* [PATCH 6.10 009/273] netfs, ceph: Revert "netfs: Remove deprecated use of PG_private_2 as a second writeback flag"
[not found] <20240827143833.371588371@linuxfoundation.org>
@ 2024-08-27 14:35 ` Greg Kroah-Hartman
2024-08-27 14:36 ` [PATCH 6.10 050/273] fs/netfs/fscache_cookie: add missing "n_accesses" check Greg Kroah-Hartman
` (2 subsequent siblings)
3 siblings, 0 replies; 7+ messages in thread
From: Greg Kroah-Hartman @ 2024-08-27 14:35 UTC (permalink / raw)
To: stable
Cc: Greg Kroah-Hartman, patches, Max Kellermann, David Howells,
Ilya Dryomov, Xiubo Li, Jeff Layton, Matthew Wilcox, ceph-devel,
netfs, linux-fsdevel, linux-mm, Christian Brauner
6.10-stable review patch. If anyone has any objections, please let me know.
------------------
From: David Howells <dhowells@redhat.com>
commit 8e5ced7804cb9184c4a23f8054551240562a8eda upstream.
This reverts commit ae678317b95e760607c7b20b97c9cd4ca9ed6e1a.
Revert the patch that removes the deprecated use of PG_private_2 in
netfslib for the moment as Ceph is actually still using this to track
data copied to the cache.
Fixes: ae678317b95e ("netfs: Remove deprecated use of PG_private_2 as a second writeback flag")
Reported-by: Max Kellermann <max.kellermann@ionos.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Ilya Dryomov <idryomov@gmail.com>
cc: Xiubo Li <xiubli@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: Matthew Wilcox <willy@infradead.org>
cc: ceph-devel@vger.kernel.org
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
https: //lore.kernel.org/r/3575457.1722355300@warthog.procyon.org.uk
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
fs/ceph/addr.c | 19 +++++
fs/netfs/buffered_read.c | 8 ++
fs/netfs/io.c | 144 +++++++++++++++++++++++++++++++++++++++++++
include/trace/events/netfs.h | 1
4 files changed, 170 insertions(+), 2 deletions(-)
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -498,6 +498,11 @@ const struct netfs_request_ops ceph_netf
};
#ifdef CONFIG_CEPH_FSCACHE
+static void ceph_set_page_fscache(struct page *page)
+{
+ folio_start_private_2(page_folio(page)); /* [DEPRECATED] */
+}
+
static void ceph_fscache_write_terminated(void *priv, ssize_t error, bool was_async)
{
struct inode *inode = priv;
@@ -515,6 +520,10 @@ static void ceph_fscache_write_to_cache(
ceph_fscache_write_terminated, inode, true, 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)
{
}
@@ -706,6 +715,8 @@ static int writepage_nounlock(struct pag
len = wlen;
set_page_writeback(page);
+ if (caching)
+ ceph_set_page_fscache(page);
ceph_fscache_write_to_cache(inode, page_off, len, caching);
if (IS_ENCRYPTED(inode)) {
@@ -789,6 +800,8 @@ static int ceph_writepage(struct page *p
return AOP_WRITEPAGE_ACTIVATE;
}
+ folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */
+
err = writepage_nounlock(page, wbc);
if (err == -ERESTARTSYS) {
/* direct memory reclaimer was killed by SIGKILL. return 0
@@ -1062,7 +1075,8 @@ get_more_pages:
unlock_page(page);
break;
}
- if (PageWriteback(page)) {
+ if (PageWriteback(page) ||
+ PagePrivate2(page) /* [DEPRECATED] */) {
if (wbc->sync_mode == WB_SYNC_NONE) {
doutc(cl, "%p under writeback\n", page);
unlock_page(page);
@@ -1070,6 +1084,7 @@ get_more_pages:
}
doutc(cl, "waiting on writeback %p\n", page);
wait_on_page_writeback(page);
+ folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */
}
if (!clear_page_dirty_for_io(page)) {
@@ -1254,6 +1269,8 @@ new_request:
}
set_page_writeback(page);
+ if (caching)
+ ceph_set_page_fscache(page);
len += thp_size(page);
}
ceph_fscache_write_to_cache(inode, offset, len, caching);
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -466,7 +466,7 @@ retry:
if (!netfs_is_cache_enabled(ctx) &&
netfs_skip_folio_read(folio, pos, len, false)) {
netfs_stat(&netfs_n_rh_write_zskip);
- goto have_folio;
+ goto have_folio_no_wait;
}
rreq = netfs_alloc_request(mapping, file,
@@ -507,6 +507,12 @@ retry:
netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
have_folio:
+ if (test_bit(NETFS_ICTX_USE_PGPRIV2, &ctx->flags)) {
+ ret = folio_wait_private_2_killable(folio);
+ if (ret < 0)
+ goto error;
+ }
+have_folio_no_wait:
*_folio = folio;
kleave(" = 0");
return 0;
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -99,6 +99,146 @@ static void netfs_rreq_completed(struct
}
/*
+ * [DEPRECATED] Deal with the completion of writing the data to the cache. We
+ * have to clear the PG_fscache bits on the folios involved and release the
+ * caller's ref.
