summaryrefslogtreecommitdiff
path: root/drivers/net
AgeCommit message (Collapse)Author
2019-11-04can: flexcan: increase error counters if skb enqueueing via ↵Marc Kleine-Budde
can_rx_offload_queue_sorted() fails The call to can_rx_offload_queue_sorted() may fail and return an error (in the current implementation due to resource shortage). The passed skb is consumed. This patch adds incrementing of the appropriate error counters to let the device statistics reflect that there's a problem. Reported-by: Martin Hundebøll <martin@geanix.com> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04can: rx-offload: can_rx_offload_irq_offload_fifo(): continue on errorMarc Kleine-Budde
In case of a resource shortage, i.e. the rx_offload queue will overflow or a skb fails to be allocated (due to OOM), can_rx_offload_offload_one() will call mailbox_read() to discard the mailbox and return an ERR_PTR. If the hardware FIFO is empty can_rx_offload_offload_one() will return NULL. In case a CAN frame was read from the hardware, can_rx_offload_offload_one() returns the skb containing it. Without this patch can_rx_offload_irq_offload_fifo() bails out if no skb returned, regardless of the reason. Similar to can_rx_offload_irq_offload_timestamp() in case of a resource shortage the whole FIFO should be discarded, to avoid an IRQ storm and give the system some time to recover. However if the FIFO is empty the loop can be left. With this patch the loop is left in case of empty FIFO, but not on errors. Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04can: rx-offload: can_rx_offload_irq_offload_timestamp(): continue on errorJeroen Hofstee
In case of a resource shortage, i.e. the rx_offload queue will overflow or a skb fails to be allocated (due to OOM), can_rx_offload_offload_one() will call mailbox_read() to discard the mailbox and return an ERR_PTR. However can_rx_offload_irq_offload_timestamp() bails out in the error case. In case of a resource shortage all mailboxes should be discarded, to avoid an IRQ storm and give the system some time to recover. Since can_rx_offload_irq_offload_timestamp() is typically called from a while loop, all message will eventually be discarded. So let's continue on error instead to discard them directly. Signed-off-by: Jeroen Hofstee <jhofstee@victronenergy.com> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04can: rx-offload: can_rx_offload_offload_one(): use ERR_PTR() to propagate ↵Marc Kleine-Budde
error value in case of errors Before this patch can_rx_offload_offload_one() returns a pointer to a skb containing the read CAN frame or a NULL pointer. However the meaning of the NULL pointer is ambiguous, it can either mean the requested mailbox is empty or there was an error. This patch fixes this situation by returning: - pointer to skb on success - NULL pointer if mailbox is empty - ERR_PTR() in case of an error All users of can_rx_offload_offload_one() have been adopted, no functional change intended. Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04can: rx-offload: can_rx_offload_offload_one(): increment rx_fifo_errors on ↵Marc Kleine-Budde
queue overflow or OOM If the rx-offload skb_queue is full or the skb allocation fails (due to OOM), the mailbox contents is discarded. This patch adds the incrementing of the rx_fifo_errors statistics counter. Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04can: rx-offload: can_rx_offload_offload_one(): do not increase the skb_queue ↵Marc Kleine-Budde
beyond skb_queue_len_max The skb_queue is a linked list, holding the skb to be processed in the next NAPI call. Without this patch, the queue length in can_rx_offload_offload_one() is limited to skb_queue_len_max + 1. As the skb_queue is a linked list, no array or other resources are accessed out-of-bound, however this behaviour is counterintuitive. This patch limits the rx-offload skb_queue length to skb_queue_len_max. Fixes: d254586c3453 ("can: rx-offload: Add support for HW fifo based irq offloading") Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04can: rx-offload: can_rx_offload_queue_tail(): fix error handling, avoid skb ↵Marc Kleine-Budde
