From f3c84a8e3e922afdcbc55f04df8fdf8a548f5a21 Mon Sep 17 00:00:00 2001 From: Nir Dotan Date: Thu, 4 Oct 2018 15:48:02 +0000 Subject: mlxsw: pci: Derive event type from event queue number Due to a hardware issue in Spectrum-2, the field event_type of the event queue element (EQE) has become reserved. It was used to distinguish between command interface completion events and completion events. Use queue number to determine event type, as command interface completion events are always received on EQ0 and mlxsw driver maps completion events to EQ1. Fixes: c3ab435466d5 ("mlxsw: spectrum: Extend to support Spectrum-2 ASIC") Signed-off-by: Nir Dotan Reviewed-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/pci.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 4d271fb3de3d..5890fdfd62c3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -718,14 +718,17 @@ static void mlxsw_pci_eq_tasklet(unsigned long data) memset(&active_cqns, 0, sizeof(active_cqns)); while ((eqe = mlxsw_pci_eq_sw_eqe_get(q))) { - u8 event_type = mlxsw_pci_eqe_event_type_get(eqe); - switch (event_type) { - case MLXSW_PCI_EQE_EVENT_TYPE_CMD: + /* Command interface completion events are always received on + * queue MLXSW_PCI_EQ_ASYNC_NUM (EQ0) and completion events + * are mapped to queue MLXSW_PCI_EQ_COMP_NUM (EQ1). + */ + switch (q->num) { + case MLXSW_PCI_EQ_ASYNC_NUM: mlxsw_pci_eq_cmd_event(mlxsw_pci, eqe); q->u.eq.ev_cmd_count++; break; - case MLXSW_PCI_EQE_EVENT_TYPE_COMP: + case MLXSW_PCI_EQ_COMP_NUM: cqn = mlxsw_pci_eqe_cqn_get(eqe); set_bit(cqn, active_cqns); cq_handle = true; -- cgit v1.2.3 From c360867ec46a4ec5cb19e5c329d65dff522cc69d Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 4 Oct 2018 15:48:03 +0000 Subject: mlxsw: spectrum: Delete RIF when VLAN device is removed In commit 602b74eda813 ("mlxsw: spectrum_switchdev: Do not leak RIFs when removing bridge") I handled the case where RIFs created for VLAN devices were not properly cleaned up when their real device (a bridge) was removed. However, I forgot to handle the case of the VLAN device itself being removed. Do so now when the VLAN device is being unlinked from its real device. Fixes: 99f44bb3527b ("mlxsw: spectrum: Enable L3 interfaces on top of bridge devices") Signed-off-by: Ido Schimmel Reviewed-by: Jiri Pirko Reported-by: Artem Shvorin Tested-by: Artem Shvorin Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index b492152c8881..30bb2c533cec 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4845,6 +4845,8 @@ static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev, upper_dev = info->upper_dev; if (info->linking) break; + if (is_vlan_dev(upper_dev)) + mlxsw_sp_rif_destroy_by_dev(mlxsw_sp, upper_dev); if (netif_is_macvlan(upper_dev)) mlxsw_sp_rif_macvlan_del(mlxsw_sp, upper_dev); break; -- cgit v1.2.3 From f7b2a56e1f3dcbdb4cf09b2b63e859ffe0e09df8 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Fri, 28 Sep 2018 17:04:30 -0600 Subject: net/usb: cancel pending work when unbinding smsc75xx Cancel pending work before freeing smsc75xx private data structure during binding. This fixes the following crash in the driver: BUG: unable to handle kernel NULL pointer dereference at 0000000000000050 IP: mutex_lock+0x2b/0x3f Workqueue: events smsc75xx_deferred_multicast_write [smsc75xx] task: ffff8caa83e85700 task.stack: ffff948b80518000 RIP: 0010:mutex_lock+0x2b/0x3f Call Trace: smsc75xx_deferred_multicast_write+0x40/0x1af [smsc75xx] process_one_work+0x18d/0x2fc worker_thread+0x1a2/0x269 ? pr_cont_work+0x58/0x58 kthread+0xfa/0x10a ? pr_cont_work+0x58/0x58 ? rcu_read_unlock_sched_notrace+0x48/0x48 ret_from_fork+0x22/0x40 Signed-off-by: Yu Zhao Signed-off-by: David S. Miller --- drivers/net/usb/smsc75xx.