+ *
+ * May be called in softirq mode and we inherit a ref from the caller.
+ */
+static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq,
+ bool was_async)
+{
+ struct netfs_io_subrequest *subreq;
+ struct folio *folio;
+ pgoff_t unlocked = 0;
+ bool have_unlocked = false;
+
+ rcu_read_lock();
+
+ list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
+ XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE);
+
+ xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) {
+ if (xas_retry(&xas, folio))
+ continue;
+
+ /* We might have multiple writes from the same huge
+ * folio, but we mustn't unlock a folio more than once.
+ */
+ if (have_unlocked && folio->index <= unlocked)
+ continue;
+ unlocked = folio_next_index(folio) - 1;
+ trace_netfs_folio(folio, netfs_folio_trace_end_copy);
+ folio_end_private_2(folio);
+ have_unlocked = true;
+ }
+ }
+
+ rcu_read_unlock();
+ netfs_rreq_completed(rreq, was_async);
+}
+
+static void netfs_rreq_copy_terminated(void *priv, ssize_t transferred_or_error,
+ bool was_async) /* [DEPRECATED] */
+{
+ struct netfs_io_subrequest *subreq = priv;
+ struct netfs_io_request *rreq = subreq->rreq;
+
+ if (IS_ERR_VALUE(transferred_or_error)) {
+ netfs_stat(&netfs_n_rh_write_failed);
+ trace_netfs_failure(rreq, subreq, transferred_or_error,
+ netfs_fail_copy_to_cache);
+ } else {
+ netfs_stat(&netfs_n_rh_write_done);
+ }
+
+ trace_netfs_sreq(subreq, netfs_sreq_trace_write_term);
+
+ /* If we decrement nr_copy_ops to 0, the ref belongs to us. */
+ if (atomic_dec_and_test(&rreq->nr_copy_ops))
+ netfs_rreq_unmark_after_write(rreq, was_async);
+
+ netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated);
+}
+
+/*
+ * [DEPRECATED] Perform any outstanding writes to the cache. We inherit a ref
+ * from the caller.
+ */
+static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq)
+{
+ struct netfs_cache_resources *cres = &rreq->cache_resources;
+ struct netfs_io_subrequest *subreq, *next, *p;
+ struct iov_iter iter;
+ int ret;
+
+ trace_netfs_rreq(rreq, netfs_rreq_trace_copy);
+
+ /* We don't want terminating writes trying to wake us up whilst we're
+ * still going through the list.
+ */
+ atomic_inc(&rreq->nr_copy_ops);
+
+ list_for_each_entry_safe(subreq, p, &rreq->subrequests, rreq_link) {
+ if (!test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) {
+ list_del_init(&subreq->rreq_link);
+ netfs_put_subrequest(subreq, false,
+ netfs_sreq_trace_put_no_copy);
+ }
+ }
+
+ list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
+ /* Amalgamate adjacent writes */
+ while (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) {
+ next = list_next_entry(subreq, rreq_link);
+ if (next->start != subreq->start + subreq->len)
+ break;
+ subreq->len += next->len;
+ list_del_init(&next->rreq_link);
+ netfs_put_subrequest(next, false,
+ netfs_sreq_trace_put_merged);
+ }
+
+ ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len,
+ subreq->len, rreq->i_size, true);
+ if (ret < 0) {
+ trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write);
+ trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip);
+ continue;
+ }
+
+ iov_iter_xarray(&iter, ITER_SOURCE, &rreq->mapping->i_pages,
+ subreq->start, subreq->len);
+
+ atomic_inc(&rreq->nr_copy_ops);
+ netfs_stat(&netfs_n_rh_write);
+ netfs_get_subrequest(subreq, netfs_sreq_trace_get_copy_to_cache);
+ trace_netfs_sreq(subreq, netfs_sreq_trace_write);
+ cres->ops->write(cres, subreq->start, &iter,
+ netfs_rreq_copy_terminated, subreq);
+ }
+
+ /* If we decrement nr_copy_ops to 0, the usage ref belongs to us. */
+ if (atomic_dec_and_test(&rreq->nr_copy_ops))
+ netfs_rreq_unmark_after_write(rreq, false);
+}
+
+static void netfs_rreq_write_to_cache_work(struct work_struct *work) /* [DEPRECATED] */
+{
+ struct netfs_io_request *rreq =
+ container_of(work, struct netfs_io_request, work);
+
+ netfs_rreq_do_write_to_cache(rreq);
+}
+
+static void netfs_rreq_write_to_cache(struct netfs_io_request *rreq) /* [DEPRECATED] */
+{
+ rreq->work.func = netfs_rreq_write_to_cache_work;
+ if (!queue_work(system_unbound_wq, &rreq->work))
+ BUG();
+}
+
+/*
* Handle a short read.
