Message-ID: <CANn89iL8ihnVyi+g1aKNu3=BJCQoRv4_s29OvVSXBBQdOM4foQ@mail.gmail.com>
Date: Mon, 16 Dec 2024 14:29:12 +0100
From: Eric Dumazet <edumazet@...gle.com>
To: Shahar Shitrit <shshitrit@...dia.com>
Cc: "brianvv@...gle.com" <brianvv@...gle.com>, "davem@...emloft.net" <davem@...emloft.net>, 
	"eric.dumazet@...il.com" <eric.dumazet@...il.com>, "kuba@...nel.org" <kuba@...nel.org>, 
	"kuniyu@...zon.com" <kuniyu@...zon.com>, "martin.lau@...nel.org" <martin.lau@...nel.org>, 
	"ncardwell@...gle.com" <ncardwell@...gle.com>, "netdev@...r.kernel.org" <netdev@...r.kernel.org>, 
	"pabeni@...hat.com" <pabeni@...hat.com>, Tariq Toukan <tariqt@...dia.com>, Gal Pressman <gal@...dia.com>, 
	Ziyad Atiyyeh <ziyadat@...dia.com>, Dror Tennenbaum <drort@...dia.com>
Subject: Re: [PATCH v3 net-next 4/5] ipv6: tcp: give socket pointer to control skbs

On Mon, Dec 16, 2024 at 2:18 PM Shahar Shitrit <shshitrit@...dia.com> wrote:
>
> Hello,
>
>
>
> We observe memory leaks reported by kmemleak when using IPSec in transport mode with crypto offload.
>
> The leaks reproduce for TX offload, RX offload and both.
>
> The leaks as shown in stack trace can be seen below.
>
>
>
> The issue has been bisected to this commit 507a96737d99686ca1714c7ba1f60ac323178189.
>
>

Nothing comes to mind. This might be an old bug in loopback paths.