mem leak If the rx-offload skb_queue is full can_rx_offload_queue_tail() will not queue the skb and return with an error. This patch frees the skb in case of a full queue, which brings can_rx_offload_queue_tail() in line with the can_rx_offload_queue_sorted() function, which has been adjusted in the previous patch. The return value is adjusted to -ENOBUFS to better reflect the actual problem. The device stats handling is left to the caller. Fixes: d254586c3453 ("can: rx-offload: Add support for HW fifo based irq offloading") Reported-by: Kurt Van Dijck <dev.kurt@vandijck-laurijssen.be> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04can: rx-offload: can_rx_offload_queue_sorted(): fix error handling, avoid ↵Marc Kleine-Budde
skb mem leak If the rx-offload skb_queue is full can_rx_offload_queue_sorted() will not queue the skb and return with an error. None of the callers of this function, issue a kfree_skb() to free the not queued skb. This results in a memory leak. This patch fixes the problem by freeing the skb in case of a full queue. The return value is adjusted to -ENOBUFS to better reflect the actual problem. The device stats handling is left to the callers, as this function might be used in both the rx and tx path. Fixes: 55059f2b7f86 ("can: rx-offload: introduce can_rx_offload_get_echo_skb() and can_rx_offload_queue_sorted() functions") Cc: linux-stable <stable@vger.kernel.org> Cc: Martin Hundebøll <martin@geanix.com> Reported-by: Martin Hundebøll <martin@geanix.com> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04can: xilinx_can: Fix flags field initialization for axi canAppana Durga Kedareswara rao
AXI CANIP doesn't support tx fifo empty interrupt feature(TXFEMP), update the flags filed in the driver for AXI CAN case accordingly. Fixes: 3281b380ec9f ("can: xilinx_can: Fix flags field initialization for axi can and canps") Reported-by: Anssi Hannula <anssi.hannula@bitwise.fi> Signed-off-by: Appana Durga Kedareswara rao <appana.durga.rao@xilinx.com> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04can: c_can: C_CAN: add bus recovery eventsJeroen Hofstee
While the state is updated when the error counters increase and decrease, there is no event when the bus recovers and the error counters decrease again. So add that event as well. Change the state going downward to be ERROR_PASSIVE -> ERROR_WARNING -> ERROR_ACTIVE instead of directly to ERROR_ACTIVE again. Signed-off-by: Jeroen Hofstee <jhofstee@victronenergy.com> Acked-by: Kurt Van Dijck <dev.kurt@vandijck-laurijssen.be> Tested-by: Kurt Van Dijck <dev.kurt@vandijck-laurijssen.be> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04can: c_can: D_CAN: c_can_chip_config(): perform a sofware reset on openJeroen Hofstee
When the CAN interface is closed it the hardwre is put in power down mode, but does not reset the error counters / state. Reset the D_CAN on open, so the reported state and the actual state match. According to [1], the C_CAN module doesn't have the software reset. [1] http://www.bosch-semiconductors.com/media/ip_modules/pdf_2/c_can_fd8/users_manual_c_can_fd8_r210_1.pdf Signed-off-by: Jeroen Hofstee <jhofstee@victronenergy.com> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04can: c_can: c_can_poll(): only read status register after status IRQKurt Van Dijck
When the status register is read without the status IRQ pending, the chip may not raise the interrupt line for an upcoming status interrupt and the driver may miss a status interrupt. It is critical that the BUSOFF status interrupt is forwarded to the higher layers, since no more interrupts will follow without intervention. Thanks to Wolfgang and Joe for bringing up the first idea. Signed-off-by: Kurt Van Dijck <dev.kurt@vandijck-laurijssen.be> Cc: Wolfgang Grandegger <wg@grandegger.com> Cc: Joe Burmeister <joe.burmeister@devtank.co.uk> Fixes: fa39b54ccf28 ("can: c_can: Get rid of pointless interrupts") Cc: linux-stable <stable@vger.kernel.org> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04can: peak_usb: report bus recovery as wellJeroen Hofstee
While the state changes are reported when the error counters increase and decrease, there is no event when the bus recovers and the error counters decrease again. So add those as well. Change the state going downward to be ERROR_PASSIVE -> ERROR_WARNING -> ERROR_ACTIVE instead of directly to ERROR_ACTIVE again. Signed-off-by: Jeroen Hofstee <jhofstee@victronenergy.com> Cc: Stephane Grosjean <s.grosjean@peak-system.com> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04can: peak_usb: fix slab info leakJohan Hovold