*/
static void netfs_rreq_short_read(struct netfs_io_request *rreq,
@@ -275,6 +415,10 @@ again:
clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS);
+ if (test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags) &&
+ test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags))
+ return netfs_rreq_write_to_cache(rreq);
+
netfs_rreq_completed(rreq, was_async);
}
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -145,6 +145,7 @@
EM(netfs_folio_trace_clear_g, "clear-g") \
EM(netfs_folio_trace_clear_s, "clear-s") \
EM(netfs_folio_trace_copy_to_cache, "mark-copy") \
+ EM(netfs_folio_trace_end_copy, "end-copy") \
EM(netfs_folio_trace_filled_gaps, "filled-gaps") \
EM(netfs_folio_trace_kill, "kill") \
EM(netfs_folio_trace_kill_cc, "kill-cc") \
^ permalink raw reply [flat|nested] 7+ messages in thread* [PATCH 6.10 083/273] 9p: Fix DIO read through netfs
[not found] <20240827143833.371588371@linuxfoundation.org>
2024-08-27 14:35 ` [PATCH 6.10 009/273] netfs, ceph: Revert "netfs: Remove deprecated use of PG_private_2 as a second writeback flag" Greg Kroah-Hartman
2024-08-27 14:36 ` [PATCH 6.10 050/273] fs/netfs/fscache_cookie: add missing "n_accesses" check Greg Kroah-Hartman
@ 2024-08-27 14:36 ` Greg Kroah-Hartman
2024-08-27 19:58 ` Dominique Martinet
2024-08-27 14:37 ` [PATCH 6.10 142/273] cifs: Add a tracepoint to track credits involved in R/W requests Greg Kroah-Hartman
3 siblings, 1 reply; 7+ messages in thread
From: Greg Kroah-Hartman @ 2024-08-27 14:36 UTC (permalink / raw)
To: stable
Cc: Greg Kroah-Hartman, patches, David Howells, Eric Van Hensbergen,
Latchesar Ionkov, Christian Schoenebeck, Marc Dionne,
Ilya Dryomov, Steve French, Paulo Alcantara, Trond Myklebust,
v9fs, linux-afs, ceph-devel, linux-cifs, linux-nfs, netfs,
linux-fsdevel, Dominique Martinet, Christian Brauner, Sasha Levin
6.10-stable review patch. If anyone has any objections, please let me know.
------------------
From: Dominique Martinet <asmadeus@codewreck.org>
[ Upstream commit e3786b29c54cdae3490b07180a54e2461f42144c ]
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>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
fs/9p/vfs_addr.c | 3 ++-
fs/afs/file.c | 3 ++-
fs/ceph/addr.c | 6 ++++--
fs/netfs/io.c | 17 +++++++++++------
fs/nfs/fscache.c | 3 ++-
fs/smb/client/file.c | 3 ++-
6 files changed, 23 insertions(+), 12 deletions(-)
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index a97ceb105cd8d..24fdc74caeba4 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -75,7 +75,8 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq)
/* if we just extended the file size, any portion not in
* cache won't be on server and is zeroes */
- __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ if (subreq->rreq->origin != NETFS_DIO_READ)
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
netfs_subreq_terminated(subreq, err ?: total, false);
}
diff --git a/fs/afs/file.c b/fs/afs/file.c
index c3f0c45ae9a9b..ec1be0091fdb5 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -242,7 +242,8 @@ static void afs_fetch_data_notify(struct afs_operation *op)
req->error = error;
if (subreq) {
- __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ if (subreq->rreq->origin != NETFS_DIO_READ)
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
netfs_subreq_terminated(subreq, error ?: req->actual_len, false);
req->subreq = NULL;
} else if (req->done) {
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 73b5a07bf94de..d2194022132ec 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -246,7 +246,8 @@ static void finish_netfs_read(struct ceph_osd_request *req)
if (err >= 0) {
if (sparse && err > 0)
err = ceph_sparse_ext_map_end(op);
- if (err < subreq->len)
+ if (err < subreq->len &&
+ subreq->rreq->origin != NETFS_DIO_READ)
__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
if (IS_ENCRYPTED(inode) && err > 0) {
err = ceph_fscrypt_decrypt_extents(inode,
@@ -282,7 +283,8 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
size_t len;
int mode;
- __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ if (rreq->origin != NETFS_DIO_READ)
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
__clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
if (subreq->start >= inode->i_size)
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index f3abc5dfdbc0c..19ec6990dc91e 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -530,7 +530,8 @@ void netfs_subreq_terminated(struct netfs_io_subrequest *subreq,
if (transferred_or_error == 0) {
if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) {
- subreq->error = -ENODATA;
+ if (rreq->origin != NETFS_DIO_READ)
+ subreq->error = -ENODATA;
goto failed;
}
} else {
@@ -601,9 +602,14 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
}
if (subreq->len > ictx->zero_point - subreq->start)
subreq->len = ictx->zero_point - subreq->start;
+
+ /* We limit buffered reads to the EOF, but let the
+ * server deal with larger-than-EOF DIO/unbuffered
+ * reads.
