summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/intel/ice/ice_xsk.c
AgeCommit message (Collapse)AuthorFilesLines
2025-02-10ice: use generic unrolled_count() macroAlexander Lobakin1-1/+3
ice, same as i40e, has a custom loop unrolling macros for unrolling Tx descriptors filling on XSk xmit. Replace ice defs with generic unrolled_count(), which is also more convenient as it allows passing defines as its argument, not hardcoded values, while the loop declaration will still be usual for-loop. Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com> Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Link: https://patch.msgid.link/20250206182630.3914318-4-aleksander.lobakin@intel.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-12-19xsk: make xsk_buff_add_frag() really add the frag via __xdp_buff_add_frag()Alexander Lobakin1-30/+2
Currently, xsk_buff_add_frag() only adds the frag to pool's linked list, not doing anything with the &xdp_buff. The drivers do that manually and the logic is the same. Make it really add an skb frag, just like xdp_buff_add_frag() does that, and freeing frags on error if needed. This allows to remove repeating code from i40e and ice and not add the same code again and again. Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com> Link: https://patch.msgid.link/20241218174435.1445282-5-aleksander.lobakin@intel.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-09-06ice: add new VSI type for subfunctionsPiotr Raczynski1-1/+1
Add required plumbing for new VSI type dedicated to devlink subfunctions. Make sure that the vsi is properly configured and destroyed. Also allow loading XDP and AF_XDP sockets. The first implementation of devlink subfunctions supports only one Tx/Rx queue pair per given subfunction. Reviewed-by: Simon Horman <horms@kernel.org> Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com> Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com> Signed-off-by: Piotr Raczynski <piotr.raczynski@intel.com> Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com> Tested-by: Rafal Romanowski <rafal.romanowski@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2024-09-03ice: remove ICE_CFG_BUSY locking from AF_XDP codeLarysa Zaremba1-9/+0
Locking used in ice_qp_ena() and ice_qp_dis() does pretty much nothing, because ICE_CFG_BUSY is a state flag that is supposed to be set in a PF state, not VSI one. Therefore it does not protect the queue pair from e.g. reset. Remove ICE_CFG_BUSY locking from ice_qp_dis() and ice_qp_ena(). Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com> Reviewed-by: Jacob Keller <jacob.e.keller@intel.com> Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2024-09-03ice: check for XDP rings instead of bpf program when unconfiguringLarysa Zaremba1-3/+3
If VSI rebuild is pending, .ndo_bpf() can attach/detach the XDP program on VSI without applying new ring configuration. When unconfiguring the VSI, we can encounter the state in which there is an XDP program but no XDP rings to destroy or there will be XDP rings that need to be destroyed, but no XDP program to indicate their presence. When unconfiguring, rely on the presence of XDP rings rather then XDP program, as they better represent the current state that has to be destroyed. Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com> Reviewed-by: Jacob Keller <jacob.e.keller@intel.com> Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2024-09-03ice: protect XDP configuration with a mutexLarysa Zaremba1-1/+2
The main threat to data consistency in ice_xdp() is a possible asynchronous PF reset. It can be triggered by a user or by TX timeout handler. XDP setup and PF reset code access the same resources in the following sections: * ice_vsi_close() in ice_prepare_for_reset() - already rtnl-locked * ice_vsi_rebuild() for the PF VSI - not protected * ice_vsi_open() - already rtnl-locked With an unfortunate timing, such accesses can result in a crash such as the one below: [ +1.999878] ice 0000:b1:00.0: Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring 14 [ +2.002992] ice 0000:b1:00.0: Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring 18 [Mar15 18:17] ice 0000:b1:00.0 ens801f0np0: NETDEV WATCHDOG: CPU: 38: transmit queue 14 timed out 80692736 ms [ +0.000093] ice 0000:b1:00.0 ens801f0np0: tx_timeout: VSI_num: 6, Q 14, NTC: 0x0, HW_HEAD: 0x0, NTU: 0x0, INT: 0x4000001 [ +0.000012] ice 0000:b1:00.0 ens801f0np0: tx_timeout recovery level 1, txqueue 14 [ +0.394718] ice 0000:b1:00.0: PTP reset successful [ +0.006184] BUG: kernel NULL pointer dereference, address: 0000000000000098 [ +0.000045] #PF: supervisor read access in kernel mode [ +0.000023] #PF: error_code(0x0000) - not-present page [ +0.000023] PGD 0 P4D 0 [ +0.000018] Oops: 0000 [#1] PREEMPT SMP NOPTI [ +0.000023] CPU: 38 PID: 7540 Comm: kworker/38:1 Not tainted 6.8.0-rc7 #1 [ +0.000031] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0014.082620210524 08/26/2021 [ +0.000036] Workqueue: ice ice_service_task [ice] [ +0.000183] RIP: 0010:ice_clean_tx_ring+0xa/0xd0 [ice] [...] [ +0.000013] Call Trace: [ +0.000016] <TASK> [ +0.000014] ? __die+0x1f/0x70 [ +0.000029] ? page_fault_oops+0x171/0x4f0 [ +0.000029] ? schedule+0x3b/0xd0 [ +0.000027] ? exc_page_fault+0x7b/0x180 [ +0.000022] ? asm_exc_page_fault+0x22/0x30 [ +0.000031] ? ice_clean_tx_ring+0xa/0xd0 [ice] [ +0.000194] ice_free_tx_ring+0xe/0x60 [ice] [ +0.000186] ice_destroy_xdp_rings+0x157/0x310 [ice] [ +0.000151] ice_vsi_decfg+0x53/0xe0 [ice] [ +0.000180] ice_vsi_rebuild+0x239/0x540 [ice] [ +0.000186] ice_vsi_rebuild_by_type+0x76/0x180 [ice] [ +0.000145] ice_rebuild+0x18c/0x840 [ice] [ +0.000145] ? delay_tsc+0x4a/0xc0 [ +0.000022] ? delay_tsc+0x92/0xc0 [ +0.000020] ice_do_reset+0x140/0x180 [ice] [ +0.000886] ice_service_task+0x404/0x1030 [ice] [ +0.000824] process_one_work+0x171/0x340 [ +0.000685] worker_thread+0x277/0x3a0 [ +0.000675] ? preempt_count_add+0x6a/0xa0 [ +0.000677] ? _raw_spin_lock_irqsave+0x23/0x50 [ +0.000679] ? __pfx_worker_thread+0x10/0x10 [ +0.000653] kthread+0xf0/0x120 [ +0.000635] ? __pfx_kthread+0x10/0x10 [ +0.000616] ret_from_fork+0x2d/0x50 [ +0.000612] ? __pfx_kthread+0x10/0x10 [ +0.000604] ret_from_fork_asm+0x1b/0x30 [ +0.000604] </TASK> The previous way of handling this through returning -EBUSY is not viable, particularly when destroying AF_XDP socket, because the kernel proceeds with removal anyway. There is plenty of code between those calls and there is no need to create a large critical section that covers all of them, same as there is no need to protect ice_vsi_rebuild() with rtnl_lock(). Add xdp_state_lock mutex to protect ice_vsi_rebuild() and ice_xdp(). Leaving unprotected sections in between would result in two states that have to be considered: 1. when the VSI is closed, but not yet rebuild 2. when VSI is already rebuild, but not yet open The latter case is actually already handled through !netif_running() case, we just need to adjust flag checking a little. The former one is not as trivial, because between ice_vsi_close() and ice_vsi_rebuild(), a lot of hardware interaction happens, this can make adding/deleting rings exit with an error. Luckily, VSI rebuild is pending and can apply new configuration for us in a managed fashion. Therefore, add an additional VSI state flag ICE_VSI_REBUILD_PENDING to indicate that ice_xdp() can just hot-swap the program. Also, as ice_vsi_rebuild() flow is touched in this patch, make it more consistent by deconfiguring VSI when coalesce allocation fails. Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Fixes: efc2214b6047 ("ice: Add support for XDP") Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com> Reviewed-by: Jacob Keller <jacob.e.keller@intel.com> Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com> Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2024-07-29ice: xsk: fix txq interrupt mappingMaciej Fijalkowski1-10/+14
ice_cfg_txq_interrupt() internally handles XDP Tx ring. Do not use ice_for_each_tx_ring() in ice_qvec_cfg_msix() as this causing us to treat XDP ring that belongs to queue vector as Tx ring and therefore misconfiguring the interrupts. Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Reviewed-by: Shannon Nelson <shannon.nelson@amd.com> Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel) Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2024-07-29ice: improve updating ice_{t,r}x_ring::xsk_poolMaciej Fijalkowski1-39/+64
xsk_buff_pool pointers that ice ring structs hold are updated via ndo_bpf that is executed in process context while it can be read by remote CPU at the same time within NAPI poll. Use synchronize_net() after pointer update and {READ,WRITE}_ONCE() when working with mentioned pointer. Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Reviewed-by: Shannon Nelson <shannon.nelson@amd.com> Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel) Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2024-07-29ice: toggle netif_carrier when setting up XSK poolMaciej Fijalkowski1-1/+7
This so we prevent Tx timeout issues. One of conditions checked on running in the background dev_watchdog() is netif_carrier_ok(), so let us turn it off when we disable the queues that belong to a q_vector where XSK pool is being configured. Turn carrier on in ice_qp_ena() only when ice_get_link_status() tells us that physical link is up. Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Reviewed-by: Shannon Nelson <shannon.nelson@amd.com> Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel) Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2024-07-29ice: modify error handling when setting XSK pool in ndo_bpfMaciej Fijalkowski1-14/+16
Don't bail out right when spotting an error within ice_qp_{dis,ena}() but rather track error and go through whole flow of disabling and enabling queue pair. Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Reviewed-by: Shannon Nelson <shannon.nelson@amd.com> Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel) Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2024-07-29ice: replace synchronize_rcu with synchronize_netMaciej Fijalkowski1-5/+4
Given that ice_qp_dis() is called under rtnl_lock, synchronize_net() can be called instead of synchronize_rcu() so that XDP rings can finish its job in a faster way. Also let us do this as earlier in XSK queue disable flow. Additionally, turn off regular Tx queue before disabling irqs and NAPI. Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Reviewed-by: Shannon Nelson <shannon.nelson@amd.com> Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel) Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2024-07-29ice: don't busy wait for Rx queue disable in ice_qp_dis()Maciej Fijalkowski1-3/+1
