- 04 Apr, 2019 17 commits
-
-
git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpfDavid S. Miller authored
Daniel Borkmann says: ==================== pull-request: bpf 2019-04-04 The following pull-request contains BPF updates for your *net* tree. The main changes are: 1) Batch of fixes to the existing BPF flow dissector API to support calling BPF programs from the eth_get_headlen context (support for latter is planned to be added in bpf-next), from Stanislav. ==================== Signed-off-by:David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Toke Høiland-Jørgensen says: ==================== sched: A few small fixes for sch_cake Kevin noticed a few issues with the way CAKE reads the skb protocol and the IP diffserv fields. This series fixes those two issues, and should probably go to in 4.19 as well. However, the previous refactoring patch means they don't apply as-is; I can send a follow-up directly to stable if that's OK with you? ==================== Signed-off-by: -
Toke Høiland-Jørgensen authored
There is not actually any guarantee that the IP headers are valid before we access the DSCP bits of the packets. Fix this using the same approach taken in sch_dsmark. Reported-by:
Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk> Signed-off-by:
Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by:
-
Toke Høiland-Jørgensen authored
We shouldn't be using skb->protocol directly as that will miss cases with hardware-accelerated VLAN tags. Use the helper instead to get the right protocol number. Reported-by:
-
Koen De Schepper authored
RFC8257 §3.5 explicitly states that "A DCTCP sender MUST react to loss episodes in the same way as conventional TCP". Currently, Linux DCTCP performs no cwnd reduction when losses are encountered. Optionally, the dctcp_clamp_alpha_on_loss resets alpha to its maximal value if a RTO happens. This behavior is sub-optimal for at least two reasons: i) it ignores losses triggering fast retransmissions; and ii) it causes unnecessary large cwnd reduction in the future if the loss was isolated as it resets the historical term of DCTCP's alpha EWMA to its maximal value (i.e., denoting a total congestion). The second reason has an especially noticeable effect when using DCTCP in high BDP environments, where alpha normally stays at low values. This patch replace the clamping of alpha by setting ssthresh to half of cwnd for both fast retransmissions and RTOs, at most once per RTT. Consequently, the dctcp_clamp_alpha_on_loss module parameter has been removed. The table below shows experimental results where we measured the drop probability of a PIE AQM (not applying ECN marks) at a bottleneck in the presence of a single TCP flow with either the alpha-clamping option enabled or the cwnd halving proposed by this patch. Results using reno or cubic are given for comparison. | Link | RTT | Drop TCP CC | speed | base+AQM | probability ==================|=========|==========|============ CUBIC | 40Mbps | 7+20ms | 0.21% RENO | | | 0.19% DCTCP-CLAMP-ALPHA | | | 25.80% DCTCP-HALVE-CWND | | | 0.22% ------------------|---------|----------|------------ CUBIC | 100Mbps | 7+20ms | 0.03% RENO | | | 0.02% DCTCP-CLAMP-ALPHA | | | 23.30% DCTCP-HALVE-CWND | | | 0.04% ------------------|---------|----------|------------ CUBIC | 800Mbps | 1+1ms | 0.04% RENO | | | 0.05% DCTCP-CLAMP-ALPHA | | | 18.70% DCTCP-HALVE-CWND | | | 0.06% We see that, without halving its cwnd for all source of losses, DCTCP drives the AQM to large drop probabilities in order to keep the queue length under control (i.e., it repeatedly faces RTOs). Instead, if DCTCP reacts to all source of losses, it can then be controlled by the AQM using similar drop levels than cubic or reno. Signed-off-by:Koen De Schepper <koen.de_schepper@nokia-bell-labs.com> Signed-off-by:
Olivier Tilmans <olivier.tilmans@nokia-bell-labs.com> Cc: Bob Briscoe <research@bobbriscoe.net> Cc: Lawrence Brakmo <brakmo@fb.com> Cc: Florian Westphal <fw@strlen.de> Cc: Daniel Borkmann <borkmann@iogearbox.net> Cc: Yuchung Cheng <ycheng@google.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Andrew Shewmaker <agshew@gmail.com> Cc: Glenn Judd <glenn.judd@morganstanley.com> Acked-by:
