From 4e046de0f50e04acd48eb373d6a9061ddf014e0c Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Sun, 13 Jan 2019 22:47:26 -0600 Subject: Revert "net/mlx5e: E-Switch, Initialize eswitch only if eswitch manager" This reverts commit 5f5991f36dce1e69dd8bd7495763eec2e28f08e7. With the original commit, eswitch instance will not be initialized for a function which is vport group manager but not eswitch manager such as host PF on SmartNIC (BlueField) card. This will result in a kernel crash when such a vport group manager is trying to access vports in its group. E.g, PF vport manager (not eswitch manager) tries to configure the MAC of its VF vport, a kernel trace will happen similar as bellow: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 ... RIP: 0010:mlx5_eswitch_get_vport_config+0xc/0x180 [mlx5_core] ... Fixes: 5f5991f36dce ("net/mlx5e: E-Switch, Initialize eswitch only if eswitch manager") Signed-off-by: Bodong Wang Reported-by: Yuval Avnery Reviewed-by: Daniel Jurgens Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index a44ea7b85614..ab7a038c207c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1728,7 +1728,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) int vport_num; int err; - if (!MLX5_ESWITCH_MANAGER(dev)) + if (!MLX5_VPORT_MANAGER(dev)) return 0; esw_info(dev, @@ -1797,7 +1797,7 @@ abort: void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) { - if (!esw || !MLX5_ESWITCH_MANAGER(esw->dev)) + if (!esw || !MLX5_VPORT_MANAGER(esw->dev)) return; esw_info(esw->dev, "cleanup\n"); -- cgit v1.2.3 From 92b32772940b981240f6471a70c0fdbff23983ea Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Sun, 6 Jan 2019 17:55:59 +0200 Subject: net/mlx5e: Fix wrong private flag usage causing checksum disable MLX5E_PFLAG_* definitions were changed from bitmask to enumerated values. However, in mlx5e_open_rq(), the proper API (MLX5E_GET_PFLAG macro) was not used to read the flag value of MLX5E_PFLAG_RX_NO_CSUM_COMPLETE. Fixed it. Fixes: 8ff57c18e9f6 ("net/mlx5e: Improve ethtool private-flags code structure") Signed-off-by: Shay Agroskin Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 8cfd2ec7c0a2..01819e5c9975 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -950,7 +950,7 @@ static int mlx5e_open_rq(struct mlx5e_channel *c, if (params->rx_dim_enabled) __set_bit(MLX5E_RQ_STATE_AM, &c->rq.state); - if (params->pflags & MLX5E_PFLAG_RX_NO_CSUM_COMPLETE) + if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE)) __set_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &c->rq.state); return 0; -- cgit v1.2.3 From 33814e5d127e21f53b52e17b0722c1b57d4f4d29 Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Wed, 26 Dec 2018 19:21:21 +0200 Subject: net/mlx5: Take lock with IRQs disabled to avoid deadlock The lock in qp_table might be taken from process context or from interrupt context. This may lead to a deadlock unless it is taken with IRQs disabled. Discovered by lockdep ================================ WARNING: inconsistent lock state 4.20.0-rc6 -------------------------------- inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} python/12572 [HC1[1]:SC0[0]:HE0:SE1] takes: 00000000052a4df4 (&(&table->lock)->rlock#2){?.+.}, /0x50 [mlx5_core] {HARDIRQ-ON-W} state was registered at: _raw_spin_lock+0x33/0x70 mlx5_get_rsc+0x1a/0x50 [mlx5_core] mlx5_ib_eqe_pf_action+0x493/0x1be0 [mlx5_ib] process_one_work+0x90c/0x1820 worker_thread+0x87/0xbb0 kthread+0x320/0x3e0 ret_from_fork+0x24/0x30 irq event stamp: 103928 hardirqs last enabled at (103927): [] nk+0x1a/0x1c hardirqs last disabled at (103928): [] unk+0x1a/0x1c softirqs last enabled at (103924): [] tcp_sendmsg+0x31/0x40 softirqs last disabled at (103922): [] 80 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&(&table->lock)->rlock#2); lock(&(&table->lock)->rlock#2); *** DEADLOCK *** Fixes: 032080ab43ac ("IB/mlx5: Lock QP during page fault handling") Signed-off-by: Moni Shoua Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/qp.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index 388f205a497f..370ca94b6775 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -44,14 +44,15 @@ static struct mlx5_core_rsc_common * mlx5_get_rsc(struct mlx5_qp_table *table, u32 rsn) { struct mlx5_core_rsc_common *common; + unsigned long flags; - spin_lock(&table->lock); + spin_lock_irqsave(&table->lock, flags); common = radix_tree_lookup(&table->tree, rsn); if (common) atomic_inc(&common->refcount); - spin_unlock(&table->lock); + spin_unlock_irqrestore(&table->lock, flags); return common; } -- cgit v1.2.3 From 9d2cbdc5d334967c35b5f58c7bf3208e17325647 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Mon, 24 Dec 2018 09:48:42 +0200 Subject: net/mlx5e: Allow MAC invalidation while spoofchk is ON Prior to this patch the driver prohibited spoof checking on invalid MAC. Now the user can set this configuration if it wishes to. This is required since libvirt might invalidate the VF Mac by setting it to zero, while spoofcheck is ON. Fixes: 1ab2068a4c66 ("net/mlx5: Implement vports admin state backup/restore") Signed-off-by: Aya Levin Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index ab7a038c207c..5b492b67f4e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1134,13 +1134,6 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw, int err = 0; u8 *smac_v; - if (vport->info.spoofchk && !is_valid_ether_addr(vport->info.mac)) { - mlx5_core_warn(esw->dev, - "vport[%d] configure ingress rules failed, illegal mac with spoofchk\n", - vport->vport); - return -EPERM; - } - esw_vport_cleanup_ingress_rules(esw, vport); if (!vport->info.vlan && !vport->info.qos && !vport->info.spoofchk) { @@ -1827,13 +1820,10 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw, mutex_lock(&esw->state_lock); evport = &esw->vports[vport]; - if (evport->info.spoofchk && !is_valid_ether_addr(mac)) { + if (evport->info.spoofchk && !is_valid_ether_addr(mac)) mlx5_core_warn(esw->dev, - "MAC invalidation is not allowed when spoofchk is on, vport(%d)\n", + "Set invalid MAC while spoofchk is on, vport(%d)\n", vport); - err = -EPERM; - goto unlock; - } err = mlx5_modify_nic_vport_mac_address(esw->dev, vport, mac); if (err) { @@ -1979,6 +1969,10 @@ int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw, evport = &esw->vports[vport]; pschk = evport->info.spoofchk; evport->info.spoofchk = spoofchk; + if (pschk && !is_valid_ether_addr(evport->info.mac)) + mlx5_core_warn(esw->dev, + "Spoofchk in set while MAC is invalid, vport(%d)\n", + evport->vport); if (evport->enabled && esw->mode == SRIOV_LEGACY) err = esw_vport_ingress_config(esw, evport); if (err) -- cgit v1.2.3 From c12ecc2305648822970002871230979359edb2c0 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Wed, 25 Apr 2018 17:32:04 +0300 Subject: net/mlx5e: Move to use common phys port names for vport representors With VF LAG commit 491c37e49b48 "net/mlx5e: In case of LAG, one switch parent id is used for all representors", both uplinks and all the VFs (on both of them) get the same switchdev id. This cause the provisioning system method to identify the rep of a given VF from the parent PF PCI device using switchev id and physical port name to break, since VFm of PF0 will have the (id, name) as VFm of PF1. To fix that, we align to use the framework agreed upstream and set by nfp commit 168c478e107e "nfp: wire get_phys_port_name on representors": $ cat /sys/class/net/eth4_*/phys_port_name p0 pf0vf0 pf0vf1 Now, the names will be different, e.g. pf0vf0 vs. pf1vf0. Fixes: 491c37e49b48 ("net/mlx5e: In case of LAG, one switch parent id is used for all representors") Signed-off-by: Or Gerlitz Reported-by: Waleed Musa Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 12 ++++++++++-- drivers/net/ethernet/mellanox/mlx5/core/lag.c | 21 +++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h | 2 ++ 3 files changed, 33 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 04736212a21c..f75227222db3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1126,9 +1126,17 @@ static int mlx5e_rep_get_phys_port_name(struct net_device *dev, struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep = rpriv->rep; - int ret; + int ret, pf_num; + + ret = mlx5_lag_get_pf_num(priv->mdev, &pf_num); + if (ret) + return ret; + + if (rep->vport == FDB_UPLINK_VPORT) + ret = snprintf(buf, len, "p%d", pf_num); + else + ret = snprintf(buf, len, "pf%dvf%d", pf_num, rep->vport - 1); - ret = snprintf(buf, len, "%d", rep->vport - 1); if (ret >= len) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index 3a6baed722d8..2d223385dc81 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -616,6 +616,27 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev) } } +int mlx5_lag_get_pf_num(struct mlx5_core_dev *dev, int *pf_num) +{ + struct mlx5_lag *ldev; + int n; + + ldev = mlx5_lag_dev_get(dev); + if (!ldev) { + mlx5_core_warn(dev, "no lag device, can't get pf num\n"); + return -EINVAL; + } + + for (n = 0; n < MLX5_MAX_PORTS; n++) + if (ldev->pf[n].dev == dev) { + *pf_num = n; + return 0; + } + + mlx5_core_warn(dev, "wasn't able to locate pf in the lag device\n"); + return -EINVAL; +} + /* Must be called with intf_mutex held */ void mlx5_lag_remove(struct mlx5_core_dev *dev) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index c68dcea5985b..5300b0b6d836 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -187,6 +187,8 @@ static inline int mlx5_lag_is_lacp_owner(struct mlx5_core_dev *dev) MLX5_CAP_GEN(dev, lag_master); } +int mlx5_lag_get_pf_num(struct mlx5_core_dev *dev, int *pf_num); + void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol); void mlx5_lag_update(struct mlx5_core_dev *dev); -- cgit v1.2.3 From 6ce966fd2671899a48037abe7bf1df80a5adf029 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Tue, 1 Jan 2019 12:44:52 +0200 Subject: net/mlx5e: Unblock setting vid 0 for VFs through the uplink rep It turns out that libvirt uses 0-vid as a default if no vlan was set for the guest (which is the case for switchdev mode) and errs if we disallow that: error: Failed to start domain vm75 error: Cannot set interface MAC/vlanid to 6a:66:2d:48:92:c2/0 \ for ifname enp59s0f0 vf 0: Operation not supported So allow this in order not to break existing systems. Signed-off-by: Or Gerlitz Reported-by: Maor Dickman Reviewed-by: Gavi Teitz Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'drivers') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index f75227222db3..f2573c2d2b5c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1293,6 +1293,18 @@ static int mlx5e_uplink_rep_set_mac(struct net_device *netdev, void *addr) return 0; } +static int mlx5e_uplink_rep_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos, + __be16 vlan_proto) +{ + netdev_warn_once(dev, "legacy vf vlan setting isn't supported in switchdev mode\n"); + + if (vlan != 0) + return -EOPNOTSUPP; + + /* allow setting 0-vid for compatibility with libvirt */ + return 0; +} + static const struct switchdev_ops mlx5e_rep_switchdev_ops = { .switchdev_port_attr_get = mlx5e_attr_get, }; @@ -1327,6 +1339,7 @@ static const struct net_device_ops mlx5e_netdev_ops_uplink_rep = { .ndo_set_vf_rate = mlx5e_set_vf_rate, .ndo_get_vf_config = mlx5e_get_vf_config, .ndo_get_vf_stats = mlx5e_get_vf_stats, + .ndo_set_vf_vlan = mlx5e_uplink_rep_set_vf_vlan, }; bool mlx5e_eswitch_rep(struct net_device *netdev) -- cgit v1.2.3 From 6571ebce112a21ec9be68ef2f53b96fcd41fd81b Mon Sep 17 00:00:00 2001 From: Tomonori Sakita Date: Fri, 25 Jan 2019 11:02:22 +0900 Subject: net: altera_tse: fix msgdma_tx_completion on non-zero fill_level case If fill_level was not zero and status was not BUSY, result of "tx_prod - tx_cons - inuse" might be zero. Subtracting 1 unconditionally results invalid negative return value on this case. Make sure not to return an negative value. Signed-off-by: Tomonori Sakita Signed-off-by: Atsushi Nemoto Reviewed-by: Dalon L Westergreen Acked-by: Thor Thayer Signed-off-by: David S. Miller --- drivers/net/ethernet/altera/altera_msgdma.