From 404e5a12691fe797486475fe28cc0b80cb8bef2c Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Thu, 3 Jun 2021 16:19:39 +0300 Subject: RDMA/mlx4: Do not map the core_clock page to user space unless enabled Currently when mlx4 maps the hca_core_clock page to the user space there are read-modifiable registers, one of which is semaphore, on this page as well as the clock counter. If user reads the wrong offset, it can modify the semaphore and hang the device. Do not map the hca_core_clock page to the user space unless the device has been put in a backwards compatibility mode to support this feature. After this patch, mlx4 core_clock won't be mapped to user space on the majority of existing devices and the uverbs device time feature in ibv_query_rt_values_ex() will be disabled. Fixes: 52033cfb5aab ("IB/mlx4: Add mmap call to map the hardware clock") Link: https://lore.kernel.org/r/9632304e0d6790af84b3b706d8c18732bc0d5e27.1622726305.git.leonro@nvidia.com Signed-off-by: Shay Drory Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/net/ethernet/mellanox/mlx4/fw.c | 3 +++ drivers/net/ethernet/mellanox/mlx4/fw.h | 1 + drivers/net/ethernet/mellanox/mlx4/main.c | 6 ++++++ 3 files changed, 10 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index f6cfec81ccc3..dc4ac1a2b6b6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -823,6 +823,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) #define QUERY_DEV_CAP_MAD_DEMUX_OFFSET 0xb0 #define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_BASE_OFFSET 0xa8 #define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_RANGE_OFFSET 0xac +#define QUERY_DEV_CAP_MAP_CLOCK_TO_USER 0xc1 #define QUERY_DEV_CAP_QP_RATE_LIMIT_NUM_OFFSET 0xcc #define QUERY_DEV_CAP_QP_RATE_LIMIT_MAX_OFFSET 0xd0 #define QUERY_DEV_CAP_QP_RATE_LIMIT_MIN_OFFSET 0xd2 @@ -841,6 +842,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) if (mlx4_is_mfunc(dev)) disable_unsupported_roce_caps(outbox); + MLX4_GET(field, outbox, QUERY_DEV_CAP_MAP_CLOCK_TO_USER); + dev_cap->map_clock_to_user = field & 0x80; MLX4_GET(field, outbox, QUERY_DEV_CAP_RSVD_QP_OFFSET); dev_cap->reserved_qps = 1 << (field & 0xf); MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_QP_OFFSET); diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h index 8f020f26ebf5..cf64e54eecb0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.h +++ b/drivers/net/ethernet/mellanox/mlx4/fw.h @@ -131,6 +131,7 @@ struct mlx4_dev_cap { u32 health_buffer_addrs; struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1]; bool wol_port[MLX4_MAX_PORTS + 1]; + bool map_clock_to_user; }; struct mlx4_func_cap { diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index c326b434734e..00c84656b2e7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -498,6 +498,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) } } + dev->caps.map_clock_to_user = dev_cap->map_clock_to_user; dev->caps.uar_page_size = PAGE_SIZE; dev->caps.num_uars = dev_cap->uar_size / PAGE_SIZE; dev->caps.local_ca_ack_delay = dev_cap->local_ca_ack_delay; @@ -1948,6 +1949,11 @@ int mlx4_get_internal_clock_params(struct mlx4_dev *dev, if (mlx4_is_slave(dev)) return -EOPNOTSUPP; + if (!dev->caps.map_clock_to_user) { + mlx4_dbg(dev, "Map clock to user is not supported.\n"); + return -EOPNOTSUPP; + } + if (!params) return -EINVAL; -- cgit v1.2.3 From 306b9228c097b4101c150ccd262372ded8348644 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Sun, 6 Jun 2021 11:24:30 +0300 Subject: mlxsw: reg: Spectrum-3: Enforce lowest max-shaper burst size of 11 A max-shaper is the HW component responsible for delaying egress traffic above a configured transmission rate. Burst size is the amount of traffic that is allowed to pass without accounting. The burst size value needs to be such that it can be expressed as 2^BS * 512 bits, where BS lies in a certain ASIC-dependent range. mlxsw enforces that this holds before attempting to configure the shaper. The assumption for Spectrum-3 was that the lower limit of BS would be 5, like for Spectrum-1. But as of now, the limit is still 11. Therefore fix the driver accordingly, so that incorrect values are rejected early with a proper message. Fixes: 23effa2479ba ("mlxsw: reg: Add max_shaper_bs to QoS ETS Element Configuration") Reported-by: Maksym Yaremchuk Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/reg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 900b4bf5bb5b..2bc5a9003c6d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -3907,7 +3907,7 @@ MLXSW_ITEM32(reg, qeec, max_shaper_bs, 0x1C, 0, 6); #define MLXSW_REG_QEEC_HIGHEST_SHAPER_BS 25 #define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP1 5 #define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP2 11 -#define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP3 5 +#define MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP3 11 static inline void mlxsw_reg_qeec_pack(char *payload, u8 local_port, enum mlxsw_reg_qeec_hr hr, u8 index, -- cgit v1.2.3 From d566ed04e42bbb7144cf52718b77ca5c791abc09 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Sun, 6 Jun 2021 11:24:31 +0300 Subject: mlxsw: spectrum_qdisc: Pass handle, not band number to find_class() In mlxsw Qdisc offload, find_class() is an operation that yields a qdisc offload descriptor given a parental qdisc descriptor and a class handle. In __mlxsw_sp_qdisc_ets_graft() however, a band number is passed to that function instead of a handle. This can lead to a trigger of a WARN_ON with the following splat: WARNING: CPU: 3 PID: 808 at drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c:1356 __mlxsw_sp_qdisc_ets_graft+0x115/0x130 [mlxsw_spectrum] [...] Call Trace: mlxsw_sp_setup_tc_prio+0xe3/0x100 [mlxsw_spectrum] qdisc_offload_graft_helper+0x35/0xa0 prio_graft+0x176/0x290 [sch_prio] qdisc_graft+0xb3/0x540 tc_modify_qdisc+0x56a/0x8a0 rtnetlink_rcv_msg+0x12c/0x370 netlink_rcv_skb+0x49/0xf0 netlink_unicast+0x1f6/0x2b0 netlink_sendmsg+0x1fb/0x410 ____sys_sendmsg+0x1f3/0x220 ___sys_sendmsg+0x70/0xb0 __sys_sendmsg+0x54/0xa0 do_syscall_64+0x3a/0x70 entry_SYSCALL_64_after_hwframe+0x44/0xae Since the parent handle is not passed with the offload information, compute it from the band number and qdisc handle. Fixes: 28052e618b04 ("mlxsw: spectrum_qdisc: Track children per qdisc") Reported-by: Maksym Yaremchuk Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c index 04672eb5c7f3..9958d503bf0e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c @@ -1332,6 +1332,7 @@ __mlxsw_sp_qdisc_ets_graft(struct mlxsw_sp_port *mlxsw_sp_port, u8 band, u32 child_handle) { struct mlxsw_sp_qdisc *old_qdisc; + u32 parent; if (band < mlxsw_sp_qdisc->num_classes && mlxsw_sp_qdisc->qdiscs[band].handle == child_handle) @@ -1352,7 +1353,9 @@ __mlxsw_sp_qdisc_ets_graft(struct mlxsw_sp_port *mlxsw_sp_port, if (old_qdisc) mlxsw_sp_qdisc_destroy(mlxsw_sp_port, old_qdisc); - mlxsw_sp_qdisc = mlxsw_sp_qdisc->ops->find_class(mlxsw_sp_qdisc, band); + parent = TC_H_MAKE(mlxsw_sp_qdisc->handle, band + 1); + mlxsw_sp_qdisc = mlxsw_sp_qdisc->ops->find_class(mlxsw_sp_qdisc, + parent); if (!WARN_ON(!mlxsw_sp_qdisc)) mlxsw_sp_qdisc_destroy(mlxsw_sp_port, mlxsw_sp_qdisc); -- cgit v1.2.3 From 2fd8d84ce3095e8a7b5fe96532c91b1b9e07339c Mon Sep 17 00:00:00 2001 From: Mykola Kostenok Date: Sun, 6 Jun 2021 11:24:32 +0300 Subject: mlxsw: core: Set thermal zone polling delay argument to real value at init Thermal polling delay argument for modules and gearboxes thermal zones used to be initialized with zero value, while actual delay was used to be set by mlxsw_thermal_set_mode() by thermal operation callback set_mode(). After operations set_mode()/get_mode() have been removed by cited commits, modules and gearboxes thermal zones always have polling time set to zero and do not perform temperature monitoring. Set non-zero "polling_delay" in thermal_zone_device_register() routine, thus, the relevant thermal zones will perform thermal monitoring. Cc: Andrzej Pietrasiewicz Fixes: 5d7bd8aa7c35 ("thermal: Simplify or eliminate unnecessary set_mode() methods") Fixes: 1ee14820fd8e ("thermal: remove get_mode() operation of drivers") Signed-off-by: Mykola Kostenok Acked-by: Vadim Pasternak Reviewed-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c index dfea14399607..85f0ce285146 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c @@ -693,7 +693,8 @@ mlxsw_thermal_module_tz_init(struct mlxsw_thermal_module *module_tz) MLXSW_THERMAL_TRIP_MASK, module_tz, &mlxsw_thermal_module_ops, - NULL, 0, 0); + NULL, 0, + module_tz->parent->polling_delay); if (IS_ERR(module_tz->tzdev)) { err = PTR_ERR(module_tz->tzdev); return err; @@ -815,7 +816,8 @@ mlxsw_thermal_gearbox_tz_init(struct mlxsw_thermal_module *gearbox_tz) MLXSW_THERMAL_TRIP_MASK, gearbox_tz, &mlxsw_thermal_gearbox_ops, - NULL, 0, 0); + NULL, 0, + gearbox_tz->parent->polling_delay); if (IS_ERR(gearbox_tz->tzdev)) return PTR_ERR(gearbox_tz->tzdev); -- cgit v1.2.3 From 1650bdb1c516c248fb06f6d076559ff6437a5853 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 8 Jun 2021 14:15:35 +0300 Subject: net: dsa: felix: re-enable TX flow control in ocelot_port_flush() Because flow control is set up statically in ocelot_init_port(), and not in phylink_mac_link_up(), what happens is that after the blamed commit, the flow control remains disabled after the port flushing procedure. Fixes: eb4733d7cffc ("net: dsa: felix: implement port flushing on .phylink_mac_link_down") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 0c4283319d7f..adfb9781799e 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -379,6 +379,7 @@ static u32 ocelot_read_eq_avail(struct ocelot *ocelot, int port) int ocelot_port_flush(struct ocelot *ocelot, int port) { + unsigned int pause_ena; int err, val; /* Disable dequeuing from the egress queues */ @@ -387,6 +388,7 @@ int ocelot_port_flush(struct ocelot *ocelot, int port) QSYS_PORT_MODE, port); /* Disable flow control */ + ocelot_fields_read(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, &pause_ena); ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, 0); /* Disable priority flow control */ @@ -422,6 +424,9 @@ int ocelot_port_flush(struct ocelot *ocelot, int port) /* Clear flushing again. */ ocelot_rmw_gix(ocelot, 0, REW_PORT_CFG_FLUSH_ENA, REW_PORT_CFG, port); + /* Re-enable flow control */ + ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, pause_ena); + return err; } EXPORT_SYMBOL(ocelot_port_flush); -- cgit v1.2.3 From 504fd6a5390c30b1b7670768e314dd5d473da06a Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Tue, 8 Jun 2021 19:42:54 +0300 Subject: net: ena: fix DMA mapping function issues in XDP This patch fixes several bugs found when (DMA/LLQ) mapping a packet for transmission. The mapping procedure makes the transmitted packet accessible by the device. When using LLQ, this requires copying the packet's header to push header (which would be passed to LLQ) and creating DMA mapping for the payload (if the packet doesn't fit the maximum push length). When not using LLQ, we map the whole packet with DMA. The following bugs are fixed in the code: 1. Add support for non-LLQ machines: The ena_xdp_tx_map_frame() function assumed that LLQ is supported, and never mapped the whole packet using DMA. On some instances, which don't support LLQ, this causes loss of traffic. 2. Wrong DMA buffer length passed to device: When using LLQ, the first 'tx_max_header_size' bytes of the packet would be copied to push header. The rest of the packet would be copied to a DMA'd buffer. 3. Freeing the XDP buffer twice in case of a mapping error: In case a buffer DMA mapping fails, the function uses xdp_return_frame_rx_napi() to free the RX buffer and returns from the function with an error. XDP frames that fail to xmit get freed by the kernel and so there is no need for this call. Fixes: 548c4940b9f1 ("net: ena: Implement XDP_TX action") Signed-off-by: Shay Agroskin Signed-off-by: David S. Miller --- drivers/net/ethernet/amazon/ena/ena_netdev.c | 54 ++++++++++++++-------------- 1 file changed, 28 insertions(+), 26 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 881f88754bf6..52571486705e 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -236,36 +236,48 @@ static int ena_xdp_io_poll(struct napi_struct *napi, int budget) static int ena_xdp_tx_map_frame(struct ena_ring *xdp_ring, struct ena_tx_buffer *tx_info, struct xdp_frame *xdpf, - void **push_hdr, - u32 *push_len) + struct ena_com_tx_ctx *ena_tx_ctx) { struct ena_adapter *adapter = xdp_ring->adapter; struct ena_com_buf *ena_buf; - dma_addr_t dma = 0; + int push_len = 0; + dma_addr_t dma; + void *data; u32 size; tx_info->xdpf = xdpf; + data = tx_info->xdpf->data; size = tx_info->xdpf->len; - ena_buf = tx_info->bufs; - /* llq push buffer */ - *push_len = min_t(u32, size, xdp_ring->tx_max_header_size); - *push_hdr = tx_info->xdpf->data; + if (xdp_ring->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV) { + /* Designate part of the packet for LLQ */ + push_len = min_t(u32, size, xdp_ring->tx_max_header_size); + + ena_tx_ctx->push_header = data; + + size -= push_len; + data += push_len; + } + + ena_tx_ctx->header_len = push_len; - if (size - *push_len > 0) { + if (size > 0) { dma = dma_map_single(xdp_ring->dev, - *push_hdr + *push_len, - size - *push_len, + data, + size, DMA_TO_DEVICE); if (unlikely(dma_mapping_error(xdp_ring->dev, dma))) goto error_report_dma_error; - tx_info->map_linear_data = 1; - tx_info->num_of_bufs = 1; - } + tx_info->map_linear_data = 0; - ena_buf->paddr = dma; - ena_buf->len = size; + ena_buf = tx_info->bufs; + ena_buf->paddr = dma; + ena_buf->len = size; + + ena_tx_ctx->ena_bufs = ena_buf; + ena_tx_ctx->num_bufs = tx_info->num_of_bufs = 1; + } return 0; @@ -274,10 +286,6 @@ error_report_dma_error: &xdp_ring->syncp); netif_warn(adapter, tx_queued, adapter->netdev, "Failed to map xdp buff\n"); - xdp_return_frame_rx_napi(tx_info->xdpf); - tx_info->xdpf = NULL; - tx_info->num_of_bufs = 0; - return -EINVAL; } @@ -289,8 +297,6 @@ static int ena_xdp_xmit_frame(struct ena_ring *xdp_ring, struct ena_com_tx_ctx ena_tx_ctx = {}; struct ena_tx_buffer *tx_info; u16 next_to_use, req_id; - void *push_hdr; - u32 push_len; int rc; next_to_use = xdp_ring->next_to_use; @@ -298,15 +304,11 @@ static int ena_xdp_xmit_frame(struct ena_ring *xdp_ring, tx_info = &xdp_ring->tx_buffer_info[req_id]; tx_info->num_of_bufs = 0; - rc = ena_xdp_tx_map_frame(xdp_ring, tx_info, xdpf, &push_hdr, &push_len); + rc = ena_xdp_tx_map_frame(xdp_ring, tx_info, xdpf, &ena_tx_ctx); if (unlikely(rc)) return rc; - ena_tx_ctx.ena_bufs = tx_info->bufs; - ena_tx_ctx.push_header = push_hdr; - ena_tx_ctx.num_bufs = tx_info->num_of_bufs; ena_tx_ctx.req_id = req_id; - ena_tx_ctx.header_len = push_len; rc = ena_xmit_common(dev, xdp_ring, -- cgit v1.2.3 From f2386cf7c5f4ff5d7b584f5d92014edd7df6c676 Mon Sep 17 00:00:00 2001 From: Aleksander Jan Bajkowski Date: Tue, 8 Jun 2021 23:21:07 +0200 Subject: net: lantiq: disable interrupt before sheduling NAPI This patch fixes TX hangs with threaded NAPI enabled. The scheduled NAPI seems to be executed in parallel with the interrupt on second thread. Sometimes it happens that ltq_dma_disable_irq() is executed after xrx200_tx_housekeeping(). The symptom is that TX interrupts are disabled in the DMA controller. As a result, the TX hangs after a few seconds of the iperf test. Scheduling NAPI after disabling interrupts fixes this issue. Tested on Lantiq xRX200 (BT Home Hub 5A). Fixes: 9423361da523 ("net: lantiq: Disable IRQs only if NAPI gets scheduled ") Signed-off-by: Aleksander Jan Bajkowski Acked-by: Hauke Mehrtens Signed-off-by: David S. Miller --- drivers/net/ethernet/lantiq_xrx200.