aboutsummaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/intel
AgeCommit message (Collapse)AuthorFilesLines
2020-05-21ice: Don't reset and rebuild for Tx timeout on PFC enabled queueAvinash JD5-0/+94
When there's a Tx timeout for a queue which belongs to a PFC enabled TC, then it's not because the queue is hung but because PFC is in action. In PFC, peer sends a pause frame for a specified period of time when its buffer threshold is exceeded (due to congestion). Netdev on the other hand checks if ACK is received within a specified time for a TX packet, if not, it'll invoke the tx_timeout routine. Signed-off-by: Avinash JD <[email protected]> Signed-off-by: Tony Nguyen <[email protected]> Tested-by: Andrew Bowers <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-21ice: Add VF promiscuous supportBrett Creeley4-2/+223
Implement promiscuous support for VF VSIs. Behaviour of promiscuous support is based on VF trust as well as the, introduced, vf-true-promisc flag. A trusted VF with vf-true-promisc disabled will be the default VSI, which means that all traffic without a matching destination MAC address in the device's internal switch will be forwarded to this VF VSI. A trusted VF with vf-true-promisc enabled will go into "true promiscuous mode". This amounts to the VF receiving all ingress and egress traffic that hits the device's internal switch. An untrusted VF will only receive traffic destined for that VF. The vf-true-promisc-support flag cannot be toggled while any VF is in promiscuous mode. This flag should be set prior to loading the iavf driver or spawning VF(s). Signed-off-by: Brett Creeley <[email protected]> Tested-by: Andrew Bowers <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-21ice: Add support for tunnel offloadsTony Nguyen14-14/+867
Create a boost TCAM entry for each tunnel port in order to get a tunnel PTYPE. Update netdev feature flags and implement the appropriate logic to get and set values for hardware offloads. Signed-off-by: Tony Nguyen <[email protected]> Signed-off-by: Henry Tieman <[email protected]> Tested-by: Andrew Bowers <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-21ice: report netlist version in .info_getJacob Keller4-0/+147
The flash memory for the ice hardware contains a block of information used for link management called the Netlist module. As this essentially represents another section of firmware, add its version information to the output of the driver's .info_get handler. This includes both a version and the first few bytes of a hash of the module contents. fw.netlist -> the version information extracted from the netlist module fw.netlist.build-> first 4 bytes of the hash of the contents, similar to fw.mgmt.build Signed-off-by: Jacob Keller <[email protected]> Tested-by: Andrew Bowers <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-21ixgbe, xsk: Migrate to new MEM_TYPE_XSK_BUFF_POOLBjörn Töpel4-271/+62
Remove MEM_TYPE_ZERO_COPY in favor of the new MEM_TYPE_XSK_BUFF_POOL APIs. v1->v2: Fixed xdp_buff data_end update. (Björn) Signed-off-by: Björn Töpel <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Cc: [email protected] Link: https://lore.kernel.org/bpf/[email protected]
2020-05-21ice, xsk: Migrate to new MEM_TYPE_XSK_BUFF_POOLBjörn Töpel4-359/+54
Remove MEM_TYPE_ZERO_COPY in favor of the new MEM_TYPE_XSK_BUFF_POOL APIs. v4->v5: Fixed "warning: Excess function parameter 'alloc' description in 'ice_alloc_rx_bufs_zc'" and "warning: Excess function parameter 'xdp' description in 'ice_construct_skb_zc'". (Jakub) Signed-off-by: Maciej Fijalkowski <[email protected]> Signed-off-by: Björn Töpel <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Cc: [email protected] Link: https://lore.kernel.org/bpf/[email protected]
2020-05-21i40e, xsk: Migrate to new MEM_TYPE_XSK_BUFF_POOLBjörn Töpel4-335/+47
Remove MEM_TYPE_ZERO_COPY in favor of the new MEM_TYPE_XSK_BUFF_POOL APIs. The AF_XDP zero-copy rx_bi ring is now simply a struct xdp_buff pointer. v4->v5: Fixed "warning: Excess function parameter 'bi' description in 'i40e_construct_skb_zc'". (Jakub) Signed-off-by: Björn Töpel <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Cc: [email protected] Link: https://lore.kernel.org/bpf/[email protected]
2020-05-21i40e: Separate kernel allocated rx_bi rings from AF_XDP ringsBjörn Töpel7-127/+142
Continuing the path to support MEM_TYPE_XSK_BUFF_POOL, the AF_XDP zero-copy/sk_buff rx_bi rings are now separate. Functions to properly allocate the different rings are added as well. v3->v4: Made i40e_fd_handle_status() static. (kbuild test robot) v4->v5: Fix kdoc for i40e_clean_programming_status(). (Jakub) Signed-off-by: Björn Töpel <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Cc: [email protected] Link: https://lore.kernel.org/bpf/[email protected]
