Skip to content

R
raspberrypi-kernel

openeuler / raspberrypi-kernel

通知 13
Star 1
Fork 0
R
raspberrypi-kernel
提交 91f85756 编写于 作者: L Linus Torvalds
浏览文件
操作

Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client 

Pull Ceph changes from Alex Elder:
 "This is a big pull.

  Most of it is culmination of Alex's work to implement RBD image
  layering, which is now complete (yay!).

  There is also some work from Yan to fix i_mutex behavior surrounding
  writes in cephfs, a sync write fix, a fix for RBD images that get
  resized while they are mapped, and a few patches from me that resolve
  annoying auth warnings and fix several bugs in the ceph auth code."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (254 commits)
  rbd: fix image request leak on parent read
  libceph: use slab cache for osd client requests
  libceph: allocate ceph message data with a slab allocator
  libceph: allocate ceph messages with a slab allocator
  rbd: allocate image object names with a slab allocator
  rbd: allocate object requests with a slab allocator
  rbd: allocate name separate from obj_request
  rbd: allocate image requests with a slab allocator
  rbd: use binary search for snapshot lookup
  rbd: clear EXISTS flag if mapped snapshot disappears
  rbd: kill off the snapshot list
  rbd: define rbd_snap_size() and rbd_snap_features()
  rbd: use snap_id not index to look up snap info
  rbd: look up snapshot name in names buffer
  rbd: drop obj_request->version
  rbd: drop rbd_obj_method_sync() version parameter
  rbd: more version parameter removal
  rbd: get rid of some version parameters
  rbd: stop tracking header object version
  rbd: snap names are pointer to constant data
  ...
上级 2e378f3e b5b09be3
展开全部 显示空白变更内容
内联 并排
Showing with 4201 addition and 2285 deletion
Documentation/ABI/testing/sysfs-bus-rbd
浏览文件 @ 91f85756
......@@ -66,27 +66,7 @@ current_snap
The current snapshot for which the device is mapped.
snap_*
A directory per each snapshot
parent
Information identifying the pool, image, and snapshot id for
the parent image in a layered rbd image (format 2 only).
Entries under /sys/bus/rbd/devices/<dev-id>/snap_<snap-name>
-------------------------------------------------------------
snap_id
The rados internal snapshot id assigned for this snapshot
snap_size
The size of the image when this snapshot was taken.
snap_features
A hexadecimal encoding of the feature bits for this snapshot.
drivers/block/rbd.c
浏览文件 @ 91f85756
此差异已折叠。
fs/ceph/addr.c
浏览文件 @ 91f85756
......@@ -236,15 +236,21 @@ static int ceph_readpage(struct file *filp, struct page *page)
static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg)
{
struct inode *inode = req->r_inode;
struct ceph_osd_data *osd_data;
int rc = req->r_result;
int bytes = le32_to_cpu(msg->hdr.data_len);
int num_pages;
int i;
dout("finish_read %p req %p rc %d bytes %d\n", inode, req, rc, bytes);
/* unlock all pages, zeroing any data we didn't read */
for (i = 0; i < req->r_num_pages; i++, bytes -= PAGE_CACHE_SIZE) {
struct page *page = req->r_pages[i];
osd_data = osd_req_op_extent_osd_data(req, 0);
BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_PAGES);
num_pages = calc_pages_for((u64)osd_data->alignment,
(u64)osd_data->length);
for (i = 0; i < num_pages; i++) {
struct page *page = osd_data->pages[i];
if (bytes < (int)PAGE_CACHE_SIZE) {
/* zero (remainder of) page */
......@@ -257,8 +263,9 @@ static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg)
SetPageUptodate(page);
unlock_page(page);
page_cache_release(page);
bytes -= PAGE_CACHE_SIZE;
}
kfree(req->r_pages);
kfree(osd_data->pages);
}
static void ceph_unlock_page_vector(struct page **pages, int num_pages)
......@@ -279,6 +286,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
&ceph_inode_to_client(inode)->client->osdc;
struct ceph_inode_info *ci = ceph_inode(inode);
struct page *page = list_entry(page_list->prev, struct page, lru);
struct ceph_vino vino;
struct ceph_osd_request *req;
u64 off;
u64 len;
......@@ -303,18 +311,17 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
len = nr_pages << PAGE_CACHE_SHIFT;
dout("start_read %p nr_pages %d is %lld~%lld\n", inode, nr_pages,
off, len);
req = ceph_osdc_new_request(osdc, &ci->i_layout, ceph_vino(inode),
off, &len,
CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
NULL, 0,
vino = ceph_vino(inode);
req = ceph_osdc_new_request(osdc, &ci->i_layout, vino, off, &len,
1, CEPH_OSD_OP_READ,
CEPH_OSD_FLAG_READ, NULL,
ci->i_truncate_seq, ci->i_truncate_size,
NULL, false, 0);
false);
if (IS_ERR(req))
return PTR_ERR(req);
/* build page vector */
nr_pages = len >> PAGE_CACHE_SHIFT;
nr_pages = calc_pages_for(0, len);
pages = kmalloc(sizeof(*pages) * nr_pages, GFP_NOFS);
ret = -ENOMEM;
if (!pages)
......@@ -336,11 +343,12 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
}
pages[i] = page;
}
req->r_pages = pages;
req->r_num_pages = nr_pages;
osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, false, false);
req->r_callback = finish_read;
req->r_inode = inode;
ceph_osdc_build_request(req, off, NULL, vino.snap, NULL);
dout("start_read %p starting %p %lld~%lld\n", inode, req, off, len);
