Netdev List
 help / color / mirror / Atom feed
From: Breno Leitao <leitao@debian.org>
To: Allison Henderson <achender@kernel.org>,
	 "David S. Miller" <davem@davemloft.net>,
	Eric Dumazet <edumazet@google.com>,
	 Jakub Kicinski <kuba@kernel.org>,
	Paolo Abeni <pabeni@redhat.com>,  Simon Horman <horms@kernel.org>,
	Shuah Khan <shuah@kernel.org>,
	 Andy Grover <andy.grover@oracle.com>
Cc: linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
	 linux-rdma@vger.kernel.org, rds-devel@oss.oracle.com,
	 linux-kselftest@vger.kernel.org,
	Breno Leitao <leitao@debian.org>,
	 kernel-team@meta.com
Subject: [PATCH net-next v3 2/2] rds: convert to getsockopt_iter
Date: Mon, 08 Jun 2026 02:44:58 -0700	[thread overview]
Message-ID: <20260608-getsock_more-v3-2-706ecf2ea332@debian.org> (raw)
In-Reply-To: <20260608-getsock_more-v3-0-706ecf2ea332@debian.org>

Convert RDS socket's getsockopt implementation to use the new
getsockopt_iter callback with sockopt_t.

Key changes:
- Replace (char __user *optval, int __user *optlen) with sockopt_t *opt
- Use opt->optlen for buffer length (input) and returned size (output)
- Use copy_to_iter() instead of put_user()/copy_to_user()

The RDS_INFO_* snapshot path in rds_info_getsockopt() used to pin the
userspace buffer with pin_user_pages_fast() on the raw optval address;
the info producers then memcpy into those pages under a spinlock via
kmap_atomic() and so must not fault. Obtain the same page array and
starting offset from opt->iter_out with iov_iter_extract_pages(), which
pins for write because iter_out is ITER_DEST.

The page array is preallocated here (sized with iov_iter_npages()) and
passed in, so iov_iter_extract_pages() fills it in place rather than
allocating one for us; RDS therefore keeps ownership of the array on
every return path and frees it itself. The rds_info_iterator /
rds_info_copy machinery and all producer callbacks are unchanged.

Kernel buffers (ITER_KVEC) are not page-backed in a way the info
producers can use, so the RDS_INFO path returns -EOPNOTSUPP for them;
this matches the previous behaviour, where a kernel-buffer getsockopt
hit the WARN_ONCE() path in do_sock_getsockopt() and returned
-EOPNOTSUPP. The simple RDS_RECVERR and SO_RDS_TRANSPORT options keep
working for kernel buffers via copy_to_iter().

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Allison Henderson <achender@kernel.org>
---
 net/rds/af_rds.c | 36 +++++++++++++++------------
 net/rds/info.c   | 76 ++++++++++++++++++++++++++++++++------------------------
 net/rds/info.h   |  3 +--
 3 files changed, 65 insertions(+), 50 deletions(-)

diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index 6f4f9cf352bd..d5defe9172e3 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -37,6 +37,7 @@
 #include <linux/in.h>
 #include <linux/ipv6.h>
 #include <linux/poll.h>
+#include <linux/uio.h>
 #include <net/sock.h>
 
 #include "rds.h"
@@ -485,35 +486,36 @@ static int rds_setsockopt(struct socket *sock, int level, int optname,
 }
 
 static int rds_getsockopt(struct socket *sock, int level, int optname,
-			  char __user *optval, int __user *optlen)
+			  sockopt_t *opt)
 {
 	struct rds_sock *rs = rds_sk_to_rs(sock->sk);
 	int ret = -ENOPROTOOPT, len;
 	int trans;
+	int val;
 
 	if (level != SOL_RDS)
 		goto out;
 