2020-05-21i40e: Refactor rx_bi accessesBjörn Töpel2-12/+23
As a first step to migrate i40e to the new MEM_TYPE_XSK_BUFF_POOL APIs, code that accesses the rx_bi (SW/shadow ring) is refactored to use an accessor function. Signed-off-by: Björn Töpel <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Cc: [email protected] Link: https://lore.kernel.org/bpf/[email protected]
2020-05-21xsk: Move driver interface to xdp_sock_drv.hMagnus Karlsson4-4/+4
Move the AF_XDP zero-copy driver interface to its own include file called xdp_sock_drv.h. This, hopefully, will make it more clear for NIC driver implementors to know what functions to use for zero-copy support. v4->v5: Fix -Wmissing-prototypes by include header file. (Jakub) Signed-off-by: Magnus Karlsson <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-05-21igc: Change byte order in struct igc_nfc_filterAndre Guedes2-22/+13
Every time we access the 'etype' and 'vlan_tci' fields from struct igc_nfc_filter to enable or disable filters in hardware we have to convert them from big endian to host order so it makes more sense to simply have these fields in host order. The byte order conversion should take place in igc_ethtool_get_nfc_ rule() and igc_ethtool_add_nfc_rule(), which are called by .get_rxnfc and .set_rxnfc ethtool ops, since ethtool subsystem is the one who deals with them in big endian order. Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-21igc: Align terms used in NFC support codeAndre Guedes3-117/+114
The Network Flow Classification (NFC) support code from IGC driver uses terms such as 'rule', 'filter', 'entry', 'input' interchangeably when referring to NFC rules, making it harder to follow the code. This patch renames IGC's internal APIs, structs, and variables so we stick with the term 'rule' since this is the term used in ethtool APIs. It also removes some not applicable comments along the way. No functionality is changed by this patch. Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-21igc: Add 'igc_ethtool_' prefix to functions in igc_ethtool.cAndre Guedes3-108/+112
This patch adds the prefix 'igc_ethtool_' to all functions defined in igc_ethtool.c so they align with the name convention already followed by other parts of the driver (e.g. igc_tsn, igc_ptp). Also, this avoids some name clashing with functions added to igc_main.c by upcoming patches in this series. No functionality is changed by this patch, just function renaming. Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-21igc: Early return in igc_get_ethtool_nfc_entry()Andre Guedes1-30/+28
This patch re-writes the second half of igc_ethtool_get_nfc_entry() to follow the 'return early' pattern seen in other parts of the driver and removes some duplicate comments. Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-21igc: Cleanup _get|set_rxnfc ethtool opsAndre Guedes1-23/+10
This patch does a trivial change in igc_ethtool_get_rxnfc() and igc_ethtool_set_rxnfc() to simplify their logic. Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-21igc: Get rid of igc_max_channels()Andre Guedes2-13/+3
The local function igc_max_channels() is a pointless wrapper around igc_get_max_rss_queues(). This patch removes it and updates the callers accordingly. It also does some cleanup on igc_get_max_rss_queues(). Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-21igc: Remove unused field from igc_nfc_filterAndre Guedes1-1/+0
The 'cookie' field is not used anywhere in the code so this patch removes it from struct igc_nfc_filter. Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-21igc: Remove per queue good transmited counter registerSasha Neftin1-3/+0
Per queue good transmitted packet counter not applicable for i225 device. This patch comes to clean up this register. Signed-off-by: Sasha Neftin <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-21igc: Remove header redirection registerSasha Neftin1-1/+0
Header redirection missed packet counter not applicable for i225 device. This patch comes to clean up this register. Signed-off-by: Sasha Neftin <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-21igc: Remove obsolete circuit breaker registersSasha Neftin2-11/+0
Part of circuit breaker registers is obsolete and not applicable for i225 device. This patch comes to clean up these registers. Signed-off-by: Sasha Neftin <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-21e1000: Do not perform reset in reset_task if we are already downAlexander Duyck1-4/+14