When ice driver is spammed with multiple xdpsock instances and flow control is enabled, there are cases when Rx queue gets stuck and unable to reflect the disable state in QRX_CTRL register. Similar issue has previously been addressed in commit 13a6233b033f ("ice: Add support to enable/disable all Rx queues before waiting"). To workaround this, let us simply not wait for a disabled state as later patch will make sure that regardless of the encountered error in the process of disabling a queue pair, the Rx queue will be enabled. Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Reviewed-by: Shannon Nelson <shannon.nelson@amd.com> Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel) Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2024-07-29ice: respect netif readiness in AF_XDP ZC related ndo'sMichal Kubiak1-1/+5
Address a scenario in which XSK ZC Tx produces descriptors to XDP Tx ring when link is either not yet fully initialized or process of stopping the netdev has already started. To avoid this, add checks against carrier readiness in ice_xsk_wakeup() and in ice_xmit_zc(). One could argue that bailing out early in ice_xsk_wakeup() would be sufficient but given the fact that we produce Tx descriptors on behalf of NAPI that is triggered for Rx traffic, the latter is also needed. Bringing link up is an asynchronous event executed within ice_service_task so even though interface has been brought up there is still a time frame where link is not yet ok. Without this patch, when AF_XDP ZC Tx is used simultaneously with stack Tx, Tx timeouts occur after going through link flap (admin brings interface down then up again). HW seem to be unable to transmit descriptor to the wire after HW tail register bump which in turn causes bit __QUEUE_STATE_STACK_XOFF to be set forever as netdev_tx_completed_queue() sees no cleaned bytes on the input. Fixes: 126cdfe1007a ("ice: xsk: Improve AF_XDP ZC Tx and use batching API") Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Reviewed-by: Shannon Nelson <shannon.nelson@amd.com> Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel) Signed-off-by: Michal Kubiak <michal.kubiak@intel.com> Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2024-06-05ice: remove af_xdp_zc_qps bitmapLarysa Zaremba1-7/+6
Referenced commit has introduced a bitmap to distinguish between ZC and copy-mode AF_XDP queues, because xsk_get_pool_from_qid() does not do this for us. The bitmap would be especially useful when restoring previous state after rebuild, if only it was not reallocated in the process. This leads to e.g. xdpsock dying after changing number of queues. Instead of preserving the bitmap during the rebuild, remove it completely and distinguish between ZC and copy-mode queues based on the presence of a device associated with the pool. Fixes: e102db780e1c ("ice: track AF_XDP ZC enabled queues in bitmap") Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com> Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com> Reviewed-by: Simon Horman <horms@kernel.org> Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> Link: https://lore.kernel.org/r/20240603-net-2024-05-30-intel-net-fixes-v2-3-e3563aa89b0c@intel.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-05-20Merge tag 'dma-mapping-6.10-2024-05-20' of ↵Linus Torvalds1-1/+1
git://git.infradead.org/users/hch/dma-mapping Pull dma-mapping updates from Christoph Hellwig: - optimize DMA sync calls when they are no-ops (Alexander Lobakin) - fix swiotlb padding for untrusted devices (Michael Kelley) - add documentation for swiotb (Michael Kelley) * tag 'dma-mapping-6.10-2024-05-20' of git://git.infradead.org/users/hch/dma-mapping: dma: fix DMA sync for drivers not calling dma_set_mask*() xsk: use generic DMA sync shortcut instead of a custom one page_pool: check for DMA sync shortcut earlier page_pool: don't use driver-set flags field directly page_pool: make sure frag API fields don't span between cachelines iommu/dma: avoid expensive indirect calls for sync operations dma: avoid redundant calls for sync operations dma: compile-out DMA sync op calls when not used iommu/dma: fix zeroing of bounce buffer padding used by untrusted devices swiotlb: remove alloc_size argument to swiotlb_tbl_map_single() Documentation/core-api: add swiotlb documentation
2024-05-08xsk: use generic DMA sync shortcut instead of a custom oneAlexander Lobakin1-1/+1
XSk infra's been using its own DMA sync shortcut to try avoiding redundant function calls. Now that there is a generic one, remove the custom implementation and rely on the generic helpers. xsk_buff_dma_sync_for_cpu() doesn't need the second argument anymore, remove it. Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
2024-03-28net: remove gfp_mask from napi_alloc_skb()Jakub Kicinski1-2/+1
__napi_alloc_skb() is napi_alloc_skb() with the added flexibility of choosing gfp_mask. This is a NAPI function, so GFP_ATOMIC is implied. The only practical choice the caller has is whether to set __GFP_NOWARN. But that's a false choice, too, allocation failures in atomic context will happen, and printing warnings in logs, effectively for a packet drop, is both too much and very likely non-actionable. This leads me to a conclusion that most uses of napi_alloc_skb() are simply misguided, and should use __GFP_NOWARN in the first place. We also have a "standard" way of reporting allocation failures via the queue stat API (qstats::rx-alloc-fail). The direct motivation for this patch is that one of the drivers used at Meta calls napi_alloc_skb() (so prior to this patch without __GFP_NOWARN), and the resulting OOM warning is the top networking warning in our fleet. Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com> Reviewed-by: Simon Horman <horms@kernel.org> Reviewed-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20240327040213.3153864-1-kuba@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-03-07Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/netJakub Kicinski1-4/+5
Cross-merge networking fixes after downstream PR. No conflicts. Adjacent changes: net/core/page_pool_user.c 0b11b1c5c320 ("netdev: let netlink core handle -EMSGSIZE errors") 429679dcf7d9 ("page_pool: fix netlink dump stop/resume") Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-03-01ice: reorder disabling IRQ and NAPI in ice_qp_disMaciej Fijalkowski1-4/+5