Fix a small slab info leak due to a failure to clear the command buffer at allocation. The first 16 bytes of the command buffer are always sent to the device in pcan_usb_send_cmd() even though only the first two may have been initialised in case no argument payload is provided (e.g. when waiting for a response). Fixes: bb4785551f64 ("can: usb: PEAK-System Technik USB adapters driver core") Cc: stable <stable@vger.kernel.org> # 3.4 Reported-by: syzbot+863724e7128e14b26732@syzkaller.appspotmail.com Signed-off-by: Johan Hovold <johan@kernel.org> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04can: peak_usb: fix a potential out-of-sync while decoding packetsStephane Grosjean
When decoding a buffer received from PCAN-USB, the first timestamp read in a packet is a 16-bit coded time base, and the next ones are an 8-bit offset to this base, regardless of the type of packet read. This patch corrects a potential loss of synchronization by using a timestamp index read from the buffer, rather than an index of received data packets, to determine on the sizeof the timestamp to be read from the packet being decoded. Signed-off-by: Stephane Grosjean <s.grosjean@peak-system.com> Fixes: 46be265d3388 ("can: usb: PEAK-System Technik PCAN-USB specific part") Cc: linux-stable <stable@vger.kernel.org> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04can: flexcan: disable completely the ECC mechanismJoakim Zhang
The ECC (memory error detection and correction) mechanism can be activated or not, controlled by the ECCDIS bit in CAN_MECR. When disabled, updates on indications and reporting registers are stopped. So if want to disable ECC completely, had better assert ECCDIS bit, not just mask the related interrupts. Fixes: cdce844865be ("can: flexcan: add vf610 support for FlexCAN") Signed-off-by: Joakim Zhang <qiangqing.zhang@nxp.com> Cc: linux-stable <stable@vger.kernel.org> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04can: usb_8dev: fix use-after-free on disconnectJohan Hovold
The driver was accessing its driver data after having freed it. Fixes: 0024d8ad1639 ("can: usb_8dev: Add support for USB2CAN interface from 8 devices") Cc: stable <stable@vger.kernel.org> # 3.9 Cc: Bernd Krumboeck <b.krumboeck@gmail.com> Cc: Wolfgang Grandegger <wg@grandegger.com> Signed-off-by: Johan Hovold <johan@kernel.org> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04can: mcba_usb: fix use-after-free on disconnectJohan Hovold
The driver was accessing its driver data after having freed it. Fixes: 51f3baad7de9 ("can: mcba_usb: Add support for Microchip CAN BUS Analyzer") Cc: stable <stable@vger.kernel.org> # 4.12 Cc: Remigiusz Kołłątaj <remigiusz.kollataj@mobica.com> Reported-by: syzbot+e29b17e5042bbc56fae9@syzkaller.appspotmail.com Signed-off-by: Johan Hovold <johan@kernel.org> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04can: gs_usb: gs_can_open(): prevent memory leakNavid Emamdoost
In gs_can_open() if usb_submit_urb() fails the allocated urb should be released. Fixes: d08e973a77d1 ("can: gs_usb: Added support for the GS_USB CAN devices") Cc: linux-stable <stable@vger.kernel.org> Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04can: dev: add missing of_node_put() after calling of_get_child_by_name()Wen Yang
of_node_put() needs to be called when the device node which is got from of_get_child_by_name() finished using. Fixes: 2290aefa2e90 ("can: dev: Add support for limiting configured bitrate") Cc: Franklin S Cooper Jr <fcooper@ti.com> Signed-off-by: Wen Yang <wenyang@linux.alibaba.com> Cc: linux-stable <stable@vger.kernel.org> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2019-11-04ice: Add support for AF_XDPKrzysztof Kazimierczak
Add zero copy AF_XDP support. This patch adds zero copy support for Tx and Rx; code for zero copy is added to ice_xsk.h and ice_xsk.c. For Tx, implement ndo_xsk_wakeup. As with other drivers, reuse existing XDP Tx queues for this task, since XDP_REDIRECT guarantees mutual exclusion between different NAPI contexts based on CPU ID. In turn, a netdev can XDP_REDIRECT to another netdev with a different NAPI context, since the operation is bound to a specific core and each core has its own hardware ring. For Rx, allocate frames as MEM_TYPE_ZERO_COPY on queues that AF_XDP is enabled. Signed-off-by: Krzysztof Kazimierczak <krzysztof.kazimierczak@intel.com> Co-developed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2019-11-04ice: Move common functions to ice_txrx_lib.cKrzysztof Kazimierczak
