linux/fs/9p/vfs_addr.c

170 lines
4.5 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* This file contians vfs address (mmap) ops for 9P2000.
*
* Copyright (C) 2005 by Eric Van Hensbergen <ericvh@gmail.com>
* Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
*/
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/pagemap.h>
#include <linux/sched.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
2021-12-22 17:21:04 +00:00
#include <linux/swap.h>
#include <linux/uio.h>
9p: Convert to using the netfs helper lib to do reads and caching Convert the 9p filesystem to use the netfs helper lib to handle readpage, readahead and write_begin, converting those into a common issue_op for the filesystem itself to handle. The netfs helper lib also handles reading from fscache if a cache is available, and interleaving reads from both sources. This change also switches from the old fscache I/O API to the new one, meaning that fscache no longer keeps track of netfs pages and instead does async DIO between the backing files and the 9p file pagecache. As a part of this change, the handling of PG_fscache changes. It now just means that the cache has a write I/O operation in progress on a page (PG_locked is used for a read I/O op). Note that this is a cut-down version of the fscache rewrite and does not change any of the cookie and cache coherency handling. Changes ======= ver #4: - Rebase on top of folios. - Don't use wait_on_page_bit_killable(). ver #3: - v9fs_req_issue_op() needs to terminate the subrequest. - v9fs_write_end() needs to call SetPageUptodate() a bit more often. - It's not CONFIG_{AFS,V9FS}_FSCACHE[1] - v9fs_init_rreq() should take a ref on the p9_fid and the cleanup should drop it [from Dominique Martinet]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-and-tested-by: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YUm+xucHxED+1MJp@codewreck.org/ [1] Link: https://lore.kernel.org/r/163162772646.438332.16323773205855053535.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/163189109885.2509237.7153668924503399173.stgit@warthog.procyon.org.uk/ # rfc v2 Link: https://lore.kernel.org/r/163363943896.1980952.1226527304649419689.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163551662876.1877519.14706391695553204156.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163584179557.4023316.11089762304657644342.stgit@warthog.procyon.org.uk # rebase on folio Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2021-11-02 08:29:55 +00:00
#include <linux/netfs.h>
#include <net/9p/9p.h>
#include <net/9p/client.h>
#include <trace/events/netfs.h>
#include "v9fs.h"
#include "v9fs_vfs.h"
#include "cache.h"
#include "fid.h"
/*
* Writeback calls this when it finds a folio that needs uploading. This isn't
* called if writeback only has copy-to-cache to deal with.
*/
static void v9fs_begin_writeback(struct netfs_io_request *wreq)
{
struct p9_fid *fid;
fid = v9fs_fid_find_inode(wreq->inode, true, INVALID_UID, true);
if (!fid) {
WARN_ONCE(1, "folio expected an open fid inode->i_ino=%lx\n",
wreq->inode->i_ino);
return;
}
wreq->wsize = fid->clnt->msize - P9_IOHDRSZ;
if (fid->iounit)
wreq->wsize = min(wreq->wsize, fid->iounit);
wreq->netfs_priv = fid;
wreq->io_streams[0].avail = true;
}
/*
* Issue a subrequest to write to the server.
*/
static void v9fs_issue_write(struct netfs_io_subrequest *subreq)
{
struct p9_fid *fid = subreq->rreq->netfs_priv;
int err, len;
len = p9_client_write(fid, subreq->start, &subreq->io_iter, &err);
netfs: Work around recursion by abandoning retry if nothing read syzkaller reported recursion with a loop of three calls (netfs_rreq_assess, netfs_retry_reads and netfs_rreq_terminated) hitting the limit of the stack during an unbuffered or direct I/O read. There are a number of issues: (1) There is no limit on the number of retries. (2) A subrequest is supposed to be abandoned if it does not transfer anything (NETFS_SREQ_NO_PROGRESS), but that isn't checked under all circumstances. (3) The actual root cause, which is this: if (atomic_dec_and_test(&rreq->nr_outstanding)) netfs_rreq_terminated(rreq, ...); When we do a retry, we bump the rreq->nr_outstanding counter to prevent the final cleanup phase running before we've finished dispatching the retries. The problem is if we hit 0, we have to do the cleanup phase - but we're in the cleanup phase and end up repeating the retry cycle, hence the recursion. Work around the problem by limiting the number of retries. This is based on Lizhi Xu's patch[1], and makes the following changes: (1) Replace NETFS_SREQ_NO_PROGRESS with NETFS_SREQ_MADE_PROGRESS and make the filesystem set it if it managed to read or write at least one byte of data. Clear this bit before issuing a subrequest. (2) Add a ->retry_count member to the subrequest and increment it any time we do a retry. (3) Remove the NETFS_SREQ_RETRYING flag as it is superfluous with ->retry_count. If the latter is non-zero, we're doing a retry. (4) Abandon a subrequest if retry_count is non-zero and we made no progress. (5) Use ->retry_count in both the write-side and the read-size. [?] Question: Should I set a hard limit on retry_count in both read and write? Say it hits 50, we always abandon it. The problem is that these changes only mitigate the issue. As long as it made at least one byte of progress, the recursion is still an issue. This patch mitigates the problem, but does not fix the underlying cause. I have patches that will do that, but it's an intrusive fix that's currently pending for the next merge window. The oops generated by KASAN looks something like: BUG: TASK stack guard page was hit at ffffc9000482ff48 (stack is ffffc90004830000..ffffc90004838000) Oops: stack guard page: 0000 [#1] PREEMPT SMP KASAN NOPTI ... RIP: 0010:mark_lock+0x25/0xc60 kernel/locking/lockdep.c:4686 ... mark_usage kernel/locking/lockdep.c:4646 [inline] __lock_acquire+0x906/0x3ce0 kernel/locking/lockdep.c:5156 lock_acquire.part.0+0x11b/0x380 kernel/locking/lockdep.c:5825 local_lock_acquire include/linux/local_lock_internal.h:29 [inline] ___slab_alloc+0x123/0x1880 mm/slub.c:3695 __slab_alloc.constprop.0+0x56/0xb0 mm/slub.c:3908 __slab_alloc_node mm/slub.c:3961 [inline] slab_alloc_node mm/slub.c:4122 [inline] kmem_cache_alloc_noprof+0x2a7/0x2f0 mm/slub.c:4141 radix_tree_node_alloc.constprop.0+0x1e8/0x350 lib/radix-tree.c:253 idr_get_free+0x528/0xa40 lib/radix-tree.c:1506 idr_alloc_u32+0x191/0x2f0 lib/idr.c:46 idr_alloc+0xc1/0x130 lib/idr.c:87 p9_tag_alloc+0x394/0x870 net/9p/client.c:321 p9_client_prepare_req+0x19f/0x4d0 net/9p/client.c:644 p9_client_zc_rpc.constprop.0+0x105/0x880 net/9p/client.c:793 p9_client_read_once+0x443/0x820 net/9p/client.c:1570 p9_client_read+0x13f/0x1b0 net/9p/client.c:1534 v9fs_issue_read+0x115/0x310 fs/9p/vfs_addr.c:74 netfs_retry_read_subrequests fs/netfs/read_retry.c:60 [inline] netfs_retry_reads+0x153a/0x1d00 fs/netfs/read_retry.c:232 netfs_rreq_assess+0x5d3/0x870 fs/netfs/read_collect.c:371 netfs_rreq_terminated+0xe5/0x110 fs/netfs/read_collect.c:407 netfs_retry_reads+0x155e/0x1d00 fs/netfs/read_retry.c:235 netfs_rreq_assess+0x5d3/0x870 fs/netfs/read_collect.c:371 netfs_rreq_terminated+0xe5/0x110 fs/netfs/read_collect.c:407 netfs_retry_reads+0x155e/0x1d00 fs/netfs/read_retry.c:235 netfs_rreq_assess+0x5d3/0x870 fs/netfs/read_collect.c:371 ... netfs_rreq_terminated+0xe5/0x110 fs/netfs/read_collect.c:407 netfs_retry_reads+0x155e/0x1d00 fs/netfs/read_retry.c:235 netfs_rreq_assess+0x5d3/0x870 fs/netfs/read_collect.c:371 netfs_rreq_terminated+0xe5/0x110 fs/netfs/read_collect.c:407 netfs_retry_reads+0x155e/0x1d00 fs/netfs/read_retry.c:235 netfs_rreq_assess+0x5d3/0x870 fs/netfs/read_collect.c:371 netfs_rreq_terminated+0xe5/0x110 fs/netfs/read_collect.c:407 netfs_dispatch_unbuffered_reads fs/netfs/direct_read.c:103 [inline] netfs_unbuffered_read fs/netfs/direct_read.c:127 [inline] netfs_unbuffered_read_iter_locked+0x12f6/0x19b0 fs/netfs/direct_read.c:221 netfs_unbuffered_read_iter+0xc5/0x100 fs/netfs/direct_read.c:256 v9fs_file_read_iter+0xbf/0x100 fs/9p/vfs_file.c:361 do_iter_readv_writev+0x614/0x7f0 fs/read_write.c:832 vfs_readv+0x4cf/0x890 fs/read_write.c:1025 do_preadv fs/read_write.c:1142 [inline] __do_sys_preadv fs/read_write.c:1192 [inline] __se_sys_preadv fs/read_write.c:1187 [inline] __x64_sys_preadv+0x22d/0x310 fs/read_write.c:1187 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83 Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading") Closes: https://syzkaller.appspot.com/bug?extid=1fc6f64c40a9d143cfb6 Signed-off-by: David Howells <dhowells@redhat.com> Link: https://lore.kernel.org/r/20241108034020.3695718-1-lizhi.xu@windriver.com/ [1] Link: https://lore.kernel.org/r/20241213135013.2964079-9-dhowells@redhat.com Tested-by: syzbot+885c03ad650731743489@syzkaller.appspotmail.com Suggested-by: Lizhi Xu <lizhi.xu@windriver.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: Jeff Layton <jlayton@kernel.org> cc: v9fs@lists.linux.dev cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Reported-by: syzbot+885c03ad650731743489@syzkaller.appspotmail.com Signed-off-by: Christian Brauner <brauner@kernel.org>
2024-12-13 13:50:08 +00:00
if (len > 0)
__set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags);
netfs: Fix the request's work item to not require a ref When the netfs_io_request struct's work item is queued, it must be supplied with a ref to the work item struct to prevent it being deallocated whilst on the queue or whilst it is being processed. This is tricky to manage as we have to get a ref before we try and queue it and then we may find it's already queued and is thus already holding a ref - in which case we have to try and get rid of the ref again. The problem comes if we're in BH or IRQ context and need to drop the ref: if netfs_put_request() reduces the count to 0, we have to do the cleanup - but the cleanup may need to wait. Fix this by adding a new work item to the request, ->cleanup_work, and dispatching that when the refcount hits zero. That can then synchronously cancel any outstanding work on the main work item before doing the cleanup. Adding a new work item also deals with another problem upstream where it's sometimes changing the work func in the put function and requeuing it - which has occasionally in the past caused the cleanup to happen incorrectly. As a bonus, this allows us to get rid of the 'was_async' parameter from a bunch of functions. This indicated whether the put function might not be permitted to sleep. Fixes: 3d3c95046742 ("netfs: Provide readahead and readpage netfs helpers") Signed-off-by: David Howells <dhowells@redhat.com> Link: https://lore.kernel.org/20250519090707.2848510-4-dhowells@redhat.com cc: Paulo Alcantara <pc@manguebit.com> cc: Marc Dionne <marc.dionne@auristor.com> cc: Steve French <stfrench@microsoft.com> cc: linux-cifs@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner <brauner@kernel.org>
2025-05-19 10:07:03 +01:00
netfs_write_subrequest_terminated(subreq, len ?: err);
}
/**
* v9fs_issue_read - Issue a read from 9P
9p: Convert to using the netfs helper lib to do reads and caching Convert the 9p filesystem to use the netfs helper lib to handle readpage, readahead and write_begin, converting those into a common issue_op for the filesystem itself to handle. The netfs helper lib also handles reading from fscache if a cache is available, and interleaving reads from both sources. This change also switches from the old fscache I/O API to the new one, meaning that fscache no longer keeps track of netfs pages and instead does async DIO between the backing files and the 9p file pagecache. As a part of this change, the handling of PG_fscache changes. It now just means that the cache has a write I/O operation in progress on a page (PG_locked is used for a read I/O op). Note that this is a cut-down version of the fscache rewrite and does not change any of the cookie and cache coherency handling. Changes ======= ver #4: - Rebase on top of folios. - Don't use wait_on_page_bit_killable(). ver #3: - v9fs_req_issue_op() needs to terminate the subrequest. - v9fs_write_end() needs to call SetPageUptodate() a bit more often. - It's not CONFIG_{AFS,V9FS}_FSCACHE[1] - v9fs_init_rreq() should take a ref on the p9_fid and the cleanup should drop it [from Dominique Martinet]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-and-tested-by: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YUm+xucHxED+1MJp@codewreck.org/ [1] Link: https://lore.kernel.org/r/163162772646.438332.16323773205855053535.