ice_qp_dis() currently does things in very mixed way. Tx is stopped before disabling IRQ on related queue vector, then it takes care of disabling Rx and finally NAPI is disabled. Let us start with disabling IRQs in the first place followed by turning off NAPI. Then it is safe to handle queues. One subtle change on top of that is that even though ice_qp_ena() looks more sane, clear ICE_CFG_BUSY as the last thing there. Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel) Acked-by: Magnus Karlsson <magnus.karlsson@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2024-02-02ice: make ice_vsi_cfg_txq() staticMaciej Fijalkowski1-17/+3
Currently, XSK control path in ice driver calls directly ice_vsi_cfg_txq() whereas we have ice_vsi_cfg_single_txq() for that purpose. Use the latter from XSK side and make ice_vsi_cfg_txq() static. ice_vsi_cfg_txq() resides in ice_base.c and is rather big, so to reduce the code churn let us move the callers of it from ice_lib.c to ice_base.c. This change puts ice_qp_ena() on nice diet due to the checks and operations that ice_vsi_cfg_single_{r,t}xq() do internally. add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-182 (-182) Function old new delta ice_xsk_pool_setup 2165 1983 -182 Total: Before=472597, After=472415, chg -0.04% Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Acked-by: Magnus Karlsson <magnus.karlsson@intel.com> Reviewed-by: Simon Horman <horms@kernel.org> Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2024-02-02ice: make ice_vsi_cfg_rxq() staticMaciej Fijalkowski1-1/+1
Currently, XSK control path in ice driver calls directly ice_vsi_cfg_rxq() whereas we have ice_vsi_cfg_single_rxq() for that purpose. Use the latter from XSK side and make ice_vsi_cfg_rxq() static. ice_vsi_cfg_rxq() resides in ice_base.c and is rather big, so to reduce the code churn let us move two callers of it from ice_lib.c to ice_base.c. Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Acked-by: Magnus Karlsson <magnus.karlsson@intel.com> Reviewed-by: Simon Horman <horms@kernel.org> Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2024-01-24intel: xsk: initialize skb_frag_t::bv_offset in ZC driversMaciej Fijalkowski1-1/+2
Ice and i40e ZC drivers currently set offset of a frag within skb_shared_info to 0, which is incorrect. xdp_buffs that come from xsk_buff_pool always have 256 bytes of a headroom, so they need to be taken into account to retrieve xdp_buff::data via skb_frag_address(). Otherwise, bpf_xdp_frags_increase_tail() would be starting its job from xdp_buff::data_hard_start which would result in overwriting existing payload. Fixes: 1c9ba9c14658 ("i40e: xsk: add RX multi-buffer support") Fixes: 1bbc04de607b ("ice: xsk: add RX multi-buffer support") Acked-by: Magnus Karlsson <magnus.karlsson@intel.com> Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Link: https://lore.kernel.org/r/20240124191602.566724-8-maciej.fijalkowski@intel.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2024-01-24xsk: make xsk_buff_pool responsible for clearing xdp_buff::flagsMaciej Fijalkowski1-1/+0
XDP multi-buffer support introduced XDP_FLAGS_HAS_FRAGS flag that is used by drivers to notify data path whether xdp_buff contains fragments or not. Data path looks up mentioned flag on first buffer that occupies the linear part of xdp_buff, so drivers only modify it there. This is sufficient for SKB and XDP_DRV modes as usually xdp_buff is allocated on stack or it resides within struct representing driver's queue and fragments are carried via skb_frag_t structs. IOW, we are dealing with only one xdp_buff. ZC mode though relies on list of xdp_buff structs that is carried via xsk_buff_pool::xskb_list, so ZC data path has to make sure that fragments do *not* have XDP_FLAGS_HAS_FRAGS set. Otherwise, xsk_buff_free() could misbehave if it would be executed against xdp_buff that carries a frag with XDP_FLAGS_HAS_FRAGS flag set. Such scenario can take place when within supplied XDP program bpf_xdp_adjust_tail() is used with negative offset that would in turn release the tail fragment from multi-buffer frame. Calling xsk_buff_free() on tail fragment with XDP_FLAGS_HAS_FRAGS would result in releasing all the nodes from xskb_list that were produced by driver before XDP program execution, which is not what is intended - only tail fragment should be deleted from xskb_list and then it should be put onto xsk_buff_pool::free_list. Such multi-buffer frame will never make it up to user space, so from AF_XDP application POV there would be no traffic running, however due to free_list getting constantly new nodes, driver will be able to feed HW Rx queue with recycled buffers. Bottom line is that instead of traffic being redirected to user space, it would be continuously dropped. To fix this, let us clear the mentioned flag on xsk_buff_pool side during xdp_buff initialization, which is what should have been done right from the start of XSK multi-buffer support. Fixes: 1bbc04de607b ("ice: xsk: add RX multi-buffer support") Fixes: 1c9ba9c14658 ("i40e: xsk: add RX multi-buffer support") Fixes: 24ea50127ecf ("xsk: support mbuf on ZC RX") Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Link: https://lore.kernel.org/r/20240124191602.566724-3-maciej.fijalkowski@intel.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-12-13ice: Implement VLAN tag hintLarysa Zaremba1-3/+3