+ */
+ if (subreq->len > rreq->i_size - subreq->start)
+ subreq->len = rreq->i_size - subreq->start;
}
- if (subreq->len > rreq->i_size - subreq->start)
- subreq->len = rreq->i_size - subreq->start;
if (rreq->rsize && subreq->len > rreq->rsize)
subreq->len = rreq->rsize;
@@ -739,11 +745,10 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
do {
kdebug("submit %llx + %llx >= %llx",
rreq->start, rreq->submitted, rreq->i_size);
- if (rreq->origin == NETFS_DIO_READ &&
- rreq->start + rreq->submitted >= rreq->i_size)
- break;
if (!netfs_rreq_submit_slice(rreq, &io_iter))
break;
+ if (test_bit(NETFS_SREQ_NO_PROGRESS, &rreq->flags))
+ break;
if (test_bit(NETFS_RREQ_BLOCKED, &rreq->flags) &&
test_bit(NETFS_RREQ_NONBLOCK, &rreq->flags))
break;
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index ddc1ee0319554..bc20ba50283c8 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -361,7 +361,8 @@ void nfs_netfs_read_completion(struct nfs_pgio_header *hdr)
return;
sreq = netfs->sreq;
- if (test_bit(NFS_IOHDR_EOF, &hdr->flags))
+ if (test_bit(NFS_IOHDR_EOF, &hdr->flags) &&
+ sreq->rreq->origin != NETFS_DIO_READ)
__set_bit(NETFS_SREQ_CLEAR_TAIL, &sreq->flags);
if (hdr->error)
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 2e3c4d0277dbb..9e4f4e67768b9 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -196,7 +196,8 @@ static void cifs_req_issue_read(struct netfs_io_subrequest *subreq)
goto out;
}
- __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ if (subreq->rreq->origin != NETFS_DIO_READ)
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
rc = rdata->server->ops->async_readv(rdata);
out:
--
2.43.0
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH 6.10 142/273] cifs: Add a tracepoint to track credits involved in R/W requests
[not found] <20240827143833.371588371@linuxfoundation.org>
` (2 preceding siblings ...)
2024-08-27 14:36 ` [PATCH 6.10 083/273] 9p: Fix DIO read through netfs Greg Kroah-Hartman
@ 2024-08-27 14:37 ` Greg Kroah-Hartman
3 siblings, 0 replies; 7+ messages in thread
From: Greg Kroah-Hartman @ 2024-08-27 14:37 UTC (permalink / raw)
To: stable
Cc: Greg Kroah-Hartman, patches, David Howells,
Paulo Alcantara (Red Hat), Jeff Layton, linux-cifs, netfs,
linux-fsdevel, Steve French, Sasha Levin
6.10-stable review patch. If anyone has any objections, please let me know.
------------------
From: David Howells <dhowells@redhat.com>
[ Upstream commit 519be989717c5bffaed1dc14a439e3872cb4bb8d ]
Add a tracepoint to track the credit changes and server in_flight value
involved in the lifetime of a R/W request, logging it against the
request/subreq debugging ID. This requires the debugging IDs to be
recorded in the cifs_credits struct.
The tracepoint can be enabled with:
echo 1 >/sys/kernel/debug/tracing/events/cifs/smb3_rw_credits/enable
Also add a three-state flag to struct cifs_credits to note if we're
interested in determining when the in_flight contribution ends and, if so,
to track whether we've decremented the contribution yet.
