From: David Howells <dhowells@redhat.com>
To: Jeff Layton <jlayton@kernel.org>, Steve French <smfrench@gmail.com>
Cc: David Howells <dhowells@redhat.com>,
Matthew Wilcox <willy@infradead.org>,
Marc Dionne <marc.dionne@auristor.com>,
Paulo Alcantara <pc@manguebit.com>,
Shyam Prasad N <sprasad@microsoft.com>,
Tom Talpey <tom@talpey.com>,
Dominique Martinet <asmadeus@codewreck.org>,
Eric Van Hensbergen <ericvh@kernel.org>,
Ilya Dryomov <idryomov@gmail.com>,
Christian Brauner <christian@brauner.io>,
linux-cachefs@redhat.com, linux-afs@lists.infradead.org,
linux-cifs@vger.kernel.org, linux-nfs@vger.kernel.org,
ceph-devel@vger.kernel.org, v9fs@lists.linux.dev,
linux-fsdevel@vger.kernel.org, linux-mm@kvack.org,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH v3 17/59] netfs: Limit subrequest by size or number of segments
Date: Thu, 7 Dec 2023 21:21:24 +0000 [thread overview]
Message-ID: <20231207212206.1379128-18-dhowells@redhat.com> (raw)
In-Reply-To: <20231207212206.1379128-1-dhowells@redhat.com>
Limit a subrequest to a maximum size and/or a maximum number of contiguous
physical regions. This permits, for instance, an subreq's iterator to be
limited to the number of DMA'able segments that a large RDMA request can
handle.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
fs/netfs/io.c | 18 ++++++++++++++++++
include/linux/netfs.h | 1 +
include/trace/events/netfs.h | 1 +
3 files changed, 20 insertions(+)
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index d8e9cd6ce338..c80b8eed1209 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -525,6 +525,7 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
struct iov_iter *io_iter)
{
enum netfs_io_source source;
+ size_t lsize;
_enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size);
@@ -547,13 +548,30 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
source = NETFS_INVALID_READ;
goto out;
}
+
+ if (subreq->max_nr_segs) {
+ lsize = netfs_limit_iter(io_iter, 0, subreq->len,
+ subreq->max_nr_segs);
+ if (subreq->len > lsize) {
+ subreq->len = lsize;
+ trace_netfs_sreq(subreq, netfs_sreq_trace_limited);
+ }
+ }
}
+ if (subreq->len > rreq->len)
+ pr_warn("R=%08x[%u] SREQ>RREQ %zx > %zx\n",
+ rreq->debug_id, subreq->debug_index,
+ subreq->len, rreq->len);
+
if (WARN_ON(subreq->len == 0)) {
source = NETFS_INVALID_READ;
goto out;
}
+ subreq->source = source;
+ trace_netfs_sreq(subreq, netfs_sreq_trace_prepare);
+
subreq->io_iter = *io_iter;
iov_iter_truncate(&subreq->io_iter, subreq->len);
iov_iter_advance(io_iter, subreq->len);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index a30b47e10797..406d5a3a3298 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -161,6 +161,7 @@ struct netfs_io_subrequest {
refcount_t ref;
short error; /* 0 or error that occurred */
unsigned short debug_index; /* Index in list (for debugging output) */
+ unsigned int max_nr_segs; /* 0 or max number of segments in an iterator */
enum netfs_io_source source; /* Where to read from/write to */
unsigned long flags;
#define NETFS_SREQ_COPY_TO_CACHE 0 /* Set if should copy the data to the cache */
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index beec534cbaab..fce6d0bc78e5 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -44,6 +44,7 @@
#define netfs_sreq_traces \
EM(netfs_sreq_trace_download_instead, "RDOWN") \
EM(netfs_sreq_trace_free, "FREE ") \
+ EM(netfs_sreq_trace_limited, "LIMIT") \
EM(netfs_sreq_trace_prepare, "PREP ") \
EM(netfs_sreq_trace_resubmit_short, "SHORT") \
EM(netfs_sreq_trace_submit, "SUBMT") \
next prev parent reply other threads:[~2023-12-07 21:23 UTC|newest]
