linux/fs/ceph/addr.c

2054 lines
55 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 22:07:57 +08:00
// SPDX-License-Identifier: GPL-2.0
#include <linux/ceph/ceph_debug.h>
#include <linux/backing-dev.h>
#include <linux/fs.h>
#include <linux/mm.h>
9p, afs, ceph, nfs: Use current_is_kswapd() rather than gfpflags_allow_blocking() In 9p, afs ceph, and nfs, gfpflags_allow_blocking() (which wraps a test for __GFP_DIRECT_RECLAIM being set) is used to determine if ->releasepage() should wait for the completion of a DIO write to fscache with something like: if (folio_test_fscache(folio)) { if (!gfpflags_allow_blocking(gfp) || !(gfp & __GFP_FS)) return false; folio_wait_fscache(folio); } Instead, current_is_kswapd() should be used instead. Note that this is based on a patch originally by Zhaoyang Huang[1]. In addition to extending it to the other network filesystems and putting it on top of my fscache rewrite, it also needs to include linux/swap.h in a bunch of places. Can current_is_kswapd() be moved to linux/mm.h? Changes ======= ver #5: - Dropping the changes for cifs. Originally-signed-off-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com> Co-developed-by: David Howells <dhowells@redhat.com> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: Zhaoyang Huang <zhaoyang.huang@unisoc.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Steve French <smfrench@gmail.com> cc: Trond Myklebust <trond.myklebust@hammerspace.com> cc: linux-cachefs@redhat.com cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: linux-nfs@vger.kernel.org cc: linux-mm@kvack.org Link: https://lore.kernel.org/r/1638952658-20285-1-git-send-email-huangzhaoyang@gmail.com/ [1] Link: https://lore.kernel.org/r/164021590773.640689.16777975200823659231.stgit@warthog.procyon.org.uk/ # v4
2021-12-23 01:21:04 +08:00
#include <linux/swap.h>
#include <linux/pagemap.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/pagevec.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/signal.h>
#include <linux/iversion.h>
#include <linux/ktime.h>
#include <linux/netfs.h>
#include "super.h"
#include "mds_client.h"
#include "cache.h"
#include "metric.h"
#include <linux/ceph/osd_client.h>
#include <linux/ceph/striper.h>
/*
* Ceph address space ops.
*
* There are a few funny things going on here.
*
* The page->private field is used to reference a struct
* ceph_snap_context for _every_ dirty page. This indicates which
* snapshot the page was logically dirtied in, and thus which snap
* context needs to be associated with the osd write during writeback.
*
* Similarly, struct ceph_inode_info maintains a set of counters to
* count dirty pages on the inode. In the absence of snapshots,
* i_wrbuffer_ref == i_wrbuffer_ref_head == the dirty page count.
*
* When a snapshot is taken (that is, when the client receives
* notification that a snapshot was taken), each inode with caps and
* with dirty pages (dirty pages implies there is a cap) gets a new
* ceph_cap_snap in the i_cap_snaps list (which is sorted in ascending
* order, new snaps go to the tail). The i_wrbuffer_ref_head count is
* moved to capsnap->dirty. (Unless a sync write is currently in
* progress. In that case, the capsnap is said to be "pending", new
* writes cannot start, and the capsnap isn't "finalized" until the
* write completes (or fails) and a final size/mtime for the inode for
* that snap can be settled upon.) i_wrbuffer_ref_head is reset to 0.
*
* On writeback, we must submit writes to the osd IN SNAP ORDER. So,
* we look for the first capsnap in i_cap_snaps and write out pages in
* that snap context _only_. Then we move on to the next capsnap,
* eventually reaching the "live" or "head" context (i.e., pages that
* are not yet snapped) and are writing the most recently dirtied
* pages.
*
* Invalidate and so forth must take care to ensure the dirty page
* accounting is preserved.
*/
#define CONGESTION_ON_THRESH(congestion_kb) (congestion_kb >> (PAGE_SHIFT-10))
#define CONGESTION_OFF_THRESH(congestion_kb) \
(CONGESTION_ON_THRESH(congestion_kb) - \
(CONGESTION_ON_THRESH(congestion_kb) >> 2))
static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned int len,
struct folio **foliop, void **_fsdata);
static inline struct ceph_snap_context *page_snap_context(struct page *page)
{
if (PagePrivate(page))
return (void *)page->private;
return NULL;
}
/*
* Dirty a page. Optimistically adjust accounting, on the assumption
* that we won't race with invalidate. If we do, readjust.
*/
static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio)
{
struct inode *inode;
struct ceph_inode_info *ci;
struct ceph_snap_context *snapc;
if (folio_test_dirty(folio)) {
dout("%p dirty_folio %p idx %lu -- already dirty\n",
mapping->host, folio, folio->index);
VM_BUG_ON_FOLIO(!folio_test_private(folio), folio);
return false;
}
inode = mapping->host;
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,
struct ceph_cap_snap,
ci_item);
snapc = ceph_get_snap_context(capsnap->context);
capsnap->dirty_pages++;
} else {
BUG_ON(!ci->i_head_snapc);
snapc = ceph_get_snap_context(ci->i_head_snapc);
++ci->i_wrbuffer_ref_head;
}
if (ci->i_wrbuffer_ref == 0)
ihold(inode);
++ci->i_wrbuffer_ref;
dout("%p dirty_folio %p idx %lu head %d/%d -> %d/%d "
"snapc %p seq %lld (%d snaps)\n",
mapping->host, folio, folio->index,
ci->i_wrbuffer_ref-1, ci->i_wrbuffer_ref_head-1,
ci->i_wrbuffer_ref, ci->i_wrbuffer_ref_head,
snapc, snapc->seq, snapc->num_snaps);
spin_unlock(&ci->i_ceph_lock);
/*
* Reference snap context in folio->private. Also set
* PagePrivate so that we get invalidate_folio callback.
*/
VM_BUG_ON_FOLIO(folio_test_private(folio), folio);
folio_attach_private(folio, snapc);
return ceph_fscache_dirty_folio(mapping, folio);
}
/*
* If we are truncating the full folio (i.e. offset == 0), adjust the
* dirty folio counters appropriately. Only called if there is private
* data on the folio.
*/
static void ceph_invalidate_folio(struct folio *folio, size_t offset,
size_t length)
{
struct inode *inode;
struct ceph_inode_info *ci;
struct ceph_snap_context *snapc;
inode = folio->mapping->host;
ci = ceph_inode(inode);
if (offset != 0 || length != folio_size(folio)) {
dout("%p invalidate_folio idx %lu partial dirty page %zu~%zu\n",
inode, folio->index, offset, length);
return;
}
WARN_ON(!folio_test_locked(folio));
if (folio_test_private(folio)) {
dout("%p invalidate_folio idx %lu full dirty page\n",
inode, folio->index);
snapc = folio_detach_private(folio);
ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
ceph_put_snap_context(snapc);
}
folio_wait_fscache(folio);
}
static bool ceph_release_folio(struct folio *folio, gfp_t gfp)
{
struct inode *inode = folio->mapping->host;
dout("%llx:%llx release_folio idx %lu (%sdirty)\n",
ceph_vinop(inode),
folio->index, folio_test_dirty(folio) ? "" : "not ");
if (folio_test_private(folio))
return false;
if (folio_test_fscache(folio)) {
9p, afs, ceph, nfs: Use current_is_kswapd() rather than gfpflags_allow_blocking() In 9p, afs ceph, and nfs, gfpflags_allow_blocking() (which wraps a test for __GFP_DIRECT_RECLAIM being set) is used to determine if ->releasepage() should wait for the completion of a DIO write to fscache with something like: if (folio_test_fscache(folio)) { if (!gfpflags_allow_blocking(gfp) || !(gfp & __GFP_FS)) return false; folio_wait_fscache(folio); } Instead, current_is_kswapd() should be used instead. Note that this is based on a patch originally by Zhaoyang Huang[1]. In addition to extending it to the other network filesystems and putting it on top of my fscache rewrite, it also needs to include linux/swap.h in a bunch of places. Can current_is_kswapd() be moved to linux/mm.h? Changes ======= ver #5: - Dropping the changes for cifs. Originally-signed-off-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com> Co-developed-by: David Howells <dhowells@redhat.com> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: Zhaoyang Huang <zhaoyang.huang@unisoc.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Steve French <smfrench@gmail.com> cc: Trond Myklebust <trond.myklebust@hammerspace.com> cc: linux-cachefs@redhat.com cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: linux-nfs@vger.kernel.org cc: linux-mm@kvack.org Link: https://lore.kernel.org/r/1638952658-20285-1-git-send-email-huangzhaoyang@gmail.com/ [1] Link: https://lore.kernel.org/r/164021590773.640689.16777975200823659231.stgit@warthog.procyon.org.uk/ # v4
2021-12-23 01:21:04 +08:00
if (current_is_kswapd() || !(gfp & __GFP_FS))
return false;
folio_wait_fscache(folio);
}
ceph_fscache_note_page_release(inode);
return true;
}
static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq)
{
struct inode *inode = rreq->inode;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_file_layout *lo = &ci->i_layout;
u32 blockoff;
u64 blockno;
/* Expand the start downward */
blockno = div_u64_rem(rreq->start, lo->stripe_unit, &blockoff);
rreq->start = blockno * lo->stripe_unit;
rreq->len += blockoff;
/* Now, round up the length to the next block */
rreq->len = roundup(rreq->len, lo->stripe_unit);
}
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_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 ceph_fs_client *fsc = ceph_inode_to_client(req->r_inode);
struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
struct netfs_io_subrequest *subreq = req->r_priv;
int num_pages;
int err = req->r_result;
ceph_update_read_metrics(&fsc->mdsc->metric, req->r_start_latency,
req->r_end_latency, osd_data->length, err);
dout("%s: result %d subreq->len=%zu i_size=%lld\n", __func__, req->r_result,
subreq->len, i_size_read(req->r_inode));
/* no object means success but no data */
if (err == -ENOENT)
err = 0;
else if (err == -EBLOCKLISTED)
fsc->blocklisted = true;
if (err >= 0 && err < subreq->len)
__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
netfs_subreq_terminated(subreq, err, true);
num_pages = calc_pages_for(osd_data->alignment, osd_data->length);
ceph_put_page_vector(osd_data->pages, num_pages, false);
iput(req->r_inode);
}
static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
{
struct netfs_io_request *rreq = subreq->rreq;
struct inode *inode = rreq->inode;
struct ceph_mds_reply_info_parsed *rinfo;
struct ceph_mds_reply_info_in *iinfo;
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);
__clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
if (subreq->start >= inode->i_size)
goto out;
/* We need to fetch the inline data. */
mode = ceph_try_to_choose_auth_mds(inode, CEPH_STAT_CAP_INLINE_DATA);
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_GETATTR, mode);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out;
}
req->r_ino1 = ci->i_vino;
req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INLINE_DATA);
req->r_num_caps = 2;
err = ceph_mdsc_do_request(mdsc, NULL, req);
if (err < 0)
goto out;
rinfo = &req->r_reply_info;
iinfo = &rinfo->targeti;
if (iinfo->inline_version == CEPH_INLINE_NONE) {
/* The data got uninlined */
ceph_mdsc_put_request(req);
return false;
}
len = min_t(size_t, iinfo->inline_len - subreq->start, subreq->len);
iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, subreq->start, len);
err = copy_to_iter(iinfo->inline_data + subreq->start, len, &iter);
if (err == 0)
err = -EFAULT;
ceph_mdsc_put_request(req);
out:
netfs_subreq_terminated(subreq, err, false);
return true;
}
static void ceph_netfs_issue_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_client(inode);
struct ceph_osd_request *req;
struct ceph_vino vino = ceph_vino(inode);
struct iov_iter iter;
struct page **pages;
size_t page_off;
int err = 0;
u64 len = subreq->len;
if (ci->i_inline_version != CEPH_INLINE_NONE &&
ceph_netfs_issue_op_inline(subreq))
return;
req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, subreq->start, &len,
0, 1, CEPH_OSD_OP_READ,
CEPH_OSD_FLAG_READ | fsc->client->osdc.client->options->read_from_replica,
NULL, ci->i_truncate_seq, ci->i_truncate_size, false);
if (IS_ERR(req)) {
err = PTR_ERR(req);
req = NULL;
goto out;
}
dout("%s: pos=%llu orig_len=%zu len=%llu\n", __func__, subreq->start, subreq->len, len);
iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, subreq->start, len);
err = iov_iter_get_pages_alloc(&iter, &pages, len, &page_off);
if (err < 0) {
dout("%s: iov_ter_get_pages_alloc returned %d\n", __func__, err);
goto out;
}
/* should always give us a page-aligned read */
WARN_ON_ONCE(page_off);
len = err;
osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, false, false);
req->r_callback = finish_netfs_read;
req->r_priv = subreq;
req->r_inode = inode;
ihold(inode);
err = ceph_osdc_start_request(req->r_osdc, req, false);
if (err)
iput(inode);
out:
ceph_osdc_put_request(req);
if (err)
netfs_subreq_terminated(subreq, err, false);
dout("%s: result %d\n", __func__, err);
}
static int ceph_init_request(struct netfs_io_request *rreq, struct file *file)
{
struct inode *inode = rreq->inode;
int got = 0, want = CEPH_CAP_FILE_CACHE;
int ret = 0;
if (rreq->origin != NETFS_READAHEAD)
return 0;
if (file) {
struct ceph_rw_context *rw_ctx;
struct ceph_file_info *fi = file->private_data;
rw_ctx = ceph_find_rw_context(fi);
if (rw_ctx)
return 0;
}
/*
* readahead callers do not necessarily hold Fcb caps
* (e.g. fadvise, madvise).
*/
ret = ceph_try_get_caps(inode, CEPH_CAP_FILE_RD, want, true, &got);
if (ret < 0) {
dout("start_read %p, error getting cap\n", inode);
return ret;
}
if (!(got & want)) {
dout("start_read %p, no cache cap\n", inode);
return -EACCES;
}
if (ret == 0)
return -EACCES;
rreq->netfs_priv = (void *)(uintptr_t)got;
return 0;
}
static void ceph_netfs_free_request(struct netfs_io_request *rreq)
{
struct ceph_inode_info *ci = ceph_inode(rreq->inode);
int got = (uintptr_t)rreq->netfs_priv;
if (got)
ceph_put_cap_refs(ci, got);
}
netfs: Add a netfs inode context Add a netfs_i_context struct that should be included in the network filesystem's own inode struct wrapper, directly after the VFS's inode struct, e.g.: struct my_inode { struct { /* These must be contiguous */ struct inode vfs_inode; struct netfs_i_context netfs_ctx; }; }; The netfs_i_context struct so far contains a single field for the network filesystem to use - the cache cookie: struct netfs_i_context { ... struct fscache_cookie *cache; }; Three functions are provided to help with this: (1) void netfs_i_context_init(struct inode *inode, const struct netfs_request_ops *ops); Initialise the netfs context and set the operations. (2) struct netfs_i_context *netfs_i_context(struct inode *inode); Find the netfs context from the VFS inode. (3) struct inode *netfs_inode(struct netfs_i_context *ctx); Find the VFS inode from the netfs context. Changes ======= ver #4) - Fix netfs_is_cache_enabled() to check cookie->cache_priv to see if a cache is present[3]. - Fix netfs_skip_folio_read() to zero out all of the page, not just some of it[3]. ver #3) - Split out the bit to move ceph cap-getting on readahead into ceph_init_request()[1]. - Stick in a comment to the netfs inode structs indicating the contiguity requirements[2]. ver #2) - Adjust documentation to match. - Use "#if IS_ENABLED()" in netfs_i_cookie(), not "#ifdef". - Move the cap check from ceph_readahead() to ceph_init_request() to be called from netfslib. - Remove ceph_readahead() and use netfs_readahead() directly instead. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/8af0d47f17d89c06bbf602496dd845f2b0bf25b3.camel@kernel.org/ [1] Link: https://lore.kernel.org/r/beaf4f6a6c2575ed489adb14b257253c868f9a5c.camel@kernel.org/ [2] Link: https://lore.kernel.org/r/3536452.1647421585@warthog.procyon.org.uk/ [3] Link: https://lore.kernel.org/r/164622984545.3564931.15691742939278418580.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/164678213320.1200972.16807551936267647470.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/164692909854.2099075.9535537286264248057.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/306388.1647595110@warthog.procyon.org.uk/ # v4
2021-06-30 05:37:05 +08:00
const struct netfs_request_ops ceph_netfs_ops = {
.init_request = ceph_init_request,
.free_request = ceph_netfs_free_request,
.begin_cache_operation = ceph_begin_cache_operation,
.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);
}
static void ceph_fscache_write_terminated(void *priv, ssize_t error, bool was_async)
{
struct inode *inode = priv;
if (IS_ERR_VALUE(error) && error != -ENOBUFS)
ceph_fscache_invalidate(inode, false);
}
static void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, bool caching)
{
struct ceph_inode_info *ci = ceph_inode(inode);
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);
}
#else
static inline void ceph_set_page_fscache(struct page *page)
{
}
static inline void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, bool caching)
{
}
#endif /* CONFIG_CEPH_FSCACHE */
struct ceph_writeback_ctl
{
loff_t i_size;
u64 truncate_size;
u32 truncate_seq;
bool size_stable;
bool head_snapc;
};
/*
* Get ref for the oldest snapc for an inode with dirty data... that is, the
* only snap context we are allowed to write back.
*/
static struct ceph_snap_context *
get_oldest_context(struct inode *inode, struct ceph_writeback_ctl *ctl,
struct ceph_snap_context *page_snapc)
{
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_snap_context *snapc = NULL;
struct ceph_cap_snap *capsnap = NULL;
spin_lock(&ci->i_ceph_lock);
list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
dout(" cap_snap %p snapc %p has %d dirty pages\n", capsnap,
capsnap->context, capsnap->dirty_pages);
if (!capsnap->dirty_pages)
continue;
/* get i_size, truncate_{seq,size} for page_snapc? */
if (snapc && capsnap->context != page_snapc)
continue;
if (ctl) {
if (capsnap->writing) {
ctl->i_size = i_size_read(inode);
ctl->size_stable = false;
} else {
ctl->i_size = capsnap->size;
ctl->size_stable = true;
}
ctl->truncate_size = capsnap->truncate_size;
ctl->truncate_seq = capsnap->truncate_seq;
ctl->head_snapc = false;
}
if (snapc)
break;
snapc = ceph_get_snap_context(capsnap->context);
if (!page_snapc ||
page_snapc == snapc ||
page_snapc->seq > snapc->seq)
break;
}
if (!snapc && ci->i_wrbuffer_ref_head) {
snapc = ceph_get_snap_context(ci->i_head_snapc);
dout(" head snapc %p has %d dirty pages\n",
snapc, ci->i_wrbuffer_ref_head);
if (ctl) {
ctl->i_size = i_size_read(inode);
ctl->truncate_size = ci->i_truncate_size;
ctl->truncate_seq = ci->i_truncate_seq;
ctl->size_stable = false;
ctl->head_snapc = true;
}
}
spin_unlock(&ci->i_ceph_lock);
return snapc;
}
static u64 get_writepages_data_length(struct inode *inode,
struct page *page, u64 start)
{
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_snap_context *snapc = page_snap_context(page);
struct ceph_cap_snap *capsnap = NULL;
u64 end = i_size_read(inode);
if (snapc != ci->i_head_snapc) {
bool found = false;
spin_lock(&ci->i_ceph_lock);
list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
if (capsnap->context == snapc) {
if (!capsnap->writing)
end = capsnap->size;
found = true;
break;
}
}
spin_unlock(&ci->i_ceph_lock);
WARN_ON(!found);
}
if (end > page_offset(page) + thp_size(page))
end = page_offset(page) + thp_size(page);
return end > start ? end - start : 0;
}
/*
* Write a single page, but leave the page 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).
*/
static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
{
struct folio *folio = page_folio(page);
struct inode *inode = page->mapping->host;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_snap_context *snapc, *oldest;
loff_t page_off = page_offset(page);
int err;
loff_t len = thp_size(page);
struct ceph_writeback_ctl ceph_wbc;
struct ceph_osd_client *osdc = &fsc->client->osdc;
struct ceph_osd_request *req;
bool caching = ceph_is_cache_enabled(inode);
dout("writepage %p idx %lu\n", page, page->index);
/* verify this is a writeable snap context */
snapc = page_snap_context(page);
if (!snapc) {
dout("writepage %p page %p not dirty?\n", inode, page);
return 0;
}
oldest = get_oldest_context(inode, &ceph_wbc, snapc);
if (snapc->seq > oldest->seq) {
dout("writepage %p page %p snapc %p not writeable - noop\n",
inode, page, 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);
return 0;
}
ceph_put_snap_context(oldest);
/* is this a partial page at end of file? */
if (page_off >= ceph_wbc.i_size) {
dout("folio at %lu beyond eof %llu\n", folio->index,
ceph_wbc.i_size);
folio_invalidate(folio, 0, folio_size(folio));
return 0;
}
if (ceph_wbc.i_size < page_off + len)
len = ceph_wbc.i_size - page_off;
dout("writepage %p page %p index %lu on %llu~%llu snapc %p seq %lld\n",
inode, page, page->index, page_off, len, snapc, snapc->seq);
if (atomic_long_inc_return(&fsc->writeback_count) >
CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
ceph: remove reliance on bdi congestion The bdi congestion tracking in not widely used and will be removed. CEPHfs is one of a small number of filesystems that uses it, setting just the async (write) congestion flags at what it determines are appropriate times. The only remaining effect of the async flag is to cause (some) WB_SYNC_NONE writes to be skipped. So instead of setting the flag, set an internal flag and change: - .writepages to do nothing if WB_SYNC_NONE and the flag is set - .writepage to return AOP_WRITEPAGE_ACTIVATE if WB_SYNC_NONE and the flag is set. The writepages change causes a behavioural change in that pageout() can now return PAGE_ACTIVATE instead of PAGE_KEEP, so SetPageActive() will be called on the page which (I think) wil further delay the next attempt at writeout. This might be a good thing. Link: https://lkml.kernel.org/r/164549983739.9187.14895675781408171186.stgit@noble.brown Signed-off-by: NeilBrown <neilb@suse.de> Cc: Anna Schumaker <Anna.Schumaker@Netapp.com> Cc: Chao Yu <chao@kernel.org> Cc: Darrick J. Wong <djwong@kernel.org> Cc: Ilya Dryomov <idryomov@gmail.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jan Kara <jack@suse.cz> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Lars Ellenberg <lars.ellenberg@linbit.com> Cc: Miklos Szeredi <miklos@szeredi.hu> Cc: Paolo Valente <paolo.valente@linaro.org> Cc: Philipp Reisner <philipp.reisner@linbit.com> Cc: Ryusuke Konishi <konishi.ryusuke@gmail.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 05:39:04 +08:00
fsc->write_congested = true;
req = ceph_osdc_new_request(osdc, &ci->i_layout, ceph_vino(inode), page_off, &len, 0, 1,
CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE, snapc,
ceph_wbc.truncate_seq, ceph_wbc.truncate_size,
true);
if (IS_ERR(req)) {
redirty_page_for_writepage(wbc, page);
return PTR_ERR(req);
}
set_page_writeback(page);
if (caching)
ceph_set_page_fscache(page);
ceph_fscache_write_to_cache(inode, page_off, len, caching);
/* it may be a short write due to an object boundary */
WARN_ON_ONCE(len > thp_size(page));
osd_req_op_extent_osd_data_pages(req, 0, &page, len, 0, false, false);
dout("writepage %llu~%llu (%llu bytes)\n", page_off, len, len);
req->r_mtime = inode->i_mtime;
err = ceph_osdc_start_request(osdc, req, true);
if (!err)
err = ceph_osdc_wait_request(osdc, req);
ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
req->r_end_latency, len, err);
ceph_osdc_put_request(req);
if (err == 0)
err = len;
if (err < 0) {
struct writeback_control tmp_wbc;
if (!wbc)
wbc = &tmp_wbc;
if (err == -ERESTARTSYS) {
/* killed by SIGKILL */
dout("writepage interrupted page %p\n", page);
redirty_page_for_writepage(wbc, page);
end_page_writeback(page);
return err;
}
if (err == -EBLOCKLISTED)
fsc->blocklisted = true;
dout("writepage setting page/mapping error %d %p\n",
err, page);
mapping_set_error(&inode->i_data, err);
wbc->pages_skipped++;
} else {
dout("writepage cleaned page %p\n", page);
err = 0; /* vfs expects us to return 0 */
}
oldest = detach_page_private(page);
WARN_ON_ONCE(oldest != snapc);
end_page_writeback(page);
ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
ceph_put_snap_context(snapc); /* page's reference */
if (atomic_long_dec_return(&fsc->writeback_count) <
CONGESTION_OFF_THRESH(fsc->mount_options->congestion_kb))
ceph: remove reliance on bdi congestion The bdi congestion tracking in not widely used and will be removed. CEPHfs is one of a small number of filesystems that uses it, setting just the async (write) congestion flags at what it determines are appropriate times. The only remaining effect of the async flag is to cause (some) WB_SYNC_NONE writes to be skipped. So instead of setting the flag, set an internal flag and change: - .writepages to do nothing if WB_SYNC_NONE and the flag is set - .writepage to return AOP_WRITEPAGE_ACTIVATE if WB_SYNC_NONE and the flag is set. The writepages change causes a behavioural change in that pageout() can now return PAGE_ACTIVATE instead of PAGE_KEEP, so SetPageActive() will be called on the page which (I think) wil further delay the next attempt at writeout. This might be a good thing. Link: https://lkml.kernel.org/r/164549983739.9187.14895675781408171186.stgit@noble.brown Signed-off-by: NeilBrown <neilb@suse.de> Cc: Anna Schumaker <Anna.Schumaker@Netapp.com> Cc: Chao Yu <chao@kernel.org> Cc: Darrick J. Wong <djwong@kernel.org> Cc: Ilya Dryomov <idryomov@gmail.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jan Kara <jack@suse.cz> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Lars Ellenberg <lars.ellenberg@linbit.com> Cc: Miklos Szeredi <miklos@szeredi.hu> Cc: Paolo Valente <paolo.valente@linaro.org> Cc: Philipp Reisner <philipp.reisner@linbit.com> Cc: Ryusuke Konishi <konishi.ryusuke@gmail.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 05:39:04 +08:00
fsc->write_congested = false;
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);
ceph: remove reliance on bdi congestion The bdi congestion tracking in not widely used and will be removed. CEPHfs is one of a small number of filesystems that uses it, setting just the async (write) congestion flags at what it determines are appropriate times. The only remaining effect of the async flag is to cause (some) WB_SYNC_NONE writes to be skipped. So instead of setting the flag, set an internal flag and change: - .writepages to do nothing if WB_SYNC_NONE and the flag is set - .writepage to return AOP_WRITEPAGE_ACTIVATE if WB_SYNC_NONE and the flag is set. The writepages change causes a behavioural change in that pageout() can now return PAGE_ACTIVATE instead of PAGE_KEEP, so SetPageActive() will be called on the page which (I think) wil further delay the next attempt at writeout. This might be a good thing. Link: https://lkml.kernel.org/r/164549983739.9187.14895675781408171186.stgit@noble.brown Signed-off-by: NeilBrown <neilb@suse.de> Cc: Anna Schumaker <Anna.Schumaker@Netapp.com> Cc: Chao Yu <chao@kernel.org> Cc: Darrick J. Wong <djwong@kernel.org> Cc: Ilya Dryomov <idryomov@gmail.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jan Kara <jack@suse.cz> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Lars Ellenberg <lars.ellenberg@linbit.com> Cc: Miklos Szeredi <miklos@szeredi.hu> Cc: Paolo Valente <paolo.valente@linaro.org> Cc: Philipp Reisner <philipp.reisner@linbit.com> Cc: Ryusuke Konishi <konishi.ryusuke@gmail.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 05:39:04 +08:00
if (wbc->sync_mode == WB_SYNC_NONE &&
ceph_inode_to_client(inode)->write_congested)
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.
*
* If we get an error, set the mapping error bit, but not the individual
* page error bits.
*/
static void writepages_finish(struct ceph_osd_request *req)
{
struct inode *inode = req->r_inode;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_osd_data *osd_data;
struct page *page;
int num_pages, total_pages = 0;
int i, j;
int rc = req->r_result;
struct ceph_snap_context *snapc = req->r_snapc;
struct address_space *mapping = inode->i_mapping;
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
unsigned int len = 0;
bool remove_page;
dout("writepages_finish %p rc %d\n", inode, rc);
if (rc < 0) {
mapping_set_error(mapping, rc);
ceph_set_error_write(ci);
if (rc == -EBLOCKLISTED)
fsc->blocklisted = true;
} else {
ceph_clear_error_write(ci);
}
/*
* We lost the cache cap, need to truncate the page before
* it is unlocked, otherwise we'd truncate it later in the
* page truncation thread, possibly losing some data that
* raced its way in
*/
remove_page = !(ceph_caps_issued(ci) &
(CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO));
/* clean all pages */
for (i = 0; i < req->r_num_ops; i++) {
if (req->r_ops[i].op != CEPH_OSD_OP_WRITE) {
pr_warn("%s incorrect op %d req %p index %d tid %llu\n",
__func__, req->r_ops[i].op, req, i, req->r_tid);
break;
}
osd_data = osd_req_op_extent_osd_data(req, i);
BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_PAGES);
len += osd_data->length;
num_pages = calc_pages_for((u64)osd_data->alignment,
(u64)osd_data->length);
total_pages += num_pages;
for (j = 0; j < num_pages; j++) {
page = osd_data->pages[j];
BUG_ON(!page);
WARN_ON(!PageUptodate(page));
if (atomic_long_dec_return(&fsc->writeback_count) <
CONGESTION_OFF_THRESH(
fsc->mount_options->congestion_kb))
ceph: remove reliance on bdi congestion The bdi congestion tracking in not widely used and will be removed. CEPHfs is one of a small number of filesystems that uses it, setting just the async (write) congestion flags at what it determines are appropriate times. The only remaining effect of the async flag is to cause (some) WB_SYNC_NONE writes to be skipped. So instead of setting the flag, set an internal flag and change: - .writepages to do nothing if WB_SYNC_NONE and the flag is set - .writepage to return AOP_WRITEPAGE_ACTIVATE if WB_SYNC_NONE and the flag is set. The writepages change causes a behavioural change in that pageout() can now return PAGE_ACTIVATE instead of PAGE_KEEP, so SetPageActive() will be called on the page which (I think) wil further delay the next attempt at writeout. This might be a good thing. Link: https://lkml.kernel.org/r/164549983739.9187.14895675781408171186.stgit@noble.brown Signed-off-by: NeilBrown <neilb@suse.de> Cc: Anna Schumaker <Anna.Schumaker@Netapp.com> Cc: Chao Yu <chao@kernel.org> Cc: Darrick J. Wong <djwong@kernel.org> Cc: Ilya Dryomov <idryomov@gmail.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jan Kara <jack@suse.cz> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Lars Ellenberg <lars.ellenberg@linbit.com> Cc: Miklos Szeredi <miklos@szeredi.hu> Cc: Paolo Valente <paolo.valente@linaro.org> Cc: Philipp Reisner <philipp.reisner@linbit.com> Cc: Ryusuke Konishi <konishi.ryusuke@gmail.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 05:39:04 +08:00
fsc->write_congested = false;
ceph_put_snap_context(detach_page_private(page));
end_page_writeback(page);
dout("unlocking %p\n", page);
if (remove_page)
generic_error_remove_page(inode->i_mapping,
page);
unlock_page(page);
}
dout("writepages_finish %p wrote %llu bytes cleaned %d pages\n",
inode, osd_data->length, rc >= 0 ? num_pages : 0);
release_pages(osd_data->pages, num_pages);
}
ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
req->r_end_latency, len, rc);
ceph_put_wrbuffer_cap_refs(ci, total_pages, snapc);
osd_data = osd_req_op_extent_osd_data(req, 0);
if (osd_data->pages_from_pool)
mempool_free(osd_data->pages, ceph_wb_pagevec_pool);
else
kfree(osd_data->pages);
ceph_osdc_put_request(req);
}
/*
* initiate async writeback
*/
static int ceph_writepages_start(struct address_space *mapping,
struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
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 pagevec pvec;
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);
ceph: remove reliance on bdi congestion The bdi congestion tracking in not widely used and will be removed. CEPHfs is one of a small number of filesystems that uses it, setting just the async (write) congestion flags at what it determines are appropriate times. The only remaining effect of the async flag is to cause (some) WB_SYNC_NONE writes to be skipped. So instead of setting the flag, set an internal flag and change: - .writepages to do nothing if WB_SYNC_NONE and the flag is set - .writepage to return AOP_WRITEPAGE_ACTIVATE if WB_SYNC_NONE and the flag is set. The writepages change causes a behavioural change in that pageout() can now return PAGE_ACTIVATE instead of PAGE_KEEP, so SetPageActive() will be called on the page which (I think) wil further delay the next attempt at writeout. This might be a good thing. Link: https://lkml.kernel.org/r/164549983739.9187.14895675781408171186.stgit@noble.brown Signed-off-by: NeilBrown <neilb@suse.de> Cc: Anna Schumaker <Anna.Schumaker@Netapp.com> Cc: Chao Yu <chao@kernel.org> Cc: Darrick J. Wong <djwong@kernel.org> Cc: Ilya Dryomov <idryomov@gmail.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jan Kara <jack@suse.cz> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Lars Ellenberg <lars.ellenberg@linbit.com> Cc: Miklos Szeredi <miklos@szeredi.hu> Cc: Paolo Valente <paolo.valente@linaro.org> Cc: Philipp Reisner <philipp.reisner@linbit.com> Cc: Ryusuke Konishi <konishi.ryusuke@gmail.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 05:39:04 +08:00
if (wbc->sync_mode == WB_SYNC_NONE &&
fsc->write_congested)
return 0;
dout("writepages_start %p (mode=%s)\n", 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) {
pr_warn_ratelimited(
"writepage_start %p %lld forced umount\n",
inode, ceph_ino(inode));
}
mapping_set_error(mapping, -EIO);
return -EIO; /* we're in a forced umount, don't write! */
}
if (fsc->mount_options->wsize < wsize)
wsize = fsc->mount_options->wsize;
pagevec_init(&pvec);
start_index = wbc->range_cyclic ? mapping->writeback_index : 0;
index = start_index;
retry:
/* find oldest snap context with dirty data */
snapc = get_oldest_context(inode, &ceph_wbc, NULL);
if (!snapc) {
/* hmm, why does writepages get called when there
is no dirty data? */
dout(" no snap context with dirty data?\n");
goto out;
}
dout(" 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) {
/* where to start/end? */
if (wbc->range_cyclic) {
index = start_index;
end = -1;
if (index > 0)
should_loop = true;
dout(" cyclic, start at %lu\n", index);
} else {
index = wbc->range_start >> PAGE_SHIFT;
end = wbc->range_end >> PAGE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = true;
dout(" not cyclic, %lu to %lu\n", index, end);
}
} 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;
dout(" non-head snapc, range whole\n");
}
ceph_put_snap_context(last_snapc);
last_snapc = snapc;
while (!done && index <= end) {
int num_ops = 0, op_idx;
unsigned i, pvec_pages, 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;
max_pages = wsize >> PAGE_SHIFT;
get_more_pages:
pvec_pages = pagevec_lookup_range_tag(&pvec, mapping, &index,
end, PAGECACHE_TAG_DIRTY);
dout("pagevec_lookup_range_tag got %d\n", pvec_pages);
if (!pvec_pages && !locked_pages)
break;
for (i = 0; i < pvec_pages && locked_pages < max_pages; i++) {
page = pvec.pages[i];
dout("? %p idx %lu\n", page, page->index);
if (locked_pages == 0)
lock_page(page); /* first page */
else if (!trylock_page(page))
break;
/* only dirty pages, or our accounting breaks */
if (unlikely(!PageDirty(page)) ||
unlikely(page->mapping != mapping)) {
dout("!dirty or !mapping %p\n", page);
unlock_page(page);
continue;
}
/* only if matching snap context */
pgsnapc = page_snap_context(page);
if (pgsnapc != snapc) {
dout("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;
}
if (page_offset(page) >= ceph_wbc.i_size) {
struct folio *folio = page_folio(page);
dout("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));
folio_unlock(folio);
continue;
}
if (strip_unit_end && (page->index > strip_unit_end)) {
dout("end of strip unit %p\n", page);
unlock_page(page);
break;
}
if (PageWriteback(page) || PageFsCache(page)) {
if (wbc->sync_mode == WB_SYNC_NONE) {
dout("%p under writeback\n", page);
unlock_page(page);
continue;
}
dout("waiting on writeback %p\n", page);
wait_on_page_writeback(page);
wait_on_page_fscache(page);
}
if (!clear_page_dirty_for_io(page)) {
dout("%p !clear_page_dirty_for_io\n", page);
unlock_page(page);
continue;
}
/*
* 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 +
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
((len - 1) >> PAGE_SHIFT);
BUG_ON(pages);
max_pages = calc_pages_for(0, (u64)len);
treewide: kmalloc() -> kmalloc_array() The kmalloc() function has a 2-factor argument form, kmalloc_array(). This patch replaces cases of: kmalloc(a * b, gfp) with: kmalloc_array(a * b, gfp) as well as handling cases of: kmalloc(a * b * c, gfp) with: kmalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kmalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kmalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The tools/ directory was manually excluded, since it has its own implementation of kmalloc(). The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kmalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kmalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kmalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(char) * COUNT + COUNT , ...) | kmalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kmalloc + kmalloc_array ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kmalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kmalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kmalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kmalloc(C1 * C2 * C3, ...) | kmalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kmalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kmalloc(sizeof(THING) * C2, ...) | kmalloc(sizeof(TYPE) * C2, ...) | kmalloc(C1 * C2 * C3, ...) | kmalloc(C1 * C2, ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - (E1) * E2 + E1, E2 , ...) | - kmalloc + kmalloc_array ( - (E1) * (E2) + E1, E2 , ...) | - kmalloc + kmalloc_array ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 04:55:00 +08:00
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 !=
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
(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 pvec */
dout("%p will write page %p idx %lu\n",
inode, page, page->index);
if (atomic_long_inc_return(&fsc->writeback_count) >
CONGESTION_ON_THRESH(
ceph: remove reliance on bdi congestion The bdi congestion tracking in not widely used and will be removed. CEPHfs is one of a small number of filesystems that uses it, setting just the async (write) congestion flags at what it determines are appropriate times. The only remaining effect of the async flag is to cause (some) WB_SYNC_NONE writes to be skipped. So instead of setting the flag, set an internal flag and change: - .writepages to do nothing if WB_SYNC_NONE and the flag is set - .writepage to return AOP_WRITEPAGE_ACTIVATE if WB_SYNC_NONE and the flag is set. The writepages change causes a behavioural change in that pageout() can now return PAGE_ACTIVATE instead of PAGE_KEEP, so SetPageActive() will be called on the page which (I think) wil further delay the next attempt at writeout. This might be a good thing. Link: https://lkml.kernel.org/r/164549983739.9187.14895675781408171186.stgit@noble.brown Signed-off-by: NeilBrown <neilb@suse.de> Cc: Anna Schumaker <Anna.Schumaker@Netapp.com> Cc: Chao Yu <chao@kernel.org> Cc: Darrick J. Wong <djwong@kernel.org> Cc: Ilya Dryomov <idryomov@gmail.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Jan Kara <jack@suse.cz> Cc: Jeff Layton <jlayton@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Lars Ellenberg <lars.ellenberg@linbit.com> Cc: Miklos Szeredi <miklos@szeredi.hu> Cc: Paolo Valente <paolo.valente@linaro.org> Cc: Philipp Reisner <philipp.reisner@linbit.com> Cc: Ryusuke Konishi <konishi.ryusuke@gmail.com> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-23 05:39:04 +08:00
fsc->mount_options->congestion_kb))
fsc->write_congested = true;
pages[locked_pages++] = page;
pvec.pages[i] = NULL;
len += thp_size(page);
}
/* did we get anything? */
if (!locked_pages)
goto release_pvec_pages;
if (i) {
unsigned j, n = 0;
/* shift unused page to beginning of pvec */
for (j = 0; j < pvec_pages; j++) {
if (!pvec.pages[j])
continue;
if (n < j)
pvec.pages[n] = pvec.pages[j];
n++;
}
pvec.nr = n;
if (pvec_pages && i == pvec_pages &&
locked_pages < max_pages) {
dout("reached end pvec, trying for more\n");
pagevec_release(&pvec);
goto get_more_pages;
}
}
new_request:
offset = page_offset(pages[0]);
len = wsize;
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));
}
BUG_ON(len < page_offset(pages[locked_pages - 1]) +
thp_size(page) - offset);
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++) {
u64 cur_offset = page_offset(pages[i]);
/*
* 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);
dout("writepages 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(pages[i]);
if (caching)
ceph_set_page_fscache(pages[i]);
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 == 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);
}
dout("writepages 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);
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;
treewide: kmalloc() -> kmalloc_array() The kmalloc() function has a 2-factor argument form, kmalloc_array(). This patch replaces cases of: kmalloc(a * b, gfp) with: kmalloc_array(a * b, gfp) as well as handling cases of: kmalloc(a * b * c, gfp) with: kmalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kmalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kmalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The tools/ directory was manually excluded, since it has its own implementation of kmalloc(). The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kmalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kmalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kmalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(char) * COUNT + COUNT , ...) | kmalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kmalloc + kmalloc_array ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kmalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kmalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kmalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kmalloc(C1 * C2 * C3, ...) | kmalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kmalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kmalloc(sizeof(THING) * C2, ...) | kmalloc(sizeof(TYPE) * C2, ...) | kmalloc(C1 * C2 * C3, ...) | kmalloc(C1 * C2, ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - (E1) * E2 + E1, E2 , ...) | - kmalloc + kmalloc_array ( - (E1) * (E2) + E1, E2 , ...) | - kmalloc + kmalloc_array ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 04:55:00 +08:00
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);
}
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->i_mtime;
rc = ceph_osdc_start_request(&fsc->client->osdc, req, true);
BUG_ON(rc);
req = NULL;
wbc->nr_to_write -= i;
if (pages)
goto new_request;
/*
* We stop writing back only if we are not doing
* integrity sync. In case of integrity sync we have to
* keep going until we have written all the pages
* we tagged for writeback prior to entering this loop.
*/
if (wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE)
done = true;
release_pvec_pages:
dout("pagevec_release on %d pages (%p)\n", (int)pvec.nr,
pvec.nr ? pvec.pages[0] : NULL);
pagevec_release(&pvec);
}
if (should_loop && !done) {
/* more to do; loop back to beginning of file */
dout("writepages looping back to beginning of file\n");
end = start_index - 1; /* OK even when start_index == 0 */
/* 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 = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_WRITEBACK))) {
for (i = 0; i < nr; i++) {
page = pvec.pages[i];
if (page_snap_context(page) != snapc)
continue;
wait_on_page_writeback(page);
}
pagevec_release(&pvec);
cond_resched();
}
}
start_index = 0;
index = 0;
goto retry;
}
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = index;
out:
ceph_osdc_put_request(req);
ceph_put_snap_context(last_snapc);
dout("writepages dend - startone, rc = %d\n", rc);
return rc;
}
/*
* See if a given @snapc is either writeable, or already written.
