- 21 Dec, 2019 23 commits
-
-
Yunsheng Lin authored
The function netif_skb_features() will disable the TSO feature by using dflt_features_check() if the driver does not implement ndo_features_check ops, which may cause performance degradation problem when hns3 hardware can do multiple tagged TSO. Also, the HNS3 hardware only supports checksum on the SKB with a max header len of 480 bytes, so remove the checksum and TSO related features when the header len is over 480 bytes. Signed-off-by:
Yunsheng Lin <linyunsheng@huawei.com> Signed-off-by:
Huazhong Tan <tanhuazhong@huawei.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Yufeng Mo authored
Currently, the dump FD tcam mode in debugfs is to query all FD tcams, including empty rules, which is unnecessary. This patch modify to find the position of useful rules before dump FD tcam, so that it does not need to query empty rules. This patch also modifies some help information in debugfs. Signed-off-by:
Yufeng Mo <moyufeng@huawei.com> Signed-off-by:
-
Huazhong Tan authored
When uninitializing CMDQ, HCLGE_STATE_CMD_DISABLE will be set up firstly, then the driver does not send command anymore. So, hclge_free_cmd_desc can be called without holding ring->lock. hclge_destroy_cmd_queue() and hclge_destroy_queue() are unnecessary now, so removes them, the VF driver has implemented currently. BTW, the VF driver should set up HCLGEVF_STATE_CMD_DISABLE as well in the hclgevf_cmd_uninit(), just likes what the PF driver does. Signed-off-by:
-
Huazhong Tan authored
Mutex vport_cfg_mutex has been used to protect uc_mac_list, mc_mac_list and vlan_list from being modified by unloading or reset task at the same time. But now unloading will set up HCLGE_STATE_REMOVING flag and call cancel_work_sync to break down this race condition, so this mutex is unnecessary. Signed-off-by:
-
Yunsheng Lin authored
A BD with FE bit means that it is the last BD of a packet, currently the FE bit is checked before calling hns3_add_frag(), which is unnecessary because the FE bit may have been checked in some case. This patch checks the FE bit before calling hns3_add_frag() after processing the first BD of a SKB and adjust the location of memcpy() to reduce duplication. Signed-off-by:
-
John Rutherford authored
To enable iproute2/tipc to generate backwards compatible printouts and validate command parameters for nodes using a <z.c.n> node address, it needs to be able to read the legacy address flag from the kernel. The legacy address flag records the way in which the node identity was originally specified. The legacy address flag is requested by the netlink message TIPC_NL_ADDR_LEGACY_GET. If the flag is set the attribute TIPC_NLA_NET_ADDR_LEGACY is set in the return message. Signed-off-by:
John Rutherford <john.rutherford@dektech.com.au> Acked-by:
Jon Maloy <jon.maloy@ericsson.com> Signed-off-by:
-
David S. Miller authored
Stefano Garzarella says: ==================== VSOCK: add vsock_test test suite The vsock_diag.ko module already has a test suite but the core AF_VSOCK functionality has no tests. This patch series adds several test cases that exercise AF_VSOCK SOCK_STREAM socket semantics (send/recv, connect/accept, half-closed connections, simultaneous connections). The v1 of this series was originally sent by Stefan. v3: - Patch 6: * check the byte received in the recv_byte() * use send(2)/recv(2) instead of write(2)/read(2) to test also flags (e.g. MSG_PEEK) - Patch 8: * removed unnecessary control_expectln("CLOSED") [Stefan]. - removed patches 9,10,11 added in the v2 - new Patch 9 add parameters to list and skip tests (e.g. useful for vmci that doesn't support half-closed socket in the host) - new Patch 10 prints a list of options in the help - new Patch 11 tests MSG_PEEK flags of recv(2) v2: https://patchwork.ozlabs.org/cover/1140538/ v1: https://patchwork.ozlabs.org/cover/847998/ ==================== Signed-off-by: -
Stefano Garzarella authored
Test if the MSG_PEEK flags of recv(2) works as expected. Signed-off-by:
Stefano Garzarella <sgarzare@redhat.com> Signed-off-by:
-
Stefano Garzarella authored
Since we now have several options, in the help we print the list of all supported options and a brief description of them. Signed-off-by:
-
Stefano Garzarella authored
Some tests can fail with transports that have a slightly different behavior, so let's add the possibility to specify which tests to skip. Signed-off-by:
-
Stefano Garzarella authored
Before check if a send returns -EPIPE, we need to make sure the connection is closed. To do that, we use epoll API to wait EPOLLRDHUP or EPOLLHUP events on the socket. Reported-by:
Jorgen Hansen <jhansen@vmware.com> Signed-off-by:
-
Stefan Hajnoczi authored
The vsock_test.c program runs a test suite of AF_VSOCK test cases. Signed-off-by:
Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by:
-
Stefan Hajnoczi authored
Test cases will want to transfer data. This patch adds utility functions to do this. Signed-off-by:
-
Stefan Hajnoczi authored
