From 1e9b0e1c550c42c13c111d1a31e822057232abc4 Mon Sep 17 00:00:00 2001 From: Antonio Pastor Date: Thu, 2 Jan 2025 20:23:00 -0500 Subject: [PATCH 01/16] net: 802: LLC+SNAP OID:PID lookup on start of skb data 802.2+LLC+SNAP frames received by napi_complete_done() with GRO and DSA have skb->transport_header set two bytes short, or pointing 2 bytes before network_header & skb->data. This was an issue as snap_rcv() expected offset to point to SNAP header (OID:PID), causing packet to be dropped. A fix at llc_fixup_skb() (a024e377efed) resets transport_header for any LLC consumers that may care about it, and stops SNAP packets from being dropped, but doesn't fix the problem which is that LLC and SNAP should not use transport_header offset. Ths patch eliminates the use of transport_header offset for SNAP lookup of OID:PID so that SNAP does not rely on the offset at all. The offset is reset after pull for any SNAP packet consumers that may (but shouldn't) use it. Fixes: fda55eca5a33 ("net: introduce skb_transport_header_was_set()") Signed-off-by: Antonio Pastor Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20250103012303.746521-1-antonio.pastor@gmail.com Signed-off-by: Jakub Kicinski --- net/802/psnap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/802/psnap.c b/net/802/psnap.c index fca9d454905f..389df460c8c4 100644 --- a/net/802/psnap.c +++ b/net/802/psnap.c @@ -55,11 +55,11 @@ static int snap_rcv(struct sk_buff *skb, struct net_device *dev, goto drop; rcu_read_lock(); - proto = find_snap_client(skb_transport_header(skb)); + proto = find_snap_client(skb->data); if (proto) { /* Pass the frame on. */ - skb->transport_header += 5; skb_pull_rcsum(skb, 5); + skb_reset_transport_header(skb); rc = proto->rcvfunc(skb, dev, &snap_packet_type, orig_dev); } rcu_read_unlock(); -- 2.50.1 From 3479c7549fb1dfa7a1db4efb7347c7b8ef50de4b Mon Sep 17 00:00:00 2001 From: Zhongqiu Duan Date: Thu, 2 Jan 2025 17:14:26 +0000 Subject: [PATCH 02/16] tcp/dccp: allow a connection when sk_max_ack_backlog is zero If the backlog of listen() is set to zero, sk_acceptq_is_full() allows one connection to be made, but inet_csk_reqsk_queue_is_full() does not. When the net.ipv4.tcp_syncookies is zero, inet_csk_reqsk_queue_is_full() will cause an immediate drop before the sk_acceptq_is_full() check in tcp_conn_request(), resulting in no connection can be made. This patch tries to keep consistent with 64a146513f8f ("[NET]: Revert incorrect accept queue backlog changes."). Link: https://lore.kernel.org/netdev/20250102080258.53858-1-kuniyu@amazon.com/ Fixes: ef547f2ac16b ("tcp: remove max_qlen_log") Signed-off-by: Zhongqiu Duan Reviewed-by: Kuniyuki Iwashima Reviewed-by: Jason Xing Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20250102171426.915276-1-dzq.aishenghu0@gmail.com Signed-off-by: Jakub Kicinski --- include/net/inet_connection_sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 3c82fad904d4..c7f42844c79a 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -282,7 +282,7 @@ static inline int inet_csk_reqsk_queue_len(const struct sock *sk) static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) { - return inet_csk_reqsk_queue_len(sk) >= READ_ONCE(sk->sk_max_ack_backlog); + return inet_csk_reqsk_queue_len(sk) > READ_ONCE(sk->sk_max_ack_backlog); } bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); -- 2.50.1 From a039e54397c6a75b713b9ce7894a62e06956aa92 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 3 Jan 2025 10:45:46 +0000 Subject: [PATCH 03/16] net_sched: cls_flow: validate TCA_FLOW_RSHIFT attribute syzbot found that TCA_FLOW_RSHIFT attribute was not validated. Right shitfing a 32bit integer is undefined for large shift values. UBSAN: shift-out-of-bounds in net/sched/cls_flow.c:329:23 shift exponent 9445 is too large for 32-bit type 'u32' (aka 'unsigned int') CPU: 1 UID: 0 PID: 54 Comm: kworker/u8:3 Not tainted 6.13.0-rc3-syzkaller-00180-g4f619d518db9 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 Workqueue: ipv6_addrconf addrconf_dad_work Call Trace: __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120 ubsan_epilogue lib/ubsan.c:231 [inline] __ubsan_handle_shift_out_of_bounds+0x3c8/0x420 lib/ubsan.c:468 flow_classify+0x24d5/0x25b0 net/sched/cls_flow.c:329 tc_classify include/net/tc_wrapper.h:197 [inline] __tcf_classify net/sched/cls_api.c:1771 [inline] tcf_classify+0x420/0x1160 net/sched/cls_api.c:1867 sfb_classify net/sched/sch_sfb.c:260 [inline] sfb_enqueue+0x3ad/0x18b0 net/sched/sch_sfb.c:318 dev_qdisc_enqueue+0x4b/0x290 net/core/dev.c:3793 __dev_xmit_skb net/core/dev.c:3889 [inline] __dev_queue_xmit+0xf0e/0x3f50 net/core/dev.c:4400 dev_queue_xmit include/linux/netdevice.h:3168 [inline] neigh_hh_output include/net/neighbour.h:523 [inline] neigh_output include/net/neighbour.h:537 [inline] ip_finish_output2+0xd41/0x1390 net/ipv4/ip_output.c:236 iptunnel_xmit+0x55d/0x9b0 net/ipv4/ip_tunnel_core.c:82 udp_tunnel_xmit_skb+0x262/0x3b0 net/ipv4/udp_tunnel_core.c:173 geneve_xmit_skb drivers/net/geneve.c:916 [inline] geneve_xmit+0x21dc/0x2d00 drivers/net/geneve.c:1039 __netdev_start_xmit include/linux/netdevice.h:5002 [inline] netdev_start_xmit include/linux/netdevice.h:5011 [inline] xmit_one net/core/dev.c:3590 [inline] dev_hard_start_xmit+0x27a/0x7d0 net/core/dev.c:3606 __dev_queue_xmit+0x1b73/0x3f50 net/core/dev.c:4434 Fixes: e5dfb815181f ("[NET_SCHED]: Add flow classifier") Reported-by: syzbot+1dbb57d994e54aaa04d2@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/6777bf49.050a0220.178762.0040.GAE@google.com/T/#u Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20250103104546.3714168-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/sched/cls_flow.