Thread overview: 65+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-12-07 21:21 [PATCH v3 00/59] netfs, afs, 9p, cifs: Delegate high-level I/O to netfslib David Howells
2023-12-07 21:21 ` [PATCH v3 01/59] netfs, fscache: Move fs/fscache/* into fs/netfs/ David Howells
2023-12-07 21:21 ` [PATCH v3 02/59] netfs, fscache: Combine fscache with netfs David Howells
2023-12-07 21:21 ` [PATCH v3 03/59] netfs, fscache: Remove ->begin_cache_operation David Howells
2023-12-07 21:21 ` [PATCH v3 04/59] netfs, fscache: Move /proc/fs/fscache to /proc/fs/netfs and put in a symlink David Howells
2023-12-13 15:19 ` Jeff Layton
2023-12-13 15:32 ` David Howells
2023-12-07 21:21 ` [PATCH v3 05/59] netfs: Move pinning-for-writeback from fscache to netfs David Howells
2023-12-07 21:21 ` [PATCH v3 06/59] netfs: Add a procfile to list in-progress requests David Howells
2023-12-07 21:21 ` [PATCH v3 07/59] netfs: Allow the netfs to make the io (sub)request alloc larger David Howells
2023-12-07 21:21 ` [PATCH v3 08/59] netfs: Add a ->free_subrequest() op David Howells
2023-12-07 21:21 ` [PATCH v3 09/59] afs: Don't use folio->private to record partial modification David Howells
2023-12-07 21:21 ` [PATCH v3 10/59] netfs: Provide invalidate_folio and release_folio calls David Howells
2023-12-07 21:21 ` [PATCH v3 11/59] netfs: Implement unbuffered/DIO vs buffered I/O locking David Howells
2023-12-07 21:21 ` [PATCH v3 12/59] netfs: Add iov_iters to (sub)requests to describe various buffers David Howells
2023-12-07 21:21 ` [PATCH v3 13/59] netfs: Add support for DIO buffering David Howells
2023-12-07 21:21 ` [PATCH v3 14/59] netfs: Provide tools to create a buffer in an xarray David Howells
2023-12-07 21:21 ` [PATCH v3 15/59] netfs: Add bounce buffering support David Howells
2023-12-07 21:21 ` [PATCH v3 16/59] netfs: Add func to calculate pagecount/size-limited span of an iterator David Howells
2023-12-07 21:21 ` David Howells [this message]
2023-12-07 21:21 ` [PATCH v3 18/59] netfs: Export netfs_put_subrequest() and some tracepoints David Howells
2023-12-07 21:21 ` [PATCH v3 19/59] netfs: Extend the netfs_io_*request structs to handle writes David Howells
2023-12-07 21:21 ` [PATCH v3 20/59] netfs: Add a hook to allow tell the netfs to update its i_size David Howells
2023-12-07 21:21 ` [PATCH v3 21/59] netfs: Make netfs_put_request() handle a NULL pointer David Howells
2023-12-07 21:21 ` [PATCH v3 22/59] netfs: Make the refcounting of netfs_begin_read() easier to use David Howells
2023-12-07 21:21 ` [PATCH v3 23/59] netfs: Prep to use folio->private for write grouping and streaming write David Howells
2023-12-07 21:34 ` Matthew Wilcox
2023-12-07 21:21 ` [PATCH v3 24/59] netfs: Dispatch write requests to process a writeback slice David Howells
2023-12-07 21:21 ` [PATCH v3 25/59] netfs: Provide func to copy data to pagecache for buffered write David Howells
2023-12-07 21:21 ` [PATCH v3 26/59] netfs: Make netfs_read_folio() handle streaming-write pages David Howells
2023-12-07 21:21 ` [PATCH v3 27/59] netfs: Allocate multipage folios in the writepath David Howells
2023-12-07 21:21 ` [PATCH v3 28/59] netfs: Implement support for unbuffered/DIO read David Howells
2023-12-07 21:21 ` [PATCH v3 29/59] netfs: Implement unbuffered/DIO write support David Howells
2023-12-07 21:21 ` [PATCH v3 30/59] netfs: Implement buffered write API David Howells
2023-12-07 21:21 ` [PATCH v3 31/59] netfs: Allow buffered shared-writeable mmap through netfs_page_mkwrite() David Howells