We are seeing a deadlock in e1000 down when NAPI is being disabled. Looking over the kernel function trace of the system it appears that the interface is being closed and then a reset is hitting which deadlocks the interface as the NAPI interface is already disabled. To prevent this from happening I am disabling the reset task when __E1000_DOWN is already set. In addition code has been added so that we set the __E1000_DOWN while holding the __E1000_RESET flag in e1000_close in order to guarantee that the reset task will not run after we have started the close call. Signed-off-by: Alexander Duyck <[email protected]> Tested-by: Maxim Zhukov <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-21igc: Enable NFC rules based source MAC addressAndre Guedes1-10/+22
This patch adds support for Network Flow Classification (NFC) rules based on source MAC address. Note that the controller doesn't support rules with both source and destination addresses set, so this special case is checked in igc_add_ethtool_nfc_entry(). Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-21igc: Add support for source address filters in coreAndre Guedes4-21/+49
This patch extends MAC address filter internal APIs igc_add_mac_filter() and igc_del_mac_filter(), as well as local helpers, to support filters based on source address. A new parameters 'type' is added to the APIs to indicate if the filter type is source or destination. In case it is source type, the RAH register is configured accordingly in igc_set_mac_filter_hw(). Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-20igc: Remove mac_table from igc_adapterAndre Guedes3-48/+21
In igc_adapter we keep a sort of shadow copy of RAL and RAH registers. There is not much benefit in keeping it, at the cost of maintainability, since adding/removing MAC address filters is not hot path, and we already keep filters information in adapter->nfc_filter_list for cleanup and restoration purposes. So in order to simplify the MAC address filtering code and prepare it for source address support, this patch removes the mac_table from igc_adapter. Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-20igc: Remove IGC_MAC_STATE_SRC_ADDR flagAndre Guedes3-37/+12
MAC address filters based on source address are not currently supported by the IGC driver. Despite of that, the driver have some dangling code to handle it, inherited from IGB driver. This patch removes that code to prepare for a follow up patch that adds proper source MAC address filter support. Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-19igc: Remove unused registersSasha Neftin2-9/+0
Tx data FIFO Head/Tail, Saved and Packet Count registers not applicable for i225 LAN controller. This patch comes to clean up these registers. Signed-off-by: Sasha Neftin <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-19igc: Remove unused IGC_ICS_DRSTA defineSasha Neftin1-1/+0
Device reset assert for interrupt cause register not in use for i225 device. This patch comes to clean up this define. Signed-off-by: Sasha Neftin <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-19igc: Dump ETQF registersAndre Guedes1-0/+3
This patch adds the EType Queue Filter (ETQF) registers to the list of registers dumped by igc_get_regs(). Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-19igc: Refactor ethertype filtering codeAndre Guedes3-61/+103
The whole ethertype filtering code is implemented in igc_ethtool.c and mixes logic from ethtool and core parts. This patch refactors it so core logic is moved to igc_main.c, aligning the ethertype filtering code organization with the rest of the filtering code from the driver (MAC address and VLAN priority). Besides moving code to igc_main.c, this patch also does some minor improvements to the code. Below are some highlights. In case all filters are already in use and the user tries to add another filter, we return -ENOSPC instead of -EINVAL so a more meaningful error code is provided. This also aligns with the behavior implemented in MAC address filtering code. With this code refactoring, 'etype_bitmap' array in struct igc_adapter and 'etype_reg_index' in struct igc_nfc_filter are not needed anymore and are removed. Log messages are added to help debugging the ethertype filtering code. Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-19igc: Fix MAX_ETYPE_FILTER valueAndre Guedes1-1/+1
The I225 controller has 8 ethertype filters, not 4. This patch fixes the MAX_ETYPE_FILTER macro accordingly. Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-19igc: Remove ethertype filter in PTP codeAndre Guedes3-16/+1