ret = ceph_osdc_start_request(osdc, req, false);
if (ret < 0)
......@@ -373,7 +381,8 @@ static int ceph_readpages(struct file *file, struct address_space *mapping,
max = (fsc->mount_options->rsize + PAGE_CACHE_SIZE - 1)
>> PAGE_SHIFT;
dout("readpages %p file %p nr_pages %d max %d\n", inode, file, nr_pages,
dout("readpages %p file %p nr_pages %d max %d\n", inode,
file, nr_pages,
max);
while (!list_empty(page_list)) {
rc = start_read(inode, page_list, max);
......@@ -548,17 +557,23 @@ static void writepages_finish(struct ceph_osd_request *req,
{
struct inode *inode = req->r_inode;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_osd_data *osd_data;
unsigned wrote;
struct page *page;
int num_pages;
int i;
struct ceph_snap_context *snapc = req->r_snapc;
struct address_space *mapping = inode->i_mapping;
int rc = req->r_result;
u64 bytes = le64_to_cpu(req->r_request_ops[0].extent.length);
u64 bytes = req->r_ops[0].extent.length;
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
long writeback_stat;
unsigned issued = ceph_caps_issued(ci);
osd_data = osd_req_op_extent_osd_data(req, 0);
BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_PAGES);
num_pages = calc_pages_for((u64)osd_data->alignment,
(u64)osd_data->length);
if (rc >= 0) {
/*
* Assume we wrote the pages we originally sent. The
......@@ -566,7 +581,7 @@ static void writepages_finish(struct ceph_osd_request *req,
* raced with a truncation and was adjusted at the osd,
* so don't believe the reply.
*/
wrote = req->r_num_pages;
wrote = num_pages;
} else {
wrote = 0;
mapping_set_error(mapping, rc);
......@@ -575,8 +590,8 @@ static void writepages_finish(struct ceph_osd_request *req,
inode, rc, bytes, wrote);
/* clean all pages */
for (i = 0; i < req->r_num_pages; i++) {
page = req->r_pages[i];
for (i = 0; i < num_pages; i++) {
page = osd_data->pages[i];
BUG_ON(!page);
WARN_ON(!PageUptodate(page));
......@@ -605,32 +620,34 @@ static void writepages_finish(struct ceph_osd_request *req,
unlock_page(page);
}
dout("%p wrote+cleaned %d pages\n", inode, wrote);
ceph_put_wrbuffer_cap_refs(ci, req->r_num_pages, snapc);
ceph_put_wrbuffer_cap_refs(ci, num_pages, snapc);
ceph_release_pages(req->r_pages, req->r_num_pages);
if (req->r_pages_from_pool)
mempool_free(req->r_pages,
ceph_release_pages(osd_data->pages, num_pages);
if (osd_data->pages_from_pool)
mempool_free(osd_data->pages,
ceph_sb_to_client(inode->i_sb)->wb_pagevec_pool);
else
kfree(req->r_pages);
kfree(osd_data->pages);
ceph_osdc_put_request(req);
}
/*
* allocate a page vec, either directly, or if necessary, via a the
* mempool. we avoid the mempool if we can because req->r_num_pages
* may be less than the maximum write size.
*/
static void alloc_page_vec(struct ceph_fs_client *fsc,
struct ceph_osd_request *req)
static struct ceph_osd_request *
ceph_writepages_osd_request(struct inode *inode, u64 offset, u64 *len,
struct ceph_snap_context *snapc, int num_ops)
{
req->r_pages = kmalloc(sizeof(struct page *) * req->r_num_pages,
GFP_NOFS);
if (!req->r_pages) {
req->r_pages = mempool_alloc(fsc->wb_pagevec_pool, GFP_NOFS);
req->r_pages_from_pool = 1;
WARN_ON(!req->r_pages);
}
struct ceph_fs_client *fsc;
struct ceph_inode_info *ci;
struct ceph_vino vino;
fsc = ceph_inode_to_client(inode);
ci = ceph_inode(inode);
vino = ceph_vino(inode);
/* BUG_ON(vino.snap != CEPH_NOSNAP); */
return ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
vino, offset, len, num_ops, CEPH_OSD_OP_WRITE,
CEPH_OSD_FLAG_WRITE|CEPH_OSD_FLAG_ONDISK,
snapc, ci->i_truncate_seq, ci->i_truncate_size, true);
}
/*
......@@ -653,7 +670,7 @@ static int ceph_writepages_start(struct address_space *mapping,
unsigned wsize = 1 << inode->i_blkbits;
struct ceph_osd_request *req = NULL;
int do_sync;
u64 snap_size = 0;
u64 snap_size;
/*
* Include a 'sync' in the OSD request if this is a data
......@@ -699,6 +716,7 @@ static int ceph_writepages_start(struct address_space *mapping,
retry:
/* find oldest snap context with dirty data */
ceph_put_snap_context(snapc);
snap_size = 0;
snapc = get_oldest_context(inode, &snap_size);
if (!snapc) {
/* hmm, why does writepages get called when there
......@@ -706,6 +724,8 @@ static int ceph_writepages_start(struct address_space *mapping,
dout(" no snap context with dirty data?\n");
goto out;
}
if (snap_size == 0)
snap_size = i_size_read(inode);
dout(" oldest snapc is %p seq %lld (%d snaps)\n",
snapc, snapc->seq, snapc->num_snaps);
if (last_snapc && snapc != last_snapc) {
......@@ -718,10 +738,14 @@ static int ceph_writepages_start(struct address_space *mapping,
last_snapc = snapc;
while (!done && index <= end) {
int num_ops = do_sync ? 2 : 1;
struct ceph_vino vino;
unsigned i;
int first;
pgoff_t next;
int pvec_pages, locked_pages;
struct page **pages = NULL;
mempool_t *pool = NULL; /* Becomes non-null if mempool used */
struct page *page;
int want;
u64 offset, len;
......@@ -773,11 +797,8 @@ static int ceph_writepages_start(struct address_space *mapping,
dout("waiting on writeback %p\n", page);
wait_on_page_writeback(page);
}
if ((snap_size && page_offset(page) > snap_size) ||
(!snap_size &&
page_offset(page) > i_size_read(inode))) {
dout("%p page eof %llu\n", page, snap_size ?
