summaryrefslogtreecommitdiff
path: root/fs/ceph
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ceph')
-rw-r--r--fs/ceph/Kconfig2
-rw-r--r--fs/ceph/addr.c1390
-rw-r--r--fs/ceph/caps.c133
-rw-r--r--fs/ceph/crypto.h2
-rw-r--r--fs/ceph/debugfs.c4
-rw-r--r--fs/ceph/dir.c107
-rw-r--r--fs/ceph/export.c14
-rw-r--r--fs/ceph/file.c143
-rw-r--r--fs/ceph/inode.c84
-rw-r--r--fs/ceph/mds_client.c354
-rw-r--r--fs/ceph/mds_client.h48
-rw-r--r--fs/ceph/quota.c2
-rw-r--r--fs/ceph/super.c29
-rw-r--r--fs/ceph/super.h24
-rw-r--r--fs/ceph/xattr.c14
15 files changed, 1593 insertions, 757 deletions
diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig
index 7249d70e1a43..3e7def3d31c1 100644
--- a/fs/ceph/Kconfig
+++ b/fs/ceph/Kconfig
@@ -3,7 +3,7 @@ config CEPH_FS
tristate "Ceph distributed file system"
depends on INET
select CEPH_LIB
- select LIBCRC32C
+ select CRC32
select CRYPTO_AES
select CRYPTO
select NETFS_SUPPORT
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index ee9caf7916fb..29be367905a1 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -13,6 +13,7 @@
#include <linux/iversion.h>
#include <linux/ktime.h>
#include <linux/netfs.h>
+#include <trace/events/netfs.h>
#include "super.h"
#include "mds_client.h"
@@ -81,6 +82,7 @@ static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio)
{
struct inode *inode = mapping->host;
struct ceph_client *cl = ceph_inode_to_client(inode);
+ struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
struct ceph_inode_info *ci;
struct ceph_snap_context *snapc;
@@ -91,11 +93,12 @@ static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio)
return false;
}
+ atomic64_inc(&mdsc->dirty_folios);
+
ci = ceph_inode(inode);
/* dirty the head */
spin_lock(&ci->i_ceph_lock);
- BUG_ON(ci->i_wr_ref == 0); // caller should hold Fw reference
if (__ceph_have_pending_cap_snap(ci)) {
struct ceph_cap_snap *capsnap =
list_last_entry(&ci->i_cap_snaps,
@@ -193,7 +196,7 @@ static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq)
* block, but do not exceed the file size, unless the original
* request already exceeds it.
*/
- new_end = min(round_up(end, lo->stripe_unit), rreq->i_size);
+ new_end = umin(round_up(end, lo->stripe_unit), rreq->i_size);
if (new_end > end && new_end <= rreq->start + max_len)
rreq->len = new_end - rreq->start;
@@ -205,21 +208,6 @@ static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq)
}
}
-static bool ceph_netfs_clamp_length(struct netfs_io_subrequest *subreq)
-{
- struct inode *inode = subreq->rreq->inode;
- struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
- struct ceph_inode_info *ci = ceph_inode(inode);
- u64 objno, objoff;
- u32 xlen;
-
- /* Truncate the extent at the end of the current block */
- ceph_calc_file_object_mapping(&ci->i_layout, subreq->start, subreq->len,
- &objno, &objoff, &xlen);
- subreq->len = min(xlen, fsc->mount_options->rsize);
- return true;
-}
-
static void finish_netfs_read(struct ceph_osd_request *req)
{
struct inode *inode = req->r_inode;
@@ -238,15 +226,19 @@ static void finish_netfs_read(struct ceph_osd_request *req)
subreq->len, i_size_read(req->r_inode));
/* no object means success but no data */
- if (err == -ENOENT)
+ if (err == -ENOENT) {
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags);
err = 0;
- else if (err == -EBLOCKLISTED)
+ } else if (err == -EBLOCKLISTED) {
fsc->blocklisted = true;
+ }
if (err >= 0) {
if (sparse && err > 0)
err = ceph_sparse_ext_map_end(op);
- if (err < subreq->len)
+ if (err < subreq->len &&
+ subreq->rreq->origin != NETFS_DIO_READ)
__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
if (IS_ENCRYPTED(inode) && err > 0) {
err = ceph_fscrypt_decrypt_extents(inode,
@@ -256,6 +248,8 @@ static void finish_netfs_read(struct ceph_osd_request *req)
if (err > subreq->len)
err = subreq->len;
}
+ if (err > 0)
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
}
if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGES) {
@@ -263,7 +257,13 @@ static void finish_netfs_read(struct ceph_osd_request *req)
calc_pages_for(osd_data->alignment,
osd_data->length), false);
}
- netfs_subreq_terminated(subreq, err, false);
+ if (err > 0) {
+ subreq->transferred = err;
+ err = 0;
+ }
+ subreq->error = err;
+ trace_netfs_sreq(subreq, netfs_sreq_trace_io_progress);
+ netfs_read_subreq_terminated(subreq);
iput(req->r_inode);
ceph_dec_osd_stopping_blocker(fsc->mdsc);
}
@@ -277,12 +277,12 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
struct ceph_mds_request *req;
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
struct ceph_inode_info *ci = ceph_inode(inode);
- struct iov_iter iter;
ssize_t err = 0;
size_t len;
int mode;
- __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ if (rreq->origin != NETFS_DIO_READ)
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
__clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
if (subreq->start >= inode->i_size)
@@ -299,6 +299,7 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INLINE_DATA);
req->r_num_caps = 2;
+ trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
err = ceph_mdsc_do_request(mdsc, NULL, req);
if (err < 0)
goto out;
@@ -312,17 +313,38 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
}
len = min_t(size_t, iinfo->inline_len - subreq->start, subreq->len);
- iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages, subreq->start, len);
- err = copy_to_iter(iinfo->inline_data + subreq->start, len, &iter);
- if (err == 0)
+ err = copy_to_iter(iinfo->inline_data + subreq->start, len, &subreq->io_iter);
+ if (err == 0) {
err = -EFAULT;
+ } else {
+ subreq->transferred += err;
+ err = 0;
+ }
ceph_mdsc_put_request(req);
out:
- netfs_subreq_terminated(subreq, err, false);
+ subreq->error = err;
+ trace_netfs_sreq(subreq, netfs_sreq_trace_io_progress);
+ netfs_read_subreq_terminated(subreq);
return true;
}
+static int ceph_netfs_prepare_read(struct netfs_io_subrequest *subreq)
+{
+ struct netfs_io_request *rreq = subreq->rreq;
+ struct inode *inode = rreq->inode;
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+ u64 objno, objoff;
+ u32 xlen;
+
+ /* Truncate the extent at the end of the current block */
+ ceph_calc_file_object_mapping(&ci->i_layout, subreq->start, subreq->len,
+ &objno, &objoff, &xlen);
+ rreq->io_streams[0].sreq_max_len = umin(xlen, fsc->mount_options->rsize);
+ return 0;
+}
+
static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
{
struct netfs_io_request *rreq = subreq->rreq;
@@ -332,9 +354,8 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
struct ceph_client *cl = fsc->client;
struct ceph_osd_request *req = NULL;
struct ceph_vino vino = ceph_vino(inode);
- struct iov_iter iter;
- int err = 0;
- u64 len = subreq->len;
+ int err;
+ u64 len;
bool sparse = IS_ENCRYPTED(inode) || ceph_test_mount_opt(fsc, SPARSEREAD);
u64 off = subreq->start;
int extent_cnt;
@@ -347,6 +368,12 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
if (ceph_has_inline_data(ci) && ceph_netfs_issue_op_inline(subreq))
return;
+ // TODO: This rounding here is slightly dodgy. It *should* work, for
+ // now, as the cache only deals in blocks that are a multiple of
+ // PAGE_SIZE and fscrypt blocks are at most PAGE_SIZE. What needs to
+ // happen is for the fscrypt driving to be moved into netfslib and the
+ // data in the cache also to be stored encrypted.
+ len = subreq->len;
ceph_fscrypt_adjust_off_and_len(inode, &off, &len);
req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino,
@@ -369,8 +396,6 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
doutc(cl, "%llx.%llx pos=%llu orig_len=%zu len=%llu\n",
ceph_vinop(inode), subreq->start, subreq->len, len);
- iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages, subreq->start, len);
-
/*
* FIXME: For now, use CEPH_OSD_DATA_TYPE_PAGES instead of _ITER for
* encrypted inodes. We'd need infrastructure that handles an iov_iter
@@ -382,7 +407,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
struct page **pages;
size_t page_off;
- err = iov_iter_get_pages_alloc2(&iter, &pages, len, &page_off);
+ err = iov_iter_get_pages_alloc2(&subreq->io_iter, &pages, len, &page_off);
if (err < 0) {
doutc(cl, "%llx.%llx failed to allocate pages, %d\n",
ceph_vinop(inode), err);
@@ -397,7 +422,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, false,
false);
} else {
- osd_req_op_extent_osd_iter(req, 0, &iter);
+ osd_req_op_extent_osd_iter(req, 0, &subreq->io_iter);
}
if (!ceph_inc_osd_stopping_blocker(fsc->mdsc)) {
err = -EIO;
@@ -408,22 +433,29 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
req->r_inode = inode;
ihold(inode);
+ trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
ceph_osdc_start_request(req->r_osdc, req);
out:
ceph_osdc_put_request(req);
- if (err)
- netfs_subreq_terminated(subreq, err, false);
+ if (err) {
+ subreq->error = err;
+ netfs_read_subreq_terminated(subreq);
+ }
doutc(cl, "%llx.%llx result %d\n", ceph_vinop(inode), err);
}
static int ceph_init_request(struct netfs_io_request *rreq, struct file *file)
{
struct inode *inode = rreq->inode;
+ struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
struct ceph_client *cl = ceph_inode_to_client(inode);
int got = 0, want = CEPH_CAP_FILE_CACHE;
struct ceph_netfs_request_data *priv;
int ret = 0;
+ /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */
+ __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags);
+
if (rreq->origin != NETFS_READAHEAD)
return 0;
@@ -467,10 +499,14 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file)
priv->caps = got;
rreq->netfs_priv = priv;
+ rreq->io_streams[0].sreq_max_len = fsc->mount_options->rsize;
out:
- if (ret < 0)
+ if (ret < 0) {
+ if (got)
+ ceph_put_cap_refs(ceph_inode(inode), got);
kfree(priv);
+ }
return ret;
}
@@ -491,16 +527,16 @@ static void ceph_netfs_free_request(struct netfs_io_request *rreq)
const struct netfs_request_ops ceph_netfs_ops = {
.init_request = ceph_init_request,
.free_request = ceph_netfs_free_request,
+ .prepare_read = ceph_netfs_prepare_read,
.issue_read = ceph_netfs_issue_read,
.expand_readahead = ceph_netfs_expand_readahead,
- .clamp_length = ceph_netfs_clamp_length,
.check_write_begin = ceph_netfs_check_write_begin,
};
#ifdef CONFIG_CEPH_FSCACHE
static void ceph_set_page_fscache(struct page *page)
{
- set_page_fscache(page);
+ folio_start_private_2(page_folio(page)); /* [DEPRECATED] */
}
static void ceph_fscache_write_terminated(void *priv, ssize_t error, bool was_async)
@@ -517,7 +553,7 @@ static void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, b
struct fscache_cookie *cookie = ceph_fscache_cookie(ci);
fscache_write_to_cache(cookie, inode->i_mapping, off, len, i_size_read(inode),
- ceph_fscache_write_terminated, inode, caching);
+ ceph_fscache_write_terminated, inode, true, caching);
}
#else
static inline void ceph_set_page_fscache(struct page *page)
@@ -535,7 +571,36 @@ struct ceph_writeback_ctl
u64 truncate_size;
u32 truncate_seq;
bool size_stable;
+
bool head_snapc;
+ struct ceph_snap_context *snapc;
+ struct ceph_snap_context *last_snapc;
+
+ bool done;
+ bool should_loop;
+ bool range_whole;
+ pgoff_t start_index;
+ pgoff_t index;
+ pgoff_t end;
+ xa_mark_t tag;
+
+ pgoff_t strip_unit_end;
+ unsigned int wsize;
+ unsigned int nr_folios;
+ unsigned int max_pages;
+ unsigned int locked_pages;
+
+ int op_idx;
+ int num_ops;
+ u64 offset;
+ u64 len;
+
+ struct folio_batch fbatch;
+ unsigned int processed_in_fbatch;
+
+ bool from_pool;
+ struct page **pages;
+ struct page **data_pages;
};
/*
@@ -633,22 +698,23 @@ static u64 get_writepages_data_length(struct inode *inode,
}
/*
- * Write a single page, but leave the page locked.
+ * Write a folio, but leave it locked.
*
* If we get a write error, mark the mapping for error, but still adjust the
- * dirty page accounting (i.e., page is no longer dirty).
+ * dirty page accounting (i.e., folio is no longer dirty).
*/
-static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
+static int write_folio_nounlock(struct folio *folio,
+ struct writeback_control *wbc)
{
- struct folio *folio = page_folio(page);
- struct inode *inode = page->mapping->host;
+ struct page *page = &folio->page;
+ struct inode *inode = folio->mapping->host;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
struct ceph_client *cl = fsc->client;
struct ceph_snap_context *snapc, *oldest;
- loff_t page_off = page_offset(page);
+ loff_t page_off = folio_pos(folio);
int err;
- loff_t len = thp_size(page);
+ loff_t len = folio_size(folio);
loff_t wlen;
struct ceph_writeback_ctl ceph_wbc;
struct ceph_osd_client *osdc = &fsc->client->osdc;
@@ -656,27 +722,27 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
bool caching = ceph_is_cache_enabled(inode);
struct page *bounce_page = NULL;
- doutc(cl, "%llx.%llx page %p idx %lu\n", ceph_vinop(inode), page,
- page->index);
+ doutc(cl, "%llx.%llx folio %p idx %lu\n", ceph_vinop(inode), folio,
+ folio->index);
if (ceph_inode_is_shutdown(inode))
return -EIO;
/* verify this is a writeable snap context */
- snapc = page_snap_context(page);
+ snapc = page_snap_context(&folio->page);
if (!snapc) {
- doutc(cl, "%llx.%llx page %p not dirty?\n", ceph_vinop(inode),
- page);
+ doutc(cl, "%llx.%llx folio %p not dirty?\n", ceph_vinop(inode),
+ folio);
return 0;
}
oldest = get_oldest_context(inode, &ceph_wbc, snapc);
if (snapc->seq > oldest->seq) {
- doutc(cl, "%llx.%llx page %p snapc %p not writeable - noop\n",
- ceph_vinop(inode), page, snapc);
+ doutc(cl, "%llx.%llx folio %p snapc %p not writeable - noop\n",
+ ceph_vinop(inode), folio, snapc);
/* we should only noop if called by kswapd */
WARN_ON(!(current->flags & PF_MEMALLOC));
ceph_put_snap_context(oldest);
- redirty_page_for_writepage(wbc, page);
+ folio_redirty_for_writepage(wbc, folio);
return 0;
}
ceph_put_snap_context(oldest);
@@ -693,8 +759,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
len = ceph_wbc.i_size - page_off;
wlen = IS_ENCRYPTED(inode) ? round_up(len, CEPH_FSCRYPT_BLOCK_SIZE) : len;
- doutc(cl, "%llx.%llx page %p index %lu on %llu~%llu snapc %p seq %lld\n",
- ceph_vinop(inode), page, page->index, page_off, wlen, snapc,
+ doutc(cl, "%llx.%llx folio %p index %lu on %llu~%llu snapc %p seq %lld\n",
+ ceph_vinop(inode), folio, folio->index, page_off, wlen, snapc,
snapc->seq);
if (atomic_long_inc_return(&fsc->writeback_count) >
@@ -707,32 +773,32 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
ceph_wbc.truncate_seq,
ceph_wbc.truncate_size, true);
if (IS_ERR(req)) {
- redirty_page_for_writepage(wbc, page);
+ folio_redirty_for_writepage(wbc, folio);
return PTR_ERR(req);
}
if (wlen < len)
len = wlen;
- set_page_writeback(page);
+ folio_start_writeback(folio);
if (caching)
- ceph_set_page_fscache(page);
+ ceph_set_page_fscache(&folio->page);
ceph_fscache_write_to_cache(inode, page_off, len, caching);
if (IS_ENCRYPTED(inode)) {
- bounce_page = fscrypt_encrypt_pagecache_blocks(page,
+ bounce_page = fscrypt_encrypt_pagecache_blocks(folio,
CEPH_FSCRYPT_BLOCK_SIZE, 0,
GFP_NOFS);
if (IS_ERR(bounce_page)) {
- redirty_page_for_writepage(wbc, page);
- end_page_writeback(page);
+ folio_redirty_for_writepage(wbc, folio);
+ folio_end_writeback(folio);
ceph_osdc_put_request(req);
return PTR_ERR(bounce_page);
}
}
/* it may be a short write due to an object boundary */
- WARN_ON_ONCE(len > thp_size(page));
+ WARN_ON_ONCE(len > folio_size(folio));
osd_req_op_extent_osd_data_pages(req, 0,
bounce_page ? &bounce_page : &page, wlen, 0,
false, false);
@@ -758,25 +824,25 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
if (err == -ERESTARTSYS) {
/* killed by SIGKILL */
doutc(cl, "%llx.%llx interrupted page %p\n",
- ceph_vinop(inode), page);
- redirty_page_for_writepage(wbc, page);
- end_page_writeback(page);
+ ceph_vinop(inode), folio);
+ folio_redirty_for_writepage(wbc, folio);
+ folio_end_writeback(folio);
return err;
}
if (err == -EBLOCKLISTED)
fsc->blocklisted = true;
- doutc(cl, "%llx.%llx setting page/mapping error %d %p\n",
- ceph_vinop(inode), err, page);
+ doutc(cl, "%llx.%llx setting mapping error %d %p\n",
+ ceph_vinop(inode), err, folio);
mapping_set_error(&inode->i_data, err);
wbc->pages_skipped++;
} else {
doutc(cl, "%llx.%llx cleaned page %p\n",
- ceph_vinop(inode), page);
+ ceph_vinop(inode), folio);
err = 0; /* vfs expects us to return 0 */
}
- oldest = detach_page_private(page);
+ oldest = folio_detach_private(folio);
WARN_ON_ONCE(oldest != snapc);
- end_page_writeback(page);
+ folio_end_writeback(folio);
ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
ceph_put_snap_context(snapc); /* page's reference */
@@ -787,32 +853,6 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
return err;
}
-static int ceph_writepage(struct page *page, struct writeback_control *wbc)
-{
- int err;
- struct inode *inode = page->mapping->host;
- BUG_ON(!inode);
- ihold(inode);
-
- if (wbc->sync_mode == WB_SYNC_NONE &&
- ceph_inode_to_fs_client(inode)->write_congested) {
- redirty_page_for_writepage(wbc, page);
- return AOP_WRITEPAGE_ACTIVATE;
- }
-
- wait_on_page_fscache(page);
-
- err = writepage_nounlock(page, wbc);
- if (err == -ERESTARTSYS) {
- /* direct memory reclaimer was killed by SIGKILL. return 0
- * to prevent caller from setting mapping/page error */
- err = 0;
- }
- unlock_page(page);
- iput(inode);
- return err;
-}
-
/*
* async writeback completion handler.