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/163189109885.2509237.7153668924503399173.stgit@warthog.procyon.org.uk/ # rfc v2 Link: https://lore.kernel.org/r/163363943896.1980952.1226527304649419689.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163551662876.1877519.14706391695553204156.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163584179557.4023316.11089762304657644342.stgit@warthog.procyon.org.uk # rebase on folio Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2021-11-02 08:29:55 +00:00
* @subreq: The read to make
*/
static void v9fs_issue_read(struct netfs_io_subrequest *subreq)
{
struct netfs_io_request *rreq = subreq->rreq;
9p: Convert to using the netfs helper lib to do reads and caching Convert the 9p filesystem to use the netfs helper lib to handle readpage, readahead and write_begin, converting those into a common issue_op for the filesystem itself to handle. The netfs helper lib also handles reading from fscache if a cache is available, and interleaving reads from both sources. This change also switches from the old fscache I/O API to the new one, meaning that fscache no longer keeps track of netfs pages and instead does async DIO between the backing files and the 9p file pagecache. As a part of this change, the handling of PG_fscache changes. It now just means that the cache has a write I/O operation in progress on a page (PG_locked is used for a read I/O op). Note that this is a cut-down version of the fscache rewrite and does not change any of the cookie and cache coherency handling. Changes ======= ver #4: - Rebase on top of folios. - Don't use wait_on_page_bit_killable(). ver #3: - v9fs_req_issue_op() needs to terminate the subrequest. - v9fs_write_end() needs to call SetPageUptodate() a bit more often. - It's not CONFIG_{AFS,V9FS}_FSCACHE[1] - v9fs_init_rreq() should take a ref on the p9_fid and the cleanup should drop it [from Dominique Martinet]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-and-tested-by: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YUm+xucHxED+1MJp@codewreck.org/ [1] Link: https://lore.kernel.org/r/163162772646.438332.16323773205855053535.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/163189109885.2509237.7153668924503399173.stgit@warthog.procyon.org.uk/ # rfc v2 Link: https://lore.kernel.org/r/163363943896.1980952.1226527304649419689.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163551662876.1877519.14706391695553204156.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163584179557.4023316.11089762304657644342.stgit@warthog.procyon.org.uk # rebase on folio Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2021-11-02 08:29:55 +00:00
struct p9_fid *fid = rreq->netfs_priv;
unsigned long long pos = subreq->start + subreq->transferred;
9p: Convert to using the netfs helper lib to do reads and caching Convert the 9p filesystem to use the netfs helper lib to handle readpage, readahead and write_begin, converting those into a common issue_op for the filesystem itself to handle. The netfs helper lib also handles reading from fscache if a cache is available, and interleaving reads from both sources. This change also switches from the old fscache I/O API to the new one, meaning that fscache no longer keeps track of netfs pages and instead does async DIO between the backing files and the 9p file pagecache. As a part of this change, the handling of PG_fscache changes. It now just means that the cache has a write I/O operation in progress on a page (PG_locked is used for a read I/O op). Note that this is a cut-down version of the fscache rewrite and does not change any of the cookie and cache coherency handling. Changes ======= ver #4: - Rebase on top of folios. - Don't use wait_on_page_bit_killable(). ver #3: - v9fs_req_issue_op() needs to terminate the subrequest. - v9fs_write_end() needs to call SetPageUptodate() a bit more often. - It's not CONFIG_{AFS,V9FS}_FSCACHE[1] - v9fs_init_rreq() should take a ref on the p9_fid and the cleanup should drop it [from Dominique Martinet]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-and-tested-by: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YUm+xucHxED+1MJp@codewreck.org/ [1] Link: https://lore.kernel.org/r/163162772646.438332.16323773205855053535.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/163189109885.2509237.7153668924503399173.stgit@warthog.procyon.org.uk/ # rfc v2 Link: https://lore.kernel.org/r/163363943896.1980952.1226527304649419689.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163551662876.1877519.14706391695553204156.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163584179557.4023316.11089762304657644342.stgit@warthog.procyon.org.uk # rebase on folio Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2021-11-02 08:29:55 +00:00
int total, err;
total = p9_client_read(fid, pos, &subreq->io_iter, &err);
/* if we just extended the file size, any portion not in
* cache won't be on server and is zeroes */
if (subreq->rreq->origin != NETFS_UNBUFFERED_READ &&
subreq->rreq->origin != NETFS_DIO_READ)