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers') diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index e5a4cbb366dc..ec287c9741e8 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -1520,6 +1520,7 @@ static void smsc75xx_unbind(struct usbnet *dev, struct usb_interface *intf) { struct smsc75xx_priv *pdata = (struct smsc75xx_priv *)(dev->data[0]); if (pdata) { + cancel_work_sync(&pdata->set_multicast); netif_dbg(dev, ifdown, dev->net, "free pdata\n"); kfree(pdata); pdata = NULL; -- cgit v1.2.3 From 471b83bd8bbe4e89743683ef8ecb78f7029d8288 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Mon, 1 Oct 2018 12:21:59 +0300 Subject: team: Forbid enslaving team device to itself team's ndo_add_slave() acquires 'team->lock' and later tries to open the newly enslaved device via dev_open(). This emits a 'NETDEV_UP' event that causes the VLAN driver to add VLAN 0 on the team device. team's ndo_vlan_rx_add_vid() will also try to acquire 'team->lock' and deadlock. Fix this by checking early at the enslavement function that a team device is not being enslaved to itself. A similar check was added to the bond driver in commit 09a89c219baf ("bonding: disallow enslaving a bond to itself"). WARNING: possible recursive locking detected 4.18.0-rc7+ #176 Not tainted -------------------------------------------- syz-executor4/6391 is trying to acquire lock: (____ptrval____) (&team->lock){+.+.}, at: team_vlan_rx_add_vid+0x3b/0x1e0 drivers/net/team/team.c:1868 but task is already holding lock: (____ptrval____) (&team->lock){+.+.}, at: team_add_slave+0xdb/0x1c30 drivers/net/team/team.c:1947 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&team->lock); lock(&team->lock); *** DEADLOCK *** May be due to missing lock nesting notation 2 locks held by syz-executor4/6391: #0: (____ptrval____) (rtnl_mutex){+.+.}, at: rtnl_lock net/core/rtnetlink.c:77 [inline] #0: (____ptrval____) (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x412/0xc30 net/core/rtnetlink.c:4662 #1: (____ptrval____) (&team->lock){+.+.}, at: team_add_slave+0xdb/0x1c30 drivers/net/team/team.c:1947 stack backtrace: CPU: 1 PID: 6391 Comm: syz-executor4 Not tainted 4.18.0-rc7+ #176 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1c9/0x2b4 lib/dump_stack.c:113 print_deadlock_bug kernel/locking/lockdep.c:1765 [inline] check_deadlock kernel/locking/lockdep.c:1809 [inline] validate_chain kernel/locking/lockdep.c:2405 [inline] __lock_acquire.cold.64+0x1fb/0x486 kernel/locking/lockdep.c:3435 lock_acquire+0x1e4/0x540 kernel/locking/lockdep.c:3924 __mutex_lock_common kernel/locking/mutex.c:757 [inline] __mutex_lock+0x176/0x1820 kernel/locking/mutex.c:894 mutex_lock_nested+0x16/0x20 kernel/locking/mutex.c:909 team_vlan_rx_add_vid+0x3b/0x1e0 drivers/net/team/team.c:1868 vlan_add_rx_filter_info+0x14a/0x1d0 net/8021q/vlan_core.c:210 __vlan_vid_add net/8021q/vlan_core.c:278 [inline] vlan_vid_add+0x63e/0x9d0 net/8021q/vlan_core.c:308 vlan_device_event.cold.12+0x2a/0x2f net/8021q/vlan.c:381 notifier_call_chain+0x180/0x390 kernel/notifier.c:93 __raw_notifier_call_chain kernel/notifier.c:394 [inline] raw_notifier_call_chain+0x2d/0x40 kernel/notifier.c:401 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1735 call_netdevice_notifiers net/core/dev.c:1753 [inline] dev_open+0x173/0x1b0 net/core/dev.c:1433 team_port_add drivers/net/team/team.c:1219 [inline] team_add_slave+0xa8b/0x1c30 drivers/net/team/team.c:1948 do_set_master+0x1c9/0x220 net/core/rtnetlink.c:2248 