-	if (get_user(len, optlen)) {
-		ret = -EFAULT;
-		goto out;
-	}
+	len = opt->optlen;
 
 	switch (optname) {
 	case RDS_INFO_FIRST ... RDS_INFO_LAST:
-		ret = rds_info_getsockopt(sock, optname, optval,
-					  optlen);
+		ret = rds_info_getsockopt(sock, optname, opt);
 		break;
 
 	case RDS_RECVERR:
-		if (len < sizeof(int))
+		if (len < sizeof(int)) {
 			ret = -EINVAL;
-		else
-		if (put_user(rs->rs_recverr, (int __user *) optval) ||
-		    put_user(sizeof(int), optlen))
+			break;
+		}
+		val = rs->rs_recverr;
+		if (copy_to_iter(&val, sizeof(int), &opt->iter_out) !=
+		    sizeof(int)) {
 			ret = -EFAULT;
-		else
+		} else {
+			opt->optlen = sizeof(int);
 			ret = 0;
+		}
 		break;
 	case SO_RDS_TRANSPORT:
 		if (len < sizeof(int)) {
@@ -522,11 +524,13 @@ static int rds_getsockopt(struct socket *sock, int level, int optname,
 		}
 		trans = (rs->rs_transport ? rs->rs_transport->t_type :
 			 RDS_TRANS_NONE); /* unbound */
-		if (put_user(trans, (int __user *)optval) ||
-		    put_user(sizeof(int), optlen))
+		if (copy_to_iter(&trans, sizeof(int), &opt->iter_out) !=
+		    sizeof(int)) {
 			ret = -EFAULT;
-		else
+		} else {
+			opt->optlen = sizeof(int);
 			ret = 0;
+		}
 		break;
 	default:
 		break;
@@ -653,7 +657,7 @@ static const struct proto_ops rds_proto_ops = {
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,
 	.setsockopt =	rds_setsockopt,
-	.getsockopt =	rds_getsockopt,
+	.getsockopt_iter =	rds_getsockopt,
 	.sendmsg =	rds_sendmsg,
 	.recvmsg =	rds_recvmsg,
 	.mmap =		sock_no_mmap,
diff --git a/net/rds/info.c b/net/rds/info.c
index f1b29994934a..499b3774860e 100644
--- a/net/rds/info.c
+++ b/net/rds/info.c
@@ -35,6 +35,7 @@
 #include <linux/slab.h>
 #include <linux/proc_fs.h>
 #include <linux/export.h>
+#include <linux/uio.h>
 
 #include "rds.h"
 
@@ -144,60 +145,68 @@ void rds_info_copy(struct rds_info_iterator *iter, void *data,
 EXPORT_SYMBOL_GPL(rds_info_copy);
 
 /*
- * @optval points to the userspace buffer that the information snapshot
- * will be copied into.
- *
- * @optlen on input is the size of the buffer in userspace.  @optlen
- * on output is the size of the requested snapshot in bytes.
+ * @opt->iter_out describes the buffer that the information snapshot will be
+ * copied into, and @opt->optlen is the size of that buffer on input.  On
+ * output @opt->optlen is set to the size of the requested snapshot in bytes.
  *
  * This function returns -errno if there is a failure, particularly -ENOSPC
- * if the given userspace buffer was not large enough to fit the snapshot.
- * On success it returns the positive number of bytes of each array element
- * in the snapshot.
+ * if the given buffer was not large enough to fit the snapshot.  On success
+ * it returns the positive number of bytes of each array element in the
+ * snapshot.
  */
-int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval,
-			int __user *optlen)
+int rds_info_getsockopt(struct socket *sock, int optname, sockopt_t *opt)
 {
 	struct rds_info_iterator iter;
 	struct rds_info_lengths lens;
 	unsigned long nr_pages = 0;
-	unsigned long start;
 	rds_info_func func;
 	struct page **pages = NULL;
+	size_t offset0 = 0;
+	int npages = 0;
 	int ret;
 	int len;
 	int total;
 
-	if (get_user(len, optlen)) {
-		ret = -EFAULT;
-		goto out;
-	}
+	len = opt->optlen;
 
 	/* check for all kinds of wrapping and the like */
-	start = (unsigned long)optval;
-	if (len < 0 || len > INT_MAX - PAGE_SIZE + 1 || start + len < start) {
+	if (len < 0 || len > INT_MAX - PAGE_SIZE + 1) {
 		ret = -EINVAL;
 		goto out;
 	}
 