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 5502998aace7..5c2580a07530 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -356,7 +356,8 @@ static const struct nla_policy flow_policy[TCA_FLOW_MAX + 1] = { [TCA_FLOW_KEYS] = { .type = NLA_U32 }, [TCA_FLOW_MODE] = { .type = NLA_U32 }, [TCA_FLOW_BASECLASS] = { .type = NLA_U32 }, - [TCA_FLOW_RSHIFT] = { .type = NLA_U32 }, + [TCA_FLOW_RSHIFT] = NLA_POLICY_MAX(NLA_U32, + 31 /* BITS_PER_U32 - 1 */), [TCA_FLOW_ADDEND] = { .type = NLA_U32 }, [TCA_FLOW_MASK] = { .type = NLA_U32 }, [TCA_FLOW_XOR] = { .type = NLA_U32 }, -- 2.50.1 From e95274dfe86490ec2a5633035c24b2de6722841f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 3 Jan 2025 10:24:58 -0800 Subject: [PATCH 04/16] selftests: tc-testing: reduce rshift value After previous change rshift >= 32 is no longer allowed. Modify the test to use 31, the test doesn't seem to send any traffic so the exact value shouldn't matter. Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20250103182458.1213486-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/tc-testing/tc-tests/filters/flow.json | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json index 996448afe31b..91d120548bf5 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json @@ -78,10 +78,10 @@ "setup": [ "$TC qdisc add dev $DEV1 ingress" ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 protocol ip flow map key dst rshift 0xff", + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 protocol ip flow map key dst rshift 0x1f", "expExitCode": "0", "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 protocol ip prio 1 flow", - "matchPattern": "filter parent ffff: protocol ip pref 1 flow chain [0-9]+ handle 0x1 map keys dst rshift 255 baseclass", + "matchPattern": "filter parent ffff: protocol ip pref 1 flow chain [0-9]+ handle 0x1 map keys dst rshift 31 baseclass", "matchCount": "1", "teardown": [ "$TC qdisc del dev $DEV1 ingress" -- 2.50.1 From 8ce4f287524c74a118b0af1eebd4b24a8efca57a Mon Sep 17 00:00:00 2001 From: Jiawen Wu Date: Fri, 3 Jan 2025 16:10:13 +0800 Subject: [PATCH 05/16] net: libwx: fix firmware mailbox abnormal return The existing SW-FW interaction flow on the driver is wrong. Follow this wrong flow, driver would never return error if there is a unknown command. Since firmware writes back 'firmware ready' and 'unknown command' in the mailbox message if there is an unknown command sent by driver. So reading 'firmware ready' does not timeout. Then driver would mistakenly believe that the interaction has completed successfully. It tends to happen with the use of custom firmware. Move the check for 'unknown command' out of the poll timeout for 'firmware ready'. And adjust the debug log so that mailbox messages are always printed when commands timeout. Fixes: 1efa9bfe58c5 ("net: libwx: Implement interaction with firmware") Signed-off-by: Jiawen Wu Link: https://patch.msgid.link/20250103081013.1995939-1-jiawenwu@trustnetic.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/wangxun/libwx/wx_hw.c | 24 ++++++++++------------ 1 file changed, 11 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index 1bf9c38e4125..deaf670c160e 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -334,27 +334,25 @@ int wx_host_interface_command(struct wx *wx, u32 *buffer, status = read_poll_timeout(rd32, hicr, hicr & WX_MNG_MBOX_CTL_FWRDY, 1000, timeout * 1000, false, wx, WX_MNG_MBOX_CTL); + buf[0] = rd32(wx, WX_MNG_MBOX); + if ((buf[0] & 0xff0000) >> 16 == 0x80) { + wx_err(wx, "Unknown FW command: 0x%x\n", buffer[0] & 0xff); + status = -EINVAL; + goto rel_out; + } + /* Check command completion */ if (status) { - wx_dbg(wx, "Command has failed with no status valid.\n"); - - buf[0] = rd32(wx, WX_MNG_MBOX); - if ((buffer[0] & 0xff) != (~buf[0] >> 24)) { - status = -EINVAL; - goto rel_out; - } - if ((buf[0] & 0xff0000) >> 16 == 0x80) { - wx_dbg(wx, "It's unknown cmd.\n"); - status = -EINVAL; - goto rel_out; - } - + wx_err(wx, "Command has failed with no status valid.\n"); wx_dbg(wx, "write value:\n"); for (i = 0; i < dword_len; i++) wx_dbg(wx, "%x ", buffer[i]); wx_dbg(wx, "read value:\n"); for (i = 0; i < dword_len; i++) wx_dbg(wx, "%x ", buf[i]); + wx_dbg(wx, "\ncheck: %x %x\n", buffer[0] & 0xff, ~buf[0] >> 24); + + goto rel_out; } if (!return_data) -- 2.50.1 From 8c817eb26230dc0ae553cee16ff43a4a895f6756 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Fri, 3 Jan 2025 11:51:47 -0800 Subject: [PATCH 06/16] pds_core: limit loop over fw name list Add an array size limit to the for-loop to be sure we don't try to reference a fw_version string off the end of the fw info names array. We know that our firmware only has a limited number of firmware slot names, but we shouldn't leave this unchecked. Fixes: 45d76f492938 ("pds_core: set up device and adminq") Signed-off-by: Shannon Nelson Reviewed-by: Simon Horman Reviewed-by: Brett Creeley Reviewed-by: Jacob Keller Link: https://patch.msgid.link/20250103195147.7408-1-shannon.nelson@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/amd/pds_core/devlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c index 2681889162a2..44971e71991f 100644 --- a/drivers/net/ethernet/amd/pds_core/devlink.c +++ b/drivers/net/ethernet/amd/pds_core/devlink.c @@ -118,7 +118,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req, if (err && err != -EIO) return err; - listlen = fw_list.num_fw_slots; + listlen = min(fw_list.num_fw_slots, ARRAY_SIZE(fw_list.fw_names)); for (i = 0; i < listlen; i++) { if (i < ARRAY_SIZE(fw_slotnames)) strscpy(buf, fw_slotnames[i], sizeof(buf)); -- 2.50.1 From c8dafb0e4398dacc362832098a04b97da3b0395b Mon Sep 17 00:00:00 2001 From: Kalesh AP Date: Fri, 3 Jan 2025 20:38:47 -0800 Subject: [PATCH 07/16] bnxt_en: Fix possible memory leak when hwrm_req_replace fails When hwrm_req_replace() fails, the driver is not invoking bnxt_req_drop() which could cause a memory leak. Fixes: bbf33d1d9805 ("bnxt_en: update all firmware calls to use the new APIs") Reviewed-by: Pavan Chebbi Signed-off-by: Kalesh AP Signed-off-by: Michael Chan Link: https://patch.msgid.link/20250104043849.3482067-2-michael.chan@broadcom.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index b771c84cdd89..0ed26e3a28f4 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -208,7 +208,7 @@ int bnxt_send_msg(struct bnxt_en_dev *edev, rc = hwrm_req_replace(bp, req, fw_msg->msg, fw_msg->msg_len); if (rc) - return rc; + goto drop_req; hwrm_req_timeout(bp, req, fw_msg->timeout); resp = hwrm_req_hold(bp, req); @@ -220,6 +220,7 @@ int bnxt_send_msg(struct bnxt_en_dev *edev, memcpy(fw_msg->resp, resp, resp_len); } +drop_req: hwrm_req_drop(bp, req); return rc; } -- 2.50.1 From 40452969a50652e3cbf89dac83d54eebf2206d27 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Fri, 3 Jan 2025 20:38:48 -0800 Subject: [PATCH 08/16] bnxt_en: Fix DIM shutdown DIM work will call the firmware to adjust the coalescing parameters on the RX rings. We should cancel DIM work before we call the firmware to free the RX rings. Otherwise, FW will reject the call from DIM work if the RX ring has been freed. This will generate an error message like this: bnxt_en 0000:21:00.1 ens2f1np1: hwrm req_type 0x53 seq id 0x6fca error 0x2 and cause unnecessary concern for the user. It is also possible to modify the coalescing parameters of the wrong ring if the ring has been re-allocated. To prevent this, cancel DIM work right before freeing the RX rings. We also have to add a check in NAPI poll to not schedule DIM if the RX rings are shutting down. Check that the VNIC is active before we schedule DIM. The VNIC is always disabled before we free the RX rings. Fixes: 0bc0b97fca73 ("bnxt_en: cleanup DIM work on device shutdown") Reviewed-by: Hongguang Gao Reviewed-by: Kalesh AP Reviewed-by: Somnath Kotur Signed-off-by: Michael Chan Link: https://patch.msgid.link/20250104043849.3482067-3-michael.chan@broadcom.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 38 ++++++++++++++++++++--- 1 file changed, 33 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index b86f980fa7ea..aeaa74f03046 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2897,6 +2897,13 @@ static int bnxt_hwrm_handler(struct bnxt *bp, struct tx_cmp *txcmp) return 0; } +static bool bnxt_vnic_is_active(struct bnxt *bp) +{ + struct bnxt_vnic_info *vnic = &bp->vnic_info[0]; + + return vnic->fw_vnic_id != INVALID_HW_RING_ID && vnic->mru > 0; +} + static irqreturn_t bnxt_msix(int irq, void *dev_instance) { struct bnxt_napi *bnapi = dev_instance; @@ -3164,7 +3171,7 @@ static int bnxt_poll(struct napi_struct *napi, int budget) break; } } - if (bp->flags & BNXT_FLAG_DIM) { + if ((bp->flags & BNXT_FLAG_DIM) && bnxt_vnic_is_active(bp)) { struct dim_sample dim_sample = {}; dim_update_sample(cpr->event_ctr, @@ -3295,7 +3302,7 @@ static int bnxt_poll_p5(struct napi_struct *napi, int budget) poll_done: cpr_rx = &cpr->cp_ring_arr[0]; if (cpr_rx->cp_ring_type == BNXT_NQ_HDL_TYPE_RX && - (bp->flags & BNXT_FLAG_DIM)) { + (bp->flags & BNXT_FLAG_DIM) && bnxt_vnic_is_active(bp)) { struct dim_sample dim_sample = {}; dim_update_sample(cpr->event_ctr, @@ -7266,6 +7273,26 @@ err_out: return rc; } +static void bnxt_cancel_dim(struct bnxt *bp) +{ + int i; + + /* DIM work is initialized in bnxt_enable_napi(). Proceed only + * if NAPI is enabled. + */ + if (!bp->bnapi || test_bit(BNXT_STATE_NAPI_DISABLED, &bp->state)) + return; + + /* Make sure NAPI sees that the VNIC is disabled */ + synchronize_net(); + for (i = 0; i < bp->rx_nr_rings; i++) { + struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; + struct bnxt_napi *bnapi = rxr->bnapi; + + cancel_work_sync(&bnapi->cp_ring.dim.work); + } +} + static int hwrm_ring_free_send_msg(struct bnxt *bp, struct bnxt_ring_struct *ring, u32 ring_type, int cmpl_ring_id) @@ -7366,6 +7393,7 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path) } } + bnxt_cancel_dim(bp); for (i = 0; i < bp->rx_nr_rings; i++) { bnxt_hwrm_rx_ring_free(bp, &bp->rx_ring[i], close_path); bnxt_hwrm_rx_agg_ring_free(bp, &bp->rx_ring[i], close_path); @@ -11309,8 +11337,6 @@ static void bnxt_disable_napi(struct bnxt *bp) if (bnapi->in_reset) cpr->sw_stats->rx.rx_resets++; napi_disable(&bnapi->napi); - if (bnapi->rx_ring) - cancel_work_sync(&cpr->dim.work); } } @@ -15572,8 +15598,10 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx) bnxt_hwrm_vnic_update(bp, vnic, VNIC_UPDATE_REQ_ENABLES_MRU_VALID); } - + /* Make sure NAPI sees that the VNIC is disabled */ + synchronize_net(); rxr = &bp->rx_ring[idx]; + cancel_work_sync(&rxr->bnapi->cp_ring.dim.work); bnxt_hwrm_rx_ring_free(bp, rxr, false); bnxt_hwrm_rx_agg_ring_free(bp, rxr, false); rxr->rx_next_cons = 0; -- 2.50.1 From 4c1224501e9d6c5fd12d83752f1c1b444e0e3418 Mon Sep 17 00:00:00 2001 From: Anumula Murali Mohan Reddy Date: Fri, 3 Jan 2025 14:53:27 +0530 Subject: [PATCH 09/16] cxgb4: Avoid removal of uninserted tid During ARP failure, tid is not inserted but _c4iw_free_ep() attempts to remove tid which results in error. This patch fixes the issue by avoiding removal of uninserted tid. Fixes: 59437d78f088 ("cxgb4/chtls: fix ULD connection failures due to wrong TID base") Signed-off-by: Anumula Murali Mohan Reddy Signed-off-by: Potnuri Bharat Teja Link: https://patch.msgid.link/20250103092327.1011925-1-anumula@chelsio.