aboutsummaryrefslogtreecommitdiff
path: root/sys/dev/ixgbe/ix_txrx.c
Commit message (Collapse)AuthorAgeFilesLines
* if_ixv: disable RSS configuration on 82599 and X540 VFsAndriy Gapon2019-11-051-0/+6
| | | | | | | | | | | | | | | | | | | | It is reported that those VFs share their RSS configuration with PF and, thus, they cannot be configured independently. Also: - add missing opt_rss.h to if_ixv.c, otherwise RSS kernel option could not be seen - do not enable IXGBE_FEATURE_RSS on the older VFs - set flowid / hash type to M_HASHTYPE_NONE or M_HASHTYPE_OPAQUE_HASH (based on what the hardware reports) if IXGBE_FEATURE_RSS is not set Reviewed by: nobody MFC after: 4 weeks Sponsored by: Panzura Differential Revision: https://reviews.freebsd.org/D21705 Notes: svn path=/head/; revision=354349
* ix(4),ixv(4): Fix TSO offloads when TXCSUM is disabledEric Joyner2019-01-311-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch and commit message are based on r340256 created by Jacob Keller: The iflib stack does not disable TSO automatically when TXCSUM is disabled, instead assuming that the driver will correctly handle TSOs even when CSUM_IP is not set. This results in iflib calling ixgbe_isc_txd_encap with packets which have CSUM_IP_TSO, but do not have CSUM_IP or CSUM_IP_TCP set. Because of this, ixgbe_tx_ctx_setup will not setup the IPv4 checksum offloading. This results in bad TSO packets being sent if a user disables TXCSUM without disabling TSO. Fix this by updating the ixgbe_tx_ctx_setup function to check both CSUM_IP and CSUM_IP_TSO when deciding whether to enable checksums. Once this is corrected, another issue for TSO packets is revealed. The driver sets IFLIB_NEED_ZERO_CSUM in order to enable a work around that causes the ip->sum field to be zero'd. This is necessary for ix hardware to correctly perform TSOs. However, if TXCSUM is disabled, then the work around is not enabled, as CSUM_IP will not be set when the iflib stack checks to see if it should clear the sum field. Fix this by adding IFLIB_TSO_INIT_IP to the iflib flags for the ix and ixv interface files. Once both of these changes are made, the ix and ixv drivers should correctly offload TSO packets when TSO offload is enabled, regardless of whether TXCSUM is enabled or disabled. Submitted by: Piotr Pietruszewski <piotr.pietruszewski@intel.com> Reviewed by: IntelNetworking Sponsored by: Intel Corporation Differential Revision: https://reviews.freebsd.org/D18470 Notes: svn path=/head/; revision=343622
* intel iflib drivers: correct initialization of tx_cidx_processedEric Joyner2019-01-241-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | From Jake: In r341156 ("Fix first-packet completion", 2018-11-28) a hack to work around a delta calculation determining how many descriptors were used was added to ixl_isc_tx_credits_update_dwb. The same fix was also applied to the em and igb drivers in r340310, and to ix in r341156. The hack checked the case where prev and cur were equal, and then added one. This works, because by the time we do the delta check, we already know there is at least one packet available, so the delta should be at least one. However, it's not a complete fix, and as indicated by the comment is really a hack to work around the real bug. The real problem is that the first time that we transmit a packet, tx_cidx_processed will be set to point to the start of the ring. Ultimately, the credits_update function expects it to point to the *last* descriptor that was processed. Since we haven't yet processed any descriptors, pointing it to 0 results in this incorrect calculation. Fix the initialization code to have it point to the end of the ring instead. One way to think about this, is that we are setting the value to be one prior to the first available descriptor. Doing so, corrects the delta calculation in all cases. The original fix only works if the first packet has exactly one descriptor. Otherwise, we will report 1 less than the correct value. As part of this fix, also update the MPASS assertions to match the real