*
@@ -832,6 +872,7 @@ static void writepages_finish(struct ceph_osd_request *req)
struct ceph_snap_context *snapc = req->r_snapc;
struct address_space *mapping = inode->i_mapping;
struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+ struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
unsigned int len = 0;
bool remove_page;
@@ -887,6 +928,12 @@ static void writepages_finish(struct ceph_osd_request *req)
ceph_put_snap_context(detach_page_private(page));
end_page_writeback(page);
+
+ if (atomic64_dec_return(&mdsc->dirty_folios) <= 0) {
+ wake_up_all(&mdsc->flush_end_wq);
+ WARN_ON(atomic64_read(&mdsc->dirty_folios) < 0);
+ }
+
doutc(cl, "unlocking %p\n", page);
if (remove_page)
@@ -916,36 +963,13 @@ static void writepages_finish(struct ceph_osd_request *req)
ceph_dec_osd_stopping_blocker(fsc->mdsc);
}
-/*
- * initiate async writeback
- */
-static int ceph_writepages_start(struct address_space *mapping,
- struct writeback_control *wbc)
+static inline
+bool is_forced_umount(struct address_space *mapping)
{
struct inode *inode = mapping->host;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
struct ceph_client *cl = fsc->client;
- struct ceph_vino vino = ceph_vino(inode);
- pgoff_t index, start_index, end = -1;
- struct ceph_snap_context *snapc = NULL, *last_snapc = NULL, *pgsnapc;
- struct folio_batch fbatch;
- int rc = 0;
- unsigned int wsize = i_blocksize(inode);
- struct ceph_osd_request *req = NULL;
- struct ceph_writeback_ctl ceph_wbc;
- bool should_loop, range_whole = false;
- bool done = false;
- bool caching = ceph_is_cache_enabled(inode);
- xa_mark_t tag;
-
- if (wbc->sync_mode == WB_SYNC_NONE &&
- fsc->write_congested)
- return 0;
-
- doutc(cl, "%llx.%llx (mode=%s)\n", ceph_vinop(inode),
- wbc->sync_mode == WB_SYNC_NONE ? "NONE" :
- (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
if (ceph_inode_is_shutdown(inode)) {
if (ci->i_wrbuffer_ref > 0) {
@@ -954,387 +978,733 @@ static int ceph_writepages_start(struct address_space *mapping,
ceph_vinop(inode), ceph_ino(inode));
}
mapping_set_error(mapping, -EIO);
- return -EIO; /* we're in a forced umount, don't write! */
+ return true;
}
+
+ return false;
+}
+
+static inline
+unsigned int ceph_define_write_size(struct address_space *mapping)
+{
+ struct inode *inode = mapping->host;
+ struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+ unsigned int wsize = i_blocksize(inode);
+
if (fsc->mount_options->wsize < wsize)
wsize = fsc->mount_options->wsize;
- folio_batch_init(&fbatch);
+ return wsize;
+}
+
+static inline
+void ceph_folio_batch_init(struct ceph_writeback_ctl *ceph_wbc)
+{
+ folio_batch_init(&ceph_wbc->fbatch);
+ ceph_wbc->processed_in_fbatch = 0;
+}
+
+static inline
+void ceph_folio_batch_reinit(struct ceph_writeback_ctl *ceph_wbc)
+{
+ folio_batch_release(&ceph_wbc->fbatch);
+ ceph_folio_batch_init(ceph_wbc);
+}
+
+static inline
+void ceph_init_writeback_ctl(struct address_space *mapping,
+ struct writeback_control *wbc,
+ struct ceph_writeback_ctl *ceph_wbc)
+{
+ ceph_wbc->snapc = NULL;
+ ceph_wbc->last_snapc = NULL;
- start_index = wbc->range_cyclic ? mapping->writeback_index : 0;
- index = start_index;
+ ceph_wbc->strip_unit_end = 0;
+ ceph_wbc->wsize = ceph_define_write_size(mapping);
+
+ ceph_wbc->nr_folios = 0;
+ ceph_wbc->max_pages = 0;
+ ceph_wbc->locked_pages = 0;
+
+ ceph_wbc->done = false;
+ ceph_wbc->should_loop = false;
+ ceph_wbc->range_whole = false;
+
+ ceph_wbc->start_index = wbc->range_cyclic ? mapping->writeback_index : 0;
+ ceph_wbc->index = ceph_wbc->start_index;
+ ceph_wbc->end = -1;
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) {
- tag = PAGECACHE_TAG_TOWRITE;
+ ceph_wbc->tag = PAGECACHE_TAG_TOWRITE;
} else {
- tag = PAGECACHE_TAG_DIRTY;
+ ceph_wbc->tag = PAGECACHE_TAG_DIRTY;
}
-retry:
+
+ ceph_wbc->op_idx = -1;
+ ceph_wbc->num_ops = 0;
+ ceph_wbc->offset = 0;
+ ceph_wbc->len = 0;
+ ceph_wbc->from_pool = false;
+
+ ceph_folio_batch_init(ceph_wbc);
+
+ ceph_wbc->pages = NULL;
+ ceph_wbc->data_pages = NULL;
+}
+
+static inline
+int ceph_define_writeback_range(struct address_space *mapping,
+ struct writeback_control *wbc,
+ struct ceph_writeback_ctl *ceph_wbc)
+{
+ struct inode *inode = mapping->host;
+ struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+ struct ceph_client *cl = fsc->client;
+
/* find oldest snap context with dirty data */
- snapc = get_oldest_context(inode, &ceph_wbc, NULL);
- if (!snapc) {
+ ceph_wbc->snapc = get_oldest_context(inode, ceph_wbc, NULL);
+ if (!ceph_wbc->snapc) {
/* hmm, why does writepages get called when there
is no dirty data? */
doutc(cl, " no snap context with dirty data?\n");
- goto out;
+ return -ENODATA;
}
- doutc(cl, " oldest snapc is %p seq %lld (%d snaps)\n", snapc,
- snapc->seq, snapc->num_snaps);
- should_loop = false;
- if (ceph_wbc.head_snapc && snapc != last_snapc) {
+ doutc(cl, " oldest snapc is %p seq %lld (%d snaps)\n",
+ ceph_wbc->snapc, ceph_wbc->snapc->seq,
+ ceph_wbc->snapc->num_snaps);
+
+ ceph_wbc->should_loop = false;
+
+ if (ceph_wbc->head_snapc && ceph_wbc->snapc != ceph_wbc->last_snapc) {
/* where to start/end? */
if (wbc->range_cyclic) {
- index = start_index;
- end = -1;
- if (index > 0)
- should_loop = true;
- doutc(cl, " cyclic, start at %lu\n", index);
+ ceph_wbc->index = ceph_wbc->start_index;
+ ceph_wbc->end = -1;
+ if (ceph_wbc->index > 0)
+ ceph_wbc->should_loop = true;
+ doutc(cl, " cyclic, start at %lu\n", ceph_wbc->index);
} else {
- index = wbc->range_start >> PAGE_SHIFT;
- end = wbc->range_end >> PAGE_SHIFT;
+ ceph_wbc->index = wbc->range_start >> PAGE_SHIFT;
+ ceph_wbc->end = wbc->range_end >> PAGE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
- range_whole = true;
- doutc(cl, " not cyclic, %lu to %lu\n", index, end);
+ ceph_wbc->range_whole = true;
+ doutc(cl, " not cyclic, %lu to %lu\n",
+ ceph_wbc->index, ceph_wbc->end);
}
- } else if (!ceph_wbc.head_snapc) {
+ } else if (!ceph_wbc->head_snapc) {
/* Do not respect wbc->range_{start,end}. Dirty pages
* in that range can be associated with newer snapc.
* They are not writeable until we write all dirty pages
* associated with 'snapc' get written */
- if (index > 0)
- should_loop = true;
+ if (ceph_wbc->index > 0)
+ ceph_wbc->should_loop = true;
doutc(cl, " non-head snapc, range whole\n");
}
- if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
- tag_pages_for_writeback(mapping, index, end);
+ ceph_put_snap_context(ceph_wbc->last_snapc);
+ ceph_wbc->last_snapc = ceph_wbc->snapc;
- ceph_put_snap_context(last_snapc);
- last_snapc = snapc;
+ return 0;
+}
- while (!done && index <= end) {
- int num_ops = 0, op_idx;
- unsigned i, nr_folios, max_pages, locked_pages = 0;
- struct page **pages = NULL, **data_pages;
- struct page *page;
- pgoff_t strip_unit_end = 0;
- u64 offset = 0, len = 0;
- bool from_pool = false;
+static inline
+bool has_writeback_done(struct ceph_writeback_ctl *ceph_wbc)
+{
+ return ceph_wbc->done && ceph_wbc->index > ceph_wbc->end;
+}
- max_pages = wsize >> PAGE_SHIFT;
+static inline
+bool can_next_page_be_processed(struct ceph_writeback_ctl *ceph_wbc,
+ unsigned index)
+{
+ return index < ceph_wbc->nr_folios &&
+ ceph_wbc->locked_pages < ceph_wbc->max_pages;
+}
-get_more_pages:
- nr_folios = filemap_get_folios_tag(mapping, &index,
- end, tag, &fbatch);
- doutc(cl, "pagevec_lookup_range_tag got %d\n", nr_folios);
- if (!nr_folios && !locked_pages)
- break;
- for (i = 0; i < nr_folios && locked_pages < max_pages; i++) {
- page = &fbatch.folios[i]->page;
- doutc(cl, "? %p idx %lu\n", page, page->index);
- if (locked_pages == 0)
- lock_page(page); /* first page */
- else if (!trylock_page(page))
- break;
+static
+int ceph_check_page_before_write(struct address_space *mapping,
+ struct writeback_control *wbc,
+ struct ceph_writeback_ctl *ceph_wbc,
+ struct folio *folio)
+{
+ struct inode *inode = mapping->host;
+ struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+ struct ceph_client *cl = fsc->client;
+ struct ceph_snap_context *pgsnapc;
- /* only dirty pages, or our accounting breaks */
- if (unlikely(!PageDirty(page)) ||
- unlikely(page->mapping != mapping)) {
- doutc(cl, "!dirty or !mapping %p\n", page);
- unlock_page(page);
- continue;
- }
- /* only if matching snap context */
- pgsnapc = page_snap_context(page);
- if (pgsnapc != snapc) {
- doutc(cl, "page snapc %p %lld != oldest %p %lld\n",
- pgsnapc, pgsnapc->seq, snapc, snapc->seq);
- if (!should_loop &&
- !ceph_wbc.head_snapc &&
- wbc->sync_mode != WB_SYNC_NONE)
- should_loop = true;
- unlock_page(page);
- continue;
+ /* only dirty folios, or our accounting breaks */
+ if (unlikely(!folio_test_dirty(folio) || folio->mapping != mapping)) {
+ doutc(cl, "!dirty or !mapping %p\n", folio);
+ return -ENODATA;
+ }
+
+ /* only if matching snap context */
+ pgsnapc = page_snap_context(&folio->page);
+ if (pgsnapc != ceph_wbc->snapc) {
+ doutc(cl, "folio snapc %p %lld != oldest %p %lld\n",
+ pgsnapc, pgsnapc->seq,
+ ceph_wbc->snapc, ceph_wbc->snapc->seq);
+
+ if (!ceph_wbc->should_loop && !ceph_wbc->head_snapc &&
+ wbc->sync_mode != WB_SYNC_NONE)
+ ceph_wbc->should_loop = true;
+
+ return -ENODATA;
+ }
+
+ if (folio_pos(folio) >= ceph_wbc->i_size) {
+ doutc(cl, "folio at %lu beyond eof %llu\n",
+ folio->index, ceph_wbc->i_size);
+
+ if ((ceph_wbc->size_stable ||
+ folio_pos(folio) >= i_size_read(inode)) &&
+ folio_clear_dirty_for_io(folio))
+ folio_invalidate(folio, 0, folio_size(folio));
+
+ return -ENODATA;
+ }
+
+ if (ceph_wbc->strip_unit_end &&
+ (folio->index > ceph_wbc->strip_unit_end)) {
+ doutc(cl, "end of strip unit %p\n", folio);
+ return -E2BIG;
+ }
+
+ return 0;
+}
+
+static inline
+void __ceph_allocate_page_array(struct ceph_writeback_ctl *ceph_wbc,
+ unsigned int max_pages)
+{
+ ceph_wbc->pages = kmalloc_array(max_pages,
+ sizeof(*ceph_wbc->pages),
+ GFP_NOFS);
+ if (!ceph_wbc->pages) {
+ ceph_wbc->from_pool = true;
+ ceph_wbc->pages = mempool_alloc(ceph_wb_pagevec_pool, GFP_NOFS);
+ BUG_ON(!ceph_wbc->pages);
+ }
+}
+
+static inline
+void ceph_allocate_page_array(struct address_space *mapping,
+ struct ceph_writeback_ctl *ceph_wbc,
+ struct folio *folio)
+{
+ struct inode *inode = mapping->host;
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ u64 objnum;
+ u64 objoff;
+ u32 xlen;
+
+ /* prepare async write request */
+ ceph_wbc->offset = (u64)folio_pos(folio);
+ ceph_calc_file_object_mapping(&ci->i_layout,
+ ceph_wbc->offset, ceph_wbc->wsize,
+ &objnum, &objoff, &xlen);
+
+ ceph_wbc->num_ops = 1;
+ ceph_wbc->strip_unit_end = folio->index + ((xlen - 1) >> PAGE_SHIFT);
+
+ BUG_ON(ceph_wbc->pages);
+ ceph_wbc->max_pages = calc_pages_for(0, (u64)xlen);
+ __ceph_allocate_page_array(ceph_wbc, ceph_wbc->max_pages);
+
+ ceph_wbc->len = 0;
+}
+
+static inline
+bool is_folio_index_contiguous(const struct ceph_writeback_ctl *ceph_wbc,
+ const struct folio *folio)
+{
+ return folio->index == (ceph_wbc->offset + ceph_wbc->len) >> PAGE_SHIFT;
+}
+
+static inline
+bool is_num_ops_too_big(struct ceph_writeback_ctl *ceph_wbc)
+{
+ return ceph_wbc->num_ops >=
+ (ceph_wbc->from_pool ? CEPH_OSD_SLAB_OPS : CEPH_OSD_MAX_OPS);
+}
+
+static inline
+bool is_write_congestion_happened(struct ceph_fs_client *fsc)
+{
+ return atomic_long_inc_return(&fsc->writeback_count) >
+ CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb);
+}
+
+static inline int move_dirty_folio_in_page_array(struct address_space *mapping,
+ struct writeback_control *wbc,
+ struct ceph_writeback_ctl *ceph_wbc, struct folio *folio)
+{
+ struct inode *inode = mapping->host;
+ struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+ struct ceph_client *cl = fsc->client;
+ struct page **pages = ceph_wbc->pages;
+ unsigned int index = ceph_wbc->locked_pages;
+ gfp_t gfp_flags = ceph_wbc->locked_pages ? GFP_NOWAIT : GFP_NOFS;
+
+ if (IS_ENCRYPTED(inode)) {
+ pages[index] = fscrypt_encrypt_pagecache_blocks(folio,
+ PAGE_SIZE,
+ 0,
+ gfp_flags);
+ if (IS_ERR(pages[index])) {
+ if (PTR_ERR(pages[index]) == -EINVAL) {
+ pr_err_client(cl, "inode->i_blkbits=%hhu\n",
+ inode->i_blkbits);
}
- if (page_offset(page) >= ceph_wbc.i_size) {
- struct folio *folio = page_folio(page);
-
- doutc(cl, "folio at %lu beyond eof %llu\n",
- folio->index, ceph_wbc.i_size);
- if ((ceph_wbc.size_stable ||
- folio_pos(folio) >= i_size_read(inode)) &&
- folio_clear_dirty_for_io(folio))
- folio_invalidate(folio, 0,
- folio_size(folio));
+
+ /* better not fail on first page! */
+ BUG_ON(ceph_wbc->locked_pages == 0);
+
+ pages[index] = NULL;
+ return PTR_ERR(pages[index]);
+ }
+ } else {
+ pages[index] = &folio->page;
+ }
+
+ ceph_wbc->locked_pages++;
+
+ return 0;
+}
+
+static
+int ceph_process_folio_batch(struct address_space *mapping,
+ struct writeback_control *wbc,
+ struct ceph_writeback_ctl *ceph_wbc)
+{
+ struct inode *inode = mapping->host;
+ struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+ struct ceph_client *cl = fsc->client;
+ struct folio *folio = NULL;
+ unsigned i;
+ int rc = 0;
+
+ for (i = 0; can_next_page_be_processed(ceph_wbc, i); i++) {
+ folio = ceph_wbc->fbatch.folios[i];
+
+ if (!folio)
+ continue;
+
+ doutc(cl, "? %p idx %lu, folio_test_writeback %#x, "
+ "folio_test_dirty %#x, folio_test_locked %#x\n",
+ folio, folio->index, folio_test_writeback(folio),
+ folio_test_dirty(folio),
+ folio_test_locked(folio));
+
+ if (folio_test_writeback(folio) ||
+ folio_test_private_2(folio) /* [DEPRECATED] */) {
+ doutc(cl, "waiting on writeback %p\n", folio);
+ folio_wait_writeback(folio);
+ folio_wait_private_2(folio); /* [DEPRECATED] */
+ continue;
+ }
+
+ if (ceph_wbc->locked_pages == 0)
+ folio_lock(folio);
+ else if (!folio_trylock(folio))
+ break;
+
+ rc = ceph_check_page_before_write(mapping, wbc,
+ ceph_wbc, folio);
+ if (rc == -ENODATA) {
+ rc = 0;
+ folio_unlock(folio);
+ ceph_wbc->fbatch.folios[i] = NULL;
+ continue;
+ } else if (rc == -E2BIG) {
+ rc = 0;
+ folio_unlock(folio);
+ ceph_wbc->fbatch.folios[i] = NULL;
+ break;
+ }
+
+ if (!folio_clear_dirty_for_io(folio)) {
+ doutc(cl, "%p !folio_clear_dirty_for_io\n", folio);
+ folio_unlock(folio);
+ ceph_wbc->fbatch.folios[i] = NULL;
+ continue;
+ }
+
+ /*
+ * We have something to write. If this is
+ * the first locked page this time through,
+ * calculate max possible write size and
+ * allocate a page array
+ */
+ if (ceph_wbc->locked_pages == 0) {
+ ceph_allocate_page_array(mapping, ceph_wbc, folio);
+ } else if (!is_folio_index_contiguous(ceph_wbc, folio)) {
+ if (is_num_ops_too_big(ceph_wbc)) {
+ folio_redirty_for_writepage(wbc, folio);
folio_unlock(folio);
- continue;
- }
- if (strip_unit_end && (page->index > strip_unit_end)) {
- doutc(cl, "end of strip unit %p\n", page);
- unlock_page(page);
break;
}
- if (PageWriteback(page) || PageFsCache(page)) {
- if (wbc->sync_mode == WB_SYNC_NONE) {
- doutc(cl, "%p under writeback\n", page);
- unlock_page(page);
- continue;
- }
- doutc(cl, "waiting on writeback %p\n", page);
- wait_on_page_writeback(page);
- wait_on_page_fscache(page);
- }
- if (!clear_page_dirty_for_io(page)) {
- doutc(cl, "%p !clear_page_dirty_for_io\n", page);
- unlock_page(page);
- continue;
- }
+ ceph_wbc->num_ops++;
+ ceph_wbc->offset = (u64)folio_pos(folio);