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index bc3af0054406..604dcfd49aa4 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -1799,7 +1799,10 @@ void cxgb4_remove_tid(struct tid_info *t, unsigned int chan, unsigned int tid, struct adapter *adap = container_of(t, struct adapter, tids); struct sk_buff *skb; - WARN_ON(tid_out_of_range(&adap->tids, tid)); + if (tid_out_of_range(&adap->tids, tid)) { + dev_err(adap->pdev_dev, "tid %d out of range\n", tid); + return; + } if (t->tid_tab[tid - adap->tids.tid_base]) { t->tid_tab[tid - adap->tids.tid_base] = NULL; -- 2.50.1 From fd48f071a3d6d51e737e953bb43fe69785cf59a9 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 3 Jan 2025 10:32:07 -0800 Subject: [PATCH 10/16] net: don't dump Tx and uninitialized NAPIs We use NAPI ID as the key for continuing dumps. We also depend on the NAPIs being sorted by ID within the driver list. Tx NAPIs (which don't have an ID assigned) break this expectation, it's not currently possible to dump them reliably. Since Tx NAPIs are relatively rare, and can't be used in doit (GET or SET) hide them from the dump API as well. Fixes: 27f91aaf49b3 ("netdev-genl: Add netlink framework functions for napi") Signed-off-by: Jakub Kicinski Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20250103183207.1216004-1-kuba@kernel.org Signed-off-by: Paolo Abeni --- net/core/netdev-genl.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index b0772d135efb..125b660004d3 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -176,8 +176,7 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi, if (!hdr) return -EMSGSIZE; - if (napi->napi_id >= MIN_NAPI_ID && - nla_put_u32(rsp, NETDEV_A_NAPI_ID, napi->napi_id)) + if (nla_put_u32(rsp, NETDEV_A_NAPI_ID, napi->napi_id)) goto nla_put_failure; if (nla_put_u32(rsp, NETDEV_A_NAPI_IFINDEX, napi->dev->ifindex)) @@ -272,6 +271,8 @@ netdev_nl_napi_dump_one(struct net_device *netdev, struct sk_buff *rsp, return err; list_for_each_entry(napi, &netdev->napi_list, dev_list) { + if (napi->napi_id < MIN_NAPI_ID) + continue; if (ctx->napi_id && napi->napi_id >= ctx->napi_id) continue; -- 2.50.1 From 95978931d55fb7685f8c0b2598d6c12a9b6bc82a Mon Sep 17 00:00:00 2001 From: Su Hui Date: Mon, 6 Jan 2025 10:36:48 +0800 Subject: [PATCH 11/16] eth: fbnic: Revert "eth: fbnic: Add hardware monitoring support via HWMON interface" There is a garbage value problem in fbnic_mac_get_sensor_asic(). 'fw_cmpl' is uninitialized which makes 'sensor' and '*val' to be stored garbage value. Revert commit d85ebade02e8 ("eth: fbnic: Add hardware monitoring support via HWMON interface") to avoid this problem. Fixes: d85ebade02e8 ("eth: fbnic: Add hardware monitoring support via HWMON interface") Signed-off-by: Su Hui Suggested-by: Jakub Kicinski Suggested-by: Michal Swiatkowski Link: https://patch.msgid.link/20250106023647.47756-1-suhui@nfschina.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/meta/fbnic/Makefile | 1 - drivers/net/ethernet/meta/fbnic/fbnic.h | 5 -- drivers/net/ethernet/meta/fbnic/fbnic_fw.h | 7 -- drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c | 81 ------------------- drivers/net/ethernet/meta/fbnic/fbnic_mac.c | 22 ----- drivers/net/ethernet/meta/fbnic/fbnic_mac.h | 7 -- drivers/net/ethernet/meta/fbnic/fbnic_pci.c | 3 - 7 files changed, 126 deletions(-) delete mode 100644 drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c diff --git a/drivers/net/ethernet/meta/fbnic/Makefile b/drivers/net/ethernet/meta/fbnic/Makefile index 239b2258ec65..ea6214ca48e7 100644 --- a/drivers/net/ethernet/meta/fbnic/Makefile +++ b/drivers/net/ethernet/meta/fbnic/Makefile @@ -13,7 +13,6 @@ fbnic-y := fbnic_csr.o \ fbnic_ethtool.o \ fbnic_fw.o \ fbnic_hw_stats.o \ - fbnic_hwmon.o \ fbnic_irq.o \ fbnic_mac.o \ fbnic_netdev.o \ diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h index 706ae6104c8e..744eb0d95449 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic.h @@ -20,7 +20,6 @@ struct fbnic_dev { struct device *dev; struct net_device *netdev; struct dentry *dbg_fbd; - struct device *hwmon; u32 __iomem *uc_addr0; u32 __iomem *uc_addr4; @@ -33,7 +32,6 @@ struct fbnic_dev { struct fbnic_fw_mbx mbx[FBNIC_IPC_MBX_INDICES]; struct fbnic_fw_cap fw_cap; - struct fbnic_fw_completion *cmpl_data; /* Lock protecting Tx Mailbox queue to prevent possible races */ spinlock_t fw_tx_lock; @@ -142,9 +140,6 @@ void fbnic_devlink_unregister(struct fbnic_dev *fbd); int fbnic_fw_enable_mbx(struct fbnic_dev *fbd); void fbnic_fw_disable_mbx(struct fbnic_dev *fbd); -void fbnic_hwmon_register(struct fbnic_dev *fbd); -void fbnic_hwmon_unregister(struct fbnic_dev *fbd); - int fbnic_pcs_irq_enable(struct fbnic_dev *fbd); void fbnic_pcs_irq_disable(struct fbnic_dev *fbd); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h index 7cd8841920e4..221faf8c6756 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h @@ -44,13 +44,6 @@ struct fbnic_fw_cap { u8 link_fec; }; -struct fbnic_fw_completion { - struct { - s32 millivolts; - s32 millidegrees; - } tsene; -}; - void fbnic_mbx_init(struct fbnic_dev *fbd); void fbnic_mbx_clean(struct fbnic_dev *fbd); void fbnic_mbx_poll(struct fbnic_dev *fbd); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c b/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c deleted file mode 100644 index bcd1086e3768..000000000000 --- a/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c +++ /dev/null @@ -1,81 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) Meta Platforms, Inc. and affiliates. */ - -#include - -#include "fbnic.h" -#include "fbnic_mac.h" - -static int fbnic_hwmon_sensor_id(enum hwmon_sensor_types type) -{ - if (type == hwmon_temp) - return FBNIC_SENSOR_TEMP; - if (type == hwmon_in) - return FBNIC_SENSOR_VOLTAGE; - - return -EOPNOTSUPP; -} - -static umode_t fbnic_hwmon_is_visible(const void *drvdata, - enum hwmon_sensor_types type, - u32 attr, int channel) -{ - if (type == hwmon_temp && attr == hwmon_temp_input) - return 0444; - if (type == hwmon_in && attr == hwmon_in_input) - return 0444; - - return 0; -} - -static int fbnic_hwmon_read(struct device *dev, enum hwmon_sensor_types type, - u32 attr, int channel, long *val) -{ - struct fbnic_dev *fbd = dev_get_drvdata(dev); - const struct fbnic_mac *mac = fbd->mac; - int id; - - id = fbnic_hwmon_sensor_id(type); - return id < 0 ? id : mac->get_sensor(fbd, id, val); -} - -static const struct hwmon_ops fbnic_hwmon_ops = { - .is_visible = fbnic_hwmon_is_visible, - .read = fbnic_hwmon_read, -}; - -static const struct hwmon_channel_info *fbnic_hwmon_info[] = { - HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT), - HWMON_CHANNEL_INFO(in, HWMON_I_INPUT), - NULL -}; - -static const struct hwmon_chip_info fbnic_chip_info = { - .ops = &fbnic_hwmon_ops, - .info = fbnic_hwmon_info, -}; - -void fbnic_hwmon_register(struct fbnic_dev *fbd) -{ - if (!IS_REACHABLE(CONFIG_HWMON)) - return; - - fbd->hwmon = hwmon_device_register_with_info(fbd->dev, "fbnic", - fbd, &fbnic_chip_info, - NULL); - if (IS_ERR(fbd->hwmon)) { - dev_notice(fbd->dev, - "Failed to register hwmon device %pe\n", - fbd->hwmon); - fbd->hwmon = NULL; - } -} - -void fbnic_hwmon_unregister(struct fbnic_dev *fbd) -{ - if (!IS_REACHABLE(CONFIG_HWMON) || !fbd->hwmon) - return; - - hwmon_device_unregister(fbd->hwmon); - fbd->hwmon = NULL; -} diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c index 80b82ff12c4d..7b654d0a6dac 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c @@ -686,27 +686,6 @@ fbnic_mac_get_eth_mac_stats(struct fbnic_dev *fbd, bool reset, MAC_STAT_TX_BROADCAST); } -static int fbnic_mac_get_sensor_asic(struct fbnic_dev *fbd, int id, long *val) -{ - struct fbnic_fw_completion fw_cmpl; - s32 *sensor; - - switch (id) { - case FBNIC_SENSOR_TEMP: - sensor = &fw_cmpl.tsene.millidegrees; - break; - case FBNIC_SENSOR_VOLTAGE: - sensor = &fw_cmpl.tsene.millivolts; - break; - default: - return -EINVAL; - } - - *val = *sensor; - - return 0; -} - static const struct fbnic_mac fbnic_mac_asic = { .init_regs = fbnic_mac_init_regs, .pcs_enable = fbnic_pcs_enable_asic, @@ -716,7 +695,6 @@ static const struct fbnic_mac fbnic_mac_asic = { .get_eth_mac_stats = fbnic_mac_get_eth_mac_stats, .link_down = fbnic_mac_link_down_asic, .link_up = fbnic_mac_link_up_asic, - .get_sensor = fbnic_mac_get_sensor_asic, }; /** diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.h b/drivers/net/ethernet/meta/fbnic/fbnic_mac.h index 05a591653e09..476239a9d381 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.h @@ -47,11 +47,6 @@ enum { #define FBNIC_LINK_MODE_PAM4 (FBNIC_LINK_50R1) #define FBNIC_LINK_MODE_MASK (FBNIC_LINK_AUTO - 1) -enum fbnic_sensor_id { - FBNIC_SENSOR_TEMP, /* Temp in millidegrees Centigrade */ - FBNIC_SENSOR_VOLTAGE, /* Voltage in millivolts */ -}; - /* This structure defines the interface hooks for the MAC. The MAC hooks * will be configured as a const struct provided with a set of function * pointers. @@ -88,8 +83,6 @@ struct fbnic_mac { void (*link_down)(struct fbnic_dev *fbd); void (*link_up)(struct fbnic_dev *fbd, bool tx_pause, bool rx_pause); - - int (*get_sensor)(struct fbnic_dev *fbd, int id, long *val); }; int fbnic_mac_init(struct fbnic_dev *fbd); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c index 32702dc4a066..7ccf192f13d5 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c @@ -296,8 +296,6 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Capture snapshot of hardware stats so netdev can calculate delta */ fbnic_reset_hw_stats(fbd); - fbnic_hwmon_register(fbd); - if (!fbd->dsn) { dev_warn(&pdev->dev, "Reading serial number failed\n"); goto init_failure_mode; @@ -360,7 +358,6 @@ static void fbnic_remove(struct pci_dev *pdev) fbnic_netdev_free(fbd); } - fbnic_hwmon_unregister(fbd); fbnic_dbg_fbd_exit(fbd); fbnic_devlink_unregister(fbd); fbnic_fw_disable_mbx(fbd); -- 2.50.1 From b341ca51d2679829d26a3f6a4aa9aee9abd94f92 Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Sat, 4 Jan 2025 10:29:45 -0500 Subject: [PATCH 12/16] tls: Fix tls_sw_sendmsg error handling We've noticed that NFS can hang when using RPC over TLS on an unstable connection, and investigation shows that the RPC layer is stuck in a tight loop attempting to transmit, but forever getting -EBADMSG back from the underlying network. The loop begins when tcp_sendmsg_locked() returns -EPIPE to tls_tx_records(), but that error is converted to -EBADMSG when calling the socket's error reporting handler. Instead of converting errors