expectations. First, ensure that prev is not equal to cur, since this should never happen. Second, remove the assertion about prev==0 || delta != 0. It looks like that originated from when the em driver was converted to iflib. It seems like it was supposed to ensure that delta was non-zero. However, because we originally returned 0 delta for the first calculation, the "prev == 0" was tacked on. Instead, replace this with a check that delta is greater than zero, after the correction necessary when the ring pointers wrap around. This new solution should fix the same bug as r341156 did, but in a more robust way. Submitted by: Jacob Keller <jacob.e.keller@intel.com> Reviewed by: shurd@ Sponsored by: Intel Corporation Differential Revision: https://reviews.freebsd.org/D18545 Notes: svn path=/head/; revision=343369
* Fix first-packet completionStephen Hurd2018-11-281-0/+2
| | | | | | | | | | | | | | | | | | | The first packet after the ring is initialized was never completed as isc_txd_credits_update() would not include it in the count of completed packets. This caused netmap to never complete a batch. See PR 233022 for more details. This is the same fix as the r340310 for e1000 PR: 233607 Reported by: lev Reviewed by: lev MFC after: 3 days Sponsored by: Limelight Networks Differential Revision: https://reviews.freebsd.org/D18368 Notes: svn path=/head/; revision=341156
* em/igb/ix(4): Port two Tx/Rx fixes made to ixl in r339338Eric Joyner2018-10-141-13/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | - Fix assert/panic on receive when Jumbo Frames are enabled. From the commit I made to ixl: "It turns out that *_isc_rxd_available is supposed to return how many packets are available to be cleaned on the rx ring. This patch removes a section of code where if the budget argument is 1, the function would return one if there was a descriptor available, not necessarily a packet. This is okay in regular mtu 1500 traffic since the max frame size is less than the configured receive buffer size (2048), but this doesn't work when received packets can span more than one descriptor, as is the case when the mtu is 9000 and the receive buffer size is 4096." - Fix possible Tx hang because *_isc_txd_credits_update returns incorrect result From the commit by Krzysztof Galazka to ixl: "Function isc_txd_update_credits called with clear set to false should return 1 if there are TX descriptors already handled by HW. It was always returning 0 causing troubles with UDP TX traffic." PR: 231659 Reported by: lev@ Approved by: re (gjb@) Sponsored by: Intel Corporation Notes: svn path=/head/; revision=339354
* ix(4), ixv(4): VLAN tag stripping fixes for Amazon EC2 Enhanced NetworkingEric Joyner2018-09-111-1/+2
| | | | | | | | | | | | | | | | | | | | | | | From Piotr: ix(4), ixv(4): Add VLAN tag strip check when receiving packets ixv(4): Fix support for VLAN_HWTAGGING and VLAN_HWFILTER flags This change will prevent driver from passing VLAN tags when interface configuration is not expecting them. VF driver will check for VLAN_HWTAGGING and VLAN_HWFILTER flags and act adequately. This patch resolves problem occuring on EC2 platforms. Submitted by: Piotr Pietruszewski <piotr.pietruszewski@intel.com> Reported by: cperciva@ Reviewed by: cperciva@, Intel Networking Approved by: re Sponsored by: Intel Corporation Differential Revision: https://reviews.freebsd.org/D17061 Notes: svn path=/head/; revision=338593
* netmap and iflib drivers, silence unused var warningsMatt Macy2018-05-191-0/+1
| | | | Notes: svn path=/head/; revision=333870
* Use C99 initializers for iflib function tables.Mark Johnston2018-04-111-8/+8
| | | | | | | | | Reviewed by: sbruno MFC after: 1 week Differential Revision: https://reviews.freebsd.org/D15041 Notes: svn path=/head/; revision=332409
* ixgbe(4): Convert driver to use iflibEric Joyner2017-12-201-1994/+341