snap_size : i_size_read(inode));
if (page_offset(page) >= snap_size) {
dout("%p page eof %llu\n", page, snap_size);
done = 1;
unlock_page(page);
break;
......@@ -805,22 +826,23 @@ static int ceph_writepages_start(struct address_space *mapping,
break;
}
/* ok */
/*
* We have something to write. If this is
* the first locked page this time through,
* allocate an osd request and a page array
* that it will use.
*/
if (locked_pages == 0) {
size_t size;
BUG_ON(pages);
/* prepare async write request */
offset = (u64) page_offset(page);
offset = (u64)page_offset(page);
len = wsize;
req = ceph_osdc_new_request(&fsc->client->osdc,
&ci->i_layout,
ceph_vino(inode),
offset, &len,
CEPH_OSD_OP_WRITE,
CEPH_OSD_FLAG_WRITE |
CEPH_OSD_FLAG_ONDISK,
snapc, do_sync,
ci->i_truncate_seq,
ci->i_truncate_size,
&inode->i_mtime, true, 0);
req = ceph_writepages_osd_request(inode,
offset, &len, snapc,
num_ops);
if (IS_ERR(req)) {
rc = PTR_ERR(req);
......@@ -828,11 +850,17 @@ static int ceph_writepages_start(struct address_space *mapping,
break;
}
max_pages = req->r_num_pages;
alloc_page_vec(fsc, req);
req->r_callback = writepages_finish;
req->r_inode = inode;
max_pages = calc_pages_for(0, (u64)len);
size = max_pages * sizeof (*pages);
pages = kmalloc(size, GFP_NOFS);
if (!pages) {
pool = fsc->wb_pagevec_pool;
pages = mempool_alloc(pool, GFP_NOFS);
BUG_ON(!pages);
}
}
/* note position of first page in pvec */
......@@ -850,7 +878,7 @@ static int ceph_writepages_start(struct address_space *mapping,
}
set_page_writeback(page);
req->r_pages[locked_pages] = page;
pages[locked_pages] = page;
locked_pages++;
next = page->index + 1;
}
......@@ -879,18 +907,27 @@ static int ceph_writepages_start(struct address_space *mapping,
pvec.nr -= i-first;
}
/* submit the write */
offset = req->r_pages[0]->index << PAGE_CACHE_SHIFT;
len = min((snap_size ? snap_size : i_size_read(inode)) - offset,
/* Format the osd request message and submit the write */
offset = page_offset(pages[0]);
len = min(snap_size - offset,
(u64)locked_pages << PAGE_CACHE_SHIFT);
dout("writepages got %d pages at %llu~%llu\n",
locked_pages, offset, len);
/* revise final length, page count */
req->r_num_pages = locked_pages;
req->r_request_ops[0].extent.length = cpu_to_le64(len);
req->r_request_ops[0].payload_len = cpu_to_le32(len);
req->r_request->hdr.data_len = cpu_to_le32(len);
osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0,
!!pool, false);
pages = NULL; /* request message now owns the pages array */
pool = NULL;
/* Update the write op length in case we changed it */
osd_req_op_extent_update(req, 0, len);
vino = ceph_vino(inode);
ceph_osdc_build_request(req, offset, snapc, vino.snap,
&inode->i_mtime);
rc = ceph_osdc_start_request(&fsc->client->osdc, req, true);
BUG_ON(rc);
......@@ -1067,51 +1104,23 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping,
struct page **pagep, void **fsdata)
{
struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_file_info *fi = file->private_data;
struct page *page;
pgoff_t index = pos >> PAGE_CACHE_SHIFT;
int r, want, got = 0;
if (fi->fmode & CEPH_FILE_MODE_LAZY)
want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
else
want = CEPH_CAP_FILE_BUFFER;
dout("write_begin %p %llx.%llx %llu~%u getting caps. i_size %llu\n",
inode, ceph_vinop(inode), pos, len, inode->i_size);
r = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, &got, pos+len);
if (r < 0)
return r;
dout("write_begin %p %llx.%llx %llu~%u got cap refs on %s\n",
inode, ceph_vinop(inode), pos, len, ceph_cap_string(got));
if (!(got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO))) {
ceph_put_cap_refs(ci, got);
return -EAGAIN;
}
int r;
do {
/* get a page */
page = grab_cache_page_write_begin(mapping, index, 0);
if (!page) {
r = -ENOMEM;
break;
}
if (!page)
return -ENOMEM;
*pagep = page;