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cifs@vger.kernel.org
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
Stable-dep-of: 74c2ab6d653b ("smb/client: avoid possible NULL dereference in cifs_free_subrequest()")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
fs/smb/client/cifsglob.h | 17 +++++++-----
fs/smb/client/file.c | 32 ++++++++++++++++++++++-
fs/smb/client/smb1ops.c | 2 +-
fs/smb/client/smb2ops.c | 42 ++++++++++++++++++++++++++----
fs/smb/client/smb2pdu.c | 40 +++++++++++++++++++++++++---
fs/smb/client/trace.h | 55 ++++++++++++++++++++++++++++++++++++++-
fs/smb/client/transport.c | 8 +++---
7 files changed, 173 insertions(+), 23 deletions(-)
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index d4bcc7da700c6..0a271b9fbc622 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -290,7 +290,7 @@ struct smb_version_operations {
int (*check_receive)(struct mid_q_entry *, struct TCP_Server_Info *,
bool);
void (*add_credits)(struct TCP_Server_Info *server,
- const struct cifs_credits *credits,
+ struct cifs_credits *credits,
const int optype);
void (*set_credits)(struct TCP_Server_Info *, const int);
int * (*get_credits_field)(struct TCP_Server_Info *, const int);
@@ -550,8 +550,8 @@ struct smb_version_operations {
size_t *, struct cifs_credits *);
/* adjust previously taken mtu credits to request size */
int (*adjust_credits)(struct TCP_Server_Info *server,
- struct cifs_credits *credits,
- const unsigned int payload_size);
+ struct cifs_io_subrequest *subreq,
+ unsigned int /*enum smb3_rw_credits_trace*/ trace);
/* check if we need to issue closedir */
bool (*dir_needs_close)(struct cifsFileInfo *);
long (*fallocate)(struct file *, struct cifs_tcon *, int, loff_t,
@@ -848,6 +848,9 @@ static inline void cifs_server_unlock(struct TCP_Server_Info *server)
struct cifs_credits {
unsigned int value;
unsigned int instance;
+ unsigned int in_flight_check;
+ unsigned int rreq_debug_id;
+ unsigned int rreq_debug_index;
};
static inline unsigned int
@@ -873,7 +876,7 @@ has_credits(struct TCP_Server_Info *server, int *credits, int num_credits)
}
static inline void
-add_credits(struct TCP_Server_Info *server, const struct cifs_credits *credits,
+add_credits(struct TCP_Server_Info *server, struct cifs_credits *credits,
const int optype)
{
server->ops->add_credits(server, credits, optype);
@@ -897,11 +900,11 @@ set_credits(struct TCP_Server_Info *server, const int val)
}
static inline int
-adjust_credits(struct TCP_Server_Info *server, struct cifs_credits *credits,
- const unsigned int payload_size)
+adjust_credits(struct TCP_Server_Info *server, struct cifs_io_subrequest *subreq,
+ unsigned int /* enum smb3_rw_credits_trace */ trace)
{
return server->ops->adjust_credits ?
- server->ops->adjust_credits(server, credits, payload_size) : 0;
+ server->ops->adjust_credits(server, subreq, trace) : 0;
}
static inline __le64
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 9e4f4e67768b9..b413cfef05422 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -80,6 +80,16 @@ static void cifs_prepare_write(struct netfs_io_subrequest *subreq)
return netfs_prepare_write_failed(subreq);
}
+ wdata->credits.rreq_debug_id = subreq->rreq->debug_id;
+ wdata->credits.rreq_debug_index = subreq->debug_index;
+ wdata->credits.in_flight_check = 1;
+ trace_smb3_rw_credits(wdata->rreq->debug_id,
+ wdata->subreq.debug_index,
+ wdata->credits.value,
+ server->credits, server->in_flight,
+ wdata->credits.value,
+ cifs_trace_rw_credits_write_prepare);
+
#ifdef CONFIG_CIFS_SMB_DIRECT
if (server->smbd_conn)
subreq->max_nr_segs = server->smbd_conn->max_frmr_depth;
@@ -101,7 +111,7 @@ static void cifs_issue_write(struct netfs_io_subrequest *subreq)
goto fail;
}
- rc = adjust_credits(wdata->server, &wdata->credits, wdata->subreq.len);
+ rc = adjust_credits(wdata->server, wdata, cifs_trace_rw_credits_issue_write_adjust);
if (rc)
goto fail;
@@ -163,7 +173,18 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq)
return false;
}
+ rdata->credits.in_flight_check = 1;
+ rdata->credits.rreq_debug_id = rreq->debug_id;
+ rdata->credits.rreq_debug_index = subreq->debug_index;
+
+ trace_smb3_rw_credits(rdata->rreq->debug_id,