9p: Fix DIO read through netfs If a program is watching a file on a 9p mount, it won't see any change in size if the file being exported by the server is changed directly in the source filesystem, presumably because 9p doesn't have change notifications, and because netfs skips the reads if the file is empty. Fix this by attempting to read the full size specified when a DIO read is requested (such as when 9p is operating in unbuffered mode) and dealing with a short read if the EOF was less than the expected read. To make this work, filesystems using netfslib must not set NETFS_SREQ_CLEAR_TAIL if performing a DIO read where that read hit the EOF. I don't want to mandatorily clear this flag in netfslib for DIO because, say, ceph might make a read from an object that is not completely filled, but does not reside at the end of file - and so we need to clear the excess. This can be tested by watching an empty file over 9p within a VM (such as in the ktest framework): while true; do read content; if [ -n "$content" ]; then echo $content; break; fi; done < /host/tmp/foo then writing something into the empty file. The watcher should immediately display the file content and break out of the loop. Without this fix, it remains in the loop indefinitely. Fixes: 80105ed2fd27 ("9p: Use netfslib read/write_iter") Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218916 Signed-off-by: David Howells <dhowells@redhat.com> Link: https://lore.kernel.org/r/1229195.1723211769@warthog.procyon.org.uk cc: Eric Van Hensbergen <ericvh@kernel.org> cc: Latchesar Ionkov <lucho@ionkov.net> cc: Christian Schoenebeck <linux_oss@crudebyte.com> cc: Marc Dionne <marc.dionne@auristor.com> cc: Ilya Dryomov <idryomov@gmail.com> cc: Steve French <sfrench@samba.org> cc: Paulo Alcantara <pc@manguebit.com> cc: Trond Myklebust <trond.myklebust@hammerspace.com> cc: v9fs@lists.linux.dev 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: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Dominique Martinet <asmadeus@codewreck.org> Signed-off-by: Christian Brauner <brauner@kernel.org>
2024-08-08 14:29:38 +01:00
__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
if (pos + total >= i_size_read(rreq->inode))
__set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags);
netfs: Change the read result collector to only use one work item Change the way netfslib collects read results to do all the collection for a particular read request using a single work item that walks along the subrequest queue as subrequests make progress or complete, unlocking folios progressively rather than doing the unlock in parallel as parallel requests come in. The code is remodelled to be more like the write-side code, though only using a single stream. This makes it more directly comparable and thus easier to duplicate fixes between the two sides. This has a number of advantages: (1) It's simpler. There doesn't need to be a complex donation mechanism to handle mismatches between the size and alignment of subrequests and folios. The collector unlocks folios as the subrequests covering each complete. (2) It should cause less scheduler overhead as there's a single work item in play unlocking pages in parallel when a read gets split up into a lot of subrequests instead of one per subrequest. Whilst the parallellism is nice in theory, in practice, the vast majority of loads are sequential reads of the whole file, so committing a bunch of threads to unlocking folios out of order doesn't help in those cases. (3) It should make it easier to implement content decryption. A folio cannot be decrypted until all the requests that contribute to it have completed - and, again, most loads are sequential and so, most of the time, we want to begin decryption sequentially (though it's great if the decryption can happen in parallel). There is a disadvantage in that we're losing the ability to decrypt and unlock things on an as-things-arrive basis which may affect some applications. Signed-off-by: David Howells <dhowells@redhat.com> Link: https://lore.kernel.org/r/20241216204124.3752367-28-dhowells@redhat.com cc: Jeff Layton <jlayton@kernel.org> cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner <brauner@kernel.org>
2024-12-16 20:41:17 +00:00
if (!err && total) {
subreq->transferred += total;
netfs: Work around recursion by abandoning retry if nothing read syzkaller reported recursion with a loop of three calls (netfs_rreq_assess, netfs_retry_reads and netfs_rreq_terminated) hitting the limit of the stack during an unbuffered or direct I/O read. There are a number of issues: (1) There is no limit on the number of retries. (2) A subrequest is supposed to be abandoned if it does not transfer anything (NETFS_SREQ_NO_PROGRESS), but that isn't checked under all circumstances. (3) The actual root cause, which is this: if (atomic_dec_and_test(&rreq->nr_outstanding)) netfs_rreq_terminated(rreq, ...); When we do a retry, we bump the rreq->nr_outstanding counter to prevent the final cleanup phase running before we've finished dispatching the retries. The problem is if we hit 0, we have to do the cleanup phase - but we're in the cleanup phase and end up repeating the retry cycle, hence the recursion. Work around the problem by limiting the number of retries. This is based on Lizhi Xu's patch[1], and makes the following changes: (1) Replace NETFS_SREQ_NO_PROGRESS with NETFS_SREQ_MADE_PROGRESS and make the filesystem set it if it managed to read or write at least one byte of data. Clear this bit before issuing a subrequest. (2) Add a ->retry_count member to the subrequest and increment it any time we do a retry. (3) Remove the NETFS_SREQ_RETRYING flag as it is superfluous with ->retry_count. If the latter is non-zero, we're doing a retry. (4) Abandon a subrequest if retry_count is non-zero and we made no progress. (5) Use ->retry_count in both the write-side and the read-size. [?] Question: Should I set a hard limit on retry_count in both read and write? Say it hits 50, we always abandon it. The problem is that these changes only mitigate the issue. As long as it made at least one byte of progress, the recursion is still an issue. This patch mitigates the problem, but does not fix the underlying cause. I have patches that will do that, but it's an intrusive fix that's currently pending for the next merge window. The oops generated by KASAN looks something like: BUG: TASK stack guard page was hit at ffffc9000482ff48 (stack is ffffc90004830000..ffffc90004838000) Oops: stack guard page: 0000 [#1] PREEMPT SMP KASAN NOPTI ... RIP: 0010:mark_lock+0x25/0xc60 