dout("write_begin file %p inode %p page %p %d~%d\n", file,
inode, page, (int)pos, (int)len);
r = ceph_update_writeable_page(file, pos, len, page);
if (r)
page_cache_release(page);
} while (r == -EAGAIN);
if (r) {
ceph_put_cap_refs(ci, got);
} else {
*pagep = page;
*(int *)fsdata = got;
}
return r;
}
......@@ -1125,12 +1134,10 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
struct page *page, void *fsdata)
{
struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_mds_client *mdsc = fsc->mdsc;
unsigned from = pos & (PAGE_CACHE_SIZE - 1);
int check_cap = 0;
int got = (unsigned long)fsdata;
dout("write_end file %p inode %p page %p %d~%d (%d)\n", file,
inode, page, (int)pos, (int)copied, (int)len);
......@@ -1153,19 +1160,6 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
up_read(&mdsc->snap_rwsem);
page_cache_release(page);
if (copied > 0) {
int dirty;
spin_lock(&ci->i_ceph_lock);
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
spin_unlock(&ci->i_ceph_lock);
if (dirty)
__mark_inode_dirty(inode, dirty);
}
dout("write_end %p %llx.%llx %llu~%u dropping cap refs on %s\n",
inode, ceph_vinop(inode), pos, len, ceph_cap_string(got));
ceph_put_cap_refs(ci, got);
if (check_cap)
ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY, NULL);
......
fs/ceph/caps.c
浏览文件 @ 91f85756
......@@ -490,15 +490,17 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
ci->i_rdcache_gen++;
/*
* if we are newly issued FILE_SHARED, clear D_COMPLETE; we
* if we are newly issued FILE_SHARED, mark dir not complete; we
* don't know what happened to this directory while we didn't
* have the cap.
*/
if ((issued & CEPH_CAP_FILE_SHARED) &&
(had & CEPH_CAP_FILE_SHARED) == 0) {
ci->i_shared_gen++;
if (S_ISDIR(ci->vfs_inode.i_mode))
ceph_dir_clear_complete(&ci->vfs_inode);
if (S_ISDIR(ci->vfs_inode.i_mode)) {
dout(" marking %p NOT complete\n", &ci->vfs_inode);
__ceph_dir_clear_complete(ci);
}
}
}
......@@ -553,6 +555,7 @@ int ceph_add_cap(struct inode *inode,
cap->implemented = 0;
cap->mds = mds;
cap->mds_wanted = 0;
cap->mseq = 0;
cap->ci = ci;
__insert_cap_node(ci, cap);
......@@ -628,6 +631,9 @@ int ceph_add_cap(struct inode *inode,
cap->cap_id = cap_id;
cap->issued = issued;
cap->implemented |= issued;
if (mseq > cap->mseq)
cap->mds_wanted = wanted;
else
cap->mds_wanted |= wanted;
cap->seq = seq;
cap->issue_seq = seq;
......@@ -997,7 +1003,7 @@ static int send_cap_msg(struct ceph_mds_session *session,
return 0;
}
static void __queue_cap_release(struct ceph_mds_session *session,
void __queue_cap_release(struct ceph_mds_session *session,
u64 ino, u64 cap_id, u32 migrate_seq,
u32 issue_seq)
{
......@@ -2046,6 +2052,13 @@ static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want,
goto out;
}
/* finish pending truncate */
while (ci->i_truncate_pending) {
spin_unlock(&ci->i_ceph_lock);
__ceph_do_pending_vmtruncate(inode, !(need & CEPH_CAP_FILE_WR));
spin_lock(&ci->i_ceph_lock);
}
if (need & CEPH_CAP_FILE_WR) {
if (endoff >= 0 && endoff > (loff_t)ci->i_max_size) {
dout("get_cap_refs %p endoff %llu > maxsize %llu\n",
......@@ -2067,12 +2080,6 @@ static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want,
}
have = __ceph_caps_issued(ci, &implemented);
/*
* disallow writes while a truncate is pending
*/
if (ci->i_truncate_pending)
have &= ~CEPH_CAP_FILE_WR;
if ((have & need) == need) {
/*
* Look at (implemented & ~have & not) so that we keep waiting
......
fs/ceph/dir.c
浏览文件 @ 91f85756
......@@ -107,7 +107,7 @@ static unsigned fpos_off(loff_t p)
* falling back to a "normal" sync readdir if any dentries in the dir
* are dropped.
*
* D_COMPLETE tells indicates we have all dentries in the dir. It is
* Complete dir indicates that we have all dentries in the dir. It is
* defined IFF we hold CEPH_CAP_FILE_SHARED (which will be revoked by
* the MDS if/when the directory is modified).