In preparation of AF XDP, move functions that will be used both by skb and zero-copy paths to a new file called ice_txrx_lib.c. This allows us to avoid using ifdefs to control the staticness of said functions. Move other functions (ice_rx_csum, ice_rx_hash and ice_ptype_to_htype) called only by the moved ones to the new file as well. Signed-off-by: Krzysztof Kazimierczak <krzysztof.kazimierczak@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2019-11-04net: fec: add missed clk_disable_unprepare in removeChuhong Yuan
This driver forgets to disable and unprepare clks when remove. Add calls to clk_disable_unprepare to fix it. Signed-off-by: Chuhong Yuan <hslester96@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-04net: ethernet: stmmac: drop unused variable in stm32mp1_set_mode()Christophe Roullier
Building with W=1 (cf.scripts/Makefile.extrawarn) outputs: warning: variable ‘ret’ set but not used [-Wunused-but-set-variable] Drop the unused 'ret' variable. Signed-off-by: Christophe Roullier <christophe.roullier@st.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-04net: sgi: ioc3-eth: ensure tx ring is 16k aligned.Thomas Bogendoerfer
IOC3 hardware needs a 16k aligned TX ring. Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-04net: sgi: ioc3-eth: fix setting NETIF_F_HIGHDMAChristoph Hellwig
Set NETIF_F_HIGHDMA together with the NETIF_F_IP_CSUM flag instead of letting the second assignment overwrite it. Probably doesn't matter in practice as none of the systems an IOC3 is usually found in has highmem to start with. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-04net: sgi: ioc3-eth: simplify setting the DMA maskChristoph Hellwig
There is no need to fall back to a lower mask these days, the DMA mask just communicates the hardware supported features. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-04net: sgi: ioc3-eth: fix usage of GFP_* flagsChristoph Hellwig
dma_alloc_coherent always zeroes memory, there is no need for __GFP_ZERO. Also doing a GFP_ATOMIC allocation just before a GFP_KERNEL one is clearly bogus. Fixes: ed870f6a7aa2 ("net: sgi: ioc3-eth: use dma-direct for dma allocations") Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-04net: sgi: ioc3-eth: don't abuse dma_direct_* callsChristoph Hellwig
dma_direct_ is a low-level API that must never be used by drivers directly. Switch to use the proper DMA API instead. Fixes: ed870f6a7aa2 ("net: sgi: ioc3-eth: use dma-direct for dma allocations") Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-04net: of_get_phy_mode: Change API to solve int/unit warningsAndrew Lunn
Before this change of_get_phy_mode() returned an enum, phy_interface_t. On error, -ENODEV etc, is returned. If the result of the function is stored in a variable of type phy_interface_t, and the compiler has decided to represent this as an unsigned int, comparision with -ENODEV etc, is a signed vs unsigned comparision. Fix this problem by changing the API. Make the function return an error, or 0 on success, and pass a pointer, of type phy_interface_t, where the phy mode should be stored. v2: Return with *interface set to PHY_INTERFACE_MODE_NA on error. Add error checks to all users of of_get_phy_mode() Fixup a few reverse christmas tree errors Fixup a few slightly malformed reverse christmas trees v3: Fix 0-day reported errors. Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-04ice: Add support for XDPMaciej Fijalkowski
Add support for XDP. Implement ndo_bpf and ndo_xdp_xmit. Upon load of an XDP program, allocate additional Tx rings for dedicated XDP use. The following actions are supported: XDP_TX, XDP_DROP, XDP_REDIRECT, XDP_PASS, and XDP_ABORTED. Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2019-11-04ice: get rid of per-tc flow in Tx queue configuration routinesMaciej Fijalkowski
There's no reason for treating DCB as first class citizen when configuring the Tx queues and going through TCs. Reverse the logic and base the configuration logic on rings, which is the object of interest anyway. Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2019-11-04ice: Introduce ice_base.cAnirudh Venkataramanan
Remove a few uses of kernel configuration flags from ice_lib.c by introducing a new source file ice_base.c. Also move corresponding function prototypes from ice_lib.h to ice_base.h and include ice_base.h where required. Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2019-11-03Merge tag 'mlx5-updates-2019-11-01' of ↵David S. Miller
