From ed779fe4c9b5a20b4ab4fd6f3e19807445bb78c7 Mon Sep 17 00:00:00 2001 From: Qingfang DENG Date: Thu, 1 Jun 2023 09:54:32 +0800 Subject: neighbour: fix unaligned access to pneigh_entry After the blamed commit, the member key is longer 4-byte aligned. On platforms that do not support unaligned access, e.g., MIPS32R2 with unaligned_action set to 1, this will trigger a crash when accessing an IPv6 pneigh_entry, as the key is cast to an in6_addr pointer. Change the type of the key to u32 to make it aligned. Fixes: 62dd93181aaa ("[IPV6] NDISC: Set per-entry is_router flag in Proxy NA.") Signed-off-by: Qingfang DENG Link: https://lore.kernel.org/r/20230601015432.159066-1-dqfext@gmail.com Signed-off-by: Jakub Kicinski --- include/net/neighbour.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 3fa5774bddac..f6a8ecc6b1fa 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -180,7 +180,7 @@ struct pneigh_entry { netdevice_tracker dev_tracker; u32 flags; u8 protocol; - u8 key[]; + u32 key[]; }; /* -- cgit v1.2.3 From e209fee4118fe9a449d4d805361eb2de6796be39 Mon Sep 17 00:00:00 2001 From: Akihiro Suda Date: Thu, 1 Jun 2023 12:13:05 +0900 Subject: net/ipv4: ping_group_range: allow GID from 2147483648 to 4294967294 With this commit, all the GIDs ("0 4294967294") can be written to the "net.ipv4.ping_group_range" sysctl. Note that 4294967295 (0xffffffff) is an invalid GID (see gid_valid() in include/linux/uidgid.h), and an attempt to register this number will cause -EINVAL. Prior to this commit, only up to GID 2147483647 could be covered. Documentation/networking/ip-sysctl.rst had "0 4294967295" as an example value, but this example was wrong and causing -EINVAL. Fixes: c319b4d76b9e ("net: ipv4: add IPPROTO_ICMP socket kind") Co-developed-by: Kuniyuki Iwashima Signed-off-by: Kuniyuki Iwashima Signed-off-by: Akihiro Suda Signed-off-by: David S. Miller --- include/net/ping.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/ping.h b/include/net/ping.h index 9233ad3de0ad..bc7779262e60 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -16,11 +16,7 @@ #define PING_HTABLE_SIZE 64 #define PING_HTABLE_MASK (PING_HTABLE_SIZE-1) -/* - * gid_t is either uint or ushort. We want to pass it to - * proc_dointvec_minmax(), so it must not be larger than MAX_INT - */ -#define GID_T_MAX (((gid_t)~0U) >> 1) +#define GID_T_MAX (((gid_t)~0U) - 1) /* Compatibility glue so we can support IPv6 when it's compiled as a module */ struct pingv6_ops { -- cgit v1.2.3 From edf2e1d2019b2730d6076dbe4c040d37d7c10bbe Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 1 Jun 2023 16:04:44 +0000 Subject: net/ipv6: fix bool/int mismatch for skip_notify_on_dev_down skip_notify_on_dev_down ctl table expects this field to be an int (4 bytes), not a bool (1 byte). Because proc_dou8vec_minmax() was added in 5.13, this patch converts skip_notify_on_dev_down to an int. Following patch then converts the field to u8 and use proc_dou8vec_minmax(). Fixes: 7c6bb7d2faaf ("net/ipv6: Add knob to skip DELROUTE message on device down") Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Acked-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- include/net/netns/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 3cceb3e9320b..d44b2ee49698 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -53,7 +53,7 @@ struct netns_sysctl_ipv6 { int seg6_flowlabel; u32 ioam6_id; u64 ioam6_id_wide; - bool skip_notify_on_dev_down; + int skip_notify_on_dev_down; u8 fib_notify_on_flag_change; u8 icmpv6_error_anycast_as_unicast; }; -- cgit v1.2.3 From ef62c0ae6db11c095880e473db9f846132d7eba8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 1 Jun 2023 16:04:45 +0000 Subject: net/ipv6: convert skip_notify_on_dev_down sysctl to u8 Save a bit a space, and could help future sysctls to use the same pattern. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Acked-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- include/net/netns/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index d44b2ee49698..5f2cfd84570a 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -53,7 +53,7 @@ struct netns_sysctl_ipv6 { int seg6_flowlabel; u32 ioam6_id; u64 ioam6_id_wide; - int skip_notify_on_dev_down; + u8 skip_notify_on_dev_down; u8 fib_notify_on_flag_change; u8 icmpv6_error_anycast_as_unicast; }; -- cgit v1.2.3 From 132328e8e85174ea788faf8f627c33258c88fbad Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 5 Jun 2023 15:14:45 +0200 Subject: bpf: netfilter: Add BPF_NETFILTER bpf_attach_type Andrii Nakryiko writes: And we currently don't have an attach type for NETLINK BPF link. Thankfully it's not too late to add it. I see that link_create() in kernel/bpf/syscall.c just bypasses attach_type check. We shouldn't have done that. Instead we need to add BPF_NETLINK attach type to enum bpf_attach_type. And wire all that properly throughout the kernel and libbpf itself. This adds BPF_NETFILTER and uses it. This breaks uabi but this wasn't in any non-rc release yet, so it should be fine. v2: check link_attack prog type in link_create too Fixes: 84601d6ee68a ("bpf: add bpf_link support for BPF_NETFILTER programs") Suggested-by: Andrii Nakryiko Signed-off-by: Florian Westphal Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/CAEf4BzZ69YgrQW7DHCJUT_X+GqMq_ZQQPBwopaJJVGFD5=d5Vg@mail.gmail.com/ Link: https://lore.kernel.org/bpf/20230605131445.32016-1-fw@strlen.de --- include/uapi/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1bb11a6ee667..c994ff5b157c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1035,6 +1035,7 @@ enum bpf_attach_type { BPF_TRACE_KPROBE_MULTI, BPF_LSM_CGROUP, BPF_STRUCT_OPS, + BPF_NETFILTER, __MAX_BPF_ATTACH_TYPE }; -- cgit v1.2.3 From 1857c19941c87eb36ad47f22a406be5dfe5eff9f Mon Sep 17 00:00:00 2001 From: Zhengping Jiang Date: Wed, 24 May 2023 17:11:58 -0700 Subject: Bluetooth: hci_sync: add lock to protect HCI_UNREGISTER When the HCI_UNREGISTER flag is set, no jobs should be scheduled. Fix potential race when HCI_UNREGISTER is set after the flag is tested in hci_cmd_sync_queue. Fixes: 0b94f2651f56 ("Bluetooth: hci_sync: Fix queuing commands when HCI_UNREGISTER is set") Signed-off-by: Zhengping Jiang Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 8baf34639939..fe3893855cd2 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -515,6 +515,7 @@ struct hci_dev { struct work_struct cmd_sync_work; struct list_head cmd_sync_work_list; struct mutex cmd_sync_work_lock; + struct mutex unregister_lock; struct work_struct cmd_sync_cancel_work; struct work_struct reenable_adv_work; -- cgit v1.2.3 From fe2ccc6c29d53e14d3c8b3ddf8ad965a92e074ee Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 31 May 2023 10:57:58 +0200 Subject: Bluetooth: fix debugfs registration Since commit ec6cef9cd98d ("Bluetooth: Fix SMP channel registration for unconfigured controllers") the debugfs interface for unconfigured controllers will be created when the controller is configured. There is however currently nothing preventing a controller from being configured multiple time (e.g. setting the device address using btmgmt) which results in failed attempts to register the already registered debugfs entries: debugfs: File 'features' in directory 'hci0' already present! debugfs: File 'manufacturer' in directory 'hci0' already