*/
......@@ -198,8 +198,8 @@ static int __dcache_readdir(struct file *filp,
filp->f_pos++;
/* make sure a dentry wasn't dropped while we didn't have parent lock */
if (!ceph_dir_test_complete(dir)) {
dout(" lost D_COMPLETE on %p; falling back to mds\n", dir);
if (!ceph_dir_is_complete(dir)) {
dout(" lost dir complete on %p; falling back to mds\n", dir);
err = -EAGAIN;
goto out;
}
......@@ -258,7 +258,7 @@ static int ceph_readdir(struct file *filp, void *dirent, filldir_t filldir)
if (filp->f_pos == 0) {
/* note dir version at start of readdir so we can tell
* if any dentries get dropped */
fi->dir_release_count = ci->i_release_count;
fi->dir_release_count = atomic_read(&ci->i_release_count);
dout("readdir off 0 -> '.'\n");
if (filldir(dirent, ".", 1, ceph_make_fpos(0, 0),
......@@ -284,7 +284,7 @@ static int ceph_readdir(struct file *filp, void *dirent, filldir_t filldir)
if ((filp->f_pos == 2 || fi->dentry) &&
!ceph_test_mount_opt(fsc, NOASYNCREADDIR) &&
ceph_snap(inode) != CEPH_SNAPDIR &&
ceph_dir_test_complete(inode) &&
__ceph_dir_is_complete(ci) &&
__ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1)) {
spin_unlock(&ci->i_ceph_lock);
err = __dcache_readdir(filp, dirent, filldir);
......@@ -350,7 +350,8 @@ static int ceph_readdir(struct file *filp, void *dirent, filldir_t filldir)
if (!req->r_did_prepopulate) {
dout("readdir !did_prepopulate");
fi->dir_release_count--; /* preclude D_COMPLETE */
/* preclude from marking dir complete */
fi->dir_release_count--;
}
/* note next offset and last dentry name */
......@@ -428,8 +429,9 @@ static int ceph_readdir(struct file *filp, void *dirent, filldir_t filldir)
* the complete dir contents in our cache.
*/
spin_lock(&ci->i_ceph_lock);
if (ci->i_release_count == fi->dir_release_count) {
ceph_dir_set_complete(inode);
if (atomic_read(&ci->i_release_count) == fi->dir_release_count) {
dout(" marking %p complete\n", inode);
__ceph_dir_set_complete(ci, fi->dir_release_count);
ci->i_max_offset = filp->f_pos;
}
spin_unlock(&ci->i_ceph_lock);
......@@ -604,7 +606,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
fsc->mount_options->snapdir_name,
dentry->d_name.len) &&
!is_root_ceph_dentry(dir, dentry) &&
ceph_dir_test_complete(dir) &&
__ceph_dir_is_complete(ci) &&
(__ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1))) {
spin_unlock(&ci->i_ceph_lock);
dout(" dir %p complete, -ENOENT\n", dir);
......@@ -1064,44 +1066,6 @@ static int ceph_snapdir_d_revalidate(struct dentry *dentry,
return 1;
}
/*
* Set/clear/test dir complete flag on the dir's dentry.
*/
void ceph_dir_set_complete(struct inode *inode)
{
struct dentry *dentry = d_find_any_alias(inode);
if (dentry && ceph_dentry(dentry) &&
ceph_test_mount_opt(ceph_sb_to_client(dentry->d_sb), DCACHE)) {
dout(" marking %p (%p) complete\n", inode, dentry);
set_bit(CEPH_D_COMPLETE, &ceph_dentry(dentry)->flags);
}
dput(dentry);
}
void ceph_dir_clear_complete(struct inode *inode)
{
struct dentry *dentry = d_find_any_alias(inode);
if (dentry && ceph_dentry(dentry)) {
dout(" marking %p (%p) complete\n", inode, dentry);
set_bit(CEPH_D_COMPLETE, &ceph_dentry(dentry)->flags);
}
dput(dentry);
}
bool ceph_dir_test_complete(struct inode *inode)
{
struct dentry *dentry = d_find_any_alias(inode);
if (dentry && ceph_dentry(dentry)) {
dout(" marking %p (%p) NOT complete\n", inode, dentry);
clear_bit(CEPH_D_COMPLETE, &ceph_dentry(dentry)->flags);
}
dput(dentry);
return false;
}
/*
* When the VFS prunes a dentry from the cache, we need to clear the
* complete flag on the parent directory.
......@@ -1110,15 +1074,13 @@ bool ceph_dir_test_complete(struct inode *inode)
*/
static void ceph_d_prune(struct dentry *dentry)
{
struct ceph_dentry_info *di;
dout("ceph_d_prune %p\n", dentry);
/* do we have a valid parent? */
if (IS_ROOT(dentry))
return;
/* if we are not hashed, we don't affect D_COMPLETE */
/* if we are not hashed, we don't affect dir's completeness */
if (d_unhashed(dentry))
return;
......@@ -1126,8 +1088,7 @@ static void ceph_d_prune(struct dentry *dentry)
* we hold d_lock, so d_parent is stable, and d_fsdata is never
* cleared until d_release
*/
di = ceph_dentry(dentry->d_parent);
clear_bit(CEPH_D_COMPLETE, &di->flags);
ceph_dir_clear_complete(dentry->d_parent->d_inode);
}
/*
......