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/altera/altera_msgdma.c b/drivers/net/ethernet/altera/altera_msgdma.c index 0fb986ba3290..0ae723f75341 100644 --- a/drivers/net/ethernet/altera/altera_msgdma.c +++ b/drivers/net/ethernet/altera/altera_msgdma.c @@ -145,7 +145,8 @@ u32 msgdma_tx_completions(struct altera_tse_private *priv) & 0xffff; if (inuse) { /* Tx FIFO is not empty */ - ready = priv->tx_prod - priv->tx_cons - inuse - 1; + ready = max_t(int, + priv->tx_prod - priv->tx_cons - inuse - 1, 0); } else { /* Check for buffered last packet */ status = csrrd32(priv->tx_dma_csr, msgdma_csroffs(status)); -- cgit v1.2.3 From 263c6d75f9a544a3c2f8f6a26de4f4808d8f59cf Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Sat, 26 Jan 2019 17:18:25 +0800 Subject: net: hns: Fix for missing of_node_put() after of_parse_phandle() In hns enet driver, we use of_parse_handle() to get hold of the device node related to "ae-handle" but we have missed to put the node reference using of_node_put() after we are done using the node. This patch fixes it. Note: This problem is stated in Link: https://lkml.org/lkml/2018/12/22/217 Fixes: 48189d6aaf1e ("net: hns: enet specifies a reference to dsaf") Reported-by: Alexey Khoroshilov Signed-off-by: Yonglong Liu Signed-off-by: Peng Li Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'drivers') diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 5b33238c6680..60e7d7ae3787 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -2418,6 +2418,8 @@ static int hns_nic_dev_probe(struct platform_device *pdev) out_notify_fail: (void)cancel_work_sync(&priv->service_task); out_read_prop_fail: + /* safe for ACPI FW */ + of_node_put(to_of_node(priv->fwnode)); free_netdev(ndev); return ret; } @@ -2447,6 +2449,9 @@ static int hns_nic_dev_remove(struct platform_device *pdev) set_bit(NIC_STATE_REMOVING, &priv->state); (void)cancel_work_sync(&priv->service_task); + /* safe for ACPI FW */ + of_node_put(to_of_node(priv->fwnode)); + free_netdev(ndev); return 0; } -- cgit v1.2.3 From ed29ca8b9592562559c64d027fb5eb126e463e2c Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Sat, 26 Jan 2019 17:18:26 +0800 Subject: net: hns: Restart autoneg need return failed when autoneg off The hns driver of earlier devices, when autoneg off, restart autoneg will return -EINVAL, so make the hns driver for the latest devices do the same. Signed-off-by: Yonglong Liu Signed-off-by: Peng Li Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_ethtool.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 8e9b95871d30..ce15d2350db9 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -1157,16 +1157,18 @@ static int hns_get_regs_len(struct net_device *net_dev) */ static int hns_nic_nway_reset(struct net_device *netdev) { - int ret = 0; struct phy_device *phy = netdev->phydev; - if (netif_running(netdev)) { - /* if autoneg is disabled, don't restart auto-negotiation */ - if (phy && phy->autoneg == AUTONEG_ENABLE) - ret = genphy_restart_aneg(phy); - } + if (!netif_running(netdev)) + return 0; - return ret; + if (!phy) + return -EOPNOTSUPP; + + if (phy->autoneg != AUTONEG_ENABLE) + return -EINVAL; + + return genphy_restart_aneg(phy); } static u32 -- cgit v1.2.3 From cec8abba13e6a26729dfed41019720068eeeff2b Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Sat, 26 Jan 2019 17:18:27 +0800 Subject: net: hns: Fix wrong read accesses via Clause 45 MDIO protocol When reading phy registers via Clause 45 MDIO protocol, after write address operation, the driver use another write address operation, so can not read the right value of any phy registers. This patch fixes it. Signed-off-by: Yonglong Liu Signed-off-by: Peng Li Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns_mdio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c index 017e08452d8c..baf5cc251f32 100644 --- a/drivers/net/ethernet/hisilicon/hns_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns_mdio.c @@ -321,7 +321,7 @@ static int hns_mdio_read(struct mii_bus *bus, int phy_id, int regnum) } hns_mdio_cmd_write(mdio_dev, is_c45, - MDIO_C45_WRITE_ADDR, phy_id, devad); + MDIO_C45_READ, phy_id, devad); } /* Step 5: waitting for MDIO_COMMAND_REG 's mdio_start==0,*/ -- cgit v1.2.3 From c69c29a1a0a8f68cd87e98ba4a5a79fb8ef2a58c Mon Sep 17 00:00:00 2001 From: Alexey Khoroshilov Date: Sat, 26 Jan 2019 22:48:57 +0300 Subject: net: stmmac: dwmac-rk: fix error handling in rk_gmac_powerup() If phy_power_on() fails in rk_gmac_powerup(), clocks are left enabled. Found by Linux Driver Verification project (linuxtesting.org). Signed-off-by: Alexey Khoroshilov Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 7b923362ee55..3b174eae77c1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -1342,8 +1342,10 @@ static int rk_gmac_powerup(struct rk_priv_data *bsp_priv) } ret = phy_power_on(bsp_priv, true); - if (ret) + if (ret) { + gmac_clk_enable(bsp_priv, false); return ret; + } pm_runtime_enable(dev); pm_runtime_get_sync(dev); -- cgit v1.2.3 From 6fb6e6371f8c463020a41cc0ed1915e140219c3d Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 27 Jan 2019 22:48:00 +0100 Subject: net: dsa: mv88e6xxx: Fix serdes irq setup going recursive Duec to a typo, mv88e6390_serdes_irq_setup() calls itself, rather than mv88e6390x_serdes_irq_setup(). It then blows the stack, and shortly after the machine blows up. Fixes: 2defda1f4b91 ("net: dsa: mv88e6xxx: Add support for SERDES on ports 2-8 for 6390X") Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/serdes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index 2caa8c8b4b55..1bfc5ff8d81d 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -664,7 +664,7 @@ int mv88e6390_serdes_irq_setup(struct mv88e6xxx_chip *chip, int port) if (port < 9) return 0; - return mv88e6390_serdes_irq_setup(chip, port); + return mv88e6390x_serdes_irq_setup(chip, port); } void mv88e6390x_serdes_irq_free(struct mv88e6xxx_chip *chip, int port) -- cgit v1.2.3 From ca899324305d953c19abb583b96f0dd81274b0b2 Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Mon, 28 Jan 2019 22:42:25 +0800 Subject: net: i825xx: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles dev_consume_skb_irq() should be called in i596_interrupt() when skb xmit done. It makes drop profiles(dropwatch, perf) more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/i825xx/82596.