kernel/locking/lockdep.c:4686 ... mark_usage kernel/locking/lockdep.c:4646 [inline] __lock_acquire+0x906/0x3ce0 kernel/locking/lockdep.c:5156 lock_acquire.part.0+0x11b/0x380 kernel/locking/lockdep.c:5825 local_lock_acquire include/linux/local_lock_internal.h:29 [inline] ___slab_alloc+0x123/0x1880 mm/slub.c:3695 __slab_alloc.constprop.0+0x56/0xb0 mm/slub.c:3908 __slab_alloc_node mm/slub.c:3961 [inline] slab_alloc_node mm/slub.c:4122 [inline] kmem_cache_alloc_noprof+0x2a7/0x2f0 mm/slub.c:4141 radix_tree_node_alloc.constprop.0+0x1e8/0x350 lib/radix-tree.c:253 idr_get_free+0x528/0xa40 lib/radix-tree.c:1506 idr_alloc_u32+0x191/0x2f0 lib/idr.c:46 idr_alloc+0xc1/0x130 lib/idr.c:87 p9_tag_alloc+0x394/0x870 net/9p/client.c:321 p9_client_prepare_req+0x19f/0x4d0 net/9p/client.c:644 p9_client_zc_rpc.constprop.0+0x105/0x880 net/9p/client.c:793 p9_client_read_once+0x443/0x820 net/9p/client.c:1570 p9_client_read+0x13f/0x1b0 net/9p/client.c:1534 v9fs_issue_read+0x115/0x310 fs/9p/vfs_addr.c:74 netfs_retry_read_subrequests fs/netfs/read_retry.c:60 [inline] netfs_retry_reads+0x153a/0x1d00 fs/netfs/read_retry.c:232 netfs_rreq_assess+0x5d3/0x870 fs/netfs/read_collect.c:371 netfs_rreq_terminated+0xe5/0x110 fs/netfs/read_collect.c:407 netfs_retry_reads+0x155e/0x1d00 fs/netfs/read_retry.c:235 netfs_rreq_assess+0x5d3/0x870 fs/netfs/read_collect.c:371 netfs_rreq_terminated+0xe5/0x110 fs/netfs/read_collect.c:407 netfs_retry_reads+0x155e/0x1d00 fs/netfs/read_retry.c:235 netfs_rreq_assess+0x5d3/0x870 fs/netfs/read_collect.c:371 ... netfs_rreq_terminated+0xe5/0x110 fs/netfs/read_collect.c:407 netfs_retry_reads+0x155e/0x1d00 fs/netfs/read_retry.c:235 netfs_rreq_assess+0x5d3/0x870 fs/netfs/read_collect.c:371 netfs_rreq_terminated+0xe5/0x110 fs/netfs/read_collect.c:407 netfs_retry_reads+0x155e/0x1d00 fs/netfs/read_retry.c:235 netfs_rreq_assess+0x5d3/0x870 fs/netfs/read_collect.c:371 netfs_rreq_terminated+0xe5/0x110 fs/netfs/read_collect.c:407 netfs_dispatch_unbuffered_reads fs/netfs/direct_read.c:103 [inline] netfs_unbuffered_read fs/netfs/direct_read.c:127 [inline] netfs_unbuffered_read_iter_locked+0x12f6/0x19b0 fs/netfs/direct_read.c:221 netfs_unbuffered_read_iter+0xc5/0x100 fs/netfs/direct_read.c:256 v9fs_file_read_iter+0xbf/0x100 fs/9p/vfs_file.c:361 do_iter_readv_writev+0x614/0x7f0 fs/read_write.c:832 vfs_readv+0x4cf/0x890 fs/read_write.c:1025 do_preadv fs/read_write.c:1142 [inline] __do_sys_preadv fs/read_write.c:1192 [inline] __se_sys_preadv fs/read_write.c:1187 [inline] __x64_sys_preadv+0x22d/0x310 fs/read_write.c:1187 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83 Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading") Closes: https://syzkaller.appspot.com/bug?extid=1fc6f64c40a9d143cfb6 Signed-off-by: David Howells <dhowells@redhat.com> Link: https://lore.kernel.org/r/20241108034020.3695718-1-lizhi.xu@windriver.com/ [1] Link: https://lore.kernel.org/r/20241213135013.2964079-9-dhowells@redhat.com Tested-by: syzbot+885c03ad650731743489@syzkaller.appspotmail.com Suggested-by: Lizhi Xu <lizhi.xu@windriver.com> cc: Dominique Martinet <asmadeus@codewreck.org> cc: Jeff Layton <jlayton@kernel.org> cc: v9fs@lists.linux.dev cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Reported-by: syzbot+885c03ad650731743489@syzkaller.appspotmail.com Signed-off-by: Christian Brauner <brauner@kernel.org>
2024-12-13 13:50:08 +00:00
__set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags);
}
subreq->error = err;
netfs_read_subreq_terminated(subreq);
9p: Convert to using the netfs helper lib to do reads and caching Convert the 9p filesystem to use the netfs helper lib to handle readpage, readahead and write_begin, converting those into a common issue_op for the filesystem itself to handle. The netfs helper lib also handles reading from fscache if a cache is available, and interleaving reads from both sources. This change also switches from the old fscache I/O API to the new one, meaning that fscache no longer keeps track of netfs pages and instead does async DIO between the backing files and the 9p file pagecache. As a part of this change, the handling of PG_fscache changes. It now just means that the cache has a write I/O operation in progress on a page (PG_locked is used for a read I/O op). Note that this is a cut-down version of the fscache rewrite and does not change any of the cookie and cache coherency handling. Changes ======= ver #4: - Rebase on top of folios. - Don't use wait_on_page_bit_killable(). ver #3: - v9fs_req_issue_op() needs to terminate the subrequest. - v9fs_write_end() needs to call SetPageUptodate() a bit more often. - It's not CONFIG_{AFS,V9FS}_FSCACHE[1] - v9fs_init_rreq() should take a ref on the p9_fid and the cleanup should drop it [from Dominique Martinet]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-and-tested-by: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YUm+xucHxED+1MJp@codewreck.org/ [1] Link: https://lore.kernel.org/r/163162772646.438332.16323773205855053535.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/163189109885.2509237.7153668924503399173.stgit@warthog.procyon.org.uk/ # rfc v2 Link: https://lore.kernel.org/r/163363943896.1980952.1226527304649419689.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163551662876.1877519.14706391695553204156.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163584179557.4023316.11089762304657644342.stgit@warthog.procyon.org.uk # rebase on folio Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2021-11-02 08:29:55 +00:00
}