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c index 36dc3e5f6218..0e10d8aeffe1 100644 --- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -352,8 +352,8 @@ static irqreturn_t xrx200_dma_irq(int irq, void *ptr) struct xrx200_chan *ch = ptr; if (napi_schedule_prep(&ch->napi)) { - __napi_schedule(&ch->napi); ltq_dma_disable_irq(&ch->dma); + __napi_schedule(&ch->napi); } ltq_dma_ack_irq(&ch->dma); -- cgit v1.2.3 From ebc5399ea1dfcddac31974091086a3379141899b Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Thu, 20 May 2021 08:34:59 +0200 Subject: ice: add ndo_bpf callback for safe mode netdev ops ice driver requires a programmable pipeline firmware package in order to have a support for advanced features. Otherwise, driver falls back to so called 'safe mode'. For that mode, ndo_bpf callback is not exposed and when user tries to load XDP program, the following happens: $ sudo ./xdp1 enp179s0f1 libbpf: Kernel error message: Underlying driver does not support XDP in native mode link set xdp fd failed which is sort of confusing, as there is a native XDP support, but not in the current mode. Improve the user experience by providing the specific ndo_bpf callback dedicated for safe mode which will make use of extack to explicitly let the user know that the DDP package is missing and that's the reason that the XDP can't be loaded onto interface currently. Cc: Jamal Hadi Salim Fixes: efc2214b6047 ("ice: Add support for XDP") Signed-off-by: Maciej Fijalkowski Tested-by: Kiran Bhandare Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_main.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 4ee85a217c6f..0eb2307325d3 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2555,6 +2555,20 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, return (ret || xdp_ring_err) ? -ENOMEM : 0; } +/** + * ice_xdp_safe_mode - XDP handler for safe mode + * @dev: netdevice + * @xdp: XDP command + */ +static int ice_xdp_safe_mode(struct net_device __always_unused *dev, + struct netdev_bpf *xdp) +{ + NL_SET_ERR_MSG_MOD(xdp->extack, + "Please provide working DDP firmware package in order to use XDP\n" + "Refer to Documentation/networking/device_drivers/ethernet/intel/ice.rst"); + return -EOPNOTSUPP; +} + /** * ice_xdp - implements XDP handler * @dev: netdevice @@ -6937,6 +6951,7 @@ static const struct net_device_ops ice_netdev_safe_mode_ops = { .ndo_change_mtu = ice_change_mtu, .ndo_get_stats64 = ice_get_stats64, .ndo_tx_timeout = ice_tx_timeout, + .ndo_bpf = ice_xdp_safe_mode, }; static const struct net_device_ops ice_netdev_ops = { -- cgit v1.2.3 From 2e84f6b3773f43263124c76499c0c4ec3f40aa9b Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Thu, 20 May 2021 08:35:00 +0200 Subject: ice: parameterize functions responsible for Tx ring management Commit ae15e0ba1b33 ("ice: Change number of XDP Tx queues to match number of Rx queues") tried to address the incorrect setting of XDP queue count that was based on the Tx queue count, whereas in theory we should provide the XDP queue per Rx queue. However, the routines that setup and destroy the set of Tx resources are still based on the vsi->num_txq. Ice supports the asynchronous Tx/Rx queue count, so for a setup where vsi->num_txq > vsi->num_rxq, ice_vsi_stop_tx_rings and ice_vsi_cfg_txqs will be accessing the vsi->xdp_rings out of the bounds. Parameterize two mentioned functions so they get the size of Tx resources array as the input. Fixes: ae15e0ba1b33 ("ice: Change number of XDP Tx queues to match number of Rx queues") Signed-off-by: Maciej Fijalkowski Tested-by: Kiran Bhandare Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_lib.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index d70ee573fde5..27f9dac8719c 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1717,12 +1717,13 @@ setup_rings: * ice_vsi_cfg_txqs - Configure the VSI for Tx * @vsi: the VSI being configured * @rings: Tx ring array to be configured + * @count: number of Tx ring array elements * * Return 0 on success and a negative value on error * Configure the Tx VSI for operation. */ static int -ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings) +ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings, u16 count) { struct ice_aqc_add_tx_qgrp *qg_buf; u16 q_idx = 0; @@ -1734,7 +1735,7 @@ ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings) qg_buf->num_txqs = 1; - for (q_idx = 0; q_idx < vsi->num_txq; q_idx++) { + for (q_idx = 0; q_idx < count; q_idx++) { err = ice_vsi_cfg_txq(vsi, rings[q_idx], qg_buf); if (err) goto err_cfg_txqs; @@ -1754,7 +1755,7 @@ err_cfg_txqs: */ int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi) { - return ice_vsi_cfg_txqs(vsi, vsi->tx_rings); + return ice_vsi_cfg_txqs(vsi, vsi->tx_rings, vsi->num_txq); } /** @@ -1769,7 +1770,7 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi) int ret; int i; - ret = ice_vsi_cfg_txqs(vsi, vsi->xdp_rings); + ret = ice_vsi_cfg_txqs(vsi, vsi->xdp_rings, vsi->num_xdp_txq); if (ret) return ret; @@ -2009,17 +2010,18 @@ int ice_vsi_stop_all_rx_rings(struct ice_vsi *vsi) * @rst_src: reset source * @rel_vmvf_num: Relative ID of VF/VM * @rings: Tx ring array to be stopped + * @count: number of Tx ring array elements */ static int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, - u16 rel_vmvf_num, struct ice_ring **rings) + u16 rel_vmvf_num, struct ice_ring **rings, u16 count) { u16 q_idx; if (vsi->num_txq > ICE_LAN_TXQ_MAX_QDIS) return -EINVAL; - for (q_idx = 0; q_idx < vsi->num_txq; q_idx++) { + for (q_idx = 0; q_idx < count; q_idx++) { struct ice_txq_meta txq_meta = { }; int status; @@ -2047,7 +2049,7 @@ int ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, u16 rel_vmvf_num) { - return ice_vsi_stop_tx_rings(vsi, rst_src, rel_vmvf_num, vsi->tx_rings); + return ice_vsi_stop_tx_rings(vsi, rst_src, rel_vmvf_num, vsi->tx_rings, vsi->num_txq); } /** @@ -2056,7 +2058,7 @@ ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, */ int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi) { - return ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0, vsi->xdp_rings); + return ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0, vsi->xdp_rings, vsi->num_xdp_txq); } /** -- cgit v1.2.3 From 2bf8d2ae3480da06e64dad3b326ebd2e40c0be86 Mon Sep 17 00:00:00 2001 From: Yang Li Date: Fri, 4 Jun 2021 18:08:27 +0800 Subject: net/mlx5e: Fix an error code in mlx5e_arfs_create_tables() When the code execute 'if (!priv->fs.arfs->wq)', the value of err is 0. So, we use -ENOMEM to indicate that the function create_singlethread_workqueue() return NULL. Clean up smatch warning: drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c:373 mlx5e_arfs_create_tables() warn: missing error code 'err'. Reported-by: Abaci Robot Fixes: f6755b80d693 ("net/mlx5e: Dynamic alloc arfs table for netdev when needed") Signed-off-by: Yang Li Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 5cd466ec6492..25403af32859 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -356,7 +356,7 @@ err: int mlx5e_arfs_create_tables(struct mlx5e_priv *priv) { - int err = 0; + int err = -ENOMEM; int i; if (!(priv->netdev->hw_features & NETIF_F_NTUPLE)) -- cgit v1.2.3 From fb1a3132ee1ac968316e45d21a48703a6db0b6c3 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 31 May 2021 16:28:39 +0300 Subject: net/mlx5e: Fix use-after-free of encap entry in neigh update handler Function mlx5e_rep_neigh_update() wasn't updated to accommodate rtnl lock removal from TC filter update path and properly handle concurrent encap entry insertion/deletion which can lead to following use-after-free: [23827.464923] ================================================================== [23827.469446] BUG: KASAN: use-after-free in mlx5e_encap_take+0x72/0x140 [mlx5_core] [23827.470971] Read of size 4 at addr ffff8881d132228c by task kworker/u20:6/21635 [23827.472251] [23827.472615] CPU: 9 PID: 21635 Comm: kworker/u20:6 Not tainted 5.13.0-rc3+ #5 [23827.473788] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [23827.475639] Workqueue: mlx5e mlx5e_rep_neigh_update [mlx5_core] [23827.476731] Call Trace: [23827.477260] dump_stack+0xbb/0x107 [23827.477906] print_address_description.constprop.0+0x18/0x140 [23827.478896] ? mlx5e_encap_take+0x72/0x140 [mlx5_core] [23827.479879] ? mlx5e_encap_take+0x72/0x140 [mlx5_core] [23827.480905] kasan_report.cold+0x7c/0xd8 [23827.481701] ? mlx5e_encap_take+0x72/0x140 [mlx5_core] [23827.482744] kasan_check_range+0x145/0x1a0 [23827.493112] mlx5e_encap_take+0x72/0x140 [mlx5_core] [23827.494054] ? mlx5e_tc_tun_encap_info_equal_generic+0x140/0x140 [mlx5_core] [23827.495296] mlx5e_rep_neigh_update+0x41e/0x5e0 [mlx5_core] [23827.496338] ? mlx5e_rep_neigh_entry_release+0xb80/0xb80 [mlx5_core] [23827.497486] ? read_word_at_a_time+0xe/0x20 [23827.498250] ? strscpy+0xa0/0x2a0 [23827.498889] process_one_work+0x8ac/0x14e0 [23827.499638] ? lockdep_hardirqs_on_prepare+0x400/0x400 [23827.500537] ? pwq_dec_nr_in_flight+0x2c0/0x2c0 [23827.501359] ? rwlock_bug.part.0+0x90/0x90 [23827.502116] worker_thread+0x53b/0x1220 [23827.502831] ? process_one_work+0x14e0/0x14e0 [23827.503627] kthread+0x328/0x3f0 [23827.504254] ? _raw_spin_unlock_irq+0x24/0x40 [23827.505065] ? __kthread_bind_mask+0x90/0x90 [23827.505912] ret_from_fork+0x1f/0x30 [23827.506621] [23827.506987] Allocated by task 28248: [23827.507694] kasan_save_stack+0x1b/0x40 [23827.508476] __kasan_kmalloc+0x7c/0x90 [23827.509197] mlx5e_attach_encap+0xde1/0x1d40 [mlx5_core] [23827.510194] mlx5e_tc_add_fdb_flow+0x397/0xc40 [mlx5_core] [23827.511218] __mlx5e_add_fdb_flow+0x519/0xb30 [mlx5_core] [23827.512234] mlx5e_configure_flower+0x191c/0x4870 [mlx5_core] [23827.513298] tc_setup_cb_add+0x1d5/0x420 [23827.514023] fl_hw_replace_filter+0x382/0x6a0 [cls_flower] [23827.514975] fl_change+0x2ceb/0x4a51 [cls_flower] [23827.515821] tc_new_tfilter+0x89a/0x2070 [23827.516548] rtnetlink_rcv_msg+0x644/0x8c0 [23827.517300] netlink_rcv_skb+0x11d/0x340 [23827.518021] netlink_unicast+0x42b/0x700 [23827.518742] netlink_sendmsg+0x743/0xc20 [23827.519467] sock_sendmsg+0xb2/0xe0 [23827.520131] ____sys_sendmsg+0x590/0x770 [23827.520851] ___sys_sendmsg+0xd8/0x160 [23827.521552] __sys_sendmsg+0xb7/0x140 [23827.522238] do_syscall_64+0x3a/0x70 [23827.522907] entry_SYSCALL_64_after_hwframe+0x44/0xae [23827.523797] [23827.524163] Freed by task 25948: [23827.524780] kasan_save_stack+0x1b/0x40 [23827.525488] kasan_set_track+0x1c/0x30 [23827.526187] kasan_set_free_info+0x20/0x30 [23827.526968] __kasan_slab_free+0xed/0x130 [23827.527709] slab_free_freelist_hook+0xcf/0x1d0 [23827.528528] kmem_cache_free_bulk+0x33a/0x6e0 [23827.529317] kfree_rcu_work+0x55f/0xb70 [23827.530024] process_one_work+0x8ac/0x14e0 [23827.530770] worker_thread+0x53b/0x1220 [23827.531480] kthread+0x328/0x3f0 [23827.532114] ret_from_fork+0x1f/0x30 [23827.532785] [23827.533147] Last potentially related work creation: [23827.534007] kasan_save_stack+0x1b/0x40 [23827.534710] kasan_record_aux_stack+0xab/0xc0 [23827.535492] kvfree_call_rcu+0x31/0x7b0 [23827.536206] mlx5e_tc_del_fdb_flow+0x577/0xef0 [mlx5_core] [23827.537305] mlx5e_flow_put+0x49/0x80 [mlx5_core] [23827.538290] mlx5e_delete_flower+0x6d1/0xe60 [mlx5_core] [23827.539300] tc_setup_cb_destroy+0x18e/0x2f0 [23827.540144] fl_hw_destroy_filter+0x1d2/0x310 [cls_flower] [23827.541148] __fl_delete+0x4dc/0x660 [cls_flower] [23827.541985] fl_delete+0x97/0x160 [cls_flower] [23827.542782] tc_del_tfilter+0x7ab/0x13d0 [23827.543503] rtnetlink_rcv_msg+0x644/0x8c0 [23827.544257] netlink_rcv_skb+0x11d/0x340 [23827.544981] netlink_unicast+0x42b/0x700 [23827.545700] netlink_sendmsg+0x743/0xc20 [23827.546424] sock_sendmsg+0xb2/0xe0 [23827.547084] ____sys_sendmsg+0x590/0x770 [23827.547850] ___sys_sendmsg+0xd8/0x160 [23827.548606] __sys_sendmsg+0xb7/0x140 [23827.549303] do_syscall_64+0x3a/0x70 [23827.549969] entry_SYSCALL_64_after_hwframe+0x44/0xae [23827.550853] [23827.551217] The buggy address belongs to the object at ffff8881d1322200 [23827.551217] which belongs to the cache kmalloc-256 of size 256 [23827.553341] The buggy address is located 140 bytes