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 --- net/ipv4/xfrm4_input.c | 229 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 229 insertions(+) create mode 100644 net/ipv4/xfrm4_input.c (limited to 'net/ipv4/xfrm4_input.c') diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c new file mode 100644 index 000000000..f6f2a8ef3 --- /dev/null +++ b/net/ipv4/xfrm4_input.c @@ -0,0 +1,229 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * xfrm4_input.c + * + * Changes: + * YOSHIFUJI Hideaki @USAGI + * Split up af-specific portion + * Derek Atkins + * Add Encapsulation support + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static int xfrm4_rcv_encap_finish2(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + return dst_input(skb); +} + +static inline int xfrm4_rcv_encap_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + if (!skb_dst(skb)) { + const struct iphdr *iph = ip_hdr(skb); + + if (ip_route_input_noref(skb, iph->daddr, iph->saddr, + ip4h_dscp(iph), skb->dev)) + goto drop; + } + + if (xfrm_trans_queue(skb, xfrm4_rcv_encap_finish2)) + goto drop; + + return 0; +drop: + kfree_skb(skb); + return NET_RX_DROP; +} + +int xfrm4_transport_finish(struct sk_buff *skb, int async) +{ + struct xfrm_offload *xo = xfrm_offload(skb); + struct iphdr *iph = ip_hdr(skb); + struct net_device *dev = skb->dev; + + iph->protocol = XFRM_MODE_SKB_CB(skb)->protocol; + +#ifndef CONFIG_NETFILTER + if (!async) + return -iph->protocol; +#endif + + __skb_push(skb, -skb_network_offset(skb)); + iph->tot_len = htons(skb->len); + ip_send_check(iph); + + if (xo && (xo->flags & XFRM_GRO)) { + /* The full l2 header needs to be preserved so that re-injecting the packet at l2 + * works correctly in the presence of vlan tags. + */ + skb_mac_header_rebuild_full(skb, xo->orig_mac_len); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + return 0; + } + + NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, + dev_net(dev), NULL, skb, dev, NULL, + xfrm4_rcv_encap_finish); + return 0; +} + +static int __xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb, bool pull) +{ + struct udp_sock *up = udp_sk(sk); + struct udphdr *uh; + struct iphdr *iph; + int iphlen, len; + __u8 *udpdata; + __be32 *udpdata32; + u16 encap_type; + + encap_type = READ_ONCE(up->encap_type); + /* if this is not encapsulated socket, then just return now */ + if (!encap_type) + return 1; + + /* If this is a paged skb, make sure we pull up + * whatever data we need to look at. */ + len = skb->len - sizeof(struct udphdr); + if (!pskb_may_pull(skb, sizeof(struct udphdr) + min(len, 8))) + return 1; + + /* Now we can get the pointers */ + uh = udp_hdr(skb); + udpdata = (__u8 *)uh + sizeof(struct udphdr); + udpdata32 = (__be32 *)udpdata; + + switch (encap_type) { + default: + case UDP_ENCAP_ESPINUDP: + /* Check if this is a keepalive packet. If so, eat it. */ + if (len == 1 && udpdata[0] == 0xff) { + return -EINVAL; + } else if (len > sizeof(struct ip_esp_hdr) && udpdata32[0] != 0) { + /* ESP Packet without Non-ESP header */ + len = sizeof(struct udphdr); + } else + /* Must be an IKE packet.. pass it through */ + return 1; + break; + } + + /* At this point we are sure that this is an ESPinUDP packet, + * so we need to remove 'len' bytes from the packet (the UDP + * header and optional ESP marker bytes) and then modify the + * protocol to ESP, and then call into the transform receiver. + */ + if (skb_unclone(skb, GFP_ATOMIC)) + return -EINVAL; + + /* Now we can update and verify the packet length... */ + iph = ip_hdr(skb); + iphlen = iph->ihl << 2; + iph->tot_len = htons(ntohs(iph->tot_len) - len); + if (skb->len < iphlen + len) { + /* packet is too small!?! */ + return -EINVAL; + } + + /* pull the data buffer up to the ESP header and set the + * transport header to point to ESP. Keep UDP on the stack + * for later. + */ + if (pull) { + __skb_pull(skb, len); + skb_reset_transport_header(skb); + } else { + skb_set_transport_header(skb, len); + } + + /* process ESP */ + return 0; +} + +/* If it's a keepalive packet, then just eat it. + * If it's an encapsulated packet, then pass it to the + * IPsec xfrm input. + * Returns 0 if skb passed to xfrm or was dropped. + * Returns >0 if skb should be passed to UDP. + * Returns <0 if skb should be resubmitted (-ret is protocol) + */ +int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) +{ + int ret; + + ret = __xfrm4_udp_encap_rcv(sk, skb, true); + if (!ret) + return xfrm4_rcv_encap(skb, IPPROTO_ESP, 0, + udp_sk(sk)->encap_type); + + if (ret < 0) { + kfree_skb(skb); + return 0; + } + + return ret; +} +EXPORT_SYMBOL(xfrm4_udp_encap_rcv); + +struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, + struct sk_buff *skb) +{ + int offset = skb_gro_offset(skb); + const struct net_offload *ops; + struct sk_buff *pp = NULL; + int len, dlen; + __u8 *udpdata; + __be32 *udpdata32; + + len = skb->len - offset; + dlen = offset + min(len, 8); + udpdata = skb_gro_header(skb, dlen, offset); + udpdata32 = (__be32 *)udpdata; + if (unlikely(!udpdata)) + return NULL; + + rcu_read_lock(); + ops = rcu_dereference(inet_offloads[IPPROTO_ESP]); + if (!ops || !ops->callbacks.gro_receive) + goto out; + + /* check if it is a keepalive or IKE packet */ + if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0) + goto out; + + /* set the transport header to ESP */ + skb_set_transport_header(skb, offset); + + NAPI_GRO_CB(skb)->proto = IPPROTO_UDP; + + pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); + rcu_read_unlock(); + + return pp; + +out: + rcu_read_unlock(); + NAPI_GRO_CB(skb)->same_flow = 0; + NAPI_GRO_CB(skb)->flush = 1; + + return NULL; +} +EXPORT_SYMBOL(xfrm4_gro_udp_encap_rcv); + +int xfrm4_rcv(struct sk_buff *skb) +{ + return xfrm4_rcv_spi(skb, ip_hdr(skb)->protocol, 0); +} +EXPORT_SYMBOL(xfrm4_rcv); -- cgit v1.3.1