Florian Westphal <fw@strlen.de> Acked-by:
Neal Cardwell <ncardwell@google.com> Acked-by:
Daniel Borkmann <daniel@iogearbox.net> Signed-off-by:
-
Davide Caratti authored
the control path of 'sample' action does not validate the value of 'rate' provided by the user, but then it uses it as divisor in the traffic path. Validate it in tcf_sample_init(), and return -EINVAL with a proper extack message in case that value is zero, to fix a splat with the script below: # tc f a dev test0 egress matchall action sample rate 0 group 1 index 2 # tc -s a s action sample total acts 1 action order 0: sample rate 1/0 group 1 pipe index 2 ref 1 bind 1 installed 19 sec used 19 sec Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 # ping 192.0.2.1 -I test0 -c1 -q divide error: 0000 [#1] SMP PTI CPU: 1 PID: 6192 Comm: ping Not tainted 5.1.0-rc2.diag2+ #591 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:tcf_sample_act+0x9e/0x1e0 [act_sample] Code: 6a f1 85 c0 74 0d 80 3d 83 1a 00 00 00 0f 84 9c 00 00 00 4d 85 e4 0f 84 85 00 00 00 e8 9b d7 9c f1 44 8b 8b e0 00 00 00 31 d2 <41> f7 f1 85 d2 75 70 f6 85 83 00 00 00 10 48 8b 45 10 8b 88 08 01 RSP: 0018:ffffae320190ba30 EFLAGS: 00010246 RAX: 00000000b0677d21 RBX: ffff8af1ed9ec000 RCX: 0000000059a9fe49 RDX: 0000000000000000 RSI: 000000000c7e33b7 RDI: ffff8af23daa0af0 RBP: ffff8af1ee11b200 R08: 0000000074fcaf7e R09: 0000000000000000 R10: 0000000000000050 R11: ffffffffb3088680 R12: ffff8af232307f80 R13: 0000000000000003 R14: ffff8af1ed9ec000 R15: 0000000000000000 FS: 00007fe9c6d2f740(0000) GS:ffff8af23da80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fff6772f000 CR3: 00000000746a2004 CR4: 00000000001606e0 Call Trace: tcf_action_exec+0x7c/0x1c0 tcf_classify+0x57/0x160 __dev_queue_xmit+0x3dc/0xd10 ip_finish_output2+0x257/0x6d0 ip_output+0x75/0x280 ip_send_skb+0x15/0x40 raw_sendmsg+0xae3/0x1410 sock_sendmsg+0x36/0x40 __sys_sendto+0x10e/0x140 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x60/0x210 entry_SYSCALL_64_after_hwframe+0x49/0xbe [...] Kernel panic - not syncing: Fatal exception in interrupt Add a TDC selftest to document that 'rate' is now being validated. Reported-by:Matteo Croce <mcroce@redhat.com> Fixes: 5c5670fa ("net/sched: Introduce sample tc action") Signed-off-by:
Davide Caratti <dcaratti@redhat.com> Acked-by:
Yotam Gigi <yotam.gi@gmail.com> Signed-off-by:
-
Lorenzo Bianconi authored
When a bpf program is uploaded, the driver computes the number of xdp tx queues resulting in the allocation of additional qsets. Starting from commit '2ecbe4f4 ("net: thunderx: replace global nicvf_rx_mode_wq work queue for all VFs to private for each of them")' the driver runs link state polling for each VF resulting in the following NULL pointer dereference: [ 56.169256] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020 [ 56.178032] Mem abort info: [ 56.180834] ESR = 0x96000005 [ 56.183877] Exception class = DABT (current EL), IL = 32 bits [ 56.189792] SET = 0, FnV = 0 [ 56.192834] EA = 0, S1PTW = 0 [ 56.195963] Data abort info: [ 56.198831] ISV = 0, ISS = 0x00000005 [ 56.202662] CM = 0, WnR = 0 [ 56.205619] user pgtable: 64k pages, 48-bit VAs, pgdp = 0000000021f0c7a0 [ 56.212315] [0000000000000020] pgd=0000000000000000, pud=0000000000000000 [ 56.219094] Internal error: Oops: 96000005 [#1] SMP [ 56.260459] CPU: 39 PID: 2034 Comm: ip Not tainted 5.1.0-rc3+ #3 [ 56.266452] Hardware name: GIGABYTE R120-T33/MT30-GS1, BIOS T49 02/02/2018 [ 56.273315] pstate: 80000005 (Nzcv daif -PAN -UAO) [ 56.278098] pc : __ll_sc___cmpxchg_case_acq_64+0x4/0x20 [ 56.283312] lr : mutex_lock+0x2c/0x50 [ 56.286962] sp : ffff0000219af1b0 [ 56.290264] x29: ffff0000219af1b0 x28: ffff800f64de49a0 [ 56.295565] x27: 0000000000000000 x26: 0000000000000015 [ 56.300865] x25: 0000000000000000 x24: 0000000000000000 [ 56.306165] x23: 0000000000000000 x22: ffff000011117000 [ 56.311465] x21: ffff800f64dfc080 x20: 0000000000000020 [ 56.316766] x19: 0000000000000020 x18: 0000000000000001 [ 56.322066] x17: 0000000000000000 x16: ffff800f2e077080 [ 56.327367] x15: 0000000000000004 x14: 0000000000000000 [ 56.332667] x13: ffff000010964438 x12: 0000000000000002 [ 56.337967] x11: 0000000000000000 x10: 0000000000000c70 [ 56.343268] x9 : ffff0000219af120 