See code comment for details. Signed-off-by:
-
Stefan Hajnoczi authored
Many test cases will need to connect to the server or accept incoming connections. This patch extracts these operations into utility functions that can be reused. Signed-off-by:
-
Stefan Hajnoczi authored
Move useful functions into a separate file in preparation for more vsock test programs. Signed-off-by:
-
Stefan Hajnoczi authored
Signed-off-by:
-
Stefan Hajnoczi authored
The vsock_diag_test program directly included ../../../include/uapi/ headers from the source tree. Tests are supposed to use the usr/include/linux/ headers that have been prepared with make headers_install instead. Suggested-by:
-
David S. Miller authored
Oleksij Rempel says: ==================== add dsa switch support for ar9331 changes v6: - remove ag71xx changes from this patch set. It needs more work. - ar9331: fix register definition and add ASCII art switch documentation. changes v6: - rebase against net-next changes v5: - remote support for port5. The effort of using this port is questionable. Currently, it is better to not use it at all, then adding buggy support. - remove port enable call back. There is nothing what we actually need to enable. - rebase it against v5.5-rc1 changes v4: - ag71xx: ag71xx_mac_validate fix always false comparison (&& -> ||) - tag_ar9331: use skb_pull_rcsum() instead of skb_pull(). - tag_ar9331: drop skb_set_mac_header() changes v3: - ag71xx: ag71xx_mac_config: ignore MLO_AN_INBAND mode. It is not supported by HW and SW. - ag71xx: ag71xx_mac_validate: return all supported bits on PHY_INTERFACE_MODE_NA changes v2: - move Atheros AR9331 TAG format to separate patch - use netdev_warn_once in the tag driver to reduce potential message spam - typo fixes - reorder tag driver alphabetically - configure switch to maximal frame size - use mdiobus_read/write - fail if mdio sub node is not found - add comment for post reset state - remove deprecated comment about device id - remove phy-handle option for node with fixed-link - ag71xx: set 1G support only for GMII mode This patch series provides dsa switch support for Atheros ar9331 WiSoC. As side effect ag71xx needed to be ported to phylink to make the switch driver (as well phylink based) work properly. ==================== Signed-off-by: -
Oleksij Rempel authored
Provide basic support for Atheros AR9331 built-in switch. So far it works as port multiplexer without any hardware offloading support. Reviewed-by:
Andrew Lunn <andrew@lunn.ch> Reviewed-by:
Vivien Didelot <vivien.didelot@gmail.com> Signed-off-by:
Oleksij Rempel <o.rempel@pengutronix.de> Signed-off-by:
-
Oleksij Rempel authored
Add support for tag format used in Atheros AR9331 built-in switch. Reviewed-by:
-
Oleksij Rempel authored
Add switch node supported by dsa ar9331 driver. Signed-off-by:
-
Oleksij Rempel authored
Atheros AR9331 has built-in 5 port switch. The switch can be configured to use all 5 or 4 ports. One of built-in PHYs can be used by first built-in ethernet controller or to be used directly by the switch over second ethernet controller. Signed-off-by:
-
- 20 Dec, 2019 17 commits
-
-
Nathan Chancellor authored
Clang warns ../drivers/nfc/pn544/pn544.c:696:4: warning: misleading indentation; statement is not part of the previous 'if' [-Wmisleading-indentation] return nfc_hci_send_cmd(hdev, NFC_HCI_RF_READER_A_GATE, ^ ../drivers/nfc/pn544/pn544.c:692:3: note: previous statement is here if (target->nfcid1_len != 4 && target->nfcid1_len != 7 && ^ 1 warning generated. This warning occurs because there is a space after the tab on this line. Remove it so that the indentation is consistent with the Linux kernel coding style and clang no longer warns. Fixes: da052850 ("NFC: Add pn544 presence check for different targets") Link: https://github.com/ClangBuiltLinux/linux/issues/814Signed-off-by:Nathan Chancellor <natechancellor@gmail.com> Signed-off-by:
-
David S. Miller authored
Doug Berger says: ==================== net: bcmgenet: Turn on offloads by default This commit stack is based on Florian's commit 4e8aedfe78c7 ("net: systemport: Turn on offloads by default") and enables the offloads for the bcmgenet driver by default. The first commit adds support for the HIGHDMA feature to the driver. The second converts the Tx checksum implementation to use the generic hardware logic rather than the deprecated IP centric methods. The third modifies the Rx checksum implementation to use the hardware offload to compute the complete checksum rather than filtering out bad packets detected by the hardware's IP centric implementation. This may increase processing load by passing bad packets to the network stack, but it provides for more flexible handling of packets by the network stack without requiring software computation of the checksum. The remaining commits mirror the extensions Florian made to the sysport driver to retain symmetry with that driver and to make the benefits of the hardware offloads more ubiquitous. ==================== Signed-off-by: -
