summaryrefslogtreecommitdiff
path: root/fs/ceph/file.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-08-11 22:41:07 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2022-08-11 22:41:07 +0300
commit786da5da5671c2d4cf812fe1ccc980bdde30c69e (patch)
tree7fa5659b8f44f798610bc64ef12c2dbb3ef3c648 /fs/ceph/file.c
parente18a90427c4ef26e9208a8710b7d10eaf02bed48 (diff)
parenta8af0d682ae0c9cf62dd0ad6afdb1480951d6a10 (diff)
downloadlinux-786da5da5671c2d4cf812fe1ccc980bdde30c69e.tar.xz
Merge tag 'ceph-for-5.20-rc1' of https://github.com/ceph/ceph-client
Pull ceph updates from Ilya Dryomov: "We have a good pile of various fixes and cleanups from Xiubo, Jeff, Luis and others, almost exclusively in the filesystem. Several patches touch files outside of our normal purview to set the stage for bringing in Jeff's long awaited ceph+fscrypt series in the near future. All of them have appropriate acks and sat in linux-next for a while" * tag 'ceph-for-5.20-rc1' of https://github.com/ceph/ceph-client: (27 commits) libceph: clean up ceph_osdc_start_request prototype libceph: fix ceph_pagelist_reserve() comment typo ceph: remove useless check for the folio ceph: don't truncate file in atomic_open ceph: make f_bsize always equal to f_frsize ceph: flush the dirty caps immediatelly when quota is approaching libceph: print fsid and epoch with osd id libceph: check pointer before assigned to "c->rules[]" ceph: don't get the inline data for new creating files ceph: update the auth cap when the async create req is forwarded ceph: make change_auth_cap_ses a global symbol ceph: fix incorrect old_size length in ceph_mds_request_args ceph: switch back to testing for NULL folio->private in ceph_dirty_folio ceph: call netfs_subreq_terminated with was_async == false ceph: convert to generic_file_llseek ceph: fix the incorrect comment for the ceph_mds_caps struct ceph: don't leak snap_rwsem in handle_cap_grant ceph: prevent a client from exceeding the MDS maximum xattr size ceph: choose auth MDS for getxattr with the Xs caps ceph: add session already open notify support ...
Diffstat (limited to 'fs/ceph/file.c')
-rw-r--r--fs/ceph/file.c123
1 files changed, 48 insertions, 75 deletions
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 284d2fda663d..04fd34557de8 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -240,8 +240,7 @@ static int ceph_init_file_info(struct inode *inode, struct file *file,
INIT_LIST_HEAD(&fi->rw_contexts);
fi->filp_gen = READ_ONCE(ceph_inode_to_client(inode)->filp_gen);
- if ((file->f_mode & FMODE_WRITE) &&
- ci->i_inline_version != CEPH_INLINE_NONE) {
+ if ((file->f_mode & FMODE_WRITE) && ceph_has_inline_data(ci)) {
ret = ceph_uninline_data(file);
if (ret < 0)
goto error;
@@ -568,7 +567,7 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc,
char *path = ceph_mdsc_build_path(req->r_dentry, &pathlen,
&base, 0);
- pr_warn("ceph: async create failure path=(%llx)%s result=%d!\n",
+ pr_warn("async create failure path=(%llx)%s result=%d!\n",
base, IS_ERR(path) ? "<<bad>>" : path, result);
ceph_mdsc_free_path(path, pathlen);
@@ -611,6 +610,7 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,
struct ceph_mds_reply_inode in = { };
struct ceph_mds_reply_info_in iinfo = { .in = &in };
struct ceph_inode_info *ci = ceph_inode(dir);
+ struct ceph_dentry_info *di = ceph_dentry(dentry);
struct inode *inode;
struct timespec64 now;
struct ceph_string *pool_ns;
@@ -709,6 +709,12 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,
file->f_mode |= FMODE_CREATED;
ret = finish_open(file, dentry, ceph_open);
}
+
+ spin_lock(&dentry->d_lock);
+ di->flags &= ~CEPH_DENTRY_ASYNC_CREATE;
+ wake_up_bit(&di->flags, CEPH_DENTRY_ASYNC_CREATE_BIT);
+ spin_unlock(&dentry->d_lock);
+
return ret;
}
@@ -735,6 +741,15 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
if (dentry->d_name.len > NAME_MAX)
return -ENAMETOOLONG;
+ err = ceph_wait_on_conflict_unlink(dentry);
+ if (err)
+ return err;
+ /*
+ * Do not truncate the file, since atomic_open is called before the
+ * permission check. The caller will do the truncation afterward.