+ rdata->subreq.debug_index,
+ rdata->credits.value,
+ server->credits, server->in_flight, 0,
+ cifs_trace_rw_credits_read_submit);
+
subreq->len = min_t(size_t, subreq->len, rsize);
+
#ifdef CONFIG_CIFS_SMB_DIRECT
if (server->smbd_conn)
subreq->max_nr_segs = server->smbd_conn->max_frmr_depth;
@@ -295,6 +316,15 @@ static void cifs_free_subrequest(struct netfs_io_subrequest *subreq)
#endif
}
+ if (rdata->credits.value != 0)
+ trace_smb3_rw_credits(rdata->rreq->debug_id,
+ rdata->subreq.debug_index,
+ rdata->credits.value,
+ rdata->server ? rdata->server->credits : 0,
+ rdata->server ? rdata->server->in_flight : 0,
+ -rdata->credits.value,
+ cifs_trace_rw_credits_free_subreq);
+
add_credits_and_wake_if(rdata->server, &rdata->credits, 0);
if (rdata->have_xid)
free_xid(rdata->xid);
diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
index 212ec6f66ec65..e1f2feb56f45f 100644
--- a/fs/smb/client/smb1ops.c
+++ b/fs/smb/client/smb1ops.c
@@ -108,7 +108,7 @@ cifs_find_mid(struct TCP_Server_Info *server, char *buffer)
static void
cifs_add_credits(struct TCP_Server_Info *server,
- const struct cifs_credits *credits, const int optype)
+ struct cifs_credits *credits, const int optype)
{
spin_lock(&server->req_lock);
server->credits += credits->value;
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index c8e536540895a..7fe59235f0901 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -66,7 +66,7 @@ change_conf(struct TCP_Server_Info *server)
static void
smb2_add_credits(struct TCP_Server_Info *server,
- const struct cifs_credits *credits, const int optype)
+ struct cifs_credits *credits, const int optype)
{
int *val, rc = -1;
int scredits, in_flight;
@@ -94,7 +94,21 @@ smb2_add_credits(struct TCP_Server_Info *server,
server->conn_id, server->hostname, *val,
add, server->in_flight);
}
- WARN_ON_ONCE(server->in_flight == 0);
+ if (credits->in_flight_check > 1) {
+ pr_warn_once("rreq R=%08x[%x] Credits not in flight\n",
+ credits->rreq_debug_id, credits->rreq_debug_index);
+ } else {
+ credits->in_flight_check = 2;
+ }
+ if (WARN_ON_ONCE(server->in_flight == 0)) {
+ pr_warn_once("rreq R=%08x[%x] Zero in_flight\n",
+ credits->rreq_debug_id, credits->rreq_debug_index);
+ trace_smb3_rw_credits(credits->rreq_debug_id,
+ credits->rreq_debug_index,
+ credits->value,
+ server->credits, server->in_flight, 0,
+ cifs_trace_rw_credits_zero_in_flight);
+ }
server->in_flight--;
if (server->in_flight == 0 &&
((optype & CIFS_OP_MASK) != CIFS_NEG_OP) &&
@@ -283,16 +297,23 @@ smb2_wait_mtu_credits(struct TCP_Server_Info *server, size_t size,
static int
smb2_adjust_credits(struct TCP_Server_Info *server,
- struct cifs_credits *credits,
- const unsigned int payload_size)
+ struct cifs_io_subrequest *subreq,
+ unsigned int /*enum smb3_rw_credits_trace*/ trace)
{
- int new_val = DIV_ROUND_UP(payload_size, SMB2_MAX_BUFFER_SIZE);
+ struct cifs_credits *credits = &subreq->credits;
+ int new_val = DIV_ROUND_UP(subreq->subreq.len, SMB2_MAX_BUFFER_SIZE);
int scredits, in_flight;
if (!credits->value || credits->value == new_val)
return 0;
if (credits->value < new_val) {
+ trace_smb3_rw_credits(subreq->rreq->debug_id,
+ subreq->subreq.debug_index,
+ credits->value,
+ server->credits, server->in_flight,
+ new_val - credits->value,
+ cifs_trace_rw_credits_no_adjust_up);
trace_smb3_too_many_credits(server->CurrentMid,
server->conn_id, server->hostname, 0, credits->value - new_val, 0);
cifs_server_dbg(VFS, "request has less credits (%d) than required (%d)",
@@ -308,6 +329,12 @@ smb2_adjust_credits(struct TCP_Server_Info *server,
in_flight = server->in_flight;
spin_unlock(&server->req_lock);
+ trace_smb3_rw_credits(subreq->rreq->debug_id,
+ subreq->subreq.debug_index,
+ credits->value,
+ server->credits, server->in_flight,
+ new_val - credits->value,
+ cifs_trace_rw_credits_old_session);
trace_smb3_reconnect_detected(server->CurrentMid,
server->conn_id, server->hostname, scredits,
credits->value - new_val, in_flight);
@@ -316,6 +343,11 @@ smb2_adjust_credits(struct TCP_Server_Info *server,
return -EAGAIN;
}
+ trace_smb3_rw_credits(subreq->rreq->debug_id,
+ subreq->subreq.debug_index,
+ credits->value,