Implement .xmo_rx_vlan_tag callback to allow XDP code to read packet's VLAN tag. At the same time, use vlan_tci instead of vlan_tag in touched code, because VLAN tag often refers to VLAN proto and VLAN TCI combined, while in the code we clearly store only VLAN TCI. Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com> Link: https://lore.kernel.org/r/20231205210847.28460-11-larysa.zaremba@intel.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-12-13ice: Support XDP hints in AF_XDP ZC modeLarysa Zaremba1-0/+5
In AF_XDP ZC, xdp_buff is not stored on ring, instead it is provided by xsk_buff_pool. Space for metadata sources right after such buffers was already reserved in commit 94ecc5ca4dbf ("xsk: Add cb area to struct xdp_buff_xsk"). Some things (such as pointer to packet context) do not change on a per-packet basis, so they can be set at the same time as RX queue info. On the other hand, RX descriptor is unique for each packet, but is already known when setting DMA addresses. This minimizes performance impact of hints on regular packet processing. Update AF_XDP ZC packet processing to support XDP hints. Co-developed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com> Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Link: https://lore.kernel.org/r/20231205210847.28460-9-larysa.zaremba@intel.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-12-13ice: Make ptype internal to descriptor info processingLarysa Zaremba1-5/+1
Currently, rx_ptype variable is used only as an argument to ice_process_skb_fields() and is computed just before the function call. Therefore, there is no reason to pass this value as an argument. Instead, remove this argument and compute the value directly inside ice_process_skb_fields() function. Also, separate its calculation into a short function, so the code can later be reused in .xmo_() callbacks. Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com> Link: https://lore.kernel.org/r/20231205210847.28460-4-larysa.zaremba@intel.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-10-03ice: make use of DEFINE_FLEX() for struct ice_aqc_add_tx_qgrpPrzemek Kitszel1-14/+8
Use DEFINE_FLEX() macro for 1-elem flex array use case of struct ice_aqc_add_tx_qgrp. Signed-off-by: Przemek Kitszel <przemyslaw.kitszel@intel.com> Link: https://lore.kernel.org/r/20230912115937.1645707-6-przemyslaw.kitszel@intel.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-07-19ice: xsk: Tx multi-buffer supportMaciej Fijalkowski1-23/+60
Most of this patch is about actually supporting XDP_TX action. Pure Tx ZC support is only about looking at XDP_PKT_CONTD presence at options field and based on that generating EOP bit on Tx HW descriptor. This is that simple due to the implementation on xsk_tx_peek_release_desc_batch() where we are making sure that last produced descriptor is an EOP one. Overwrite xdp_zc_max_segs with a value that defines max scatter-gatter count on Tx side that HW can handle. Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Link: https://lore.kernel.org/r/20230719132421.584801-16-maciej.fijalkowski@intel.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-07-19ice: xsk: add RX multi-buffer supportMaciej Fijalkowski1-35/+101
This support is strongly inspired by work that introduced multi-buffer support to regular Rx data path in ice. There are some differences, though. When adding a frag, besides adding it to skb_shared_info, use also fresh xsk_buff_add_frag() helper. Reason for doing both things is that we can not rule out the fact that AF_XDP pipeline could use XDP program that needs to access frame fragments. Without them being in skb_shared_info it will not be possible. Another difference is that XDP_PASS has to allocate a new pages for each frags and copy contents from memory backed by xsk_buff_pool. chain_len that is used for programming HW Rx descriptors no longer has to be limited to 1 when xsk_pool is present - remove this restriction. Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Link: https://lore.kernel.org/r/20230719132421.584801-13-maciej.fijalkowski@intel.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-05-16ice: add individual interrupt allocationPiotr Raczynski1-4/+1
Currently interrupt allocations, depending on a feature are distributed in batches. Also, after allocation there is a series of operations that distributes per irq settings through that batch of interrupts. Although driver does not yet support dynamic interrupt allocation, keep allocated interrupts in a pool and add allocation abstraction logic to make code more flexible. Keep per interrupt information in the ice_q_vector structure, which yields ice_vsi::base_vector redundant. Also, as a result there are a few functions that can be removed. Reviewed-by: Jacob Keller <jacob.e.keller@intel.com> Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel) Signed-off-by: Piotr Raczynski <piotr.raczynski@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2023-05-16ice: use pci_irq_vector helper functionPiotr Raczynski1-1/+1
