From 034dd340b08be1f2f0477ad16131d609f9dbd53c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 30 Aug 2026 09:22:00 -0700 Subject: Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Fix error output of boot instance creation failure Currently if a boot instance creation fails, instead of printing out the name of the instance that failed, it prints "(null)". That is because it prints "cur_str" that had already been processed by strsep(). Print the saved name instead. While at it, print the error code of the failure. - Fix use-after-free for same named historgrams Histograms can be named so that they can be used in multiple events. But if the named histogram has a variable attached, the second event that uses the named histogram which duplicates it and needs to free the original after duplication leaves the old variable in place and still visible. If another histogram uses than variable, it will use the stale one which will try to reference the freed duplicate histogram and crash the kernel. Free the duplicate variables along with the duplicated histogram data. - Check return value of kthread_run() in event self test The events self tests uses a kthread for testing but does not check if it succeeded in creating a kthread. If the kthread creation were to fail, the code will still try to call kthread_stop() on the error returned. - Fix race between reading trace_pipe and updating subbuffer size If a user is reading the trace_pipe file at the same time they update the ring buffer sub-buffer size, can cause the trace_pipe read to read stale data. Add trace_access_lock() around updating the ring buffer sub-buffer size. - Fix eventfs_inode on failure path in creation of the events directory In the creation of the "events" directory, if after allocating the eventfs_inode a failure is detected, it calls cleanup_ei() which calls free_ei(). The free_ei() will test if eventfs_inode being freed has no children. It is a bug if it does. But on the failure case of the creation of the "events" directory, the children lists have not yet been initialized and the free will trigger a warning because list_empty() on an uninitialized list returns false. Move the initialization into init_ei() where it makes more sense and makes sure that a created eventfs_inode has its lists initialized upon creation. - Check return value of kthread_run() in ftrace direct sample code The sample code that shows how to use the ftrace direct calls does not test the return of kthread_run() to see if it succeeds. Return a failure if the kthread_run() doesn't succeed. - Clear user events state on fork in case of alloc failure On fork, the child gets a pointer to the parent's user events state. It makes a copy of it then updates the child's pointer to it. But if the allocation fails, the duplication function leaves the child with a pointer to its parent's descriptor. When the child cleans up its data, it will free the parent's descriptor while the parent is still using it. In the duplication function, set the child's user_event_mm to NULL before testing if the allocation succeeded, and when it exits it will not free the parent's descriptor. - Fix retry exhaustion in simple ring buffer reader swap simple_ring_buffer_swap_reader_page() starts with retry set to 8 and post-decrements it only after a failed link replacement. On the final attempt, a successful replacement leaves retry at zero, while a failed replacement leaves it at -1. But the check for success expects the retry value to be non-zero and exits with an error on zero. This is the opposite result. Fix it. - Fail nicely when the remote swap_reader_page() returns an error Currently, if the swap_reader_page() of a remote buffer fails, it triggers a WARN_ON_ONCE() and continues normally. Instead, have it exit with an error and a pr_warn() print instead of a full WARNING. * tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: ring-buffer: Stop remote reader update when page swap fails tracing: Fix retry exhaustion in simple ring buffer reader swap tracing/user_events: Clear copied tracing state before fork duplication samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify eventfs: Initialize ei->children and ei->list in init_ei() tracing: Fix use-after-free in trace_pipe read on sub-buffer order change tracing: Fix crash passing ERR_PTR to kthread_stop() tracing: Fix use-after-free with same-name named triggers tracing: Fix logged instance name on creation failure --- include/net/af_vsock.h | 330 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 330 insertions(+) create mode 100644 include/net/af_vsock.h (limited to 'include/net/af_vsock.h') diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h new file mode 100644 index 000000000..3357ee62d --- /dev/null +++ b/include/net/af_vsock.h @@ -0,0 +1,330 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * VMware vSockets Driver + * + * Copyright (C) 2007-2013 VMware, Inc. All rights reserved. + */ + +#ifndef __AF_VSOCK_H__ +#define __AF_VSOCK_H__ + +#include +#include +#include +#include +#include + +#include "vsock_addr.h" + +#define LAST_RESERVED_PORT 1023 + +#define VSOCK_HASH_SIZE 251 +extern struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1]; +extern struct list_head vsock_connected_table[VSOCK_HASH_SIZE]; +extern spinlock_t vsock_table_lock; + +#define vsock_sk(__sk) ((struct vsock_sock *)__sk) +#define sk_vsock(__vsk) (&(__vsk)->sk) + +struct vsock_sock { + /* sk must be the first member. */ + struct sock sk; + const struct vsock_transport *transport; + struct sockaddr_vm local_addr; + struct sockaddr_vm remote_addr; + /* Links for the global tables of bound and connected sockets. */ + struct list_head bound_table; + struct list_head connected_table; + /* Accessed without the socket lock held. This means it can never be + * modified outsided of socket create or destruct. + */ + bool trusted; + bool cached_peer_allow_dgram; /* Dgram communication allowed to + * cached peer? + */ + u32 cached_peer; /* Context ID of last dgram destination check. */ + const struct cred *owner; + /* Rest are SOCK_STREAM only. */ + long connect_timeout; + /* Listening socket that this came from. */ + struct sock *listener; + /* Used for pending list and accept queue during connection handshake. + * The listening socket is the head for both lists. Sockets created + * for connection requests are placed in the pending list until they + * are connected, at which point they are put in the accept queue list + * so they can be accepted in accept(). + */ + struct list_head pending_links; + struct list_head accept_queue; + struct delayed_work connect_work; + struct delayed_work pending_work; + struct delayed_work close_work; + bool close_work_scheduled; + u32 peer_shutdown; + bool sent_request; + bool ignore_connecting_rst; + + /* Protected by lock_sock(sk) */ + u64 buffer_size; + u64 buffer_min_size; + u64 buffer_max_size; + + /* Private to transport. */ + void *trans; +}; + +s64 vsock_connectible_has_data(struct vsock_sock *vsk); +s64 vsock_stream_has_data(struct vsock_sock *vsk); +s64 vsock_stream_has_space(struct vsock_sock *vsk); +struct sock *vsock_create_connected(struct sock *parent); +void vsock_data_ready(struct sock *sk); + +/**** TRANSPORT ****/ + +struct vsock_transport_recv_notify_data { + u64 data1; /* Transport-defined. */ + u64 data2; /* Transport-defined. */ + bool notify_on_block; +}; + +struct vsock_transport_send_notify_data { + u64 data1; /* Transport-defined. */ + u64 data2; /* Transport-defined. */ +}; + +/* Transport features flags */ +/* Transport provides host->guest communication */ +#define VSOCK_TRANSPORT_F_H2G 0x00000001 +/* Transport provides guest->host communication */ +#define VSOCK_TRANSPORT_F_G2H 0x00000002 +/* Transport provides DGRAM communication */ +#define VSOCK_TRANSPORT_F_DGRAM 