The driver only supports hardware timestamping for all incoming traffic (HWTSTAMP_FILTER_ALL) which is enabled via Rx Time Sync Control (TSYNCRXCTL) register already. Therefore, the ethertype filter set in in igc_ptp_set_timestamp_mode() is useless so this patch removes it. Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-19igc: Remove duplicated IGC_RXPBS macroAndre Guedes1-2/+0
This patch remove the IGC_RXPBS macro defined in line 233 since it is already defined in line 18 with the exactly same value. Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-19igc: Refactor VLAN priority filtering codeAndre Guedes3-51/+68
The whole VLAN priority filtering code is implemented in igc_ethtool.c and mixes logic from ethtool and core parts. This patch refactors it so core logic is moved to igc_main.c, aligning the VLAN priority filtering code organization with the MAC address filtering code. This patch also takes the opportunity to add some log messages to ease debugging. Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-19igc: Return -EOPNOTSUPP when VLAN mask doesn't matchAndre Guedes1-1/+2
The I225 controller supports Rx queue assignment based on VLAN priority only. Other Tag Control Information (TCI) are valid, but not supported by the driver. So this patch changes the returning code from igc_add_ ethtool_nfc_entry() to -EOPNOTSUPP in order to provide more meaningful information on why the function failed. It also adds a debug messages to give the user a hint about what went wrong with the NFC setup. Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-19igc: Dump VLANPQF registerAndre Guedes1-0/+2
This patch adds the VLAN Priority Queue Filter Register (VLANPQF) to the list of registers dumped by igc_get_regs(). Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-19igc: Rename IGC_VLAPQF macroAndre Guedes3-16/+15
This patch renames the IGC_VLAPQF macro to IGC_VLANPQF as well as related macros so they match the register name and fields described in the data sheet. Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-19igc: Clean up obsolete NVM definesSasha Neftin1-5/+0
Packet buffer allocation, reserved word and pointer guard not applicable for i225 parts. This patch comes to clean up these obsolete defines Signed-off-by: Sasha Neftin <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-19igc: remove IGC_REMOVED functionVitaly Lifshits3-9/+1
igc driver has leftovers from the previous device that supported Virtualization. This can be found in the function IGC_REMOVED which became obsolete, and can be removed. Signed-off-by: Vitaly Lifshits <[email protected]> Acked-by: Sasha Neftin <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-19igc: Remove PCIe Control registerSasha Neftin1-3/+0
GCR (PCIe Control) register not in use and should be removed This patch clean up this register Signed-off-by: Sasha Neftin <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-18igc: Remove unneeded registerSasha Neftin1-1/+0
Flow control status register not applicable for i225 parts so clean up the unneeded define. Signed-off-by: Sasha Neftin <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-18igc: Remove unneeded definitionSasha Neftin1-1/+0
PHY_FORCE_LIMIT definition not in use and could be removed i225 parts support auto negotiation mechanism Signed-off-by: Sasha Neftin <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-18igc: Use netdev log helpers in igc_base.cAndre Guedes1-3/+3
This patch coverts one pr_debug() call to hw_dbg() in order to keep log output aligned with the rest of the driver. hw_dbg() is actually a macro defined in igc_hw.h that expands to netdev_dbg(). Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-18igc: Use netdev log helpers in igc_dump.cAndre Guedes1-55/+54
In igc_dump.c we print log messages using dev_* and pr_* helpers, generating inconsistent output with the rest of the driver. Since this is a network device driver, we should preferably use netdev_* helpers because they append the interface name to the message, helping making sense out of the logs. This patch converts all dev_* and pr_* calls to netdev_*. Quick note about igc_rings_dump(): This function is always called with valid adapter->netdev so there is not need to check it. Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-18igc: Use netdev log helpers in igc_ptp.cAndre Guedes1-7/+5