+	/* The info producers write into the pages with kmap_atomic() while
+	 * holding a spinlock, so they need a genuine page-backed user buffer.
+	 */
+	if (!user_backed_iter(&opt->iter_out)) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
 	/* a 0 len call is just trying to probe its length */
 	if (len == 0)
 		goto call_func;
 
-	nr_pages = (PAGE_ALIGN(start + len) - (start & PAGE_MASK))
-			>> PAGE_SHIFT;
-
-	pages = kmalloc_objs(struct page *, nr_pages);
+	/*
+	 * Preallocate the page array and pass it in so that
+	 * iov_iter_extract_pages() fills it in place rather than allocating
+	 * one for us.  Handing it a non-NULL array keeps ownership of the
+	 * array with us on every return path, instead of depending on the
+	 * iterator code to allocate and hand it back.
+	 */
+	npages = iov_iter_npages(&opt->iter_out, INT_MAX);
+	pages = kvmalloc_array(npages, sizeof(*pages), GFP_KERNEL);
 	if (!pages) {
 		ret = -ENOMEM;
 		goto out;
 	}
-	ret = pin_user_pages_fast(start, nr_pages, FOLL_WRITE, pages);
-	if (ret != nr_pages) {
-		if (ret > 0)
-			nr_pages = ret;
-		else
-			nr_pages = 0;
+
+	ret = iov_iter_extract_pages(&opt->iter_out, &pages, len, npages,
+				     0, &offset0);
+	if (ret < 0)
+		goto out;
+	nr_pages = DIV_ROUND_UP(offset0 + ret, PAGE_SIZE);
+	if (ret != len) {
 		ret = -EAGAIN; /* XXX ? */
 		goto out;
 	}
@@ -213,7 +222,7 @@ int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval,
 
 	iter.pages = pages;
 	iter.addr = NULL;
-	iter.offset = start & (PAGE_SIZE - 1);
+	iter.offset = offset0;
 
 	func(sock, len, &iter, &lens);
 	BUG_ON(lens.each == 0);
@@ -230,13 +239,16 @@ int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval,
 		ret = lens.each;
 	}
 
-	if (put_user(len, optlen))
-		ret = -EFAULT;
+	opt->optlen = len;
 
 out:
-	if (pages)
+	/*
+	 * iov_iter_extract_pages() pins only user-backed (ubuf) iters;
+	 * iov_iter_extract_will_pin() reports whether an unpin is owed here.
+	 */
+	if (pages && iov_iter_extract_will_pin(&opt->iter_out))
 		unpin_user_pages(pages, nr_pages);
-	kfree(pages);
+	kvfree(pages);
 
 	return ret;
 }
diff --git a/net/rds/info.h b/net/rds/info.h
index a069b51c4679..1aab62ab6d00 100644
--- a/net/rds/info.h
+++ b/net/rds/info.h
@@ -21,8 +21,7 @@ typedef void (*rds_info_func)(struct socket *sock, unsigned int len,
 
 void rds_info_register_func(int optname, rds_info_func func);
 void rds_info_deregister_func(int optname, rds_info_func func);
-int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval,
-			int __user *optlen);
+int rds_info_getsockopt(struct socket *sock, int optname, sockopt_t *opt);
 void rds_info_copy(struct rds_info_iterator *iter, void *data,
 		   unsigned long bytes);
 void rds_info_iter_unmap(struct rds_info_iterator *iter);

-- 
2.53.0-Meta


      parent reply	other threads:[~2026-06-08  9:46 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-08  9:44 [PATCH net-next v3 0/2] net: rds: convert rds to getsockopt_iter Breno Leitao
2026-06-08  9:44 ` [PATCH net-next v3 1/2] selftests: net: rds: add getsockopt() conversion test Breno Leitao
2026-06-08  9:44 ` Breno Leitao [this message]

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=20260608-getsock_more-v3-2-706ecf2ea332@debian.org \
    --to=leitao@debian.org \
    --cc=achender@kernel.org \
    --cc=andy.grover@oracle.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=horms@kernel.org \
    --cc=kernel-team@meta.com \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=rds-devel@oss.oracle.com \
    --cc=shuah@kernel.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