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/i825xx/82596.c b/drivers/net/ethernet/i825xx/82596.c index d719668a6684..92929750f832 100644 --- a/drivers/net/ethernet/i825xx/82596.c +++ b/drivers/net/ethernet/i825xx/82596.c @@ -1310,7 +1310,7 @@ static irqreturn_t i596_interrupt(int irq, void *dev_id) dev->stats.tx_aborted_errors++; } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); tx_cmd->cmd.command = 0; /* Mark free */ break; -- cgit v1.2.3 From 9e71a15d8b5bbce25c637f7f8833cd3f45b65646 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Mon, 28 Jan 2019 10:05:04 -0800 Subject: qed: Fix bug in tx promiscuous mode settings When running tx switched traffic between VNICs created via a bridge(to which VFs are added), adapter drops the unicast packets in tx flow due to VNIC's ucast mac being unknown to it. But VF interfaces being in promiscuous mode should have caused adapter to accept all the unknown ucast packets. Later, it was found that driver doesn't really configure tx promiscuous mode settings to accept all unknown unicast macs. This patch fixes tx promiscuous mode settings to accept all unknown/unmatched unicast macs and works out the scenario. Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_l2.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 67c02ea93906..b8baa6fcef8e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -609,6 +609,10 @@ qed_sp_update_accept_mode(struct qed_hwfn *p_hwfn, (!!(accept_filter & QED_ACCEPT_MCAST_MATCHED) && !!(accept_filter & QED_ACCEPT_MCAST_UNMATCHED))); + SET_FIELD(state, ETH_VPORT_TX_MODE_UCAST_ACCEPT_ALL, + (!!(accept_filter & QED_ACCEPT_UCAST_MATCHED) && + !!(accept_filter & QED_ACCEPT_UCAST_UNMATCHED))); + SET_FIELD(state, ETH_VPORT_TX_MODE_BCAST_ACCEPT_ALL, !!(accept_filter & QED_ACCEPT_BCAST)); @@ -2688,7 +2692,8 @@ static int qed_configure_filter_rx_mode(struct qed_dev *cdev, if (type == QED_FILTER_RX_MODE_TYPE_PROMISC) { accept_flags.rx_accept_filter |= QED_ACCEPT_UCAST_UNMATCHED | QED_ACCEPT_MCAST_UNMATCHED; - accept_flags.tx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED; + accept_flags.tx_accept_filter |= QED_ACCEPT_UCAST_UNMATCHED | + QED_ACCEPT_MCAST_UNMATCHED; } else if (type == QED_FILTER_RX_MODE_TYPE_MULTI_PROMISC) { accept_flags.rx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED; accept_flags.tx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED; -- cgit v1.2.3 From ff9296966e5e00b0d0d00477b2365a178f0f06a3 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Mon, 28 Jan 2019 10:05:05 -0800 Subject: qed: Fix LACP pdu drops for VFs VF is always configured to drop control frames (with reserved mac addresses) but to work LACP on the VFs, it would require LACP control frames to be forwarded or transmitted successfully. This patch fixes this in such a way that trusted VFs (marked through ndo_set_vf_trust) would be allowed to pass the control frames such as LACP pdus. Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_l2.c | 5 +++++ drivers/net/ethernet/qlogic/qed/qed_l2.h | 3 +++ drivers/net/ethernet/qlogic/qed/qed_sriov.c | 10 ++++++++-- 3 files changed, 16 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index b8baa6fcef8e..e68ca83ae915 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -748,6 +748,11 @@ int qed_sp_vport_update(struct qed_hwfn *p_hwfn, return rc; } + if (p_params->update_ctl_frame_check) { + p_cmn->ctl_frame_mac_check_en = p_params->mac_chk_en; + p_cmn->ctl_frame_ethtype_check_en = p_params->ethtype_chk_en; + } + /* Update mcast bins for VFs, PF doesn't use this functionality */ qed_sp_update_mcast_bin(p_hwfn, p_ramrod, p_params); diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h index 8d80f1095d17..7127d5aaac42 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h @@ -219,6 +219,9 @@ struct qed_sp_vport_update_params { struct qed_rss_params *rss_params; struct qed_filter_accept_flags accept_flags; struct qed_sge_tpa_params *sge_tpa_params; + u8 update_ctl_frame_check; + u8 mac_chk_en; + u8 ethtype_chk_en; }; int qed_sp_vport_update(struct qed_hwfn *p_hwfn, diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index ca6290fa0f30..71a7af134dd8 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -1969,7 +1969,9 @@ static void qed_iov_vf_mbx_start_vport(struct qed_hwfn *p_hwfn, params.vport_id = vf->vport_id; params.max_buffers_per_cqe = start->max_buffers_per_cqe; params.mtu = vf->mtu; - params.check_mac = true; + + /* Non trusted VFs should enable control frame filtering */ + params.check_mac = !vf->p_vf_info.is_trusted_configured; rc = qed_sp_eth_vport_start(p_hwfn, ¶ms); if (rc) { @@ -5130,6 +5132,9 @@ static void qed_iov_handle_trust_change(struct qed_hwfn *hwfn) params.opaque_fid = vf->opaque_fid; params.vport_id = vf->vport_id; + params.update_ctl_frame_check = 1; + params.mac_chk_en = !vf_info->is_trusted_configured; + if (vf_info->rx_accept_mode & mask) { flags->update_rx_mode_config = 1; flags->rx_accept_filter = vf_info->rx_accept_mode; @@ -5147,7 +5152,8 @@ static void qed_iov_handle_trust_change(struct qed_hwfn *hwfn) } if (flags->update_rx_mode_config || - flags->update_tx_mode_config) + flags->update_tx_mode_config || + params.update_ctl_frame_check) qed_sp_vport_update(hwfn, ¶ms, QED_SPQ_MODE_EBLOCK, NULL); } -- cgit v1.2.3 From 327852ec64205bb651be391a069784872098a3b2 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Mon, 28 Jan 2019 10:05:06 -0800 Subject: qed: Fix VF probe failure while FLR VFs may hit VF-PF channel timeout while probing, as in some cases it was observed that VF FLR and VF "acquire" message transaction (i.e first message from VF to PF in VF's probe flow) could occur simultaneously which could lead VF to fail sending "acquire" message to PF as VF is marked disabled from HW perspective due to FLR, which will result into channel timeout and VF probe failure. In such cases, try retrying VF "acquire" message so that in later attempts it could be successful to pass message to PF after the VF FLR is completed and can be probed successfully. Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_vf.