+ ceph_wbc->len = 0;
+ }
- /*
- * We have something to write. If this is
- * the first locked page this time through,
- * calculate max possinle write size and
- * allocate a page array
- */
- if (locked_pages == 0) {
- u64 objnum;
- u64 objoff;
- u32 xlen;
-
- /* prepare async write request */
- offset = (u64)page_offset(page);
- ceph_calc_file_object_mapping(&ci->i_layout,
- offset, wsize,
- &objnum, &objoff,
- &xlen);
- len = xlen;
-
- num_ops = 1;
- strip_unit_end = page->index +
- ((len - 1) >> PAGE_SHIFT);
-
- BUG_ON(pages);
- max_pages = calc_pages_for(0, (u64)len);
- pages = kmalloc_array(max_pages,
- sizeof(*pages),
- GFP_NOFS);
- if (!pages) {
- from_pool = true;
- pages = mempool_alloc(ceph_wb_pagevec_pool, GFP_NOFS);
- BUG_ON(!pages);
- }
-
- len = 0;
- } else if (page->index !=
- (offset + len) >> PAGE_SHIFT) {
- if (num_ops >= (from_pool ? CEPH_OSD_SLAB_OPS :
- CEPH_OSD_MAX_OPS)) {
- redirty_page_for_writepage(wbc, page);
- unlock_page(page);
- break;
- }
-
- num_ops++;
- offset = (u64)page_offset(page);
- len = 0;
- }
+ /* note position of first page in fbatch */
+ doutc(cl, "%llx.%llx will write folio %p idx %lu\n",
+ ceph_vinop(inode), folio, folio->index);
- /* note position of first page in fbatch */
- doutc(cl, "%llx.%llx will write page %p idx %lu\n",
- ceph_vinop(inode), page, page->index);
-
- if (atomic_long_inc_return(&fsc->writeback_count) >
- CONGESTION_ON_THRESH(
- fsc->mount_options->congestion_kb))
- fsc->write_congested = true;
-
- if (IS_ENCRYPTED(inode)) {
- pages[locked_pages] =
- fscrypt_encrypt_pagecache_blocks(page,
- PAGE_SIZE, 0,
- locked_pages ? GFP_NOWAIT : GFP_NOFS);
- if (IS_ERR(pages[locked_pages])) {
- if (PTR_ERR(pages[locked_pages]) == -EINVAL)
- pr_err_client(cl,
- "inode->i_blkbits=%hhu\n",
- inode->i_blkbits);
- /* better not fail on first page! */
- BUG_ON(locked_pages == 0);
- pages[locked_pages] = NULL;
- redirty_page_for_writepage(wbc, page);
- unlock_page(page);
- break;
- }
- ++locked_pages;
- } else {
- pages[locked_pages++] = page;
- }
+ fsc->write_congested = is_write_congestion_happened(fsc);
- fbatch.folios[i] = NULL;
- len += thp_size(page);
+ rc = move_dirty_folio_in_page_array(mapping, wbc, ceph_wbc,
+ folio);
+ if (rc) {
+ folio_redirty_for_writepage(wbc, folio);
+ folio_unlock(folio);
+ break;
}
- /* did we get anything? */
- if (!locked_pages)
- goto release_folios;
- if (i) {
- unsigned j, n = 0;
- /* shift unused page to beginning of fbatch */
- for (j = 0; j < nr_folios; j++) {
- if (!fbatch.folios[j])
- continue;
- if (n < j)
- fbatch.folios[n] = fbatch.folios[j];
- n++;
- }
- fbatch.nr = n;
+ ceph_wbc->fbatch.folios[i] = NULL;
+ ceph_wbc->len += folio_size(folio);
+ }
- if (nr_folios && i == nr_folios &&
- locked_pages < max_pages) {
- doutc(cl, "reached end fbatch, trying for more\n");
- folio_batch_release(&fbatch);
- goto get_more_pages;
- }
+ ceph_wbc->processed_in_fbatch = i;
+
+ return rc;
+}
+
+static inline
+void ceph_shift_unused_folios_left(struct folio_batch *fbatch)
+{
+ unsigned j, n = 0;
+
+ /* shift unused page to beginning of fbatch */
+ for (j = 0; j < folio_batch_count(fbatch); j++) {
+ if (!fbatch->folios[j])
+ continue;
+
+ if (n < j) {
+ fbatch->folios[n] = fbatch->folios[j];
}
+ n++;
+ }
+
+ fbatch->nr = n;
+}
+
+static
+int ceph_submit_write(struct address_space *mapping,
+ struct writeback_control *wbc,
+ struct ceph_writeback_ctl *ceph_wbc)
+{
+ struct inode *inode = mapping->host;
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+ struct ceph_client *cl = fsc->client;
+ struct ceph_vino vino = ceph_vino(inode);
+ struct ceph_osd_request *req = NULL;
+ struct page *page = NULL;
+ bool caching = ceph_is_cache_enabled(inode);
+ u64 offset;
+ u64 len;
+ unsigned i;
+
new_request:
- offset = ceph_fscrypt_page_offset(pages[0]);
- len = wsize;
+ offset = ceph_fscrypt_page_offset(ceph_wbc->pages[0]);
+ len = ceph_wbc->wsize;
+ req = ceph_osdc_new_request(&fsc->client->osdc,
+ &ci->i_layout, vino,
+ offset, &len, 0, ceph_wbc->num_ops,
+ CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE,
+ ceph_wbc->snapc, ceph_wbc->truncate_seq,
+ ceph_wbc->truncate_size, false);
+ if (IS_ERR(req)) {
req = ceph_osdc_new_request(&fsc->client->osdc,
- &ci->i_layout, vino,
- offset, &len, 0, num_ops,
- CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE,
- snapc, ceph_wbc.truncate_seq,
- ceph_wbc.truncate_size, false);
- if (IS_ERR(req)) {
- req = ceph_osdc_new_request(&fsc->client->osdc,
- &ci->i_layout, vino,
- offset, &len, 0,
- min(num_ops,
- CEPH_OSD_SLAB_OPS),
- CEPH_OSD_OP_WRITE,
- CEPH_OSD_FLAG_WRITE,
- snapc, ceph_wbc.truncate_seq,
- ceph_wbc.truncate_size, true);
- BUG_ON(IS_ERR(req));
+ &ci->i_layout, vino,
+ offset, &len, 0,
+ min(ceph_wbc->num_ops,
+ CEPH_OSD_SLAB_OPS),
+ CEPH_OSD_OP_WRITE,
+ CEPH_OSD_FLAG_WRITE,
+ ceph_wbc->snapc,
+ ceph_wbc->truncate_seq,
+ ceph_wbc->truncate_size,
+ true);
+ BUG_ON(IS_ERR(req));
+ }
+
+ page = ceph_wbc->pages[ceph_wbc->locked_pages - 1];
+ BUG_ON(len < ceph_fscrypt_page_offset(page) + thp_size(page) - offset);
+
+ if (!ceph_inc_osd_stopping_blocker(fsc->mdsc)) {
+ for (i = 0; i < folio_batch_count(&ceph_wbc->fbatch); i++) {
+ struct folio *folio = ceph_wbc->fbatch.folios[i];
+
+ if (!folio)
+ continue;
+
+ page = &folio->page;
+ redirty_page_for_writepage(wbc, page);
+ unlock_page(page);
}
- BUG_ON(len < ceph_fscrypt_page_offset(pages[locked_pages - 1]) +
- thp_size(pages[locked_pages - 1]) - offset);
- if (!ceph_inc_osd_stopping_blocker(fsc->mdsc)) {
- rc = -EIO;
- goto release_folios;
+ for (i = 0; i < ceph_wbc->locked_pages; i++) {
+ page = ceph_fscrypt_pagecache_page(ceph_wbc->pages[i]);
+
+ if (!page)
+ continue;
+
+ redirty_page_for_writepage(wbc, page);
+ unlock_page(page);
}
- req->r_callback = writepages_finish;
- req->r_inode = inode;
-
- /* Format the osd request message and submit the write */
- len = 0;
- data_pages = pages;
- op_idx = 0;
- for (i = 0; i < locked_pages; i++) {
- struct page *page = ceph_fscrypt_pagecache_page(pages[i]);
-
- u64 cur_offset = page_offset(page);
- /*
- * Discontinuity in page range? Ceph can handle that by just passing
- * multiple extents in the write op.
- */
- if (offset + len != cur_offset) {
- /* If it's full, stop here */
- if (op_idx + 1 == req->r_num_ops)
- break;
-
- /* Kick off an fscache write with what we have so far. */
- ceph_fscache_write_to_cache(inode, offset, len, caching);
-
- /* Start a new extent */
- osd_req_op_extent_dup_last(req, op_idx,
- cur_offset - offset);
- doutc(cl, "got pages at %llu~%llu\n", offset,
- len);
- osd_req_op_extent_osd_data_pages(req, op_idx,
- data_pages, len, 0,
- from_pool, false);
- osd_req_op_extent_update(req, op_idx, len);
-
- len = 0;
- offset = cur_offset;
- data_pages = pages + i;
- op_idx++;
- }
- set_page_writeback(page);
- if (caching)
- ceph_set_page_fscache(page);
- len += thp_size(page);
+ ceph_osdc_put_request(req);
+ return -EIO;
+ }
+
+ req->r_callback = writepages_finish;
+ req->r_inode = inode;
+
+ /* Format the osd request message and submit the write */
+ len = 0;
+ ceph_wbc->data_pages = ceph_wbc->pages;
+ ceph_wbc->op_idx = 0;
+ for (i = 0; i < ceph_wbc->locked_pages; i++) {
+ u64 cur_offset;
+
+ page = ceph_fscrypt_pagecache_page(ceph_wbc->pages[i]);
+ cur_offset = page_offset(page);
+
+ /*
+ * Discontinuity in page range? Ceph can handle that by just passing
+ * multiple extents in the write op.
+ */
+ if (offset + len != cur_offset) {
+ /* If it's full, stop here */
+ if (ceph_wbc->op_idx + 1 == req->r_num_ops)
+ break;
+
+ /* Kick off an fscache write with what we have so far. */
+ ceph_fscache_write_to_cache(inode, offset, len, caching);
+
+ /* Start a new extent */
+ osd_req_op_extent_dup_last(req, ceph_wbc->op_idx,
+ cur_offset - offset);
+
+ doutc(cl, "got pages at %llu~%llu\n", offset, len);
+
+ osd_req_op_extent_osd_data_pages(req, ceph_wbc->op_idx,
+ ceph_wbc->data_pages,
+ len, 0,
+ ceph_wbc->from_pool,
+ false);
+ osd_req_op_extent_update(req, ceph_wbc->op_idx, len);
+
+ len = 0;
+ offset = cur_offset;
+ ceph_wbc->data_pages = ceph_wbc->pages + i;
+ ceph_wbc->op_idx++;
}
- ceph_fscache_write_to_cache(inode, offset, len, caching);
-
- if (ceph_wbc.size_stable) {
- len = min(len, ceph_wbc.i_size - offset);
- } else if (i == locked_pages) {
- /* writepages_finish() clears writeback pages
- * according to the data length, so make sure
- * data length covers all locked pages */
- u64 min_len = len + 1 - thp_size(page);
- len = get_writepages_data_length(inode, pages[i - 1],
- offset);
- len = max(len, min_len);
+
+ set_page_writeback(page);
+
+ if (caching)
+ ceph_set_page_fscache(page);
+
+ len += thp_size(page);
+ }
+
+ ceph_fscache_write_to_cache(inode, offset, len, caching);
+
+ if (ceph_wbc->size_stable) {
+ len = min(len, ceph_wbc->i_size - offset);
+ } else if (i == ceph_wbc->locked_pages) {
+ /* writepages_finish() clears writeback pages
+ * according to the data length, so make sure
+ * data length covers all locked pages */
+ u64 min_len = len + 1 - thp_size(page);
+ len = get_writepages_data_length(inode,
+ ceph_wbc->pages[i - 1],
+ offset);
+ len = max(len, min_len);
+ }
+
+ if (IS_ENCRYPTED(inode))
+ len = round_up(len, CEPH_FSCRYPT_BLOCK_SIZE);
+
+ doutc(cl, "got pages at %llu~%llu\n", offset, len);
+
+ if (IS_ENCRYPTED(inode) &&
+ ((offset | len) & ~CEPH_FSCRYPT_BLOCK_MASK)) {
+ pr_warn_client(cl,
+ "bad encrypted write offset=%lld len=%llu\n",
+ offset, len);
+ }
+
+ osd_req_op_extent_osd_data_pages(req, ceph_wbc->op_idx,
+ ceph_wbc->data_pages, len,
+ 0, ceph_wbc->from_pool, false);
+ osd_req_op_extent_update(req, ceph_wbc->op_idx, len);
+
+ BUG_ON(ceph_wbc->op_idx + 1 != req->r_num_ops);
+
+ ceph_wbc->from_pool = false;
+ if (i < ceph_wbc->locked_pages) {
+ BUG_ON(ceph_wbc->num_ops <= req->r_num_ops);
+ ceph_wbc->num_ops -= req->r_num_ops;
+ ceph_wbc->locked_pages -= i;
+
+ /* allocate new pages array for next request */
+ ceph_wbc->data_pages = ceph_wbc->pages;
+ __ceph_allocate_page_array(ceph_wbc, ceph_wbc->locked_pages);
+ memcpy(ceph_wbc->pages, ceph_wbc->data_pages + i,
+ ceph_wbc->locked_pages * sizeof(*ceph_wbc->pages));
+ memset(ceph_wbc->data_pages + i, 0,
+ ceph_wbc->locked_pages * sizeof(*ceph_wbc->pages));
+ } else {
+ BUG_ON(ceph_wbc->num_ops != req->r_num_ops);
+ /* request message now owns the pages array */
+ ceph_wbc->pages = NULL;
+ }
+
+ req->r_mtime = inode_get_mtime(inode);
+ ceph_osdc_start_request(&fsc->client->osdc, req);
+ req = NULL;
+
+ wbc->nr_to_write -= i;
+ if (ceph_wbc->pages)
+ goto new_request;
+
+ return 0;
+}
+
+static
+void ceph_wait_until_current_writes_complete(struct address_space *mapping,
+ struct writeback_control *wbc,
+ struct ceph_writeback_ctl *ceph_wbc)
+{
+ struct page *page;
+ unsigned i, nr;
+
+ if (wbc->sync_mode != WB_SYNC_NONE &&
+ ceph_wbc->start_index == 0 && /* all dirty pages were checked */
+ !ceph_wbc->head_snapc) {
+ ceph_wbc->index = 0;
+
+ while ((ceph_wbc->index <= ceph_wbc->end) &&
+ (nr = filemap_get_folios_tag(mapping,
+ &ceph_wbc->index,
+ (pgoff_t)-1,
+ PAGECACHE_TAG_WRITEBACK,
+ &ceph_wbc->fbatch))) {
+ for (i = 0; i < nr; i++) {
+ page = &ceph_wbc->fbatch.folios[i]->page;
+ if (page_snap_context(page) != ceph_wbc->snapc)
+ continue;
+ wait_on_page_writeback(page);
+ }
+
+ folio_batch_release(&ceph_wbc->fbatch);
+ cond_resched();
}
- if (IS_ENCRYPTED(inode))
- len = round_up(len, CEPH_FSCRYPT_BLOCK_SIZE);
+ }
+}
- doutc(cl, "got pages at %llu~%llu\n", offset, len);
+/*
+ * initiate async writeback
+ */
+static int ceph_writepages_start(struct address_space *mapping,
+ struct writeback_control *wbc)
+{
+ struct inode *inode = mapping->host;
+ struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+ struct ceph_client *cl = fsc->client;
+ struct ceph_writeback_ctl ceph_wbc;
+ int rc = 0;
- if (IS_ENCRYPTED(inode) &&
- ((offset | len) & ~CEPH_FSCRYPT_BLOCK_MASK))
- pr_warn_client(cl,
- "bad encrypted write offset=%lld len=%llu\n",
- offset, len);
-
- osd_req_op_extent_osd_data_pages(req, op_idx, data_pages, len,
- 0, from_pool, false);
- osd_req_op_extent_update(req, op_idx, len);
-
- BUG_ON(op_idx + 1 != req->r_num_ops);
-
- from_pool = false;
- if (i < locked_pages) {
- BUG_ON(num_ops <= req->r_num_ops);
- num_ops -= req->r_num_ops;
- locked_pages -= i;
-
- /* allocate new pages array for next request */
- data_pages = pages;
- pages = kmalloc_array(locked_pages, sizeof(*pages),
- GFP_NOFS);
- if (!pages) {
- from_pool = true;
- pages = mempool_alloc(ceph_wb_pagevec_pool, GFP_NOFS);
- BUG_ON(!pages);
+ if (wbc->sync_mode == WB_SYNC_NONE && fsc->write_congested)
+ return 0;
+
+ doutc(cl, "%llx.%llx (mode=%s)\n", ceph_vinop(inode),
+ wbc->sync_mode == WB_SYNC_NONE ? "NONE" :
+ (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
+
+ if (is_forced_umount(mapping)) {
+ /* we're in a forced umount, don't write! */
+ return -EIO;
+ }
+
+ ceph_init_writeback_ctl(mapping, wbc, &ceph_wbc);
+
+ if (!ceph_inc_osd_stopping_blocker(fsc->mdsc)) {
+ rc = -EIO;
+ goto out;
+ }
+
+retry:
+ rc = ceph_define_writeback_range(mapping, wbc, &ceph_wbc);
+ if (rc == -ENODATA) {
+ /* hmm, why does writepages get called when there
+ is no dirty data? */
+ rc = 0;
+ goto dec_osd_stopping_blocker;
+ }
+
+ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
+ tag_pages_for_writeback(mapping, ceph_wbc.index, ceph_wbc.end);
+
+ while (!has_writeback_done(&ceph_wbc)) {
+ ceph_wbc.locked_pages = 0;
+ ceph_wbc.max_pages = ceph_wbc.wsize >> PAGE_SHIFT;
+
+get_more_pages:
+ ceph_folio_batch_reinit(&ceph_wbc);
+
+ ceph_wbc.nr_folios = filemap_get_folios_tag(mapping,
+ &ceph_wbc.index,
+ ceph_wbc.end,
+ ceph_wbc.tag,
+ &ceph_wbc.fbatch);
+ doutc(cl, "pagevec_lookup_range_tag for tag %#x got %d\n",
+ ceph_wbc.tag, ceph_wbc.nr_folios);
+
+ if (!ceph_wbc.nr_folios && !ceph_wbc.locked_pages)
+ break;
+
+process_folio_batch:
+ rc = ceph_process_folio_batch(mapping, wbc, &ceph_wbc);
+ if (rc)
+ goto release_folios;
+
+ /* did we get anything? */
+ if (!ceph_wbc.locked_pages)
+ goto release_folios;
+
+ if (ceph_wbc.processed_in_fbatch) {
+ ceph_shift_unused_folios_left(&ceph_wbc.fbatch);
+
+ if (folio_batch_count(&ceph_wbc.fbatch) == 0 &&
+ ceph_wbc.locked_pages < ceph_wbc.max_pages) {
+ doutc(cl, "reached end fbatch, trying for more\n");
+ goto get_more_pages;
}
- memcpy(pages, data_pages + i,
- locked_pages * sizeof(*pages));
- memset(data_pages + i, 0,
- locked_pages * sizeof(*pages));
- } else {
- BUG_ON(num_ops != req->r_num_ops);
- index = pages[i - 1]->index + 1;
- /* request message now owns the pages array */
- pages = NULL;
}
- req->r_mtime = inode_get_mtime(inode);
- ceph_osdc_start_request(&fsc->client->osdc, req);
- req = NULL;
+ rc = ceph_submit_write(mapping, wbc, &ceph_wbc);
+ if (rc)
+ goto release_folios;
+
+ ceph_wbc.locked_pages = 0;
+ ceph_wbc.strip_unit_end = 0;
- wbc->nr_to_write -= i;
- if (pages)
- goto new_request;
+ if (folio_batch_count(&ceph_wbc.fbatch) > 0) {
+ ceph_wbc.nr_folios =
+ folio_batch_count(&ceph_wbc.fbatch);
+ goto process_folio_batch;
+ }
/*
* We stop writing back only if we are not doing
@@ -1343,61 +1713,44 @@ new_request:
* we tagged for writeback prior to entering this loop.