+ server->credits, server->in_flight,
+ new_val - credits->value, trace);
server->credits += credits->value - new_val;
scredits = server->credits;
in_flight = server->in_flight;
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 896147ba6660e..4cd5c33be2a1a 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -4505,8 +4505,15 @@ smb2_readv_callback(struct mid_q_entry *mid)
struct TCP_Server_Info *server = rdata->server;
struct smb2_hdr *shdr =
(struct smb2_hdr *)rdata->iov[0].iov_base;
- struct cifs_credits credits = { .value = 0, .instance = 0 };
+ struct cifs_credits credits = {
+ .value = 0,
+ .instance = 0,
+ .rreq_debug_id = rdata->rreq->debug_id,
+ .rreq_debug_index = rdata->subreq.debug_index,
+ };
struct smb_rqst rqst = { .rq_iov = &rdata->iov[1], .rq_nvec = 1 };
+ unsigned int rreq_debug_id = rdata->rreq->debug_id;
+ unsigned int subreq_debug_index = rdata->subreq.debug_index;
if (rdata->got_bytes) {
rqst.rq_iter = rdata->subreq.io_iter;
@@ -4590,10 +4597,16 @@ smb2_readv_callback(struct mid_q_entry *mid)
if (rdata->subreq.start < rdata->subreq.rreq->i_size)
rdata->result = 0;
}
+ trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, rdata->credits.value,
+ server->credits, server->in_flight,
+ 0, cifs_trace_rw_credits_read_response_clear);
rdata->credits.value = 0;
INIT_WORK(&rdata->subreq.work, smb2_readv_worker);
queue_work(cifsiod_wq, &rdata->subreq.work);
release_mid(mid);
+ trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, 0,
+ server->credits, server->in_flight,
+ credits.value, cifs_trace_rw_credits_read_response_add);
add_credits(server, &credits, 0);
}
@@ -4650,7 +4663,7 @@ smb2_async_readv(struct cifs_io_subrequest *rdata)
min_t(int, server->max_credits -
server->credits, credit_request));
- rc = adjust_credits(server, &rdata->credits, rdata->subreq.len);
+ rc = adjust_credits(server, rdata, cifs_trace_rw_credits_call_readv_adjust);
if (rc)
goto async_readv_out;
@@ -4769,7 +4782,14 @@ smb2_writev_callback(struct mid_q_entry *mid)
struct cifs_tcon *tcon = tlink_tcon(wdata->req->cfile->tlink);
struct TCP_Server_Info *server = wdata->server;
struct smb2_write_rsp *rsp = (struct smb2_write_rsp *)mid->resp_buf;
- struct cifs_credits credits = { .value = 0, .instance = 0 };
+ struct cifs_credits credits = {
+ .value = 0,
+ .instance = 0,
+ .rreq_debug_id = wdata->rreq->debug_id,
+ .rreq_debug_index = wdata->subreq.debug_index,
+ };
+ unsigned int rreq_debug_id = wdata->rreq->debug_id;
+ unsigned int subreq_debug_index = wdata->subreq.debug_index;
ssize_t result = 0;
size_t written;
@@ -4840,9 +4860,15 @@ smb2_writev_callback(struct mid_q_entry *mid)
tcon->tid, tcon->ses->Suid,
wdata->subreq.start, wdata->subreq.len);
+ trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, wdata->credits.value,
+ server->credits, server->in_flight,
+ 0, cifs_trace_rw_credits_write_response_clear);
wdata->credits.value = 0;
cifs_write_subrequest_terminated(wdata, result ?: written, true);
release_mid(mid);
+ trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, 0,
+ server->credits, server->in_flight,
+ credits.value, cifs_trace_rw_credits_write_response_add);
add_credits(server, &credits, 0);
}
@@ -4972,7 +4998,7 @@ smb2_async_writev(struct cifs_io_subrequest *wdata)
min_t(int, server->max_credits -
server->credits, credit_request));
- rc = adjust_credits(server, &wdata->credits, io_parms->length);
+ rc = adjust_credits(server, wdata, cifs_trace_rw_credits_call_writev_adjust);
if (rc)
goto async_writev_out;
@@ -4997,6 +5023,12 @@ smb2_async_writev(struct cifs_io_subrequest *wdata)
cifs_small_buf_release(req);
out:
if (rc) {
+ trace_smb3_rw_credits(wdata->rreq->debug_id,
+ wdata->subreq.debug_index,
+ wdata->credits.value,
+ server->credits, server->in_flight,
+ -(int)wdata->credits.value,
+ cifs_trace_rw_credits_write_response_clear);
add_credits_and_wake_if(wdata->server, &wdata->credits, 0);
cifs_write_subrequest_terminated(wdata, rc, true);
}
diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
index 36d47ce596317..36d5295c2a6f9 100644
--- a/fs/smb/client/trace.h
+++ b/fs/smb/client/trace.h
@@ -20,6 +20,22 @@
/*
* Specify enums for tracing information.