0x00000004 +/* Transport provides local (loopback) communication */ +#define VSOCK_TRANSPORT_F_LOCAL 0x00000008 + +struct vsock_transport { + struct module *module; + + /* Initialize/tear-down socket. */ + int (*init)(struct vsock_sock *, struct vsock_sock *); + void (*destruct)(struct vsock_sock *); + void (*release)(struct vsock_sock *); + + /* Cancel all pending packets sent on vsock. */ + int (*cancel_pkt)(struct vsock_sock *vsk); + + /* Connections. */ + int (*connect)(struct vsock_sock *); + + /* DGRAM. */ + int (*dgram_bind)(struct vsock_sock *, struct sockaddr_vm *); + int (*dgram_dequeue)(struct vsock_sock *vsk, struct msghdr *msg, + size_t len, int flags); + int (*dgram_enqueue)(struct vsock_sock *, struct sockaddr_vm *, + struct msghdr *, size_t len); + bool (*dgram_allow)(struct vsock_sock *vsk, u32 cid, u32 port); + + /* STREAM. */ + /* TODO: stream_bind() */ + ssize_t (*stream_dequeue)(struct vsock_sock *, struct msghdr *, + size_t len, int flags); + ssize_t (*stream_enqueue)(struct vsock_sock *, struct msghdr *, + size_t len); + s64 (*stream_has_data)(struct vsock_sock *); + s64 (*stream_has_space)(struct vsock_sock *); + u64 (*stream_rcvhiwat)(struct vsock_sock *); + bool (*stream_is_active)(struct vsock_sock *); + bool (*stream_allow)(struct vsock_sock *vsk, u32 cid, u32 port); + + /* SEQ_PACKET. */ + ssize_t (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg, + int flags); + int (*seqpacket_enqueue)(struct vsock_sock *vsk, struct msghdr *msg, + size_t len); + bool (*seqpacket_allow)(struct vsock_sock *vsk, u32 remote_cid); + u32 (*seqpacket_has_data)(struct vsock_sock *vsk); + + /* Notification. */ + int (*notify_poll_in)(struct vsock_sock *, size_t, bool *); + int (*notify_poll_out)(struct vsock_sock *, size_t, bool *); + int (*notify_recv_init)(struct vsock_sock *, size_t, + struct vsock_transport_recv_notify_data *); + int (*notify_recv_pre_block)(struct vsock_sock *, size_t, + struct vsock_transport_recv_notify_data *); + int (*notify_recv_pre_dequeue)(struct vsock_sock *, size_t, + struct vsock_transport_recv_notify_data *); + int (*notify_recv_post_dequeue)(struct vsock_sock *, size_t, + ssize_t, bool, struct vsock_transport_recv_notify_data *); + int (*notify_send_init)(struct vsock_sock *, + struct vsock_transport_send_notify_data *); + int (*notify_send_pre_block)(struct vsock_sock *, + struct vsock_transport_send_notify_data *); + int (*notify_send_pre_enqueue)(struct vsock_sock *, + struct vsock_transport_send_notify_data *); + int (*notify_send_post_enqueue)(struct vsock_sock *, ssize_t, + struct vsock_transport_send_notify_data *); + /* sk_lock held by the caller */ + void (*notify_buffer_size)(struct vsock_sock *, u64 *); + int (*notify_set_rcvlowat)(struct vsock_sock *vsk, int val); + + /* SIOCOUTQ ioctl */ + ssize_t (*unsent_bytes)(struct vsock_sock *vsk); + + /* Shutdown. */ + int (*shutdown)(struct vsock_sock *, int); + + /* Addressing. */ + u32 (*get_local_cid)(void); + + /* Check if this transport serves a specific remote CID. + * For H2G transports: return true if the CID belongs to a registered + * guest. If not implemented, all CIDs > VMADDR_CID_HOST go to H2G. + * For G2H transports: return true if the transport can reach arbitrary + * CIDs via the hypervisor (i.e. supports the fallback overlay). VMCI + * does not implement this as it only serves CIDs 0 and 2. + */ + bool (*has_remote_cid)(struct vsock_sock *vsk, u32 remote_cid); + + /* Read a single skb */ + int (*read_skb)(struct vsock_sock *, skb_read_actor_t); + + /* Zero-copy. */ + bool (*msgzerocopy_allow)(void); +}; + +/**** CORE ****/ + +int vsock_core_register(const struct vsock_transport *t, int features); +void vsock_core_unregister(const struct vsock_transport *t); + +/* The transport may downcast this to access transport-specific functions */ +const struct vsock_transport *vsock_core_get_transport(struct vsock_sock *vsk); + +/**** UTILS ****/ + +/* vsock_table_lock must be held */ +static inline bool __vsock_in_bound_table(struct vsock_sock *vsk) +{ + return !list_empty(&vsk->bound_table); +} + +/* vsock_table_lock must be held */ +static inline bool __vsock_in_connected_table(struct vsock_sock *vsk) +{ + return !list_empty(&vsk->connected_table); +} + +void vsock_add_pending(struct sock *listener, struct sock *pending); +void vsock_remove_pending(struct sock *listener, struct sock *pending); +void vsock_enqueue_accept(struct sock *listener, struct sock *connected); +void vsock_pending_to_accept(struct sock *listener, struct sock *pending); +void vsock_insert_connected(struct vsock_sock *vsk); +void vsock_remove_bound(struct vsock_sock *vsk); +void vsock_remove_connected(struct vsock_sock *vsk); +struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr); +struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, + struct sockaddr_vm *dst); +struct sock *vsock_find_bound_socket_net(struct sockaddr_vm *addr, + struct net *net); +struct sock *vsock_find_connected_socket_net(struct sockaddr_vm *src, + struct sockaddr_vm *dst, + struct net *net); +void vsock_remove_sock(struct vsock_sock *vsk); +void vsock_for_each_connected_socket(struct vsock_transport *transport, + void (*fn)(struct sock *sk)); +int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk); +bool vsock_find_cid(unsigned int cid); +void vsock_linger(struct sock *sk); + +/**** TAP ****/ + +struct vsock_tap { + struct net_device *dev; + struct module *module; + struct list_head list; +}; + +int vsock_add_tap(struct vsock_tap *vt); +int vsock_remove_tap(struct vsock_tap *vt); +void vsock_deliver_tap(struct sk_buff *build_skb(void *opaque), void *opaque); +int __vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags); +int vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags); +int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags); +int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags); + +extern struct proto vsock_proto; +#ifdef CONFIG_BPF_SYSCALL +int vsock_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); +void __init vsock_bpf_build_proto(void); +#else +static inline void __init vsock_bpf_build_proto(void) +{} +#endif + +static inline bool vsock_msgzerocopy_allow(const struct vsock_transport *t) +{ + return t->msgzerocopy_allow && t->msgzerocopy_allow(); +} + +static inline enum vsock_net_mode vsock_net_mode(struct net *net) +{ + if (!net) + return VSOCK_NET_MODE_GLOBAL; + + return READ_ONCE(net->vsock.mode); +} + +static inline bool vsock_net_mode_global(struct vsock_sock *vsk) +{ + return vsock_net_mode(sock_net(sk_vsock(vsk))) == VSOCK_NET_MODE_GLOBAL; +} + +static inline bool vsock_net_set_child_mode(struct net *net, + enum vsock_net_mode mode) +{ + int new_locked = mode + 1; + int old_locked = 0; /* unlocked */ + + if (try_cmpxchg(&net->vsock.child_ns_mode_locked, + &old_locked, new_locked)) { + WRITE_ONCE(net->vsock.child_ns_mode, mode); + return true; + } + + return old_locked == new_locked; +} + +static inline enum vsock_net_mode vsock_net_child_mode(struct net *net) +{ + return READ_ONCE(net->vsock.child_ns_mode); +} + +/* Return true if two namespaces pass the mode rules. Otherwise, return false. + * + * A NULL namespace is treated as VSOCK_NET_MODE_GLOBAL. + * + * Read more about modes in the comment header of net/vmw_vsock/af_vsock.c. + */ +static inline bool vsock_net_check_mode(struct net *ns0, struct net *ns1) +{ + enum vsock_net_mode mode0, mode1; + + /* Any vsocks within the same network namespace are always reachable, + * regardless of the mode. + */ + if (net_eq(ns0, ns1)) + return true; + + mode0 = vsock_net_mode(ns0); + mode1 = vsock_net_mode(ns1); + + /* Different namespaces are only reachable if they are both + * global mode. + */ + return mode0 == VSOCK_NET_MODE_GLOBAL && mode0 == mode1; +} +#endif /* __AF_VSOCK_H__ */ -- cgit v1.3.1