The motivation for this is to remove the SOL_SOCKET limitation from io_uring_cmd_getsockopt(). The reason for this limitation is that io_uring_cmd_getsockopt() passes a kernel pointer. The first idea would be to change the optval and optlen arguments to the protocol specific hooks also to sockptr_t, as that is already used for setsockopt() and also by do_sock_getsockopt() sk_getsockopt() and BPF_CGROUP_RUN_PROG_GETSOCKOPT(). But as Linus don't like 'sockptr_t' I used a different approach. Instead of passing the optlen as user or kernel pointer, we only ever pass a kernel pointer and do the translation from/to userspace in do_sock_getsockopt(). The simple solution would be to just remove the '__user' from the int *optlen argument, but it seems the compiler doesn't complain about '__user' vs. without it, so instead I used a helper struct in order to make sure everything compiles with a typesafe change. That together with get_optlen() and put_optlen() helper macros make it relatively easy to review and check the behaviour is most likely unchanged. In order to avoid uapi changes regarding different error code orders regarding -EFAULT, the real -EFAULT handling is deferred to get_optlen() and put_optlen(). This allows io_uring_cmd_getsockopt() to remove the SOL_SOCKET limitation. Removing 'sockptr_t optlen' from existing code is for patch for another day. Link: https://lore.kernel.org/io-uring/86b1dce5-4bb4-4a0b-9cff-e72f488bf57d@xxxxxxxxx/T/#t Cc: Jens Axboe <axboe@xxxxxxxxx> Cc: Pavel Begunkov <asml.silence@xxxxxxxxx> Cc: Breno Leitao <leitao@xxxxxxxxxx> Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Cc: Jakub Kicinski <kuba@xxxxxxxxxx> Cc: Christoph Hellwig <hch@xxxxxx> Cc: Karsten Keil <isdn@xxxxxxxxxxxxxx> Cc: Ayush Sawal <ayush.sawal@xxxxxxxxxxx> Cc: Andrew Lunn <andrew+netdev@xxxxxxx> Cc: "David S. Miller" <davem@xxxxxxxxxxxxx> Cc: Eric Dumazet <edumazet@xxxxxxxxxx> Cc: Paolo Abeni <pabeni@xxxxxxxxxx> Cc: Simon Horman <horms@xxxxxxxxxx> Cc: Kuniyuki Iwashima <kuniyu@xxxxxxxxxx> Cc: Willem de Bruijn <willemb@xxxxxxxxxx> Cc: David Ahern <dsahern@xxxxxxxxxx> Cc: Marcelo Ricardo Leitner <marcelo.leitner@xxxxxxxxx> Cc: Xin Long <lucien.xin@xxxxxxxxx> Cc: Neal Cardwell <ncardwell@xxxxxxxxxx> Cc: Joerg Reuter <jreuter@xxxxxxxx> Cc: Marcel Holtmann <marcel@xxxxxxxxxxxx> Cc: Johan Hedberg <johan.hedberg@xxxxxxxxx> Cc: Luiz Augusto von Dentz <luiz.dentz@xxxxxxxxx> Cc: Oliver Hartkopp <socketcan@xxxxxxxxxxxx> Cc: Marc Kleine-Budde <mkl@xxxxxxxxxxxxxx> Cc: Robin van der Gracht <robin@xxxxxxxxxxx> Cc: Oleksij Rempel <o.rempel@xxxxxxxxxxxxxx> Cc: kernel@xxxxxxxxxxxxxx Cc: Alexander Aring <alex.aring@xxxxxxxxx> Cc: Stefan Schmidt <stefan@xxxxxxxxxxxxxxxxxx> Cc: Miquel Raynal <miquel.raynal@xxxxxxxxxxx> Cc: Alexandra Winter <wintera@xxxxxxxxxxxxx> Cc: Thorsten Winkler <twinkler@xxxxxxxxxxxxx> Cc: James Chapman <jchapman@xxxxxxxxxxx> Cc: Jeremy Kerr <jk@xxxxxxxxxxxxxxxxxxxx> Cc: Matt Johnston <matt@xxxxxxxxxxxxxxxxxxxx> Cc: Matthieu Baerts <matttbe@xxxxxxxxxx> Cc: Mat Martineau <martineau@xxxxxxxxxx> Cc: Geliang Tang <geliang@xxxxxxxxxx> Cc: Krzysztof Kozlowski <krzk@xxxxxxxxxx> Cc: Remi Denis-Courmont <courmisch@xxxxxxxxx> Cc: Allison Henderson <allison.henderson@xxxxxxxxxx> Cc: David Howells <dhowells@xxxxxxxxxx> Cc: Marc Dionne <marc.dionne@xxxxxxxxxxxx> Cc: Wenjia Zhang <wenjia@xxxxxxxxxxxxx> Cc: Jan Karcher <jaka@xxxxxxxxxxxxx> Cc: "D. Wythe" <alibuda@xxxxxxxxxxxxxxxxx> Cc: Tony Lu <tonylu@xxxxxxxxxxxxxxxxx> Cc: Wen Gu <guwen@xxxxxxxxxxxxxxxxx> Cc: Jon Maloy <jmaloy@xxxxxxxxxx> Cc: Boris Pismenny <borisp@xxxxxxxxxx> Cc: John Fastabend <john.fastabend@xxxxxxxxx> Cc: Stefano Garzarella <sgarzare@xxxxxxxxxx> Cc: Martin Schiller <ms@xxxxxxxxxx> Cc: "Björn Töpel" <bjorn@xxxxxxxxxx> Cc: Magnus Karlsson <magnus.karlsson@xxxxxxxxx> Cc: Maciej Fijalkowski <maciej.fijalkowski@xxxxxxxxx> Cc: Jonathan Lemon <jonathan.lemon@xxxxxxxxx> Cc: Alexei Starovoitov <ast@xxxxxxxxxx> Cc: Daniel Borkmann <daniel@xxxxxxxxxxxxx> Cc: Jesper Dangaard Brouer <hawk@xxxxxxxxxx> CC: Stefan Metzmacher <metze@xxxxxxxxx> Cc: netdev@xxxxxxxxxxxxxxx Cc: linux-kernel@xxxxxxxxxxxxxxx Cc: linux-sctp@xxxxxxxxxxxxxxx Cc: linux-hams@xxxxxxxxxxxxxxx Cc: linux-bluetooth@xxxxxxxxxxxxxxx Cc: linux-can@xxxxxxxxxxxxxxx Cc: dccp@xxxxxxxxxxxxxxx Cc: linux-wpan@xxxxxxxxxxxxxxx Cc: linux-s390@xxxxxxxxxxxxxxx Cc: mptcp@xxxxxxxxxxxxxxx Cc: linux-rdma@xxxxxxxxxxxxxxx Cc: rds-devel@xxxxxxxxxxxxxx Cc: linux-afs@xxxxxxxxxxxxxxxxxxx Cc: tipc-discussion@xxxxxxxxxxxxxxxxxxxxx Cc: virtualization@xxxxxxxxxxxxxxx Cc: linux-x25@xxxxxxxxxxxxxxx Cc: bpf@xxxxxxxxxxxxxxx Cc: isdn4linux@xxxxxxxxxxxxxxxxxxxxxx Cc: io-uring@xxxxxxxxxxxxxxx Signed-off-by: Stefan Metzmacher <metze@xxxxxxxxx> --- include/linux/sockptr.h | 20 +++++++++++++++----- net/socket.c | 31 +++++++++++++++++++++++++++++-- 2 files changed, 44 insertions(+), 7 deletions(-) diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index 1baf66f26f4f..06ec7fd73028 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -170,20 +170,25 @@ static inline int check_zeroed_sockptr(sockptr_t src, size_t offset, } typedef struct { - int __user *up; + int *kp; } optlen_t; #define __check_optlen_t(__optlen) \ ({ \ optlen_t *__ptr __maybe_unused = &__optlen; \ - BUILD_BUG_ON(sizeof(*((__ptr)->up)) != sizeof(int)); \ + BUILD_BUG_ON(sizeof(*((__ptr)->kp)) != sizeof(int)); \ }) #define get_optlen(__val, __optlen) \ ({ \ long __err; \ __check_optlen_t(__optlen); \ - __err = get_user(__val, __optlen.up); \ + if ((__optlen).kp != NULL) { \ + (__val) = *((__optlen).kp); \ + __err = 0; \ + } else { \ + __err = -EFAULT; \ + } \ __err; \ }) @@ -191,13 +196,18 @@ typedef struct { ({ \ long __err; \ __check_optlen_t(__optlen); \ - __err = put_user(__val, __optlen.up); \ + if ((__optlen).kp != NULL) { \ + *((__optlen).kp) = (__val); \ + __err = 0; \ + } else { \ + __err = -EFAULT; \ + } \ __err; \ }) static inline sockptr_t OPTLEN_SOCKPTR(optlen_t optlen) { - return (sockptr_t) { .user = optlen.up, }; + return (sockptr_t) { .kernel = optlen.kp, .is_kernel = true }; } #endif /* _LINUX_SOCKPTR_H */ diff --git a/net/socket.c b/net/socket.c index fa2de12c10e6..81e5c9767bbc 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2350,15 +2350,42 @@ int do_sock_getsockopt(struct socket *sock, bool compat, int level, } else if (unlikely(!ops->getsockopt)) { err = -EOPNOTSUPP; } else { - optlen_t _optlen = { .up = NULL, }; + optlen_t _optlen = { .kp = NULL, }; + int koptlen; if (WARN_ONCE(optval.is_kernel, "Invalid argument type")) return -EOPNOTSUPP; - _optlen.up = optlen.user; + if (optlen.is_kernel) { + _optlen.kp = optlen.kernel; + } else if (optlen.user != NULL) { + /* + * If optlen.user is NULL, + * we pass _optlen.kp = NULL + * in order to avoid breaking + * any uapi for getsockopt() + * implementations that ignore + * the optlen pointer completely + * or do any level and optname + * checking before hitting a + * potential -EFAULT condition. + * + * Also when optlen.user is not NULL, + * but copy_from_sockptr() causes -EFAULT, + * we'll pass optlen.kp = NULL in order + * to defer a possible -EFAULT return + * to the caller to get_optlen() and put_optlen(). + */ + if (copy_from_sockptr(&koptlen, optlen, sizeof(koptlen)) == 0) + _optlen.kp = &koptlen; + } err = ops->getsockopt(sock, level, optname, optval.user, _optlen); + if (err != -EFAULT && _optlen.kp == &koptlen) { + if (copy_to_sockptr(optlen, &koptlen, sizeof(koptlen))) + return -EFAULT; + } } if (!compat) -- 2.34.1