do_setlink+0xba4/0x3e10 net/core/rtnetlink.c:2382 rtnl_setlink+0x2a9/0x400 net/core/rtnetlink.c:2636 rtnetlink_rcv_msg+0x46e/0xc30 net/core/rtnetlink.c:4665 netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2455 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:4683 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x5a0/0x760 net/netlink/af_netlink.c:1343 netlink_sendmsg+0xa18/0xfd0 net/netlink/af_netlink.c:1908 sock_sendmsg_nosec net/socket.c:642 [inline] sock_sendmsg+0xd5/0x120 net/socket.c:652 ___sys_sendmsg+0x7fd/0x930 net/socket.c:2126 __sys_sendmsg+0x11d/0x290 net/socket.c:2164 __do_sys_sendmsg net/socket.c:2173 [inline] __se_sys_sendmsg net/socket.c:2171 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2171 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x456b29 Code: fd b4 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 cb b4 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f9706bf8c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f9706bf96d4 RCX: 0000000000456b29 RDX: 0000000000000000 RSI: 0000000020000240 RDI: 0000000000000004 RBP: 00000000009300a0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff R13: 00000000004d3548 R14: 00000000004c8227 R15: 0000000000000000 Fixes: 87002b03baab ("net: introduce vlan_vid_[add/del] and use them instead of direct [add/kill]_vid ndo calls") Signed-off-by: Ido Schimmel Reported-and-tested-by: syzbot+bd051aba086537515cdb@syzkaller.appspotmail.com Signed-off-by: David S. Miller --- drivers/net/team/team.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'drivers') diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 6a047d30e8c6..d887016e54b6 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1167,6 +1167,12 @@ static int team_port_add(struct team *team, struct net_device *port_dev, return -EBUSY; } + if (dev == port_dev) { + NL_SET_ERR_MSG(extack, "Cannot enslave team device to itself"); + netdev_err(dev, "Cannot enslave team device to itself\n"); + return -EINVAL; + } + if (port_dev->features & NETIF_F_VLAN_CHALLENGED && vlan_uses_dev(dev)) { NL_SET_ERR_MSG(extack, "Device is VLAN challenged and team device has VLAN set up"); -- cgit v1.2.3 From dbe80d446c859873820eedfff4abc61c71f1927b Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Fri, 5 Oct 2018 00:26:00 -0400 Subject: bnxt_en: Fix VNIC reservations on the PF. The enables bit for VNIC was set wrong when calling the HWRM_FUNC_CFG firmware call to reserve VNICs. This has the effect that the firmware will keep a large number of VNICs for the PF, and having very few for VFs. DPDK driver running on the VFs, which requires more VNICs, may not work properly as a result. Fixes: 674f50a5b026 ("bnxt_en: Implement new method to reserve rings.") Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 0478e562abac..2564a92dcb02 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4650,7 +4650,7 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, struct hwrm_func_cfg_input *req, FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0; enables |= ring_grps ? FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS : 0; - enables |= vnics ? FUNC_VF_CFG_REQ_ENABLES_NUM_VNICS : 0; + enables |= vnics ? FUNC_CFG_REQ_ENABLES_NUM_VNICS : 0; req->num_rx_rings = cpu_to_le16(rx_rings); req->num_hw_ring_grps = cpu_to_le16(ring_grps); -- cgit v1.2.3 From 5db0e0969af6501ad45fe0494039d3b9c797822b Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Fri, 5 Oct 2018 00:26:01 -0400 Subject: bnxt_en: Fix enables field in HWRM_QUEUE_COS2BW_CFG request In HWRM_QUEUE_COS2BW_CFG request, enables field should have the