| | | | | | | | | | | | | | | | | Initial update to the ixgbe PF and VF drivers to support the iflib interface. The PF driver version is bumped to 4.0.0, and the VF driver version is bumped to 2.0.0. Special thanks to sbruno@ for the support in helping make this conversion happen. Submitted by: Jeb Cramer <cramerj@intel.com>, Krzysztof Galazka (Chris) <krzysztof.galazka@intel.com>, Piotr Pietruszewski <piotr.pietruszewski@intel.com> Reviewed by: sbruno@, shurd@, #IntelNetworking Tested by: Jeffrey Pieper <jeffrey.e.pieper@intel.com>, Sergey Kozlov <kozlov.sergey.404@gmail.com> Sponsored by: Limelight Networks, Intel Corporation Differential Revision: https://reviews.freebsd.org/D11727 Notes: svn path=/head/; revision=327031
* Drop ixgbe RX lock during TCP_LRO processing. This eliminates a "storm"Sean Bruno2017-07-251-4/+4
| | | | | | | | | | | of LOR detection and a bit of lock release/acquire collision when using LRO. Submitted by: Kevin Bowling <kevin.bowling@kev009.com> MFC after: 2 days Differential Revision: https://reviews.freebsd.org/D11712 Notes: svn path=/head/; revision=321476
* ixgbe(4): Update HEAD (p3) to 3.2.12-kEric Joyner2017-07-051-847/+755
| | | | | | | | | | | | | | | | | | | Includes: - Support for X550EM devices. - Support for Bypass adapters. - Flow Director code moved to separate files - SR-IOV code moved to separate files - Netmap code moved to separate files Differential Revision: https://reviews.freebsd.org/D11232 Submitted by: Jeb Cramer <cramerj@intel.com> Reviewed by: erj@ Tested by: Jeff Pieper <jeffrey.e.pieper@intel.com> Sponsored by: Intel Corporation Notes: svn path=/head/; revision=320688
* Fix a double free in ixgbe_rxeof()Sean Bruno2017-04-051-21/+9
| | | | | | | | | Submitted by: rstone MFC after: 1 week Differential Revision: https://reviews.freebsd.org/D10255 Notes: svn path=/head/; revision=316541
* net: Use M_HASHTYPE_OPAQUE_HASH if the mbuf flowid has hash propertiesSepherosa Ziehau2016-06-071-1/+1
| | | | | | | | | Reviewed by: hps, erj, tuexen Sponsored by: Microsoft OSTC Differential Revision: https://reviews.freebsd.org/D6688 Notes: svn path=/head/; revision=301538
* Correct possible underflow conditions when checking for available spaceSean Bruno2016-04-181-1/+1
| | | | | | | | | | | | in the tx h/w ring buffer. Reviewed by: gnn jeb.j.cramer@intel.com MFC after: 1 week Sponsored by: Limelight Networks Differential Revision: https://reviews.freebsd.org/D5918 Notes: svn path=/head/; revision=298224
* tcp/lro: Use tcp_lro_flush_all in device drivers to avoid code duplicationSepherosa Ziehau2016-04-011-5/+1
| | | | | | | | | | | | And factor out tcp_lro_rx_done, which deduplicates the same logic with netinet/tcp_lro.c Reviewed by: gallatin (1st version), hps, zbb, np, Dexuan Cui <decui microsoft com> Sponsored by: Microsoft OSTC Differential Revision: https://reviews.freebsd.org/D5725 Notes: svn path=/head/; revision=297482
* Add missing #ifdef INET after r292674 to allow NOIP and NOINET kernelsBjoern A. Zeeb2015-12-261-0/+2
| | | | | | | to build. Notes: svn path=/head/; revision=292751
* Fix NO INET6 build broken at svn r292674Sean Bruno2015-12-241-0/+2
| | | | | | | Reported by: ohartman@zedat.fu-berlin.de Notes: svn path=/head/; revision=292697
* ixgbe(4): Update to version 3.1.13-kSean Bruno2015-12-231-66/+67
| | | | | | | | | | | | | Add support for two new devices: X552 SFP+ 10 GbE, and the single port version of X550T. Submitted by: erj Reviewed by: gnn Sponsored by: Intel Corporation Differential Revision: https://reviews.freebsd.org/D4186 Notes: svn path=/head/; revision=292674
* Add support for sysctl knobs to live tune the per interrupt rx/tx packetSean Bruno2015-10-131-3/+3
| | | | | | | | | | | processing limits in ixgbe(4) Differential Revision: https://reviews.freebsd.org/D3719 Submitted by: jason wolfe (j-nitrology.com) MFC after: 2 weeks Notes: svn path=/head/; revision=289238
* Remove FreeBSD version check for deprecated M_FLOWID.Hiren Panchasara2015-07-151-4/+0
| | | | | | | | Reviewed by: erj Sponsored by: Limelight Networks Notes: svn path=/head/; revision=285591
* Expose full 32bit RSS hash from card regardless of whether RSS is defined orHiren Panchasara2015-07-141-45/+52