present! debugfs: File 'hci_version' in directory 'hci0' already present! ... debugfs: File 'quirk_simultaneous_discovery' in directory 'hci0' already present! Add a controller flag to avoid trying to register the debugfs interface more than once. Fixes: ec6cef9cd98d ("Bluetooth: Fix SMP channel registration for unconfigured controllers") Cc: stable@vger.kernel.org # 4.0 Signed-off-by: Johan Hovold Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 07df96c47ef4..872dcb91a540 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -350,6 +350,7 @@ enum { enum { HCI_SETUP, HCI_CONFIG, + HCI_DEBUGFS_CREATED, HCI_AUTO_OFF, HCI_RFKILLED, HCI_MGMT, -- cgit v1.2.3 From 71e9588435c38112d6a8686d3d8e7cc1de8fe22c Mon Sep 17 00:00:00 2001 From: Pauli Virtanen Date: Thu, 1 Jun 2023 09:34:45 +0300 Subject: Bluetooth: ISO: use correct CIS order in Set CIG Parameters event The order of CIS handle array in Set CIG Parameters response shall match the order of the CIS_ID array in the command (Core v5.3 Vol 4 Part E Sec 7.8.97). We send CIS_IDs mainly in the order of increasing CIS_ID (but with "last" CIS first if it has fixed CIG_ID). In handling of the reply, we currently assume this is also the same as the order of hci_conn in hdev->conn_hash, but that is not true. Match the correct hci_conn to the correct handle by matching them based on the CIG+CIS combination. The CIG+CIS combination shall be unique for ISO_LINK hci_conn at state >= BT_BOUND, which we maintain in hci_le_set_cig_params. Fixes: 26afbd826ee3 ("Bluetooth: Add initial implementation of CIS connections") Signed-off-by: Pauli Virtanen Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index fe3893855cd2..9654567cfae3 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1202,7 +1202,8 @@ static inline struct hci_conn *hci_conn_hash_lookup_cis(struct hci_dev *hdev, if (id != BT_ISO_QOS_CIS_UNSET && id != c->iso_qos.ucast.cis) continue; - if (ba_type == c->dst_type && !bacmp(&c->dst, ba)) { + /* Match destination address if set */ + if (!ba || (ba_type == c->dst_type && !bacmp(&c->dst, ba))) { rcu_read_unlock(); return c; } -- cgit v1.2.3 From a2f4c143d76b1a47c91ef9bc46907116b111da0b Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 5 Jun 2023 11:06:17 -0700 Subject: ipv6: rpl: Fix Route of Death. A remote DoS vulnerability of RPL Source Routing is assigned CVE-2023-2156. The Source Routing Header (SRH) has the following format: 0 1 2 3 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Next Header | Hdr Ext Len | Routing Type | Segments Left | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | CmprI | CmprE | Pad | Reserved | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | . . . Addresses[1..n] . . . | | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ The originator of an SRH places the first hop's IPv6 address in the IPv6 header's IPv6 Destination Address and the second hop's IPv6 address as the first address in Addresses[1..n]. The CmprI and CmprE fields indicate the number of prefix octets that are shared with the IPv6 Destination Address. When CmprI or CmprE is not 0, Addresses[1..n] are compressed as follows: 1..n-1 : (16 - CmprI) bytes n : (16 - CmprE) bytes Segments Left indicates the number of route segments remaining. When the value is not zero, the SRH is forwarded to the next hop. Its address is extracted from Addresses[n - Segment Left + 1] and swapped with IPv6 Destination Address. When Segment Left is greater than or equal to 2, the size of SRH is not changed because Addresses[1..n-1] are decompressed and recompressed with CmprI. OTOH, when Segment Left changes from 1 to 0, the new SRH could have