fs/ceph/file.c
浏览文件 @ 91f85756
此差异已折叠。
fs/ceph/inode.c
浏览文件 @ 91f85756
......@@ -302,7 +302,8 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
ci->i_version = 0;
ci->i_time_warp_seq = 0;
ci->i_ceph_flags = 0;
ci->i_release_count = 0;
atomic_set(&ci->i_release_count, 1);
atomic_set(&ci->i_complete_count, 0);
ci->i_symlink = NULL;
memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout));
......@@ -561,7 +562,6 @@ static int fill_inode(struct inode *inode,
struct ceph_inode_info *ci = ceph_inode(inode);
int i;
int issued = 0, implemented;
int updating_inode = 0;
struct timespec mtime, atime, ctime;
u32 nsplits;
struct ceph_buffer *xattr_blob = NULL;
......@@ -601,7 +601,6 @@ static int fill_inode(struct inode *inode,
(ci->i_version & ~1) >= le64_to_cpu(info->version))
goto no_change;
updating_inode = 1;
issued = __ceph_caps_issued(ci, &implemented);
issued |= implemented | __ceph_caps_dirty(ci);
......@@ -717,6 +716,17 @@ static int fill_inode(struct inode *inode,
ceph_vinop(inode), inode->i_mode);
}
/* set dir completion flag? */
if (S_ISDIR(inode->i_mode) &&
ci->i_files == 0 && ci->i_subdirs == 0 &&
ceph_snap(inode) == CEPH_NOSNAP &&
(le32_to_cpu(info->cap.caps) & CEPH_CAP_FILE_SHARED) &&
(issued & CEPH_CAP_FILE_EXCL) == 0 &&
!__ceph_dir_is_complete(ci)) {
dout(" marking %p complete (empty)\n", inode);
__ceph_dir_set_complete(ci, atomic_read(&ci->i_release_count));
ci->i_max_offset = 2;
}
no_change:
spin_unlock(&ci->i_ceph_lock);
......@@ -767,19 +777,6 @@ static int fill_inode(struct inode *inode,
__ceph_get_fmode(ci, cap_fmode);
}
/* set dir completion flag? */
if (S_ISDIR(inode->i_mode) &&
updating_inode && /* didn't jump to no_change */
ci->i_files == 0 && ci->i_subdirs == 0 &&
ceph_snap(inode) == CEPH_NOSNAP &&
(le32_to_cpu(info->cap.caps) & CEPH_CAP_FILE_SHARED) &&
(issued & CEPH_CAP_FILE_EXCL) == 0 &&
!ceph_dir_test_complete(inode)) {
dout(" marking %p complete (empty)\n", inode);
ceph_dir_set_complete(inode);
ci->i_max_offset = 2;
}
/* update delegation info? */
if (dirinfo)
ceph_fill_dirfrag(inode, dirinfo);
......@@ -861,7 +858,7 @@ static void ceph_set_dentry_offset(struct dentry *dn)
di = ceph_dentry(dn);
spin_lock(&ci->i_ceph_lock);
if (!ceph_dir_test_complete(inode)) {
if (!__ceph_dir_is_complete(ci)) {
spin_unlock(&ci->i_ceph_lock);
return;
}
......@@ -1065,8 +1062,8 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
/*
* d_move() puts the renamed dentry at the end of
* d_subdirs. We need to assign it an appropriate
* directory offset so we can behave when holding
* D_COMPLETE.
* directory offset so we can behave when dir is
* complete.
*/
ceph_set_dentry_offset(req->r_old_dentry);
dout("dn %p gets new offset %lld\n", req->r_old_dentry,
......@@ -1457,7 +1454,7 @@ static void ceph_invalidate_work(struct work_struct *work)
/*
* called by trunc_wq; take i_mutex ourselves
* called by trunc_wq;
*
* We also truncate in a separate thread as well.
*/
......@@ -1468,9 +1465,7 @@ static void ceph_vmtruncate_work(struct work_struct *work)
struct inode *inode = &ci->vfs_inode;
dout("vmtruncate_work %p\n", inode);
mutex_lock(&inode->i_mutex);
__ceph_do_pending_vmtruncate(inode);
mutex_unlock(&inode->i_mutex);
__ceph_do_pending_vmtruncate(inode, true);
iput(inode);
}
......@@ -1494,12 +1489,10 @@ void ceph_queue_vmtruncate(struct inode *inode)
}
/*
* called with i_mutex held.
*
* Make sure any pending truncation is applied before doing anything
* that may depend on it.
*/
void __ceph_do_pending_vmtruncate(struct inode *inode)
void __ceph_do_pending_vmtruncate(struct inode *inode, bool needlock)
{
struct ceph_inode_info *ci = ceph_inode(inode);
u64 to;
......@@ -1532,7 +1525,11 @@ void __ceph_do_pending_vmtruncate(struct inode *inode)
ci->i_truncate_pending, to);
spin_unlock(&ci->i_ceph_lock);
if (needlock)
mutex_lock(&inode->i_mutex);
truncate_inode_pages(inode->i_mapping, to);
if (needlock)
mutex_unlock(&inode->i_mutex);
spin_lock(&ci->i_ceph_lock);
if (to == ci->i_truncate_size) {
......@@ -1563,6 +1560,12 @@ static void *ceph_sym_follow_link(struct dentry *dentry, struct nameidata *nd)
static const struct inode_operations ceph_symlink_iops = {
.readlink = generic_readlink,
.follow_link = ceph_sym_follow_link,
.setattr = ceph_setattr,
.getattr = ceph_getattr,
.setxattr = ceph_setxattr,
.getxattr = ceph_getxattr,
.listxattr = ceph_listxattr,
.removexattr = ceph_removexattr,
};
/*
......@@ -1585,7 +1588,7 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
if (ceph_snap(inode) != CEPH_NOSNAP)
return -EROFS;
__ceph_do_pending_vmtruncate(inode);
__ceph_do_pending_vmtruncate(inode, false);
err = inode_change_ok(inode, attr);
if (err != 0)
......@@ -1767,7 +1770,7 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
ceph_cap_string(dirtied), mask);
ceph_mdsc_put_request(req);
__ceph_do_pending_vmtruncate(inode);
__ceph_do_pending_vmtruncate(inode, false);
return err;
out:
spin_unlock(&ci->i_ceph_lock);
......