x8 : ffff800f2e077d50 [ 56.348568] x7 : 0000000000000027 x6 : 000000062a9d6a84 [ 56.353869] x5 : 0000000000000000 x4 : ffff800f2e077480 [ 56.359169] x3 : 0000000000000008 x2 : ffff800f2e077080 [ 56.364469] x1 : 0000000000000000 x0 : 0000000000000020 [ 56.369770] Process ip (pid: 2034, stack limit = 0x00000000c862da3a) [ 56.376110] Call trace: [ 56.378546] __ll_sc___cmpxchg_case_acq_64+0x4/0x20 [ 56.383414] drain_workqueue+0x34/0x198 [ 56.387247] nicvf_open+0x48/0x9e8 [nicvf] [ 56.391334] nicvf_open+0x898/0x9e8 [nicvf] [ 56.395507] nicvf_xdp+0x1bc/0x238 [nicvf] [ 56.399595] dev_xdp_install+0x68/0x90 [ 56.403333] dev_change_xdp_fd+0xc8/0x240 [ 56.407333] do_setlink+0x8e0/0xbe8 [ 56.410810] __rtnl_newlink+0x5b8/0x6d8 [ 56.414634] rtnl_newlink+0x54/0x80 [ 56.418112] rtnetlink_rcv_msg+0x22c/0x2f8 [ 56.422199] netlink_rcv_skb+0x60/0x120 [ 56.426023] rtnetlink_rcv+0x28/0x38 [ 56.429587] netlink_unicast+0x1c8/0x258 [ 56.433498] netlink_sendmsg+0x1b4/0x350 [ 56.437410] sock_sendmsg+0x4c/0x68 [ 56.440887] ___sys_sendmsg+0x240/0x280 [ 56.444711] __sys_sendmsg+0x68/0xb0 [ 56.448275] __arm64_sys_sendmsg+0x2c/0x38 [ 56.452361] el0_svc_handler+0x9c/0x128 [ 56.456186] el0_svc+0x8/0xc [ 56.459056] Code: 35ffff91 2a1003e0 d65f03c0 f9800011 (c85ffc10) [ 56.465166] ---[ end trace 4a57fdc27b0a572c ]--- [ 56.469772] Kernel panic - not syncing: Fatal exception Fix it by checking nicvf_rx_mode_wq pointer in nicvf_open and nicvf_stop Fixes: 2ecbe4f4 ("net: thunderx: replace global nicvf_rx_mode_wq work queue for all VFs to private for each of them") Fixes: 2c632ad8 ("net: thunderx: move link state polling function to VF") Reported-by:
Lorenzo Bianconi <lorenzo.bianconi@redhat.com> Tested-by:
-
David S. Miller authored
Yonglong Liu says: ==================== net: hns: bugfixes for HNS Driver This patchset fix some bugs that were found in the test of various scenarios, or identify by KASAN/sparse. ==================== Signed-off-by: -
Yonglong Liu authored
There are some sparse warnings in the HNS drivers: warning: incorrect type in assignment (different address spaces) expected void [noderef] <asn:2> *io_base got void *vaddr warning: cast removes address space '<asn:2>' of expression [...] Add __iomem and change all the u8 __iomem to void __iomem to fix these kind of warnings. warning: incorrect type in argument 1 (different address spaces) expected void [noderef] <asn:2> *base got unsigned char [usertype] *base_addr warning: cast to restricted __le16 warning: incorrect type in assignment (different base types) expected unsigned int [usertype] tbl_tcam_data_high got restricted __le32 [usertype] warning: cast to restricted __le32 [...] These variables used u32/u16 as their type, and finally as a parameter of writel(), writel() will do the cpu_to_le32 coversion so remove the little endian covert code to fix these kind of warnings. Signed-off-by:Yonglong Liu <liuyonglong@huawei.com> Signed-off-by:
-
Yonglong Liu authored
When enable SMMU, remove HNS driver will cause a WARNING: [ 141.924177] WARNING: CPU: 36 PID: 2708 at drivers/iommu/dma-iommu.c:443 __iommu_dma_unmap+0xc0/0xc8 [ 141.954673] Modules linked in: hns_enet_drv(-) [ 141.963615] CPU: 36 PID: 2708 Comm: rmmod Tainted: G W 5.0.0-rc1-28723-gb729c57de95c-dirty #32 [ 141.983593] Hardware name: Huawei D05/D05, BIOS Hisilicon D05 UEFI Nemo 1.8 RC0 08/31/2017 [ 142.000244] pstate: 60000005 (nZCv daif -PAN -UAO) [ 142.009886] pc : __iommu_dma_unmap+0xc0/0xc8 [ 142.018476] lr : __iommu_dma_unmap+0xc0/0xc8 [ 142.027066] sp : ffff000013533b90 [ 142.033728] x29: ffff000013533b90 x28: ffff8013e6983600 [ 142.044420] x27: 0000000000000000 x26: 0000000000000000 [ 142.055113] x25: 0000000056000000 x24: 0000000000000015 [ 142.065806] x23: 0000000000000028 x22: ffff8013e66eee68 [ 142.076499] x21: ffff8013db919800 x20: 0000ffffefbff000 [ 142.087192] x19: 0000000000001000 x18: 0000000000000007 [ 142.097885] x17: 000000000000000e x16: 0000000000000001 [ 142.108578] x15: 0000000000000019 x14: 363139343a70616d [ 142.119270] x13: 6e75656761705f67 x12: 0000000000000000 [ 142.129963] x11: 00000000ffffffff x10: 0000000000000006 [ 142.140656] x9 : 1346c1aa88093500 x8 : ffff0000114de4e0 [ 142.151349] x7 : 6662666578303d72 x6 : ffff0000105ffec8 [ 142.162042] x5 : 0000000000000000 x4 : 0000000000000000 [ 142.172734] x3 : 00000000ffffffff x2 : ffff0000114de500 [ 142.183427] x1 : 0000000000000000 x0 : 0000000000000035 [ 142.194120] Call trace: [ 142.199030] __iommu_dma_unmap+0xc0/0xc8 [ 142.206920] iommu_dma_unmap_page+0x20/0x28 [ 142.215335] __iommu_unmap_page+0x40/0x60 [ 142.223399] hnae_unmap_buffer+0x110/0x134 [ 142.231639] hnae_free_desc+0x6c/0x10c [ 142.239177] hnae_fini_ring+0x14/0x34 [ 142.246540] hnae_fini_queue+0x2c/0x40 [ 142.254080] hnae_put_handle+0x38/0xcc [ 142.261619] hns_nic_dev_remove+0x54/0xfc [hns_enet_drv] [ 142.272312] platform_drv_remove+0x24/0x64 [ 142.280552] device_release_driver_internal+0x17c/0x20c [ 142.291070] driver_detach+0x4c/0x90 [ 142.298259] bus_remove_driver+0x5c/0xd8 [ 142.306148] driver_unregister+0x2c/0x54 [ 142.314037] platform_driver_unregister+0x10/0x18 [ 142.323505] hns_nic_dev_driver_exit+0x14/0xf0c [hns_enet_drv] [ 142.335248] __arm64_sys_delete_module+0x214/0x25c [ 142.344891] el0_svc_common+0xb0/0x10c [ 142.352430] el0_svc_handler+0x24/0x80 [ 142.359968] el0_svc+0x8/0x7c0 [ 142.366104] ---[ end trace 60ad1cd58e63c407 ]--- The tx ring buffer map when xmit and unmap when xmit done. So in hnae_init_ring() did not map tx ring buffer, but in hnae_fini_ring() have a unmap operation for tx ring buffer, which is already unmapped when xmit done, than cause this WARNING. The hnae_alloc_buffers() is called in hnae_init_ring(), so the hnae_free_buffers() should be in hnae_fini_ring(), not in hnae_free_desc(). In hnae_fini_ring(), adds a check is_rx_ring() as in hnae_init_ring(). When the ring buffer is tx ring, adds a piece of code to ensure that the tx ring is unmap. Signed-off-by:
Peng Li <lipeng321@huawei.com> Signed-off-by:
-
Yonglong Liu authored
ICMP6 neighbor solicitation messages will be discard by the Hip06 chips, because of not setting forwarding pool. Enable promisc mode has the same problem. This patch fix the wrong forwarding table configs for the multicast vague matching when enable promisc mode, and add forwarding pool for the forwarding table. Signed-off-by:
-
Yonglong Liu authored
When reboot the system again and again, may cause a memory overwrite. [ 15.638922] systemd[1]: Reached target Swap. [ 15.667561] tun: Universal TUN/TAP device driver, 1.6 [ 15.676756] Bridge firewalling registered [ 17.344135] Unable to handle kernel paging request at virtual address 0000000200000040 [ 17.352179] Mem abort info: [ 17.355007] ESR = 0x96000004 [ 17.358105] Exception class = DABT (current EL), IL = 32 bits [ 17.364112] SET = 0, FnV = 0 [ 17.367209] EA = 0, S1PTW = 0 [ 17.370393] Data abort info: [ 17.373315] ISV = 0, ISS = 0x00000004 [ 17.377206] CM = 0, WnR = 0 [ 17.380214] user pgtable: 4k pages, 48-bit VAs, pgdp = (____ptrval____) [ 17.386926] [0000000200000040] pgd=0000000000000000 [ 17.391878] Internal error: Oops: 96000004 [#1] SMP [ 17.396824] CPU: 23 PID: 95 Comm: kworker/u130:0 Tainted: G E 4.19.25-1.2.78.aarch64 #1 [ 17.414175] Hardware name: Huawei TaiShan 2280 /BC11SPCD, BIOS 1.54 08/16/2018 [ 17.425615] Workqueue: events_unbound async_run_entry_fn [ 17.435151] pstate: 00000005 (nzcv daif -PAN -UAO) [ 17.444139] pc : __mutex_lock.isra.1+0x74/0x540 [ 17.453002] lr : __mutex_lock.isra.1+0x3c/0x540 [ 17.461701] sp : ffff000100d9bb60 [ 17.469146] x29: ffff000100d9bb60 x28: 0000000000000000 [ 17.478547] x27: 0000000000000000 x26: ffff802fb8945000 [ 17.488063] x25: 0000000000000000 x24: ffff802fa32081a8 [ 17.497381] x23: 0000000000000002 x22: ffff801fa2b15220 [ 17.506701] x21: ffff000009809000 x20: ffff802fa23a0888 [ 17.515980] x19: ffff801fa2b15220 x18: 0000000000000000 [ 17.525272] x17: 0000000200000000 x16: 0000000200000000 [ 17.534511] x15: 0000000000000000 x14: 0000000000000000 [ 17.543652] x13: ffff000008d95db8 x12: 000000000000000d [ 17.552780] x11: ffff000008d95d90 x10: 0000000000000b00 [ 17.561819] x9 : ffff000100d9bb90 x8 : ffff802fb89d6560 [ 17.570829] x7 : 0000000000000004 x6 : 00000004a1801d05 [ 17.579839] x5 : 0000000000000000 x4 : 0000000000000000 [ 17.588852] x3 : ffff802fb89d5a00 x2 : 0000000000000000 [ 17.597734] x1 : 0000000200000000 x0 : 0000000200000000 [ 17.606631] Process kworker/u130:0 (pid: 