rds: convert to getsockopt_iter

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>
Link: https://patch.msgid.link/20260608-getsock_more-v3-2-706ecf2ea332@debian.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
This commit is contained in:
Breno Leitao
2026-06-08 02:44:58 -07:00
committed by Paolo Abeni
parent b74360369e
commit 6e94eeb2a2
3 changed files with 65 additions and 50 deletions
+20 -16
View File
@@ -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 @@ out:
}
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,
+44 -32
View File
@@ -35,6 +35,7 @@
#include <linux/slab.h>
#include <linux/proc_fs.h>
#include <linux/export.h>
#include <linux/uio.h>
#include "rds.h"
@@ -144,39 +145,41 @@ 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;
len = opt->optlen;
/* check for all kinds of wrapping and the like */
if (len < 0 || len > INT_MAX - PAGE_SIZE + 1) {
ret = -EINVAL;
goto out;
}
/* 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) {
ret = -EINVAL;
/* 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;
}
@@ -184,20 +187,26 @@ int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval,
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 @@ call_func:
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 @@ call_func:
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;
}
+1 -2
View File
@@ -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);