Currently, driver gets interrupt number directly from ice_pf::msix_entries array. Use helper function dedicated to do just that. While at it use a variable to store interrupt number in ice_free_irq_msix_misc instead of calling the helper function twice. Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel) Signed-off-by: Piotr Raczynski <piotr.raczynski@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2023-03-16ice: xsk: disable txq irq before flushing hwMaciej Fijalkowski1-3/+2
ice_qp_dis() intends to stop a given queue pair that is a target of xsk pool attach/detach. One of the steps is to disable interrupts on these queues. It currently is broken in a way that txq irq is turned off *after* HW flush which in turn takes no effect. ice_qp_dis(): -> ice_qvec_dis_irq() --> disable rxq irq --> flush hw -> ice_vsi_stop_tx_ring() -->disable txq irq Below splat can be triggered by following steps: - start xdpsock WITHOUT loading xdp prog - run xdp_rxq_info with XDP_TX action on this interface - start traffic - terminate xdpsock [ 256.312485] BUG: kernel NULL pointer dereference, address: 0000000000000018 [ 256.319560] #PF: supervisor read access in kernel mode [ 256.324775] #PF: error_code(0x0000) - not-present page [ 256.329994] PGD 0 P4D 0 [ 256.332574] Oops: 0000 [#1] PREEMPT SMP NOPTI [ 256.337006] CPU: 3 PID: 32 Comm: ksoftirqd/3 Tainted: G OE 6.2.0-rc5+ #51 [ 256.345218] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0008.031920191559 03/19/2019 [ 256.355807] RIP: 0010:ice_clean_rx_irq_zc+0x9c/0x7d0 [ice] [ 256.361423] Code: b7 8f 8a 00 00 00 66 39 ca 0f 84 f1 04 00 00 49 8b 47 40 4c 8b 24 d0 41 0f b7 45 04 66 25 ff 3f 66 89 04 24 0f 84 85 02 00 00 <49> 8b 44 24 18 0f b7 14 24 48 05 00 01 00 00 49 89 04 24 49 89 44 [ 256.380463] RSP: 0018:ffffc900088bfd20 EFLAGS: 00010206 [ 256.385765] RAX: 000000000000003c RBX: 0000000000000035 RCX: 000000000000067f [ 256.393012] RDX: 0000000000000775 RSI: 0000000000000000 RDI: ffff8881deb3ac80 [ 256.400256] RBP: 000000000000003c R08: ffff889847982710 R09: 0000000000010000 [ 256.407500] R10: ffffffff82c060c0 R11: 0000000000000004 R12: 0000000000000000 [ 256.414746] R13: ffff88811165eea0 R14: ffffc9000d255000 R15: ffff888119b37600 [ 256.421990] FS: 0000000000000000(0000) GS:ffff8897e0cc0000(0000) knlGS:0000000000000000 [ 256.430207] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 256.436036] CR2: 0000000000000018 CR3: 0000000005c0a006 CR4: 00000000007706e0 [ 256.443283] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 256.450527] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 256.457770] PKRU: 55555554 [ 256.460529] Call Trace: [ 256.463015] <TASK> [ 256.465157] ? ice_xmit_zc+0x6e/0x150 [ice] [ 256.469437] ice_napi_poll+0x46d/0x680 [ice] [ 256.473815] ? _raw_spin_unlock_irqrestore+0x1b/0x40 [ 256.478863] __napi_poll+0x29/0x160 [ 256.482409] net_rx_action+0x136/0x260 [ 256.486222] __do_softirq+0xe8/0x2e5 [ 256.489853] ? smpboot_thread_fn+0x2c/0x270 [ 256.494108] run_ksoftirqd+0x2a/0x50 [ 256.497747] smpboot_thread_fn+0x1c1/0x270 [ 256.501907] ? __pfx_smpboot_thread_fn+0x10/0x10 [ 256.506594] kthread+0xea/0x120 [ 256.509785] ? __pfx_kthread+0x10/0x10 [ 256.513597] ret_from_fork+0x29/0x50 [ 256.517238] </TASK> In fact, irqs were not disabled and napi managed to be scheduled and run while xsk_pool pointer was still valid, but SW ring of xdp_buff pointers was already freed. To fix this, call ice_qvec_dis_irq() after ice_vsi_stop_tx_ring(). Also while at it, remove redundant ice_clean_rx_ring() call - this is handled in ice_qp_clean_rings(). Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Reviewed-by: Larysa Zaremba <larysa.zaremba@intel.com> Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel) Acked-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com> Reviewed-by: Leon Romanovsky <leonro@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-02-20Merge tag 'for-netdev' of ↵Jakub Kicinski1-24/+11
https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next Daniel Borkmann says: ==================== pull-request: bpf-next 2023-02-17 We've added 64 non-merge commits during the last 7 day(s) which contain a total of 158 files changed, 4190 insertions(+), 988 deletions(-). The main changes are: 1) Add a rbtree data structure following the "next-gen data structure" precedent set by recently-added linked-list, that is, by using kfunc + kptr instead of adding a new BPF map type, from Dave Marchevsky. 2) Add a new benchmark for hashmap lookups to BPF selftests, from Anton Protopopov. 3) Fix bpf_fib_lookup to only return valid neighbors and add an option to skip the neigh table lookup, from Martin KaFai Lau. 4) Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accouting for container environments, from Yafang Shao. 5) Batch of ice multi-buffer and driver performance fixes, from Alexander Lobakin. 6) Fix a bug in determining whether global subprog's argument is PTR_TO_CTX, which is based on type names which breaks kprobe progs, from Andrii Nakryiko. 7) Prep work for future -mcpu=v4 LLVM option which includes usage of BPF_ST insn. Thus improve BPF_ST-related value tracking in verifier, from Eduard Zingerman. 8) More prep work for later building selftests with Memory Sanitizer in order to detect usages of undefined memory, from Ilya Leoshkevich. 9) Fix xsk sockets to check IFF_UP earlier to avoid a NULL pointer dereference via sendmsg(), from Maciej Fijalkowski. 