From 2bfc66850952b6921b2033b09729ec59eabbc81d Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 7 Jun 2023 19:19:10 +0100 Subject: splice, net: Add a splice_eof op to file-ops and socket-ops Add an optional method, ->splice_eof(), to allow splice to indicate the premature termination of a splice to struct file_operations and struct proto_ops. This is called if sendfile() or splice() encounters all of the following conditions inside splice_direct_to_actor(): (1) the user did not set SPLICE_F_MORE (splice only), and (2) an EOF condition occurred (->splice_read() returned 0), and (3) we haven't read enough to fulfill the request (ie. len > 0 still), and (4) we have already spliced at least one byte. A further patch will modify the behaviour of SPLICE_F_MORE to always be passed to the actor if either the user set it or we haven't yet read sufficient data to fulfill the request. Suggested-by: Linus Torvalds Link: https://lore.kernel.org/r/CAHk-=wh=V579PDYvkpnTobCLGczbgxpMgGmmhqiTyE34Cpi5Gg@mail.gmail.com/ Signed-off-by: David Howells Reviewed-by: Jakub Kicinski cc: Jens Axboe cc: Christoph Hellwig cc: Al Viro cc: Matthew Wilcox cc: Jan Kara cc: Jeff Layton cc: David Hildenbrand cc: Christian Brauner cc: Chuck Lever cc: Boris Pismenny cc: John Fastabend cc: linux-mm@kvack.org Signed-off-by: Jakub Kicinski --- include/net/sock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net/sock.h') diff --git a/include/net/sock.h b/include/net/sock.h index 6f428a7f3567..2790133b4b76 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1279,6 +1279,7 @@ struct proto { size_t len, int flags, int *addr_len); int (*sendpage)(struct sock *sk, struct page *page, int offset, size_t size, int flags); + void (*splice_eof)(struct socket *sock); int (*bind)(struct sock *sk, struct sockaddr *addr, int addr_len); int (*bind_add)(struct sock *sk, -- cgit From e1d001fa5b477c4da46a29be1fcece91db7c7c6f Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Fri, 9 Jun 2023 08:27:42 -0700 Subject: net: ioctl: Use kernel memory on protocol ioctl callbacks Most of the ioctls to net protocols operates directly on userspace argument (arg). Usually doing get_user()/put_user() directly in the ioctl callback. This is not flexible, because it is hard to reuse these functions without passing userspace buffers. Change the "struct proto" ioctls to avoid touching userspace memory and operate on kernel buffers, i.e., all protocol's ioctl callbacks is adapted to operate on a kernel memory other than on userspace (so, no more {put,get}_user() and friends being called in the ioctl callback). This changes the "struct proto" ioctl format in the following way: int (*ioctl)(struct sock *sk, int cmd, - unsigned long arg); + int *karg); (Important to say that this patch does not touch the "struct proto_ops" protocols) So, the "karg" argument, which is passed to the ioctl callback, is a pointer allocated to kernel space memory (inside a function wrapper). This buffer (karg) may contain input argument (copied from userspace in a prep function) and it might return a value/buffer, which is copied back to userspace if necessary. There is not one-size-fits-all format (that is I am using 'may' above), but basically, there are three type of ioctls: 1) Do not read from userspace, returns a result to userspace 2) Read an input parameter from userspace, and does not return anything to userspace 3) Read an input from userspace, and return a buffer to userspace. The default case (1) (where no input parameter is given, and an "int" is returned to userspace) encompasses more than 90% of the cases, but there are two other exceptions. Here is a list of exceptions: * Protocol RAW: * cmd = SIOCGETVIFCNT: * input and output = struct sioc_vif_req * cmd = SIOCGETSGCNT * input and output = struct sioc_sg_req * Explanation: for the SIOCGETVIFCNT case, userspace passes the input argument, which is struct sioc_vif_req. Then the callback populates the struct, which is copied back to userspace. * Protocol RAW6: * cmd = SIOCGETMIFCNT_IN6 * input and output = struct sioc_mif_req6 * cmd = SIOCGETSGCNT_IN6 * input and output = struct sioc_sg_req6 * Protocol PHONET: * cmd == SIOCPNADDRESOURCE | SIOCPNDELRESOURCE * input int (4 bytes) * Nothing is copied back to userspace. For the exception cases, functions sock_sk_ioctl_inout() will copy the userspace input, and copy it back to kernel space. The wrapper that prepare the buffer and put the buffer back to user is sk_ioctl(), so, instead of calling sk->sk_prot->ioctl(), the callee now calls sk_ioctl(), which will handle all cases. Signed-off-by: Breno Leitao Reviewed-by: Willem de Bruijn Reviewed-by: David Ahern Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230609152800.830401-1-leitao@debian.org Signed-off-by: Jakub Kicinski --- include/net/sock.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/net/sock.h') diff --git a/include/net/sock.h b/include/net/sock.h index 2790133b4b76..62a1b99da349 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1258,7 +1258,7 @@ struct proto { bool kern); int (*ioctl)(struct sock *sk, int cmd, - unsigned long arg); + int *karg); int (*init)(struct sock *sk); void (*destroy)(struct sock *sk); void (*shutdown)(struct sock *sk, int how); @@ -2974,6 +2974,9 @@ int sock_get_timeout(long timeo, void *optval, bool old_timeval); int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, sockptr_t optval, int optlen, bool old_timeval); +int sock_ioctl_inout(struct sock *sk, unsigned int cmd, + void __user *arg, void *karg, size_t size); +int sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); static inline bool sk_is_readable(struct sock *sk) { if (sk->sk_prot->sock_is_readable) -- cgit From dc97391e661009eab46783030d2404c9b6e6f2e7 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 23 Jun 2023 23:55:12 +0100 Subject: sock: Remove ->sendpage*() in favour of sendmsg(MSG_SPLICE_PAGES) Remove ->sendpage() and ->sendpage_locked(). sendmsg() with MSG_SPLICE_PAGES should be used instead. This allows multiple pages and multipage folios to be passed through. Signed-off-by: David Howells Acked-by: Marc Kleine-Budde # for net/can cc: Jens Axboe cc: Matthew Wilcox cc: linux-afs@lists.infradead.org cc: mptcp@lists.linux.dev cc: rds-devel@oss.oracle.com cc: tipc-discussion@lists.sourceforge.net cc: virtualization@lists.linux-foundation.org Link: https://lore.kernel.org/r/20230623225513.2732256-16-dhowells@redhat.com Signed-off-by: Jakub Kicinski --- include/net/sock.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/net/sock.h') diff --git a/include/net/sock.h b/include/net/sock.h index 62a1b99da349..121284f455a8 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1277,8 +1277,6 @@ struct proto { size_t len); int (*recvmsg)(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len); - int (*sendpage)(struct sock *sk, struct page *page, - int offset, size_t size, int flags); void (*splice_eof)(struct socket *sock); int (*bind)(struct sock *sk, struct sockaddr *addr, int addr_len); @@ -1919,10 +1917,6 @@ int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t len); int sock_no_recvmsg(struct socket *, struct msghdr *, size_t, int); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma); -ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, - size_t size, int flags); -ssize_t sock_no_sendpage_locked(struct sock *sk, struct page *page, - int offset, size_t size, int flags); /* * Functions to fill in entries in struct proto_ops when a protocol -- cgit From 25a9c8a4431c364f97f75558cb346d2ad3f53fbb Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 26 Jun 2023 09:43:13 -0700 Subject: netlink: Add __sock_i_ino() for __netlink_diag_dump(). syzbot reported a warning in __local_bh_enable_ip(). [0] Commit 8d61f926d420 ("netlink: fix potential deadlock in netlink_set_err()") converted read_lock(&nl_table_lock) to