bits set only for the queue ids which are having the valid parameters. This causes firmware to return error when the TC to hardware CoS queue mapping is not 1:1 during DCBNL ETS setup. Fixes: 2e8ef77ee0ff ("bnxt_en: Add TC to hardware QoS queue mapping logic.") Signed-off-by: Vasundhara Volam Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c index ddc98c359488..a85d2be986af 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c @@ -98,13 +98,13 @@ static int bnxt_hwrm_queue_cos2bw_cfg(struct bnxt *bp, struct ieee_ets *ets, bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_COS2BW_CFG, -1, -1); for (i = 0; i < max_tc; i++) { - u8 qidx; + u8 qidx = bp->tc_to_qidx[i]; req.enables |= cpu_to_le32( - QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID0_VALID << i); + QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID0_VALID << + qidx); memset(&cos2bw, 0, sizeof(cos2bw)); - qidx = bp->tc_to_qidx[i]; cos2bw.queue_id = bp->q_info[qidx].queue_id; if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_STRICT) { cos2bw.tsa = -- cgit v1.2.3 From a2bf74f4e1b82395dad2b08d2a911d9151db71c1 Mon Sep 17 00:00:00 2001 From: Venkat Duvvuru Date: Fri, 5 Oct 2018 00:26:02 -0400 Subject: bnxt_en: free hwrm resources, if driver probe fails. When the driver probe fails, all the resources that were allocated prior to the failure must be freed. However, hwrm dma response memory is not getting freed. This patch fixes the problem described above. Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.") Signed-off-by: Venkat Duvvuru Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 2564a92dcb02..3718984a8185 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3017,10 +3017,11 @@ static void bnxt_free_hwrm_resources(struct bnxt *bp) { struct pci_dev *pdev = bp->pdev; - dma_free_coherent(&pdev->dev, PAGE_SIZE, bp->hwrm_cmd_resp_addr, - bp->hwrm_cmd_resp_dma_addr); - - bp->hwrm_cmd_resp_addr = NULL; + if (bp->hwrm_cmd_resp_addr) { + dma_free_coherent(&pdev->dev, PAGE_SIZE, bp->hwrm_cmd_resp_addr, + bp->hwrm_cmd_resp_dma_addr); + bp->hwrm_cmd_resp_addr = NULL; + } } static int bnxt_alloc_hwrm_resources(struct bnxt *bp) @@ -9057,6 +9058,7 @@ init_err_cleanup_tc: bnxt_clear_int_mode(bp); init_err_pci_clean: + bnxt_free_hwrm_resources(bp); bnxt_cleanup_pci(bp); init_err_free: -- cgit v1.2.3 From c78fe058879bdea919d44f23e21da26f603e9166 Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Fri, 5 Oct 2018 00:26:03 -0400 Subject: bnxt_en: get the reduced max_irqs by the ones used by RDMA When getting the max rings supported, get the reduced max_irqs by the ones used by RDMA. If the number MSIX is the limiting factor, this bug may cause the max ring count to be higher than it should be when RDMA driver is loaded and may result in ring allocation failures. Fixes: 30f529473ec9 ("bnxt_en: Do not modify max IRQ count after RDMA driver requests/frees IRQs.") Signed-off-by: Vasundhara Volam Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 3718984a8185..e2d92548226a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -8622,7 +8622,7 @@ static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx, *max_tx = hw_resc->max_tx_rings; *max_rx = hw_resc->max_rx_rings; *max_cp = min_t(int, bnxt_get_max_func_cp_rings_for_en(bp), - hw_resc->max_irqs); + hw_resc->max_irqs - bnxt_get_ulp_msix_num(bp)); *max_cp = min_t(int, *max_cp, hw_resc->max_stat_ctxs); max_ring_grps = hw_resc->max_hw_ring_grps; if (BNXT_CHIP_TYPE_NITRO_A0(bp) && BNXT_PF(bp)) { -- cgit v1.2.3 From ca8931948344c485569b04821d1f6bcebccd376b Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 4 