*/
if (wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE)
- done = true;
+ ceph_wbc.done = true;
release_folios:
doutc(cl, "folio_batch release on %d folios (%p)\n",
- (int)fbatch.nr, fbatch.nr ? fbatch.folios[0] : NULL);
- folio_batch_release(&fbatch);
+ (int)ceph_wbc.fbatch.nr,
+ ceph_wbc.fbatch.nr ? ceph_wbc.fbatch.folios[0] : NULL);
+ folio_batch_release(&ceph_wbc.fbatch);
}
- if (should_loop && !done) {
+ if (ceph_wbc.should_loop && !ceph_wbc.done) {
/* more to do; loop back to beginning of file */
doutc(cl, "looping back to beginning of file\n");
- end = start_index - 1; /* OK even when start_index == 0 */
+ /* OK even when start_index == 0 */
+ ceph_wbc.end = ceph_wbc.start_index - 1;
/* to write dirty pages associated with next snapc,
* we need to wait until current writes complete */
- if (wbc->sync_mode != WB_SYNC_NONE &&
- start_index == 0 && /* all dirty pages were checked */
- !ceph_wbc.head_snapc) {
- struct page *page;
- unsigned i, nr;
- index = 0;
- while ((index <= end) &&
- (nr = filemap_get_folios_tag(mapping, &index,
- (pgoff_t)-1,
- PAGECACHE_TAG_WRITEBACK,
- &fbatch))) {
- for (i = 0; i < nr; i++) {
- page = &fbatch.folios[i]->page;
- if (page_snap_context(page) != snapc)
- continue;
- wait_on_page_writeback(page);
- }
- folio_batch_release(&fbatch);
- cond_resched();
- }
- }
+ ceph_wait_until_current_writes_complete(mapping, wbc, &ceph_wbc);
- start_index = 0;
- index = 0;
+ ceph_wbc.start_index = 0;
+ ceph_wbc.index = 0;
goto retry;
}
- if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
- mapping->writeback_index = index;
+ if (wbc->range_cyclic || (ceph_wbc.range_whole && wbc->nr_to_write > 0))
+ mapping->writeback_index = ceph_wbc.index;
+
+dec_osd_stopping_blocker:
+ ceph_dec_osd_stopping_blocker(fsc->mdsc);
out:
- ceph_osdc_put_request(req);
- ceph_put_snap_context(last_snapc);
+ ceph_put_snap_context(ceph_wbc.last_snapc);
doutc(cl, "%llx.%llx dend - startone, rc = %d\n", ceph_vinop(inode),
rc);
+
return rc;
}
-
-
/*
* See if a given @snapc is either writeable, or already written.
*/
@@ -1413,56 +1766,56 @@ static int context_is_writeable_or_written(struct inode *inode,
/**
* ceph_find_incompatible - find an incompatible context and return it
- * @page: page being dirtied
+ * @folio: folio being dirtied
*
- * We are only allowed to write into/dirty a page if the page is
+ * We are only allowed to write into/dirty a folio if the folio is
* clean, or already dirty within the same snap context. Returns a
* conflicting context if there is one, NULL if there isn't, or a
* negative error code on other errors.
*
- * Must be called with page lock held.
+ * Must be called with folio lock held.
*/
static struct ceph_snap_context *
-ceph_find_incompatible(struct page *page)
+ceph_find_incompatible(struct folio *folio)
{
- struct inode *inode = page->mapping->host;
+ struct inode *inode = folio->mapping->host;
struct ceph_client *cl = ceph_inode_to_client(inode);
struct ceph_inode_info *ci = ceph_inode(inode);
if (ceph_inode_is_shutdown(inode)) {
- doutc(cl, " %llx.%llx page %p is shutdown\n",
- ceph_vinop(inode), page);
+ doutc(cl, " %llx.%llx folio %p is shutdown\n",
+ ceph_vinop(inode), folio);
return ERR_PTR(-ESTALE);
}
for (;;) {
struct ceph_snap_context *snapc, *oldest;
- wait_on_page_writeback(page);
+ folio_wait_writeback(folio);
- snapc = page_snap_context(page);
+ snapc = page_snap_context(&folio->page);
if (!snapc || snapc == ci->i_head_snapc)
break;
/*
- * this page is already dirty in another (older) snap
+ * this folio is already dirty in another (older) snap
* context! is it writeable now?
*/
oldest = get_oldest_context(inode, NULL, NULL);
if (snapc->seq > oldest->seq) {
/* not writeable -- return it for the caller to deal with */
ceph_put_snap_context(oldest);
- doutc(cl, " %llx.%llx page %p snapc %p not current or oldest\n",
- ceph_vinop(inode), page, snapc);
+ doutc(cl, " %llx.%llx folio %p snapc %p not current or oldest\n",
+ ceph_vinop(inode), folio, snapc);
return ceph_get_snap_context(snapc);
}
ceph_put_snap_context(oldest);
- /* yay, writeable, do it now (without dropping page lock) */
- doutc(cl, " %llx.%llx page %p snapc %p not current, but oldest\n",
- ceph_vinop(inode), page, snapc);
- if (clear_page_dirty_for_io(page)) {
- int r = writepage_nounlock(page, NULL);
+ /* yay, writeable, do it now (without dropping folio lock) */
+ doutc(cl, " %llx.%llx folio %p snapc %p not current, but oldest\n",
+ ceph_vinop(inode), folio, snapc);
+ if (folio_clear_dirty_for_io(folio)) {
+ int r = write_folio_nounlock(folio, NULL);
if (r < 0)
return ERR_PTR(r);
}
@@ -1477,7 +1830,7 @@ static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_snap_context *snapc;
- snapc = ceph_find_incompatible(folio_page(*foliop, 0));
+ snapc = ceph_find_incompatible(*foliop);
if (snapc) {
int r;
@@ -1502,20 +1855,18 @@ static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned
*/
static int ceph_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len,
- struct page **pagep, void **fsdata)
+ struct folio **foliop, void **fsdata)
{
struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
- struct folio *folio = NULL;
int r;
- r = netfs_write_begin(&ci->netfs, file, inode->i_mapping, pos, len, &folio, NULL);
+ r = netfs_write_begin(&ci->netfs, file, inode->i_mapping, pos, len, foliop, NULL);
if (r < 0)
return r;
- folio_wait_fscache(folio);
- WARN_ON_ONCE(!folio_test_locked(folio));
- *pagep = &folio->page;
+ folio_wait_private_2(*foliop); /* [DEPRECATED] */
+ WARN_ON_ONCE(!folio_test_locked(*foliop));
return 0;
}
@@ -1525,9 +1876,8 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping,
*/
static int ceph_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
- struct page *subpage, void *fsdata)
+ struct folio *folio, void *fsdata)
{
- struct folio *folio = page_folio(subpage);
struct inode *inode = file_inode(file);
struct ceph_client *cl = ceph_inode_to_client(inode);
bool check_cap = false;
@@ -1563,7 +1913,6 @@ out:
const struct address_space_operations ceph_aops = {
.read_folio = netfs_read_folio,
.readahead = netfs_readahead,
- .writepage = ceph_writepage,
.writepages = ceph_writepages_start,
.write_begin = ceph_write_begin,
.write_end = ceph_write_end,
@@ -1571,6 +1920,7 @@ const struct address_space_operations ceph_aops = {
.invalidate_folio = ceph_invalidate_folio,
.release_folio = netfs_release_folio,
.direct_IO = noop_direct_IO,
+ .migrate_folio = filemap_migrate_folio,
};
static void ceph_block_sigs(sigset_t *oldset)
@@ -1687,8 +2037,8 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_file_info *fi = vma->vm_file->private_data;
struct ceph_cap_flush *prealloc_cf;
- struct page *page = vmf->page;
- loff_t off = page_offset(page);
+ struct folio *folio = page_folio(vmf->page);
+ loff_t off = folio_pos(folio);
loff_t size = i_size_read(inode);
size_t len;
int want, got, err;
@@ -1705,10 +2055,10 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
sb_start_pagefault(inode->i_sb);
ceph_block_sigs(&oldset);
- if (off + thp_size(page) <= size)
- len = thp_size(page);
+ if (off + folio_size(folio) <= size)
+ len = folio_size(folio);
else
- len = offset_in_thp(page, size);
+ len = offset_in_folio(folio, size);
doutc(cl, "%llx.%llx %llu~%zd getting caps i_size %llu\n",
ceph_vinop(inode), off, len, size);
@@ -1725,30 +2075,30 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
doutc(cl, "%llx.%llx %llu~%zd got cap refs on %s\n", ceph_vinop(inode),
off, len, ceph_cap_string(got));
- /* Update time before taking page lock */
+ /* Update time before taking folio lock */
file_update_time(vma->vm_file);
inode_inc_iversion_raw(inode);
do {
struct ceph_snap_context *snapc;
- lock_page(page);
+ folio_lock(folio);
- if (page_mkwrite_check_truncate(page, inode) < 0) {
- unlock_page(page);
+ if (folio_mkwrite_check_truncate(folio, inode) < 0) {
+ folio_unlock(folio);
ret = VM_FAULT_NOPAGE;
break;
}
- snapc = ceph_find_incompatible(page);
+ snapc = ceph_find_incompatible(folio);
if (!snapc) {
- /* success. we'll keep the page locked. */
- set_page_dirty(page);
+ /* success. we'll keep the folio locked. */
+ folio_mark_dirty(folio);
ret = VM_FAULT_LOCKED;
break;
}
- unlock_page(page);
+ folio_unlock(folio);
if (IS_ERR(snapc)) {
ret = VM_FAULT_SIGBUS;
@@ -2127,7 +2477,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
}
pool_ns_len = pool_ns ? pool_ns->len : 0;
- perm = kmalloc(sizeof(*perm) + pool_ns_len + 1, GFP_NOFS);
+ perm = kmalloc(struct_size(perm, pool_ns, pool_ns_len + 1), GFP_NOFS);
if (!perm) {
err = -ENOMEM;
goto out_unlock;
@@ -2174,7 +2524,7 @@ int ceph_pool_perm_check(struct inode *inode, int need)
if (ci->i_vino.snap != CEPH_NOSNAP) {
/*
* Pool permission check needs to write to the first object.
- * But for snapshot, head of the first object may have alread
+ * But for snapshot, head of the first object may have already
* been deleted. Skip check to avoid creating orphan object.
*/
return 0;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index c4941ba245ac..a8d8b56cf9d2 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -10,6 +10,7 @@
#include <linux/writeback.h>
#include <linux/iversion.h>
#include <linux/filelock.h>
+#include <linux/jiffies.h>
#include "super.h"
#include "mds_client.h"
@@ -977,20 +978,6 @@ int __ceph_caps_revoking_other(struct ceph_inode_info *ci,
return 0;
}
-int ceph_caps_revoking(struct ceph_inode_info *ci, int mask)
-{
- struct inode *inode = &ci->netfs.inode;
- struct ceph_client *cl = ceph_inode_to_client(inode);
- int ret;
-
- spin_lock(&ci->i_ceph_lock);
- ret = __ceph_caps_revoking_other(ci, NULL, mask);
- spin_unlock(&ci->i_ceph_lock);
- doutc(cl, "%p %llx.%llx %s = %d\n", inode, ceph_vinop(inode),
- ceph_cap_string(mask), ret);
- return ret;
-}
-
int __ceph_caps_used(struct ceph_inode_info *ci)
{
int used = 0;
@@ -2016,6 +2003,8 @@ bool __ceph_should_report_size(struct ceph_inode_info *ci)
* CHECK_CAPS_AUTHONLY - we should only check the auth cap
* CHECK_CAPS_FLUSH - we should flush any dirty caps immediately, without
* further delay.
+ * CHECK_CAPS_FLUSH_FORCE - we should flush any caps immediately, without
+ * further delay.
*/
void ceph_check_caps(struct ceph_inode_info *ci, int flags)
{
@@ -2097,7 +2086,7 @@ retry:
}
doutc(cl, "%p %llx.%llx file_want %s used %s dirty %s "
- "flushing %s issued %s revoking %s retain %s %s%s%s\n",
+ "flushing %s issued %s revoking %s retain %s %s%s%s%s\n",
inode, ceph_vinop(inode), ceph_cap_string(file_wanted),
ceph_cap_string(used), ceph_cap_string(ci->i_dirty_caps),
ceph_cap_string(ci->i_flushing_caps),
@@ -2105,7 +2094,8 @@ retry:
ceph_cap_string(retain),
(flags & CHECK_CAPS_AUTHONLY) ? " AUTHONLY" : "",
(flags & CHECK_CAPS_FLUSH) ? " FLUSH" : "",
- (flags & CHECK_CAPS_NOINVAL) ? " NOINVAL" : "");
+ (flags & CHECK_CAPS_NOINVAL) ? " NOINVAL" : "",
+ (flags & CHECK_CAPS_FLUSH_FORCE) ? " FLUSH_FORCE" : "");
/*
* If we no longer need to hold onto old our caps, and we may
@@ -2180,6 +2170,11 @@ retry:
queue_writeback = true;
}
+ if (flags & CHECK_CAPS_FLUSH_FORCE) {
+ doutc(cl, "force to flush caps\n");
+ goto ack;
+ }
+
if (cap == ci->i_auth_cap &&
(cap->issued & CEPH_CAP_FILE_WR)) {
/* request larger max_size from MDS? */
@@ -2804,7 +2799,7 @@ void ceph_take_cap_refs(struct ceph_inode_info *ci, int got,
* requested from the MDS.
*
* Returns 0 if caps were not able to be acquired (yet), 1 if succeed,
- * or a negative error code. There are 3 speical error codes:
+ * or a negative error code. There are 3 special error codes:
* -EAGAIN: need to sleep but non-blocking is specified
* -EFBIG: ask caller to call check_max_size() and try again.
* -EUCLEAN: ask caller to call ceph_renew_caps() and try again.