inside of [23827.553341] 256-byte region [ffff8881d1322200, ffff8881d1322300) [23827.555747] The buggy address belongs to the page: [23827.556847] page:00000000898762aa refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1d1320 [23827.558651] head:00000000898762aa order:2 compound_mapcount:0 compound_pincount:0 [23827.559961] flags: 0x2ffff800010200(slab|head|node=0|zone=2|lastcpupid=0x1ffff) [23827.561243] raw: 002ffff800010200 dead000000000100 dead000000000122 ffff888100042b40 [23827.562653] raw: 0000000000000000 0000000000200020 00000001ffffffff 0000000000000000 [23827.564112] page dumped because: kasan: bad access detected [23827.565439] [23827.565932] Memory state around the buggy address: [23827.566917] ffff8881d1322180: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [23827.568485] ffff8881d1322200: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [23827.569818] >ffff8881d1322280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [23827.571143] ^ [23827.571879] ffff8881d1322300: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [23827.573283] ffff8881d1322380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [23827.574654] ================================================================== Most of the necessary logic is already correctly implemented by mlx5e_get_next_valid_encap() helper that is used in neigh stats update handler. Make the handler generic by renaming it to mlx5e_get_next_matching_encap() and use callback to test whether flow is matching instead of hardcoded check for 'valid' flag value. Implement mlx5e_get_next_valid_encap() by calling mlx5e_get_next_matching_encap() with callback that tests encap MLX5_ENCAP_ENTRY_VALID flag. Implement new mlx5e_get_next_init_encap() helper by calling mlx5e_get_next_matching_encap() with callback that tests encap completion result to be non-error and use it in mlx5e_rep_neigh_update() to safely iterate over nhe->encap_list. Remove encap completion logic from mlx5e_rep_update_flows() since the encap entries passed to this function are already guaranteed to be properly initialized by similar code in mlx5e_get_next_init_encap(). Fixes: 2a1f1768fa17 ("net/mlx5e: Refactor neigh update for concurrent execution") Signed-off-by: Vlad Buslov Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en/rep/neigh.c | 15 ++++------ .../net/ethernet/mellanox/mlx5/core/en/rep/tc.c | 6 +--- .../ethernet/mellanox/mlx5/core/en/tc_tun_encap.c | 33 ++++++++++++++++++++-- drivers/net/ethernet/mellanox/mlx5/core/en_tc.h | 3 ++ 4 files changed, 40 insertions(+), 17 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c index be0ee03de721..2e9bee4e5209 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c @@ -129,10 +129,9 @@ static void mlx5e_rep_neigh_update(struct work_struct *work) work); struct mlx5e_neigh_hash_entry *nhe = update_work->nhe; struct neighbour *n = update_work->n; + struct mlx5e_encap_entry *e = NULL; bool neigh_connected, same_dev; - struct mlx5e_encap_entry *e; unsigned char ha[ETH_ALEN]; - struct mlx5e_priv *priv; u8 nud_state, dead; rtnl_lock(); @@ -156,14 +155,12 @@ static void mlx5e_rep_neigh_update(struct work_struct *work) if (!same_dev) goto out; - list_for_each_entry(e, &nhe->encap_list, encap_list) { - if (!mlx5e_encap_take(e)) - continue; + /* mlx5e_get_next_init_encap() releases previous encap before returning + * the next one. + */ + while ((e = mlx5e_get_next_init_encap(nhe, e)) != NULL) + mlx5e_rep_update_flows(netdev_priv(e->out_dev), e, neigh_connected, ha); - priv = netdev_priv(e->out_dev); - mlx5e_rep_update_flows(priv, e, neigh_connected, ha); - mlx5e_encap_put(priv, e); - } out: rtnl_unlock(); mlx5e_release_neigh_update_work(update_work); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index 311382261840..85eaadc989df 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -94,13 +94,9 @@ void mlx5e_rep_update_flows(struct mlx5e_priv *priv, ASSERT_RTNL(); - /* wait for encap to be fully initialized */ - wait_for_completion(&e->res_ready); - mutex_lock(&esw->offloads.encap_tbl_lock); encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID); - if (e->compl_result < 0 || (encap_connected == neigh_connected && - ether_addr_equal(e->h_dest, ha))) + if (encap_connected == neigh_connected && ether_addr_equal(e->h_dest, ha)) goto unlock; mlx5e_take_all_encap_flows(e, &flow_list); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index f1fb11680d20..490131e06efb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -251,9 +251,12 @@ static void mlx5e_take_all_route_decap_flows(struct mlx5e_route_entry *r, mlx5e_take_tmp_flow(flow, flow_list, 0); } +typedef bool (match_cb)(struct mlx5e_encap_entry *); + static struct mlx5e_encap_entry * -mlx5e_get_next_valid_encap(struct mlx5e_neigh_hash_entry *nhe, - struct mlx5e_encap_entry *e) +mlx5e_get_next_matching_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e, + match_cb match) { struct mlx5e_encap_entry *next = NULL; @@ -288,7 +291,7 @@ retry: /* wait for encap to be fully initialized */ wait_for_completion(&next->res_ready); /* continue searching if encap entry is not in valid state after completion */ - if (!(next->flags & MLX5_ENCAP_ENTRY_VALID)) { + if (!match(next)) { e = next; goto retry; } @@ -296,6 +299,30 @@ retry: return next; } +static bool mlx5e_encap_valid(struct mlx5e_encap_entry *e) +{ + return e->flags & MLX5_ENCAP_ENTRY_VALID; +} + +static struct mlx5e_encap_entry * +mlx5e_get_next_valid_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e) +{ + return mlx5e_get_next_matching_encap(nhe, e, mlx5e_encap_valid); +} + +static bool mlx5e_encap_initialized(struct mlx5e_encap_entry *e) +{ + return e->compl_result >= 0; +} + +struct mlx5e_encap_entry * +mlx5e_get_next_init_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e) +{ + return mlx5e_get_next_matching_encap(nhe, e, mlx5e_encap_initialized); +} + void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) { struct mlx5e_neigh *m_neigh = &nhe->m_neigh; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 25c091795bcd..17027536efba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -178,6 +178,9 @@ void mlx5e_take_all_encap_flows(struct mlx5e_encap_entry *e, struct list_head *f void mlx5e_put_flow_list(struct mlx5e_priv *priv, struct list_head *flow_list); struct mlx5e_neigh_hash_entry; +struct mlx5e_encap_entry * +mlx5e_get_next_init_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e); void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe); void mlx5e_tc_reoffload_flows_work(struct work_struct *work); -- cgit v1.2.3 From 8ad893e516a77209a1818a2072d2027d87db809f Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Fri, 28 May 2021 13:20:32 -0500 Subject: net/mlx5e: Remove dependency in IPsec initialization flows Currently, IPsec feature is disabled because mlx5e_build_nic_netdev is required to be called after mlx5e_ipsec_init. This requirement is invalid as mlx5e_build_nic_netdev and mlx5e_ipsec_init initialize independent resources. Remove ipsec pointer check in mlx5e_build_nic_netdev so that the two functions can be called at any order. Fixes: 547eede070eb ("net/mlx5e: IPSec, Innova IPSec offload infrastructure") Signed-off-by: Huy Nguyen Reviewed-by: Raed Salem Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 3d45341e2216..26f7fab109d9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -532,9 +532,6 @@ void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv) struct mlx5_core_dev *mdev = priv->mdev; struct net_device *netdev = priv->netdev; - if (!priv->ipsec) - return; - if (!(mlx5_accel_ipsec_device_caps(mdev) & MLX5_ACCEL_IPSEC_CAP_ESP) || !MLX5_CAP_ETH(mdev, swp)) { mlx5_core_dbg(mdev, "mlx5e: ESP and SWP offload not supported\n"); -- cgit v1.2.3 From a3e5fd9314dfc4314a9567cde96e1aef83a7458a Mon Sep 17 00:00:00 2001 From: Dima Chumak Date: Wed, 26 May 2021 13:45:10 +0300 Subject: net/mlx5e: Fix page reclaim for dead peer hairpin When adding a hairpin flow, a firmware-side send queue is created for the peer net device, which claims some host memory pages for its internal ring buffer. If the peer net device is removed/unbound before the hairpin flow is deleted, then the send queue is not destroyed which leads to a stack trace on pci device remove: [ 748.005230] mlx5_core 0000:08:00.2: wait_func:1094:(pid 12985): MANAGE_PAGES(0x108) timeout. Will cause a leak of a command resource [ 748.005231] mlx5_core 0000:08:00.2: reclaim_pages:514:(pid 12985): failed reclaiming pages: err -110 [ 748.001835] mlx5_core 0000:08:00.2: mlx5_reclaim_root_pages:653:(pid 12985): failed reclaiming pages (-110) for func id 0x0 [ 748.002171] ------------[ cut here ]------------ [ 748.001177] FW pages counter is 4 after reclaiming all pages [ 748.001186] WARNING: CPU: 1 PID: 12985 at drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c:685 mlx5_reclaim_startup_pages+0x34b/0x460 [mlx5_core] [ +0.002771] Modules linked in: cls_flower mlx5_ib mlx5_core ptp pps_core act_mirred sch_ingress openvswitch nsh xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 br_netfilter rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi rdma_cm ib_umad ib_ipoib iw_cm ib_cm ib_uverbs ib_core overlay fuse [last unloaded: pps_core] [ 748.007225] CPU: 1 PID: 12985 Comm: tee Not tainted 5.12.0+ #1 [ 748.001376] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 748.002315] RIP: 0010:mlx5_reclaim_startup_pages+0x34b/0x460 [mlx5_core] [ 748.001679] Code: 28 00 00 00 0f 85 22 01 00 00 48 81 c4 b0 00 00 00 31 c0 5b 5d 41 5c 41 5d 41 5e 41 5f c3 48 c7 c7 40 cc 19 a1 e8 9f 71 0e e2 <0f> 0b e9 30 ff ff ff 48 c7 c7 a0 cc 19 a1 e8 8c 71 0e e2 0f 0b e9 [ 748.003781] RSP: 0018:ffff88815220faf8 EFLAGS: 00010286 [ 748.001149] RAX: 0000000000000000 RBX: ffff8881b4900280 RCX: 0000000000000000 [ 748.001445] RDX: 0000000000000027 RSI: 0000000000000004 RDI: ffffed102a441f51 [ 748.001614] RBP: 00000000000032b9 R08: 0000000000000001 R09: ffffed1054a15ee8 [ 748.001446] R10: ffff8882a50af73b R11: ffffed1054a15ee7 R12: fffffbfff07c1e30 [ 748.001447] R13: dffffc0000000000 R14: ffff8881b492cba8 R15: 0000000000000000 [ 748.001429] FS: 00007f58bd08b580(0000) GS:ffff8882a5080000(0000) knlGS:0000000000000000 [ 748.001695] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 748.001309] CR2: 000055a026351740 CR3: 00000001d3b48006 CR4: 0000000000370ea0 [ 748.001506] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 748.001483] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 748.001654] Call Trace: [ 748.000576] ? mlx5_satisfy_startup_pages+0x290/0x290 [mlx5_core] [ 748.001416] ? mlx5_cmd_teardown_hca+0xa2/0xd0 [mlx5_core] [ 748.001354] ? mlx5_cmd_init_hca+0x280/0x280 [mlx5_core] [ 748.001203] mlx5_function_teardown+0x30/0x60 [mlx5_core] [ 748.001275] mlx5_uninit_one+0xa7/0xc0 [mlx5_core] [ 748.001200] remove_one+0x5f/0xc0 [mlx5_core] [ 748.001075] pci_device_remove+0x9f/0x1d0 [ 748.000833] device_release_driver_internal+0x1e0/0x490 [ 748.001207] unbind_store+0x19f/0x200 [ 748.000942] ? sysfs_file_ops+0x170/0x170 [ 748.001000] kernfs_fop_write_iter+0x2bc/0x450 [ 748.000970] new_sync_write+0x373/0x610 [ 748.001124] ? new_sync_read+0x600/0x600 [ 748.001057] ? lock_acquire+0x4d6/0x700 [ 748.000908] ? lockdep_hardirqs_on_prepare+0x400/0x400 [ 748.001126] ? fd_install+0x1c9/0x4d0 [ 748.000951] vfs_write+0x4d0/0x800 [ 748.000804] ksys_write+0xf9/0x1d0 [ 748.000868] ? __x64_sys_read+0xb0/0xb0 [ 748.000811] ? filp_open+0x50/0x50 [ 748.000919] ? syscall_enter_from_user_mode+0x1d/0x50 [ 748.001223] do_syscall_64+0x3f/0x80 [ 748.000892] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 748.001026] RIP: 0033:0x7f58bcfb22f7 [ 748.000944] Code: 0d 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24 [ 748.003925] RSP: 002b:00007fffd7f2aaa8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 748.001732] RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007f58bcfb22f7 [ 748.001426] RDX: 000000000000000d RSI: 00007fffd7f2abc0 RDI: 0000000000000003 [ 748.001746] RBP: 00007fffd7f2abc0 R08: 0000000000000000 R09: 0000000000000001 [ 748.001631] R10: 00000000000001b6 R11: 0000000000000246 R12: 000000000000000d [ 748.001537] R13: 00005597ac2c24a0 R14: 000000000000000d R15: 00007f58bd084700 [ 748.001564] irq event stamp: 0 [ 748.000787] hardirqs last enabled at (0): [<0000000000000000>] 0x0 [ 748.001399] hardirqs last disabled at (0): [] copy_process+0x146f/0x5eb0 [ 748.001854] softirqs last enabled at (0): [] copy_process+0x14ae/0x5eb0 [ 748.013431] softirqs last disabled at (0): [<0000000000000000>] 0x0 [ 748.001492] ---[ end trace a6fabd773d1c51ae ]--- Fix by destroying the send queue of a hairpin peer net device that is being removed/unbound, which returns the allocated ring buffer pages to the host. Fixes: 4d8fcf216c90 ("net/mlx5e: Avoid unbounded peer devices when unpairing TC hairpin rules") Signed-off-by: Dima Chumak Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/transobj.c | 30 +++++++++++++++++----- include/linux/mlx5/transobj.h | 1 + 3 files changed, 26 insertions(+), 7 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index dd64878e5b38..d4b0f270b6bb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -4765,7 +4765,7 @@ static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv, list_for_each_entry_safe(hpe, tmp, &init_wait_list, dead_peer_wait_list) { wait_for_completion(&hpe->res_ready); if (!IS_ERR_OR_NULL(hpe->hp) && hpe->peer_vhca_id == peer_vhca_id) - hpe->hp->pair->peer_gone = true; + mlx5_core_hairpin_clear_dead_peer(hpe->hp->pair); mlx5e_hairpin_put(priv, hpe); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c index 01cc00ad8acf..b6931bbe52d2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c @@ -424,6 +424,15 @@ err_modify_sq: return err; } +static void mlx5_hairpin_unpair_peer_sq(struct mlx5_hairpin *hp) +{ + int i; + + for (i = 0; i < hp->num_channels; i++) + mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY, + MLX5_SQC_STATE_RST, 0, 0); +} + static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp) { int i; @@ -432,13 +441,9 @@ static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp) for (i = 0; i < hp->num_channels; i++) mlx5_hairpin_modify_rq(hp->func_mdev, hp->rqn[i], MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_RST, 0, 0); - /* unset peer SQs */ - if (hp->peer_gone) - return; - for (i = 0; i < hp->num_channels; i++) - mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY, - MLX5_SQC_STATE_RST, 0, 0); + if (!hp->peer_gone) + mlx5_hairpin_unpair_peer_sq(hp); } struct mlx5_hairpin * @@ -485,3 +490,16 @@ void mlx5_core_hairpin_destroy(struct mlx5_hairpin *hp) mlx5_hairpin_destroy_queues(hp); kfree(hp); } + +void mlx5_core_hairpin_clear_dead_peer(struct mlx5_hairpin *hp) +{ + int i; + + mlx5_hairpin_unpair_peer_sq(hp); + + /* destroy peer SQ */ + for (i = 0; i < hp->num_channels; i++) + mlx5_core_destroy_sq(hp->peer_mdev, hp->sqn[i]); + + hp->peer_gone = true; +} diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h index 028f442530cf..60ffeb6b67ae 100644 --- a/include/linux/mlx5/transobj.h +++ b/include/linux/mlx5/transobj.h @@ -85,4 +85,5 @@ mlx5_core_hairpin_create(struct mlx5_core_dev *func_mdev, struct mlx5_hairpin_params *params); void mlx5_core_hairpin_destroy(struct mlx5_hairpin *pair); +void mlx5_core_hairpin_clear_dead_peer(struct mlx5_hairpin *hp); #endif /* __TRANSOBJ_H__ */ -- cgit v1.2.3 From c189716b2a7c1d2d8658e269735273caa1c38b54 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Sun, 6 Jun 2021 11:20:46 +0300 Subject: net/mlx5: Consider RoCE cap before init RDMA resources Check if RoCE is supported by the device before enable it in the vport context and create all the RDMA steering objects. Fixes: 80f09dfc237f ("net/mlx5: Eswitch, enable RoCE loopback traffic") Signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/rdma.