Oct 2018 20:24:13 -0700 Subject: net: dsa: b53: Keep CPU port as tagged in all VLANs Commit c499696e7901 ("net: dsa: b53: Stop using dev->cpu_port incorrectly") was a bit too trigger happy in removing the CPU port from the VLAN membership because we rely on DSA to program the CPU port VLAN, which it does, except it does not bother itself with tagged/untagged and just usese untagged. Having the CPU port "follow" the user ports tagged/untagged is not great and does not allow for properly differentiating, so keep the CPU port tagged in all VLANs. Reported-by: Gerhard Wiesinger Fixes: c499696e7901 ("net: dsa: b53: Stop using dev->cpu_port incorrectly") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/b53/b53_common.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index d93c790bfbe8..ad534b90ef21 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1107,7 +1107,7 @@ void b53_vlan_add(struct dsa_switch *ds, int port, b53_get_vlan_entry(dev, vid, vl); vl->members |= BIT(port); - if (untagged) + if (untagged && !dsa_is_cpu_port(ds, port)) vl->untag |= BIT(port); else vl->untag &= ~BIT(port); @@ -1149,7 +1149,7 @@ int b53_vlan_del(struct dsa_switch *ds, int port, pvid = 0; } - if (untagged) + if (untagged && !dsa_is_cpu_port(ds, port)) vl->untag &= ~(BIT(port)); b53_set_vlan_entry(dev, vid, vl); -- cgit v1.2.3 From 2d52527e80c2dc0c5f43f50adf183781262ec565 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Wed, 3 Oct 2018 15:20:58 +0200 Subject: be2net: don't flip hw_features when VXLANs are added/deleted the be2net implementation of .ndo_tunnel_{add,del}() changes the value of NETIF_F_GSO_UDP_TUNNEL bit in 'features' and 'hw_features', but it forgets to call netdev_features_change(). Moreover, ethtool setting for that bit can potentially be reverted after a tunnel is added or removed. GSO already does software segmentation when 'hw_enc_features' is 0, even if VXLAN offload is turned on. In addition, commit 096de2f83ebc ("benet: stricter vxlan offloading check in be_features_check") avoids hardware segmentation of non-VXLAN tunneled packets, or VXLAN packets having wrong destination port. So, it's safe to avoid flipping the above feature on addition/deletion of VXLAN tunnels. Fixes: 630f4b70567f ("be2net: Export tunnel offloads only when a VxLAN tunnel is created") Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_main.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 74d122616e76..534787291b44 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -4002,8 +4002,6 @@ static int be_enable_vxlan_offloads(struct be_adapter *adapter) netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_UDP_TUNNEL; - netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; - netdev->features |= NETIF_F_GSO_UDP_TUNNEL; dev_info(dev, "Enabled VxLAN offloads for UDP port %d\n", be16_to_cpu(port)); @@ -4025,8 +4023,6 @@ static void be_disable_vxlan_offloads(struct be_adapter *adapter) adapter->vxlan_port = 0; netdev->hw_enc_features = 0; - netdev->hw_features &= ~(NETIF_F_GSO_UDP_TUNNEL); - netdev->features &= ~(NETIF_F_GSO_UDP_TUNNEL); } static void be_calculate_vf_res(struct be_adapter *adapter, u16 num_vfs, @@ -5320,6 +5316,7 @@ static void be_netdev_init(struct net_device *netdev) struct be_adapter *adapter = netdev_priv(netdev); netdev->hw_features |= NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_GSO_UDP_TUNNEL | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX; if ((be_if_cap_flags(adapter) & BE_IF_FLAGS_RSS)) -- cgit v1.2.3 From 7e4183752735deb7543e179a44f4f4b44917cd6f Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Wed, 