| | | | | | | | | | | | | | | | not. When doing multiqueue, we are all setup to have full 32bit RSS hash from the card. We do not need to hide that under "ifdef RSS" and should expose that by default so others like lagg(4) can use that and avoid hashing the traffic by themselves. While here, delete the FreeBSD version check and use of deprecated M_FLOWID. Reviewed by: adrian, erj MFC after: 1 week Sponsored by: Limelight Networks Notes: svn path=/head/; revision=285528
* Delta D2489 - Add SRIOV support to the Intel 10G driver.Jack F Vogel2015-06-011-9/+24
| | | | | | | | | | NOTE: This is a technology preview, while it has undergone development testing, Intel has not yet completed full validation of the feature. It is being integrated for early access and customer testing. Notes: svn path=/head/; revision=283883
* Revert last commit, to remove added skeleton tree.Jack F Vogel2015-06-011-24/+9
| | | | Notes: svn path=/head/; revision=283882
* Delta D2489 - Add SRIOV support to the Intel 10G driver.Jack F Vogel2015-06-011-9/+24
| | | | | | | | | NOTE: This is a technology preview, while it has undergone development tests, Intel has not yet completed full validation of the feature. It is being integrated for early access and customer testing. Notes: svn path=/head/; revision=283881
* Add support for certain Intel X550 devices.Eric Joyner2015-04-301-20/+37
| | | | | | | | | | | | | | | These include standalone X550 adapters, X552 10GbE backplane, and X552/X557-AT 10GBASE-T; with the latter two being integrated into Xeon D SoCs. As well, this bumps the ixgbe version number to 2.8.3, and includes updates to shared code for support for the new devices. Differential Revision: D2414 Reviewed by: gnn, adrian Approved by: jfv (mentor), gnn (mentor) Notes: svn path=/head/; revision=282289
* Make changes to busdma code in tx/rx path similar to the ones made in r257541.Eric Joyner2015-04-011-4/+3
| | | | | | | | | | | | | - bus_dmamap_create() does not take the BUS_DMA_NOWAIT flag - properly unload maps - do not assign NULL to dma map pointers Submitted by: Konstantin Belousov <kostikbel@gmail.com> Approved by: jfv (mentor) MFC after: 1 week Notes: svn path=/head/; revision=280962
* Fix building ixgbe with gcc, it doesn't like nested extern declarations.Andrew Turner2015-03-191-1/+2
| | | | | | | | The fix is to move the extern declaration ix_crcstrip out of ixgbe_setup_hw_rsc. Notes: svn path=/head/; revision=280252
* Fix ixgbe(4) to compile - with RSS; with ix+ixv in the kernel.Adrian Chadd2015-03-181-0/+1
| | | | | | | | | | | | | | | | | | * Fix the multiple same-named devclasses; the duplicate name trips up the linker. * Re-do the taskqueue stuff to use the new cpuset API, not the old pinned API. * Add includes for the new location of the RSS configuration routines. This allows ixgbe to compile as a module /and/ linked into the kernel, along with RSS working. Sponsored by: Norse Corp, Inc. Notes: svn path=/head/; revision=280204
* Resolve a few build issues, add module directories back into Makefile,Jack F Vogel2015-03-171-0/+7
| | | | | | | | then correct a NETMAP problem resulting from the split, and finally temporarily disable the X550 functionality. Notes: svn path=/head/; revision=280197
* Update to the Intel ixgbe driver:Jack F Vogel2015-03-171-0/+2259
- Split the driver into independent pf and vf loadables. This is in preparation for SRIOV support which will be following shortly. This also allows us to keep a seperate revision control over the two parts, making for easier sustaining. - Make the TX/RX code a shared/seperated file, in the old code base the ixv code would miss fixes that went into ixgbe, this model will eliminate that problem. - The driver loadables will now match the device names, something that has been requested for some time. - Rather than a modules/ixgbe there is now modules/ix and modules/ixv - It will also be possible to make your static kernel with only one or the other for streamlined installs, or both. Enjoy! Submitted by: jfv and erj Notes: svn path=/head/; revision=280182
generated by cgit v1.3 (git 2.53.0) at 2026-04-09 22:10:27 +0000