*/
+#define smb3_rw_credits_traces \
+ EM(cifs_trace_rw_credits_call_readv_adjust, "rd-call-adj") \
+ EM(cifs_trace_rw_credits_call_writev_adjust, "wr-call-adj") \
+ EM(cifs_trace_rw_credits_free_subreq, "free-subreq") \
+ EM(cifs_trace_rw_credits_issue_read_adjust, "rd-issu-adj") \
+ EM(cifs_trace_rw_credits_issue_write_adjust, "wr-issu-adj") \
+ EM(cifs_trace_rw_credits_no_adjust_up, "no-adj-up ") \
+ EM(cifs_trace_rw_credits_old_session, "old-session") \
+ EM(cifs_trace_rw_credits_read_response_add, "rd-resp-add") \
+ EM(cifs_trace_rw_credits_read_response_clear, "rd-resp-clr") \
+ EM(cifs_trace_rw_credits_read_submit, "rd-submit ") \
+ EM(cifs_trace_rw_credits_write_prepare, "wr-prepare ") \
+ EM(cifs_trace_rw_credits_write_response_add, "wr-resp-add") \
+ EM(cifs_trace_rw_credits_write_response_clear, "wr-resp-clr") \
+ E_(cifs_trace_rw_credits_zero_in_flight, "ZERO-IN-FLT")
+
#define smb3_tcon_ref_traces \
EM(netfs_trace_tcon_ref_dec_dfs_refer, "DEC DfsRef") \
EM(netfs_trace_tcon_ref_free, "FRE ") \
@@ -59,7 +75,8 @@
#define EM(a, b) a,
#define E_(a, b) a
-enum smb3_tcon_ref_trace { smb3_tcon_ref_traces } __mode(byte);
+enum smb3_rw_credits_trace { smb3_rw_credits_traces } __mode(byte);
+enum smb3_tcon_ref_trace { smb3_tcon_ref_traces } __mode(byte);
#undef EM
#undef E_
@@ -71,6 +88,7 @@ enum smb3_tcon_ref_trace { smb3_tcon_ref_traces } __mode(byte);
#define EM(a, b) TRACE_DEFINE_ENUM(a);
#define E_(a, b) TRACE_DEFINE_ENUM(a);
+smb3_rw_credits_traces;
smb3_tcon_ref_traces;
#undef EM
@@ -1316,6 +1334,41 @@ TRACE_EVENT(smb3_tcon_ref,
__entry->ref)
);
+TRACE_EVENT(smb3_rw_credits,
+ TP_PROTO(unsigned int rreq_debug_id,
+ unsigned int subreq_debug_index,
+ unsigned int subreq_credits,
+ unsigned int server_credits,
+ int server_in_flight,
+ int credit_change,
+ enum smb3_rw_credits_trace trace),
+ TP_ARGS(rreq_debug_id, subreq_debug_index, subreq_credits,
+ server_credits, server_in_flight, credit_change, trace),
+ TP_STRUCT__entry(
+ __field(unsigned int, rreq_debug_id)
+ __field(unsigned int, subreq_debug_index)
+ __field(unsigned int, subreq_credits)
+ __field(unsigned int, server_credits)
+ __field(int, in_flight)
+ __field(int, credit_change)
+ __field(enum smb3_rw_credits_trace, trace)
+ ),
+ TP_fast_assign(
+ __entry->rreq_debug_id = rreq_debug_id;
+ __entry->subreq_debug_index = subreq_debug_index;
+ __entry->subreq_credits = subreq_credits;
+ __entry->server_credits = server_credits;
+ __entry->in_flight = server_in_flight;
+ __entry->credit_change = credit_change;
+ __entry->trace = trace;
+ ),
+ TP_printk("R=%08x[%x] %s cred=%u chg=%d pool=%u ifl=%d",
+ __entry->rreq_debug_id, __entry->subreq_debug_index,
+ __print_symbolic(__entry->trace, smb3_rw_credits_traces),
+ __entry->subreq_credits, __entry->credit_change,
+ __entry->server_credits, __entry->in_flight)
+ );
+
#undef EM
#undef E_
diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c
index 012b9bd069952..adfe0d0587010 100644
--- a/fs/smb/client/transport.c
+++ b/fs/smb/client/transport.c
@@ -988,10 +988,10 @@ static void
cifs_compound_callback(struct mid_q_entry *mid)
{
struct TCP_Server_Info *server = mid->server;
- struct cifs_credits credits;
-
- credits.value = server->ops->get_credits(mid);
- credits.instance = server->reconnect_instance;
+ struct cifs_credits credits = {
+ .value = server->ops->get_credits(mid),
+ .instance = server->reconnect_instance,
+ };
add_credits(server, &credits, mid->optype);
--
2.43.0
^ permalink raw reply related [flat|nested] 7+ messages in thread