from tcp_sendmsg_locked(), let's pass them along in this path. The RPC layer handles -EPIPE by reconnecting the transport, which prevents the endless attempts to transmit on a broken connection. Signed-off-by: Benjamin Coddington Fixes: a42055e8d2c3 ("net/tls: Add support for async encryption of records for performance") Link: https://patch.msgid.link/9594185559881679d81f071b181a10eb07cd079f.1736004079.git.bcodding@redhat.com Signed-off-by: Jakub Kicinski --- net/tls/tls_sw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index bbf26cc4f6ee..7bcc9b4408a2 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -458,7 +458,7 @@ int tls_tx_records(struct sock *sk, int flags) tx_err: if (rc < 0 && rc != -EAGAIN) - tls_err_abort(sk, -EBADMSG); + tls_err_abort(sk, rc); return rc; } -- 2.50.1 From cb358ff94154774d031159b018adf45e17673941 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 6 Jan 2025 16:19:11 +0900 Subject: [PATCH 13/16] ipvlan: Fix use-after-free in ipvlan_get_iflink(). syzbot presented an use-after-free report [0] regarding ipvlan and linkwatch. ipvlan does not hold a refcnt of the lower device unlike vlan and macvlan. If the linkwatch work is triggered for the ipvlan dev, the lower dev might have already been freed, resulting in UAF of ipvlan->phy_dev in ipvlan_get_iflink(). We can delay the lower dev unregistration like vlan and macvlan by holding the lower dev's refcnt in dev->netdev_ops->ndo_init() and releasing it in dev->priv_destructor(). Jakub pointed out calling .ndo_XXX after unregister_netdevice() has returned is error prone and suggested [1] addressing this UAF in the core by taking commit 750e51603395 ("net: avoid potential UAF in default_operstate()") further. Let's assume unregistering devices DOWN and use RCU protection in default_operstate() not to race with the device unregistration. [0]: BUG: KASAN: slab-use-after-free in ipvlan_get_iflink+0x84/0x88 drivers/net/ipvlan/ipvlan_main.c:353 Read of size 4 at addr ffff0000d768c0e0 by task kworker/u8:35/6944 CPU: 0 UID: 0 PID: 6944 Comm: kworker/u8:35 Not tainted 6.13.0-rc2-g9bc5c9515b48 #12 4c3cb9e8b4565456f6a355f312ff91f4f29b3c47 Hardware name: linux,dummy-virt (DT) Workqueue: events_unbound linkwatch_event Call trace: show_stack+0x38/0x50 arch/arm64/kernel/stacktrace.c:484 (C) __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0xbc/0x108 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0x16c/0x6f0 mm/kasan/report.c:489 kasan_report+0xc0/0x120 mm/kasan/report.c:602 __asan_report_load4_noabort+0x20/0x30 mm/kasan/report_generic.c:380 ipvlan_get_iflink+0x84/0x88 drivers/net/ipvlan/ipvlan_main.c:353 dev_get_iflink+0x7c/0xd8 net/core/dev.c:674 default_operstate net/core/link_watch.c:45 [inline] rfc2863_policy+0x144/0x360 net/core/link_watch.c:72 linkwatch_do_dev+0x60/0x228 net/core/link_watch.c:175 __linkwatch_run_queue+0x2f4/0x5b8 net/core/link_watch.c:239 linkwatch_event+0x64/0xa8 net/core/link_watch.c:282 process_one_work+0x700/0x1398 kernel/workqueue.c:3229 process_scheduled_works kernel/workqueue.c:3310 [inline] worker_thread+0x8c4/0xe10 kernel/workqueue.c:3391 kthread+0x2b0/0x360 kernel/kthread.c:389 ret_from_fork+0x10/0x20 arch/arm64/kernel/entry.S:862 Allocated by task 9303: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x30/0x68 mm/kasan/common.c:68 kasan_save_alloc_info+0x44/0x58 mm/kasan/generic.c:568 poison_kmalloc_redzone mm/kasan/common.c:377 [inline] __kasan_kmalloc+0x84/0xa0 mm/kasan/common.c:394 kasan_kmalloc include/linux/kasan.h:260 [inline] __do_kmalloc_node mm/slub.c:4283 [inline] __kmalloc_node_noprof+0x2a0/0x560 mm/slub.c:4289 __kvmalloc_node_noprof+0x9c/0x230 mm/util.c:650 alloc_netdev_mqs+0xb4/0x1118 net/core/dev.c:11209 rtnl_create_link+0x2b8/0xb60 net/core/rtnetlink.c:3595 rtnl_newlink_create+0x19c/0x868 net/core/rtnetlink.c:3771 __rtnl_newlink net/core/rtnetlink.c:3896 [inline] rtnl_newlink+0x122c/0x15c0 net/core/rtnetlink.c:4011 rtnetlink_rcv_msg+0x61c/0x918 net/core/rtnetlink.c:6901 netlink_rcv_skb+0x1dc/0x398 net/netlink/af_netlink.c:2542 rtnetlink_rcv+0x34/0x50 net/core/rtnetlink.c:6928 netlink_unicast_kernel net/netlink/af_netlink.c:1321 [inline] netlink_unicast+0x618/0x838 net/netlink/af_netlink.c:1347 netlink_sendmsg+0x5fc/0x8b0 net/netlink/af_netlink.c:1891 sock_sendmsg_nosec net/socket.c:711 [inline] __sock_sendmsg net/socket.c:726 [inline] __sys_sendto+0x2ec/0x438 net/socket.c:2197 __do_sys_sendto net/socket.c:2204 [inline] __se_sys_sendto net/socket.c:2200 [inline] __arm64_sys_sendto+0xe4/0x110 net/socket.c:2200 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline] invoke_syscall+0x90/0x278 arch/arm64/kernel/syscall.c:49 el0_svc_common+0x13c/0x250 arch/arm64/kernel/syscall.c:132 do_el0_svc+0x54/0x70 arch/arm64/kernel/syscall.c:151 el0_svc+0x4c/0xa8 arch/arm64/kernel/entry-common.c:744 el0t_64_sync_handler+0x78/0x108 arch/arm64/kernel/entry-common.c:762 el0t_64_sync+0x198/0x1a0 arch/arm64/kernel/entry.S:600 Freed by task 10200: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x30/0x68 mm/kasan/common.c:68 kasan_save_free_info+0x58/0x70 mm/kasan/generic.c:582 poison_slab_object mm/kasan/common.c:247 [inline] __kasan_slab_free+0x48/0x68 mm/kasan/common.c:264 kasan_slab_free include/linux/kasan.h:233 [inline] slab_free_hook mm/slub.c:2338 [inline] slab_free mm/slub.c:4598 [inline] kfree+0x140/0x420 mm/slub.c:4746 kvfree+0x4c/0x68 mm/util.c:693 netdev_release+0x94/0xc8 net/core/net-sysfs.c:2034 device_release+0x98/0x1c0 kobject_cleanup lib/kobject.c:689 [inline] kobject_release lib/kobject.c:720 [inline] kref_put include/linux/kref.h:65 [inline] kobject_put+0x2b0/0x438 lib/kobject.c:737 netdev_run_todo+0xdd8/0xf48 net/core/dev.c:10924 rtnl_unlock net/core/rtnetlink.c:152 [inline] rtnl_net_unlock net/core/rtnetlink.c:209 [inline] rtnl_dellink+0x484/0x680 net/core/rtnetlink.c:3526 rtnetlink_rcv_msg+0x61c/0x918 net/core/rtnetlink.c:6901 netlink_rcv_skb+0x1dc/0x398 net/netlink/af_netlink.c:2542 rtnetlink_rcv+0x34/0x50 net/core/rtnetlink.c:6928 netlink_unicast_kernel net/netlink/af_netlink.c:1321 [inline] netlink_unicast+0x618/0x838 net/netlink/af_netlink.c:1347 netlink_sendmsg+0x5fc/0x8b0 net/netlink/af_netlink.c:1891 sock_sendmsg_nosec net/socket.c:711 [inline] __sock_sendmsg net/socket.c:726 [inline] ____sys_sendmsg+0x410/0x708 net/socket.c:2583 ___sys_sendmsg+0x178/0x1d8 net/socket.c:2637 __sys_sendmsg net/socket.c:2669 [inline] __do_sys_sendmsg net/socket.c:2674 [inline] __se_sys_sendmsg net/socket.c:2672 [inline] __arm64_sys_sendmsg+0x12c/0x1c8 net/socket.c:2672 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline] invoke_syscall+0x90/0x278 arch/arm64/kernel/syscall.c:49 el0_svc_common+0x13c/0x250 arch/arm64/kernel/syscall.c:132 do_el0_svc+0x54/0x70 arch/arm64/kernel/syscall.c:151 el0_svc+0x4c/0xa8 arch/arm64/kernel/entry-common.c:744 el0t_64_sync_handler+0x78/0x108 arch/arm64/kernel/entry-common.c:762 el0t_64_sync+0x198/0x1a0 arch/arm64/kernel/entry.S:600 The buggy address belongs to the object at ffff0000d768c000 which belongs to the cache kmalloc-cg-4k of size 4096 The buggy address is located 224 bytes inside of freed 4096-byte region [ffff0000d768c000, ffff0000d768d000) The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x117688 head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0 memcg:ffff0000c77ef981 flags: 0xbfffe0000000040(head|node=0|zone=2|lastcpupid=0x1ffff) page_type: f5(slab) raw: 0bfffe0000000040 ffff0000c000f500 dead000000000100 dead000000000122 raw: 0000000000000000 0000000000040004 00000001f5000000 ffff0000c77ef981 head: 0bfffe0000000040 ffff0000c000f500 dead000000000100 dead000000000122 head: 0000000000000000 0000000000040004 00000001f5000000 ffff0000c77ef981 head: 0bfffe0000000003 fffffdffc35da201 ffffffffffffffff 0000000000000000 head: 0000000000000008 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff0000d768bf80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff0000d768c000: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff0000d768c080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff0000d768c100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff0000d768c180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: 8c55facecd7a ("net: linkwatch: only report IF_OPER_LOWERLAYERDOWN if iflink is actually down") Reported-by: syzkaller Suggested-by: Jakub Kicinski Link: https://lore.kernel.org/netdev/20250102174400.085fd8ac@kernel.org/ [1] Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20250106071911.64355-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- net/core/link_watch.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 1b4d39e38084..cb04ef2b9807 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -42,14 +42,18 @@ static unsigned int default_operstate(const struct net_device *dev) * first check whether lower is indeed the source of its down state. */ if (!netif_carrier_ok(dev)) { - int iflink = dev_get_iflink(dev); struct net_device *peer; + int iflink; /* If called from netdev_run_todo()/linkwatch_sync_dev(), * dev_net(dev) can be already freed, and RTNL is not held. */ - if (dev->reg_state == NETREG_UNREGISTERED || - iflink == dev->ifindex) + if (dev->reg_state <= NETREG_REGISTERED) + iflink = dev_get_iflink(dev); + else + iflink = dev->ifindex; + + if (iflink == dev->ifindex) return IF_OPER_DOWN; ASSERT_RTNL(); -- 2.50.1 From db78475ba0d3c66d430f7ded2388cc041078a542 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 6 Jan 2025 10:02:10 -0800 Subject: [PATCH 14/16] eth: gve: use appropriate helper to set xdp_features Commit f85949f98206 ("xdp: add xdp_set_features_flag utility routine") added routines to inform the core about XDP flag changes. GVE support was added around the same time and missed using them. GVE only changes the flags on error recover or resume. Presumably the flags may change during resume if VM migrated. User would not get the notification and upper devices would not get a chance to recalculate their flags. Fixes: 75eaae158b1b ("gve: Add XDP DROP and TX support for GQI-QPL format") Reviewed-By: Jeroen de Borst Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20250106180210.1861784-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/google/gve/gve_main.