10) Implement BPF trampoline for RV64 JIT compiler, from Pu Lehui. 11) Fix BPF memory allocator in combination with BPF hashtab where it could corrupt special fields e.g. used in bpf_spin_lock, from Hou Tao. 12) Fix LoongArch BPF JIT to always use 4 instructions for function address so that instruction sequences don't change between passes, from Hengqi Chen. * tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (64 commits) selftests/bpf: Add bpf_fib_lookup test bpf: Add BPF_FIB_LOOKUP_SKIP_NEIGH for bpf_fib_lookup riscv, bpf: Add bpf trampoline support for RV64 riscv, bpf: Add bpf_arch_text_poke support for RV64 riscv, bpf: Factor out emit_call for kernel and bpf context riscv: Extend patch_text for multiple instructions Revert "bpf, test_run: fix &xdp_frame misplacement for LIVE_FRAMES" selftests/bpf: Add global subprog context passing tests selftests/bpf: Convert test_global_funcs test to test_loader framework bpf: Fix global subprog context argument resolution logic LoongArch, bpf: Use 4 instructions for function address in JIT bpf: bpf_fib_lookup should not return neigh in NUD_FAILED state bpf: Disable bh in bpf_test_run for xdp and tc prog xsk: check IFF_UP earlier in Tx path Fix typos in selftest/bpf files selftests/bpf: Use bpf_{btf,link,map,prog}_get_info_by_fd() samples/bpf: Use bpf_{btf,link,map,prog}_get_info_by_fd() bpftool: Use bpf_{btf,link,map,prog}_get_info_by_fd() libbpf: Use bpf_{btf,link,map,prog}_get_info_by_fd() libbpf: Introduce bpf_{btf,link,map,prog}_get_info_by_fd() ... ==================== Link: https://lore.kernel.org/r/20230217221737.31122-1-daniel@iogearbox.net Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-02-17Merge ra.kernel.org:/pub/scm/linux/kernel/git/netdev/netDavid S. Miller1-13/+31
Some of the devlink bits were tricky, but I think I got it right. Signed-off-by: David S. Miller <davem@davemloft.net>
2023-02-13ice: Robustify cleaning/completing XDP Tx buffersAlexander Lobakin1-5/+7
When queueing frames from a Page Pool for redirecting to a device backed by the ice driver, `perf top` shows heavy load on page_alloc() and page_frag_free(), despite that on a properly working system it must be fully or at least almost zero-alloc. The problem is in fact a bit deeper and raises from how ice cleans up completed Tx buffers. The story so far: when cleaning/freeing the resources related to a particular completed Tx frame (skbs, DMA mappings etc.), ice uses some heuristics only without setting any type explicitly (except for dummy Flow Director packets, which are marked via ice_tx_buf::tx_flags). This kinda works, but only up to some point. For example, currently ice assumes that each frame coming to __ice_xmit_xdp_ring(), is backed by either plain order-0 page or plain page frag, while it may also be backed by Page Pool or any other possible memory models introduced in future. This means any &xdp_frame must be freed properly via xdp_return_frame() family with no assumptions. In order to do that, the whole heuristics must be replaced with setting the Tx buffer/frame type explicitly, just how it's always been done via an enum. Let us reuse 16 bits from ::tx_flags -- 1 bit-and instr won't hurt much -- especially given that sometimes there was a check for %ICE_TX_FLAGS_DUMMY_PKT, which is now turned from a flag to an enum member. The rest of the changes is straightforward and most of it is just a conversion to rely now on the type set in &ice_tx_buf rather than to some secondary properties. For now, no functional changes intended, the change only prepares the ground for starting freeing XDP frames properly next step. And it must be done atomically/synchronously to not break stuff. Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Link: https://lore.kernel.org/bpf/20230210170618.1973430-5-alexandr.lobakin@intel.com
2023-02-10ice: xsk: Fix cleaning of XDP_TX framesLarysa Zaremba1-6/+9
Incrementation of xsk_frames inside the for-loop produces infinite loop, if we have both normal AF_XDP-TX and XDP_TXed buffers to complete. Split xsk_frames into 2 variables (xsk_frames and completed_frames) to eliminate this bug. Fixes: 29322791bc8b ("ice: xsk: change batched Tx descriptor cleaning") Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com> Reviewed-by: Alexander Duyck <alexanderduyck@fb.com> Acked-by: Tony Nguyen <anthony.l.nguyen@intel.com> Link: https://lore.kernel.org/r/20230209160130.1779890-1-larysa.zaremba@intel.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-02-01ice: xsk: Do not convert to buff to frame for XDP_TXMaciej Fijalkowski1-72/+104
Let us store pointer to xdp_buff that came from xsk_buff_pool on tx_buf so that it will be possible to recycle it via xsk_buff_free() on Tx cleaning side. This way it is not necessary to do expensive copy to another xdp_buff backed by a newly allocated page. Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com> Link: https://lore.kernel.org/bpf/20230131204506.219292-14-maciej.fijalkowski@intel.com
2023-02-01ice: Add support for XDP multi-buffer on Tx sideMaciej Fijalkowski1-15/+1