a different size because Addresses[1..n-1] are decompressed with CmprI and recompressed with CmprE. Let's say CmprI is 15 and CmprE is 0. When we receive SRH with Segment Left >= 2, Addresses[1..n-1] have 1 byte for each, and Addresses[n] has 16 bytes. When Segment Left is 1, Addresses[1..n-1] is decompressed to 16 bytes and not recompressed. Finally, the new SRH will need more room in the header, and the size is (16 - 1) * (n - 1) bytes. Here the max value of n is 255 as Segment Left is u8, so in the worst case, we have to allocate 3825 bytes in the skb headroom. However, now we only allocate a small fixed buffer that is IPV6_RPL_SRH_WORST_SWAP_SIZE (16 + 7 bytes). If the decompressed size overflows the room, skb_push() hits BUG() below [0]. Instead of allocating the fixed buffer for every packet, let's allocate enough headroom only when we receive SRH with Segment Left 1. [0]: skbuff: skb_under_panic: text:ffffffff81c9f6e2 len:576 put:576 head:ffff8880070b5180 data:ffff8880070b4fb0 tail:0x70 end:0x140 dev:lo kernel BUG at net/core/skbuff.c:200! invalid opcode: 0000 [#1] PREEMPT SMP PTI CPU: 0 PID: 154 Comm: python3 Not tainted 6.4.0-rc4-00190-gc308e9ec0047 #7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 RIP: 0010:skb_panic (net/core/skbuff.c:200) Code: 4f 70 50 8b 87 bc 00 00 00 50 8b 87 b8 00 00 00 50 ff b7 c8 00 00 00 4c 8b 8f c0 00 00 00 48 c7 c7 80 6e 77 82 e8 ad 8b 60 ff <0f> 0b 66 66 2e 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90 90 90 90 RSP: 0018:ffffc90000003da0 EFLAGS: 00000246 RAX: 0000000000000085 RBX: ffff8880058a6600 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff88807dc1c540 RDI: ffff88807dc1c540 RBP: ffffc90000003e48 R08: ffffffff82b392c8 R09: 00000000ffffdfff R10: ffffffff82a592e0 R11: ffffffff82b092e0 R12: ffff888005b1c800 R13: ffff8880070b51b8 R14: ffff888005b1ca18 R15: ffff8880070b5190 FS: 00007f4539f0b740(0000) GS:ffff88807dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055670baf3000 CR3: 0000000005b0e000 CR4: 00000000007506f0 PKRU: 55555554 Call Trace: skb_push (net/core/skbuff.c:210) ipv6_rthdr_rcv (./include/linux/skbuff.h:2880 net/ipv6/exthdrs.c:634 net/ipv6/exthdrs.c:718) ip6_protocol_deliver_rcu (net/ipv6/ip6_input.c:437 (discriminator 5)) ip6_input_finish (./include/linux/rcupdate.h:805 net/ipv6/ip6_input.c:483) __netif_receive_skb_one_core (net/core/dev.c:5494) process_backlog (./include/linux/rcupdate.h:805 net/core/dev.c:5934) __napi_poll (net/core/dev.c:6496) net_rx_action (net/core/dev.c:6565 net/core/dev.c:6696) __do_softirq (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/irq.h:142 kernel/softirq.c:572) do_softirq (kernel/softirq.c:472 kernel/softirq.c:459) __local_bh_enable_ip (kernel/softirq.c:396) __dev_queue_xmit (net/core/dev.c:4272) ip6_finish_output2 (./include/net/neighbour.h:544 net/ipv6/ip6_output.c:134) rawv6_sendmsg (./include/net/dst.h:458 ./include/linux/netfilter.h:303 net/ipv6/raw.c:656 net/ipv6/raw.c:914) sock_sendmsg (net/socket.c:724 net/socket.c:747) __sys_sendto (net/socket.c:2144) __x64_sys_sendto (net/socket.c:2156 net/socket.c:2152 net/socket.c:2152) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) RIP: 0033:0x7f453a138aea Code: d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 f3 0f 1e fa 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 15 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 7e c3 0f 1f 44 00 00 41 54 48 83 ec 30 44 89 RSP: 002b:00007ffcc212a1c8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00007ffcc212a288 RCX: 00007f453a138aea RDX: 0000000000000060 RSI: 00007f4539084c20 RDI: 0000000000000003 RBP: 00007f4538308e80 R08: 00007ffcc212a300 R09: 000000000000001c R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: ffffffffc4653600 R14: 0000000000000001 R15: 00007f4539712d1b Modules linked in: Fixes: 8610c7c6e3bd ("net: ipv6: add support for rpl sr exthdr") Reported-by: Max VA Closes: https://www.interruptlabs.co.uk/articles/linux-ipv6-route-of-death Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230605180617.67284-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- include/net/rpl.