@@ -3067,10 +3062,13 @@ int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need,
flags, &_got);
WARN_ON_ONCE(ret == -EAGAIN);
if (!ret) {
+#ifdef CONFIG_DEBUG_FS
struct ceph_mds_client *mdsc = fsc->mdsc;
struct cap_wait cw;
+#endif
DEFINE_WAIT_FUNC(wait, woken_wake_function);
+#ifdef CONFIG_DEBUG_FS
cw.ino = ceph_ino(inode);
cw.tgid = current->tgid;
cw.need = need;
@@ -3079,6 +3077,7 @@ int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need,
spin_lock(&mdsc->caps_list_lock);
list_add(&cw.list, &mdsc->cap_wait_list);
spin_unlock(&mdsc->caps_list_lock);
+#endif
/* make sure used fmode not timeout */
ceph_get_fmode(ci, flags, FMODE_WAIT_BIAS);
@@ -3097,9 +3096,11 @@ int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need,
remove_wait_queue(&ci->i_cap_wq, &wait);
ceph_put_fmode(ci, flags, FMODE_WAIT_BIAS);
+#ifdef CONFIG_DEBUG_FS
spin_lock(&mdsc->caps_list_lock);
list_del(&cw.list);
spin_unlock(&mdsc->caps_list_lock);
+#endif
if (ret == -EAGAIN)
continue;
@@ -3504,6 +3505,8 @@ static void handle_cap_grant(struct inode *inode,
bool queue_invalidate = false;
bool deleted_inode = false;
bool fill_inline = false;
+ bool revoke_wait = false;
+ int flags = 0;
/*
* If there is at least one crypto block then we'll trust
@@ -3699,16 +3702,18 @@ static void handle_cap_grant(struct inode *inode,
ceph_cap_string(cap->issued), ceph_cap_string(newcaps),
ceph_cap_string(revoking));
if (S_ISREG(inode->i_mode) &&
- (revoking & used & CEPH_CAP_FILE_BUFFER))
+ (revoking & used & CEPH_CAP_FILE_BUFFER)) {
writeback = true; /* initiate writeback; will delay ack */
- else if (queue_invalidate &&
+ revoke_wait = true;
+ } else if (queue_invalidate &&
revoking == CEPH_CAP_FILE_CACHE &&
- (newcaps & CEPH_CAP_FILE_LAZYIO) == 0)
- ; /* do nothing yet, invalidation will be queued */
- else if (cap == ci->i_auth_cap)
+ (newcaps & CEPH_CAP_FILE_LAZYIO) == 0) {
+ revoke_wait = true; /* do nothing yet, invalidation will be queued */
+ } else if (cap == ci->i_auth_cap) {
check_caps = 1; /* check auth cap only */
- else
+ } else {
check_caps = 2; /* check all caps */
+ }
/* If there is new caps, try to wake up the waiters */
if (~cap->issued & newcaps)
wake = true;
@@ -3735,8 +3740,9 @@ static void handle_cap_grant(struct inode *inode,
BUG_ON(cap->issued & ~cap->implemented);
/* don't let check_caps skip sending a response to MDS for revoke msgs */
- if (le32_to_cpu(grant->op) == CEPH_CAP_OP_REVOKE) {
+ if (!revoke_wait && le32_to_cpu(grant->op) == CEPH_CAP_OP_REVOKE) {
cap->mds_wanted = 0;
+ flags |= CHECK_CAPS_FLUSH_FORCE;
if (cap == ci->i_auth_cap)
check_caps = 1; /* check auth cap only */
else
@@ -3792,9 +3798,9 @@ static void handle_cap_grant(struct inode *inode,
mutex_unlock(&session->s_mutex);
if (check_caps == 1)
- ceph_check_caps(ci, CHECK_CAPS_AUTHONLY | CHECK_CAPS_NOINVAL);
+ ceph_check_caps(ci, flags | CHECK_CAPS_AUTHONLY | CHECK_CAPS_NOINVAL);
else if (check_caps == 2)
- ceph_check_caps(ci, CHECK_CAPS_NOINVAL);
+ ceph_check_caps(ci, flags | CHECK_CAPS_NOINVAL);
}
/*
@@ -4065,23 +4071,22 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex,
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);
- unsigned t_seq, t_mseq;
+ u32 t_issue_seq, t_mseq;
int target, issued;
int mds = session->s_mds;
if (ph) {
t_cap_id = le64_to_cpu(ph->cap_id);
- t_seq = le32_to_cpu(ph->seq);
+ t_issue_seq = le32_to_cpu(ph->issue_seq);
t_mseq = le32_to_cpu(ph->mseq);
target = le32_to_cpu(ph->mds);
} else {
- t_cap_id = t_seq = t_mseq = 0;
+ t_cap_id = t_issue_seq = t_mseq = 0;
target = -1;
}
- doutc(cl, "%p %llx.%llx ci %p mds%d mseq %d target %d\n",
- inode, ceph_vinop(inode), ci, mds, mseq, target);
+ doutc(cl, " cap %llx.%llx export to peer %d piseq %u pmseq %u\n",
+ ceph_vinop(inode), target, t_issue_seq, t_mseq);
retry:
down_read(&mdsc->snap_rwsem);
spin_lock(&ci->i_ceph_lock);
@@ -4114,12 +4119,12 @@ retry:
if (tcap) {
/* already have caps from the target */
if (tcap->cap_id == t_cap_id &&
- ceph_seq_cmp(tcap->seq, t_seq) < 0) {
+ ceph_seq_cmp(tcap->seq, t_issue_seq) < 0) {
doutc(cl, " updating import cap %p mds%d\n", tcap,
target);
tcap->cap_id = t_cap_id;
- tcap->seq = t_seq - 1;
- tcap->issue_seq = t_seq - 1;
+ tcap->seq = t_issue_seq - 1;
+ tcap->issue_seq = t_issue_seq - 1;
tcap->issued |= issued;
tcap->implemented |= issued;
if (cap == ci->i_auth_cap) {
@@ -4130,11 +4135,11 @@ retry:
ceph_remove_cap(mdsc, cap, false);
goto out_unlock;
} else if (tsession) {
- /* add placeholder for the export tagert */
+ /* add placeholder for the export target */
int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0;
tcap = new_cap;
ceph_add_cap(inode, tsession, t_cap_id, issued, 0,
- t_seq - 1, t_mseq, (u64)-1, flag, &new_cap);
+ t_issue_seq - 1, t_mseq, (u64)-1, flag, &new_cap);
if (!list_empty(&ci->i_cap_flush_list) &&
ci->i_auth_cap == tcap) {
@@ -4208,18 +4213,22 @@ static void handle_cap_import(struct ceph_mds_client *mdsc,
u64 realmino = le64_to_cpu(im->realm);
u64 cap_id = le64_to_cpu(im->cap_id);
u64 p_cap_id;
+ u32 piseq = 0;
+ u32 pmseq = 0;
int peer;
if (ph) {
p_cap_id = le64_to_cpu(ph->cap_id);
peer = le32_to_cpu(ph->mds);
+ piseq = le32_to_cpu(ph->issue_seq);
+ pmseq = le32_to_cpu(ph->mseq);
} else {
p_cap_id = 0;
peer = -1;
}
- doutc(cl, "%p %llx.%llx ci %p mds%d mseq %d peer %d\n",
- inode, ceph_vinop(inode), ci, mds, mseq, peer);
+ doutc(cl, " cap %llx.%llx import from peer %d piseq %u pmseq %u\n",
+ ceph_vinop(inode), peer, piseq, pmseq);
retry:
cap = __get_cap_for_mds(ci, mds);
if (!cap) {
@@ -4248,15 +4257,13 @@ retry:
doutc(cl, " remove export cap %p mds%d flags %d\n",
ocap, peer, ph->flags);
if ((ph->flags & CEPH_CAP_FLAG_AUTH) &&
- (ocap->seq != le32_to_cpu(ph->seq) ||
- ocap->mseq != le32_to_cpu(ph->mseq))) {
+ (ocap->seq != piseq ||
+ ocap->mseq != pmseq)) {
pr_err_ratelimited_client(cl, "mismatched seq/mseq: "
"%p %llx.%llx mds%d seq %d mseq %d"
" importer mds%d has peer seq %d mseq %d\n",
inode, ceph_vinop(inode), peer,
- ocap->seq, ocap->mseq, mds,
- le32_to_cpu(ph->seq),
- le32_to_cpu(ph->mseq));
+ ocap->seq, ocap->mseq, mds, piseq, pmseq);
}
ceph_remove_cap(mdsc, ocap, (ph->flags & CEPH_CAP_FLAG_RELEASE));
}
@@ -4330,7 +4337,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
struct ceph_snap_realm *realm = NULL;
int op;
int msg_version = le16_to_cpu(msg->hdr.version);
- u32 seq, mseq;
+ u32 seq, mseq, issue_seq;
struct ceph_vino vino;
void *snaptrace;
size_t snaptrace_len;
@@ -4340,8 +4347,6 @@ void ceph_handle_caps(struct ceph_mds_session *session,
bool close_sessions = false;
bool do_cap_release = false;
- doutc(cl, "from mds%d\n", session->s_mds);
-
if (!ceph_inc_mds_stopping_blocker(mdsc, session))
return;
@@ -4355,6 +4360,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
vino.snap = CEPH_NOSNAP;
seq = le32_to_cpu(h->seq);
mseq = le32_to_cpu(h->migrate_seq);
+ issue_seq = le32_to_cpu(h->issue_seq);
snaptrace = h + 1;
snaptrace_len = le32_to_cpu(h->snap_trace_len);
@@ -4442,12 +4448,11 @@ void ceph_handle_caps(struct ceph_mds_session *session,
/* lookup ino */
inode = ceph_find_inode(mdsc->fsc->sb, vino);
- doutc(cl, " op %s ino %llx.%llx inode %p\n", ceph_cap_op_name(op),
- vino.ino, vino.snap, inode);
+ doutc(cl, " caps mds%d op %s ino %llx.%llx inode %p seq %u iseq %u mseq %u\n",
+ session->s_mds, ceph_cap_op_name(op), vino.ino, vino.snap, inode,
+ seq, issue_seq, mseq);
mutex_lock(&session->s_mutex);
- doutc(cl, " mds%d seq %lld cap seq %u\n", session->s_mds,
- session->s_seq, (unsigned)seq);
if (!inode) {
doutc(cl, " i don't have ino %llx\n", vino.ino);
@@ -4583,7 +4588,7 @@ flush_cap_releases:
__ceph_queue_cap_release(session, cap);
spin_unlock(&session->s_cap_lock);
}
- ceph_flush_cap_releases(mdsc, session);
+ ceph_flush_session_cap_releases(mdsc, session);
goto done;
bad:
@@ -4640,7 +4645,7 @@ unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
* slowness doesn't block mdsc delayed work,
* preventing send_renew_caps() from running.
*/
- if (jiffies - loop_start >= 5 * HZ)
+ if (time_after_eq(jiffies, loop_start + 5 * HZ))
break;
}
spin_unlock(&mdsc->cap_delay_lock);
@@ -4682,6 +4687,28 @@ void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc)
ceph_mdsc_iterate_sessions(mdsc, flush_dirty_session_caps, true);
}
+/*
+ * Flush all cap releases to the mds
+ */
+static void flush_cap_releases(struct ceph_mds_session *s)
+{
+ struct ceph_mds_client *mdsc = s->s_mdsc;
+ struct ceph_client *cl = mdsc->fsc->client;
+
+ doutc(cl, "begin\n");
+ spin_lock(&s->s_cap_lock);
+ if (s->s_num_cap_releases)
+ ceph_flush_session_cap_releases(mdsc, s);
+ spin_unlock(&s->s_cap_lock);
+ doutc(cl, "done\n");
+
+}
+
+void ceph_flush_cap_releases(struct ceph_mds_client *mdsc)
+{
+ ceph_mdsc_iterate_sessions(mdsc, flush_cap_releases, true);
+}
+
void __ceph_touch_fmode(struct ceph_inode_info *ci,
struct ceph_mds_client *mdsc, int fmode)
{
diff --git a/fs/ceph/crypto.h b/fs/ceph/crypto.h
index 47e0c319fc68..d0768239a1c9 100644
--- a/fs/ceph/crypto.h
+++ b/fs/ceph/crypto.h
@@ -27,7 +27,7 @@ struct ceph_fname {
};
/*
- * Header for the crypted file when truncating the size, this
+ * Header for the encrypted file when truncating the size, this
* will be sent to MDS, and the MDS will update the encrypted
* last block and then truncate the size.
*/
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 24c08078f5aa..fdd404fc8112 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -357,7 +357,7 @@ static int status_show(struct seq_file *s, void *p)
seq_printf(s, "instance: %s.%lld %s/%u\n", ENTITY_NAME(inst->name),
ceph_pr_addr(client_addr), le32_to_cpu(client_addr->nonce));
- seq_printf(s, "blocklisted: %s\n", fsc->blocklisted ? "true" : "false");
+ seq_printf(s, "blocklisted: %s\n", str_true_false(fsc->blocklisted));
return 0;
}
@@ -412,7 +412,7 @@ void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
void ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
{
- char name[100];
+ char name[NAME_MAX];
doutc(fsc->client, "begin\n");
fsc->debugfs_congestion_kb =
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 0e9f56eaba1e..a321aa6d0ed2 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -141,17 +141,18 @@ __dcache_find_get_entry(struct dentry *parent, u64 idx,
if (ptr_pos >= i_size_read(dir))
return NULL;
- if (!cache_ctl->page || ptr_pgoff != page_index(cache_ctl->page)) {
+ if (!cache_ctl->folio || ptr_pgoff != cache_ctl->folio->index) {
ceph_readdir_cache_release(cache_ctl);
- cache_ctl->page = find_lock_page(&dir->i_data, ptr_pgoff);
- if (!cache_ctl->page) {
- doutc(cl, " page %lu not found\n", ptr_pgoff);
+ cache_ctl->folio = filemap_lock_folio(&dir->i_data, ptr_pgoff);
+ if (IS_ERR(cache_ctl->folio)) {
+ cache_ctl->folio = NULL;
+ doutc(cl, " folio %lu not found\n", ptr_pgoff);
return ERR_PTR(-EAGAIN);
}
/* reading/filling the cache are serialized by
- i_rwsem, no need to use page lock */
- unlock_page(cache_ctl->page);
- cache_ctl->dentries = kmap(cache_ctl->page);
+ i_rwsem, no need to use folio lock */
+ folio_unlock(cache_ctl->folio);
+ cache_ctl->dentries = kmap_local_folio(cache_ctl->folio, 0);
}
cache_ctl->index = idx & idx_mask;
@@ -207,7 +208,7 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx,
dentry = __dcache_find_get_entry(parent, idx + step,
&cache_ctl);
if (!dentry) {
- /* use linar search */
+ /* use linear search */
idx = 0;
break;
}
@@ -659,7 +660,7 @@ static bool need_reset_readdir(struct ceph_dir_file_info *dfi, loff_t new_pos)
return true;
if (is_hash_order(new_pos)) {
/* no need to reset last_name for a forward seek when
- * dentries are sotred in hash order */
+ * dentries are sorted in hash order */
} else if (dfi->frag != fpos_frag(new_pos)) {
return true;
}
@@ -707,7 +708,6 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int whence)
if (offset != file->f_pos) {
file->f_pos = offset;
- file->f_version = 0;
dfi->file_info.flags &= ~CEPH_F_ATEND;
}
retval = offset;
@@ -1093,19 +1093,20 @@ out:
return err;
}
-static int ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir,
- struct dentry *dentry, umode_t mode)
+static struct dentry *ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
struct ceph_client *cl = mdsc->fsc->client;
struct ceph_mds_request *req;
struct ceph_acl_sec_ctx as_ctx = {};
+ struct dentry *ret;
int err;
int op;
err = ceph_wait_on_conflict_unlink(dentry);
if (err)
- return err;
+ return ERR_PTR(err);
if (ceph_snap(dir) == CEPH_SNAPDIR) {
/* mkdir .snap/foo is a MKSNAP */
@@ -1117,32 +1118,32 @@ static int ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir,
ceph_vinop(dir), dentry, dentry, mode);
op = CEPH_MDS_OP_MKDIR;
} else {
- err = -EROFS;
+ ret = ERR_PTR(-EROFS);
goto out;
}
if (op == CEPH_MDS_OP_MKDIR &&
ceph_quota_is_max_files_exceeded(dir)) {
- err = -EDQUOT;
+ ret = ERR_PTR(-EDQUOT);
goto out;
}
if ((op == CEPH_MDS_OP_MKSNAP) && IS_ENCRYPTED(dir) &&
!fscrypt_has_encryption_key(dir)) {
- err = -ENOKEY;
+ ret = ERR_PTR(-ENOKEY);
goto out;
}
req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
if (IS_ERR(req)) {
- err = PTR_ERR(req);
+ ret = ERR_CAST(req);
goto out;
}
mode |= S_IFDIR;
req->r_new_inode = ceph_new_inode(dir, dentry, &mode, &as_ctx);
if (IS_ERR(req->r_new_inode)) {
- err = PTR_ERR(req->r_new_inode);
+ ret = ERR_CAST(req->r_new_inode);
req->r_new_inode = NULL;
goto out_req;
}
@@ -1166,15 +1167,22 @@ static int ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir,
!req->r_reply_info.head->is_target &&
!req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
+ ret = ERR_PTR(err);
out_req:
+ if (!IS_ERR(ret) && req->r_dentry != dentry)
+ /* Some other dentry was spliced in */
+ ret = dget(req->r_dentry);
ceph_mdsc_put_request(req);
out:
- if (!err)
+ if (!IS_ERR(ret)) {
+ if (ret)
+ dentry = ret;
ceph_init_inode_acls(d_inode(dentry), &as_ctx);
- else
+ } else {
d_drop(dentry);
+ }
ceph_release_acl_sec_ctx(&as_ctx);
- return err;
+ return ret;
}
static int ceph_link(struct dentry *old_dentry, struct inode *dir,
@@ -1336,8 +1344,12 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry)
struct inode *inode = d_inode(dentry);
struct ceph_mds_request *req;
bool try_async = ceph_test_mount_opt(fsc, ASYNC_DIROPS);
+ struct dentry *dn;
int err = -EROFS;
int op;
+ char *path;
+ int pathlen;
+ u64 pathbase;
if (ceph_snap(dir) == CEPH_SNAPDIR) {
/* rmdir .snap/foo is RMSNAP */
@@ -1351,6 +1363,30 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry)
CEPH_MDS_OP_RMDIR : CEPH_MDS_OP_UNLINK;
} else
goto out;
+
+ dn = d_find_alias(dir);
+ if (!dn) {
+ try_async = false;
+ } else {
+ path = ceph_mdsc_build_path(mdsc, dn, &pathlen, &pathbase, 0);
+ if (IS_ERR(path)) {
+ try_async = false;
+ err = 0;
+ } else {
+ err = ceph_mds_check_access(mdsc, path, MAY_WRITE);
+ }
+ ceph_mdsc_free_path(path, pathlen);
+ dput(dn);
+
+ /* For none EACCES cases will let the MDS do the mds auth check */
+ if (err == -EACCES) {
+ return err;
+ } else if (err < 0) {
+ try_async = false;
+ err = 0;
+ }
+ }
+
retry:
req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
if (IS_ERR(req)) {
@@ -1561,7 +1597,7 @@ void __ceph_dentry_dir_lease_touch(struct ceph_dentry_info *di)
}
spin_lock(&mdsc->dentry_list_lock);
- __dentry_dir_lease_touch(mdsc, di),
+ __dentry_dir_lease_touch(mdsc, di);
spin_unlock(&mdsc->dentry_list_lock);
}
@@ -1913,29 +1949,19 @@ static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry,
/*
* Check if cached dentry can be trusted.