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'drivers') diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index b6cccf44bf40..5dda547772c1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -261,6 +261,7 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn) struct pfvf_acquire_resp_tlv *resp = &p_iov->pf2vf_reply->acquire_resp; struct pf_vf_pfdev_info *pfdev_info = &resp->pfdev_info; struct vf_pf_resc_request *p_resc; + u8 retry_cnt = VF_ACQUIRE_THRESH; bool resources_acquired = false; struct vfpf_acquire_tlv *req; int rc = 0, attempts = 0; @@ -314,6 +315,15 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn) /* send acquire request */ rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp)); + + /* Re-try acquire in case of vf-pf hw channel timeout */ + if (retry_cnt && rc == -EBUSY) { + DP_VERBOSE(p_hwfn, QED_MSG_IOV, + "VF retrying to acquire due to VPC timeout\n"); + retry_cnt--; + continue; + } + if (rc) goto exit; -- cgit v1.2.3 From 7c81626a3c37e4ac320b8ad785694ba498f24794 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Mon, 28 Jan 2019 10:05:07 -0800 Subject: qed: Fix system crash in ll2 xmit Cache number of fragments in the skb locally as in case of linear skb (with zero fragments), tx completion (or freeing of skb) may happen before driver tries to get number of frgaments from the skb which could lead to stale access to an already freed skb. Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_ll2.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index d9237c65a838..b5f419b71287 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -2451,19 +2451,24 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb, { struct qed_ll2_tx_pkt_info pkt; const skb_frag_t *frag; + u8 flags = 0, nr_frags; int rc = -EINVAL, i; dma_addr_t mapping; u16 vlan = 0; - u8 flags = 0; if (unlikely(skb->ip_summed != CHECKSUM_NONE)) { DP_INFO(cdev, "Cannot transmit a checksummed packet\n"); return -EINVAL; } - if (1 + skb_shinfo(skb)->nr_frags > CORE_LL2_TX_MAX_BDS_PER_PACKET) { + /* Cache number of fragments from SKB since SKB may be freed by + * the completion routine after calling qed_ll2_prepare_tx_packet() + */ + nr_frags = skb_shinfo(skb)->nr_frags; + + if (1 + nr_frags > CORE_LL2_TX_MAX_BDS_PER_PACKET) { DP_ERR(cdev, "Cannot transmit a packet with %d fragments\n", - 1 + skb_shinfo(skb)->nr_frags); + 1 + nr_frags); return -EINVAL; } @@ -2485,7 +2490,7 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb, } memset(&pkt, 0, sizeof(pkt)); - pkt.num_of_bds = 1 + skb_shinfo(skb)->nr_frags; + pkt.num_of_bds = 1 + nr_frags; pkt.vlan = vlan; pkt.bd_flags = flags; pkt.tx_dest = QED_LL2_TX_DEST_NW; @@ -2496,12 +2501,17 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb, test_bit(QED_LL2_XMIT_FLAGS_FIP_DISCOVERY, &xmit_flags)) pkt.remove_stag = true; + /* qed_ll2_prepare_tx_packet() may actually send the packet if + * there are no fragments in the skb and subsequently the completion + * routine may run and free the SKB, so no dereferencing the SKB + * beyond this point unless skb has any fragments. + */ rc = qed_ll2_prepare_tx_packet(&cdev->hwfns[0], cdev->ll2->handle, &pkt, 1); if (rc) goto err; - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + for (i = 0; i < nr_frags; i++) { frag = &skb_shinfo(skb)->frags[i]; mapping = skb_frag_dma_map(&cdev->pdev->dev, frag, 0, -- cgit v1.2.3 From ffb057f98928aa099b08e419bbe5afc26ec9f448 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Mon, 28 Jan 2019 10:05:08 -0800 Subject: qed: Fix stack out of bounds bug KASAN reported following bug in qed_init_qm_get_idx_from_flags due to inappropriate casting of "pq_flags". Fix the type of "pq_flags". [ 196.624707] BUG: KASAN: stack-out-of-bounds in qed_init_qm_get_idx_from_flags+0x1a4/0x1b8 [qed] [ 196.624712] Read of size 8 at addr ffff809b00bc7360 by task kworker/0:9/1712 [ 196.624714] [ 196.624720] CPU: 0 PID: 1712 Comm: kworker/0:9 Not tainted 4.18.0-60.el8.aarch64+debug #1 [ 196.624723] Hardware name: To be filled by O.E.M. Saber/Saber, BIOS 0ACKL024 09/26/2018 [ 196.624733] Workqueue: events work_for_cpu_fn [ 196.624738] Call trace: [ 196.624742] dump_backtrace+0x0/0x2f8 [ 196.624745] show_stack+0x24/0x30 [ 196.624749] dump_stack+0xe0/0x11c [ 196.624755] print_address_description+0x68/0x260 [ 196.624759] kasan_report+0x178/0x340 [ 196.624762] __asan_report_load_n_noabort+0x38/0x48 [ 196.624786] qed_init_qm_get_idx_from_flags+0x1a4/0x1b8 [qed] [ 196.624808] qed_init_qm_info+0xec0/0x2200 [qed] [ 196.624830] qed_resc_alloc+0x284/0x7e8 [qed] [ 196.624853] qed_slowpath_start+0x6cc/0x1ae8 [qed] [ 196.624864] __qede_probe.isra.10+0x1cc/0x12c0 [qede] [ 196.624874] qede_probe+0x78/0xf0 [qede] [ 196.624879] local_pci_probe+0xc4/0x180 [ 196.624882] work_for_cpu_fn+0x54/0x98 [ 196.624885] process_one_work+0x758/0x1900 [ 196.624888] worker_thread+0x4e0/0xd18 [ 196.624892] kthread+0x2c8/0x350 [ 196.624897] ret_from_fork+0x10/0x18 [ 196.624899] [ 196.624902] Allocated by task 2: [ 196.624906] kasan_kmalloc.part.1+0x40/0x108 [ 196.624909] kasan_kmalloc+0xb4/0xc8 [ 196.624913] kasan_slab_alloc+0x14/0x20 [ 196.624916] kmem_cache_alloc_node+0x1dc/0x480 [ 196.624921] copy_process.isra.1.part.2+0x1d8/0x4a98 [ 196.624924] _do_fork+0x150/0xfa0 [ 196.624926] kernel_thread+0x48/0x58 [ 196.624930] kthreadd+0x3a4/0x5a0 [ 196.624932] ret_from_fork+0x10/0x18 [ 196.624934] [ 196.624937] Freed by task 0: [ 196.624938] (stack is not available) [ 196.624940] [ 196.624943] The buggy address belongs to the object at ffff809b00bc0000 [ 196.624943] which belongs to the cache thread_stack of size 32768 [ 196.624946] The buggy address is located 29536 bytes inside of [ 196.624946] 32768-byte region [ffff809b00bc0000, ffff809b00bc8000) [ 196.624948] The buggy address belongs to the page: [ 196.624952] page:ffff7fe026c02e00 count:1 mapcount:0 mapping:ffff809b4001c000 index:0x0 compound_mapcount: 0 [ 196.624960] flags: 0xfffff8000008100(slab|head) [ 196.624967] raw: 0fffff8000008100 dead000000000100 dead000000000200 ffff809b4001c000 [ 196.624970] raw: 0000000000000000 0000000000080008 00000001ffffffff 0000000000000000 [ 196.624973] page dumped because: kasan: bad access detected [ 196.624974] [ 196.624976] Memory state around the buggy address: [ 196.624980] ffff809b00bc7200: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 196.624983] ffff809b00bc7280: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 196.624985] >ffff809b00bc7300: 00 00 00 00 00 00 00 00 f1 f1 f1 f1 04 f2 f2 f2 [ 196.624988] ^ [ 196.624990] ffff809b00bc7380: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 196.624993] ffff809b00bc7400: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 196.624995] ================================================================== Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_dev.