2023-12-07 21:21 ` [PATCH v3 32/59] netfs: Provide netfs_file_read_iter() David Howells
2023-12-07 21:21 ` [PATCH v3 33/59] netfs, cachefiles: Pass upper bound length to allow expansion David Howells
2023-12-07 21:21 ` [PATCH v3 34/59] netfs: Provide a writepages implementation David Howells
2023-12-07 21:21 ` [PATCH v3 35/59] netfs: Provide minimum blocksize parameter David Howells
2023-12-07 21:21 ` [PATCH v3 36/59] netfs: Make netfs_skip_folio_read() take account of blocksize David Howells
2023-12-07 21:21 ` [PATCH v3 37/59] netfs: Perform content encryption David Howells
2023-12-07 21:21 ` [PATCH v3 38/59] netfs: Decrypt encrypted content David Howells
2023-12-07 21:21 ` [PATCH v3 39/59] netfs: Support decryption on ubuffered/DIO read David Howells
2023-12-07 21:21 ` [PATCH v3 40/59] netfs: Support encryption on Unbuffered/DIO write David Howells
2023-12-07 21:21 ` [PATCH v3 41/59] netfs: Provide a launder_folio implementation David Howells
2023-12-07 21:21 ` [PATCH v3 42/59] netfs: Implement a write-through caching option David Howells
2023-12-07 21:21 ` [PATCH v3 43/59] netfs: Rearrange netfs_io_subrequest to put request pointer first David Howells
2023-12-07 21:21 ` [PATCH v3 44/59] netfs: Optimise away reads above the point at which there can be no data David Howells
2023-12-07 21:21 ` [PATCH v3 45/59] afs: Use the netfs write helpers David Howells
2023-12-07 21:21 ` [PATCH v3 46/59] 9p: Use netfslib read/write_iter David Howells
2023-12-07 21:21 ` [PATCH v3 47/59] cifs: Replace cifs_readdata with a wrapper around netfs_io_subrequest David Howells
2023-12-07 21:21 ` [PATCH v3 48/59] cifs: Share server EOF pos with netfslib David Howells
2023-12-07 21:21 ` [PATCH v3 49/59] cifs: Set zero_point in the copy_file_range() and remap_file_range() David Howells
2023-12-07 21:21 ` [PATCH v3 50/59] cifs: Replace cifs_writedata with a wrapper around netfs_io_subrequest David Howells
2023-12-07 21:21 ` [PATCH v3 51/59] cifs: Use more fields from netfs_io_subrequest David Howells
2023-12-07 21:21 ` [PATCH v3 52/59] cifs: Make wait_mtu_credits take size_t args David Howells
2023-12-07 21:22 ` [PATCH v3 53/59] cifs: Implement netfslib hooks David Howells
2023-12-07 21:22 ` [PATCH v3 54/59] cifs: Move cifs_loose_read_iter() and cifs_file_write_iter() to file.c David Howells
2023-12-07 21:22 ` [PATCH v3 55/59] cifs: Cut over to using netfslib David Howells
2023-12-07 21:22 ` [PATCH v3 56/59] cifs: Remove some code that's no longer used, part 1 David Howells
2023-12-07 21:22 ` [PATCH v3 57/59] cifs: Remove some code that's no longer used, part 2 David Howells
2023-12-07 21:22 ` [PATCH v3 58/59] cifs: Remove some code that's no longer used, part 3 David Howells
2023-12-07 21:22 ` [PATCH v3 59/59] netfs: Eliminate PG_fscache by setting folio->private and marking dirty David Howells
2023-12-07 21:38 ` Matthew Wilcox
2023-12-07 21:57 ` David Howells
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20231207212206.1379128-18-dhowells@redhat.com \
--to=dhowells@redhat.com \
--cc=asmadeus@codewreck.org \
--cc=ceph-devel@vger.kernel.org \
--cc=christian@brauner.io \
--cc=ericvh@kernel.org \
--cc=idryomov@gmail.com \
--cc=jlayton@kernel.org \
--cc=linux-afs@lists.infradead.org \
--cc=linux-cachefs@redhat.com \
--cc=linux-cifs@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-nfs@vger.kernel.org \
--cc=marc.dionne@auristor.com \
--cc=netdev@vger.kernel.org \
--cc=pc@manguebit.com \
--cc=smfrench@gmail.com \
--cc=sprasad@microsoft.com \
--cc=tom@talpey.com \
--cc=v9fs@lists.linux.dev \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox