From e45469e594b255ef8d750ed5576698743450d2ac Mon Sep 17 00:00:00 2001 From: Anna Emese Nyiri Date: Fri, 13 Dec 2024 09:44:57 +0100 Subject: sock: Introduce SO_RCVPRIORITY socket option Add new socket option, SO_RCVPRIORITY, to include SO_PRIORITY in the ancillary data returned by recvmsg(). This is analogous to the existing support for SO_RCVMARK, as implemented in commit 6fd1d51cfa253 ("net: SO_RCVMARK socket option for SO_MARK with recvmsg()"). Reviewed-by: Willem de Bruijn Suggested-by: Ferenc Fejes Signed-off-by: Anna Emese Nyiri Link: https://patch.msgid.link/20241213084457.45120-5-annaemesenyiri@gmail.com Signed-off-by: Jakub Kicinski --- net/socket.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'net/socket.c') diff --git a/net/socket.c b/net/socket.c index 9a117248f18f..16402b8be5a7 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1008,12 +1008,23 @@ static void sock_recv_mark(struct msghdr *msg, struct sock *sk, } } +static void sock_recv_priority(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) +{ + if (sock_flag(sk, SOCK_RCVPRIORITY) && skb) { + __u32 priority = skb->priority; + + put_cmsg(msg, SOL_SOCKET, SO_PRIORITY, sizeof(__u32), &priority); + } +} + void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { sock_recv_timestamp(msg, sk, skb); sock_recv_drops(msg, sk, skb); sock_recv_mark(msg, sk, skb); + sock_recv_priority(msg, sk, skb); } EXPORT_SYMBOL_GPL(__sock_recv_cmsgs); -- cgit v1.2.3 From 21520e74ba454c549f4f732d014f180f8c0c041c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 9 Jan 2025 16:49:24 -0800 Subject: net: hide the definition of dev_get_by_napi_id() There are no module callers of dev_get_by_napi_id(), and commit d1cacd747768 ("netdev: prevent accessing NAPI instances from another namespace") proves that getting NAPI by id needs to be done with care. So hide dev_get_by_napi_id(). Reviewed-by: Jacob Keller Reviewed-by: Kalesh AP Reviewed-by: Joe Damato Link: https://patch.msgid.link/20250110004924.3212260-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 - net/core/dev.c | 2 -- net/core/dev.h | 1 + net/socket.c | 2 ++ 4 files changed, 3 insertions(+), 3 deletions(-) (limited to 'net/socket.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1812564b5204..aeb4a6cff171 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3252,7 +3252,6 @@ struct net_device *netdev_get_by_index(struct net *net, int ifindex, struct net_device *netdev_get_by_name(struct net *net, const char *name, netdevice_tracker *tracker, gfp_t gfp); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); -struct net_device *dev_get_by_napi_id(unsigned int napi_id); void netdev_copy_name(struct net_device *dev, char *name); static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, diff --git a/net/core/dev.c b/net/core/dev.c index 4452ca2c91ea..1a90ed8cc6cc 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -957,7 +957,6 @@ EXPORT_SYMBOL(netdev_get_by_index); * its reference counter increased so the caller must be careful * about locking. The caller must hold RCU lock. */ - struct net_device *dev_get_by_napi_id(unsigned int napi_id) { struct napi_struct *napi; @@ -971,7 +970,6 @@ struct net_device *dev_get_by_napi_id(unsigned int napi_id) return napi ? napi->dev : NULL; } -EXPORT_SYMBOL(dev_get_by_napi_id); static DEFINE_SEQLOCK(netdev_rename_lock); diff --git a/net/core/dev.h b/net/core/dev.h index 08812a025a9b..d8966847794c 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -23,6 +23,7 @@ struct sd_flow_limit { extern int netdev_flow_limit_table_len; struct napi_struct *netdev_napi_by_id(struct net *net, unsigned int napi_id); +struct net_device *dev_get_by_napi_id(unsigned int napi_id); #ifdef CONFIG_PROC_FS int __init dev_proc_init(void); diff --git a/net/socket.c b/net/socket.c index 16402b8be5a7..4afe31656a2b 100644 --- a/net/socket.c +++ b/net/socket.c @@ -110,6 +110,8 @@ #include #include +#include "core/dev.h" + #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sysctl_net_busy_read __read_mostly; unsigned int sysctl_net_busy_poll __read_mostly; -- cgit v1.2.3 From b6be5ba8f1c6b28c2daa039fd9e9df32f62852bd Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Sun, 12 Jan 2025 13:13:18 +0000 Subject: socket: Remove unused kernel_sendmsg_locked The last use of kernel_sendmsg_locked() was removed in 2023 by commit dc97391e6610 ("sock: Remove ->sendpage*() in favour of sendmsg(MSG_SPLICE_PAGES)") Remove it. Signed-off-by: Dr. David Alan Gilbert Reviewed-by: Kalesh AP Reviewed-by: Kuniyuki Iwashima Reviewed-by: Joe Damato Link: https://patch.msgid.link/20250112131318.63753-1-linux@treblig.org Signed-off-by: Jakub Kicinski --- include/linux/net.h | 2 -- net/socket.c | 28 ---------------------------- 2 files changed, 30 deletions(-) (limited to 'net/socket.c') diff --git a/include/linux/net.h b/include/linux/net.h index b75bc534c1b3..0ff950eecc6b 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -343,8 +343,6 @@ static inline bool sendpages_ok(struct page *page, size_t len, size_t offset) int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); -int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, - struct kvec *vec, size_t num, size_t len); int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len, int flags); diff --git a/net/socket.c b/net/socket.c index 4afe31656a2b..262a28b59c7f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -776,34 +776,6 @@ int kernel_sendmsg(struct socket *sock, struct msghdr *msg, } EXPORT_SYMBOL(kernel_sendmsg); -/** - * kernel_sendmsg_locked - send a message through @sock (kernel-space) - * @sk: sock - * @msg: message header - * @vec: output s/g array - * @num: output s/g array length - * @size: total message data size - * - * Builds the message data with @vec and sends it through @sock. - * Returns the number of bytes sent, or an error code. - * Caller must hold @sk. - */ - -int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, - struct kvec *vec, size_t num, size_t size) -{ - struct socket *sock = sk->sk_socket; - const struct proto_ops *ops = READ_ONCE(sock->ops); - - if (!ops->sendmsg_locked) - return sock_no_sendmsg_locked(sk, msg, size); - - iov_iter_kvec(&msg->msg_iter, ITER_SOURCE, vec, num, size); - - return ops->sendmsg_locked(sk, msg, msg_data_left(msg)); -} -EXPORT_SYMBOL(kernel_sendmsg_locked); - static bool skb_is_err_queue(const struct sk_buff *skb) { /* pkt_type of skbs enqueued on the error queue are set to -- cgit v1.2.3 From 2a42754b3104d78a2bc7a2ad8844427411c76ca6 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 3 Feb 2025 23:32:04 +0100 Subject: fsnotify: disable notification by default for all pseudo files Most pseudo files are not applicable for fsnotify events at all, let alone to the new pre-content events. Disable notifications to all files allocated with alloc_file_pseudo() and enable legacy inotify events for the specific cases of pipe and socket, which have known users of inotify events. Pre-content events are also kept disabled for sockets and pipes. Fixes: 20bf82a898b6 ("mm: don't allow huge faults for files with pre content watches") Reported-by: Alex Williamson Closes: https://lore.kernel.org/linux-fsdevel/20250131121703.1e4d00a7.alex.williamson@redhat.com/ Suggested-by: Linus Torvalds Link: https://lore.kernel.org/linux-fsdevel/CAHk-=wi2pThSVY=zhO=ZKxViBj5QCRX-=AS2+rVknQgJnHXDFg@mail.gmail.com/ Tested-by: Alex Williamson Signed-off-by: Amir Goldstein Link: https://lore.kernel.org/r/20250203223205.861346-3-amir73il@gmail.com Signed-off-by: Christian Brauner --- fs/file_table.c | 11 +++++++++++ fs/open.c | 4 ++-- fs/pipe.c | 6 ++++++ net/socket.c | 5 +++++ 4 files changed, 24 insertions(+), 2 deletions(-) (limited to 'net/socket.c') diff --git a/fs/file_table.c b/fs/file_table.c index f0291a66f9db..35b93da6c5cb 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -375,7 +375,13 @@ struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt, if (IS_ERR(file)) { ihold(inode); path_put(&path); + return file; } + /* + * Disable all fsnotify events for pseudo files by default. + * They may be enabled by caller with file_set_fsnotify_mode(). + */ + file_set_fsnotify_mode(file, FMODE_NONOTIFY); return file; } EXPORT_SYMBOL(alloc_file_pseudo); @@ -400,6 +406,11 @@ struct file *alloc_file_pseudo_noaccount(struct inode *inode, return file; } file_init_path(file, &path, fops); + /* + * Disable all fsnotify events for pseudo files by default. + * They may be enabled by caller with file_set_fsnotify_mode(). + */ + file_set_fsnotify_mode(file, FMODE_NONOTIFY); return file; } EXPORT_SYMBOL_GPL(alloc_file_pseudo_noaccount); diff --git a/fs/open.c b/fs/open.c index 3fcbfff8aede..1be20de9f283 100644 --- a/fs/open.c +++ b/fs/open.c @@ -936,8 +936,8 @@ static int do_dentry_open(struct file *f, /* * Set FMODE_NONOTIFY_* bits according to existing permission watches. - * If FMODE_NONOTIFY was already set for an fanotify fd, this doesn't - * change anything. + * If FMODE_NONOTIFY mode was already set for an fanotify fd or for a + * pseudo file, this call will not change the mode. */ file_set_fsnotify_mode_from_watchers(f); error = fsnotify_open_perm(f); diff --git a/fs/pipe.c b/fs/pipe.c index 94b59045ab44..ce1af7592780 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -960,6 +960,12 @@ int create_pipe_files(struct file **res, int flags) res[1] = f; stream_open(inode, res[0]); stream_open(inode, res[1]); + /* + * Disable permission and pre-content events, but enable legacy + * inotify events for legacy users. + */ + file_set_fsnotify_mode(res[0], FMODE_NONOTIFY_PERM); + file_set_fsnotify_mode(res[1], FMODE_NONOTIFY_PERM); return 0; } diff --git a/net/socket.c b/net/socket.c index 262a28b59c7f..28bae5a94234 100644 --- a/net/socket.c +++ b/net/socket.c @@ -479,6 +479,11 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) sock->file = file; file->private_data = sock; stream_open(SOCK_INODE(sock), file); + /* + * Disable permission and pre-content events, but enable legacy + * inotify events for legacy users. + */ + file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM); return file; } EXPORT_SYMBOL(sock_alloc_file); -- cgit v1.2.3