git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux Saeed Mahameed says: ==================== mlx5-updates-2019-11-01 Misc updates for mlx5 netdev and core driver 1) Steering Core: Replace CRC32 internal implementation with standard kernel lib. 2) Steering Core: Support IPv4 and IPv6 mixed matcher. 3) Steering Core: Lockless FTE read lookups 4) TC: Bit sized fields rewrite support. 5) FPGA: Standalone FPGA support. 6) SRIOV: Reset VF parameters configurations on SRIOV disable. 7) netdev: Dump WQs wqe descriptors on CQE with error events. 8) MISC Cleanups. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-02Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/netDavid S. Miller
The only slightly tricky merge conflict was the netdevsim because the mutex locking fix overlapped a lot of driver reload reorganization. The rest were (relatively) trivial in nature. Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-01r8169: fix wrong PHY ID issue with RTL8168dpHeiner Kallweit
As reported in [0] at least one RTL8168dp version has problems establishing a link. This chip version has an integrated RTL8211b PHY, however the chip seems to report a wrong PHY ID, resulting in a wrong PHY driver (for Generic Realtek PHY) being loaded. Work around this issue by adding a hook to r8168dp_2_mdio_read() for returning the correct PHY ID. [0] https://bbs.archlinux.org/viewtopic.php?id=246508 Fixes: 242cd9b5866a ("r8169: use phy_resume/phy_suspend") Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-01net: dsa: bcm_sf2: Fix IMP setup for port different than 8Florian Fainelli
Since it became possible for the DSA core to use a CPU port different than 8, our bcm_sf2_imp_setup() function was broken because it assumes that registers are applicable to port 8. In particular, the port's MAC is going to stay disabled, so make sure we clear the RX_DIS and TX_DIS bits if we are not configured for port 8. Fixes: 9f91484f6fcc ("net: dsa: make "label" property optional for dsa2") Signed-off-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-01net: phylink: Fix phylink_dbg() macroFlorian Fainelli
The phylink_dbg() macro does not follow dynamic debug or defined(DEBUG) and as a result, it spams the kernel log since a PR_DEBUG level is currently used. Fix it to be defined appropriately whether CONFIG_DYNAMIC_DEBUG or defined(DEBUG) are set. Fixes: 17091180b152 ("net: phylink: Add phylink_{printk, err, warn, info, dbg} macros") Signed-off-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-01gve: Fixes DMA synchronization.Yangchun Fu
Synces the DMA buffer properly in order for CPU and device to see the most up-to-data data. Signed-off-by: Yangchun Fu <yangchun@google.com> Reviewed-by: Catherine Sullivan <csully@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-01net/mlx5: DR, Support IPv4 and IPv6 mixed matcherAlex Vesker
Until now SW steering supported matchers that are IPv4 and IPv6. The limitation was mixed matchers in which the outer header IP version was different from the inner header IP version. To support the mixed matcher we create all the possible ste_builder combinations, once we create a rule we select the correct one to be used for rule creation. Signed-off-by: Alex Vesker <valex@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2019-11-01net/mlx5: LAG, Use affinity type enumeratorsErez Alfasi
Instead of using explicit indexes, simply use affinity type enumerators to make the code more readable. Fixes: 544fe7c2e654 ("net/mlx5e: Activate HW multipath and handle port affinity based on FIB events") Signed-off-by: Erez Alfasi <ereza@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2019-11-01net/mlx5: LAG, Use port enumeratorsErez Alfasi
Instead of using explicit array indexes, simply use ports enumerators to make the code more readable. Fixes: 7907f23adc18 ("net/mlx5: Implement RoCE LAG feature") Signed-off-by: Erez Alfasi <ereza@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2019-11-01net/mlx5: rate limit alloc_ent error messagesLi RongQing
when debug a bug, which triggers TX hang, and kernel log is spammed with the following info message [ 1172.044764] mlx5_core 0000:21:00.0: cmd_work_handler:930:(pid 8): failed to allocate command entry Signed-off-by: Li RongQing <lirongqing@baidu.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2019-11-01net/mlx5e: Add ToS (DSCP) header rewrite supportDmytro Linkin
Add support for rewriting of DSCP part of ToS field. Next commands, for example, can be used to offload rewrite action: OVS: $ ovs-ofctl add-flow ovs-sriov "ip, in_port=REP, \ actions=mod_nw_tos:68, output:NIC" iproute2 (used retain mask, as tc command rewrite whole ToS field): $ tc filter add dev REP ingress protocol ip prio 1 flower skip_sw \ ip_proto icmp action pedit munge ip tos set 68 retain 0xfc pipe \ action mirred egress redirect dev NIC Signed-off-by: Dmytro Linkin <dmitrolin@mellanox.com> Reviewed-by: Roi Dayan <roid@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2019-11-01net/mlx5e: Bit sized fields rewrite supportDmytro Linkin