95, stack limit = 0x(____ptrval____)) [ 17.617438] Call trace: [ 17.623349] __mutex_lock.isra.1+0x74/0x540 [ 17.630927] __mutex_lock_slowpath+0x24/0x30 [ 17.638602] mutex_lock+0x50/0x60 [ 17.645295] drain_workqueue+0x34/0x198 [ 17.652623] __sas_drain_work+0x7c/0x168 [ 17.659903] sas_drain_work+0x60/0x68 [ 17.666947] hisi_sas_scan_finished+0x30/0x40 [hisi_sas_main] [ 17.676129] do_scsi_scan_host+0x70/0xb0 [ 17.683534] do_scan_async+0x20/0x228 [ 17.690586] async_run_entry_fn+0x4c/0x1d0 [ 17.697997] process_one_work+0x1b4/0x3f8 [ 17.705296] worker_thread+0x54/0x470 Every time the call trace is not the same, but the overwrite address is always the same: Unable to handle kernel paging request at virtual address 0000000200000040 The root cause is, when write the reg XGMAC_MAC_TX_LF_RF_CONTROL_REG, didn't use the io_base offset. Signed-off-by:
-
Yonglong Liu authored
When the HNS driver loaded, always have an error print: "netif_napi_add() called with weight 256" This is because the kernel checks the NAPI polling weights requested by drivers and it prints an error message if a driver requests a weight bigger than 64. So use NAPI_POLL_WEIGHT to fix it. Signed-off-by:
-
Liubin Shu authored
This patch is trying to fix the issue due to: [27237.844750] BUG: KASAN: use-after-free in hns_nic_net_xmit_hw+0x708/0xa18[hns_enet_drv] After hnae_queue_xmit() in hns_nic_net_xmit_hw(), can be interrupted by interruptions, and than call hns_nic_tx_poll_one() to handle the new packets, and free the skb. So, when turn back to hns_nic_net_xmit_hw(), calling skb->len will cause use-after-free. This patch update tx ring statistics in hns_nic_tx_poll_one() to fix the bug. Signed-off-by:
Liubin Shu <shuliubin@huawei.com> Signed-off-by:
Zhen Lei <thunder.leizhen@huawei.com> Signed-off-by:
-
Stanislav Fomichev authored
Rename bpf_flow_dissector.txt to bpf_flow_dissector.rst and fix formatting. Also, link it from the Documentation/networking/index.rst. Tested with 'make htmldocs' to make sure it looks reasonable. Fixes: ae82899b ("flow_dissector: document BPF flow dissector environment") Signed-off-by:
Stanislav Fomichev <sdf@google.com> Acked-by:
Martin KaFai Lau <kafai@fb.com> Signed-off-by:
-
Junwei Hu authored
At the beginning of ip6_fragment func, the prevhdr pointer is obtained in the ip6_find_1stfragopt func. However, all the pointers pointing into skb header may change when calling skb_checksum_help func with skb->ip_summed = CHECKSUM_PARTIAL condition. The prevhdr pointe will be dangling if it is not reloaded after calling __skb_linearize func in skb_checksum_help func. Here, I add a variable, nexthdr_offset, to evaluate the offset, which does not changes even after calling __skb_linearize func. Fixes: 405c92f7 ("ipv6: add defensive check for CHECKSUM_PARTIAL skbs in ip_fragment") Signed-off-by:
Junwei Hu <hujunwei4@huawei.com> Reported-by:
Wenhao Zhang <zhangwenhao8@huawei.com> Reported-by: syzbot+e8ce541d095e486074fc@syzkaller.appspotmail.com Reviewed-by:
Zhiqiang Liu <liuzhiqiang26@huawei.com> Acked-by:
-
Steffen Klassert authored
Currently we may merge incorrectly a received GSO packet or a packet with frag_list into a packet sitting in the gro_hash list. skb_segment() may crash case because the assumptions on the skb layout are not met. The correct behaviour would be to flush the packet in the gro_hash list and send the received GSO packet directly afterwards. Commit d61d072e ("net-gro: avoid reorders") sets NAPI_GRO_CB(skb)->flush in this case, but this is not checked before merging. This patch makes sure to check this flag and to not merge in that case. Fixes: d61d072e ("net-gro: avoid reorders") Signed-off-by:
Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by:
-
- 03 Apr, 2019 6 commits
-
-
Daniel Borkmann authored
Stanislav Fomichev says: ==================== This patch series fixes the existing BPF flow dissector API to support calling BPF progs from the eth_get_headlen context (the support itself will be added in bpf-next tree). The summary of the changes: * fix VLAN handling in bpf_flow.c, we don't need to peek back and look at skb->vlan_present; add selftests * pass and use flow_keys->n_proto instead of skb->protocol * fix clamping of flow_keys->nhoff for packets with nhoff > 0 * prohibit access to most of the __sk_buff fields from BPF flow dissector progs; only data/data_end/flow_keys are allowed (all input is now passed via flow_keys) * finally, document BPF flow dissector program environment ==================== Acked-by:Willem de Bruijn <willemb@google.com> Acked-by:
