From: Chuck Lever <cel@kernel.org>
To: NeilBrown <neil@brown.name>, Jeff Layton <jlayton@kernel.org>,
Olga Kornievskaia <okorniev@redhat.com>,
Dai Ngo <dai.ngo@oracle.com>, Tom Talpey <tom@talpey.com>
Cc: <linux-nfs@vger.kernel.org>, Chuck Lever <chuck.lever@oracle.com>
Subject: [RFC PATCH 3/3] NFSD: Remove the cap on number of operations per NFSv4 COMPOUND
Date: Tue, 10 Jun 2025 12:05:09 -0400 [thread overview]
Message-ID: <20250610160509.97599-4-cel@kernel.org> (raw)
In-Reply-To: <20250610160509.97599-1-cel@kernel.org>
From: Chuck Lever <chuck.lever@oracle.com>
This limit has always been a sanity check; in nearly all cases a
large COMPOUND is a sign of a malfunctioning client. The only real
limit on COMPOUND size and complexity is the size of NFSD's send
and receive buffers.
However, there are a few cases where a large COMPOUND is sane. For
example, when a client implementation wants to walk down a long file
pathname in a single round trip.
A small risk is that now a client can construct a COMPOUND request
that can keep a single nfsd thread busy for quite some time.
Suggested-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfsd/nfs4proc.c | 14 ++------------
fs/nfsd/nfs4state.c | 1 -
fs/nfsd/nfs4xdr.c | 4 +---
fs/nfsd/nfsd.h | 3 ---
fs/nfsd/xdr4.h | 1 -
5 files changed, 3 insertions(+), 20 deletions(-)
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index f13abbb13b38..f4edf222e00e 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2842,20 +2842,10 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
rqstp->rq_lease_breaker = (void **)&cstate->clp;
- trace_nfsd_compound(rqstp, args->tag, args->taglen, args->client_opcnt);
+ trace_nfsd_compound(rqstp, args->tag, args->taglen, args->opcnt);
while (!status && resp->opcnt < args->opcnt) {
op = &args->ops[resp->opcnt++];
- if (unlikely(resp->opcnt == NFSD_MAX_OPS_PER_COMPOUND)) {
- /* If there are still more operations to process,
- * stop here and report NFS4ERR_RESOURCE. */
- if (cstate->minorversion == 0 &&
- args->client_opcnt > resp->opcnt) {
- op->status = nfserr_resource;
- goto encode_op;
- }
- }
-
/*
* The XDR decode routines may have pre-set op->status;
* for example, if there is a miscellaneous XDR error
@@ -2932,7 +2922,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
status = op->status;
}
- trace_nfsd_compound_status(args->client_opcnt, resp->opcnt,
+ trace_nfsd_compound_status(args->opcnt, resp->opcnt,
status, nfsd4_op_name(op->opnum));
nfsd4_cstate_clear_replay(cstate);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index d5694987f86f..4b6ae8e54cd2 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3872,7 +3872,6 @@ static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfs
ca->headerpadsz = 0;
ca->maxreq_sz = min_t(u32, ca->maxreq_sz, maxrpc);
ca->maxresp_sz = min_t(u32, ca->maxresp_sz, maxrpc);
- ca->maxops = min_t(u32, ca->maxops, NFSD_MAX_OPS_PER_COMPOUND);
ca->maxresp_cached = min_t(u32, ca->maxresp_cached,
NFSD_SLOT_CACHE_SIZE + NFSD_MIN_HDR_SEQ_SZ);
ca->maxreqs = min_t(u32, ca->maxreqs, NFSD_MAX_SLOTS_PER_SESSION);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 3afcdbed6e14..ea91bad4eee2 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2500,10 +2500,8 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
if (xdr_stream_decode_u32(argp->xdr, &argp->minorversion) < 0)
return false;
- if (xdr_stream_decode_u32(argp->xdr, &argp->client_opcnt) < 0)
+ if (xdr_stream_decode_u32(argp->xdr, &argp->opcnt) < 0)
return false;
- argp->opcnt = min_t(u32, argp->client_opcnt,
- NFSD_MAX_OPS_PER_COMPOUND);
if (argp->opcnt > ARRAY_SIZE(argp->iops)) {
argp->ops = vcalloc(argp->opcnt, sizeof(*argp->ops));
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 570065285e67..54a96042f5ac 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -57,9 +57,6 @@ struct readdir_cd {
__be32 err; /* 0, nfserr, or nfserr_eof */
};
-/* Maximum number of operations per session compound */
-#define NFSD_MAX_OPS_PER_COMPOUND 50
-
struct nfsd_genl_rqstp {
struct sockaddr rq_daddr;
struct sockaddr rq_saddr;
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index aa2a356da784..a23bc56051ca 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -870,7 +870,6 @@ struct nfsd4_compoundargs {
char * tag;
u32 taglen;
u32 minorversion;
- u32 client_opcnt;
u32 opcnt;
bool splice_ok;
struct nfsd4_op *ops;
--
2.49.0
next prev parent reply other threads:[~2025-06-10 16:05 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-06-10 16:05 [RFC PATCH 0/3] Remove the max-ops-per-compound-limit Chuck Lever
2025-06-10 16:05 ` [RFC PATCH 1/3] NFSD: Rename a function parameter Chuck Lever
2025-06-10 16:05 ` [RFC PATCH 2/3] NFSD: Make nfsd_genl_rqstp::rq_ops array best-effort Chuck Lever
2025-06-10 16:05 ` Chuck Lever [this message]
2025-06-10 17:01 ` [RFC PATCH 3/3] NFSD: Remove the cap on number of operations per NFSv4 COMPOUND Jeff Layton
2025-06-10 17:07 ` Chuck Lever
2025-06-10 17:28 ` [RFC PATCH 0/3] Remove the max-ops-per-compound-limit Jeff Layton
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=20250610160509.97599-4-cel@kernel.org \
--to=cel@kernel.org \
--cc=chuck.lever@oracle.com \
--cc=dai.ngo@oracle.com \
--cc=jlayton@kernel.org \
--cc=linux-nfs@vger.kernel.org \
--cc=neil@brown.name \
--cc=okorniev@redhat.com \
--cc=tom@talpey.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.