*/
static int context_is_writeable_or_written(struct inode *inode,
struct ceph_snap_context *snapc)
{
struct ceph_snap_context *oldest = get_oldest_context(inode, NULL, NULL);
int ret = !oldest || snapc->seq <= oldest->seq;
ceph_put_snap_context(oldest);
return ret;
}
/**
* ceph_find_incompatible - find an incompatible context and return it
* @page: page being dirtied
*
* We are only allowed to write into/dirty a page if the page 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.
*/
static struct ceph_snap_context *
ceph_find_incompatible(struct page *page)
{
struct inode *inode = page->mapping->host;
struct ceph_inode_info *ci = ceph_inode(inode);
if (ceph_inode_is_shutdown(inode)) {
dout(" page %p %llx:%llx is shutdown\n", page,
ceph_vinop(inode));
return ERR_PTR(-ESTALE);
}
for (;;) {
struct ceph_snap_context *snapc, *oldest;
wait_on_page_writeback(page);
snapc = page_snap_context(page);
if (!snapc || snapc == ci->i_head_snapc)
break;
/*
* this page 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);
dout(" page %p snapc %p not current or oldest\n", page, snapc);
return ceph_get_snap_context(snapc);
}
ceph_put_snap_context(oldest);
/* yay, writeable, do it now (without dropping page lock) */
dout(" page %p snapc %p not current, but oldest\n", page, snapc);
if (clear_page_dirty_for_io(page)) {
int r = writepage_nounlock(page, NULL);
if (r < 0)
return ERR_PTR(r);
}
}
return NULL;
}
static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned int len,
struct folio **foliop, void **_fsdata)
{
struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_snap_context *snapc;
snapc = ceph_find_incompatible(folio_page(*foliop, 0));
if (snapc) {
int r;
folio_unlock(*foliop);
folio_put(*foliop);
*foliop = NULL;
if (IS_ERR(snapc))
return PTR_ERR(snapc);
ceph_queue_writeback(inode);
r = wait_event_killable(ci->i_cap_wq,
context_is_writeable_or_written(inode, snapc));
ceph_put_snap_context(snapc);
return r == 0 ? -EAGAIN : r;
}
return 0;
}
/*
* We are only allowed to write into/dirty the page if the page is
* clean, or already dirty within the same snap context.
*/
static int ceph_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len,
struct page **pagep, void **fsdata)
{
struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dominique Martinet <asmadeus@codewreck.org> Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) <willy@infradead.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5
2021-08-11 16:49:13 +08:00
struct folio *folio = NULL;
int r;
r = netfs_write_begin(&ci->netfs, file, inode->i_mapping, pos, len, &folio, NULL);
if (r == 0)
netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dominique Martinet <asmadeus@codewreck.org> Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) <willy@infradead.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5
2021-08-11 16:49:13 +08:00
folio_wait_fscache(folio);
if (r < 0) {
netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dominique Martinet <asmadeus@codewreck.org> Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) <willy@infradead.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5
2021-08-11 16:49:13 +08:00
if (folio)
folio_put(folio);
} else {
netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dominique Martinet <asmadeus@codewreck.org> Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) <willy@infradead.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5
2021-08-11 16:49:13 +08:00
WARN_ON_ONCE(!folio_test_locked(folio));
*pagep = &folio->page;
}
return r;
}
/*
* we don't do anything in here that simple_write_end doesn't do
* except adjust dirty page accounting
*/
static int ceph_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dominique Martinet <asmadeus@codewreck.org> Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) <willy@infradead.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5
2021-08-11 16:49:13 +08:00
struct page *subpage, void *fsdata)
{
netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dominique Martinet <asmadeus@codewreck.org> Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) <willy@infradead.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5
2021-08-11 16:49:13 +08:00
struct folio *folio = page_folio(subpage);
struct inode *inode = file_inode(file);
bool check_cap = false;
netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dominique Martinet <asmadeus@codewreck.org> Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) <willy@infradead.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5
2021-08-11 16:49:13 +08:00
dout("write_end file %p inode %p folio %p %d~%d (%d)\n", file,
inode, folio, (int)pos, (int)copied, (int)len);
netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dominique Martinet <asmadeus@codewreck.org> Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) <willy@infradead.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5
2021-08-11 16:49:13 +08:00
if (!folio_test_uptodate(folio)) {
/* just return that nothing was copied on a short copy */
if (copied < len) {
copied = 0;
goto out;
}
netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dominique Martinet <asmadeus@codewreck.org> Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) <willy@infradead.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5
2021-08-11 16:49:13 +08:00
folio_mark_uptodate(folio);
}
/* did file size increase? */
if (pos+copied > i_size_read(inode))
check_cap = ceph_inode_set_size(inode, pos+copied);
netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dominique Martinet <asmadeus@codewreck.org> Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) <willy@infradead.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5
2021-08-11 16:49:13 +08:00
folio_mark_dirty(folio);
out:
netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Tested-by: Jeff Layton <jlayton@kernel.org> Tested-by: Dominique Martinet <asmadeus@codewreck.org> Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) <willy@infradead.org> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5
2021-08-11 16:49:13 +08:00
folio_unlock(folio);
folio_put(folio);
if (check_cap)
ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY, NULL);
return copied;
}
const struct address_space_operations ceph_aops = {
.read_folio = netfs_read_folio,
netfs: Add a netfs inode context Add a netfs_i_context struct that should be included in the network filesystem's own inode struct wrapper, directly after the VFS's inode struct, e.g.: struct my_inode { struct { /* These must be contiguous */ struct inode vfs_inode; struct netfs_i_context netfs_ctx; }; }; The netfs_i_context struct so far contains a single field for the network filesystem to use - the cache cookie: struct netfs_i_context { ... struct fscache_cookie *cache; }; Three functions are provided to help with this: (1) void netfs_i_context_init(struct inode *inode, const struct netfs_request_ops *ops); Initialise the netfs context and set the operations. (2) struct netfs_i_context *netfs_i_context(struct inode *inode); Find the netfs context from the VFS inode. (3) struct inode *netfs_inode(struct netfs_i_context *ctx); Find the VFS inode from the netfs context. Changes ======= ver #4) - Fix netfs_is_cache_enabled() to check cookie->cache_priv to see if a cache is present[3]. - Fix netfs_skip_folio_read() to zero out all of the page, not just some of it[3]. ver #3) - Split out the bit to move ceph cap-getting on readahead into ceph_init_request()[1]. - Stick in a comment to the netfs inode structs indicating the contiguity requirements[2]. ver #2) - Adjust documentation to match. - Use "#if IS_ENABLED()" in netfs_i_cookie(), not "#ifdef". - Move the cap check from ceph_readahead() to ceph_init_request() to be called from netfslib. - Remove ceph_readahead() and use netfs_readahead() directly instead. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/8af0d47f17d89c06bbf602496dd845f2b0bf25b3.camel@kernel.org/ [1] Link: https://lore.kernel.org/r/beaf4f6a6c2575ed489adb14b257253c868f9a5c.camel@kernel.org/ [2] Link: https://lore.kernel.org/r/3536452.1647421585@warthog.procyon.org.uk/ [3] Link: https://lore.kernel.org/r/164622984545.3564931.15691742939278418580.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/164678213320.1200972.16807551936267647470.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/164692909854.2099075.9535537286264248057.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/306388.1647595110@warthog.procyon.org.uk/ # v4
2021-06-30 05:37:05 +08:00
.readahead = netfs_readahead,
.writepage = ceph_writepage,
.writepages = ceph_writepages_start,
.write_begin = ceph_write_begin,
.write_end = ceph_write_end,
.dirty_folio = ceph_dirty_folio,
.invalidate_folio = ceph_invalidate_folio,
.release_folio = ceph_release_folio,
.direct_IO = noop_direct_IO,
};
static void ceph_block_sigs(sigset_t *oldset)
{
sigset_t mask;
siginitsetinv(&mask, sigmask(SIGKILL));
sigprocmask(SIG_BLOCK, &mask, oldset);
}
static void ceph_restore_sigs(sigset_t *oldset)
{
sigprocmask(SIG_SETMASK, oldset, NULL);
}
/*
* vm ops
*/
static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct inode *inode = file_inode(vma->vm_file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_file_info *fi = vma->vm_file->private_data;
loff_t off = (loff_t)vmf->pgoff << PAGE_SHIFT;
int want, got, err;
sigset_t oldset;
vm_fault_t ret = VM_FAULT_SIGBUS;
if (ceph_inode_is_shutdown(inode))
return ret;
ceph_block_sigs(&oldset);
dout("filemap_fault %p %llx.%llx %llu trying to get caps\n",
inode, ceph_vinop(inode), off);
if (fi->fmode & CEPH_FILE_MODE_LAZY)
want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
else
want = CEPH_CAP_FILE_CACHE;
got = 0;
err = ceph_get_caps(vma->vm_file, CEPH_CAP_FILE_RD, want, -1, &got);
if (err < 0)
goto out_restore;
dout("filemap_fault %p %llu got cap refs on %s\n",
inode, off, ceph_cap_string(got));
if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) ||