Petar Penkov <peterpenkov96@gmail.com> Signed-off-by:
-
Stanislav Fomichev authored
Short doc on what BPF flow dissector should expect in the input __sk_buff and flow_keys. Signed-off-by:
-
Stanislav Fomichev authored
Use whitelist instead of a blacklist and allow only a small set of fields that might be relevant in the context of flow dissector: * data * data_end * flow_keys This is required for the eth_get_headlen case where we have only a chunk of data to dissect (i.e. trying to read the other skb fields doesn't make sense). Note, that it is a breaking API change! However, we've provided flow_keys->n_proto as a substitute for skb->protocol; and there is no need to manually handle skb->vlan_present. So even if we break somebody, the migration is trivial. Unfortunately, we can't support eth_get_headlen use-case without those breaking changes. Signed-off-by:
-
Stanislav Fomichev authored
Don't allow BPF program to set flow_keys->nhoff to less than initial value. We currently don't read the value afterwards in anything but the tests, but it's still a good practice to return consistent values to the test programs. Signed-off-by:
-
Stanislav Fomichev authored
This is a preparation for the next commit that would prohibit access to the most fields of __sk_buff from the BPF programs. Instead of requiring BPF flow dissector programs to look into skb, pass all input data in the flow_keys. Signed-off-by:
-
Stanislav Fomichev authored
When we tail call PROG(VLAN) from parse_eth_proto we don't need to peek back to handle vlan proto because we didn't adjust nhoff/thoff yet. Use flow_keys->n_proto, that we set in parse_eth_proto instead and properly increment nhoff as well. Also, always use skb->protocol and don't look at skb->vlan_present. skb->vlan_present indicates that vlan information is stored out-of-band in skb->vlan_{tci,proto} and vlan header is already pulled from skb. That means, skb->vlan_present == true is not relevant for BPF flow dissector. Add simple test cases with VLAN tagged frames: * single vlan for ipv4 * double vlan for ipv6 Signed-off-by:
-
- 02 Apr, 2019 7 commits
-
-
git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-queueDavid S. Miller authored
Jeff Kirsher says: ==================== Intel Wired LAN Driver Fixes 2019-04-01 This series contains two fixes for XDP in the i40e driver. Björn provides both fixes, first moving a function out of the header and into the main.c file. Second fixes a regression introduced in an earlier patch that removed umem from the VSI. This caused an issue because the setup code would try to enable AF_XDP zero copy unconditionally, as long as there was a umem placed in the netdev receive structure. ==================== Signed-off-by: -
Sheena Mira-ato authored
The device type for ip6 tunnels is set to ARPHRD_TUNNEL6. However, the ip4ip6_err function is expecting the device type of the tunnel to be ARPHRD_TUNNEL. Since the device types do not match, the function exits and the ICMP error packet is not sent to the originating host. Note that the device type for IPv4 tunnels is set to ARPHRD_TUNNEL. Fix is to expect a tunnel device type of ARPHRD_TUNNEL6 instead. Now the tunnel device type matches and the ICMP error packet is sent to the originating host. Signed-off-by:
Sheena Mira-ato <sheena.mira-ato@alliedtelesis.co.nz> Signed-off-by:
-
YueHaibing authored
If dccp_feat_push_change fails, we forget free the mem which is alloced by kmemdup in dccp_feat_clone_sp_val. Reported-by:
Hulk Robot <hulkci@huawei.com> Fixes: e8ef967a ("dccp: Registration routines for changing feature values") Reviewed-by:
Mukesh Ojha <mojha@codeaurora.org> Signed-off-by:
YueHaibing <yuehaibing@huawei.com> Signed-off-by:
-
Xin Long authored
