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/request_sock.h | 253 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 253 insertions(+) create mode 100644 include/net/request_sock.h (limited to 'include/net/request_sock.h') diff --git a/include/net/request_sock.h b/include/net/request_sock.h new file mode 100644 index 000000000..5a9c826a7 --- /dev/null +++ b/include/net/request_sock.h @@ -0,0 +1,253 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * NET Generic infrastructure for Network protocols. + * + * Definitions for request_sock + * + * Authors: Arnaldo Carvalho de Melo + * + * From code originally in include/net/tcp.h + */ +#ifndef _REQUEST_SOCK_H +#define _REQUEST_SOCK_H + +#include +#include +#include +#include +#include + +#include +#include + +struct request_sock; +struct sk_buff; +struct dst_entry; +struct proto; + +struct request_sock_ops { + int family; + unsigned int obj_size; + struct kmem_cache *slab; + char *slab_name; + void (*send_ack)(const struct sock *sk, struct sk_buff *skb, + struct request_sock *req); + void (*send_reset)(const struct sock *sk, + struct sk_buff *skb, + enum sk_rst_reason reason); + void (*destructor)(struct request_sock *req); +}; + +struct saved_syn { + u32 mac_hdrlen; + u32 network_hdrlen; + u32 tcp_hdrlen; + u8 data[]; +}; + +/* struct request_sock - mini sock to represent a connection request + */ +struct request_sock { + struct sock_common __req_common; +#define rsk_refcnt __req_common.skc_refcnt +#define rsk_hash __req_common.skc_hash +#define rsk_listener __req_common.skc_listener +#define rsk_window_clamp __req_common.skc_window_clamp +#define rsk_rcv_wnd __req_common.skc_rcv_wnd + + struct request_sock *dl_next; + u16 mss; + u8 num_retrans; /* number of retransmits */ + u8 syncookie:1; /* True if + * 1) tcpopts needs to be encoded in + * TS of SYN+ACK + * 2) ACK is validated by BPF kfunc. + */ + u8 num_timeout:7; /* number of timeouts */ + u32 ts_recent; + struct timer_list rsk_timer; + const struct request_sock_ops *rsk_ops; + struct sock *sk; + struct saved_syn *saved_syn; + u32 secid; + u32 peer_secid; + u32 timeout; +}; + +static inline struct request_sock *inet_reqsk(const struct sock *sk) +{ + return (struct request_sock *)sk; +} + +static inline struct sock *req_to_sk(struct request_sock *req) +{ + return (struct sock *)req; +} + +/** + * skb_steal_sock - steal a socket from an sk_buff + * @skb: sk_buff to steal the socket from + * @refcounted: is set to true if the socket is reference-counted + * @prefetched: is set to true if the socket was assigned from bpf + */ +static inline struct sock *skb_steal_sock(struct sk_buff *skb, + bool *refcounted, bool *prefetched) +{ + struct sock *sk = skb->sk; + + if (!sk) { + *prefetched = false; + *refcounted = false; + return NULL; + } + + *prefetched = skb_sk_is_prefetched(skb); + if (*prefetched) { +#if IS_ENABLED(CONFIG_SYN_COOKIES) + if (sk->sk_state == TCP_NEW_SYN_RECV && inet_reqsk(sk)->syncookie) { + struct request_sock *req = inet_reqsk(sk); + + *refcounted = false; + sk = req->rsk_listener; + req->rsk_listener = NULL; + return sk; + } +#endif + *refcounted = sk_is_refcounted(sk); + } else { + *refcounted = true; + } + + skb->destructor = NULL; + skb->sk = NULL; + return sk; +} + +void __reqsk_free(struct request_sock *req); + +static inline void reqsk_free(struct request_sock *req) +{ + DEBUG_NET_WARN_ON_ONCE(refcount_read(&req->rsk_refcnt) != 0); + __reqsk_free(req); +} + +static inline void reqsk_put(struct request_sock *req) +{ + if (refcount_dec_and_test(&req->rsk_refcnt)) + __reqsk_free(req); +} + +/* + * For a TCP Fast Open listener - + * lock - protects the access to all the reqsk, which is co-owned by + * the listener and the child socket. + * qlen - pending TFO requests (still in TCP_SYN_RECV). + * max_qlen - max TFO reqs allowed before TFO is disabled. + * + * XXX (TFO) - ideally these fields can be made as part of "listen_sock" + * structure above. But there is some implementation difficulty due to + * listen_sock being part of request_sock_queue hence will be freed when + * a listener is stopped. But TFO related fields may continue to be + * accessed even after a listener is closed, until its sk_refcnt drops + * to 0 implying no more outstanding TFO reqs. One solution is to keep + * listen_opt around until sk_refcnt drops to 0. But there is some other + * complexity that needs to be resolved. E.g., a listener can be disabled + * temporarily through shutdown()->tcp_disconnect(), and re-enabled later. + */ +struct fastopen_queue { + struct request_sock *rskq_rst_head; /* Keep track of past TFO */ + struct request_sock *rskq_rst_tail; /* requests that caused RST. + * This is part of the defense + * against spoofing attack. + */ + spinlock_t lock; + int qlen; /* # of pending (TCP_SYN_RECV) reqs */ + int max_qlen; /* != 0 iff TFO is currently enabled */ + + struct tcp_fastopen_context __rcu *ctx; /* cipher context for cookie */ +}; + +/** struct request_sock_queue - queue of request_socks + * + * @rskq_accept_head - FIFO head of established children + * @rskq_accept_tail - FIFO tail of established children + * @rskq_defer_accept - User waits for some data after accept() + * + */ +struct request_sock_queue { + spinlock_t rskq_lock; + u8 rskq_defer_accept; + u8 synflood_warned; + + atomic_t qlen; + atomic_t young; + + struct request_sock *rskq_accept_head; + struct request_sock *rskq_accept_tail; + struct fastopen_queue fastopenq; /* Check max_qlen != 0 to determine + * if TFO is enabled. + */ +}; + +void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, + bool reset); + +static inline bool reqsk_queue_empty(const struct request_sock_queue *queue) +{ + return READ_ONCE(queue->rskq_accept_head) == NULL; +} + +static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue, + struct sock *parent) +{ + struct request_sock *req; + + spin_lock_bh(&queue->rskq_lock); + req = queue->rskq_accept_head; + if (req) { + sk_acceptq_removed(parent); + WRITE_ONCE(queue->rskq_accept_head, req->dl_next); + if (queue->rskq_accept_head == NULL) + queue->rskq_accept_tail = NULL; + } + spin_unlock_bh(&queue->rskq_lock); + return req; +} + +static inline void reqsk_queue_removed(struct request_sock_queue *queue, + const struct request_sock *req) +{ + if (req->num_timeout == 0) + atomic_dec(&queue->young); + atomic_dec(&queue->qlen); +} + +static inline void reqsk_queue_added(struct request_sock_queue *queue) +{ + atomic_inc(&queue->young); + atomic_inc(&queue->qlen); +} + +static inline int reqsk_queue_len(const struct request_sock_queue *queue) +{ + return atomic_read(&queue->qlen); +} + +static inline int reqsk_queue_len_young(const struct request_sock_queue *queue) +{ + return atomic_read(&queue->young); +} + +/* RFC 7323 2.3 Using the Window Scale Option + * The window field (SEG.WND) of every outgoing segment, with the + * exception of segments, MUST be right-shifted by + * Rcv.Wind.Shift bits. + * + * This means the SEG.WND carried in SYNACK can not exceed 65535. + * We use this property to harden TCP stack while in NEW_SYN_RECV state. + */ +static inline u32 tcp_synack_window(const struct request_sock *req) +{ + return min(req->rsk_rcv_wnd, 65535U); +} +#endif /* _REQUEST_SOCK_H */ -- cgit v1.3.1