ci->i_inline_version == CEPH_INLINE_NONE) {
CEPH_DEFINE_RW_CONTEXT(rw_ctx, got);
ceph_add_rw_context(fi, &rw_ctx);
ret = filemap_fault(vmf);
ceph_del_rw_context(fi, &rw_ctx);
dout("filemap_fault %p %llu drop cap refs %s ret %x\n",
inode, off, ceph_cap_string(got), ret);
} else
err = -EAGAIN;
ceph_put_cap_refs(ci, got);
if (err != -EAGAIN)
goto out_restore;
/* read inline data */
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
if (off >= PAGE_SIZE) {
/* does not support inline data > PAGE_SIZE */
ret = VM_FAULT_SIGBUS;
} else {
struct address_space *mapping = inode->i_mapping;
struct page *page;
filemap_invalidate_lock_shared(mapping);
page = find_or_create_page(mapping, 0,
mapping_gfp_constraint(mapping, ~__GFP_FS));
if (!page) {
ret = VM_FAULT_OOM;
goto out_inline;
}
err = __ceph_do_getattr(inode, page,
CEPH_STAT_CAP_INLINE_DATA, true);
if (err < 0 || off >= i_size_read(inode)) {
unlock_page(page);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
put_page(page);
ret = vmf_error(err);
goto out_inline;
}
if (err < PAGE_SIZE)
zero_user_segment(page, err, PAGE_SIZE);
else
flush_dcache_page(page);
SetPageUptodate(page);
vmf->page = page;
ret = VM_FAULT_MAJOR | VM_FAULT_LOCKED;
out_inline:
filemap_invalidate_unlock_shared(mapping);
dout("filemap_fault %p %llu read inline data ret %x\n",
inode, off, ret);
}
out_restore:
ceph_restore_sigs(&oldset);
if (err < 0)
ret = vmf_error(err);
return ret;
}
static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct inode *inode = file_inode(vma->vm_file);
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);
loff_t size = i_size_read(inode);
size_t len;
int want, got, err;
sigset_t oldset;
vm_fault_t ret = VM_FAULT_SIGBUS;
if (ceph_inode_is_shutdown(inode))
return ret;
prealloc_cf = ceph_alloc_cap_flush();
if (!prealloc_cf)
return VM_FAULT_OOM;
sb_start_pagefault(inode->i_sb);
ceph_block_sigs(&oldset);
if (off + thp_size(page) <= size)
len = thp_size(page);
else
len = offset_in_thp(page, size);
dout("page_mkwrite %p %llx.%llx %llu~%zd getting caps i_size %llu\n",
inode, ceph_vinop(inode), off, len, size);
if (fi->fmode & CEPH_FILE_MODE_LAZY)
want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
else
want = CEPH_CAP_FILE_BUFFER;
got = 0;
err = ceph_get_caps(vma->vm_file, CEPH_CAP_FILE_WR, want, off + len, &got);
if (err < 0)
goto out_free;
dout("page_mkwrite %p %llu~%zd got cap refs on %s\n",
inode, off, len, ceph_cap_string(got));
/* Update time before taking page lock */
file_update_time(vma->vm_file);
inode_inc_iversion_raw(inode);
do {
struct ceph_snap_context *snapc;
lock_page(page);
if (page_mkwrite_check_truncate(page, inode) < 0) {
unlock_page(page);
ret = VM_FAULT_NOPAGE;
break;
}
snapc = ceph_find_incompatible(page);
if (!snapc) {
/* success. we'll keep the page locked. */
set_page_dirty(page);
ret = VM_FAULT_LOCKED;
break;
}
unlock_page(page);
if (IS_ERR(snapc)) {
ret = VM_FAULT_SIGBUS;
break;
}
ceph_queue_writeback(inode);
err = wait_event_killable(ci->i_cap_wq,
context_is_writeable_or_written(inode, snapc));
ceph_put_snap_context(snapc);
} while (err == 0);
if (ret == VM_FAULT_LOCKED) {
int dirty;
spin_lock(&ci->i_ceph_lock);
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR,
&prealloc_cf);
spin_unlock(&ci->i_ceph_lock);
if (dirty)
__mark_inode_dirty(inode, dirty);
}
dout("page_mkwrite %p %llu~%zd dropping cap refs on %s ret %x\n",
inode, off, len, ceph_cap_string(got), ret);
ceph_put_cap_refs_async(ci, got);
out_free:
ceph_restore_sigs(&oldset);
sb_end_pagefault(inode->i_sb);
ceph_free_cap_flush(prealloc_cf);
if (err < 0)
ret = vmf_error(err);
return ret;
}
void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
char *data, size_t len)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
if (locked_page) {
page = locked_page;
} else {
if (i_size_read(inode) == 0)
return;
page = find_or_create_page(mapping, 0,
mapping_gfp_constraint(mapping,
~__GFP_FS));
if (!page)
return;
if (PageUptodate(page)) {
unlock_page(page);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
put_page(page);
return;
}
}
dout("fill_inline_data %p %llx.%llx len %zu locked_page %p\n",
inode, ceph_vinop(inode), len, locked_page);
if (len > 0) {
void *kaddr = kmap_atomic(page);
memcpy(kaddr, data, len);
kunmap_atomic(kaddr);
}
if (page != locked_page) {
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
if (len < PAGE_SIZE)
zero_user_segment(page, len, PAGE_SIZE);
else
flush_dcache_page(page);
SetPageUptodate(page);
unlock_page(page);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
put_page(page);
}
}
int ceph_uninline_data(struct file *file)
{
struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
ceph: fix possible deadlock when holding Fwb to get inline_data 1, mount with wsync. 2, create a file with O_RDWR, and the request was sent to mds.0: ceph_atomic_open()--> ceph_mdsc_do_request(openc) finish_open(file, dentry, ceph_open)--> ceph_open()--> ceph_init_file()--> ceph_init_file_info()--> ceph_uninline_data()--> { ... if (inline_version == 1 || /* initial version, no data */ inline_version == CEPH_INLINE_NONE) goto out_unlock; ... } The inline_version will be 1, which is the initial version for the new create file. And here the ci->i_inline_version will keep with 1, it's buggy. 3, buffer write to the file immediately: ceph_write_iter()--> ceph_get_caps(file, need=Fw, want=Fb, ...); generic_perform_write()--> a_ops->write_begin()--> ceph_write_begin()--> netfs_write_begin()--> netfs_begin_read()--> netfs_rreq_submit_slice()--> netfs_read_from_server()--> rreq->netfs_ops->issue_read()--> ceph_netfs_issue_read()--> { ... if (ci->i_inline_version != CEPH_INLINE_NONE && ceph_netfs_issue_op_inline(subreq)) return; ... } ceph_put_cap_refs(ci, Fwb); The ceph_netfs_issue_op_inline() will send a getattr(Fsr) request to mds.1. 4, then the mds.1 will request the rd lock for CInode::filelock from the auth mds.0, the mds.0 will do the CInode::filelock state transation from excl --> sync, but it need to revoke the Fxwb caps back from the clients. While the kernel client has aleady held the Fwb caps and waiting for the getattr(Fsr). It's deadlock! URL: https://tracker.ceph.com/issues/55377 Signed-off-by: Xiubo Li <xiubli@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
2022-04-25 16:08:24 +08:00
struct ceph_osd_request *req = NULL;
struct ceph_cap_flush *prealloc_cf;
struct folio *folio = NULL;
u64 inline_version = CEPH_INLINE_NONE;
struct page *pages[1];
int err = 0;
u64 len;
ceph: fix possible deadlock when holding Fwb to get inline_data 1, mount with wsync. 2, create a file with O_RDWR, and the request was sent to mds.0: ceph_atomic_open()--> ceph_mdsc_do_request(openc) finish_open(file, dentry, ceph_open)--> ceph_open()--> ceph_init_file()--> ceph_init_file_info()--> ceph_uninline_data()--> { ... if (inline_version == 1 || /* initial version, no data */ inline_version == CEPH_INLINE_NONE) goto out_unlock; ... } The inline_version will be 1, which is the initial version for the new create file. And here the ci->i_inline_version will keep with 1, it's buggy. 3, buffer write to the file immediately: ceph_write_iter()--> ceph_get_caps(file, need=Fw, want=Fb, ...); generic_perform_write()--> a_ops->write_begin()--> ceph_write_begin()--> netfs_write_begin()--> netfs_begin_read()--> netfs_rreq_submit_slice()--> netfs_read_from_server()--> rreq->netfs_ops->issue_read()--> ceph_netfs_issue_read()--> { ... if (ci->i_inline_version != CEPH_INLINE_NONE && ceph_netfs_issue_op_inline(subreq)) return; ... } ceph_put_cap_refs(ci, Fwb); The ceph_netfs_issue_op_inline() will send a getattr(Fsr) request to mds.1. 4, then the mds.1 will request the rd lock for CInode::filelock from the auth mds.0, the mds.0 will do the CInode::filelock state transation from excl --> sync, but it need to revoke the Fxwb caps back from the clients. While the kernel client has aleady held the Fwb caps and waiting for the getattr(Fsr). It's deadlock! URL: https://tracker.ceph.com/issues/55377 Signed-off-by: Xiubo Li <xiubli@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
2022-04-25 16:08:24 +08:00
spin_lock(&ci->i_ceph_lock);
inline_version = ci->i_inline_version;
spin_unlock(&ci->i_ceph_lock);
dout("uninline_data %p %llx.%llx inline_version %llu\n",
inode, ceph_vinop(inode), inline_version);
if (inline_version == CEPH_INLINE_NONE)
return 0;
prealloc_cf = ceph_alloc_cap_flush();
if (!prealloc_cf)
return -ENOMEM;
ceph: fix possible deadlock when holding Fwb to get inline_data 1, mount with wsync. 2, create a file with O_RDWR, and the request was sent to mds.0: ceph_atomic_open()--> ceph_mdsc_do_request(openc) finish_open(file, dentry, ceph_open)--> ceph_open()--> ceph_init_file()--> ceph_init_file_info()--> ceph_uninline_data()--> { ... if (inline_version == 1 || /* initial version, no data */ inline_version == CEPH_INLINE_NONE) goto out_unlock; ... } The inline_version will be 1, which is the initial version for the new create file. And here the ci->i_inline_version will keep with 1, it's buggy. 3, buffer write to the file immediately: ceph_write_iter()--> ceph_get_caps(file, need=Fw, want=Fb, ...); generic_perform_write()--> a_ops->write_begin()--> ceph_write_begin()--> netfs_write_begin()--> netfs_begin_read()--> netfs_rreq_submit_slice()--> netfs_read_from_server()--> rreq->netfs_ops->issue_read()--> ceph_netfs_issue_read()--> { ... if (ci->i_inline_version != CEPH_INLINE_NONE && ceph_netfs_issue_op_inline(subreq)) return; ... } ceph_put_cap_refs(ci, Fwb); The ceph_netfs_issue_op_inline() will send a getattr(Fsr) request to mds.1. 4, then the mds.1 will request the rd lock for CInode::filelock from the auth mds.0, the mds.0 will do the CInode::filelock state transation from excl --> sync, but it need to revoke the Fxwb caps back from the clients. While the kernel client has aleady held the Fwb caps and waiting for the getattr(Fsr). It's deadlock! URL: https://tracker.ceph.com/issues/55377 Signed-off-by: Xiubo Li <xiubli@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