9p: Convert to using the netfs helper lib to do reads and caching Convert the 9p filesystem to use the netfs helper lib to handle readpage, readahead and write_begin, converting those into a common issue_op for the filesystem itself to handle. The netfs helper lib also handles reading from fscache if a cache is available, and interleaving reads from both sources. This change also switches from the old fscache I/O API to the new one, meaning that fscache no longer keeps track of netfs pages and instead does async DIO between the backing files and the 9p file pagecache. As a part of this change, the handling of PG_fscache changes. It now just means that the cache has a write I/O operation in progress on a page (PG_locked is used for a read I/O op). Note that this is a cut-down version of the fscache rewrite and does not change any of the cookie and cache coherency handling. Changes ======= ver #4: - Rebase on top of folios. - Don't use wait_on_page_bit_killable(). ver #3: - v9fs_req_issue_op() needs to terminate the subrequest. - v9fs_write_end() needs to call SetPageUptodate() a bit more often. - It's not CONFIG_{AFS,V9FS}_FSCACHE[1] - v9fs_init_rreq() should take a ref on the p9_fid and the cleanup should drop it [from Dominique Martinet]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-and-tested-by: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YUm+xucHxED+1MJp@codewreck.org/ [1] Link: https://lore.kernel.org/r/163162772646.438332.16323773205855053535.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/163189109885.2509237.7153668924503399173.stgit@warthog.procyon.org.uk/ # rfc v2 Link: https://lore.kernel.org/r/163363943896.1980952.1226527304649419689.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163551662876.1877519.14706391695553204156.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163584179557.4023316.11089762304657644342.stgit@warthog.procyon.org.uk # rebase on folio Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2021-11-02 08:29:55 +00:00
/**
* v9fs_init_request - Initialise a request
9p: Convert to using the netfs helper lib to do reads and caching Convert the 9p filesystem to use the netfs helper lib to handle readpage, readahead and write_begin, converting those into a common issue_op for the filesystem itself to handle. The netfs helper lib also handles reading from fscache if a cache is available, and interleaving reads from both sources. This change also switches from the old fscache I/O API to the new one, meaning that fscache no longer keeps track of netfs pages and instead does async DIO between the backing files and the 9p file pagecache. As a part of this change, the handling of PG_fscache changes. It now just means that the cache has a write I/O operation in progress on a page (PG_locked is used for a read I/O op). Note that this is a cut-down version of the fscache rewrite and does not change any of the cookie and cache coherency handling. Changes ======= ver #4: - Rebase on top of folios. - Don't use wait_on_page_bit_killable(). ver #3: - v9fs_req_issue_op() needs to terminate the subrequest. - v9fs_write_end() needs to call SetPageUptodate() a bit more often. - It's not CONFIG_{AFS,V9FS}_FSCACHE[1] - v9fs_init_rreq() should take a ref on the p9_fid and the cleanup should drop it [from Dominique Martinet]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-and-tested-by: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YUm+xucHxED+1MJp@codewreck.org/ [1] Link: https://lore.kernel.org/r/163162772646.438332.16323773205855053535.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/163189109885.2509237.7153668924503399173.stgit@warthog.procyon.org.uk/ # rfc v2 Link: https://lore.kernel.org/r/163363943896.1980952.1226527304649419689.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163551662876.1877519.14706391695553204156.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163584179557.4023316.11089762304657644342.stgit@warthog.procyon.org.uk # rebase on folio Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2021-11-02 08:29:55 +00:00
* @rreq: The read request
* @file: The file being read from
*/
static int v9fs_init_request(struct netfs_io_request *rreq, struct file *file)
9p: Convert to using the netfs helper lib to do reads and caching Convert the 9p filesystem to use the netfs helper lib to handle readpage, readahead and write_begin, converting those into a common issue_op for the filesystem itself to handle. The netfs helper lib also handles reading from fscache if a cache is available, and interleaving reads from both sources. This change also switches from the old fscache I/O API to the new one, meaning that fscache no longer keeps track of netfs pages and instead does async DIO between the backing files and the 9p file pagecache. As a part of this change, the handling of PG_fscache changes. It now just means that the cache has a write I/O operation in progress on a page (PG_locked is used for a read I/O op). Note that this is a cut-down version of the fscache rewrite and does not change any of the cookie and cache coherency handling. Changes ======= ver #4: - Rebase on top of folios. - Don't use wait_on_page_bit_killable(). ver #3: - v9fs_req_issue_op() needs to terminate the subrequest. - v9fs_write_end() needs to call SetPageUptodate() a bit more often. - It's not CONFIG_{AFS,V9FS}_FSCACHE[1] - v9fs_init_rreq() should take a ref on the p9_fid and the cleanup should drop it [from Dominique Martinet]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-and-tested-by: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YUm+xucHxED+1MJp@codewreck.org/ [1] Link: https://lore.kernel.org/r/163162772646.438332.16323773205855053535.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/163189109885.2509237.7153668924503399173.stgit@warthog.procyon.org.uk/ # rfc v2 Link: https://lore.kernel.org/r/163363943896.1980952.1226527304649419689.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163551662876.1877519.14706391695553204156.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163584179557.4023316.11089762304657644342.stgit@warthog.procyon.org.uk # rebase on folio Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2021-11-02 08:29:55 +00:00
{
struct p9_fid *fid;
bool writing = (rreq->origin == NETFS_READ_FOR_WRITE ||
rreq->origin == NETFS_WRITETHROUGH ||
rreq->origin == NETFS_UNBUFFERED_WRITE ||
rreq->origin == NETFS_DIO_WRITE);
if (rreq->origin == NETFS_WRITEBACK)
return 0; /* We don't get the write handle until we find we
* have actually dirty data and not just
* copy-to-cache data.