*/
-static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
+static int ceph_d_revalidate(struct inode *dir, const struct qstr *name,
+ struct dentry *dentry, unsigned int flags)
{
struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(dentry->d_sb)->mdsc;
struct ceph_client *cl = mdsc->fsc->client;
int valid = 0;
- struct dentry *parent;
- struct inode *dir, *inode;
+ struct inode *inode;
- valid = fscrypt_d_revalidate(dentry, flags);
+ valid = fscrypt_d_revalidate(dir, name, dentry, flags);
if (valid <= 0)
return valid;
- if (flags & LOOKUP_RCU) {
- parent = READ_ONCE(dentry->d_parent);
- dir = d_inode_rcu(parent);
- if (!dir)
- return -ECHILD;
- inode = d_inode_rcu(dentry);
- } else {
- parent = dget_parent(dentry);
- dir = d_inode(parent);
- inode = d_inode(dentry);
- }
+ inode = d_inode_rcu(dentry);
doutc(cl, "%p '%pd' inode %p offset 0x%llx nokey %d\n",
dentry, dentry, inode, ceph_dentry(dentry)->offset,
@@ -1981,6 +2007,8 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
req->r_parent = dir;
ihold(dir);
+ req->r_dname = name;
+
mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED;
if (ceph_security_xattr_wanted(dir))
mask |= CEPH_CAP_XATTR_SHARED;
@@ -2011,9 +2039,6 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
doutc(cl, "%p '%pd' %s\n", dentry, dentry, valid ? "valid" : "invalid");
if (!valid)
ceph_dir_clear_complete(dir);
-
- if (!(flags & LOOKUP_RCU))
- dput(parent);
return valid;
}
@@ -2031,7 +2056,7 @@ static int ceph_d_delete(const struct dentry *dentry)
return 0;
if (ceph_snap(d_inode(dentry)) != CEPH_NOSNAP)
return 0;
- /* vaild lease? */
+ /* valid lease? */
di = ceph_dentry(dentry);
if (di) {
if (__dentry_lease_is_valid(di))
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index a79f163ae4ed..150076ced937 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -3,7 +3,7 @@
#include <linux/exportfs.h>
#include <linux/slab.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "super.h"
#include "mds_client.h"
@@ -393,9 +393,9 @@ static struct dentry *ceph_get_parent(struct dentry *child)
}
dir = snapdir;
}
- /* If directory has already been deleted, futher get_parent
+ /* If directory has already been deleted, further get_parent
* will fail. Do not mark snapdir dentry as disconnected,
- * this prevent exportfs from doing futher get_parent. */
+ * this prevents exportfs from doing further get_parent. */
if (unlinked)
dn = d_obtain_root(dir);
else
@@ -452,7 +452,13 @@ static int __get_snap_name(struct dentry *parent, char *name,
goto out;
if (ceph_snap(inode) == CEPH_SNAPDIR) {
if (ceph_snap(dir) == CEPH_NOSNAP) {
- strcpy(name, fsc->mount_options->snapdir_name);
+ /*
+ * .get_name() from struct export_operations
+ * assumes that its 'name' parameter is pointing
+ * to a NAME_MAX+1 sized buffer
+ */
+ strscpy(name, fsc->mount_options->snapdir_name,
+ NAME_MAX + 1);
err = 0;
}
goto out;
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 16873d07692f..851d70200c6b 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -366,6 +366,12 @@ int ceph_open(struct inode *inode, struct file *file)
struct ceph_file_info *fi = file->private_data;
int err;
int flags, fmode, wanted;
+ struct dentry *dentry;
+ char *path;
+ int pathlen;
+ u64 pathbase;
+ bool do_sync = false;
+ int mask = MAY_READ;
if (fi) {
doutc(cl, "file %p is already opened\n", file);
@@ -387,6 +393,31 @@ int ceph_open(struct inode *inode, struct file *file)
fmode = ceph_flags_to_mode(flags);
wanted = ceph_caps_for_mode(fmode);
+ if (fmode & CEPH_FILE_MODE_WR)
+ mask |= MAY_WRITE;
+ dentry = d_find_alias(inode);
+ if (!dentry) {
+ do_sync = true;
+ } else {
+ path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase, 0);
+ if (IS_ERR(path)) {
+ do_sync = true;
+ err = 0;
+ } else {
+ err = ceph_mds_check_access(mdsc, path, mask);
+ }
+ ceph_mdsc_free_path(path, pathlen);
+ dput(dentry);
+
+ /* For none EACCES cases will let the MDS do the mds auth check */
+ if (err == -EACCES) {
+ return err;
+ } else if (err < 0) {
+ do_sync = true;
+ err = 0;
+ }
+ }
+
/* snapped files are read-only */
if (ceph_snap(inode) != CEPH_NOSNAP && (file->f_mode & FMODE_WRITE))
return -EROFS;
@@ -402,7 +433,7 @@ int ceph_open(struct inode *inode, struct file *file)
* asynchronously.
*/
spin_lock(&ci->i_ceph_lock);
- if (__ceph_is_any_real_caps(ci) &&
+ if (!do_sync && __ceph_is_any_real_caps(ci) &&
(((fmode & CEPH_FILE_MODE_WR) == 0) || ci->i_auth_cap)) {
int mds_wanted = __ceph_caps_mds_wanted(ci, true);
int issued = __ceph_caps_issued(ci, NULL);
@@ -420,7 +451,7 @@ int ceph_open(struct inode *inode, struct file *file)
ceph_check_caps(ci, 0);
return ceph_init_file(inode, file, fmode);
- } else if (ceph_snap(inode) != CEPH_NOSNAP &&
+ } else if (!do_sync && ceph_snap(inode) != CEPH_NOSNAP &&
(ci->i_snap_caps & wanted) == wanted) {
__ceph_touch_fmode(ci, mdsc, fmode);
spin_unlock(&ci->i_ceph_lock);
@@ -759,6 +790,9 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
bool try_async = ceph_test_mount_opt(fsc, ASYNC_DIROPS);
int mask;
int err;
+ char *path;
+ int pathlen;
+ u64 pathbase;
doutc(cl, "%p %llx.%llx dentry %p '%pd' %s flags %d mode 0%o\n",
dir, ceph_vinop(dir), dentry, dentry,
@@ -776,6 +810,34 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
*/
flags &= ~O_TRUNC;
+ dn = d_find_alias(dir);
+ if (!dn) {
+ try_async = false;
+ } else {
+ path = ceph_mdsc_build_path(mdsc, dn, &pathlen, &pathbase, 0);
+ if (IS_ERR(path)) {
+ try_async = false;
+ err = 0;
+ } else {
+ int fmode = ceph_flags_to_mode(flags);
+
+ mask = MAY_READ;
+ if (fmode & CEPH_FILE_MODE_WR)
+ mask |= MAY_WRITE;
+ err = ceph_mds_check_access(mdsc, path, mask);
+ }
+ ceph_mdsc_free_path(path, pathlen);
+ dput(dn);
+
+ /* For none EACCES cases will let the MDS do the mds auth check */
+ if (err == -EACCES) {
+ return err;
+ } else if (err < 0) {
+ try_async = false;
+ err = 0;
+ }
+ }
+
retry:
if (flags & O_CREAT) {
if (ceph_quota_is_max_files_exceeded(dir))
@@ -1004,7 +1066,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
if (ceph_inode_is_shutdown(inode))
return -EIO;
- if (!len)
+ if (!len || !i_size)
return 0;
/*
* flush any page cache pages in this range. this
@@ -1024,7 +1086,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
int num_pages;
size_t page_off;
bool more;
- int idx;
+ int idx = 0;
size_t left;
struct ceph_osd_req_op *op;
u64 read_off = off;
@@ -1054,6 +1116,16 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
len = read_off + read_len - off;
more = len < iov_iter_count(to);
+ op = &req->r_ops[0];
+ if (sparse) {
+ extent_cnt = __ceph_sparse_read_ext_count(inode, read_len);
+ ret = ceph_alloc_sparse_ext_map(op, extent_cnt);
+ if (ret) {
+ ceph_osdc_put_request(req);
+ break;
+ }
+ }
+
num_pages = calc_pages_for(read_off, read_len);
page_off = offset_in_page(off);
pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
@@ -1065,17 +1137,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
osd_req_op_extent_osd_data_pages(req, 0, pages, read_len,
offset_in_page(read_off),
- false, false);
-
- op = &req->r_ops[0];
- if (sparse) {
- extent_cnt = __ceph_sparse_read_ext_count(inode, read_len);
- ret = ceph_alloc_sparse_ext_map(op, extent_cnt);
- if (ret) {
- ceph_osdc_put_request(req);
- break;
- }
- }
+ false, true);
ceph_osdc_start_request(osdc, req);
ret = ceph_osdc_wait_request(osdc, req);
@@ -1098,7 +1160,14 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
else if (ret == -ENOENT)
ret = 0;
- if (ret > 0 && IS_ENCRYPTED(inode)) {
+ if (ret < 0) {
+ ceph_osdc_put_request(req);
+ if (ret == -EBLOCKLISTED)
+ fsc->blocklisted = true;
+ break;
+ }
+
+ if (IS_ENCRYPTED(inode)) {
int fret;
fret = ceph_fscrypt_decrypt_extents(inode, pages,
@@ -1124,10 +1193,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
ret = min_t(ssize_t, fret, len);
}
- ceph_osdc_put_request(req);
-
/* Short read but not EOF? Zero out the remainder. */
- if (ret >= 0 && ret < len && (off + ret < i_size)) {
+ if (ret < len && (off + ret < i_size)) {
int zlen = min(len - ret, i_size - off - ret);
int zoff = page_off + ret;
@@ -1137,13 +1204,11 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
ret += zlen;
}
- idx = 0;
- if (ret <= 0)
- left = 0;
- else if (off + ret > i_size)
- left = i_size - off;
+ if (off + ret > i_size)
+ left = (i_size > off) ? i_size - off : 0;
else
left = ret;
+
while (left > 0) {
size_t plen, copied;
@@ -1159,13 +1224,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
break;
}
}
- ceph_release_page_vector(pages, num_pages);
- if (ret < 0) {
- if (ret == -EBLOCKLISTED)
- fsc->blocklisted = true;
- break;
- }
+ ceph_osdc_put_request(req);
if (off >= i_size || !more)
break;
@@ -1491,6 +1551,16 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
break;
}
+ op = &req->r_ops[0];
+ if (!write && sparse) {
+ extent_cnt = __ceph_sparse_read_ext_count(inode, size);
+ ret = ceph_alloc_sparse_ext_map(op, extent_cnt);
+ if (ret) {
+ ceph_osdc_put_request(req);
+ break;
+ }
+ }
+
len = iter_get_bvecs_alloc(iter, size, &bvecs, &num_pages);
if (len < 0) {
ceph_osdc_put_request(req);
@@ -1500,6 +1570,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
if (len != size)
osd_req_op_extent_update(req, 0, len);
+ osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len);
+
/*
* To simplify error handling, allow AIO when IO within i_size
* or IO can be satisfied by single OSD request.
@@ -1531,17 +1603,6 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
req->r_mtime = mtime;
}
- osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len);
- op = &req->r_ops[0];
- if (sparse) {
- extent_cnt = __ceph_sparse_read_ext_count(inode, size);
- ret = ceph_alloc_sparse_ext_map(op, extent_cnt);
- if (ret) {
- ceph_osdc_put_request(req);
- break;
- }
- }
-
if (aio_req) {
aio_req->total_len += len;
aio_req->num_reqs++;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 7b2e77517f23..06cd2963e41e 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -160,7 +160,7 @@ struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino,
}
/*
- * get/constuct snapdir inode for a given directory
+ * get/construct snapdir inode for a given directory
*/
struct inode *ceph_get_snapdir(struct inode *parent)
{
@@ -695,6 +695,7 @@ void ceph_evict_inode(struct inode *inode)
percpu_counter_dec(&mdsc->metric.total_inodes);
+ netfs_wait_for_outstanding_io(inode);
truncate_inode_pages_final(&inode->i_data);
if (inode->i_state & I_PINNING_NETFS_WB)
ceph_fscache_unuse_cookie(inode, true);
@@ -1778,7 +1779,7 @@ retry_lookup:
if (err < 0)
goto done;
} else if (rinfo->head->is_dentry && req->r_dentry) {
- /* parent inode is not locked, be carefull */
+ /* parent inode is not locked, be careful */
struct ceph_vino *ptvino = NULL;
dvino.ino = le64_to_cpu(rinfo->diri.in->ino);
dvino.snap = le64_to_cpu(rinfo->diri.in->snapid);
@@ -1844,10 +1845,9 @@ static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req,
void ceph_readdir_cache_release(struct ceph_readdir_cache_control *ctl)
{
- if (ctl->page) {
- kunmap(ctl->page);
- put_page(ctl->page);
- ctl->page = NULL;
+ if (ctl->folio) {
+ folio_release_kmap(ctl->folio, ctl->dentries);
+ ctl->folio = NULL;
}
}
@@ -1861,20 +1861,26 @@ static int fill_readdir_cache(struct inode *dir, struct dentry *dn,
unsigned idx = ctl->index % nsize;
pgoff_t pgoff = ctl->index / nsize;
- if (!ctl->page || pgoff != page_index(ctl->page)) {
+ if (!ctl->folio || pgoff != ctl->folio->index) {
ceph_readdir_cache_release(ctl);
+ fgf_t fgf = FGP_LOCK;
+
if (idx == 0)
- ctl->page = grab_cache_page(&dir->i_data, pgoff);
- else
- ctl->page = find_lock_page(&dir->i_data, pgoff);
- if (!ctl->page) {
+ fgf |= FGP_ACCESSED | FGP_CREAT;
+
+ ctl->folio = __filemap_get_folio(&dir->i_data, pgoff,
+ fgf, mapping_gfp_mask(&dir->i_data));
+ if (IS_ERR(ctl->folio)) {
+ int err = PTR_ERR(ctl->folio);
+
+ ctl->folio = NULL;
ctl->index = -1;
- return idx == 0 ? -ENOMEM : 0;
+ return idx == 0 ? err : 0;
}
/* reading/filling the cache are serialized by
- * i_rwsem, no need to use page lock */
- unlock_page(ctl->page);
- ctl->dentries = kmap(ctl->page);
+ * i_rwsem, no need to use folio lock */
+ folio_unlock(ctl->folio);
+ ctl->dentries = kmap_local_folio(ctl->folio, 0);
if (idx == 0)
memset(ctl->dentries, 0, PAGE_SIZE);
}
@@ -2361,7 +2367,7 @@ static int fill_fscrypt_truncate(struct inode *inode,
/* Try to writeback the dirty pagecaches */
if (issued & (CEPH_CAP_FILE_BUFFER)) {
- loff_t lend = orig_pos + CEPH_FSCRYPT_BLOCK_SHIFT - 1;
+ loff_t lend = orig_pos + CEPH_FSCRYPT_BLOCK_SIZE - 1;
ret = filemap_write_and_wait_range(inode->i_mapping,
orig_pos, lend);
@@ -2480,6 +2486,34 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode,
bool lock_snap_rwsem = false;
bool fill_fscrypt;
int truncate_retry = 20; /* The RMW will take around 50ms */
+ struct dentry *dentry;
+ char *path;
+ int pathlen;
+ u64 pathbase;
+ bool do_sync = false;
+
+ dentry = d_find_alias(inode);
+ if (!dentry) {
+ do_sync = true;
+ } else {
+ path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase, 0);
+ if (IS_ERR(path)) {
+ do_sync = true;
+ err = 0;
+ } else {
+ err = ceph_mds_check_access(mdsc, path, MAY_WRITE);
+ }
+ ceph_mdsc_free_path(path, pathlen);
+ dput(dentry);
+
+ /* For none EACCES cases will let the MDS do the mds auth check */
+ if (err == -EACCES) {
+ return err;
+ } else if (err < 0) {
+ do_sync = true;
+ err = 0;
+ }
+ }
retry:
prealloc_cf = ceph_alloc_cap_flush();
@@ -2526,7 +2560,7 @@ retry:
/* It should never be re-set once set */
WARN_ON_ONCE(ci->fscrypt_auth);
- if (issued & CEPH_CAP_AUTH_EXCL) {
+ if (!do_sync && (issued & CEPH_CAP_AUTH_EXCL)) {
dirtied |= CEPH_CAP_AUTH_EXCL;
kfree(ci->fscrypt_auth);
ci->fscrypt_auth = (u8 *)cia->fscrypt_auth;
@@ -2555,7 +2589,7 @@ retry:
ceph_vinop(inode),
from_kuid(&init_user_ns, inode->i_uid),
from_kuid(&init_user_ns, attr->ia_uid));
- if (issued & CEPH_CAP_AUTH_EXCL) {
+ if (!do_sync && (issued & CEPH_CAP_AUTH_EXCL)) {
inode->i_uid = fsuid;
dirtied |= CEPH_CAP_AUTH_EXCL;
} else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 ||
@@ -2573,7 +2607,7 @@ retry:
ceph_vinop(inode),
from_kgid(&init_user_ns, inode->i_gid),
from_kgid(&init_user_ns, attr->ia_gid));
- if (issued & CEPH_CAP_AUTH_EXCL) {
+ if (!do_sync && (issued & CEPH_CAP_AUTH_EXCL)) {
inode->i_gid = fsgid;
dirtied |= CEPH_CAP_AUTH_EXCL;
} else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 ||
@@ -2587,7 +2621,7 @@ retry:
if (ia_valid & ATTR_MODE) {
doutc(cl, "%p %llx.%llx mode 0%o -> 0%o\n", inode,
ceph_vinop(inode), inode->i_mode, attr->ia_mode);
- if (issued & CEPH_CAP_AUTH_EXCL) {
+ if (!do_sync && (issued & CEPH_CAP_AUTH_EXCL)) {
inode->i_mode = attr->ia_mode;
dirtied |= CEPH_CAP_AUTH_EXCL;
} else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 ||
@@ -2606,11 +2640,11 @@ retry:
inode, ceph_vinop(inode),
atime.tv_sec, atime.tv_nsec,
attr->ia_atime.tv_sec, attr->ia_atime.tv_nsec);
- if (issued & CEPH_CAP_FILE_EXCL) {
+ if (!do_sync && (issued & CEPH_CAP_FILE_EXCL)) {
ci->i_time_warp_seq++;
inode_set_atime_to_ts(inode, attr->ia_atime);
dirtied |= CEPH_CAP_FILE_EXCL;
- } else if ((issued & CEPH_CAP_FILE_WR) &&
+ } else if (!do_sync && (issued & CEPH_CAP_FILE_WR) &&
timespec64_compare(&atime,
&attr->ia_atime) < 0) {
inode_set_atime_to_ts(inode, attr->ia_atime);
@@ -2646,7 +2680,7 @@ retry:
CEPH_FSCRYPT_BLOCK_SIZE));
req->r_fscrypt_file = attr->ia_size;
fill_fscrypt = true;
- } else if ((issued & CEPH_CAP_FILE_EXCL) && attr->ia_size >= isize) {
+ } else if (!do_sync && (issued & CEPH_CAP_FILE_EXCL) && attr->ia_size >= isize) {
if (attr->ia_size > isize) {
i_size_write(inode, attr->ia_size);
inode->i_blocks = calc_inode_blocks(attr->ia_size);
@@ -2683,11 +2717,11 @@ retry:
inode, ceph_vinop(inode),
mtime.tv_sec, mtime.tv_nsec,
attr->ia_mtime.tv_sec, attr->ia_mtime.tv_nsec);
- if (issued & CEPH_CAP_FILE_EXCL) {
+ if (!do_sync && (issued & CEPH_CAP_FILE_EXCL)) {
ci->i_time_warp_seq++;
inode_set_mtime_to_ts(inode, attr->ia_mtime);
dirtied |= CEPH_CAP_FILE_EXCL;
- } else if ((issued & CEPH_CAP_FILE_WR) &&
+ } else if (!do_sync && (issued & CEPH_CAP_FILE_WR) &&
timespec64_compare(&mtime, &attr->ia_mtime) < 0) {
inode_set_mtime_to_ts(inode, attr->ia_mtime);
dirtied |= CEPH_CAP_FILE_WR;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 360b686c3c67..230e0c3f341f 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -827,7 +827,7 @@ static void destroy_reply_info(struct ceph_mds_reply_info_parsed *info)
* And the worst case is that for the none async openc request it will
* successfully open the file if the CDentry hasn't been unlinked yet,
* but later the previous delayed async unlink request will remove the
- * CDenty. That means the just created file is possiblly deleted later
+ * CDentry. That means the just created file is possibly deleted later
* by accident.