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c index 441b5453acae..540cf05f6373 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c @@ -156,6 +156,9 @@ void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) { int err; + if (!MLX5_CAP_GEN(dev, roce)) + return; + err = mlx5_nic_vport_enable_roce(dev); if (err) { mlx5_core_err(dev, "Failed to enable RoCE: %d\n", err); -- cgit v1.2.3 From 4aaf96ac8b45d8e2e019b6b53cce65a73c4ace2c Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Sun, 6 Jun 2021 11:23:41 +0300 Subject: net/mlx5: DR, Don't use SW steering when RoCE is not supported SW steering uses RC QP to write/read to/from ICM, hence it's not supported when RoCE is not supported as well. Fixes: 70605ea545e8 ("net/mlx5: DR, Expose APIs for direct rule managing") Signed-off-by: Maor Gottlieb Reviewed-by: Alex Vesker Reviewed-by: Yevgeny Kliteynik Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index 612b0ac31db2..9737565cd8d4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -124,10 +124,11 @@ int mlx5dr_action_destroy(struct mlx5dr_action *action); static inline bool mlx5dr_is_supported(struct mlx5_core_dev *dev) { - return MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner) || - (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner_v2) && - (MLX5_CAP_GEN(dev, steering_format_version) <= - MLX5_STEERING_FORMAT_CONNECTX_6DX)); + return MLX5_CAP_GEN(dev, roce) && + (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner) || + (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner_v2) && + (MLX5_CAP_GEN(dev, steering_format_version) <= + MLX5_STEERING_FORMAT_CONNECTX_6DX))); } /* buddy functions & structure */ -- cgit v1.2.3 From 11f5ac3e05c134d333afe6f84ab10e22bc0a5d5a Mon Sep 17 00:00:00 2001 From: Chris Mi Date: Wed, 28 Apr 2021 19:39:26 +0800 Subject: net/mlx5e: Verify dev is present in get devlink port ndo When changing eswitch mode, the netdev is detached from the hardware resources. So verify dev is present in get devlink port ndo. Otherwise, we will hit the following panic: [241535.973539] RIP: 0010:__devlink_port_phys_port_name_get+0x13/0x1b0 [241535.976471] RSP: 0018:ffff9eaf0ae1b7c8 EFLAGS: 00010292 [241535.977471] RAX: 000000000002d370 RBX: 000000000002d370 RCX: 0000000000000000 [241535.978479] RDX: 0000000000000010 RSI: ffff9eaf0ae1b858 RDI: 000000000002d370 [241535.979482] RBP: ffff9eaf0ae1b7e0 R08: 000000000000002a R09: ffff8888d54d13da [241535.980486] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8888e6700000 [241535.981491] R13: ffff9eaf0ae1b858 R14: 0000000000000010 R15: 0000000000000000 [241535.982489] FS: 00007fd374ef3740(0000) GS:ffff88909ea00000(0000) knlGS:0000000000000000 [241535.983494] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [241535.984487] CR2: 000000000002d444 CR3: 000000089fd26006 CR4: 00000000003706e0 [241535.985502] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [241535.986499] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [241535.987477] Call Trace: [241535.988426] ? nla_put_64bit+0x71/0xa0 [241535.989368] devlink_compat_phys_port_name_get+0x50/0xa0 [241535.990312] dev_get_phys_port_name+0x4b/0x60 [241535.991252] rtnl_fill_ifinfo+0x57b/0xcb0 [241535.992192] rtnl_dump_ifinfo+0x58f/0x6d0 [241535.993123] ? ksize+0x14/0x20 [241535.994033] ? __alloc_skb+0xe8/0x250 [241535.994935] netlink_dump+0x17c/0x300 [241535.995821] netlink_recvmsg+0x1de/0x2c0 [241535.996677] sock_recvmsg+0x70/0x80 [241535.997518] ____sys_recvmsg+0x9b/0x1b0 [241535.998360] ? iovec_from_user+0x82/0x120 [241535.999202] ? __import_iovec+0x2c/0x130 [241536.000031] ___sys_recvmsg+0x94/0x130 [241536.000850] ? __handle_mm_fault+0x56d/0x6e0 [241536.001668] __sys_recvmsg+0x5f/0xb0 [241536.002464] ? syscall_enter_from_user_mode+0x2b/0x80 [241536.003242] __x64_sys_recvmsg+0x1f/0x30 [241536.004008] do_syscall_64+0x38/0x50 [241536.004767] entry_SYSCALL_64_after_hwframe+0x44/0xae [241536.005532] RIP: 0033:0x7fd375014f47 Fixes: 2ff349c5edfe ("net/mlx5e: Verify dev is present in some ndos") Signed-off-by: Roi Dayan Signed-off-by: Chris Mi Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c index 0dd7615e5931..bc33eaada3b9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c @@ -64,6 +64,8 @@ struct devlink_port *mlx5e_get_devlink_port(struct net_device *dev) struct mlx5e_priv *priv = netdev_priv(dev); struct devlink_port *port; + if (!netif_device_present(dev)) + return NULL; port = mlx5e_devlink_get_dl_port(priv); if (port->registered) return port; -- cgit v1.2.3 From 9ae8c18c5e4d8814d3b405a07712fa5464070e3e Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Thu, 29 Apr 2021 10:03:20 +0300 Subject: net/mlx5e: Don't update netdev RQs with PTP-RQ Since the driver opens the PTP-RQ under channel 0, it appears to the stack as if the SKB was received on rxq0. So from thew stack POV there are still the same number of RX queues. Fixes: 960fbfe222a4 ("net/mlx5e: Allow coexistence of CQE compression and HW TS PTP") Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Reviewed-by: Maxim Mikityanskiy Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index ec6bafe7a2e5..263adc82b4e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2705,8 +2705,6 @@ static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv) nch = priv->channels.params.num_channels; ntc = priv->channels.params.num_tc; num_rxqs = nch * priv->profile->rq_groups; - if (priv->channels.params.ptp_rx) - num_rxqs++; mlx5e_netdev_set_tcs(netdev, nch, ntc); -- cgit v1.2.3 From a6ee6f5f1082c416f9bfffbae1a87feff8a6ab3d Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Mon, 19 Apr 2021 11:58:31 +0300 Subject: net/mlx5e: Fix select queue to consider SKBTX_HW_TSTAMP Steering packets to PTP-SQ should be done only if the SKB has SKBTX_HW_TSTAMP set in the tx_flags. While here, take the function into a header and inline it. Set the whole condition to select the PTP-SQ to unlikely. Fixes: 24c22dd0918b ("net/mlx5e: Add states to PTP channel") Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Reviewed-by: Maxim Mikityanskiy Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c | 1 - drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h | 22 +++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 25 +++--------------------- 3 files changed, 25 insertions(+), 23 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index d907c1acd4d5..778e229310a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB // Copyright (c) 2020 Mellanox Technologies -#include #include "en/ptp.h" #include "en/txrx.h" #include "en/params.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h index ab935cce952b..c96668bd701c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h @@ -6,6 +6,7 @@ #include "en.h" #include "en_stats.h" +#include struct mlx5e_ptpsq { struct mlx5e_txqsq txqsq; @@ -43,6 +44,27 @@ struct mlx5e_ptp { DECLARE_BITMAP(state, MLX5E_PTP_STATE_NUM_STATES); }; +static inline bool mlx5e_use_ptpsq(struct sk_buff *skb) +{ + struct flow_keys fk; + + if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) + return false; + + if (!skb_flow_dissect_flow_keys(skb, &fk, 0)) + return false; + + if (fk.basic.n_proto == htons(ETH_P_1588)) + return true; + + if (fk.basic.n_proto != htons(ETH_P_IP) && + fk.basic.n_proto != htons(ETH_P_IPV6)) + return false; + + return (fk.basic.ip_proto == IPPROTO_UDP && + fk.ports.dst == htons(PTP_EV_PORT)); +} + int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params, u8 lag_port, struct mlx5e_ptp **cp); void mlx5e_ptp_close(struct mlx5e_ptp *c); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 8ba62671f5f1..320fe0cda917 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -32,7 +32,6 @@ #include #include -#include #include #include #include "en.h" @@ -67,24 +66,6 @@ static inline int mlx5e_get_dscp_up(struct mlx5e_priv *priv, struct sk_buff *skb } #endif -static bool mlx5e_use_ptpsq(struct sk_buff *skb) -{ - struct flow_keys fk; - - if (!skb_flow_dissect_flow_keys(skb, &fk, 0)) - return false; - - if (fk.basic.n_proto == htons(ETH_P_1588)) - return true; - - if (fk.basic.n_proto != htons(ETH_P_IP) && - fk.basic.n_proto != htons(ETH_P_IPV6)) - return false; - - return (fk.basic.ip_proto == IPPROTO_UDP && - fk.ports.dst == htons(PTP_EV_PORT)); -} - static u16 mlx5e_select_ptpsq(struct net_device *dev, struct sk_buff *skb) { struct mlx5e_priv *priv = netdev_priv(dev); @@ -145,9 +126,9 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, } ptp_channel = READ_ONCE(priv->channels.ptp); - if (unlikely(ptp_channel) && - test_bit(MLX5E_PTP_STATE_TX, ptp_channel->state) && - mlx5e_use_ptpsq(skb)) + if (unlikely(ptp_channel && + test_bit(MLX5E_PTP_STATE_TX, ptp_channel->state) && + mlx5e_use_ptpsq(skb))) return mlx5e_select_ptpsq(dev, skb); txq_ix = netdev_pick_tx(dev, skb, NULL); -- cgit v1.2.3 From 7a545077cb6701957e84c7f158630bb5c984e648 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Thu, 25 Feb 2021 12:27:53 +0200 Subject: Revert "net/mlx5: Arm only EQs with EQEs" In the scenario described below, an EQ can remain in FIRED state which can result in missing an interrupt generation. The scenario: device mlx5_core driver ------ ---------------- EQ1.eqe generated EQ1.MSI-X sent EQ1.state = FIRED EQ2.eqe generated mlx5_irq() polls - eq1_eqes() arm eq1 polls - eq2_eqes() arm eq2 EQ2.MSI-X sent EQ2.state = FIRED mlx5_irq() polls - eq2_eqes() -- no eqes found driver skips EQ arming; ->EQ2 remains fired, misses generating interrupt. Hence, always arm the EQ by reverting the cited commit in fixes tag. Fixes: d894892dda25 ("net/mlx5: Arm only EQs with EQEs") Signed-off-by: Shay Drory Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 77c0ca655975..940333410267 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -136,7 +136,7 @@ static int mlx5_eq_comp_int(struct notifier_block *nb, eqe = next_eqe_sw(eq); if (!eqe) - return 0; + goto out; do { struct mlx5_core_cq *cq; @@ -161,6 +161,8 @@ static int mlx5_eq_comp_int(struct notifier_block *nb, ++eq->cons_index; } while ((++num_eqes < MLX5_EQ_POLLING_BUDGET) && (eqe = next_eqe_sw(eq))); + +out: eq_update_ci(eq, 1); if (cqn != -1) @@ -248,9 +250,9 @@ static int mlx5_eq_async_int(struct notifier_block *nb, ++eq->cons_index; } while ((++num_eqes < MLX5_EQ_POLLING_BUDGET) && (eqe = next_eqe_sw(eq))); - eq_update_ci(eq, 1); out: + eq_update_ci(eq, 1); mlx5_eq_async_int_unlock(eq_async, recovery, &flags); return unlikely(recovery) ? num_eqes : 0; -- cgit v1.2.3 From 6d6727dddc7f93fcc155cb8d0c49c29ae0e71122 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Mon, 10 May 2021 14:34:58 +0300 Subject: net/mlx5e: Block offload of outer header csum for UDP tunnels The device is able to offload either the outer header csum or inner header csum. The driver utilizes the inner csum offload. Hence, block setting of tx-udp_tnl-csum-segmentation and set it to off[fixed]. Fixes: b49663c8fb49 ("net/mlx5e: Add support for UDP tunnel segmentation with outer checksum offload") Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 263adc82b4e1..d4167f7be99c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4822,13 +4822,9 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) } if (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev)) { - netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; - netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; - netdev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM; - netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; + netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; + netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL; + netdev->vlan_features |= NETIF_F_GSO_UDP_TUNNEL; } if (mlx5e_tunnel_proto_supported_tx(mdev, IPPROTO_GRE)) { -- cgit v1.2.3 From 54e1217b90486c94b26f24dcee1ee5ef5372f832 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Wed, 26 May 2021 10:40:36 +0300 Subject: net/mlx5e: Block offload of outer header csum for GRE tunnel The device is able to offload either the outer header csum or inner header csum. The driver utilizes the inner csum offload. So, prohibit setting of tx-gre-csum-segmentation and let it be: off[fixed]. Fixes: 2729984149e6 ("net/mlx5e: Support TSO and TX checksum offloads for GRE tunnels") Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index d4167f7be99c..d26b8ed51195 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4828,12 +4828,9 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) } if (mlx5e_tunnel_proto_supported_tx(mdev, IPPROTO_GRE)) { - netdev->hw_features |= NETIF_F_GSO_GRE | - NETIF_F_GSO_GRE_CSUM; - netdev->hw_enc_features |= NETIF_F_GSO_GRE | - NETIF_F_GSO_GRE_CSUM; - netdev->gso_partial_features |= NETIF_F_GSO_GRE | - NETIF_F_GSO_GRE_CSUM; + netdev->hw_features |= NETIF_F_GSO_GRE; + netdev->hw_enc_features |= NETIF_F_GSO_GRE; + netdev->gso_partial_features |= NETIF_F_GSO_GRE; } if (mlx5e_tunnel_proto_supported_tx(mdev, IPPROTO_IPIP)) { -- cgit v1.2.3 From 33e381448cf7a05d76ac0b47d4a6531ecd0e5c53 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Fri, 11 Jun 2021 08:13:39 +0200 Subject: alx: Fix an error handling path in 'alx_probe()' If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function. Fixes: ab69bde6b2e9 ("alx: add a simple AR816x/AR817x device driver") Signed-off-by: Christophe JAILLET Signed-off-by: David S. Miller --- drivers/net/ethernet/atheros/alx/main.