*/
if (file) {
fid = file->private_data;
if (!fid)
goto no_fid;
p9_fid_get(fid);
} else {
fid = v9fs_fid_find_inode(rreq->inode, writing, INVALID_UID, true);
if (!fid)
goto no_fid;
}
rreq->wsize = fid->clnt->msize - P9_IOHDRSZ;
if (fid->iounit)
rreq->wsize = min(rreq->wsize, fid->iounit);
/* we might need to read from a fid that was opened write-only
* for read-modify-write of page cache, use the writeback fid
* for that */
WARN_ON(rreq->origin == NETFS_READ_FOR_WRITE && !(fid->mode & P9_ORDWR));
9p: Convert to using the netfs helper lib to do reads and caching Convert the 9p filesystem to use the netfs helper lib to handle readpage, readahead and write_begin, converting those into a common issue_op for the filesystem itself to handle. The netfs helper lib also handles reading from fscache if a cache is available, and interleaving reads from both sources. This change also switches from the old fscache I/O API to the new one, meaning that fscache no longer keeps track of netfs pages and instead does async DIO between the backing files and the 9p file pagecache. As a part of this change, the handling of PG_fscache changes. It now just means that the cache has a write I/O operation in progress on a page (PG_locked is used for a read I/O op). Note that this is a cut-down version of the fscache rewrite and does not change any of the cookie and cache coherency handling. Changes ======= ver #4: - Rebase on top of folios. - Don't use wait_on_page_bit_killable(). ver #3: - v9fs_req_issue_op() needs to terminate the subrequest. - v9fs_write_end() needs to call SetPageUptodate() a bit more often. - It's not CONFIG_{AFS,V9FS}_FSCACHE[1] - v9fs_init_rreq() should take a ref on the p9_fid and the cleanup should drop it [from Dominique Martinet]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-and-tested-by: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YUm+xucHxED+1MJp@codewreck.org/ [1] Link: https://lore.kernel.org/r/163162772646.438332.16323773205855053535.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/163189109885.2509237.7153668924503399173.stgit@warthog.procyon.org.uk/ # rfc v2 Link: https://lore.kernel.org/r/163363943896.1980952.1226527304649419689.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163551662876.1877519.14706391695553204156.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163584179557.4023316.11089762304657644342.stgit@warthog.procyon.org.uk # rebase on folio Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2021-11-02 08:29:55 +00:00
rreq->netfs_priv = fid;
return 0;
no_fid:
WARN_ONCE(1, "folio expected an open fid inode->i_ino=%lx\n",
rreq->inode->i_ino);
return -EINVAL;
9p: Convert to using the netfs helper lib to do reads and caching Convert the 9p filesystem to use the netfs helper lib to handle readpage, readahead and write_begin, converting those into a common issue_op for the filesystem itself to handle. The netfs helper lib also handles reading from fscache if a cache is available, and interleaving reads from both sources. This change also switches from the old fscache I/O API to the new one, meaning that fscache no longer keeps track of netfs pages and instead does async DIO between the backing files and the 9p file pagecache. As a part of this change, the handling of PG_fscache changes. It now just means that the cache has a write I/O operation in progress on a page (PG_locked is used for a read I/O op). Note that this is a cut-down version of the fscache rewrite and does not change any of the cookie and cache coherency handling. Changes ======= ver #4: - Rebase on top of folios. - Don't use wait_on_page_bit_killable(). ver #3: - v9fs_req_issue_op() needs to terminate the subrequest. - v9fs_write_end() needs to call SetPageUptodate() a bit more often. - It's not CONFIG_{AFS,V9FS}_FSCACHE[1] - v9fs_init_rreq() should take a ref on the p9_fid and the cleanup should drop it [from Dominique Martinet]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-and-tested-by: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YUm+xucHxED+1MJp@codewreck.org/ [1] Link: https://lore.kernel.org/r/163162772646.438332.16323773205855053535.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/163189109885.2509237.7153668924503399173.stgit@warthog.procyon.org.uk/ # rfc v2 Link: https://lore.kernel.org/r/163363943896.1980952.1226527304649419689.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163551662876.1877519.14706391695553204156.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163584179557.4023316.11089762304657644342.stgit@warthog.procyon.org.uk # rebase on folio Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2021-11-02 08:29:55 +00:00
}
9p: Convert to using the netfs helper lib to do reads and caching Convert the 9p filesystem to use the netfs helper lib to handle readpage, readahead and write_begin, converting those into a common issue_op for the filesystem itself to handle. The netfs helper lib also handles reading from fscache if a cache is available, and interleaving reads from both sources. This change also switches from the old fscache I/O API to the new one, meaning that fscache no longer keeps track of netfs pages and instead does async DIO between the backing files and the 9p file pagecache. As a part of this change, the handling of PG_fscache changes. It now just means that the cache has a write I/O operation in progress on a page (PG_locked is used for a read I/O op). Note that this is a cut-down version of the fscache rewrite and does not change any of the cookie and cache coherency handling. Changes ======= ver #4: - Rebase on top of folios. - Don't use wait_on_page_bit_killable(). ver #3: - v9fs_req_issue_op() needs to terminate the subrequest. - v9fs_write_end() needs to call SetPageUptodate() a bit more often. - It's not CONFIG_{AFS,V9FS}_FSCACHE[1] - v9fs_init_rreq() should take a ref on the p9_fid and the cleanup should drop it [from Dominique Martinet]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-and-tested-by: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YUm+xucHxED+1MJp@codewreck.org/ [1] Link: https://lore.kernel.org/r/163162772646.438332.16323773205855053535.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/163189109885.2509237.7153668924503399173.stgit@warthog.procyon.org.uk/ # rfc v2 Link: https://lore.kernel.org/r/163363943896.1980952.1226527304649419689.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163551662876.1877519.14706391695553204156.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163584179557.4023316.11089762304657644342.stgit@warthog.procyon.org.uk # rebase on folio Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2021-11-02 08:29:55 +00:00
/**
* v9fs_free_request - Cleanup request initialized by v9fs_init_rreq
* @rreq: The I/O request to clean up
9p: Convert to using the netfs helper lib to do reads and caching Convert the 9p filesystem to use the netfs helper lib to handle readpage, readahead and write_begin, converting those into a common issue_op for the filesystem itself to handle. The netfs helper lib also handles reading from fscache if a cache is available, and interleaving reads from both sources. This change also switches from the old fscache I/O API to the new one, meaning that fscache no longer keeps track of netfs pages and instead does async DIO between the backing files and the 9p file pagecache. As a part of this change, the handling of PG_fscache changes. It now just means that the cache has a write I/O operation in progress on a page (PG_locked is used for a read I/O op). Note that this is a cut-down version of the fscache rewrite and does not change any of the cookie and cache coherency handling. Changes ======= ver #4: - Rebase on top of folios. - Don't use wait_on_page_bit_killable(). ver #3: - v9fs_req_issue_op() needs to terminate the subrequest. - v9fs_write_end() needs to call SetPageUptodate() a bit more often. - It's not CONFIG_{AFS,V9FS}_FSCACHE[1] - v9fs_init_rreq() should take a ref on the p9_fid and the cleanup should drop it [from Dominique Martinet]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-and-tested-by: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YUm+xucHxED+1MJp@codewreck.org/ [1] Link: https://lore.kernel.org/r/163162772646.438332.16323773205855053535.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/163189109885.2509237.7153668924503399173.stgit@warthog.procyon.org.uk/ # rfc v2 Link: https://lore.kernel.org/r/163363943896.1980952.1226527304649419689.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163551662876.1877519.14706391695553204156.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163584179557.4023316.11089762304657644342.stgit@warthog.procyon.org.uk # rebase on folio Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2021-11-02 08:29:55 +00:00