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/rpl.h b/include/net/rpl.h index 308ef0a05cae..30fe780d1e7c 100644 --- a/include/net/rpl.h +++ b/include/net/rpl.h @@ -23,9 +23,6 @@ static inline int rpl_init(void) static inline void rpl_exit(void) {} #endif -/* Worst decompression memory usage ipv6 address (16) + pad 7 */ -#define IPV6_RPL_SRH_WORST_SWAP_SIZE (sizeof(struct in6_addr) + 7) - size_t ipv6_rpl_srh_size(unsigned char n, unsigned char cmpri, unsigned char cmpre); -- cgit v1.2.3 From 1e5c647c3f6d4f8497dedcd226204e1880e0ffb3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Jun 2023 07:41:14 +0000 Subject: rfs: annotate lockless accesses to sk->sk_rxhash Add READ_ONCE()/WRITE_ONCE() on accesses to sk->sk_rxhash. This also prevents a (smart ?) compiler to remove the condition in: if (sk->sk_rxhash != newval) sk->sk_rxhash = newval; We need the condition to avoid dirtying a shared cache line. Fixes: fec5e652e58f ("rfs: Receive Flow Steering") Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/net/sock.h | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index b418425d7230..6f428a7f3567 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1152,8 +1152,12 @@ static inline void sock_rps_record_flow(const struct sock *sk) * OR an additional socket flag * [1] : sk_state and sk_prot are in the same cache line. */ - if (sk->sk_state == TCP_ESTABLISHED) - sock_rps_record_flow_hash(sk->sk_rxhash); + if (sk->sk_state == TCP_ESTABLISHED) { + /* This READ_ONCE() is paired with the WRITE_ONCE() + * from sock_rps_save_rxhash() and sock_rps_reset_rxhash(). + */ + sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash)); + } } #endif } @@ -1162,15 +1166,19 @@ static inline void sock_rps_save_rxhash(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_RPS - if (unlikely(sk->sk_rxhash != skb->hash)) - sk->sk_rxhash = skb->hash; + /* The following WRITE_ONCE() is paired with the READ_ONCE() + * here, and another one in sock_rps_record_flow(). + */ + if (unlikely(READ_ONCE(sk->sk_rxhash) != skb->hash)) + WRITE_ONCE(sk->sk_rxhash, skb->hash); #endif } static inline void sock_rps_reset_rxhash(struct sock *sk) { #ifdef CONFIG_RPS - sk->sk_rxhash = 0; + /* Paired with READ_ONCE() in sock_rps_record_flow() */ + WRITE_ONCE(sk->sk_rxhash, 0); #endif } -- cgit v1.2.3 From 5c3b74a92aa285a3df722bf6329ba7ccf70346d6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Jun 2023 07:41:15 +0000 Subject: rfs: annotate lockless accesses to RFS sock flow table Add READ_ONCE()/WRITE_ONCE() on accesses to the sock flow table. This also prevents a (smart ?) compiler to remove the condition in: if (table->ents[index] != newval) table->ents[index] = newval; We need the condition to avoid dirtying a shared cache line. Fixes: fec5e652e58f ("rfs: Receive Flow Steering") Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 08fbd4622ccf..e6f22b7403d0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -768,8 +768,11 @@ static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, /* We only give a hint, preemption can change CPU under us */ val |= raw_smp_processor_id(); - if (table->ents[index] != val) - table->ents[index] = val; + /* The