fs/ceph/ioctl.c
浏览文件 @ 91f85756
......@@ -208,8 +208,9 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
snprintf(dl.object_name, sizeof(dl.object_name), "%llx.%08llx",
ceph_ino(inode), dl.object_no);
ceph_calc_object_layout(&pgid, dl.object_name, &ci->i_layout,
osdc->osdmap);
ceph_calc_ceph_pg(&pgid, dl.object_name, osdc->osdmap,
ceph_file_layout_pg_pool(ci->i_layout));
dl.osd = ceph_calc_pg_primary(osdc->osdmap, pgid);
if (dl.osd >= 0) {
......
fs/ceph/mds_client.c
浏览文件 @ 91f85756
......@@ -265,7 +265,8 @@ static int parse_reply_info_extra(void **p, void *end,
{
if (info->head->op == CEPH_MDS_OP_GETFILELOCK)
return parse_reply_info_filelock(p, end, info, features);
else if (info->head->op == CEPH_MDS_OP_READDIR)
else if (info->head->op == CEPH_MDS_OP_READDIR ||
info->head->op == CEPH_MDS_OP_LSSNAP)
return parse_reply_info_dir(p, end, info, features);
else if (info->head->op == CEPH_MDS_OP_CREATE)
return parse_reply_info_create(p, end, info, features);
......@@ -364,7 +365,7 @@ void ceph_put_mds_session(struct ceph_mds_session *s)
atomic_read(&s->s_ref), atomic_read(&s->s_ref)-1);
if (atomic_dec_and_test(&s->s_ref)) {
if (s->s_auth.authorizer)
s->s_mdsc->fsc->client->monc.auth->ops->destroy_authorizer(
ceph_auth_destroy_authorizer(
s->s_mdsc->fsc->client->monc.auth,
s->s_auth.authorizer);
kfree(s);
......@@ -1196,6 +1197,8 @@ static int trim_caps_cb(struct inode *inode, struct ceph_cap *cap, void *arg)
session->s_trim_caps--;
if (oissued) {
/* we aren't the only cap.. just remove us */
__queue_cap_release(session, ceph_ino(inode), cap->cap_id,
cap->mseq, cap->issue_seq);
__ceph_remove_cap(cap);
} else {
/* try to drop referring dentries */
......@@ -1718,8 +1721,12 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
msg->front.iov_len = p - msg->front.iov_base;
msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
msg->pages = req->r_pages;
msg->nr_pages = req->r_num_pages;
if (req->r_data_len) {
/* outbound data set only by ceph_sync_setxattr() */
BUG_ON(!req->r_pages);
ceph_msg_data_add_pages(msg, req->r_pages, req->r_data_len, 0);
}
msg->hdr.data_len = cpu_to_le32(req->r_data_len);
msg->hdr.data_off = cpu_to_le16(0);
......@@ -1913,6 +1920,7 @@ static void __wake_requests(struct ceph_mds_client *mdsc,
req = list_entry(tmp_list.next,
struct ceph_mds_request, r_wait);
list_del_init(&req->r_wait);
dout(" wake request %p tid %llu\n", req, req->r_tid);
__do_request(mdsc, req);
}
}
......@@ -2026,20 +2034,16 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
}
/*
* Invalidate dir D_COMPLETE, dentry lease state on an aborted MDS
* Invalidate dir's completeness, dentry lease state on an aborted MDS
* namespace request.