In igc_ptp.c we print log messages using dev_* helpers, generating inconsistent output with the rest of the driver. Since this is a network device driver, we should preferably use netdev_* helpers because they append the interface name to the message, helping making sense out of the logs. This patch converts all dev_* calls to netdev_*. Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-18igc: Use netdev log helpers in igc_ethtool.cAndre Guedes1-20/+21
In igc_ethtool.c we print log messages using dev_* helpers, generating inconsistent output with the rest of the driver. Since this is a network device driver, we should preferably use netdev_* helpers because they append the interface name to the message, helping making sense the of the logs. This patch converts all dev_* calls to netdev_*. Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-18igc: add support to eeprom, registers and link self-testsVitaly Lifshits7-3/+285
Introduced igc_diag.c and igc_diag.h, these files have the diagnostics functionality of igc driver. For the time being these files are being used by ethtool self-test callbacks. Which mean that eeprom, registers and link self-tests for ethtool were implemented. Signed-off-by: Vitaly Lifshits <[email protected]> Reported-by: kbuild test robot <[email protected]> Reported-by: Dan Carpenter <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-18igc: Use netdev log helpers in igc_main.cAndre Guedes1-61/+50
In igc_main.c we print log messages using both dev_* and netdev_* helpers, generating inconsistent output. Since this is a network device driver, we should preferably use netdev_* helpers because they append the interface name to the message, helping making sense out of the logs. This patch converts all dev_* calls to netdev_*. There is only two exceptions: 1) calls wihtin igc_probe (net_device has not been registered yet) 2) calls in igc_init_module (module initialization). It also takes this opportunity to improve some messages. Signed-off-by: Andre Guedes <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-18igc: Add ECN support for TSOSasha Neftin1-0/+1
Align with other Intel drivers and add ECN support for TSO. Add NETIF_F_TSO_ECN flag Signed-off-by: Sasha Neftin <[email protected]> Tested-by: Aaron Brown <[email protected]> Signed-off-by: Jeff Kirsher <[email protected]>
2020-05-14xdp: For Intel AF_XDP drivers add XDP frame_szJesper Dangaard Brouer3-0/+6
Intel drivers implement native AF_XDP zerocopy in separate C-files, that have its own invocation of bpf_prog_run_xdp(). The setup of xdp_buff is also handled in separately from normal code path. This patch update XDP frame_sz for AF_XDP zerocopy drivers i40e, ice and ixgbe, as the code changes needed are very similar. Introduce a helper function xsk_umem_xdp_frame_sz() for calculating frame size. Signed-off-by: Jesper Dangaard Brouer <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Acked-by: Björn Töpel <[email protected]> Cc: [email protected] Cc: Magnus Karlsson <[email protected]> Link: https://lore.kernel.org/bpf/158945347511.97035.8536753731329475655.stgit@firesoul
2020-05-14ice: Add XDP frame size to driverJesper Dangaard Brouer1-9/+25
This driver uses different memory models depending on PAGE_SIZE at compile time. For PAGE_SIZE 4K it uses page splitting, meaning for normal MTU frame size is 2048 bytes (and headroom 192 bytes). For larger MTUs the driver still use page splitting, by allocating order-1 pages (8192 bytes) for RX frames. For PAGE_SIZE larger than 4K, driver instead advance its rx_buffer->page_offset with the frame size "truesize". For XDP frame size calculations, this mean that in PAGE_SIZE larger than 4K mode the frame_sz change on a per packet basis. For the page split 4K PAGE_SIZE mode, xdp.frame_sz is more constant and can be updated once outside the main NAPI loop. The default setting in the driver uses build_skb(), which provides the necessary headroom and tailroom for XDP-redirect in RX-frame (in both modes). There is one complication, which is legacy-rx mode (configurable via ethtool priv-flags). There are zero headroom in this mode, which is a requirement for XDP-redirect to work. The conversion to xdp_frame (convert_to_xdp_frame) will detect this insufficient space, and xdp_do_redirect() call will fail. This is deemed acceptable, as it allows other XDP actions to still work in legacy-mode. In legacy-mode + larger PAGE_SIZE due to lacking tailroom, we also accept that xdp_adjust_tail shrink doesn't work. Signed-off-by: Jesper Dangaard Brouer <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Cc: [email protected] Cc: Jeff Kirsher <[email protected]> Cc: Alexander Duyck <[email protected]> Link: https://lore.kernel.org/bpf/158945347002.97035.328088795813704587.stgit@firesoul