Syzbot report a kernel-infoleak: BUG: KMSAN: kernel-infoleak in _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32 Call Trace: _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32 copy_to_user include/linux/uaccess.h:174 [inline] sctp_getsockopt_peer_addrs net/sctp/socket.c:5911 [inline] sctp_getsockopt+0x1668e/0x17f70 net/sctp/socket.c:7562 ... Uninit was stored to memory at: sctp_transport_init net/sctp/transport.c:61 [inline] sctp_transport_new+0x16d/0x9a0 net/sctp/transport.c:115 sctp_assoc_add_peer+0x532/0x1f70 net/sctp/associola.c:637 sctp_process_param net/sctp/sm_make_chunk.c:2548 [inline] sctp_process_init+0x1a1b/0x3ed0 net/sctp/sm_make_chunk.c:2361 ... Bytes 8-15 of 16 are uninitialized It was caused by that th _pad field (the 8-15 bytes) of a v4 addr (saved in struct sockaddr_in) wasn't initialized, but directly copied to user memory in sctp_getsockopt_peer_addrs(). So fix it by calling memset(addr->v4.sin_zero, 0, 8) to initialize _pad of sockaddr_in before copying it to user memory in sctp_v4_addr_to_user(), as sctp_v6_addr_to_user() does. Reported-by: syzbot+86b5c7c236a22616a72f@syzkaller.appspotmail.com Signed-off-by:Xin Long <lucien.xin@gmail.com> Tested-by:
Alexander Potapenko <glider@google.com> Acked-by:
Neil Horman <nhorman@tuxdriver.com> Signed-off-by:
-
David S. Miller authored
Jakub Kicinski says: ==================== nfp: flower: fix matching and pushing vlan CFI bit This patch clears up some confusion around the meaning of bit 12 for FW messages related to VLAN and flower offload. Pieter says: It fixes issues with matching, pushing and popping vlan tags. We replace the vlan CFI bit with a vlan present bit that indicates the presence of a vlan tag. We also no longer set the CFI when pushing vlan tags. ==================== Signed-off-by: -
Pieter Jansen van Vuuren authored
We no longer set CFI when pushing vlan tags, therefore we remove the CFI bit from push vlan. Fixes: 1a1e586f ("nfp: add basic action capabilities to flower offloads") Signed-off-by:
Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com> Signed-off-by:
Louis Peens <louis.peens@netronome.com> Reviewed-by:
Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by:
-
Pieter Jansen van Vuuren authored
Replace vlan CFI bit with a vlan present bit that indicates the presence of a vlan tag. Previously the driver incorrectly assumed that an vlan id of 0 is not matchable, therefore we indicate vlan presence with a vlan present bit. Fixes: 5571e8c9 ("nfp: extend flower matching capabilities") Signed-off-by:
-
- 01 Apr, 2019 10 commits
-
-
Jiri Slaby authored
When kcm is loaded while many processes try to create a KCM socket, a crash occurs: BUG: unable to handle kernel NULL pointer dereference at 000000000000000e IP: mutex_lock+0x27/0x40 kernel/locking/mutex.c:240 PGD 8000000016ef2067 P4D 8000000016ef2067 PUD 3d6e9067 PMD 0 Oops: 0002 [#1] SMP KASAN PTI CPU: 0 PID: 7005 Comm: syz-executor.5 Not tainted 4.12.14-396-default #1 SLE15-SP1 (unreleased) RIP: 0010:mutex_lock+0x27/0x40 kernel/locking/mutex.c:240 RSP: 0018:ffff88000d487a00 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 000000000000000e RCX: 1ffff100082b0719 ... CR2: 000000000000000e CR3: 000000004b1bc003 CR4: 0000000000060ef0 Call Trace: kcm_create+0x600/0xbf0 [kcm] __sock_create+0x324/0x750 net/socket.c:1272 ... This is due to race between sock_create and unfinished register_pernet_device. kcm_create tries to do "net_generic(net, kcm_net_id)". but kcm_net_id is not initialized yet. So switch the order of the two to close the race. This can be reproduced with mutiple processes doing socket(PF_KCM, ...) and one process doing module removal. Fixes: ab7ac4eb ("kcm: Kernel Connection Multiplexor module") Reviewed-by:
Michal Kubecek <mkubecek@suse.cz> Signed-off-by:
Jiri Slaby <jslaby@suse.cz> Signed-off-by:
-
David S. Miller authored
Paolo Abeni says: ==================== net: sched: fix stats accounting for child NOLOCK qdiscs Currently, stats accounting for NOLOCK qdisc enslaved to classful (lock) qdiscs is buggy. Per CPU values are ignored in most places, as a result, stats dump in the above scenario always report 0 length backlog and parent backlog len is not updated correctly on NOLOCK qdisc removal. The first patch address stats dumping, and the second one child qdisc removal. I'm targeting the net tree as this is a bugfix, but it could be moved to net-next due to the relatively large diffstat. ==================== Signed-off-by: -