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index b3d74332ed33..7748b276e5fd 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1849,6 +1849,7 @@ out_free_netdev: free_netdev(netdev); out_pci_release: pci_release_mem_regions(pdev); + pci_disable_pcie_error_reporting(pdev); out_pci_disable: pci_disable_device(pdev); return err; -- cgit v1.2.3 From 42a2039753a7f758ba5c85cb199fcf10dc2111eb Mon Sep 17 00:00:00 2001 From: Rahul Lakkireddy Date: Fri, 11 Jun 2021 12:17:45 +0530 Subject: cxgb4: fix endianness when flashing boot image Boot images are copied to memory and updated with current underlying device ID before flashing them to adapter. Ensure the updated images are always flashed in Big Endian to allow the firmware to read the new images during boot properly. Fixes: 550883558f17 ("cxgb4: add support to flash boot image") Signed-off-by: Rahul Lakkireddy Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 44 ++++++++++++++++++------------ 1 file changed, 27 insertions(+), 17 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 9428ef1f04a8..1293505025c1 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -3060,16 +3060,19 @@ int t4_read_flash(struct adapter *adapter, unsigned int addr, * @addr: the start address to write * @n: length of data to write in bytes * @data: the data to write + * @byte_oriented: whether to store data as bytes or as words * * Writes up to a page of data (256 bytes) to the serial flash starting * at the given address. All the data must be written to the same page. + * If @byte_oriented is set the write data is stored as byte stream + * (i.e. matches what on disk), otherwise in big-endian. */ static int t4_write_flash(struct adapter *adapter, unsigned int addr, - unsigned int n, const u8 *data) + unsigned int n, const u8 *data, bool byte_oriented) { - int ret; - u32 buf[64]; unsigned int i, c, left, val, offset = addr & 0xff; + u32 buf[64]; + int ret; if (addr >= adapter->params.sf_size || offset + n > SF_PAGE_SIZE) return -EINVAL; @@ -3080,10 +3083,14 @@ static int t4_write_flash(struct adapter *adapter, unsigned int addr, (ret = sf1_write(adapter, 4, 1, 1, val)) != 0) goto unlock; - for (left = n; left; left -= c) { + for (left = n; left; left -= c, data += c) { c = min(left, 4U); - for (val = 0, i = 0; i < c; ++i) - val = (val << 8) + *data++; + for (val = 0, i = 0; i < c; ++i) { + if (byte_oriented) + val = (val << 8) + data[i]; + else + val = (val << 8) + data[c - i - 1]; + } ret = sf1_write(adapter, c, c != left, 1, val); if (ret) @@ -3096,7 +3103,8 @@ static int t4_write_flash(struct adapter *adapter, unsigned int addr, t4_write_reg(adapter, SF_OP_A, 0); /* unlock SF */ /* Read the page to verify the write succeeded */ - ret = t4_read_flash(adapter, addr & ~0xff, ARRAY_SIZE(buf), buf, 1); + ret = t4_read_flash(adapter, addr & ~0xff, ARRAY_SIZE(buf), buf, + byte_oriented); if (ret) return ret; @@ -3692,7 +3700,7 @@ int t4_load_fw(struct adapter *adap, const u8 *fw_data, unsigned int size) */ memcpy(first_page, fw_data, SF_PAGE_SIZE); ((struct fw_hdr *)first_page)->fw_ver = cpu_to_be32(0xffffffff); - ret = t4_write_flash(adap, fw_start, SF_PAGE_SIZE, first_page); + ret = t4_write_flash(adap, fw_start, SF_PAGE_SIZE, first_page, true); if (ret) goto out; @@ -3700,14 +3708,14 @@ int t4_load_fw(struct adapter *adap, const u8 *fw_data, unsigned int size) for (size -= SF_PAGE_SIZE; size; size -= SF_PAGE_SIZE) { addr += SF_PAGE_SIZE; fw_data += SF_PAGE_SIZE; - ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, fw_data); + ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, fw_data, true); if (ret) goto out; } - ret = t4_write_flash(adap, - fw_start + offsetof(struct fw_hdr, fw_ver), - sizeof(hdr->fw_ver), (const u8 *)&hdr->fw_ver); + ret = t4_write_flash(adap, fw_start + offsetof(struct fw_hdr, fw_ver), + sizeof(hdr->fw_ver), (const u8 *)&hdr->fw_ver, + true); out: if (ret) dev_err(adap->pdev_dev, "firmware download failed, error %d\n", @@ -10208,7 +10216,7 @@ int t4_load_cfg(struct adapter *adap, const u8 *cfg_data, unsigned int size) n = size - i; else n = SF_PAGE_SIZE; - ret = t4_write_flash(adap, addr, n, cfg_data); + ret = t4_write_flash(adap, addr, n, cfg_data, true); if (ret) goto out; @@ -10677,13 +10685,14 @@ int t4_load_boot(struct adapter *adap, u8 *boot_data, for (size -= SF_PAGE_SIZE; size; size -= SF_PAGE_SIZE) { addr += SF_PAGE_SIZE; boot_data += SF_PAGE_SIZE; - ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, boot_data); + ret = t4_write_flash(adap, addr, SF_PAGE_SIZE, boot_data, + false); if (ret) goto out; } ret = t4_write_flash(adap, boot_sector, SF_PAGE_SIZE, - (const u8 *)header); + (const u8 *)header, false); out: if (ret) @@ -10758,7 +10767,7 @@ int t4_load_bootcfg(struct adapter *adap, const u8 *cfg_data, unsigned int size) for (i = 0; i < size; i += SF_PAGE_SIZE) { n = min_t(u32, size - i, SF_PAGE_SIZE); - ret = t4_write_flash(adap, addr, n, cfg_data); + ret = t4_write_flash(adap, addr, n, cfg_data, false); if (ret) goto out; @@ -10770,7 +10779,8 @@ int t4_load_bootcfg(struct adapter *adap, const u8 *cfg_data, unsigned int size) for (i = 0; i < npad; i++) { u8 data = 0; - ret = t4_write_flash(adap, cfg_addr + size + i, 1, &data); + ret = t4_write_flash(adap, cfg_addr + size + i, 1, &data, + false); if (ret) goto out; } -- cgit v1.2.3 From f046bd0ae15d8a0bbe57d4647da182420f720c3d Mon Sep 17 00:00:00 2001 From: Rahul Lakkireddy Date: Fri, 11 Jun 2021 12:17:46 +0530 Subject: cxgb4: fix sleep in atomic when flashing PHY firmware Before writing new PHY firmware to on-chip memory, driver queries firmware for current running PHY firmware version, which can result in sleep waiting for reply. So, move spinlock closer to the actual on-chip memory write operation, instead of taking it at the callers. Fixes: 5fff701c838e ("cxgb4: always sync access when flashing PHY firmware") Signed-off-by: Rahul Lakkireddy Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c | 2 -- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 2 -- drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 2 ++ 3 files changed, 2 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 61ea3ec5c3fc..bc2de01d0539 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -1337,9 +1337,7 @@ static int cxgb4_ethtool_flash_phy(struct net_device *netdev, return ret; } - spin_lock_bh(&adap->win0_lock); ret = t4_load_phy_fw(adap, MEMWIN_NIC, NULL, data, size); - spin_unlock_bh(&adap->win0_lock); if (ret) dev_err(adap->pdev_dev, "Failed to load PHY FW\n"); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 1f601de02e70..762113a04dde 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -4424,10 +4424,8 @@ static int adap_init0_phy(struct adapter *adap) /* Load PHY Firmware onto adapter. */ - spin_lock_bh(&adap->win0_lock); ret = t4_load_phy_fw(adap, MEMWIN_NIC, phy_info->phy_fw_version, (u8 *)phyf->data, phyf->size); - spin_unlock_bh(&adap->win0_lock); if (ret < 0) dev_err(adap->pdev_dev, "PHY Firmware transfer error %d\n", -ret); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 1293505025c1..a0555f4d76fc 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -3820,9 +3820,11 @@ int t4_load_phy_fw(struct adapter *adap, int win, /* Copy the supplied PHY Firmware image to the adapter memory location * allocated by the adapter firmware. */ + spin_lock_bh(&adap->win0_lock); ret = t4_memory_rw(adap, win, mtype, maddr, phy_fw_size, (__be32 *)phy_fw_data, T4_MEMORY_WRITE); + spin_unlock_bh(&adap->win0_lock); if (ret) return ret; -- cgit v1.2.3 From 6d297540f75d759489054e8b07932208fc4db2cb Mon Sep 17 00:00:00 2001 From: Rahul Lakkireddy Date: Fri, 11 Jun 2021 12:17:47 +0530 Subject: cxgb4: halt chip before flashing PHY firmware image When using firmware-assisted PHY firmware image write to flash, halt the chip before beginning the flash write operation to allow the running firmware to store the image persistently. Otherwise, the running firmware will only store the PHY image in local on-chip RAM, which will be lost after next reset. Fixes: 4ee339e1e92a ("cxgb4: add support to flash PHY image") Signed-off-by: Rahul Lakkireddy Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index bc2de01d0539..df20485b5744 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -1337,11 +1337,27 @@ static int cxgb4_ethtool_flash_phy(struct net_device *netdev, return ret; } + /* We have to RESET the chip/firmware because we need the + * chip in uninitialized state for loading new PHY image. + * Otherwise, the running firmware will only store the PHY + * image in local RAM which will be lost after next reset. + */ + ret = t4_fw_reset(adap, adap->mbox, PIORSTMODE_F | PIORST_F); + if (ret < 0) { + dev_err(adap->pdev_dev, + "Set FW to RESET for flashing PHY FW failed. ret: %d\n", + ret); + return ret; + } + ret = t4_load_phy_fw(adap, MEMWIN_NIC, NULL, data, size); - if (ret) - dev_err(adap->pdev_dev, "Failed to load PHY FW\n"); + if (ret < 0) { + dev_err(adap->pdev_dev, "Failed to load PHY FW. ret: %d\n", + ret); + return ret; + } - return ret; + return 0; } static int cxgb4_ethtool_flash_fw(struct net_device *netdev, -- cgit v1.2.3 From 1adb20f0d496b2c61e9aa1f4761b8d71f93d258e Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Fri, 11 Jun 2021 15:16:11 +0800 Subject: net: stmmac: dwmac1000: Fix extended MAC address registers definition The register starts from 0x800 is the 16th MAC address register rather than the first one. Fixes: cffb13f4d6fb ("stmmac: extend mac addr reg and fix perfect filering") Signed-off-by: Jisheng Zhang Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac1000.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h index b70d44ac0990..3c73453725f9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h @@ -76,10 +76,10 @@ enum power_event { #define LPI_CTRL_STATUS_TLPIEN 0x00000001 /* Transmit LPI Entry */ /* GMAC HW ADDR regs */ -#define GMAC_ADDR_HIGH(reg) (((reg > 15) ? 0x00000800 : 0x00000040) + \ - (reg * 8)) -#define GMAC_ADDR_LOW(reg) (((reg > 15) ? 0x00000804 : 0x00000044) + \ - (reg * 8)) +#define GMAC_ADDR_HIGH(reg) ((reg > 15) ? 0x00000800 + (reg - 16) * 8 : \ + 0x00000040 + (reg * 8)) +#define GMAC_ADDR_LOW(reg) ((reg > 15) ? 0x00000804 + (reg - 16) * 8 : \ + 0x00000044 + (reg * 8)) #define GMAC_MAX_PERFECT_ADDRESSES 1 #define GMAC_PCS_BASE 0x000000c0 /* PCS register base */ -- cgit v1.2.3 From 994c393bb6886d6d94d628475b274a8cb3fc67a4 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 11 Jun 2021 13:26:00 -0500 Subject: net: qualcomm: rmnet: don't over-count statistics The purpose of the loop using u64_stats_fetch_*_irq() is to ensure statistics on a given CPU are collected atomically. If one of the statistics values gets updated within the begin/retry window, the loop will run again. Currently the statistics totals are updated inside that window. This means that if the loop ever retries, the statistics for the CPU will be counted more than once. Fix this by taking a snapshot of a CPU's statistics inside the protected window, and then updating the counters with the snapshot values after exiting the loop. (Also add a newline at the end of this file...) Fixes: 192c4b5d48f2a ("net: qualcomm: rmnet: Add support for 64 bit stats") Signed-off-by: Alex Elder Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 41fbd2ceeede..ab1e0fcccabb 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -126,24 +126,24 @@ static void rmnet_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *s) { struct rmnet_priv *priv = netdev_priv(dev); - struct rmnet_vnd_stats total_stats; + struct rmnet_vnd_stats total_stats = { }; struct rmnet_pcpu_stats *pcpu_ptr; + struct rmnet_vnd_stats snapshot; unsigned int cpu, start; - memset(&total_stats, 0, sizeof(struct rmnet_vnd_stats)); - for_each_possible_cpu(cpu) { pcpu_ptr = per_cpu_ptr(priv->pcpu_stats, cpu); do { start = u64_stats_fetch_begin_irq(&pcpu_ptr->syncp); - total_stats.rx_pkts += pcpu_ptr->stats.rx_pkts; - total_stats.rx_bytes += pcpu_ptr->stats.rx_bytes; - total_stats.tx_pkts += pcpu_ptr->stats.tx_pkts; - total_stats.tx_bytes += pcpu_ptr->stats.tx_bytes; + snapshot = pcpu_ptr->stats; /* struct assignment */ } while (u64_stats_fetch_retry_irq(&pcpu_ptr->syncp, start)); - total_stats.tx_drops += pcpu_ptr->stats.tx_drops; + total_stats.rx_pkts += snapshot.rx_pkts; + total_stats.rx_bytes += snapshot.rx_bytes; + total_stats.tx_pkts += snapshot.tx_pkts; + total_stats.tx_bytes += snapshot.tx_bytes; + total_stats.tx_drops += snapshot.tx_drops; } s->rx_packets = total_stats.rx_pkts; @@ -354,4 +354,4 @@ int rmnet_vnd_update_dev_mtu(struct rmnet_port *port, } return 0; -} \ No newline at end of file +} -- cgit v1.2.3 From cb3376604a676e0302258b01893911bdd7aa5278 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 12 Jun 2021 14:37:46 +0200 Subject: qlcnic: Fix an error handling path in 'qlcnic_probe()' If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function. Fixes: 451724c821c1 ("qlcnic: aer support") Signed-off-by: Christophe JAILLET Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index 96b947fde646..3beafc60747e 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -2690,6 +2690,7 @@ err_out_free_hw_res: kfree(ahw); err_out_free_res: + pci_disable_pcie_error_reporting(pdev); pci_release_regions(pdev); err_out_disable_pdev: -- cgit v1.2.3 From 49a10c7b176295f8fafb338911cf028e97f65f4d Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 12 Jun 2021 14:53:12 +0200 Subject: netxen_nic: Fix an error handling path in 'netxen_nic_probe()' If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function. Fixes: e87ad5539343 ("netxen: support pci error handlers") Signed-off-by: Christophe JAILLET Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index 7e6bac85495d..344ea1143454 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -1602,6 +1602,8 @@ err_out_free_netdev: free_netdev(netdev); err_out_free_res: + if (NX_IS_REVISION_P3(pdev->revision)) + pci_disable_pcie_error_reporting(pdev); pci_release_regions(pdev); err_out_disable_pdev: -- cgit v1.2.3 From 09427c1915f754ebe7d3d8e54e79bbee48afe916 Mon Sep 17 00:00:00 2001 From: Rahul Lakkireddy Date: Sat, 12 Jun 2021 19:20:44 +0530 Subject: cxgb4: fix wrong ethtool n-tuple rule lookup The TID returned during successful filter creation is relative to the region in which the filter is created. Using it directly always returns Hi Prio/Normal filter region's entry for the first couple of entries, even though the rule is actually inserted in Hash region. Fix by analyzing in which region the filter has been inserted and save the absolute TID to be used for lookup later. Fixes: db43b30cd89c ("cxgb4: add ethtool n-tuple filter deletion") Signed-off-by: Rahul Lakkireddy Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c | 24 ++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index df20485b5744..83ed10ac8660 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -1624,16 +1624,14 @@ static struct filter_entry *cxgb4_get_filter_entry(struct adapter *adap, u32 ftid) { struct tid_info *t = &adap->tids; - struct filter_entry *f; - if (ftid < t->nhpftids) - f = &adap->tids.hpftid_tab[ftid]; - else if (ftid < t->nftids) - f = &adap->tids.ftid_tab[ftid - t->nhpftids]; - else - f = lookup_tid(&adap->tids, ftid); + if (ftid >= t->hpftid_base && ftid < t->hpftid_base + t->nhpftids) + return &t->hpftid_tab[ftid - t->hpftid_base]; + + if (ftid >= t->ftid_base && ftid < t->ftid_base + t->nftids) + return &t->ftid_tab[ftid - t->ftid_base]; - return f; + return lookup_tid(t, ftid); } static void cxgb4_fill_filter_rule(struct ethtool_rx_flow_spec *fs, @@ -1840,6 +1838,11 @@ static int cxgb4_ntuple_del_filter(struct net_device *dev, filter_id = filter_info->loc_array[cmd->fs.location]; f = cxgb4_get_filter_entry(adapter, filter_id); + if (f->fs.prio) + filter_id -= adapter->tids.hpftid_base; + else if (!f->fs.hash) + filter_id -= (adapter->tids.ftid_base - adapter->tids.nhpftids); + ret = cxgb4_flow_rule_destroy(dev, f->fs.tc_prio, &f->fs, filter_id); if (ret) goto err; @@ -1899,6 +1902,11 @@ static int cxgb4_ntuple_set_filter(struct net_device *netdev, filter_info = &adapter->ethtool_filters->port[pi->port_id]; + if (fs.prio) + tid += adapter->tids.hpftid_base; + else if (!fs.hash) + tid += (adapter->tids.ftid_base - adapter->tids.nhpftids); + filter_info->loc_array[cmd->fs.location] = tid; set_bit(cmd->fs.location, filter_info->bmap); filter_info->in_use++; -- cgit v1.2.3 From 7ea6cd16f1599c1eac6018751eadbc5fc736b99a Mon Sep 17 00:00:00 2001 From: Aleksander Jan Bajkowski Date: Tue, 15 Jun 2021 22:42:57 +0200 Subject: lantiq: net: fix duplicated skb in rx descriptor ring The previous commit didn't fix the bug properly. By mistake, it replaces the pointer of the next skb in the descriptor ring instead of the current one. As a result, the two descriptors are assigned the same SKB. The error is seen during the iperf test when skb_put tries to insert a second packet and exceeds the available buffer. Fixes: c7718ee96dbc ("net: lantiq: fix memory corruption in RX ring ") Signed-off-by: Aleksander Jan Bajkowski Signed-off-by: David S. Miller --- drivers/net/ethernet/lantiq_xrx200.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c index 0e10d8aeffe1..21ef2f128070 100644 --- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -154,6 +154,7 @@ static int xrx200_close(struct net_device *net_dev) static int xrx200_alloc_skb(struct xrx200_chan *ch) { + struct sk_buff *skb = ch->skb[ch->dma.desc]; dma_addr_t mapping; int ret = 0; @@ -168,6 +169,7 @@ static int xrx200_alloc_skb(struct xrx200_chan *ch) XRX200_DMA_DATA_LEN, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(ch->priv->dev, mapping))) { dev_kfree_skb_any(ch->skb[ch->dma.desc]); + ch->skb[ch->dma.desc] = skb; ret = -ENOMEM; goto skip; } @@ -198,7 +200,6 @@ static int xrx200_hw_receive(struct xrx200_chan *ch) ch->dma.desc %= LTQ_DESC_NUM; if (ret) { - ch->skb[ch->dma.desc] = skb; net_dev->stats.rx_dropped++; netdev_err(net_dev, "failed to allocate new rx buffer\n"); return ret; -- cgit v1.2.3 From 8f269102baf788aecfcbbc6313b6bceb54c9b990 Mon Sep 17 00:00:00 2001 From: Joakim Zhang Date: Wed, 16 Jun 2021 17:10:24 +0800 Subject: net: stmmac: disable clocks in stmmac_remove_config_dt() Platform drivers may call stmmac_probe_config_dt() to parse dt, could call stmmac_remove_config_dt() in error handing after dt parsed, so need disable clocks in stmmac_remove_config_dt(). Go through all platforms drivers which use stmmac_probe_config_dt(), none of them disable clocks manually, so it's safe to disable them in stmmac_remove_config_dt(). Fixes: commit d2ed0a7755fe ("net: ethernet: stmmac: fix of-node and fixed-link-phydev leaks") Signed-off-by: Joakim Zhang Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 1e17a23d9118..a696ada013eb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -622,6 +622,8 @@ error_pclk_get: void stmmac_remove_config_dt(struct platform_device *pdev, struct plat_stmmacenet_data *plat) { + clk_disable_unprepare(plat->stmmac_clk); + clk_disable_unprepare(plat->pclk); of_node_put(plat->phy_node); of_node_put(plat->mdio_node); } -- cgit v1.2.3 From cb3cefe3f3f8af27c6076ef7d1f00350f502055d Mon Sep 17 00:00:00 2001 From: Fugang Duan Date: Wed, 16 Jun 2021 17:14:25 +0800 Subject: net: fec_ptp: add clock rate zero check Add clock rate zero check to fix coverity issue of "divide by 0". Fixes: commit 85bd1798b24a ("net: fec: fix spin_lock dead lock") Signed-off-by: Fugang Duan Signed-off-by: Joakim Zhang Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fec_ptp.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 1753807cbf97..7326a0612823 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -604,6 +604,10 @@ void fec_ptp_init(struct platform_device *pdev, int irq_idx) fep->ptp_caps.enable = fec_ptp_enable; fep->cycle_speed = clk_get_rate(fep->clk_ptp); + if (!fep->cycle_speed) { + fep->cycle_speed = NSEC_PER_SEC; + dev_err(&fep->pdev->dev, "clk_ptp clock rate is zero\n"); + } fep->ptp_inc = NSEC_PER_SEC / fep->cycle_speed; spin_lock_init(&fep->tmreg_lock); -- cgit v1.2.3 From d23765646e71b43ed2b809930411ba5c0aadee7b Mon Sep 17 00:00:00 2001 From: Joakim Zhang Date: Wed, 16 Jun 2021 17:14:26 +0800 Subject: net: fec_ptp: fix issue caused by refactor the fec_devtype Commit da722186f654 ("net: fec: set GPR bit on suspend by DT configuration.") refactor the fec_devtype, need adjust ptp driver accordingly. Fixes: da722186f654 ("net: fec: set GPR bit on suspend by DT configuration.") Signed-off-by: Joakim Zhang Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fec_ptp.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 7326a0612823..d71eac7e1924 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -215,15 +215,13 @@ static u64 fec_ptp_read(const struct cyclecounter *cc) { struct fec_enet_private *fep = container_of(cc, struct fec_enet_private, cc); - const struct platform_device_id *id_entry = - platform_get_device_id(fep->pdev); u32 tempval; tempval = readl(fep->hwp + FEC_ATIME_CTRL); tempval |= FEC_T_CTRL_CAPTURE; writel(tempval, fep->hwp + FEC_ATIME_CTRL); - if (id_entry->driver_data & FEC_QUIRK_BUG_CAPTURE) + if (fep->quirks & FEC_QUIRK_BUG_CAPTURE) udelay(1); return readl(fep->hwp + FEC_ATIME); -- cgit v1.2.3 From 224004fbb033600715dbd626bceec10bfd9c58bc Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 16 Jun 2021 12:53:33 -0700 Subject: sh_eth: Avoid memcpy() over-reading of ETH_SS_STATS In preparation for FORTIFY_SOURCE performing compile-time and run-time field bounds checking for memcpy(), memmove(), and memset(), avoid intentionally reading across neighboring array fields. The memcpy() is copying the entire structure, not just the first array. Adjust the source argument so the compiler can do appropriate bounds checking. Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/renesas/sh_eth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index c5b154868c1f..713d3629b4c1 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -2287,7 +2287,7 @@ static void sh_eth_get_strings(struct net_device *ndev, u32 stringset, u8 *data) { switch (stringset) { case ETH_SS_STATS: - memcpy(data, *sh_eth_gstrings_stats, + memcpy(data, sh_eth_gstrings_stats, sizeof(sh_eth_gstrings_stats)); break; } -- cgit v1.2.3 From da5ac772cfe2a03058b0accfac03fad60c46c24d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 16 Jun 2021 12:53:59 -0700 Subject: r8169: Avoid memcpy() over-reading of ETH_SS_STATS In preparation for FORTIFY_SOURCE performing compile-time and run-time field bounds checking for memcpy(), memmove(), and memset(), avoid intentionally reading across neighboring array fields. The memcpy() is copying the entire structure, not just the first array. Adjust the source argument so the compiler can do appropriate bounds checking. Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/r8169_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 2c89cde7da1e..2ee72dc431cd 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -1671,7 +1671,7 @@ static void rtl8169_get_strings(struct net_device *dev, u32 stringset, u8 *data) { switch(stringset) { case ETH_SS_STATS: - memcpy(data, *rtl8169_gstrings, sizeof(rtl8169_gstrings)); + memcpy(data, rtl8169_gstrings, sizeof(rtl8169_gstrings)); break; } } -- cgit v1.2.3 From 94a4b8414d3e91104873007b659252f855ee344a Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 8 Mar 2021 15:41:55 +0200 Subject: net/mlx5: Fix error path for set HCA defaults In the case of the failure to execute mlx5_core_set_hca_defaults(), we used wrong goto label to execute error unwind flow. Fixes: 5bef709d76a2 ("net/mlx5: Enable host PF HCA after eswitch is initialized") Reviewed-by: Saeed Mahameed Reviewed-by: Moshe Shemesh Signed-off-by: Leon Romanovsky Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index a1d67bd7fb43..0d0f63a27aba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1161,7 +1161,7 @@ static int mlx5_load(struct mlx5_core_dev *dev) err = mlx5_core_set_hca_defaults(dev); if (err) { mlx5_core_err(dev, "Failed to set hca defaults\n"); - goto err_sriov; + goto err_set_hca; } mlx5_vhca_event_start(dev); @@ -1194,6 +1194,7 @@ err_ec: mlx5_sf_hw_table_destroy(dev); err_vhca: mlx5_vhca_event_stop(dev); +err_set_hca: mlx5_cleanup_fs(dev); err_fs: mlx5_accel_tls_cleanup(dev); -- cgit v1.2.3 From 2058cc9c8041fde9c0bdd8e868c72b137cff8563 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sun, 21 Mar 2021 19:57:14 +0200 Subject: net/mlx5: Check that driver was probed prior attaching the device The device can be requested to be attached despite being not probed. This situation is possible if devlink reload races with module removal, and the following kernel panic is an outcome of such race. mlx5_core 0000:00:09.0: firmware version: 4.7.9999 mlx5_core 0000:00:09.0: 0.000 Gb/s available PCIe bandwidth (8.0 GT/s PCIe x255 link) BUG: unable to handle page fault for address: fffffffffffffff0 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 3218067 P4D 3218067 PUD 321a067 PMD 0 Oops: 0000 [#1] SMP KASAN NOPTI CPU: 7 PID: 250 Comm: devlink Not tainted 5.12.0-rc2+ #2836 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:mlx5_attach_device+0x80/0x280 [mlx5_core] Code: f8 48 c1 e8 03 42 80 3c 38 00 0f 85 80 01 00 00 48 8b 45 68 48 8d 78 f0 48 89 fe 48 c1 ee 03 42 80 3c 3e 00 0f 85 70 01 00 00 <48> 8b 40 f0 48 85 c0 74 0d 48 89 ef ff d0 85 c0 0f 85 84 05 0e 00 RSP: 0018:ffff8880129675f0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000001 RCX: ffffffff827407f1 RDX: 1ffff110011336cf RSI: 1ffffffffffffffe RDI: fffffffffffffff0 RBP: ffff888008e0c000 R08: 0000000000000008 R09: ffffffffa0662ee7 R10: fffffbfff40cc5dc R11: 0000000000000000 R12: ffff88800ea002e0 R13: ffffed1001d459f7 R14: ffffffffa05ef4f8 R15: dffffc0000000000 FS: 00007f51dfeaf740(0000) GS:ffff88806d5c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffffffffffff0 CR3: 000000000bc82006 CR4: 0000000000370ea0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: mlx5_load_one+0x117/0x1d0 [mlx5_core] devlink_reload+0x2d5/0x520 ? devlink_remote_reload_actions_performed+0x30/0x30 ? mutex_trylock+0x24b/0x2d0 ? devlink_nl_cmd_reload+0x62b/0x1070 devlink_nl_cmd_reload+0x66d/0x1070 ? devlink_reload+0x520/0x520 ? devlink_nl_pre_doit+0x64/0x4d0 genl_family_rcv_msg_doit+0x1e9/0x2f0 ? mutex_lock_io_nested+0x1130/0x1130 ? genl_family_rcv_msg_attrs_parse.constprop.0+0x240/0x240 ? security_capable+0x51/0x90 genl_rcv_msg+0x27f/0x4a0 ? genl_get_cmd+0x3c0/0x3c0 ? lock_acquire+0x1a9/0x6d0 ? devlink_reload+0x520/0x520 ? lock_release+0x6c0/0x6c0 netlink_rcv_skb+0x11d/0x340 ? genl_get_cmd+0x3c0/0x3c0 ? netlink_ack+0x9f0/0x9f0 ? lock_release+0x1f9/0x6c0 genl_rcv+0x24/0x40 netlink_unicast+0x433/0x700 ? netlink_attachskb+0x730/0x730 ? _copy_from_iter_full+0x178/0x650 ? __alloc_skb+0x113/0x2b0 netlink_sendmsg+0x6f1/0xbd0 ? netlink_unicast+0x700/0x700 ? netlink_unicast+0x700/0x700 sock_sendmsg+0xb0/0xe0 __sys_sendto+0x193/0x240 ? __x64_sys_getpeername+0xb0/0xb0 ? copy_page_range+0x2300/0x2300 ? __up_read+0x1a1/0x7b0 ? do_user_addr_fault+0x219/0xdc0 __x64_sys_sendto+0xdd/0x1b0 ? syscall_enter_from_user_mode+0x1d/0x50 do_syscall_64+0x2d/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f51dffb514a Code: d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 f3 0f 1e fa 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 15 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 76 c3 0f 1f 44 00 00 55 48 83 ec 30 44 89 4c RSP: 002b:00007ffcaef22e78 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f51dffb514a RDX: 0000000000000030 RSI: 000055750daf2440 RDI: 0000000000000003 RBP: 000055750daf2410 R08: 00007f51e0081200 R09: 000000000000000c R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 Modules linked in: mlx5_core(-) ptp pps_core ib_ipoib rdma_ucm rdma_cm iw_cm ib_cm ib_umad ib_uverbs ib_core [last unloaded: mlx5_ib] CR2: fffffffffffffff0 ---[ end trace 7789831bfe74fa42 ]--- Fixes: a925b5e309c9 ("net/mlx5: Register mlx5 devices to auxiliary virtual bus") Signed-off-by: Leon Romanovsky Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/dev.