diff options
author | Maciej Fijalkowski <maciej.fijalkowski@intel.com> | 2022-04-25 17:37:45 +0200 |
---|---|---|
committer | Daniel Borkmann <daniel@iogearbox.net> | 2022-04-26 16:19:54 +0200 |
commit | ba3beec2ec1d3b4fd8672ca6e781dac4b3267f6e (patch) | |
tree | 454bb3a0a65dfa433ae5a8c669444801f5c2ea07 /net/xdp | |
parent | 1d661ed54d8613c97bcff2c7d6181c61e482a1da (diff) |
xsk: Fix possible crash when multiple sockets are created
Fix a crash that happens if an Rx only socket is created first, then a
second socket is created that is Tx only and bound to the same umem as
the first socket and also the same netdev and queue_id together with the
XDP_SHARED_UMEM flag. In this specific case, the tx_descs array page
pool was not created by the first socket as it was an Rx only socket.
When the second socket is bound it needs this tx_descs array of this
shared page pool as it has a Tx component, but unfortunately it was
never allocated, leading to a crash. Note that this array is only used
for zero-copy drivers using the batched Tx APIs, currently only ice and
i40e.
[ 5511.150360] BUG: kernel NULL pointer dereference, address: 0000000000000008
[ 5511.158419] #PF: supervisor write access in kernel mode
[ 5511.164472] #PF: error_code(0x0002) - not-present page
[ 5511.170416] PGD 0 P4D 0
[ 5511.173347] Oops: 0002 [#1] PREEMPT SMP PTI
[ 5511.178186] CPU: 0 PID: 0 Comm: swapper/0 Tainted: G E 5.18.0-rc1+ #97
[ 5511.187245] Hardware name: Intel Corp. GRANTLEY/GRANTLEY, BIOS GRRFCRB1.86B.0276.D07.1605190235 05/19/2016
[ 5511.198418] RIP: 0010:xsk_tx_peek_release_desc_batch+0x198/0x310
[ 5511.205375] Code: c0 83 c6 01 84 c2 74 6d 8d 46 ff 23 07 44 89 e1 48 83 c0 14 48 c1 e1 04 48 c1 e0 04 48 03 47 10 4c 01 c1 48 8b 50 08 48 8b 00 <48> 89 51 08 48 89 01 41 80 bd d7 00 00 00 00 75 82 48 8b 19 49 8b
[ 5511.227091] RSP: 0018:ffffc90000003dd0 EFLAGS: 00010246
[ 5511.233135] RAX: 0000000000000000 RBX: ffff88810c8da600 RCX: 0000000000000000
[ 5511.241384] RDX: 000000000000003c RSI: 0000000000000001 RDI: ffff888115f555c0
[ 5511.249634] RBP: ffffc90000003e08 R08: 0000000000000000 R09: ffff889092296b48
[ 5511.257886] R10: 0000ffffffffffff R11: ffff889092296800 R12: 0000000000000000
[ 5511.266138] R13: ffff88810c8db500 R14: 0000000000000040 R15: 0000000000000100
[ 5511.274387] FS: 0000000000000000(0000) GS:ffff88903f800000(0000) knlGS:0000000000000000
[ 5511.283746] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 5511.290389] CR2: 0000000000000008 CR3: 00000001046e2001 CR4: 00000000003706f0
[ 5511.298640] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 5511.306892] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 5511.315142] Call Trace:
[ 5511.317972] <IRQ>
[ 5511.320301] ice_xmit_zc+0x68/0x2f0 [ice]
[ 5511.324977] ? ktime_get+0x38/0xa0
[ 5511.328913] ice_napi_poll+0x7a/0x6a0 [ice]
[ 5511.333784] __napi_poll+0x2c/0x160
[ 5511.337821] net_rx_action+0xdd/0x200
[ 5511.342058] __do_softirq+0xe6/0x2dd
[ 5511.346198] irq_exit_rcu+0xb5/0x100
[ 5511.350339] common_interrupt+0xa4/0xc0
[ 5511.354777] </IRQ>
[ 5511.357201] <TASK>