3 Oct 2018 19:04:49 +0300 Subject: net: phy: phylink: fix SFP interface autodetection When connecting SFP PHY to phylink use the detected interface. Otherwise, the link fails to come up when the configured 'phy-mode' differs from the SFP detected mode. Move most of phylink_connect_phy() into __phylink_connect_phy(), and leave phylink_connect_phy() as a wrapper. phylink_sfp_connect_phy() can now pass the SFP detected PHY interface to __phylink_connect_phy(). This fixes 1GB SFP module link up on eth3 of the Macchiatobin board that is configured in the DT to "2500base-x" phy-mode. Fixes: 9525ae83959b6 ("phylink: add phylink infrastructure") Suggested-by: Russell King Signed-off-by: Baruch Siach Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 48 +++++++++++++++++++++++++++-------------------- 1 file changed, 28 insertions(+), 20 deletions(-) (limited to 'drivers') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 3ba5cf2a8a5f..7abca86c3aa9 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -717,6 +717,30 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy) return 0; } +static int __phylink_connect_phy(struct phylink *pl, struct phy_device *phy, + phy_interface_t interface) +{ + int ret; + + if (WARN_ON(pl->link_an_mode == MLO_AN_FIXED || + (pl->link_an_mode == MLO_AN_INBAND && + phy_interface_mode_is_8023z(interface)))) + return -EINVAL; + + if (pl->phydev) + return -EBUSY; + + ret = phy_attach_direct(pl->netdev, phy, 0, interface); + if (ret) + return ret; + + ret = phylink_bringup_phy(pl, phy); + if (ret) + phy_detach(phy); + + return ret; +} + /** * phylink_connect_phy() - connect a PHY to the phylink instance * @pl: a pointer to a &struct phylink returned from phylink_create() @@ -734,31 +758,13 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy) */ int phylink_connect_phy(struct phylink *pl, struct phy_device *phy) { - int ret; - - if (WARN_ON(pl->link_an_mode == MLO_AN_FIXED || - (pl->link_an_mode == MLO_AN_INBAND && - phy_interface_mode_is_8023z(pl->link_interface)))) - return -EINVAL; - - if (pl->phydev) - return -EBUSY; - /* Use PHY device/driver interface */ if (pl->link_interface == PHY_INTERFACE_MODE_NA) { pl->link_interface = phy->interface; pl->link_config.interface = pl->link_interface; } - ret = phy_attach_direct(pl->netdev, phy, 0, pl->link_interface); - if (ret) - return ret; - - ret = phylink_bringup_phy(pl, phy); - if (ret) - phy_detach(phy); - - return ret; + return __phylink_connect_phy(pl, phy, pl->link_interface); } EXPORT_SYMBOL_GPL(phylink_connect_phy); @@ -1672,7 +1678,9 @@ static void phylink_sfp_link_up(void *upstream) static int phylink_sfp_connect_phy(void *upstream, struct phy_device *phy) { - return phylink_connect_phy(upstream, phy); + struct phylink *pl = upstream; + + return __phylink_connect_phy(upstream, phy, pl->link_config.interface); } static void phylink_sfp_disconnect_phy(void *upstream) -- cgit v1.2.3 From 2c05d88818ab6571816b93edce4d53703870d7ae Mon Sep 17 00:00:00 2001 From: Wenwen Wang Date: Fri, 5 Oct 2018 08:48:27 -0500 Subject: net: cxgb3_main: fix a missing-check bug In cxgb_extension_ioctl(), the command of the ioctl is firstly copied from the user-space buffer 'useraddr' to 'cmd' and checked through the switch statement. If the command is not as expected, an error code EOPNOTSUPP is returned. In the following execution, i.e., the cases of the switch statement, the whole buffer of 'useraddr' is copied again to a specific data structure, according to what kind of command is requested. However, after the second copy, there is no re-check on the newly-copied