Paolo Abeni authored
The same code to flush qdisc tree and purge the qdisc queue is duplicated in many places and in most cases it does not respect NOLOCK qdisc: the global backlog len is used and the per CPU values are ignored. This change addresses the above, factoring-out the relevant code and using the helpers introduced by the previous patch to fetch the correct backlog len. Fixes: c5ad119f ("net: sched: pfifo_fast use skb_array") Signed-off-by:
Paolo Abeni <pabeni@redhat.com> Signed-off-by:
-
Paolo Abeni authored
Classful qdiscs can't access directly the child qdiscs backlog length: if such qdisc is NOLOCK, per CPU values should be accounted instead. Most qdiscs no not respect the above. As a result, qstats fetching for most classful qdisc is currently incorrect: if the child qdisc is NOLOCK, it always reports 0 len backlog. This change introduces a pair of helpers to safely fetch both backlog and qlen and use them in stats class dumping functions, fixing the above issue and cleaning a bit the code. DRR needs also to access the child qdisc queue length, so it needs custom handling. Fixes: c5ad119f ("net: sched: pfifo_fast use skb_array") Signed-off-by:
-
Nicolas Dichtel authored
It returned always NULL, thus it was never possible to get the filter. Example: $ ip link add foo type dummy $ ip link add bar type dummy $ tc qdisc add dev foo clsact $ tc filter add dev foo protocol all pref 1 ingress handle 1234 \ matchall action mirred ingress mirror dev bar Before the patch: $ tc filter get dev foo protocol all pref 1 ingress handle 1234 matchall Error: Specified filter handle not found. We have an error talking to the kernel After: $ tc filter get dev foo protocol all pref 1 ingress handle 1234 matchall filter ingress protocol all pref 1 matchall chain 0 handle 0x4d2 not_in_hw action order 1: mirred (Ingress Mirror to device bar) pipe index 1 ref 1 bind 1 CC: Yotam Gigi <yotamg@mellanox.com> CC: Jiri Pirko <jiri@mellanox.com> Fixes: fd62d9f5 ("net/sched: matchall: Fix configuration race") Signed-off-by:Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by:
-
Björn Töpel authored
In commit f3fef2b6 ("i40e: Remove umem from VSI") a regression was introduced; When the VSI was reset, the setup code would try to enable AF_XDP ZC unconditionally (as long as there was a umem placed in the netdev._rx struct). Here, we add a bitmap to the VSI that tracks if a certain queue pair has been "zero-copy enabled" via the ndo_bpf. The bitmap is used in i40e_xsk_umem, and enables zero-copy if and only if XDP is enabled, the corresponding qid in the bitmap is set and the umem is non-NULL. Fixes: f3fef2b6 ("i40e: Remove umem from VSI") Signed-off-by:
Björn Töpel <bjorn.topel@intel.com> Tested-by:
Aaron Brown <aaron.f.brown@intel.com> Signed-off-by:
Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-
Björn Töpel authored
The i40e_xsk_umem function was explicitly inlined in i40e.h. There is no reason for that, so move it to i40e_main.c instead. Signed-off-by:
-
Stephen Suryaputra authored
Configuration check to accept source route IP options should be made on the incoming netdevice when the skb->dev is an l3mdev master. The route lookup for the source route next hop also needs the incoming netdev. v2->v3: - Simplify by passing the original netdevice down the stack (per David Ahern). Signed-off-by:
Stephen Suryaputra <ssuryaextr@gmail.com> Reviewed-by:
David Ahern <dsahern@gmail.com> Signed-off-by:
-
Bert Kenward authored
Cc: Martin Habets <mhabets@solarflare.com> Signed-off-by:
Bert Kenward <bkenward@solarflare.com> Acked-by:
Martin Habets <mhabets@solarflare.com> Signed-off-by:
-
Dust Li authored
When tcp_sk_init() failed in inet_ctl_sock_create(), 'net->ipv4.tcp_congestion_control' will be left uninitialized, but tcp_sk_exit() hasn't check for that. This patch add checking on 'net->ipv4.tcp_congestion_control' in tcp_sk_exit() to prevent NULL-ptr dereference. Fixes: 6670e152 ("tcp: Namespace-ify sysctl_tcp_default_congestion_control") Signed-off-by:
Dust Li <dust.li@linux.alibaba.com> Signed-off-by:
Eric Dumazet <edumazet@google.com> Signed-off-by:
-