*/
void ceph_invalidate_dir_request(struct ceph_mds_request *req)
{
struct inode *inode = req->r_locked_dir;
struct ceph_inode_info *ci = ceph_inode(inode);
dout("invalidate_dir_request %p (D_COMPLETE, lease(s))\n", inode);
spin_lock(&ci->i_ceph_lock);
ceph_dir_clear_complete(inode);
ci->i_release_count++;
spin_unlock(&ci->i_ceph_lock);
dout("invalidate_dir_request %p (complete, lease(s))\n", inode);
ceph_dir_clear_complete(inode);
if (req->r_dentry)
ceph_invalidate_dentry_lease(req->r_dentry);
if (req->r_old_dentry)
......@@ -2599,11 +2603,13 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
goto fail;
}
reply->pagelist = pagelist;
if (recon_state.flock)
reply->hdr.version = cpu_to_le16(2);
if (pagelist->length) {
/* set up outbound data if we have any */
reply->hdr.data_len = cpu_to_le32(pagelist->length);
reply->nr_pages = calc_pages_for(0, pagelist->length);
ceph_msg_data_add_pagelist(reply, pagelist);
}
ceph_con_send(&session->s_con, reply);
mutex_unlock(&session->s_mutex);
......@@ -3433,12 +3439,16 @@ static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con,
struct ceph_auth_handshake *auth = &s->s_auth;
if (force_new && auth->authorizer) {
if (ac->ops && ac->ops->destroy_authorizer)
ac->ops->destroy_authorizer(ac, auth->authorizer);
ceph_auth_destroy_authorizer(ac, auth->authorizer);
auth->authorizer = NULL;
}
if (!auth->authorizer && ac->ops && ac->ops->create_authorizer) {
int ret = ac->ops->create_authorizer(ac, CEPH_ENTITY_TYPE_MDS,
if (!auth->authorizer) {
int ret = ceph_auth_create_authorizer(ac, CEPH_ENTITY_TYPE_MDS,
auth);
if (ret)
return ERR_PTR(ret);
} else {
int ret = ceph_auth_update_authorizer(ac, CEPH_ENTITY_TYPE_MDS,
auth);
if (ret)
return ERR_PTR(ret);
......@@ -3455,7 +3465,7 @@ static int verify_authorizer_reply(struct ceph_connection *con, int len)
struct ceph_mds_client *mdsc = s->s_mdsc;
struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
return ac->ops->verify_authorizer_reply(ac, s->s_auth.authorizer, len);
return ceph_auth_verify_authorizer_reply(ac, s->s_auth.authorizer, len);
}
static int invalidate_authorizer(struct ceph_connection *con)
......@@ -3464,12 +3474,32 @@ static int invalidate_authorizer(struct ceph_connection *con)
struct ceph_mds_client *mdsc = s->s_mdsc;
struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
if (ac->ops->invalidate_authorizer)
ac->ops->invalidate_authorizer(ac, CEPH_ENTITY_TYPE_MDS);
ceph_auth_invalidate_authorizer(ac, CEPH_ENTITY_TYPE_MDS);
return ceph_monc_validate_auth(&mdsc->fsc->client->monc);
}
static struct ceph_msg *mds_alloc_msg(struct ceph_connection *con,
struct ceph_msg_header *hdr, int *skip)
{
struct ceph_msg *msg;
int type = (int) le16_to_cpu(hdr->type);
int front_len = (int) le32_to_cpu(hdr->front_len);
if (con->in_msg)
return con->in_msg;
*skip = 0;
msg = ceph_msg_new(type, front_len, GFP_NOFS, false);
if (!msg) {
pr_err("unable to allocate msg type %d len %d\n",
type, front_len);
return NULL;
}
return msg;
}
static const struct ceph_connection_operations mds_con_ops = {
.get = con_get,
.put = con_put,
......@@ -3478,6 +3508,7 @@ static const struct ceph_connection_operations mds_con_ops = {
.verify_authorizer_reply = verify_authorizer_reply,
.invalidate_authorizer = invalidate_authorizer,
.peer_reset = peer_reset,
.alloc_msg = mds_alloc_msg,
};
/* eof */
fs/ceph/mdsmap.c
浏览文件 @ 91f85756
此差异已折叠。
fs/ceph/snap.c
浏览文件 @ 91f85756
此差异已折叠。
fs/ceph/super.c
浏览文件 @ 91f85756
此差异已折叠。
fs/ceph/super.h
浏览文件 @ 91f85756
此差异已折叠。
include/linux/ceph/auth.h
浏览文件 @ 91f85756
此差异已折叠。
include/linux/ceph/ceph_features.h
浏览文件 @ 91f85756
此差异已折叠。
include/linux/ceph/decode.h
浏览文件 @ 91f85756
此差异已折叠。
include/linux/ceph/libceph.h
浏览文件 @ 91f85756
此差异已折叠。
include/linux/ceph/messenger.h
浏览文件 @ 91f85756
此差异已折叠。
include/linux/ceph/msgr.h
浏览文件 @ 91f85756
......@@ -87,6 +87,7 @@ struct ceph_entity_inst {
#define CEPH_MSGR_TAG_BADPROTOVER 10 /* bad protocol version */
#define CEPH_MSGR_TAG_BADAUTHORIZER 11 /* bad authorizer */
#define CEPH_MSGR_TAG_FEATURES 12 /* insufficient features */
#define CEPH_MSGR_TAG_SEQ 13 /* 64-bit int follows with seen seq number */
/*
......
include/linux/ceph/osd_client.h
浏览文件 @ 91f85756
此差异已折叠。
include/linux/ceph/osdmap.h
浏览文件 @ 91f85756
此差异已折叠。
net/ceph/Makefile
浏览文件 @ 91f85756
此差异已折叠。
net/ceph/auth.c
浏览文件 @ 91f85756
此差异已折叠。
net/ceph/auth_x.c
浏览文件 @ 91f85756
此差异已折叠。
net/ceph/auth_x.h
浏览文件 @ 91f85756
此差异已折叠。
net/ceph/ceph_common.c
浏览文件 @ 91f85756
此差异已折叠。
net/ceph/debugfs.c
浏览文件 @ 91f85756
此差异已折叠。
net/ceph/messenger.c
浏览文件 @ 91f85756
此差异已折叠。
net/ceph/mon_client.c
浏览文件 @ 91f85756
此差异已折叠。
net/ceph/osd_client.c
浏览文件 @ 91f85756
此差异已折叠。
net/ceph/osdmap.c
浏览文件 @ 91f85756
此差异已折叠。
net/ceph/snapshot.c 0 → 100644
浏览文件 @ 91f85756
此差异已折叠。
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或