2022-04-25 16:08:24 +08:00
if (inline_version == 1) /* initial version, no data */
goto out_uninline;
folio = read_mapping_folio(inode->i_mapping, 0, file);
if (IS_ERR(folio)) {
err = PTR_ERR(folio);
goto out;
}
folio_lock(folio);
len = i_size_read(inode);
if (len > folio_size(folio))
len = folio_size(folio);
req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
ceph_vino(inode), 0, &len, 0, 1,
CEPH_OSD_OP_CREATE, CEPH_OSD_FLAG_WRITE,
NULL, 0, 0, false);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out_unlock;
}
req->r_mtime = inode->i_mtime;
err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
if (!err)
err = ceph_osdc_wait_request(&fsc->client->osdc, req);
ceph_osdc_put_request(req);
if (err < 0)
goto out_unlock;
req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
ceph_vino(inode), 0, &len, 1, 3,
CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE,
NULL, ci->i_truncate_seq,
ci->i_truncate_size, false);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out_unlock;
}
pages[0] = folio_page(folio, 0);
osd_req_op_extent_osd_data_pages(req, 1, pages, len, 0, false, false);
{
__le64 xattr_buf = cpu_to_le64(inline_version);
err = osd_req_op_xattr_init(req, 0, CEPH_OSD_OP_CMPXATTR,
"inline_version", &xattr_buf,
sizeof(xattr_buf),
CEPH_OSD_CMPXATTR_OP_GT,
CEPH_OSD_CMPXATTR_MODE_U64);
if (err)
goto out_put_req;
}
{
char xattr_buf[32];
int xattr_len = snprintf(xattr_buf, sizeof(xattr_buf),
"%llu", inline_version);
err = osd_req_op_xattr_init(req, 2, CEPH_OSD_OP_SETXATTR,
"inline_version",
xattr_buf, xattr_len, 0, 0);
if (err)
goto out_put_req;
}
req->r_mtime = inode->i_mtime;
err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
if (!err)
err = ceph_osdc_wait_request(&fsc->client->osdc, req);
ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
req->r_end_latency, len, err);
ceph: fix possible deadlock when holding Fwb to get inline_data 1, mount with wsync. 2, create a file with O_RDWR, and the request was sent to mds.0: ceph_atomic_open()--> ceph_mdsc_do_request(openc) finish_open(file, dentry, ceph_open)--> ceph_open()--> ceph_init_file()--> ceph_init_file_info()--> ceph_uninline_data()--> { ... if (inline_version == 1 || /* initial version, no data */ inline_version == CEPH_INLINE_NONE) goto out_unlock; ... } The inline_version will be 1, which is the initial version for the new create file. And here the ci->i_inline_version will keep with 1, it's buggy. 3, buffer write to the file immediately: ceph_write_iter()--> ceph_get_caps(file, need=Fw, want=Fb, ...); generic_perform_write()--> a_ops->write_begin()--> ceph_write_begin()--> netfs_write_begin()--> netfs_begin_read()--> netfs_rreq_submit_slice()--> netfs_read_from_server()--> rreq->netfs_ops->issue_read()--> ceph_netfs_issue_read()--> { ... if (ci->i_inline_version != CEPH_INLINE_NONE && ceph_netfs_issue_op_inline(subreq)) return; ... } ceph_put_cap_refs(ci, Fwb); The ceph_netfs_issue_op_inline() will send a getattr(Fsr) request to mds.1. 4, then the mds.1 will request the rd lock for CInode::filelock from the auth mds.0, the mds.0 will do the CInode::filelock state transation from excl --> sync, but it need to revoke the Fxwb caps back from the clients. While the kernel client has aleady held the Fwb caps and waiting for the getattr(Fsr). It's deadlock! URL: https://tracker.ceph.com/issues/55377 Signed-off-by: Xiubo Li <xiubli@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
2022-04-25 16:08:24 +08:00
out_uninline:
if (!err) {
int dirty;
/* Set to CAP_INLINE_NONE and dirty the caps */
down_read(&fsc->mdsc->snap_rwsem);
spin_lock(&ci->i_ceph_lock);
ci->i_inline_version = CEPH_INLINE_NONE;
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR, &prealloc_cf);
spin_unlock(&ci->i_ceph_lock);
up_read(&fsc->mdsc->snap_rwsem);
if (dirty)
__mark_inode_dirty(inode, dirty);
}
out_put_req:
ceph_osdc_put_request(req);
if (err == -ECANCELED)
err = 0;
out_unlock:
ceph: fix possible deadlock when holding Fwb to get inline_data 1, mount with wsync. 2, create a file with O_RDWR, and the request was sent to mds.0: ceph_atomic_open()--> ceph_mdsc_do_request(openc) finish_open(file, dentry, ceph_open)--> ceph_open()--> ceph_init_file()--> ceph_init_file_info()--> ceph_uninline_data()--> { ... if (inline_version == 1 || /* initial version, no data */ inline_version == CEPH_INLINE_NONE) goto out_unlock; ... } The inline_version will be 1, which is the initial version for the new create file. And here the ci->i_inline_version will keep with 1, it's buggy. 3, buffer write to the file immediately: ceph_write_iter()--> ceph_get_caps(file, need=Fw, want=Fb, ...); generic_perform_write()--> a_ops->write_begin()--> ceph_write_begin()--> netfs_write_begin()--> netfs_begin_read()--> netfs_rreq_submit_slice()--> netfs_read_from_server()--> rreq->netfs_ops->issue_read()--> ceph_netfs_issue_read()--> { ... if (ci->i_inline_version != CEPH_INLINE_NONE && ceph_netfs_issue_op_inline(subreq)) return; ... } ceph_put_cap_refs(ci, Fwb); The ceph_netfs_issue_op_inline() will send a getattr(Fsr) request to mds.1. 4, then the mds.1 will request the rd lock for CInode::filelock from the auth mds.0, the mds.0 will do the CInode::filelock state transation from excl --> sync, but it need to revoke the Fxwb caps back from the clients. While the kernel client has aleady held the Fwb caps and waiting for the getattr(Fsr). It's deadlock! URL: https://tracker.ceph.com/issues/55377 Signed-off-by: Xiubo Li <xiubli@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
2022-04-25 16:08:24 +08:00
if (folio) {
folio_unlock(folio);
folio_put(folio);
}
out:
ceph_free_cap_flush(prealloc_cf);
dout("uninline_data %p %llx.%llx inline_version %llu = %d\n",
inode, ceph_vinop(inode), inline_version, err);
return err;
}
static const struct vm_operations_struct ceph_vmops = {
.fault = ceph_filemap_fault,
.page_mkwrite = ceph_page_mkwrite,
};
int ceph_mmap(struct file *file, struct vm_area_struct *vma)
{
struct address_space *mapping = file->f_mapping;
if (!mapping->a_ops->read_folio)
return -ENOEXEC;
vma->vm_ops = &ceph_vmops;
return 0;
}
enum {
POOL_READ = 1,
POOL_WRITE = 2,
};
static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
s64 pool, struct ceph_string *pool_ns)
{
netfs: Fix gcc-12 warning by embedding vfs inode in netfs_i_context While randstruct was satisfied with using an open-coded "void *" offset cast for the netfs_i_context <-> inode casting, __builtin_object_size() as used by FORTIFY_SOURCE was not as easily fooled. This was causing the following complaint[1] from gcc v12: In file included from include/linux/string.h:253, from include/linux/ceph/ceph_debug.h:7, from fs/ceph/inode.c:2: In function 'fortify_memset_chk', inlined from 'netfs_i_context_init' at include/linux/netfs.h:326:2, inlined from 'ceph_alloc_inode' at fs/ceph/inode.c:463:2: include/linux/fortify-string.h:242:25: warning: call to '__write_overflow_field' declared with attribute warning: detected write beyond size of field (1st parameter); maybe use struct_group()? [-Wattribute-warning] 242 | __write_overflow_field(p_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Fix this by embedding a struct inode into struct netfs_i_context (which should perhaps be renamed to struct netfs_inode). The struct inode vfs_inode fields are then removed from the 9p, afs, ceph and cifs inode structs and vfs_inode is then simply changed to "netfs.inode" in those filesystems. Further, rename netfs_i_context to netfs_inode, get rid of the netfs_inode() function that converted a netfs_i_context pointer to an inode pointer (that can now be done with &ctx->inode) and rename the netfs_i_context() function to netfs_inode() (which is now a wrapper around container_of()). Most of the changes were done with: perl -p -i -e 's/vfs_inode/netfs.inode/'g \ `git grep -l 'vfs_inode' -- fs/{9p,afs,ceph,cifs}/*.[ch]` Kees suggested doing it with a pair structure[2] and a special declarator to insert that into the network filesystem's inode wrapper[3], but I think it's cleaner to embed it - and then it doesn't matter if struct randomisation reorders things. Dave Chinner suggested using a filesystem-specific VFS_I() function in each filesystem to convert that filesystem's own inode wrapper struct into the VFS inode struct[4]. Version #2: - Fix a couple of missed name changes due to a disabled cifs option. - Rename nfs_i_context to nfs_inode - Use "netfs" instead of "nic" as the member name in per-fs inode wrapper structs. [ This also undoes commit 507160f46c55 ("netfs: gcc-12: temporarily disable '-Wattribute-warning' for now") that is no longer needed ] Fixes: bc899ee1c898 ("netfs: Add a netfs inode context") Reported-by: Jeff Layton <jlayton@kernel.org> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Reviewed-by: Kees Cook <keescook@chromium.org> Reviewed-by: Xiubo Li <xiubli@redhat.com> cc: Jonathan Corbet <corbet@lwn.net> cc: Eric Van Hensbergen <ericvh@gmail.com> cc: Latchesar Ionkov <lucho@ionkov.net> cc: Dominique Martinet <asmadeus@codewreck.org> cc: Christian Schoenebeck <linux_oss@crudebyte.com> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Steve French <smfrench@gmail.com> cc: William Kucharski <william.kucharski@oracle.com> cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> cc: Dave Chinner <david@fromorbit.com> cc: linux-doc@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: samba-technical@lists.samba.org cc: linux-fsdevel@vger.kernel.org cc: linux-hardening@vger.kernel.org Link: https://lore.kernel.org/r/d2ad3a3d7bdd794c6efb562d2f2b655fb67756b9.camel@kernel.org/ [1] Link: https://lore.kernel.org/r/20220517210230.864239-1-keescook@chromium.org/ [2] Link: https://lore.kernel.org/r/20220518202212.2322058-1-keescook@chromium.org/ [3] Link: https://lore.kernel.org/r/20220524101205.GI2306852@dread.disaster.area/ [4] Link: https://lore.kernel.org/r/165296786831.3591209.12111293034669289733.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/165305805651.4094995.7763502506786714216.stgit@warthog.procyon.org.uk # v2 Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-06-10 04:46:04 +08:00