*/
static void v9fs_free_request(struct netfs_io_request *rreq)
9p: Convert to using the netfs helper lib to do reads and caching Convert the 9p filesystem to use the netfs helper lib to handle readpage, readahead and write_begin, converting those into a common issue_op for the filesystem itself to handle. The netfs helper lib also handles reading from fscache if a cache is available, and interleaving reads from both sources. This change also switches from the old fscache I/O API to the new one, meaning that fscache no longer keeps track of netfs pages and instead does async DIO between the backing files and the 9p file pagecache. As a part of this change, the handling of PG_fscache changes. It now just means that the cache has a write I/O operation in progress on a page (PG_locked is used for a read I/O op). Note that this is a cut-down version of the fscache rewrite and does not change any of the cookie and cache coherency handling. Changes ======= ver #4: - Rebase on top of folios. - Don't use wait_on_page_bit_killable(). ver #3: - v9fs_req_issue_op() needs to terminate the subrequest. - v9fs_write_end() needs to call SetPageUptodate() a bit more often. - It's not CONFIG_{AFS,V9FS}_FSCACHE[1] - v9fs_init_rreq() should take a ref on the p9_fid and the cleanup should drop it [from Dominique Martinet]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-and-tested-by: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YUm+xucHxED+1MJp@codewreck.org/ [1] Link: https://lore.kernel.org/r/163162772646.438332.16323773205855053535.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/163189109885.2509237.7153668924503399173.stgit@warthog.procyon.org.uk/ # rfc v2 Link: https://lore.kernel.org/r/163363943896.1980952.1226527304649419689.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163551662876.1877519.14706391695553204156.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163584179557.4023316.11089762304657644342.stgit@warthog.procyon.org.uk # rebase on folio Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2021-11-02 08:29:55 +00:00
{
struct p9_fid *fid = rreq->netfs_priv;
p9_fid_put(fid);
9p: Convert to using the netfs helper lib to do reads and caching Convert the 9p filesystem to use the netfs helper lib to handle readpage, readahead and write_begin, converting those into a common issue_op for the filesystem itself to handle. The netfs helper lib also handles reading from fscache if a cache is available, and interleaving reads from both sources. This change also switches from the old fscache I/O API to the new one, meaning that fscache no longer keeps track of netfs pages and instead does async DIO between the backing files and the 9p file pagecache. As a part of this change, the handling of PG_fscache changes. It now just means that the cache has a write I/O operation in progress on a page (PG_locked is used for a read I/O op). Note that this is a cut-down version of the fscache rewrite and does not change any of the cookie and cache coherency handling. Changes ======= ver #4: - Rebase on top of folios. - Don't use wait_on_page_bit_killable(). ver #3: - v9fs_req_issue_op() needs to terminate the subrequest. - v9fs_write_end() needs to call SetPageUptodate() a bit more often. - It's not CONFIG_{AFS,V9FS}_FSCACHE[1] - v9fs_init_rreq() should take a ref on the p9_fid and the cleanup should drop it [from Dominique Martinet]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-and-tested-by: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YUm+xucHxED+1MJp@codewreck.org/ [1] Link: https://lore.kernel.org/r/163162772646.438332.16323773205855053535.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/163189109885.2509237.7153668924503399173.stgit@warthog.procyon.org.uk/ # rfc v2 Link: https://lore.kernel.org/r/163363943896.1980952.1226527304649419689.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163551662876.1877519.14706391695553204156.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163584179557.4023316.11089762304657644342.stgit@warthog.procyon.org.uk # rebase on folio Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2021-11-02 08:29:55 +00:00
}
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
2021-06-29 22:37:05 +01:00
const struct netfs_request_ops v9fs_req_ops = {
.init_request = v9fs_init_request,
.free_request = v9fs_free_request,
.issue_read = v9fs_issue_read,
.begin_writeback = v9fs_begin_writeback,
.issue_write = v9fs_issue_write,
9p: Convert to using the netfs helper lib to do reads and caching Convert the 9p filesystem to use the netfs helper lib to handle readpage, readahead and write_begin, converting those into a common issue_op for the filesystem itself to handle. The netfs helper lib also handles reading from fscache if a cache is available, and interleaving reads from both sources. This change also switches from the old fscache I/O API to the new one, meaning that fscache no longer keeps track of netfs pages and instead does async DIO between the backing files and the 9p file pagecache. As a part of this change, the handling of PG_fscache changes. It now just means that the cache has a write I/O operation in progress on a page (PG_locked is used for a read I/O op). Note that this is a cut-down version of the fscache rewrite and does not change any of the cookie and cache coherency handling. Changes ======= ver #4: - Rebase on top of folios. - Don't use wait_on_page_bit_killable(). ver #3: - v9fs_req_issue_op() needs to terminate the subrequest. - v9fs_write_end() needs to call SetPageUptodate() a bit more often. - It's not CONFIG_{AFS,V9FS}_FSCACHE[1] - v9fs_init_rreq() should take a ref on the p9_fid and the cleanup should drop it [from Dominique Martinet]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-and-tested-by: Dominique Martinet <asmadeus@codewreck.org> cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YUm+xucHxED+1MJp@codewreck.org/ [1] Link: https://lore.kernel.org/r/163162772646.438332.16323773205855053535.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/163189109885.2509237.7153668924503399173.stgit@warthog.procyon.org.uk/ # rfc v2 Link: https://lore.kernel.org/r/163363943896.1980952.1226527304649419689.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163551662876.1877519.14706391695553204156.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163584179557.4023316.11089762304657644342.stgit@warthog.procyon.org.uk # rebase on folio Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2021-11-02 08:29:55 +00:00
};
const struct address_space_operations v9fs_addr_operations = {
.read_folio = netfs_read_folio,
.readahead = netfs_readahead,
.dirty_folio = netfs_dirty_folio,
.release_folio = netfs_release_folio,
.invalidate_folio = netfs_invalidate_folio,
.direct_IO = noop_direct_IO,
.writepages = netfs_writepages,
.migrate_folio = filemap_migrate_folio,
};