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 8f6551421945..2ecaaaa4469a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -795,19 +795,19 @@ static void qed_init_qm_pq(struct qed_hwfn *p_hwfn, /* get pq index according to PQ_FLAGS */ static u16 *qed_init_qm_get_idx_from_flags(struct qed_hwfn *p_hwfn, - u32 pq_flags) + unsigned long pq_flags) { struct qed_qm_info *qm_info = &p_hwfn->qm_info; /* Can't have multiple flags set here */ - if (bitmap_weight((unsigned long *)&pq_flags, + if (bitmap_weight(&pq_flags, sizeof(pq_flags) * BITS_PER_BYTE) > 1) { - DP_ERR(p_hwfn, "requested multiple pq flags 0x%x\n", pq_flags); + DP_ERR(p_hwfn, "requested multiple pq flags 0x%lx\n", pq_flags); goto err; } if (!(qed_get_pq_flags(p_hwfn) & pq_flags)) { - DP_ERR(p_hwfn, "pq flag 0x%x is not set\n", pq_flags); + DP_ERR(p_hwfn, "pq flag 0x%lx is not set\n", pq_flags); goto err; } -- cgit v1.2.3 From b46a0bf78ad7b150ef5910da83859f7f5a514ffd Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Mon, 28 Jan 2019 15:05:05 +0800 Subject: vhost: fix OOB in get_rx_bufs() After batched used ring updating was introduced in commit e2b3b35eb989 ("vhost_net: batch used ring update in rx"). We tend to batch heads in vq->heads for more than one packet. But the quota passed to get_rx_bufs() was not correctly limited, which can result a OOB write in vq->heads. headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx, vhost_len, &in, vq_log, &log, likely(mergeable) ? UIO_MAXIOV : 1); UIO_MAXIOV was still used which is wrong since we could have batched used in vq->heads, this will cause OOB if the next buffer needs more than 960 (1024 (UIO_MAXIOV) - 64 (VHOST_NET_BATCH)) heads after we've batched 64 (VHOST_NET_BATCH) heads: Acked-by: Stefan Hajnoczi ============================================================================= BUG kmalloc-8k (Tainted: G B ): Redzone overwritten ----------------------------------------------------------------------------- INFO: 0x00000000fd93b7a2-0x00000000f0713384. First byte 0xa9 instead of 0xcc INFO: Allocated in alloc_pd+0x22/0x60 age=3933677 cpu=2 pid=2674 kmem_cache_alloc_trace+0xbb/0x140 alloc_pd+0x22/0x60 gen8_ppgtt_create+0x11d/0x5f0 i915_ppgtt_create+0x16/0x80 i915_gem_create_context+0x248/0x390 i915_gem_context_create_ioctl+0x4b/0xe0 drm_ioctl_kernel+0xa5/0xf0 drm_ioctl+0x2ed/0x3a0 do_vfs_ioctl+0x9f/0x620 ksys_ioctl+0x6b/0x80 __x64_sys_ioctl+0x11/0x20 do_syscall_64+0x43/0xf0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 INFO: Slab 0x00000000d13e87af objects=3 used=3 fp=0x (null) flags=0x200000000010201 INFO: Object 0x0000000003278802 @offset=17064 fp=0x00000000e2e6652b Fixing this by allocating UIO_MAXIOV + VHOST_NET_BATCH iovs for vhost-net. This is done through set the limitation through vhost_dev_init(), then set_owner can allocate the number of iov in a per device manner. This fixes CVE-2018-16880. Fixes: e2b3b35eb989 ("vhost_net: batch used ring update in rx") Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- drivers/vhost/net.c | 3 ++- drivers/vhost/scsi.c | 2 +- drivers/vhost/vhost.c | 7 ++++--- drivers/vhost/vhost.h | 4 +++- drivers/vhost/vsock.c | 2 +- 5 files changed, 11 insertions(+), 7 deletions(-) (limited to 'drivers') diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index bca86bf7189f..df51a35cf537 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1337,7 +1337,8 @@ static int vhost_net_open(struct inode *inode, struct file *f) n->vqs[i].rx_ring = NULL; vhost_net_buf_init(&n->vqs[i].rxq); } - vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX); + vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX, + UIO_MAXIOV + VHOST_NET_BATCH); vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev); vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 344684f3e2e4..23593cb23dd0 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1627,7 +1627,7 @@ static int vhost_scsi_open(struct inode *inode, struct file *f) vqs[i] = &vs->vqs[i].vq; vs->vqs[i].vq.handle_kick = vhost_scsi_handle_kick; } - vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ); + vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ, UIO_MAXIOV); vhost_scsi_init_inflight(vs, NULL); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 15a216cdd507..24a129fcdd61 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -390,9 +390,9 @@ static long vhost_dev_alloc_iovecs(struct vhost_dev *dev) vq->indirect = kmalloc_array(UIO_MAXIOV, sizeof(*vq->indirect), GFP_KERNEL); - vq->log = kmalloc_array(UIO_MAXIOV, sizeof(*vq->log), + vq->log = kmalloc_array(dev->iov_limit, sizeof(*vq->log), GFP_KERNEL); - vq->heads = kmalloc_array(UIO_MAXIOV, sizeof(*vq->heads), + vq->heads = kmalloc_array(dev->iov_limit, sizeof(*vq->heads), GFP_KERNEL); if (!vq->indirect || !vq->log || !vq->heads) goto err_nomem; @@ -414,7 +414,7 @@ static void vhost_dev_free_iovecs(struct vhost_dev *dev) } void vhost_dev_init(struct vhost_dev *dev, - struct vhost_virtqueue **vqs, int nvqs) + struct vhost_virtqueue **vqs, int nvqs, int iov_limit) { struct vhost_virtqueue *vq; int i; @@ -427,6 +427,7 @@ void vhost_dev_init(struct vhost_dev *dev, dev->iotlb = NULL; dev->mm = NULL; dev->worker = NULL; + dev->iov_limit = iov_limit; init_llist_head(&dev->work_list); init_waitqueue_head(&dev->wait); INIT_LIST_HEAD(&dev->read_list); diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 1b675dad5e05..9490e7ddb340 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -170,9 +170,11 @@ struct vhost_dev { struct list_head read_list; struct list_head pending_list; wait_queue_head_t wait; + int iov_limit; }; -void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, int nvqs); +void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, + int nvqs, int iov_limit); long vhost_dev_set_owner(struct vhost_dev *dev); bool vhost_dev_has_owner(struct vhost_dev *dev); long vhost_dev_check_owner(struct vhost_dev *); diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 3fbc068eaa9b..bb5fc0e9fbc2 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -531,7 +531,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file) vsock->vqs[VSOCK_VQ_TX].handle_kick = vhost_vsock_handle_tx_kick; vsock->vqs[VSOCK_VQ_RX].handle_kick = vhost_vsock_handle_rx_kick; - vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs)); + vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs), UIO_MAXIOV); file->private_data = vsock; spin_lock_init(&vsock->send_pkt_list_lock); -- cgit v1.2.3 From f48af114895b2f9cdc218ed75666ade83380255b Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Sun, 27 Jan 2019 23:56:34 +0800 Subject: net: alteon: replace dev_kfree_skb_irq by dev_consume_skb_irq dev_consume_skb_irq() should be called in ace_tx_int() when xmit done. It makes drop profiles more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/alteon/acenic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c index 4f11f98347ed..1827ef1f6d55 100644 --- a/drivers/net/ethernet/alteon/acenic.c +++ b/drivers/net/ethernet/alteon/acenic.c @@ -2059,7 +2059,7 @@ static inline void ace_tx_int(struct net_device *dev, if (skb) { dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); info->skb = NULL; } -- cgit v1.2.3 From 3afa73dd7c8b586d9d01a96063d537e1550d1287 Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Sun, 27 Jan 2019 23:58:25 +0800 Subject: net: amd8111e: replace dev_kfree_skb_irq by dev_consume_skb_irq dev_consume_skb_irq() should be called in amd8111e_tx() when xmit done. It makes drop profiles more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/amd8111e.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c index a90080f12e67..e548c0ae2e00 100644 --- a/drivers/net/ethernet/amd/amd8111e.c +++ b/drivers/net/ethernet/amd/amd8111e.c @@ -666,7 +666,7 @@ static int amd8111e_tx(struct net_device *dev) pci_unmap_single(lp->pci_dev, lp->tx_dma_addr[tx_index], lp->tx_skbuff[tx_index]->len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq (lp->tx_skbuff[tx_index]); + dev_consume_skb_irq(lp->tx_skbuff[tx_index]); lp->tx_skbuff[tx_index] = NULL; lp->tx_dma_addr[tx_index] = 0; } -- cgit v1.2.3 From 100091156c1a4da11c0764265b9e328d7858f2bb Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Tue, 29 Jan 2019 07:39:13 +0800 Subject: net: apple: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles dev_consume_skb_irq() should be called in bmac_txdma_intr() when xmit done. It makes drop profiles more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/apple/bmac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c index 6a8e2567f2bd..4d3855ceb500 100644 --- a/drivers/net/ethernet/apple/bmac.c +++ b/drivers/net/ethernet/apple/bmac.c @@ -777,7 +777,7 @@ static irqreturn_t bmac_txdma_intr(int irq, void *dev_id) if (bp->tx_bufs[bp->tx_empty]) { ++dev->stats.tx_packets; - dev_kfree_skb_irq(bp->tx_bufs[bp->tx_empty]); + dev_consume_skb_irq(bp->tx_bufs[bp->tx_empty]); } bp->tx_bufs[bp->tx_empty] = NULL; bp->tx_fullup = 0; -- cgit v1.2.3 From b3379a424dde97755ad7a6f4405648a9ea13d6e3 Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Tue, 29 Jan 2019 07:40:10 +0800 Subject: net: ti: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles dev_consume_skb_irq() should be called in cpmac_end_xmit() when xmit done. It makes drop profiles more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/cpmac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c index 810dfc7de1f9..e2d47b24a869 100644 --- a/drivers/net/ethernet/ti/cpmac.c +++ b/drivers/net/ethernet/ti/cpmac.c @@ -608,7 +608,7 @@ static void cpmac_end_xmit(struct net_device *dev, int queue) netdev_dbg(dev, "sent 0x%p, len=%d\n", desc->skb, desc->skb->len); - dev_kfree_skb_irq(desc->skb); + dev_consume_skb_irq(desc->skb); desc->skb = NULL; if (__netif_subqueue_stopped(dev, queue)) netif_wake_subqueue(dev, queue); -- cgit v1.2.3 From e501070e4db0b67a4c17a5557d1e9d098f3db310 Mon Sep 17 00:00:00 2001 From: Harini Katakam Date: Tue, 29 Jan 2019 15:20:03 +0530 Subject: net: macb: Apply RXUBR workaround only to versions with errata The interrupt handler contains a workaround for RX hang applicable to Zynq and AT91RM9200 only. Subsequent versions do not need this workaround. This workaround unnecessarily resets RX whenever RX used bit read is observed, which can be often under heavy traffic. There is no other action performed on RX UBR interrupt. Hence introduce a CAPS mask; enable this interrupt and workaround only on affected versions. Signed-off-by: Harini Katakam Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb.h | 3 +++ drivers/net/ethernet/cadence/macb_main.c | 28 +++++++++++++++++----------- 2 files changed, 20 insertions(+), 11 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 3d45f4c92cf6..9bbaad9f3d63 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -643,6 +643,7 @@ #define MACB_CAPS_JUMBO 0x00000020 #define MACB_CAPS_GEM_HAS_PTP 0x00000040 #define MACB_CAPS_BD_RD_PREFETCH 0x00000080 +#define MACB_CAPS_NEEDS_RSTONUBR 0x00000100 #define MACB_CAPS_FIFO_MODE 0x10000000 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000 #define MACB_CAPS_SG_DISABLED 0x40000000 @@ -1214,6 +1215,8 @@ struct macb { int rx_bd_rd_prefetch; int tx_bd_rd_prefetch; + + u32 rx_intr_mask; }; #ifdef CONFIG_MACB_USE_HWSTAMP diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 66cc7927061a..2b2882615e8b 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -56,8 +56,7 @@ /* level of occupied TX descriptors under which we wake up TX process */ #define MACB_TX_WAKEUP_THRESH(bp) (3 * (bp)->tx_ring_size / 4) -#define MACB_RX_INT_FLAGS (MACB_BIT(RCOMP) | MACB_BIT(RXUBR) \ - | MACB_BIT(ISR_ROVR)) +#define MACB_RX_INT_FLAGS (MACB_BIT(RCOMP) | MACB_BIT(ISR_ROVR)) #define MACB_TX_ERR_FLAGS (MACB_BIT(ISR_TUND) \ | MACB_BIT(ISR_RLE) \ | MACB_BIT(TXERR)) @@ -1270,7 +1269,7 @@ static int macb_poll(struct napi_struct *napi, int budget) queue_writel(queue, ISR, MACB_BIT(RCOMP)); napi_reschedule(napi); } else { - queue_writel(queue, IER, MACB_RX_INT_FLAGS); + queue_writel(queue, IER, bp->rx_intr_mask); } } @@ -1288,7 +1287,7 @@ static void macb_hresp_error_task(unsigned long data) u32 ctrl; for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { - queue_writel(queue, IDR, MACB_RX_INT_FLAGS | + queue_writel(queue, IDR, bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); } @@ -1318,7 +1317,7 @@ static void macb_hresp_error_task(unsigned long data) /* Enable interrupts */ queue_writel(queue, IER, - MACB_RX_INT_FLAGS | + bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); } @@ -1372,14 +1371,14 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) (unsigned int)(queue - bp->queues), (unsigned long)status); - if (status & MACB_RX_INT_FLAGS) { + if (status & bp->rx_intr_mask) { /* There's no point taking any more interrupts * until we have processed the buffers. The * scheduling call may fail if the poll routine * is already scheduled, so disable interrupts * now. */ - queue_writel(queue, IDR, MACB_RX_INT_FLAGS); + queue_writel(queue, IDR, bp->rx_intr_mask); if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) queue_writel(queue, ISR, MACB_BIT(RCOMP)); @@ -1412,8 +1411,9 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) /* There is a hardware issue under heavy load where DMA can * stop, this causes endless "used buffer descriptor read" * interrupts but it can be cleared by re-enabling RX. See - * the at91 manual, section 41.3.1 or the Zynq manual - * section 16.7.4 for details. + * the at91rm9200 manual, section 41.3.1 or the Zynq manual + * section 16.7.4 for details. RXUBR is only enabled for + * these two versions. */ if (status & MACB_BIT(RXUBR)) { ctrl = macb_readl(bp, NCR); @@ -2259,7 +2259,7 @@ static void macb_init_hw(struct macb *bp) /* Enable interrupts */ queue_writel(queue, IER, - MACB_RX_INT_FLAGS | + bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); } @@ -3907,6 +3907,7 @@ static const struct macb_config sama5d4_config = { }; static const struct macb_config emac_config = { + .caps = MACB_CAPS_NEEDS_RSTONUBR, .clk_init = at91ether_clk_init, .init = at91ether_init, }; @@ -3928,7 +3929,8 @@ static const struct macb_config zynqmp_config = { }; static const struct macb_config zynq_config = { - .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_NO_GIGABIT_HALF, + .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_NO_GIGABIT_HALF | + MACB_CAPS_NEEDS_RSTONUBR, .dma_burst_length = 16, .clk_init = macb_clk_init, .init = macb_init, @@ -4083,6 +4085,10 @@ static int macb_probe(struct platform_device *pdev) macb_dma_desc_get_size(bp); } + bp->rx_intr_mask = MACB_RX_INT_FLAGS; + if (bp->caps & MACB_CAPS_NEEDS_RSTONUBR) + bp->rx_intr_mask |= MACB_BIT(RXUBR); + mac = of_get_mac_address(np); if (mac) { ether_addr_copy(bp->dev->dev_addr, mac); -- cgit v1.2.3 From 896cebc0e261a29a6f0b20ab21d1bfc06959e91d Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Tue, 29 Jan 2019 22:40:51 +0800 Subject: net: 8139cp: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles dev_consume_skb_irq() should be called in cp_tx() when skb xmit done. It makes drop profiles(dropwatch, perf) more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/8139cp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index 44f6e4873aad..4f910c4f67b0 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -691,7 +691,7 @@ static void cp_tx (struct cp_private *cp) } bytes_compl += skb->len; pkts_compl++; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } cp->tx_skb[tx_tail] = NULL; -- cgit v1.2.3 From e339f8631eb70fb48b2801e9e66a267c9a730a6a Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Tue, 29 Jan 2019 23:32:22 +0800 Subject: net: caif: call dev_consume_skb_any when skb xmit done The skb shouled be consumed when xmit done, it makes drop profiles (dropwatch, perf) more friendly. dev_kfree_skb_irq()/kfree_skb() shouled be replaced by dev_consume_skb_any(), it makes code cleaner. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/caif/caif_serial.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'drivers') diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c index a0f954f36c09..44e6c7b1b222 100644 --- a/drivers/net/caif/caif_serial.c +++ b/drivers/net/caif/caif_serial.c @@ -257,10 +257,7 @@ static int handle_tx(struct ser_device *ser) if (skb->len == 0) { struct sk_buff *tmp = skb_dequeue(&ser->head); WARN_ON(tmp != skb); - if (in_interrupt()) - dev_kfree_skb_irq(skb); - else - kfree_skb(skb); + dev_consume_skb_any(skb); } } /* Send flow off if queue is empty */ -- cgit v1.2.3 From 0f0ed8282e5bfdc87cdd562e58f3d90d893e7ee5 Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Tue, 29 Jan 2019 23:04:40 +0800 Subject: net: b44: replace dev_kfree_skb_xxx by dev_consume_skb_xxx for drop profiles The skb should be freed by dev_consume_skb_any() in b44_start_xmit() when bounce_skb is used. The skb is be replaced by bounce_skb, so the original skb should be consumed(not drop). dev_consume_skb_irq() should be called in b44_tx() when skb xmit done. It makes drop profiles(dropwatch, perf) more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/b44.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index f44808959ff3..97ab0dd25552 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -638,7 +638,7 @@ static void b44_tx(struct b44 *bp) bytes_compl += skb->len; pkts_compl++; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } netdev_completed_queue(bp->dev, pkts_compl, bytes_compl); @@ -1012,7 +1012,7 @@ static netdev_tx_t b44_start_xmit(struct sk_buff *skb, struct net_device *dev) } skb_copy_from_linear_data(skb, skb_put(bounce_skb, len), len); - dev_kfree_skb_any(skb); + dev_consume_skb_any(skb); skb = bounce_skb; } -- cgit v1.2.3