struct ceph_fs_client *fsc = ceph_inode_to_client(&ci->netfs.inode);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_osd_request *rd_req = NULL, *wr_req = NULL;
struct rb_node **p, *parent;
struct ceph_pool_perm *perm;
struct page **pages;
size_t pool_ns_len;
int err = 0, err2 = 0, have = 0;
down_read(&mdsc->pool_perm_rwsem);
p = &mdsc->pool_perm_tree.rb_node;
while (*p) {
perm = rb_entry(*p, struct ceph_pool_perm, node);
if (pool < perm->pool)
p = &(*p)->rb_left;
else if (pool > perm->pool)
p = &(*p)->rb_right;
else {
int ret = ceph_compare_string(pool_ns,
perm->pool_ns,
perm->pool_ns_len);
if (ret < 0)
p = &(*p)->rb_left;
else if (ret > 0)
p = &(*p)->rb_right;
else {
have = perm->perm;
break;
}
}
}
up_read(&mdsc->pool_perm_rwsem);
if (*p)
goto out;
if (pool_ns)
dout("__ceph_pool_perm_get pool %lld ns %.*s no perm cached\n",
pool, (int)pool_ns->len, pool_ns->str);
else
dout("__ceph_pool_perm_get pool %lld no perm cached\n", pool);
down_write(&mdsc->pool_perm_rwsem);
p = &mdsc->pool_perm_tree.rb_node;
parent = NULL;
while (*p) {
parent = *p;
perm = rb_entry(parent, struct ceph_pool_perm, node);
if (pool < perm->pool)
p = &(*p)->rb_left;
else if (pool > perm->pool)
p = &(*p)->rb_right;
else {
int ret = ceph_compare_string(pool_ns,
perm->pool_ns,
perm->pool_ns_len);
if (ret < 0)
p = &(*p)->rb_left;
else if (ret > 0)
p = &(*p)->rb_right;
else {
have = perm->perm;
break;
}
}
}
if (*p) {
up_write(&mdsc->pool_perm_rwsem);
goto out;
}
rd_req = ceph_osdc_alloc_request(&fsc->client->osdc, NULL,
1, false, GFP_NOFS);
if (!rd_req) {
err = -ENOMEM;
goto out_unlock;
}
rd_req->r_flags = CEPH_OSD_FLAG_READ;
osd_req_op_init(rd_req, 0, CEPH_OSD_OP_STAT, 0);
rd_req->r_base_oloc.pool = pool;
if (pool_ns)
rd_req->r_base_oloc.pool_ns = ceph_get_string(pool_ns);
ceph_oid_printf(&rd_req->r_base_oid, "%llx.00000000", ci->i_vino.ino);
err = ceph_osdc_alloc_messages(rd_req, GFP_NOFS);
if (err)
goto out_unlock;
wr_req = ceph_osdc_alloc_request(&fsc->client->osdc, NULL,
1, false, GFP_NOFS);
if (!wr_req) {
err = -ENOMEM;
goto out_unlock;
}
wr_req->r_flags = CEPH_OSD_FLAG_WRITE;
osd_req_op_init(wr_req, 0, CEPH_OSD_OP_CREATE, CEPH_OSD_OP_FLAG_EXCL);
ceph_oloc_copy(&wr_req->r_base_oloc, &rd_req->r_base_oloc);
ceph_oid_copy(&wr_req->r_base_oid, &rd_req->r_base_oid);
err = ceph_osdc_alloc_messages(wr_req, GFP_NOFS);
if (err)
goto out_unlock;
/* one page should be large enough for STAT data */
pages = ceph_alloc_page_vector(1, GFP_KERNEL);
if (IS_ERR(pages)) {
err = PTR_ERR(pages);
goto out_unlock;
}
osd_req_op_raw_data_in_pages(rd_req, 0, pages, PAGE_SIZE,
0, false, true);
err = ceph_osdc_start_request(&fsc->client->osdc, rd_req, false);
netfs: Fix gcc-12 warning by embedding vfs inode in netfs_i_context While randstruct was satisfied with using an open-coded "void *" offset cast for the netfs_i_context <-> inode casting, __builtin_object_size() as used by FORTIFY_SOURCE was not as easily fooled. This was causing the following complaint[1] from gcc v12: In file included from include/linux/string.h:253, from include/linux/ceph/ceph_debug.h:7, from fs/ceph/inode.c:2: In function 'fortify_memset_chk', inlined from 'netfs_i_context_init' at include/linux/netfs.h:326:2, inlined from 'ceph_alloc_inode' at fs/ceph/inode.c:463:2: include/linux/fortify-string.h:242:25: warning: call to '__write_overflow_field' declared with attribute warning: detected write beyond size of field (1st parameter); maybe use struct_group()? [-Wattribute-warning] 242 | __write_overflow_field(p_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Fix this by embedding a struct inode into struct netfs_i_context (which should perhaps be renamed to struct netfs_inode). The struct inode vfs_inode fields are then removed from the 9p, afs, ceph and cifs inode structs and vfs_inode is then simply changed to "netfs.inode" in those filesystems. Further, rename netfs_i_context to netfs_inode, get rid of the netfs_inode() function that converted a netfs_i_context pointer to an inode pointer (that can now be done with &ctx->inode) and rename the netfs_i_context() function to netfs_inode() (which is now a wrapper around container_of()). Most of the changes were done with: perl -p -i -e 's/vfs_inode/netfs.inode/'g \ `git grep -l 'vfs_inode' -- fs/{9p,afs,ceph,cifs}/*.[ch]` Kees suggested doing it with a pair structure[2] and a special declarator to insert that into the network filesystem's inode wrapper[3], but I think it's cleaner to embed it - and then it doesn't matter if struct randomisation reorders things. Dave Chinner suggested using a filesystem-specific VFS_I() function in each filesystem to convert that filesystem's own inode wrapper struct into the VFS inode struct[4]. Version #2: - Fix a couple of missed name changes due to a disabled cifs option. - Rename nfs_i_context to nfs_inode - Use "netfs" instead of "nic" as the member name in per-fs inode wrapper structs. [ This also undoes commit 507160f46c55 ("netfs: gcc-12: temporarily disable '-Wattribute-warning' for now") that is no longer needed ] Fixes: bc899ee1c898 ("netfs: Add a netfs inode context") Reported-by: Jeff Layton <jlayton@kernel.org> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Reviewed-by: Kees Cook <keescook@chromium.org> Reviewed-by: Xiubo Li <xiubli@redhat.com> cc: Jonathan Corbet <corbet@lwn.net> cc: Eric Van Hensbergen <ericvh@gmail.com> cc: Latchesar Ionkov <lucho@ionkov.net> cc: Dominique Martinet <asmadeus@codewreck.org> cc: Christian Schoenebeck <linux_oss@crudebyte.com> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Steve French <smfrench@gmail.com> cc: William Kucharski <william.kucharski@oracle.com> cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> cc: Dave Chinner <david@fromorbit.com> cc: linux-doc@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: samba-technical@lists.samba.org cc: linux-fsdevel@vger.kernel.org cc: linux-hardening@vger.kernel.org Link: https://lore.kernel.org/r/d2ad3a3d7bdd794c6efb562d2f2b655fb67756b9.camel@kernel.org/ [1] Link: https://lore.kernel.org/r/20220517210230.864239-1-keescook@chromium.org/ [2] Link: https://lore.kernel.org/r/20220518202212.2322058-1-keescook@chromium.org/ [3] Link: https://lore.kernel.org/r/20220524101205.GI2306852@dread.disaster.area/ [4] Link: https://lore.kernel.org/r/165296786831.3591209.12111293034669289733.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/165305805651.4094995.7763502506786714216.stgit@warthog.procyon.org.uk # v2 Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-06-10 04:46:04 +08:00
wr_req->r_mtime = ci->netfs.inode.i_mtime;
err2 = ceph_osdc_start_request(&fsc->client->osdc, wr_req, false);
if (!err)
err = ceph_osdc_wait_request(&fsc->client->osdc, rd_req);
if (!err2)
err2 = ceph_osdc_wait_request(&fsc->client->osdc, wr_req);
if (err >= 0 || err == -ENOENT)
have |= POOL_READ;
else if (err != -EPERM) {
if (err == -EBLOCKLISTED)
fsc->blocklisted = true;
goto out_unlock;
}
if (err2 == 0 || err2 == -EEXIST)
have |= POOL_WRITE;
else if (err2 != -EPERM) {
if (err2 == -EBLOCKLISTED)
fsc->blocklisted = true;
err = err2;
goto out_unlock;
}
pool_ns_len = pool_ns ? pool_ns->len : 0;
perm = kmalloc(sizeof(*perm) + pool_ns_len + 1, GFP_NOFS);
if (!perm) {
err = -ENOMEM;
goto out_unlock;
}
perm->pool = pool;
perm->perm = have;
perm->pool_ns_len = pool_ns_len;
if (pool_ns_len > 0)
memcpy(perm->pool_ns, pool_ns->str, pool_ns_len);
perm->pool_ns[pool_ns_len] = 0;
rb_link_node(&perm->node, parent, p);
rb_insert_color(&perm->node, &mdsc->pool_perm_tree);
err = 0;
out_unlock:
up_write(&mdsc->pool_perm_rwsem);
ceph_osdc_put_request(rd_req);
ceph_osdc_put_request(wr_req);
out:
if (!err)
err = have;
if (pool_ns)
dout("__ceph_pool_perm_get pool %lld ns %.*s result = %d\n",
pool, (int)pool_ns->len, pool_ns->str, err);
else
dout("__ceph_pool_perm_get pool %lld result = %d\n", pool, err);
return err;
}
int ceph_pool_perm_check(struct inode *inode, int need)
{
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_string *pool_ns;
s64 pool;
int ret, flags;
/* Only need to do this for regular files */
if (!S_ISREG(inode->i_mode))
return 0;
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
* been deleted. Skip check to avoid creating orphan object.
*/
return 0;
}
if (ceph_test_mount_opt(ceph_inode_to_client(inode),
NOPOOLPERM))
return 0;
spin_lock(&ci->i_ceph_lock);
flags = ci->i_ceph_flags;
pool = ci->i_layout.pool_id;
spin_unlock(&ci->i_ceph_lock);
check:
if (flags & CEPH_I_POOL_PERM) {
if ((need & CEPH_CAP_FILE_RD) && !(flags & CEPH_I_POOL_RD)) {
dout("ceph_pool_perm_check pool %lld no read perm\n",
pool);
return -EPERM;
}
if ((need & CEPH_CAP_FILE_WR) && !(flags & CEPH_I_POOL_WR)) {
dout("ceph_pool_perm_check pool %lld no write perm\n",
pool);
return -EPERM;
}
return 0;
}
pool_ns = ceph_try_get_string(ci->i_layout.pool_ns);
ret = __ceph_pool_perm_get(ci, pool, pool_ns);
ceph_put_string(pool_ns);
if (ret < 0)
return ret;
flags = CEPH_I_POOL_PERM;
if (ret & POOL_READ)
flags |= CEPH_I_POOL_RD;
if (ret & POOL_WRITE)
flags |= CEPH_I_POOL_WR;
spin_lock(&ci->i_ceph_lock);
if (pool == ci->i_layout.pool_id &&
pool_ns == rcu_dereference_raw(ci->i_layout.pool_ns)) {
ci->i_ceph_flags |= flags;
} else {
pool = ci->i_layout.pool_id;
flags = ci->i_ceph_flags;
}
spin_unlock(&ci->i_ceph_lock);
goto check;
}
void ceph_pool_perm_destroy(struct ceph_mds_client *mdsc)
{
struct ceph_pool_perm *perm;
struct rb_node *n;
while (!RB_EMPTY_ROOT(&mdsc->pool_perm_tree)) {
n = rb_first(&mdsc->pool_perm_tree);
perm = rb_entry(n, struct ceph_pool_perm, node);
rb_erase(n, &mdsc->pool_perm_tree);
kfree(perm);
}
}