This patch doesn't change any functionality, but is a pre-step for adding support for rewriting of bit-sized fields, like DSCP and ECN in IPv4 header, similar fields in IPv6, etc. Signed-off-by: Dmytro Linkin <dmitrolin@mellanox.com> Reviewed-by: Roi Dayan <roid@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2019-11-01net/mlx5: WQ, Move short getters into header fileTariq Toukan
Move short Work Queue API getter functions into the WQ header file. Signed-off-by: Tariq Toukan <tariqt@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2019-11-01net/mlx5e: TX, Dump WQs wqe descriptors on CQE with error eventsSaeed Mahameed
Dump the Work Queue's TX WQE descriptor when a completion with error is received. Example: [5.331832] mlx5_core 0000:00:04.0 enp0s4: Error cqe on cqn 0xa, ci 0x1, TXQ-SQ qpn 0xe, opcode 0xd, syndrome 0x2, vendor syndrome 0x0 [5.333127] 00000000: 55 65 02 75 31 fe c2 d2 6b 6c 62 1e f9 e1 d8 5c [5.333837] 00000010: d3 b2 6c b8 89 e4 84 20 0b f4 3c e0 f3 75 41 ca [5.334568] 00000020: 46 00 00 00 cd 70 a0 92 18 3a 01 de 00 00 00 00 [5.335313] 00000030: 7d bc 05 89 b2 e9 00 02 1e 00 00 0e 00 00 30 d2 [5.335972] WQE DUMP: WQ size 1024 WQ cur size 0, WQE index 0x0, len: 64 [5.336710] 00000000: 00 00 00 1e 00 00 0e 04 00 00 00 08 00 00 00 00 [5.337524] 00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 12 33 33 [5.338151] 00000020: 00 00 00 16 52 54 00 00 00 01 86 dd 60 00 00 00 [5.338740] 00000030: 00 00 00 48 00 00 00 00 00 00 00 00 66 ba 58 14 Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Tariq Toukan <tariqt@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2019-11-01net/mlx5: Support lockless FTE read lookupsParav Pandit
During connection tracking offloads with high number of connections, (40K connections per second), flow table group lock contention is observed. To improve the performance by reducing lock contention, lockless FTE read lookup is performed as described below. Each flow table entry is refcounted. Flow table entry is removed when refcount drops to zero. rhash table allows rcu protected lookup. Each hash table entry insertion and removal is write lock protected. Hence, it is possible to perform lockless lookup in rhash table using following scheme. (a) Guard FTE entry lookup per group using rcu read lock. (b) Before freeing the FTE entry, wait for all readers to finish accessing the FTE. Below example of one reader and write in parallel racing, shows protection in effect with rcu lock. lookup_fte_locked() rcu_read_lock(); search_hash_table() existing_flow_group_write_lock(); tree_put_node(fte) drop_ref_cnt(fte) del_sw_fte(fte) del_hash_table_entry(); call_rcu(); existing_flow_group_write_unlock(); get_ref_cnt(fte) fails rcu_read_unlock(); rcu grace period(); [..] kmem_cache_free(fte); Signed-off-by: Parav Pandit <parav@mellanox.com> Reviewed-by: Mark Bloch <markb@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2019-11-01net/mlx5: Do not hold group lock while allocating FTE in softwareParav Pandit
FTE memory allocation using alloc_fte() doesn't have any dependency on the flow group. Hence, do not hold flow group lock while performing alloc_fte(). This helps to reduce contention of flow group lock. Signed-off-by: Parav Pandit <parav@mellanox.com> Reviewed-by: Daniel Jurgens <danielj@mellanox.com> Reviewed-by: Mark Bloch <markb@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
2019-11-01net/mlx5e: Verify that rule has at least one fwd/drop actionVlad Buslov
Currently, mlx5 tc layer doesn't verify that rule has at least one forward or drop action which leads to following firmware syndrome when user tries to offload such action: [ 1824.860501] mlx5_core 0000:81:00.0: mlx5_cmd_check:753:(pid 29458): SET_FLOW_TABLE_ENTRY(0x936) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0x144b7a) Add check at the end of parse_tc_fdb_actions() that verifies that resulting attribute has action fwd or drop flag set. Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Reviewed-by: Paul Blakey <paulb@mellanox.com> Reviewed-by: Roi Dayan <roid@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
generated by cgit (git 2.34.1) at 2025-09-11 07:05:29 +0000