*
* We need to wait for the inflight async unlink requests to finish
@@ -1747,14 +1747,6 @@ static void __open_export_target_sessions(struct ceph_mds_client *mdsc,
}
}
-void ceph_mdsc_open_export_target_sessions(struct ceph_mds_client *mdsc,
- struct ceph_mds_session *session)
-{
- mutex_lock(&mdsc->mutex);
- __open_export_target_sessions(mdsc, session);
- mutex_unlock(&mdsc->mutex);
-}
-
/*
* session caps
*/
@@ -2266,7 +2258,7 @@ int ceph_trim_caps(struct ceph_mds_client *mdsc,
trim_caps - remaining);
}
- ceph_flush_cap_releases(mdsc, session);
+ ceph_flush_session_cap_releases(mdsc, session);
return 0;
}
@@ -2362,7 +2354,7 @@ again:
item->ino = cpu_to_le64(cap->cap_ino);
item->cap_id = cpu_to_le64(cap->cap_id);
item->migrate_seq = cpu_to_le32(cap->mseq);
- item->seq = cpu_to_le32(cap->issue_seq);
+ item->issue_seq = cpu_to_le32(cap->issue_seq);
msg->front.iov_len += sizeof(*item);
ceph_put_cap(mdsc, cap);
@@ -2420,7 +2412,7 @@ static void ceph_cap_release_work(struct work_struct *work)
ceph_put_mds_session(session);
}
-void ceph_flush_cap_releases(struct ceph_mds_client *mdsc,
+void ceph_flush_session_cap_releases(struct ceph_mds_client *mdsc,
struct ceph_mds_session *session)
{
struct ceph_client *cl = mdsc->fsc->client;
@@ -2447,7 +2439,7 @@ void __ceph_queue_cap_release(struct ceph_mds_session *session,
session->s_num_cap_releases++;
if (!(session->s_num_cap_releases % CEPH_CAPS_PER_RELEASE))
- ceph_flush_cap_releases(session->s_mdsc, session);
+ ceph_flush_session_cap_releases(session->s_mdsc, session);
}
static void ceph_cap_reclaim_work(struct work_struct *work)
@@ -2629,6 +2621,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen)
{
struct inode *dir = req->r_parent;
struct dentry *dentry = req->r_dentry;
+ const struct qstr *name = req->r_dname;
u8 *cryptbuf = NULL;
u32 len = 0;
int ret = 0;
@@ -2649,8 +2642,10 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen)
if (!fscrypt_has_encryption_key(dir))
goto success;
- if (!fscrypt_fname_encrypted_size(dir, dentry->d_name.len, NAME_MAX,
- &len)) {
+ if (!name)
+ name = &dentry->d_name;
+
+ if (!fscrypt_fname_encrypted_size(dir, name->len, NAME_MAX, &len)) {
WARN_ON_ONCE(1);
return ERR_PTR(-ENAMETOOLONG);
}
@@ -2665,7 +2660,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen)
if (!cryptbuf)
return ERR_PTR(-ENOMEM);
- ret = fscrypt_fname_encrypt(dir, &dentry->d_name, cryptbuf, len);
+ ret = fscrypt_fname_encrypt(dir, name, cryptbuf, len);
if (ret) {
kfree(cryptbuf);
return ERR_PTR(ret);
@@ -2808,12 +2803,11 @@ retry:
if (pos < 0) {
/*
- * A rename didn't occur, but somehow we didn't end up where
- * we thought we would. Throw a warning and try again.
+ * The path is longer than PATH_MAX and this function
+ * cannot ever succeed. Creating paths that long is
+ * possible with Ceph, but Linux cannot use them.
*/
- pr_warn_client(cl, "did not end path lookup where expected (pos = %d)\n",
- pos);
- goto retry;
+ return ERR_PTR(-ENAMETOOLONG);
}
*pbase = base;
@@ -2954,12 +2948,12 @@ static struct ceph_mds_request_head_legacy *
find_legacy_request_head(void *p, u64 features)
{
bool legacy = !(features & CEPH_FEATURE_FS_BTIME);
- struct ceph_mds_request_head_old *ohead;
+ struct ceph_mds_request_head *head;
if (legacy)
return (struct ceph_mds_request_head_legacy *)p;
- ohead = (struct ceph_mds_request_head_old *)p;
- return (struct ceph_mds_request_head_legacy *)&ohead->oldest_client_tid;
+ head = (struct ceph_mds_request_head *)p;
+ return (struct ceph_mds_request_head_legacy *)&head->oldest_client_tid;
}
/*
@@ -3029,7 +3023,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
if (legacy)
len = sizeof(struct ceph_mds_request_head_legacy);
else if (request_head_version == 1)
- len = sizeof(struct ceph_mds_request_head_old);
+ len = offsetofend(struct ceph_mds_request_head, args);
else if (request_head_version == 2)
len = offsetofend(struct ceph_mds_request_head, ext_num_fwd);
else
@@ -3113,11 +3107,11 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
msg->hdr.version = cpu_to_le16(3);
p = msg->front.iov_base + sizeof(*lhead);
} else if (request_head_version == 1) {
- struct ceph_mds_request_head_old *ohead = msg->front.iov_base;
+ struct ceph_mds_request_head *nhead = msg->front.iov_base;
msg->hdr.version = cpu_to_le16(4);
- ohead->version = cpu_to_le16(1);
- p = msg->front.iov_base + sizeof(*ohead);
+ nhead->version = cpu_to_le16(1);
+ p = msg->front.iov_base + offsetofend(struct ceph_mds_request_head, args);
} else if (request_head_version == 2) {
struct ceph_mds_request_head *nhead = msg->front.iov_base;
@@ -3269,12 +3263,12 @@ static int __prepare_send_request(struct ceph_mds_session *session,
&session->s_features);
/*
- * Avoid inifinite retrying after overflow. The client will
+ * Avoid infinite retrying after overflow. The client will
* increase the retry count and if the MDS is old version,
* so we limit to retry at most 256 times.
*/
if (req->r_attempts) {
- old_max_retry = sizeof_field(struct ceph_mds_request_head_old,
+ old_max_retry = sizeof_field(struct ceph_mds_request_head,
num_retry);
old_max_retry = 1 << (old_max_retry * BITS_PER_BYTE);
if ((old_version && req->r_attempts >= old_max_retry) ||
@@ -3522,7 +3516,7 @@ static void __do_request(struct ceph_mds_client *mdsc,
/*
* For async create we will choose the auth MDS of frag in parent
- * directory to send the request and ususally this works fine, but
+ * directory to send the request and usually this works fine, but
* if the migrated the dirtory to another MDS before it could handle
* it the request will be forwarded.
*
@@ -4033,7 +4027,7 @@ static void handle_forward(struct ceph_mds_client *mdsc,
__unregister_request(mdsc, req);
} else if (fwd_seq <= req->r_num_fwd || (uint32_t)fwd_seq >= U32_MAX) {
/*
- * Avoid inifinite retrying after overflow.
+ * Avoid infinite retrying after overflow.
*
* The MDS will increase the fwd count and in client side
* if the num_fwd is less than the one saved in request
@@ -4112,10 +4106,13 @@ static void handle_session(struct ceph_mds_session *session,
void *p = msg->front.iov_base;
void *end = p + msg->front.iov_len;
struct ceph_mds_session_head *h;
- u32 op;
+ struct ceph_mds_cap_auth *cap_auths = NULL;
+ u32 op, cap_auths_num = 0;
u64 seq, features = 0;
int wake = 0;
bool blocklisted = false;
+ u32 i;
+
/* decode */
ceph_decode_need(&p, end, sizeof(*h), bad);
@@ -4160,7 +4157,101 @@ static void handle_session(struct ceph_mds_session *session,
}
}
+ if (msg_version >= 6) {
+ ceph_decode_32_safe(&p, end, cap_auths_num, bad);
+ doutc(cl, "cap_auths_num %d\n", cap_auths_num);
+
+ if (cap_auths_num && op != CEPH_SESSION_OPEN) {
+ WARN_ON_ONCE(op != CEPH_SESSION_OPEN);
+ goto skip_cap_auths;
+ }
+
+ cap_auths = kcalloc(cap_auths_num,
+ sizeof(struct ceph_mds_cap_auth),
+ GFP_KERNEL);
+ if (!cap_auths) {
+ pr_err_client(cl, "No memory for cap_auths\n");
+ return;
+ }
+
+ for (i = 0; i < cap_auths_num; i++) {
+ u32 _len, j;
+
+ /* struct_v, struct_compat, and struct_len in MDSCapAuth */
+ ceph_decode_skip_n(&p, end, 2 + sizeof(u32), bad);
+
+ /* struct_v, struct_compat, and struct_len in MDSCapMatch */
+ ceph_decode_skip_n(&p, end, 2 + sizeof(u32), bad);
+ ceph_decode_64_safe(&p, end, cap_auths[i].match.uid, bad);
+ ceph_decode_32_safe(&p, end, _len, bad);
+ if (_len) {
+ cap_auths[i].match.gids = kcalloc(_len, sizeof(u32),
+ GFP_KERNEL);
+ if (!cap_auths[i].match.gids) {
+ pr_err_client(cl, "No memory for gids\n");
+ goto fail;
+ }
+
+ cap_auths[i].match.num_gids = _len;
+ for (j = 0; j < _len; j++)
+ ceph_decode_32_safe(&p, end,
+ cap_auths[i].match.gids[j],
+ bad);
+ }
+
+ ceph_decode_32_safe(&p, end, _len, bad);
+ if (_len) {
+ cap_auths[i].match.path = kcalloc(_len + 1, sizeof(char),
+ GFP_KERNEL);
+ if (!cap_auths[i].match.path) {
+ pr_err_client(cl, "No memory for path\n");
+ goto fail;
+ }
+ ceph_decode_copy(&p, cap_auths[i].match.path, _len);
+
+ /* Remove the tailing '/' */
+ while (_len && cap_auths[i].match.path[_len - 1] == '/') {
+ cap_auths[i].match.path[_len - 1] = '\0';
+ _len -= 1;
+ }
+ }
+
+ ceph_decode_32_safe(&p, end, _len, bad);
+ if (_len) {
+ cap_auths[i].match.fs_name = kcalloc(_len + 1, sizeof(char),
+ GFP_KERNEL);
+ if (!cap_auths[i].match.fs_name) {
+ pr_err_client(cl, "No memory for fs_name\n");
+ goto fail;
+ }
+ ceph_decode_copy(&p, cap_auths[i].match.fs_name, _len);
+ }
+
+ ceph_decode_8_safe(&p, end, cap_auths[i].match.root_squash, bad);
+ ceph_decode_8_safe(&p, end, cap_auths[i].readable, bad);
+ ceph_decode_8_safe(&p, end, cap_auths[i].writeable, bad);
+ doutc(cl, "uid %lld, num_gids %u, path %s, fs_name %s, root_squash %d, readable %d, writeable %d\n",
+ cap_auths[i].match.uid, cap_auths[i].match.num_gids,
+ cap_auths[i].match.path, cap_auths[i].match.fs_name,
+ cap_auths[i].match.root_squash,
+ cap_auths[i].readable, cap_auths[i].writeable);
+ }
+ }
+
+skip_cap_auths:
mutex_lock(&mdsc->mutex);
+ if (op == CEPH_SESSION_OPEN) {
+ if (mdsc->s_cap_auths) {
+ for (i = 0; i < mdsc->s_cap_auths_num; i++) {
+ kfree(mdsc->s_cap_auths[i].match.gids);
+ kfree(mdsc->s_cap_auths[i].match.path);
+ kfree(mdsc->s_cap_auths[i].match.fs_name);
+ }
+ kfree(mdsc->s_cap_auths);
+ }
+ mdsc->s_cap_auths_num = cap_auths_num;
+ mdsc->s_cap_auths = cap_auths;
+ }
if (op == CEPH_SESSION_CLOSE) {
ceph_get_mds_session(session);
__unregister_session(mdsc, session);
@@ -4243,7 +4334,7 @@ static void handle_session(struct ceph_mds_session *session,
/* flush cap releases */
spin_lock(&session->s_cap_lock);
if (session->s_num_cap_releases)
- ceph_flush_cap_releases(mdsc, session);
+ ceph_flush_session_cap_releases(mdsc, session);
spin_unlock(&session->s_cap_lock);
send_flushmsg_ack(mdsc, session, seq);
@@ -4290,6 +4381,13 @@ bad:
pr_err_client(cl, "corrupt message mds%d len %d\n", mds,
(int)msg->front.iov_len);
ceph_msg_dump(msg);
+fail:
+ for (i = 0; i < cap_auths_num; i++) {
+ kfree(cap_auths[i].match.gids);
+ kfree(cap_auths[i].match.path);
+ kfree(cap_auths[i].match.fs_name);
+ }
+ kfree(cap_auths);
return;
}
@@ -4806,7 +4904,7 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
} else {
recon_state.msg_version = 2;
}
- /* trsaverse this session's caps */
+ /* traverse this session's caps */
err = ceph_iterate_session_caps(session, reconnect_caps_cb, &recon_state);
spin_lock(&session->s_cap_lock);
@@ -5342,6 +5440,8 @@ static void delayed_work(struct work_struct *work)
}
mutex_unlock(&mdsc->mutex);
+ ceph_flush_session_cap_releases(mdsc, s);
+
mutex_lock(&s->s_mutex);
if (renew_caps)
send_renew_caps(mdsc, s);
@@ -5389,6 +5489,8 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
spin_lock_init(&mdsc->stopping_lock);
atomic_set(&mdsc->stopping_blockers, 0);
init_completion(&mdsc->stopping_waiter);
+ atomic64_set(&mdsc->dirty_folios, 0);
+ init_waitqueue_head(&mdsc->flush_end_wq);
init_waitqueue_head(&mdsc->session_close_wq);
INIT_LIST_HEAD(&mdsc->waiting_for_map);
mdsc->quotarealms_inodes = RB_ROOT;
@@ -5401,7 +5503,9 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
INIT_DELAYED_WORK(&mdsc->delayed_work, delayed_work);
mdsc->last_renew_caps = jiffies;
INIT_LIST_HEAD(&mdsc->cap_delay_list);
+#ifdef CONFIG_DEBUG_FS
INIT_LIST_HEAD(&mdsc->cap_wait_list);
+#endif
spin_lock_init(&mdsc->cap_delay_lock);
INIT_LIST_HEAD(&mdsc->cap_unlink_delay_list);
INIT_LIST_HEAD(&mdsc->snap_flush_list);
@@ -5499,6 +5603,173 @@ void send_flush_mdlog(struct ceph_mds_session *s)
mutex_unlock(&s->s_mutex);
}
+static int ceph_mds_auth_match(struct ceph_mds_client *mdsc,
+ struct ceph_mds_cap_auth *auth,
+ const struct cred *cred,
+ char *tpath)
+{
+ u32 caller_uid = from_kuid(&init_user_ns, cred->fsuid);
+ u32 caller_gid = from_kgid(&init_user_ns, cred->fsgid);
+ struct ceph_client *cl = mdsc->fsc->client;
+ const char *spath = mdsc->fsc->mount_options->server_path;
+ bool gid_matched = false;
+ u32 gid, tlen, len;
+ int i, j;
+
+ doutc(cl, "match.uid %lld\n", auth->match.uid);
+ if (auth->match.uid != MDS_AUTH_UID_ANY) {
+ if (auth->match.uid != caller_uid)
+ return 0;
+ if (auth->match.num_gids) {
+ for (i = 0; i < auth->match.num_gids; i++) {
+ if (caller_gid == auth->match.gids[i])
+ gid_matched = true;
+ }
+ if (!gid_matched && cred->group_info->ngroups) {
+ for (i = 0; i < cred->group_info->ngroups; i++) {
+ gid = from_kgid(&init_user_ns,
+ cred->group_info->gid[i]);
+ for (j = 0; j < auth->match.num_gids; j++) {
+ if (gid == auth->match.gids[j]) {
+ gid_matched = true;
+ break;
+ }
+ }
+ if (gid_matched)
+ break;
+ }
+ }
+ if (!gid_matched)
+ return 0;
+ }
+ }
+
+ /* path match */
+ if (auth->match.path) {
+ if (!tpath)
+ return 0;
+
+ tlen = strlen(tpath);
+ len = strlen(auth->match.path);
+ if (len) {
+ char *_tpath = tpath;
+ bool free_tpath = false;
+ int m, n;
+
+ doutc(cl, "server path %s, tpath %s, match.path %s\n",
+ spath, tpath, auth->match.path);
+ if (spath && (m = strlen(spath)) != 1) {
+ /* mount path + '/' + tpath + an extra space */
+ n = m + 1 + tlen + 1;
+ _tpath = kmalloc(n, GFP_NOFS);
+ if (!_tpath)
+ return -ENOMEM;
+ /* remove the leading '/' */
+ snprintf(_tpath, n, "%s/%s", spath + 1, tpath);
+ free_tpath = true;
+ tlen = strlen(_tpath);
+ }
+
+ /*
+ * Please note the tailing '/' for match.path has already
+ * been removed when parsing.
+ *
+ * Remove the tailing '/' for the target path.