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index a9166cd85013..8de118adfb54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -320,6 +320,16 @@ int mlx5_attach_device(struct mlx5_core_dev *dev) } } else { adev = &priv->adev[i]->adev; + + /* Pay attention that this is not PCI driver that + * mlx5_core_dev is connected, but auxiliary driver. + * + * Here we can race of module unload with devlink + * reload, but we don't need to take extra lock because + * we are holding global mlx5_intf_mutex. + */ + if (!adev->dev.driver) + continue; adrv = to_auxiliary_drv(adev->dev.driver); if (adrv->resume) @@ -350,6 +360,10 @@ void mlx5_detach_device(struct mlx5_core_dev *dev) continue; adev = &priv->adev[i]->adev; + /* Auxiliary driver was unbind manually through sysfs */ + if (!adev->dev.driver) + goto skip_suspend; + adrv = to_auxiliary_drv(adev->dev.driver); if (adrv->suspend) { @@ -357,6 +371,7 @@ void mlx5_detach_device(struct mlx5_core_dev *dev) continue; } +skip_suspend: del_adev(&priv->adev[i]->adev); priv->adev[i] = NULL; } -- cgit v1.2.3 From bbc8222dc49db8d49add0f27bcac33f4b92193dc Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 8 Jun 2021 19:14:08 +0300 Subject: net/mlx5: E-Switch, Read PF mac address External controller PF's MAC address is not read from the device during vport setup. Fail to read this results in showing all zeros to user while the factory programmed MAC is a valid value. $ devlink port show eth1 -jp { "port": { "pci/0000:03:00.0/196608": { "type": "eth", "netdev": "eth1", "flavour": "pcipf", "controller": 1, "pfnum": 0, "splittable": false, "function": { "hw_addr": "00:00:00:00:00:00" } } } } Hence, read it when enabling a vport. After the fix, $ devlink port show eth1 -jp { "port": { "pci/0000:03:00.0/196608": { "type": "eth", "netdev": "eth1", "flavour": "pcipf", "controller": 1, "pfnum": 0, "splittable": false, "function": { "hw_addr": "98:03:9b:a0:60:11" } } } } Fixes: f099fde16db3 ("net/mlx5: E-switch, Support querying port function mac address") Signed-off-by: Bodong Wang Signed-off-by: Parav Pandit Reviewed-by: Alaa Hleihel Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index b88705a3a1a8..97e6cb6f13c1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1054,6 +1054,12 @@ int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, u16 vport_num, goto err_vhca_mapping; } + /* External controller host PF has factory programmed MAC. + * Read it from the device. + */ + if (mlx5_core_is_ecpf(esw->dev) && vport_num == MLX5_VPORT_PF) + mlx5_query_nic_vport_mac_address(esw->dev, vport_num, true, vport->info.mac); + esw_vport_change_handle_locked(vport); esw->enabled_vports++; -- cgit v1.2.3 From ca36fc4d77b35b8d142cf1ed0eae5ec2e071dc3c Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 8 Jun 2021 19:03:24 +0300 Subject: net/mlx5: E-Switch, Allow setting GUID for host PF vport E-switch should be able to set the GUID of host PF vport. Currently it returns an error. This results in below error when user attempts to configure MAC address of the PF of an external controller. $ devlink port function set pci/0000:03:00.0/196608 \ hw_addr 00:00:00:11:22:33 mlx5_core 0000:03:00.0: mlx5_esw_set_vport_mac_locked:1876:(pid 6715):\ "Failed to set vport 0 node guid, err = -22. RDMA_CM will not function properly for this VF." Check for zero vport is no longer needed. Fixes: 330077d14de1 ("net/mlx5: E-switch, Supporting setting devlink port function mac address") Signed-off-by: Yuval Avnery Signed-off-by: Parav Pandit Reviewed-by: Bodong Wang Reviewed-by: Alaa Hleihel Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/vport.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 457ad42eaa2a..4c1440a95ad7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -465,8 +465,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev, void *in; int err; - if (!vport) - return -EINVAL; if (!MLX5_CAP_GEN(mdev, vport_group_manager)) return -EACCES; -- cgit v1.2.3 From c7d6c19b3bde66d7aebbe93e0f9e6d9ff57fc3fa Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Thu, 10 Jun 2021 18:39:53 +0300 Subject: net/mlx5: SF_DEV, remove SF device on invalid state When auxiliary bus autoprobe is disabled and SF is in ACTIVE state, on SF port deletion it transitions from ACTIVE->ALLOCATED->INVALID. When VHCA event handler queries the state, it is already transition to INVALID state. In this scenario, event handler missed to delete the SF device. Fix it by deleting the SF when SF state is INVALID. Fixes: 90d010b8634b ("net/mlx5: SF, Add auxiliary device support") Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c index 6a0c6f965ad1..fa0288afc0dd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c @@ -163,6 +163,7 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_ sf_index = event->function_id - base_id; sf_dev = xa_load(&table->devices, sf_index); switch (event->new_vhca_state) { + case MLX5_VHCA_STATE_INVALID: case MLX5_VHCA_STATE_ALLOCATED: if (sf_dev) mlx5_sf_dev_del(table->dev, sf_dev, sf_index); -- cgit v1.2.3 From 65fb7d109abe3a1a9f1c2d3ba7e1249bc978d5f0 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Tue, 1 Jun 2021 18:10:06 +0300 Subject: net/mlx5: DR, Fix STEv1 incorrect L3 decapsulation padding Decapsulation L3 on small inner packets which are less than 64 Bytes was done incorrectly. In small packets there is an extra padding added in L2 which should not be included in L3 length. The issue was that after decapL3 the extra L2 padding caused an update on the L3 length. To avoid this issue the new header is pushed to the beginning of the packet (offset 0) which should not cause a HW reparse and update the L3 length. Fixes: c349b4137cfd ("net/mlx5: DR, Add STEv1 modify header logic") Reviewed-by: Erez Shitrit Reviewed-by: Yevgeny Kliteynik Signed-off-by: Alex Vesker Signed-off-by: Saeed Mahameed --- .../mellanox/mlx5/core/steering/dr_ste_v1.c | 26 +++++++++++++--------- 1 file changed, 16 insertions(+), 10 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c index 054c2e2b6554..7466f016375c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c @@ -694,7 +694,11 @@ static int dr_ste_v1_set_action_decap_l3_list(void *data, if (hw_action_sz / DR_STE_ACTION_DOUBLE_SZ < DR_STE_DECAP_L3_ACTION_NUM) return -EINVAL; - memcpy(padded_data, data, data_sz); + inline_data_sz = + MLX5_FLD_SZ_BYTES(ste_double_action_insert_with_inline_v1, inline_data); + + /* Add an alignment padding */ + memcpy(padded_data + data_sz % inline_data_sz, data, data_sz); /* Remove L2L3 outer headers */ MLX5_SET(ste_single_action_remove_header_v1, hw_action, action_id, @@ -706,32 +710,34 @@ static int dr_ste_v1_set_action_decap_l3_list(void *data, hw_action += DR_STE_ACTION_DOUBLE_SZ; used_actions++; /* Remove and NOP are a single double action */ - inline_data_sz = - MLX5_FLD_SZ_BYTES(ste_double_action_insert_with_inline_v1, inline_data); + /* Point to the last dword of the header */ + data_ptr += (data_sz / inline_data_sz) * inline_data_sz; - /* Add the new header inline + 2 extra bytes */ + /* Add the new header using inline action 4Byte at a time, the header + * is added in reversed order to the beginning of the packet to avoid + * incorrect parsing by the HW. Since header is 14B or 18B an extra + * two bytes are padded and later removed. + */ for (i = 0; i < data_sz / inline_data_sz + 1; i++) { void *addr_inline; MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, action_id, DR_STE_V1_ACTION_ID_INSERT_INLINE); /* The hardware expects here offset to words (2 bytes) */ - MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, start_offset, - i * 2); + MLX5_SET(ste_double_action_insert_with_inline_v1, hw_action, start_offset, 0); /* Copy bytes one by one to avoid endianness problem */ addr_inline = MLX5_ADDR_OF(ste_double_action_insert_with_inline_v1, hw_action, inline_data); - memcpy(addr_inline, data_ptr, inline_data_sz); + memcpy(addr_inline, data_ptr - i * inline_data_sz, inline_data_sz); hw_action += DR_STE_ACTION_DOUBLE_SZ; - data_ptr += inline_data_sz; used_actions++; } - /* Remove 2 extra bytes */ + /* Remove first 2 extra bytes */ MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, action_id, DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE); - MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, start_offset, data_sz / 2); + MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, start_offset, 0); /* The hardware expects here size in words (2 bytes) */ MLX5_SET(ste_single_action_remove_header_size_v1, hw_action, remove_size, 1); used_actions++; -- cgit v1.2.3 From a5ae8fc9058e37437c8c1f82b3d412b4abd1b9e6 Mon Sep 17 00:00:00 2001 From: Dmytro Linkin Date: Fri, 14 May 2021 11:14:19 +0300 Subject: net/mlx5e: Don't create devices during unload flow Running devlink reload command for port in switchdev mode cause resources to corrupt: driver can't release allocated EQ and reclaim memory pages, because "rdma" auxiliary device had add CQs which blocks EQ from deletion. Erroneous sequence happens during reload-down phase, and is following: 1. detach device - suspends auxiliary devices which support it, destroys others. During this step "eth-rep" and "rdma-rep" are destroyed, "eth" - suspended. 2. disable SRIOV - moves device to legacy mode; as part of disablement - rescans drivers. This step adds "rdma" auxiliary device. 3. destroy EQ table - . Driver shouldn't create any device during unload flows. To handle that implement MLX5_PRIV_FLAGS_DETACH flag, set it on device detach and unset on device attach. If flag is set do no-op on drivers rescan. Fixes: a925b5e309c9 ("net/mlx5: Register mlx5 devices to auxiliary virtual bus") Signed-off-by: Dmytro Linkin Reviewed-by: Leon Romanovsky Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/dev.c | 4 ++++ include/linux/mlx5/driver.h | 4 ++++ 2 files changed, 8 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index 8de118adfb54..ceebfc20f65e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -303,6 +303,7 @@ int mlx5_attach_device(struct mlx5_core_dev *dev) int ret = 0, i; mutex_lock(&mlx5_intf_mutex); + priv->flags &= ~MLX5_PRIV_FLAGS_DETACH; for (i = 0; i < ARRAY_SIZE(mlx5_adev_devices); i++) { if (!priv->adev[i]) { bool is_supported = false; @@ -375,6 +376,7 @@ skip_suspend: del_adev(&priv->adev[i]->adev); priv->adev[i] = NULL; } + priv->flags |= MLX5_PRIV_FLAGS_DETACH; mutex_unlock(&mlx5_intf_mutex); } @@ -463,6 +465,8 @@ int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev) struct mlx5_priv *priv = &dev->priv; lockdep_assert_held(&mlx5_intf_mutex); + if (priv->flags & MLX5_PRIV_FLAGS_DETACH) + return 0; delete_drivers(dev); if (priv->flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 020a8f7fdbdd..f8902bcd91e2 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -542,6 +542,10 @@ struct mlx5_core_roce { enum { MLX5_PRIV_FLAGS_DISABLE_IB_ADEV = 1 << 0, MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV = 1 << 1, + /* Set during device detach to block any further devices + * creation/deletion on drivers rescan. Unset during device attach. + */ + MLX5_PRIV_FLAGS_DETACH = 1 << 2, }; struct mlx5_adev { -- cgit v1.2.3 From 0232fc2ddcf4ffe01069fd1aa07922652120f44a Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Thu, 10 Jun 2021 14:20:28 +0300 Subject: net/mlx5: Reset mkey index on creation Reset only the index part of the mkey and keep the variant part. On devlink reload, driver recreates mkeys, so the mkey index may change. Trying to preserve the variant part of the mkey, driver mistakenly merged the mkey index with current value. In case of a devlink reload, current value of index part is dirty, so the index may be corrupted. Fixes: 54c62e13ad76 ("{IB,net}/mlx5: Setup mkey variant before mr create command invocation") Signed-off-by: Aya Levin Signed-off-by: Amir Tzin Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/mr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index 50af84e76fb6..174f71ed5280 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -54,7 +54,7 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index); mkey->iova = MLX5_GET64(mkc, mkc, start_addr); mkey->size = MLX5_GET64(mkc, mkc, len); - mkey->key |= mlx5_idx_to_mkey(mkey_index); + mkey->key = (u32)mlx5_mkey_variant(mkey->key) | mlx5_idx_to_mkey(mkey_index); mkey->pd = MLX5_GET(mkc, mkc, pd); init_waitqueue_head(&mkey->wait); -- cgit v1.2.3 From c19c8c0e666f9259e2fc4d2fa4b9ff8e3b40ee5d Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 16 Jun 2021 20:43:37 +0200 Subject: be2net: Fix an error handling path in 'be_probe()' If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function. Fixes: d6b6d9877878 ("be2net: use PCIe AER capability") Signed-off-by: Christophe JAILLET Acked-by: Somnath Kotur Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_main.