+ */
+ flags &= ~O_TRUNC;
+
if (flags & O_CREAT) {
if (ceph_quota_is_max_files_exceeded(dir))
return -EDQUOT;
@@ -781,9 +796,16 @@ retry:
(req->r_dir_caps =
try_prep_async_create(dir, dentry, &lo,
&req->r_deleg_ino))) {
+ struct ceph_dentry_info *di = ceph_dentry(dentry);
+
set_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags);
req->r_args.open.flags |= cpu_to_le32(CEPH_O_EXCL);
req->r_callback = ceph_async_create_cb;
+
+ spin_lock(&dentry->d_lock);
+ di->flags |= CEPH_DENTRY_ASYNC_CREATE;
+ spin_unlock(&dentry->d_lock);
+
err = ceph_mdsc_submit_request(mdsc, dir, req);
if (!err) {
err = ceph_finish_async_create(dir, dentry,
@@ -802,9 +824,7 @@ retry:
}
set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
- err = ceph_mdsc_do_request(mdsc,
- (flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
- req);
+ err = ceph_mdsc_do_request(mdsc, (flags & O_CREAT) ? dir : NULL, req);
if (err == -ENOENT) {
dentry = ceph_handle_snapdir(req, dentry);
if (IS_ERR(dentry)) {
@@ -960,9 +980,8 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_off,
false, false);
- ret = ceph_osdc_start_request(osdc, req, false);
- if (!ret)
- ret = ceph_osdc_wait_request(osdc, req);
+ ceph_osdc_start_request(osdc, req);
+ ret = ceph_osdc_wait_request(osdc, req);
ceph_update_read_metrics(&fsc->mdsc->metric,
req->r_start_latency,
@@ -1225,7 +1244,7 @@ static void ceph_aio_retry_work(struct work_struct *work)
req->r_inode = inode;
req->r_priv = aio_req;
- ret = ceph_osdc_start_request(req->r_osdc, req, false);
+ ceph_osdc_start_request(req->r_osdc, req);
out:
if (ret < 0) {
req->r_result = ret;
@@ -1362,9 +1381,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
continue;
}
- ret = ceph_osdc_start_request(req->r_osdc, req, false);
- if (!ret)
- ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
+ ceph_osdc_start_request(req->r_osdc, req);
+ ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
if (write)
ceph_update_write_metrics(metric, req->r_start_latency,
@@ -1427,8 +1445,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
r_private_item);
list_del_init(&req->r_private_item);
if (ret >= 0)
- ret = ceph_osdc_start_request(req->r_osdc,
- req, false);
+ ceph_osdc_start_request(req->r_osdc, req);
if (ret < 0) {
req->r_result = ret;
ceph_aio_complete_req(req);
@@ -1541,9 +1558,8 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
false, true);
req->r_mtime = mtime;
- ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
- if (!ret)
- ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
+ ceph_osdc_start_request(&fsc->client->osdc, req);
+ ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
req->r_end_latency, len, ret);
@@ -1627,7 +1643,7 @@ again:
inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
ceph_cap_string(got));
- if (ci->i_inline_version == CEPH_INLINE_NONE) {
+ if (!ceph_has_inline_data(ci)) {
if (!retry_op && (iocb->ki_flags & IOCB_DIRECT)) {
ret = ceph_direct_read_write(iocb, to,
NULL, NULL);
@@ -1890,7 +1906,7 @@ retry_snap:
if (dirty)
__mark_inode_dirty(inode, dirty);
if (ceph_quota_is_max_bytes_approaching(inode, iocb->ki_pos))
- ceph_check_caps(ci, 0, NULL);
+ ceph_check_caps(ci, CHECK_CAPS_FLUSH, NULL);
}
dout("aio_write %p %llx.%llx %llu~%u dropping cap refs on %s\n",
@@ -1930,57 +1946,15 @@ out_unlocked:
*/
static loff_t ceph_llseek(struct file *file, loff_t offset, int whence)
{
- struct inode *inode = file->f_mapping->host;
- struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
- loff_t i_size;
- loff_t ret;
-
- inode_lock(inode);
-
if (whence == SEEK_END || whence == SEEK_DATA || whence == SEEK_HOLE) {
+ struct inode *inode = file_inode(file);
+ int ret;
+
ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false);
if (ret < 0)
- goto out;
- }
-
- i_size = i_size_read(inode);
- switch (whence) {
- case SEEK_END:
- offset += i_size;
- break;
- case SEEK_CUR:
- /*
- * Here we special-case the lseek(fd, 0, SEEK_CUR)
- * position-querying operation. Avoid rewriting the "same"
- * f_pos value back to the file because a concurrent read(),
- * write() or lseek() might have altered it
- */
- if (offset == 0) {
- ret = file->f_pos;
- goto out;
- }
- offset += file->f_pos;
- break;
- case SEEK_DATA:
- if (offset < 0 || offset >= i_size) {
- ret = -ENXIO;
- goto out;
- }
- break;
- case SEEK_HOLE:
- if (offset < 0 || offset >= i_size) {
- ret = -ENXIO;
- goto out;
- }
- offset = i_size;
- break;
+ return ret;
}
-
- ret = vfs_setpos(file, offset, max(i_size, fsc->max_file_size));
-
-out:
- inode_unlock(inode);
- return ret;
+ return generic_file_llseek(file, offset, whence);
}
static inline void ceph_zero_partial_page(
@@ -2049,12 +2023,10 @@ static int ceph_zero_partial_object(struct inode *inode,
}
req->r_mtime = inode->i_mtime;
- ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
- if (!ret) {
- ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
- if (ret == -ENOENT)
- ret = 0;
- }
+ ceph_osdc_start_request(&fsc->client->osdc, req);
+ ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
+ if (ret == -ENOENT)
+ ret = 0;
ceph_osdc_put_request(req);
out:
@@ -2356,7 +2328,7 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off
if (IS_ERR(req))
ret = PTR_ERR(req);
else {
- ceph_osdc_start_request(osdc, req, false);
+ ceph_osdc_start_request(osdc, req);
ret = ceph_osdc_wait_request(osdc, req);
ceph_update_copyfrom_metrics(&fsc->mdsc->metric,
req->r_start_latency,
@@ -2549,7 +2521,8 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
/* Let the MDS know about dst file size change */
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);
+ ceph_check_caps(dst_ci, CHECK_CAPS_AUTHONLY | CHECK_CAPS_FLUSH,
+ NULL);
}
/* Mark Fw dirty */
spin_lock(&dst_ci->i_ceph_lock);