+ */
+ while (tlen && _tpath[tlen - 1] == '/') {
+ _tpath[tlen - 1] = '\0';
+ tlen -= 1;
+ }
+ doutc(cl, "_tpath %s\n", _tpath);
+
+ /*
+ * In case first == _tpath && tlen == len:
+ * match.path=/foo --> /foo _path=/foo --> match
+ * match.path=/foo/ --> /foo _path=/foo --> match
+ *
+ * In case first == _tmatch.path && tlen > len:
+ * match.path=/foo/ --> /foo _path=/foo/ --> match
+ * match.path=/foo --> /foo _path=/foo/ --> match
+ * match.path=/foo/ --> /foo _path=/foo/d --> match
+ * match.path=/foo --> /foo _path=/food --> mismatch
+ *
+ * All the other cases --> mismatch
+ */
+ bool path_matched = true;
+ char *first = strstr(_tpath, auth->match.path);
+ if (first != _tpath ||
+ (tlen > len && _tpath[len] != '/')) {
+ path_matched = false;
+ }
+
+ if (free_tpath)
+ kfree(_tpath);
+
+ if (!path_matched)
+ return 0;
+ }
+ }
+
+ doutc(cl, "matched\n");
+ return 1;
+}
+
+int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath, int mask)
+{
+ const struct cred *cred = get_current_cred();
+ u32 caller_uid = from_kuid(&init_user_ns, cred->fsuid);
+ u32 caller_gid = from_kgid(&init_user_ns, cred->fsgid);
+ struct ceph_mds_cap_auth *rw_perms_s = NULL;
+ struct ceph_client *cl = mdsc->fsc->client;
+ bool root_squash_perms = true;
+ int i, err;
+
+ doutc(cl, "tpath '%s', mask %d, caller_uid %d, caller_gid %d\n",
+ tpath, mask, caller_uid, caller_gid);
+
+ for (i = 0; i < mdsc->s_cap_auths_num; i++) {
+ struct ceph_mds_cap_auth *s = &mdsc->s_cap_auths[i];
+
+ err = ceph_mds_auth_match(mdsc, s, cred, tpath);
+ if (err < 0) {
+ put_cred(cred);
+ return err;
+ } else if (err > 0) {
+ /* always follow the last auth caps' permission */
+ root_squash_perms = true;
+ rw_perms_s = NULL;
+ if ((mask & MAY_WRITE) && s->writeable &&
+ s->match.root_squash && (!caller_uid || !caller_gid))
+ root_squash_perms = false;
+
+ if (((mask & MAY_WRITE) && !s->writeable) ||
+ ((mask & MAY_READ) && !s->readable))
+ rw_perms_s = s;
+ }
+ }
+
+ put_cred(cred);
+
+ doutc(cl, "root_squash_perms %d, rw_perms_s %p\n", root_squash_perms,
+ rw_perms_s);
+ if (root_squash_perms && rw_perms_s == NULL) {
+ doutc(cl, "access allowed\n");
+ return 0;
+ }
+
+ if (!root_squash_perms) {
+ doutc(cl, "root_squash is enabled and user(%d %d) isn't allowed to write",
+ caller_uid, caller_gid);
+ }
+ if (rw_perms_s) {
+ doutc(cl, "mds auth caps readable/writeable %d/%d while request r/w %d/%d",
+ rw_perms_s->readable, rw_perms_s->writeable,
+ !!(mask & MAY_READ), !!(mask & MAY_WRITE));
+ }
+ doutc(cl, "access denied\n");
+ return -EACCES;
+}
+
/*
* called before mount is ro, and before dentries are torn down.
* (hmm, does this still race with new lookups?)
@@ -5605,6 +5876,7 @@ void ceph_mdsc_sync(struct ceph_mds_client *mdsc)
mutex_unlock(&mdsc->mutex);
ceph_flush_dirty_caps(mdsc);
+ ceph_flush_cap_releases(mdsc);
spin_lock(&mdsc->cap_dirty_lock);
want_flush = mdsc->last_cap_flush_tid;
if (!list_empty(&mdsc->cap_flush_list)) {
@@ -5743,6 +6015,18 @@ static void ceph_mdsc_stop(struct ceph_mds_client *mdsc)
ceph_mdsmap_destroy(mdsc->mdsmap);
kfree(mdsc->sessions);
ceph_caps_finalize(mdsc);
+
+ if (mdsc->s_cap_auths) {
+ int i;
+
+ for (i = 0; i < mdsc->s_cap_auths_num; i++) {
+ kfree(mdsc->s_cap_auths[i].match.gids);
+ kfree(mdsc->s_cap_auths[i].match.path);
+ kfree(mdsc->s_cap_auths[i].match.fs_name);
+ }
+ kfree(mdsc->s_cap_auths);
+ }
+
ceph_pool_perm_destroy(mdsc);
}
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index b88e80415224..3e2a6fa7c19a 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -35,8 +35,9 @@ enum ceph_feature_type {
CEPHFS_FEATURE_32BITS_RETRY_FWD,
CEPHFS_FEATURE_NEW_SNAPREALM_INFO,
CEPHFS_FEATURE_HAS_OWNER_UIDGID,
+ CEPHFS_FEATURE_MDS_AUTH_CAPS_CHECK,
- CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_HAS_OWNER_UIDGID,
+ CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_MDS_AUTH_CAPS_CHECK,
};
#define CEPHFS_FEATURES_CLIENT_SUPPORTED { \
@@ -52,6 +53,7 @@ enum ceph_feature_type {
CEPHFS_FEATURE_OP_GETVXATTR, \
CEPHFS_FEATURE_32BITS_RETRY_FWD, \
CEPHFS_FEATURE_HAS_OWNER_UIDGID, \
+ CEPHFS_FEATURE_MDS_AUTH_CAPS_CHECK, \
}
/*
@@ -71,6 +73,24 @@ enum ceph_feature_type {
struct ceph_fs_client;
struct ceph_cap;
+#define MDS_AUTH_UID_ANY -1
+
+struct ceph_mds_cap_match {
+ s64 uid; /* default to MDS_AUTH_UID_ANY */
+ u32 num_gids;
+ u32 *gids; /* use these GIDs */
+ char *path; /* require path to be child of this
+ (may be "" or "/" for any) */
+ char *fs_name;
+ bool root_squash; /* default to false */
+};
+
+struct ceph_mds_cap_auth {
+ struct ceph_mds_cap_match match;
+ bool readable;
+ bool writeable;
+};
+
/*
* parsed info about a single inode. pointers are into the encoded
* on-wire structures within the mds reply message payload.
@@ -279,6 +299,8 @@ struct ceph_mds_request {
struct inode *r_target_inode; /* resulting inode */
struct inode *r_new_inode; /* new inode (for creates) */
+ const struct qstr *r_dname; /* stable name (for ->d_revalidate) */
+
#define CEPH_MDS_R_DIRECT_IS_HASH (1) /* r_direct_hash is valid */
#define CEPH_MDS_R_ABORTED (2) /* call was aborted */
#define CEPH_MDS_R_GOT_UNSAFE (3) /* got an unsafe reply */
@@ -396,6 +418,8 @@ struct ceph_quotarealm_inode {
struct inode *inode;
};
+#ifdef CONFIG_DEBUG_FS
+
struct cap_wait {
struct list_head list;
u64 ino;
@@ -404,6 +428,8 @@ struct cap_wait {
int want;
};
+#endif
+
enum {
CEPH_MDSC_STOPPING_BEGIN = 1,
CEPH_MDSC_STOPPING_FLUSHING = 2,
@@ -432,6 +458,9 @@ struct ceph_mds_client {
atomic_t stopping_blockers;
struct completion stopping_waiter;
+ atomic64_t dirty_folios;
+ wait_queue_head_t flush_end_wq;
+
atomic64_t quotarealms_count; /* # realms with quota */
/*
* We keep a list of inodes we don't see in the mountpoint but that we
@@ -492,7 +521,9 @@ struct ceph_mds_client {
spinlock_t caps_list_lock;
struct list_head caps_list; /* unused (reserved or
unreserved) */
+#ifdef CONFIG_DEBUG_FS
struct list_head cap_wait_list;
+#endif
int caps_total_count; /* total caps allocated */
int caps_use_count; /* in use */
int caps_use_max; /* max used caps */
@@ -513,6 +544,9 @@ struct ceph_mds_client {
struct rw_semaphore pool_perm_rwsem;
struct rb_root pool_perm_tree;
+ u32 s_cap_auths_num;
+ struct ceph_mds_cap_auth *s_cap_auths;
+
char nodename[__NEW_UTS_LEN + 1];
};
@@ -530,9 +564,6 @@ extern struct ceph_mds_session *
ceph_get_mds_session(struct ceph_mds_session *s);
extern void ceph_put_mds_session(struct ceph_mds_session *s);
-extern int ceph_send_msg_mds(struct ceph_mds_client *mdsc,
- struct ceph_msg *msg, int mds);
-
extern int ceph_mdsc_init(struct ceph_fs_client *fsc);
extern void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc);
extern void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc);
@@ -573,14 +604,17 @@ extern void ceph_mdsc_iterate_sessions(struct ceph_mds_client *mdsc,
extern struct ceph_msg *ceph_create_session_msg(u32 op, u64 seq);
extern void __ceph_queue_cap_release(struct ceph_mds_session *session,
struct ceph_cap *cap);
-extern void ceph_flush_cap_releases(struct ceph_mds_client *mdsc,
- struct ceph_mds_session *session);
+extern void ceph_flush_session_cap_releases(struct ceph_mds_client *mdsc,
+ struct ceph_mds_session *session);
extern void ceph_queue_cap_reclaim_work(struct ceph_mds_client *mdsc);
extern void ceph_reclaim_caps_nr(struct ceph_mds_client *mdsc, int nr);
extern void ceph_queue_cap_unlink_work(struct ceph_mds_client *mdsc);
extern int ceph_iterate_session_caps(struct ceph_mds_session *session,
int (*cb)(struct inode *, int mds, void *),
void *arg);
+extern int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath,
+ int mask);
+
extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc);
static inline void ceph_mdsc_free_path(char *path, int len)
@@ -605,8 +639,6 @@ extern void ceph_mdsc_handle_fsmap(struct ceph_mds_client *mdsc,
extern struct ceph_mds_session *
ceph_mdsc_open_export_target_session(struct ceph_mds_client *mdsc, int target);
-extern void ceph_mdsc_open_export_target_sessions(struct ceph_mds_client *mdsc,
- struct ceph_mds_session *session);
extern int ceph_trim_caps(struct ceph_mds_client *mdsc,
struct ceph_mds_session *session,
diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
index 06ee397e0c3a..d90eda19bcc4 100644
--- a/fs/ceph/quota.c
+++ b/fs/ceph/quota.c
@@ -166,7 +166,7 @@ static struct inode *lookup_quotarealm_inode(struct ceph_mds_client *mdsc,
if (IS_ERR(in)) {
doutc(cl, "Can't lookup inode %llx (err: %ld)\n", realm->ino,
PTR_ERR(in));
- qri->timeout = jiffies + msecs_to_jiffies(60 * 1000); /* XXX */
+ qri->timeout = jiffies + secs_to_jiffies(60); /* XXX */
} else {
qri->timeout = 0;
qri->inode = in;
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 885cb5d4e771..f3951253e393 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -126,6 +126,7 @@ static int ceph_sync_fs(struct super_block *sb, int wait)
if (!wait) {
doutc(cl, "(non-blocking)\n");
ceph_flush_dirty_caps(fsc->mdsc);
+ ceph_flush_cap_releases(fsc->mdsc);
doutc(cl, "(non-blocking) done\n");
return 0;
}
@@ -284,8 +285,10 @@ static int ceph_parse_new_source(const char *dev_name, const char *dev_name_end,
size_t len;
struct ceph_fsid fsid;
struct ceph_parse_opts_ctx *pctx = fc->fs_private;
+ struct ceph_options *opts = pctx->copts;
struct ceph_mount_options *fsopt = pctx->opts;
- char *fsid_start, *fs_name_start;
+ const char *name_start = dev_name;
+ const char *fsid_start, *fs_name_start;
if (*dev_name_end != '=') {
dout("separator '=' missing in source");
@@ -295,8 +298,14 @@ static int ceph_parse_new_source(const char *dev_name, const char *dev_name_end,
fsid_start = strchr(dev_name, '@');
if (!fsid_start)
return invalfc(fc, "missing cluster fsid");
- ++fsid_start; /* start of cluster fsid */
+ len = fsid_start - name_start;
+ kfree(opts->name);
+ opts->name = kstrndup(name_start, len, GFP_KERNEL);
+ if (!opts->name)
+ return -ENOMEM;
+ dout("using %s entity name", opts->name);
+ ++fsid_start; /* start of cluster fsid */
fs_name_start = strchr(fsid_start, '.');
if (!fs_name_start)
return invalfc(fc, "missing file system name");
@@ -422,6 +431,8 @@ static int ceph_parse_mount_param(struct fs_context *fc,
switch (token) {
case Opt_snapdirname:
+ if (strlen(param->string) > NAME_MAX)
+ return invalfc(fc, "snapdirname too long");
kfree(fsopt->snapdir_name);
fsopt->snapdir_name = param->string;
param->string = NULL;
@@ -961,7 +972,8 @@ static int __init init_caches(void)
if (!ceph_mds_request_cachep)
goto bad_mds_req;
- ceph_wb_pagevec_pool = mempool_create_kmalloc_pool(10, CEPH_MAX_WRITE_SIZE >> PAGE_SHIFT);
+ ceph_wb_pagevec_pool = mempool_create_kmalloc_pool(10,
+ (CEPH_MAX_WRITE_SIZE >> PAGE_SHIFT) * sizeof(struct page *));
if (!ceph_wb_pagevec_pool)
goto bad_pagevec_pool;
@@ -1551,6 +1563,17 @@ static void ceph_kill_sb(struct super_block *s)
*/
sync_filesystem(s);
+ if (atomic64_read(&mdsc->dirty_folios) > 0) {
+ wait_queue_head_t *wq = &mdsc->flush_end_wq;
+ long timeleft = wait_event_killable_timeout(*wq,
+ atomic64_read(&mdsc->dirty_folios) <= 0,
+ fsc->client->options->mount_timeout);
+ if (!timeleft) /* timed out */
+ pr_warn_client(cl, "umount timed out, %ld\n", timeleft);
+ else if (timeleft < 0) /* killed */
+ pr_warn_client(cl, "umount was killed, %ld\n", timeleft);
+ }
+
spin_lock(&mdsc->stopping_lock);
mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHING;
wait = !!atomic_read(&mdsc->stopping_blockers);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index b63b4cd9b5b6..bb0db0cc8003 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -5,7 +5,7 @@
#include <linux/ceph/ceph_debug.h>
#include <linux/ceph/osd_client.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/backing-dev.h>
#include <linux/completion.h>
#include <linux/exportfs.h>
@@ -60,7 +60,7 @@
/* max size of osd read request, limited by libceph */
#define CEPH_MAX_READ_SIZE CEPH_MSG_MAX_DATA_LEN
-/* osd has a configurable limitaion of max write size.
+/* osd has a configurable limitation of max write size.
* CEPH_MSG_MAX_DATA_LEN should be small enough. */
#define CEPH_MAX_WRITE_SIZE CEPH_MSG_MAX_DATA_LEN
#define CEPH_RASIZE_DEFAULT (8192*1024) /* max readahead */
@@ -200,9 +200,10 @@ struct ceph_cap {
struct list_head caps_item;
};
-#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 */
+#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 */
+#define CHECK_CAPS_FLUSH_FORCE 8 /* force flush any caps */
struct ceph_cap_flush {
u64 tid;
@@ -795,7 +796,6 @@ extern int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
extern int __ceph_caps_revoking_other(struct ceph_inode_info *ci,
struct ceph_cap *ocap, int mask);
-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)
@@ -903,7 +903,7 @@ ceph_find_rw_context(struct ceph_file_info *cf)
}
struct ceph_readdir_cache_control {
- struct page *page;
+ struct folio *folio;
struct dentry **dentries;
int index;
};
@@ -1055,8 +1055,6 @@ extern int ceph_fill_trace(struct super_block *sb,
extern int ceph_readdir_prepopulate(struct ceph_mds_request *req,
struct ceph_mds_session *session);
-extern int ceph_inode_holds_cap(struct inode *inode, int mask);
-
extern bool ceph_inode_set_size(struct inode *inode, loff_t size);
extern void __ceph_do_pending_vmtruncate(struct inode *inode);
@@ -1134,8 +1132,7 @@ struct ceph_acl_sec_ctx {
void *acl;
#endif
#ifdef CONFIG_CEPH_FS_SECURITY_LABEL
- void *sec_ctx;
- u32 sec_ctxlen;
+ struct lsm_context lsmctx;
#endif
#ifdef CONFIG_FS_ENCRYPTION
struct ceph_fscrypt_auth *fscrypt_auth;
@@ -1207,10 +1204,6 @@ static inline void ceph_init_inode_acls(struct inode *inode,
struct ceph_acl_sec_ctx *as_ctx)
{
}
-static inline int ceph_acl_chmod(struct dentry *dentry, struct inode *inode)
-{
- return 0;
-}
static inline void ceph_forget_all_cached_acls(struct inode *inode)
{
@@ -1269,6 +1262,7 @@ extern bool __ceph_should_report_size(struct ceph_inode_info *ci);
extern void ceph_check_caps(struct ceph_inode_info *ci, int flags);
extern unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc);
extern void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc);
+extern void ceph_flush_cap_releases(struct ceph_mds_client *mdsc);
extern int ceph_drop_caps_for_unlink(struct inode *inode);
extern int ceph_encode_inode_release(void **p, struct inode *inode,
int mds, int drop, int unless, int force);
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index e066a556eccb..537165db4519 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -899,7 +899,7 @@ static int __get_required_blob_size(struct ceph_inode_info *ci, int name_size,
}
/*
- * If there are dirty xattrs, reencode xattrs into the prealloc_blob
+ * If there are dirty xattrs, re-encode xattrs into the prealloc_blob
* and swap into place. It returns the old i_xattrs.blob (or NULL) so
* that it can be freed by the caller as the i_ceph_lock is likely to be
* held.
@@ -1383,8 +1383,7 @@ int ceph_security_init_secctx(struct dentry *dentry, umode_t mode,
int err;
err = security_dentry_init_security(dentry, mode, &dentry->d_name,
- &name, &as_ctx->sec_ctx,
- &as_ctx->sec_ctxlen);
+ &name, &as_ctx->lsmctx);
if (err < 0) {
WARN_ON_ONCE(err != -EOPNOTSUPP);
err = 0; /* do nothing */
@@ -1409,7 +1408,7 @@ int ceph_security_init_secctx(struct dentry *dentry, umode_t mode,
*/
name_len = strlen(name);
err = ceph_pagelist_reserve(pagelist,
- 4 * 2 + name_len + as_ctx->sec_ctxlen);
+ 4 * 2 + name_len + as_ctx->lsmctx.len);
if (err)
goto out;
@@ -1432,8 +1431,9 @@ int ceph_security_init_secctx(struct dentry *dentry, umode_t mode,
ceph_pagelist_encode_32(pagelist, name_len);
ceph_pagelist_append(pagelist, name, name_len);
- ceph_pagelist_encode_32(pagelist, as_ctx->sec_ctxlen);
- ceph_pagelist_append(pagelist, as_ctx->sec_ctx, as_ctx->sec_ctxlen);
+ ceph_pagelist_encode_32(pagelist, as_ctx->lsmctx.len);
+ ceph_pagelist_append(pagelist, as_ctx->lsmctx.context,
+ as_ctx->lsmctx.len);
err = 0;
out:
@@ -1451,7 +1451,7 @@ void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx)
posix_acl_release(as_ctx->default_acl);
#endif
#ifdef CONFIG_CEPH_FS_SECURITY_LABEL
- security_release_secctx(as_ctx->sec_ctx, as_ctx->sec_ctxlen);
+ security_release_secctx(&as_ctx->lsmctx);
#endif
#ifdef CONFIG_FS_ENCRYPTION
kfree(as_ctx->fscrypt_auth);
generated by cgit (git 2.34.1) at 2025-07-23 07:48:08 +0000