following WRITE_ONCE() is paired with the READ_ONCE() + * here, and another one in get_rps_cpu(). + */ + if (READ_ONCE(table->ents[index]) != val) + WRITE_ONCE(table->ents[index], val); } } -- cgit v1.2.3 From d636fc5dd692c8f4e00ae6e0359c0eceeb5d9bdb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Jun 2023 11:19:29 +0000 Subject: net: sched: add rcu annotations around qdisc->qdisc_sleeping syzbot reported a race around qdisc->qdisc_sleeping [1] It is time we add proper annotations to reads and writes to/from qdisc->qdisc_sleeping. [1] BUG: KCSAN: data-race in dev_graft_qdisc / qdisc_lookup_rcu read to 0xffff8881286fc618 of 8 bytes by task 6928 on cpu 1: qdisc_lookup_rcu+0x192/0x2c0 net/sched/sch_api.c:331 __tcf_qdisc_find+0x74/0x3c0 net/sched/cls_api.c:1174 tc_get_tfilter+0x18f/0x990 net/sched/cls_api.c:2547 rtnetlink_rcv_msg+0x7af/0x8c0 net/core/rtnetlink.c:6386 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffff8881286fc618 of 8 bytes by task 6912 on cpu 0: dev_graft_qdisc+0x4f/0x80 net/sched/sch_generic.c:1115 qdisc_graft+0x7d0/0xb60 net/sched/sch_api.c:1103 tc_modify_qdisc+0x712/0xf10 net/sched/sch_api.c:1693 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 6912 Comm: syz-executor.5 Not tainted 6.4.0-rc3-syzkaller-00190-g0d85b27b0cc6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/16/2023 Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Vlad Buslov Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- include/net/sch_generic.h | 6 ++++-- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e6f22b7403d0..c2f0c6002a84 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -620,7 +620,7 @@ struct netdev_queue { netdevice_tracker dev_tracker; struct Qdisc __rcu *qdisc; - struct Qdisc *qdisc_sleeping; + struct Qdisc __rcu *qdisc_sleeping; #ifdef CONFIG_SYSFS struct kobject kobj; #endif diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index fab5ba3e61b7..27271f2b37cb 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -545,7 +545,7 @@ static inline struct Qdisc *qdisc_root_bh(const struct Qdisc *qdisc) static inline struct Qdisc *qdisc_root_sleeping(const struct Qdisc *qdisc) { - return qdisc->dev_queue->qdisc_sleeping; + return rcu_dereference_rtnl(qdisc->dev_queue->qdisc_sleeping); } static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc) @@ -754,7 +754,9 @@ static inline bool qdisc_tx_changing(const struct net_device *dev) for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - if (rcu_access_pointer(txq->qdisc) != txq->qdisc_sleeping) + + if (rcu_access_pointer(txq->qdisc) != + rcu_access_pointer(txq->qdisc_sleeping)) return true; } return false; -- cgit v1.2.3 From 886bc7d6ed3357975c5f1d3c784da96000d4bbb4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Jun 2023 11:42:33 +0000 Subject: net: sched: move rtm_tca_policy declaration to include file rtm_tca_policy is used from net/sched/sch_api.c and net/sched/cls_api.c, thus should be declared in an include file. This fixes the following sparse warning: net/sched/sch_api.c:1434:25: warning: symbol 'rtm_tca_policy' was not declared. Should it be static? Fixes: e331473fee3d ("net/sched: cls_api: add missing validation of netlink attributes") Signed-off-by: Eric Dumazet Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/pkt_sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index f436688b6efc..5722931d83d4 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -127,6 +127,8 @@ static inline void qdisc_run(struct Qdisc *q) } } +extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; + /* Calculate maximal size of packet seen by hard_start_xmit routine of this device. */ -- cgit v1.2.3