[ 5511.359625] asm_common_interrupt+0x1e/0x40
[ 5511.364466] RIP: 0010:cpuidle_enter_state+0xd2/0x360
[ 5511.370211] Code: 49 89 c5 0f 1f 44 00 00 31 ff e8 e9 00 7b ff 45 84 ff 74 12 9c 58 f6 c4 02 0f 85 72 02 00 00 31 ff e8 02 0c 80 ff fb 45 85 f6 <0f> 88 11 01 00 00 49 63 c6 4c 2b 2c 24 48 8d 14 40 48 8d 14 90 49
[ 5511.391921] RSP: 0018:ffffffff82a03e60 EFLAGS: 00000202
[ 5511.397962] RAX: ffff88903f800000 RBX: 0000000000000001 RCX: 000000000000001f
[ 5511.406214] RDX: 0000000000000000 RSI: ffffffff823400b9 RDI: ffffffff8234c046
[ 5511.424646] RBP: ffff88810a384800 R08: 000005032a28c046 R09: 0000000000000008
[ 5511.443233] R10: 000000000000000b R11: 0000000000000006 R12: ffffffff82bcf700
[ 5511.461922] R13: 000005032a28c046 R14: 0000000000000001 R15: 0000000000000000
[ 5511.480300] cpuidle_enter+0x29/0x40
[ 5511.494329] do_idle+0x1c7/0x250
[ 5511.507610] cpu_startup_entry+0x19/0x20
[ 5511.521394] start_kernel+0x649/0x66e
[ 5511.534626] secondary_startup_64_no_verify+0xc3/0xcb
[ 5511.549230] </TASK>
Detect such case during bind() and allocate this memory region via newly
introduced xp_alloc_tx_descs(). Also, use kvcalloc instead of kcalloc as
for other buffer pool allocations, so that it matches the kvfree() from
xp_destroy().
Fixes: d1bc532e99be ("i40e: xsk: Move tmp desc array from driver to pool")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20220425153745.481322-1-maciej.fijalkowski@intel.com
Diffstat (limited to 'net/xdp')
-rw-r--r-- | net/xdp/xsk.c | 13 | ||||
-rw-r--r-- | net/xdp/xsk_buff_pool.c | 16 |
2 files changed, 25 insertions, 4 deletions
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 7d3a00cb24ec..3a9348030e20 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -967,6 +967,19 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) xp_get_pool(umem_xs->pool); xs->pool = umem_xs->pool; + + /* If underlying shared umem was created without Tx + * ring, allocate Tx descs array that Tx batching API + * utilizes + */ + if (xs->tx && !xs->pool->tx_descs) { + err = xp_alloc_tx_descs(xs->pool, xs); + if (err) { + xp_put_pool(xs->pool); + sockfd_put(sock); + goto out_unlock; + } + } } xdp_get_umem(umem_xs->umem); diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index af040ffa14ff..87bdd71c7bb6 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -42,6 +42,16 @@ void xp_destroy(struct xsk_buff_pool *pool) kvfree(pool); } +int xp_alloc_tx_descs(struct xsk_buff_pool *pool, struct xdp_sock *xs) +{ + pool->tx_descs = kvcalloc(xs->tx->nentries, sizeof(*pool->tx_descs), + GFP_KERNEL); + if (!pool->tx_descs) + return -ENOMEM; + + return 0; +} + struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, struct xdp_umem *umem) { @@ -59,11 +69,9 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, if (!pool->heads) goto out; - if (xs->tx) { - pool->tx_descs = kcalloc(xs->tx->nentries, sizeof(*pool->tx_descs), GFP_KERNEL); - if (!pool->tx_descs) + if (xs->tx) + if (xp_alloc_tx_descs(pool, xs)) goto out; - } pool->chunk_mask = ~((u64)umem->chunk_size - 1); pool->addrs_cnt = umem->size; |