command. Given that the buffer 'useraddr' is in the user space, a malicious user can race to change the command between the two copies. By doing so, the attacker can supply malicious data to the kernel and cause undefined behavior. This patch adds a re-check in each case of the switch statement if there is a second copy in that case, to re-check whether the command obtained in the second copy is the same as the one in the first copy. If not, an error code EINVAL is returned. Signed-off-by: Wenwen Wang Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'drivers') diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index a19172dbe6be..c34ea385fe4a 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -2159,6 +2159,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EPERM; if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT; + if (t.cmd != CHELSIO_SET_QSET_PARAMS) + return -EINVAL; if (t.qset_idx >= SGE_QSETS) return -EINVAL; if (!in_range(t.intr_lat, 0, M_NEWTIMER) || @@ -2258,6 +2260,9 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT; + if (t.cmd != CHELSIO_GET_QSET_PARAMS) + return -EINVAL; + /* Display qsets for all ports when offload enabled */ if (test_bit(OFFLOAD_DEVMAP_BIT, &adapter->open_device_map)) { q1 = 0; @@ -2303,6 +2308,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EBUSY; if (copy_from_user(&edata, useraddr, sizeof(edata))) return -EFAULT; + if (edata.cmd != CHELSIO_SET_QSET_NUM) + return -EINVAL; if (edata.val < 1 || (edata.val > 1 && !(adapter->flags & USING_MSIX))) return -EINVAL; @@ -2343,6 +2350,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EPERM; if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT; + if (t.cmd != CHELSIO_LOAD_FW) + return -EINVAL; /* Check t.len sanity ? */ fw_data = memdup_user(useraddr + sizeof(t), t.len); if (IS_ERR(fw_data)) @@ -2366,6 +2375,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EBUSY; if (copy_from_user(&m, useraddr, sizeof(m))) return -EFAULT; + if (m.cmd != CHELSIO_SETMTUTAB) + return -EINVAL; if (m.nmtus != NMTUS) return -EINVAL; if (m.mtus[0] < 81) /* accommodate SACK */ @@ -2407,6 +2418,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EBUSY; if (copy_from_user(&m, useraddr, sizeof(m))) return -EFAULT; + if (m.cmd != CHELSIO_SET_PM) + return -EINVAL; if (!is_power_of_2(m.rx_pg_sz) || !is_power_of_2(m.tx_pg_sz)) return -EINVAL; /* not power of 2 */ @@ -2440,6 +2453,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EIO; /* need the memory controllers */ if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT; + if (t.cmd != CHELSIO_GET_MEM) + return -EINVAL; if ((t.addr & 7) || (t.len & 7)) return -EINVAL; if (t.mem_id == MEM_CM) @@ -2492,6 +2507,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EAGAIN; if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT; + if (t.cmd != CHELSIO_SET_TRACE_FILTER) + return -EINVAL; tp = (const struct trace_params *)&t.sip; if (t.config_tx) -- cgit v1.2.3 From 0781168e23a2fc8dceb989f11fc5b39b3ccacc35 Mon Sep 17 00:00:00 2001 From: Wenwen Wang Date: Fri, 5 Oct 2018 10:59:36 -0500 Subject: yam: fix a missing-check bug In yam_ioctl(), the concrete ioctl command is firstly copied from the user-space buffer 'ifr->ifr_data' to 'ioctl_cmd' and checked through the following switch statement. If the command is not as expected, an error code EINVAL is returned. In the following execution the buffer 'ifr->ifr_data' is copied again in the cases of the switch statement to specific data structures according to what kind of ioctl command is requested. However, after the second copy, no re-check is enforced on