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 8a8f6ab12a98..533e659b15b3 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -2241,14 +2241,18 @@ static void gve_service_task(struct work_struct *work) static void gve_set_netdev_xdp_features(struct gve_priv *priv) { + xdp_features_t xdp_features; + if (priv->queue_format == GVE_GQI_QPL_FORMAT) { - priv->dev->xdp_features = NETDEV_XDP_ACT_BASIC; - priv->dev->xdp_features |= NETDEV_XDP_ACT_REDIRECT; - priv->dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT; - priv->dev->xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY; + xdp_features = NETDEV_XDP_ACT_BASIC; + xdp_features |= NETDEV_XDP_ACT_REDIRECT; + xdp_features |= NETDEV_XDP_ACT_NDO_XMIT; + xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY; } else { - priv->dev->xdp_features = 0; + xdp_features = 0; } + + xdp_set_features_flag(priv->dev, xdp_features); } static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) -- 2.50.1 From c2994b008492db033d40bd767be1620229a3035e Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 25 Nov 2024 15:42:09 -0500 Subject: [PATCH 15/16] Bluetooth: hci_sync: Fix not setting Random Address when required This fixes errors such as the following when Own address type is set to Random Address but it has not been programmed yet due to either be advertising or connecting: < HCI Command: LE Set Exte.. (0x08|0x0041) plen 13 Own address type: Random (0x03) Filter policy: Ignore not in accept list (0x01) PHYs: 0x05 Entry 0: LE 1M Type: Passive (0x00) Interval: 60.000 msec (0x0060) Window: 30.000 msec (0x0030) Entry 1: LE Coded Type: Passive (0x00) Interval: 180.000 msec (0x0120) Window: 90.000 msec (0x0090) > HCI Event: Command Complete (0x0e) plen 4 LE Set Extended Scan Parameters (0x08|0x0041) ncmd 1 Status: Success (0x00) < HCI Command: LE Set Exten.. (0x08|0x0042) plen 6 Extended scan: Enabled (0x01) Filter duplicates: Enabled (0x01) Duration: 0 msec (0x0000) Period: 0.00 sec (0x0000) > HCI Event: Command Complete (0x0e) plen 4 LE Set Extended Scan Enable (0x08|0x0042) ncmd 1 Status: Invalid HCI Command Parameters (0x12) Fixes: c45074d68a9b ("Bluetooth: Fix not generating RPA when required") Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/hci_sync.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index c86f4e42e69c..7b2b04d6b856 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -1031,9 +1031,9 @@ static bool adv_use_rpa(struct hci_dev *hdev, uint32_t flags) static int hci_set_random_addr_sync(struct hci_dev *hdev, bdaddr_t *rpa) { - /* If we're advertising or initiating an LE connection we can't - * go ahead and change the random address at this time. This is - * because the eventual initiator address used for the + /* If a random_addr has been set we're advertising or initiating an LE + * connection we can't go ahead and change the random address at this + * time. This is because the eventual initiator address used for the * subsequently created connection will be undefined (some * controllers use the new address and others the one we had * when the operation started). @@ -1041,8 +1041,9 @@ static int hci_set_random_addr_sync(struct hci_dev *hdev, bdaddr_t *rpa) * In this kind of scenario skip the update and let the random * address be updated at the next cycle. */ - if (hci_dev_test_flag(hdev, HCI_LE_ADV) || - hci_lookup_le_connect(hdev)) { + if (bacmp(&hdev->random_addr, BDADDR_ANY) && + (hci_dev_test_flag(hdev, HCI_LE_ADV) || + hci_lookup_le_connect(hdev))) { bt_dev_dbg(hdev, "Deferring random address update"); hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); return 0; -- 2.50.1 From a182d9c84f9c52fb5db895ecceeee8b3a1bf661e Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 25 Nov 2024 15:42:10 -0500 Subject: [PATCH 16/16] Bluetooth: MGMT: Fix Add Device to responding before completing Add Device with LE type requires updating resolving/accept list which requires quite a number of commands to complete and each of them may fail, so instead of pretending it would always work this checks the return of hci_update_passive_scan_sync which indicates if everything worked as intended. Fixes: e8907f76544f ("Bluetooth: hci_sync: Make use of hci_cmd_sync_queue set 3") Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/mgmt.c | 38 ++++++++++++++++++++++++++++++++++++-- 1 file changed, 36 insertions(+), 2 deletions(-) diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index b31192d473d0..de47ad999d7b 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -7655,6 +7655,24 @@ static void device_added(struct sock *sk, struct hci_dev *hdev, mgmt_event(MGMT_EV_DEVICE_ADDED, hdev, &ev, sizeof(ev), sk); } +static void add_device_complete(struct hci_dev *hdev, void *data, int err) +{ + struct mgmt_pending_cmd *cmd = data; + struct mgmt_cp_add_device *cp = cmd->param; + + if (!err) { + device_added(cmd->sk, hdev, &cp->addr.bdaddr, cp->addr.type, + cp->action); + device_flags_changed(NULL, hdev, &cp->addr.bdaddr, + cp->addr.type, hdev->conn_flags, + PTR_UINT(cmd->user_data)); + } + + mgmt_cmd_complete(cmd->sk, hdev->id, MGMT_OP_ADD_DEVICE, + mgmt_status(err), &cp->addr, sizeof(cp->addr)); + mgmt_pending_free(cmd); +} + static int add_device_sync(struct hci_dev *hdev, void *data) { return hci_update_passive_scan_sync(hdev); @@ -7663,6 +7681,7 @@ static int add_device_sync(struct hci_dev *hdev, void *data) static int add_device(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { + struct mgmt_pending_cmd *cmd; struct mgmt_cp_add_device *cp = data; u8 auto_conn, addr_type; struct hci_conn_params *params; @@ -7743,9 +7762,24 @@ static int add_device(struct sock *sk, struct hci_dev *hdev, current_flags = params->flags; } - err = hci_cmd_sync_queue(hdev, add_device_sync, NULL, NULL); - if (err < 0) + cmd = mgmt_pending_new(sk, MGMT_OP_ADD_DEVICE, hdev, data, len); + if (!cmd) { + err = -ENOMEM; goto unlock; + } + + cmd->user_data = UINT_PTR(current_flags); + + err = hci_cmd_sync_queue(hdev, add_device_sync, cmd, + add_device_complete); + if (err < 0) { + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE, + MGMT_STATUS_FAILED, &cp->addr, + sizeof(cp->addr)); + mgmt_pending_free(cmd); + } + + goto unlock; added: device_added(sk, hdev, &cp->addr.bdaddr, cp->addr.type, cp->action); -- 2.50.1