read_lock_irqsave() in __netlink_diag_dump() to prevent a deadlock. However, __netlink_diag_dump() calls sock_i_ino() that uses read_lock_bh() and read_unlock_bh(). If CONFIG_TRACE_IRQFLAGS=y, read_unlock_bh() finally enables IRQ even though it should stay disabled until the following read_unlock_irqrestore(). Using read_lock() in sock_i_ino() would trigger a lockdep splat in another place that was fixed in commit f064af1e500a ("net: fix a lockdep splat"), so let's add __sock_i_ino() that would be safe to use under BH disabled. [0]: WARNING: CPU: 0 PID: 5012 at kernel/softirq.c:376 __local_bh_enable_ip+0xbe/0x130 kernel/softirq.c:376 Modules linked in: CPU: 0 PID: 5012 Comm: syz-executor487 Not tainted 6.4.0-rc7-syzkaller-00202-g6f68fc395f49 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/27/2023 RIP: 0010:__local_bh_enable_ip+0xbe/0x130 kernel/softirq.c:376 Code: 45 bf 01 00 00 00 e8 91 5b 0a 00 e8 3c 15 3d 00 fb 65 8b 05 ec e9 b5 7e 85 c0 74 58 5b 5d c3 65 8b 05 b2 b6 b4 7e 85 c0 75 a2 <0f> 0b eb 9e e8 89 15 3d 00 eb 9f 48 89 ef e8 6f 49 18 00 eb a8 0f RSP: 0018:ffffc90003a1f3d0 EFLAGS: 00010046 RAX: 0000000000000000 RBX: 0000000000000201 RCX: 1ffffffff1cf5996 RDX: 0000000000000000 RSI: 0000000000000201 RDI: ffffffff8805c6f3 RBP: ffffffff8805c6f3 R08: 0000000000000001 R09: ffff8880152b03a3 R10: ffffed1002a56074 R11: 0000000000000005 R12: 00000000000073e4 R13: dffffc0000000000 R14: 0000000000000002 R15: 0000000000000000 FS: 0000555556726300(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000045ad50 CR3: 000000007c646000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: sock_i_ino+0x83/0xa0 net/core/sock.c:2559 __netlink_diag_dump+0x45c/0x790 net/netlink/diag.c:171 netlink_diag_dump+0xd6/0x230 net/netlink/diag.c:207 netlink_dump+0x570/0xc50 net/netlink/af_netlink.c:2269 __netlink_dump_start+0x64b/0x910 net/netlink/af_netlink.c:2374 netlink_dump_start include/linux/netlink.h:329 [inline] netlink_diag_handler_dump+0x1ae/0x250 net/netlink/diag.c:238 __sock_diag_cmd net/core/sock_diag.c:238 [inline] sock_diag_rcv_msg+0x31e/0x440 net/core/sock_diag.c:269 netlink_rcv_skb+0x165/0x440 net/netlink/af_netlink.c:2547 sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:280 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x547/0x7f0 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x925/0xe30 net/netlink/af_netlink.c:1914 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg+0xde/0x190 net/socket.c:747 ____sys_sendmsg+0x71c/0x900 net/socket.c:2503 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2557 __sys_sendmsg+0xf7/0x1c0 net/socket.c:2586 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f5303aaabb9 Code: 28 c3 e8 2a 14 00 00 66 2e 0f 1f 84 00 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffc7506e548 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f5303aaabb9 RDX: 0000000000000000 RSI: 0000000020000180 RDI: 0000000000000003 RBP: 00007f5303a6ed60 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f5303a6edf0 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 Fixes: 8d61f926d420 ("netlink: fix potential deadlock in netlink_set_err()") Reported-by: syzbot+5da61cf6a9bc1902d422@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=5da61cf6a9bc1902d422 Suggested-by: Eric Dumazet Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230626164313.52528-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- include/net/sock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net/sock.h') diff --git a/include/net/sock.h b/include/net/sock.h index 6f428a7f3567..ad468fe71413 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2100,6 +2100,7 @@ static inline void sock_graft(struct sock *sk, struct socket *parent) } kuid_t sock_i_uid(struct sock *sk); +unsigned long __sock_i_ino(struct sock *sk); unsigned long sock_i_ino(struct sock *sk); static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk) -- cgit