the newly-copied command. Given that the buffer 'ifr->ifr_data' is in the user space, a malicious user can race to change the command between the two copies. This way, the attacker can inject inconsistent data and cause undefined behavior. This patch adds a re-check in each case of the switch statement if there is a second copy in that case, to re-check whether the command obtained in the second copy is the same as the one in the first copy. If not, an error code EINVAL will be returned. Signed-off-by: Wenwen Wang Signed-off-by: David S. Miller --- drivers/net/hamradio/yam.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'drivers') diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c index 16ec7af6ab7b..ba9df430fca6 100644 --- a/drivers/net/hamradio/yam.c +++ b/drivers/net/hamradio/yam.c @@ -966,6 +966,8 @@ static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) sizeof(struct yamdrv_ioctl_mcs)); if (IS_ERR(ym)) return PTR_ERR(ym); + if (ym->cmd != SIOCYAMSMCS) + return -EINVAL; if (ym->bitrate > YAM_MAXBITRATE) { kfree(ym); return -EINVAL; @@ -981,6 +983,8 @@ static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (copy_from_user(&yi, ifr->ifr_data, sizeof(struct yamdrv_ioctl_cfg))) return -EFAULT; + if (yi.cmd != SIOCYAMSCFG) + return -EINVAL; if ((yi.cfg.mask & YAM_IOBASE) && netif_running(dev)) return -EINVAL; /* Cannot change this parameter when up */ if ((yi.cfg.mask & YAM_IRQ) && netif_running(dev)) -- cgit v1.2.3 From 35f3625c21852ad839f20c91c7d81c4c1101e207 Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Fri, 5 Oct 2018 09:04:40 +0200 Subject: net: mvpp2: Extract the correct ethtype from the skb for tx csum offload When offloading the L3 and L4 csum computation on TX, we need to extract the l3_proto from the ethtype, independently of the presence of a vlan tag. The actual driver uses skb->protocol as-is, resulting in packets with the wrong L4 checksum being sent when there's a vlan tag in the packet header and checksum offloading is enabled. This commit makes use of vlan_protocol_get() to get the correct ethtype regardless the presence of a vlan tag. Fixes: 3f518509dedc ("ethernet: Add new driver for Marvell Armada 375 network unit") Signed-off-by: Maxime Chevallier Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 38cc01beea79..a74002b43b51 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -1725,7 +1725,7 @@ static void mvpp2_txq_desc_put(struct mvpp2_tx_queue *txq) } /* Set Tx descriptors fields relevant for CSUM calculation */ -static u32 mvpp2_txq_desc_csum(int l3_offs, int l3_proto, +static u32 mvpp2_txq_desc_csum(int l3_offs, __be16 l3_proto, int ip_hdr_len, int l4_proto) { u32 command; @@ -2600,14 +2600,15 @@ static u32 mvpp2_skb_tx_csum(struct mvpp2_port *port, struct sk_buff *skb) if (skb->ip_summed == CHECKSUM_PARTIAL) { int ip_hdr_len = 0; u8 l4_proto; + __be16 l3_proto = vlan_get_protocol(skb); - if (skb->protocol == htons(ETH_P_IP)) { + if (l3_proto == htons(ETH_P_IP)) { struct iphdr *ip4h = ip_hdr(skb); /* Calculate IPv4 checksum and L4 checksum */ ip_hdr_len = ip4h->ihl; l4_proto = ip4h->protocol; - } else if (skb->protocol == htons(ETH_P_IPV6)) { + } else if (l3_proto == htons(ETH_P_IPV6)) { struct ipv6hdr *ip6h = ipv6_hdr(skb); /* Read l4_protocol from one of IPv6 extra headers */ @@ -2619,7 +2620,7 @@ static u32 mvpp2_skb_tx_csum(struct mvpp2_port *port, struct sk_buff *skb) } return mvpp2_txq_desc_csum(skb_network_offset(skb), - skb->protocol, ip_hdr_len, l4_proto); + l3_proto, ip_hdr_len, l4_proto); } return MVPP2_TXD_L4_CSUM_NOT | MVPP2_TXD_IP_CSUM_DISABLE; -- cgit v1.2.3