cached_acls(struct inode *inode)
extern const char *ceph_cap_string(int c);
extern void ceph_handle_caps(struct ceph_mds_session *session,
struct ceph_msg *msg);
-extern int ceph_add_cap(struct inode *inode,
- struct ceph_mds_session *session, u64 cap_id,
- int fmode, unsigned issued, unsigned wanted,
- unsigned cap, unsigned seq, u64 realmino, int flags,
- struct ceph_cap_reservation *caps_reservation);
+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 cap, unsigned seq, u64 realmino, int flags,
+ struct ceph_cap **new_cap);
extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release);
extern void ceph_put_cap(struct ceph_mds_client *mdsc,
struct ceph_cap *cap);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-06-03 01:04:10 +0000