Doug Berger authored
When inserting the TSB, keep track of how many times we had to do it and if there was a failure in doing so, this helps profile the driver for possibly incorrect headroom settings. Signed-off-by:
Doug Berger <opendmb@gmail.com> Reviewed-by:
Florian Fainelli <f.fainelli@gmail.com> Signed-off-by:
-
Doug Berger authored
During bcmgenet_put_tx_csum() make sure we differentiate a SKB headroom re-allocation failure from the normal swap and replace path. Signed-off-by:
-
Doug Berger authored
We can turn on the RX/TX checksum offloads and the scatter/gather features by default and make sure that those are properly reflected back to e.g: stacked devices such as VLAN. Signed-off-by:
-
Doug Berger authored
During driver resume and open, the HW may have lost its context/state, utilize bcmgenet_set_features() to make sure we do restore the correct set of features that were previously configured. Signed-off-by:
-
Doug Berger authored
In preparation for unconditionally enabling TX and RX checksum offloads, refactor bcmgenet_set_features() a bit such that __netdev_update_features() during register_netdev() can make sure that features are correctly programmed during network device registration. Since we can now be called during register_netdev() with clocks gated, we need to temporarily turn them on/off in order to have a successful register programming. We also move the CRC forward setting read into bcmgenet_set_features() since priv->crc_fwd_en matters while turning on RX checksum offload, that way we are guaranteed they are in sync in case we ever add support for NETIF_F_RXFCS at some point in the future. Signed-off-by:
-
Doug Berger authored
This commit updates the Rx checksum offload behavior of the driver to use the more generic CHECKSUM_COMPLETE method that supports all protocols over the CHECKSUM_UNNECESSARY method that only applies to some protocols known by the hardware. This behavior is perceived to be superior. Signed-off-by:
-
Doug Berger authored
The GENET hardware should be capable of generating IP checksums using the NETIF_F_HW_CSUM feature, so switch to using that feature instead of the depricated NETIF_F_IP_CSUM and NETIF_F_IPV6_CSUM. Signed-off-by:
-
Doug Berger authored
This commit configures the DMA masks for the GENET driver and sets the NETIF_F_HIGHDMA flag to report support of the feature. Signed-off-by:
-
Florian Fainelli authored
SYSTEMPORT is capabable of doing up to 40-bit of physical addresses, set an appropriate DMA mask to permit that. Signed-off-by:
-
David S. Miller authored
Jakub Kicinski says: ==================== nfp: tls: implement the stream sync RX resync This small series adds support for using the device in stream scan RX resync mode which improves the RX resync success rate. Without stream scan it's pretty much impossible to successfully resync a continuous stream. ==================== Signed-off-by: -
Jakub Kicinski authored
The simple RX resync strategy controlled by the kernel does not guarantee as good results as if the device helps by detecting the potential record boundaries and keeping track of them. We've called this strategy stream scan in the tls-offload doc. Implement this strategy for the NFP. The device sends a request for record boundary confirmation, which is then recorded in per-TLS socket state and responded to once record is reached. Because the device keeps track of records passing after the request was sent the response is not as latency sensitive as when kernel just tries to tell the device the information about the next record. Signed-off-by:
Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by:
-
Jakub Kicinski authored
There is currently no way for driver to reliably check that the socket it has looked up is in fact RX offloaded. Add a helper. This allows drivers to catch misbehaving firmware. Signed-off-by:
-
Jakub Kicinski authored
Make nfp_net_parse_meta() take a packet pointer and return a drop/no drop decision. Right now it returns the end of metadata and caller compares it to the packet pointer. Signed-off-by:
-
David S. Miller authored
John Hurley says: ==================== Add ipv6 tunnel support to NFP The following patches add support for IPv6 tunnel offload to the NFP driver. Patches 1-2 do some code tidy up and prepare existing code for reuse in IPv6 tunnels. Patches 3-4 handle IPv6 tunnel decap (match) rules. Patches 5-8 handle encap (action) rules. Patch 9 adds IPv6 support to the merge and pre-tunnel rule functions. v1->v2: - fix compiler warning when building without CONFIG_IPV6 set - Jakub Kicinski (patch 7) ==================== Signed-off-by: -
John Hurley authored
Both pre-tunnel match rules and flow merge functions parse compiled match/action fields for validation. Update these validation functions to include IPv6 match and action fields. Signed-off-by:
John Hurley <john.hurley@netronome.com> Reviewed-by:
Simon Horman <simon.horman@netronome.com> Reviewed-by:
-