>
> The leaks reproduce frequently in daily regression runs.
>
> We tried to reproduce it manually with ipv6 configurations on both sides, IPSec configurations and iperf3 traffic, but didn't manage to trigger it so far.
>
>
>
> We can provide more information if needed.
>
>
>
> Regards,
>
> Shahar Shitrit
>
>
>
>
>
> Initiate kmemleak scan
> ERROR: Detected 5 memory leaks in the log
> Nov 04 10:30:05 c-237-113-80-081 kernel: kmemleak: 5 new suspected memory leaks (see /sys/kernel/debug/kmemleak)
> unreferenced object 0xffff8881a3a94240 (size 3264):
>   comm "iperf3", pid 45263, jiffies 4296417151
>   hex dump (first 32 bytes):
>     00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
>     0a 00 07 41 00 00 00 00 00 00 00 00 00 00 00 00  ...A............
>   backtrace (crc bbd45a15):
>     [<00000000e06ca7f4>] kmem_cache_alloc_noprof+0x225/0x3e0
>     [<00000000e1e2f493>] sk_prot_alloc+0x5a/0x230
>     [<000000001213af38>] sk_alloc+0x30/0x360
>     [<00000000a1686abe>] inet6_create+0x29e/0x10c0
>     [<00000000db62dfa0>] __sock_create+0x25a/0x650
>     [<00000000f8c982c4>] __sys_socket+0x114/0x1d0
>     [<00000000a045d271>] __x64_sys_socket+0x6e/0xb0
>     [<00000000102c0964>] do_syscall_64+0x6d/0x140
>     [<00000000a454f7f5>] entry_SYSCALL_64_after_hwframe+0x4b/0x53
> unreferenced object 0xffff88814b45d900 (size 232):
>   comm "softirq", pid 0, jiffies 4296417840
>   hex dump (first 32 bytes):
>     00 80 ce 0c 81 88 ff ff 40 07 fa 87 ff ff ff ff  ........@.......
>     e1 6a 00 84 ff ff ff ff 00 00 00 00 00 00 00 00  .j..............
>   backtrace (crc bfc5fbc4):
>     [<00000000e06ca7f4>] kmem_cache_alloc_noprof+0x225/0x3e0
>     [<00000000d81ccda7>] dst_alloc+0x76/0x140
>     [<0000000030d3284e>] ip6_dst_alloc+0x1f/0x80
>     [<000000007e198912>] ip6_pol_route+0x722/0xc60
>     [<000000005535207e>] fib6_rule_lookup+0x10e/0x5f0
>     [<00000000806ddab6>] ip6_route_input+0x5cd/0xa50
>     [<0000000030a268eb>] ip6_list_rcv_finish.constprop.0+0x1a5/0x9a0
>     [<00000000e6c0deb7>] ipv6_list_rcv+0x2cc/0x400
>     [<00000000eed4d9ac>] __netif_receive_skb_list_core+0x496/0x8c0
>     [<000000005616f892>] netif_receive_skb_list_internal+0x60f/0xd30
>     [<000000008137f84a>] napi_complete_done+0x1a4/0x7e0
>     [<0000000070f546d4>] gro_cell_poll+0x112/0x1e0
>     [<0000000068db02b9>] __napi_poll.constprop.0+0xa3/0x5b0
>     [<00000000e5987926>] net_rx_action+0x4fd/0xce0
>     [<00000000571a033c>] handle_softirqs+0x266/0x840
>     [<000000009757e476>] irq_exit_rcu+0xc3/0x100
> unreferenced object 0xffff88811a0f3500 (size 3264):
>   comm "softirq", pid 0, jiffies 4296417842
>   hex dump (first 32 bytes):
>     7f 00 00 06 7f 00 00 06 38 a1 90 0b aa 86 00 00  ........8.......
>     0a 00 07 41 00 00 00 00 58 42 0f 1a 81 88 ff ff  ...A....XB......
>   backtrace (crc 65fda5f0):
>     [<00000000e06ca7f4>] kmem_cache_alloc_noprof+0x225/0x3e0
>     [<00000000e1e2f493>] sk_prot_alloc+0x5a/0x230
>     [<000000008b3eab13>] sk_clone_lock+0x6a/0xfd0
>     [<00000000e061c828>] inet_csk_clone_lock+0x1a/0x4e0
>     [<0000000071a69e46>] tcp_create_openreq_child+0x26/0x1830
>     [<0000000065ed76dc>] tcp_v6_syn_recv_sock+0x165/0x1ee0
>     [<000000003535f9c5>] tcp_check_req+0x38b/0x1440
>     [<0000000073b86243>] tcp_v6_rcv+0x13ef/0x38a0
>     [<000000001734e1c2>] ip6_protocol_deliver_rcu+0x10f/0x11f0
>     [<00000000ec2e87d3>] ip6_input_finish+0x155/0x2a0
>     [<00000000a1de2827>] ip6_sublist_rcv_finish+0x8d/0x250
>     [<00000000b156115a>] ip6_list_rcv_finish.constprop.0+0x5cd/0x9a0
>     [<00000000e6c0deb7>] ipv6_list_rcv+0x2cc/0x400
>     [<00000000eed4d9ac>] __netif_receive_skb_list_core+0x496/0x8c0
>     [<000000005616f892>] netif_receive_skb_list_internal+0x60f/0xd30
>     [<000000008137f84a>] napi_complete_done+0x1a4/0x7e0
> unreferenced object 0xffff88813a93dcc0 (size 3264):
>   comm "iperf3", pid 45340, jiffies 4296426688
>   hex dump (first 32 bytes):
>     00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
>     0a 00 07 41 00 00 00 00 00 00 00 00 00 00 00 00  ...A............
>   backtrace (crc ce0c3519):
>     [<00000000e06ca7f4>] kmem_cache_alloc_noprof+0x225/0x3e0
>     [<00000000e1e2f493>] sk_prot_alloc+0x5a/0x230
>     [<000000001213af38>] sk_alloc+0x30/0x360
>     [<00000000a1686abe>] inet6_create+0x29e/0x10c0
>     [<00000000db62dfa0>] __sock_create+0x25a/0x650
>     [<00000000f8c982c4>] __sys_socket+0x114/0x1d0
>     [<00000000a045d271>] __x64_sys_socket+0x6e/0xb0
>     [<00000000102c0964>] do_syscall_64+0x6d/0x140
>     [<00000000a454f7f5>] entry_SYSCALL_64_after_hwframe+0x4b/0x53
> runtime: 3m24s
> TEST FAILED
>
>
>
>

Powered by blists - more mailing lists