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index b6eba29d8e99..7968568bbe21 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -5897,6 +5897,7 @@ drv_cleanup: unmap_bars: be_unmap_pci_bars(adapter); free_netdev: + pci_disable_pcie_error_reporting(pdev); free_netdev(netdev); rel_reg: pci_release_regions(pdev); -- cgit v1.2.3 From 1c200f832e14420fa770193f9871f4ce2df00d07 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 17 Jun 2021 10:09:53 -0700 Subject: net: qed: Fix memcpy() overflow of qed_dcbx_params() The source (&dcbx_info->operational.params) and dest (&p_hwfn->p_dcbx_info->set.config.params) are both struct qed_dcbx_params (560 bytes), not struct qed_dcbx_admin_params (564 bytes), which is used as the memcpy() size. However it seems that struct qed_dcbx_operational_params (dcbx_info->operational)'s layout matches struct qed_dcbx_admin_params (p_hwfn->p_dcbx_info->set.config)'s 4 byte difference (3 padding, 1 byte for "valid"). On the assumption that the size is wrong (rather than the source structure type), adjust the memcpy() size argument to be 4 bytes smaller and add a BUILD_BUG_ON() to validate any changes to the structure sizes. Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_dcbx.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index 17d5b649eb36..e81dd34a3cac 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -1266,9 +1266,11 @@ int qed_dcbx_get_config_params(struct qed_hwfn *p_hwfn, p_hwfn->p_dcbx_info->set.ver_num |= DCBX_CONFIG_VERSION_STATIC; p_hwfn->p_dcbx_info->set.enabled = dcbx_info->operational.enabled; + BUILD_BUG_ON(sizeof(dcbx_info->operational.params) != + sizeof(p_hwfn->p_dcbx_info->set.config.params)); memcpy(&p_hwfn->p_dcbx_info->set.config.params, &dcbx_info->operational.params, - sizeof(struct qed_dcbx_admin_params)); + sizeof(p_hwfn->p_dcbx_info->set.config.params)); p_hwfn->p_dcbx_info->set.config.valid = true; memcpy(params, &p_hwfn->p_dcbx_info->set, sizeof(struct qed_dcbx_set)); -- cgit v1.2.3 From 39eb028183bc7378bb6187067e20bf6d8c836407 Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Fri, 18 Jun 2021 11:29:48 +0200 Subject: cxgb4: fix wrong shift. While fixing coverity warning, commit dd2c79677375 introduced typo in shift value. Fix that. Signed-off-by: Pavel Machek (CIP) Fixes: dd2c79677375 ("cxgb4: Fix unintentional sign extension issues") Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index 22c9ac922eba..6260b3bebd2b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -198,7 +198,7 @@ static void set_nat_params(struct adapter *adap, struct filter_entry *f, WORD_MASK, f->fs.nat_lip[3] | f->fs.nat_lip[2] << 8 | f->fs.nat_lip[1] << 16 | - (u64)f->fs.nat_lip[0] << 25, 1); + (u64)f->fs.nat_lip[0] << 24, 1); } } -- cgit v1.2.3 From 0afd6a4e8028cc487c240b6cfe04094e45a306e4 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Fri, 18 Jun 2021 02:07:25 -0400 Subject: bnxt_en: Rediscover PHY capabilities after firmware reset There is a missing bnxt_probe_phy() call in bnxt_fw_init_one() to rediscover the PHY capabilities after a firmware reset. This can cause some PHY related functionalities to fail after a firmware reset. For example, in multi-host, the ability for any host to configure the PHY settings may be lost after a firmware reset. Fixes: ec5d31e3c15d ("bnxt_en: Handle firmware reset status during IF_UP.") Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index fcc729d52b17..3685db6dc93d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11750,6 +11750,8 @@ static void bnxt_fw_init_one_p3(struct bnxt *bp) bnxt_hwrm_coal_params_qcaps(bp); } +static int bnxt_probe_phy(struct bnxt *bp, bool fw_dflt); + static int bnxt_fw_init_one(struct bnxt *bp) { int rc; @@ -11764,6 +11766,9 @@ static int bnxt_fw_init_one(struct bnxt *bp) netdev_err(bp->dev, "Firmware init phase 2 failed\n"); return rc; } + rc = bnxt_probe_phy(bp, false); + if (rc) + return rc; rc = bnxt_approve_mac(bp, bp->dev->dev_addr, false); if (rc) return rc; -- cgit v1.2.3 From c12e1643d2738bcd4e26252ce531878841dd3f38 Mon Sep 17 00:00:00 2001 From: Rukhsana Ansari Date: Fri, 18 Jun 2021 02:07:26 -0400 Subject: bnxt_en: Fix TQM fastpath ring backing store computation TQM fastpath ring needs to be sized to store both the requester and responder side of RoCE QPs in TQM for supporting bi-directional tests. Fix bnxt_alloc_ctx_mem() to multiply the RoCE QPs by a factor of 2 when computing the number of entries for TQM fastpath ring. This fixes an RX pipeline stall issue when running bi-directional max RoCE QP tests. Fixes: c7dd7ab4b204 ("bnxt_en: Improve TQM ring context memory sizing formulas.") Signed-off-by: Rukhsana Ansari 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/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 3685db6dc93d..c913cb1f2a72 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -7308,7 +7308,7 @@ skip_rdma: entries_sp = ctx->vnic_max_vnic_entries + ctx->qp_max_l2_entries + 2 * (extra_qps + ctx->qp_min_qp1_entries) + min; entries_sp = roundup(entries_sp, ctx->tqm_entries_multiple); - entries = ctx->qp_max_l2_entries + extra_qps + ctx->qp_min_qp1_entries; + entries = ctx->qp_max_l2_entries + 2 * (extra_qps + ctx->qp_min_qp1_entries); entries = roundup(entries, ctx->tqm_entries_multiple); entries = clamp_t(u32, entries, min, ctx->tqm_max_entries_per_ring); for (i = 0; i < ctx->tqm_fp_rings_count + 1; i++) { -- cgit v1.2.3 From 03400aaa69f916a376e11526cf591901a96a3a5c Mon Sep 17 00:00:00 2001 From: Somnath Kotur Date: Fri, 18 Jun 2021 02:07:27 -0400 Subject: bnxt_en: Call bnxt_ethtool_free() in bnxt_init_one() error path bnxt_ethtool_init() may have allocated some memory and we need to call bnxt_ethtool_free() to properly unwind if bnxt_init_one() fails. Fixes: 7c3809181468 ("bnxt_en: Refactor bnxt_init_one() and turn on TPA support on 57500 chips.") Signed-off-by: Somnath Kotur Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index c913cb1f2a72..aef3fccc27a9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -13160,6 +13160,7 @@ init_err_pci_clean: bnxt_hwrm_func_drv_unrgtr(bp); bnxt_free_hwrm_short_cmd_req(bp); bnxt_free_hwrm_resources(bp); + bnxt_ethtool_free(bp); kfree(bp->fw_health); bp->fw_health = NULL; bnxt_cleanup_pci(bp); -- cgit v1.2.3 From 6aa32217a9a446275440ee8724b1ecaf1838df47 Mon Sep 17 00:00:00 2001 From: Esben Haabendal Date: Fri, 18 Jun 2021 12:52:23 +0200 Subject: net: ll_temac: Make sure to free skb when it is completely used With the skb pointer piggy-backed on the TX BD, we have a simple and efficient way to free the skb buffer when the frame has been transmitted. But in order to avoid freeing the skb while there are still fragments from the skb in use, we need to piggy-back on the TX BD of the skb, not the first. Without this, we are doing use-after-free on the DMA side, when the first BD of a multi TX BD packet is seen as completed in xmit_done, and the remaining BDs are still being processed. Cc: stable@vger.kernel.org # v5.4+ Signed-off-by: Esben Haabendal Signed-off-by: David S. Miller --- drivers/net/ethernet/xilinx/ll_temac_main.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index a1f5f07f4ca9..e82f162cd80c 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -876,7 +876,6 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_OK; } cur_p->phys = cpu_to_be32(skb_dma_addr); - ptr_to_txbd((void *)skb, cur_p); for (ii = 0; ii < num_frag; ii++) { if (++lp->tx_bd_tail >= lp->tx_bd_num) @@ -915,6 +914,11 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) } cur_p->app0 |= cpu_to_be32(STS_CTRL_APP0_EOP); + /* Mark last fragment with skb address, so it can be consumed + * in temac_start_xmit_done() + */ + ptr_to_txbd((void *)skb, cur_p); + tail_p = lp->tx_bd_p + sizeof(*lp->tx_bd_v) * lp->tx_bd_tail; lp->tx_bd_tail++; if (lp->tx_bd_tail >= lp->tx_bd_num) -- cgit v1.2.3 From 28d9fab458b16bcd83f9dd07ede3d585c3e1a69e Mon Sep 17 00:00:00 2001 From: Esben Haabendal Date: Fri, 18 Jun 2021 12:52:28 +0200 Subject: net: ll_temac: Add memory-barriers for TX BD access Add a couple of memory-barriers to ensure correct ordering of read/write access to TX BDs. In xmit_done, we should ensure that reading the additional BD fields are only done after STS_CTRL_APP0_CMPLT bit is set. When xmit_done marks the BD as free by setting APP0=0, we need to ensure that the other BD fields are reset first, so we avoid racing with the xmit path, which writes to the same fields. Finally, making sure to read APP0 of next BD after the current BD, ensures that we see all available buffers. Signed-off-by: Esben Haabendal Signed-off-by: David S. Miller --- drivers/net/ethernet/xilinx/ll_temac_main.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index e82f162cd80c..9797aa3221d1 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -774,12 +774,15 @@ static void temac_start_xmit_done(struct net_device *ndev) stat = be32_to_cpu(cur_p->app0); while (stat & STS_CTRL_APP0_CMPLT) { + /* Make sure that the other fields are read after bd is + * released by dma + */ + rmb(); dma_unmap_single(ndev->dev.parent, be32_to_cpu(cur_p->phys), be32_to_cpu(cur_p->len), DMA_TO_DEVICE); skb = (struct sk_buff *)ptr_from_txbd(cur_p); if (skb) dev_consume_skb_irq(skb); - cur_p->app0 = 0; cur_p->app1 = 0; cur_p->app2 = 0; cur_p->app3 = 0; @@ -788,6 +791,12 @@ static void temac_start_xmit_done(struct net_device *ndev) ndev->stats.tx_packets++; ndev->stats.tx_bytes += be32_to_cpu(cur_p->len); + /* app0 must be visible last, as it is used to flag + * availability of the bd + */ + smp_mb(); + cur_p->app0 = 0; + lp->tx_bd_ci++; if (lp->tx_bd_ci >= lp->tx_bd_num) lp->tx_bd_ci = 0; @@ -814,6 +823,9 @@ static inline int temac_check_tx_bd_space(struct temac_local *lp, int num_frag) if (cur_p->app0) return NETDEV_TX_BUSY; + /* Make sure to read next bd app0 after this one */ + rmb(); + tail++; if (tail >= lp->tx_bd_num) tail = 0; -- cgit v1.2.3 From c364df2489b8ef2f5e3159b1dff1ff1fdb16040d Mon Sep 17 00:00:00 2001 From: Esben Haabendal Date: Fri, 18 Jun 2021 12:52:33 +0200 Subject: net: ll_temac: Fix TX BD buffer overwrite Just as the initial check, we need to ensure num_frag+1 buffers available, as that is the number of buffers we are going to use. This fixes a buffer overflow, which might be seen during heavy network load. Complete lockup of TEMAC was reproducible within about 10 minutes of a particular load. Fixes: 84823ff80f74 ("net: ll_temac: Fix race condition causing TX hang") Cc: stable@vger.kernel.org # v5.4+ Signed-off-by: Esben Haabendal Signed-off-by: David S. Miller --- drivers/net/ethernet/xilinx/ll_temac_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 9797aa3221d1..cc482ee36501 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -861,7 +861,7 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) smp_mb(); /* Space might have just been freed - check again */ - if (temac_check_tx_bd_space(lp, num_frag)) + if (temac_check_tx_bd_space(lp, num_frag + 1)) return NETDEV_TX_BUSY; netif_wake_queue(ndev); -- cgit v1.2.3 From f6396341194234e9b01cd7538bc2c6ac4501ab14 Mon Sep 17 00:00:00 2001 From: Esben Haabendal Date: Fri, 18 Jun 2021 12:52:38 +0200 Subject: net: ll_temac: Avoid ndo_start_xmit returning NETDEV_TX_BUSY As documented in Documentation/networking/driver.rst, the ndo_start_xmit method must not return NETDEV_TX_BUSY under any normal circumstances, and as recommended, we simply stop the tx queue in advance, when there is a risk that the next xmit would cause a NETDEV_TX_BUSY return. Signed-off-by: Esben Haabendal Signed-off-by: David S. Miller --- drivers/net/ethernet/xilinx/ll_temac_main.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index cc482ee36501..9a13953ea70f 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -942,6 +942,11 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) wmb(); lp->dma_out(lp, TX_TAILDESC_PTR, tail_p); /* DMA start */ + if (temac_check_tx_bd_space(lp, MAX_SKB_FRAGS + 1)) { + netdev_info(ndev, "%s -> netif_stop_queue\n", __func__); + netif_stop_queue(ndev); + } + return NETDEV_TX_OK; } -- cgit v1.2.3 From 9cca0c2d70149160407bda9a9446ce0c29b6e6c6 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Fri, 18 Jun 2021 16:49:02 +0300 Subject: net: ethernet: fix potential use-after-free in ec_bhf_remove static void ec_bhf_remove(struct pci_dev *dev) { ... struct ec_bhf_priv *priv = netdev_priv(net_dev); unregister_netdev(net_dev); free_netdev(net_dev); pci_iounmap(dev, priv->dma_io); pci_iounmap(dev, priv->io); ... } priv is netdev private data, but it is used after free_netdev(). It can cause use-after-free when accessing priv pointer. So, fix it by moving free_netdev() after pci_iounmap() calls. Fixes: 6af55ff52b02 ("Driver for Beckhoff CX5020 EtherCAT master module.") Signed-off-by: Pavel Skripkin Signed-off-by: David S. Miller --- drivers/net/ethernet/ec_bhf.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c index 46b0dbab8aad..7c992172933b 100644 --- a/drivers/net/ethernet/ec_bhf.c +++ b/drivers/net/ethernet/ec_bhf.c @@ -576,10 +576,12 @@ static void ec_bhf_remove(struct pci_dev *dev) struct ec_bhf_priv *priv = netdev_priv(net_dev); unregister_netdev(net_dev); - free_netdev(net_dev); pci_iounmap(dev, priv->dma_io); pci_iounmap(dev, priv->io); + + free_netdev(net_dev); + pci_release_regions(dev); pci_clear_master(dev); pci_disable_device(dev); -- cgit v1.2.3