Similarly as for Rx side in previous patch, logic on XDP Tx in ice driver needs to be adjusted for multi-buffer support. Specifically, the way how HW Tx descriptors are produced and cleaned. Currently, XDP_TX works on strict ring boundaries, meaning it sets RS bit (on producer side) / looks up DD bit (on consumer/cleaning side) every quarter of the ring. It means that if for example multi buffer frame would span across the ring quarter boundary (say that frame consists of 4 frames and we start from 62 descriptor where ring is sized to 256 entries), RS bit would be produced in the middle of multi buffer frame, which would be a broken behavior as it needs to be set on the last descriptor of the frame. To make it work, set RS bit at the last descriptor from the batch of frames that XDP_TX action was used on and make the first entry remember the index of last descriptor with RS bit set. This way, cleaning side can take the index of descriptor with RS bit, look up DD bit's presence and clean from first entry to last. In order to clean up the code base introduce the common ice_set_rs_bit() which will return index of descriptor that got RS bit produced on so that standard driver can store this within proper ice_tx_buf and ZC driver can simply ignore return value. Co-developed-by: Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com> Signed-off-by: Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com> Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com> Link: https://lore.kernel.org/bpf/20230131204506.219292-12-maciej.fijalkowski@intel.com
2022-12-21ice: xsk: do not use xdp_return_frame() on tx_buf->raw_bufMaciej Fijalkowski1-1/+1
Previously ice XDP xmit routine was changed in a way that it avoids xdp_buff->xdp_frame conversion as it is simply not needed for handling XDP_TX action and what is more it saves us CPU cycles. This routine is re-used on ZC driver to handle XDP_TX action. Although for XDP_TX on Rx ZC xdp_buff that comes from xsk_buff_pool is converted to xdp_frame, xdp_frame itself is not stored inside ice_tx_buf, we only store raw data pointer. Casting this pointer to xdp_frame and calling against it xdp_return_frame in ice_clean_xdp_tx_buf() results in undefined behavior. To fix this, simply call page_frag_free() on tx_buf->raw_buf. Later intention is to remove the buff->frame conversion in order to simplify the codebase and improve XDP_TX performance on ZC. Fixes: 126cdfe1007a ("ice: xsk: Improve AF_XDP ZC Tx and use batching API") Reported-and-tested-by: Robin Cowley <robin.cowley@thehutgroup.com> Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com> Reviewed-by: Piotr Raczynski <piotr.raczynski@.intel.com> Link: https://lore.kernel.org/r/20221220175448.693999-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-11-23ice: Accumulate ring statistics over resetBenjamin Mikailenko1-7/+18
Resets may occur with or without user interaction. For example, a TX hang or reconfiguration of parameters will result in a reset. During reset, the VSI is freed, freeing any statistics structures inside as well. This would create an issue for the user where a reset happens in the background, statistics set to zero, and the user checks ring statistics expecting them to be populated. To ensure this doesn't happen, accumulate ring statistics over reset. Define a new ring statistics structure, ice_ring_stats. The new structure lives in the VSI's parent, preserving ring statistics when VSI is freed. 1. Define a new structure vsi_ring_stats in the PF scope 2. Allocate/free stats only during probe, unload, or change in ring size 3. Replace previous ring statistics functionality with new structure Signed-off-by: Benjamin Mikailenko <benjamin.mikailenko@intel.com> Tested-by: Gurucharan G <gurucharanx.g@intel.com> (A Contingent worker at Intel) Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2022-09-27ice: xsk: drop power of 2 ring size restriction for AF_XDPMaciej Fijalkowski1-13/+7
We had multiple customers in the past months that reported commit 296f13ff3854 ("ice: xsk: Force rings to be sized to power of 2") makes them unable to use ring size of 8160 in conjunction with AF_XDP. Remove this restriction. Fixes: 296f13ff3854 ("ice: xsk: Force rings to be sized to power of 2") CC: Alasdair McWilliam <alasdair.mcwilliam@outlook.com> Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Tested-by: George Kuruvinakunnel <george.kuruvinakunnel@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2022-09-27ice: xsk: change batched Tx descriptor cleaningMaciej Fijalkowski1-82/+61
AF_XDP Tx descriptor cleaning in ice driver currently works in a "lazy" way - descriptors are not cleaned immediately after send. We rather hold on with cleaning until we see that free space in ring drops below particular threshold. This was supposed to reduce the amount of unnecessary work related to cleaning and instead of keeping the ring empty, ring was rather saturated. In AF_XDP realm cleaning Tx descriptors implies producing them to CQ. This is a way of letting know user space that particular descriptor has been sent, as John points out in [0]. We tried to implement serial descriptor cleaning which would be used in conjunction with batched cleaning but it made code base more convoluted and probably harder to maintain in future. Therefore we step away from batched cleaning in a current form in favor of an approach where we set RS bit on every last descriptor from a batch and clean always at the beginning of ice_xmit_zc(). This means that we give up a bit of Tx performance, but this doesn't hurt l2fwd scenario which is way more meaningful than txonly as this can be treaten as AF_XDP based packet generator. l2fwd is not hurt due to the fact that Tx side is much faster than Rx and Rx is the one that has to catch Tx up. FWIW Tx descriptors are still produced in a batched way. [0]: https://lore.kernel.org/bpf/62b0a20232920_3573208ab@john.notmuch/ Fixes: 126cdfe1007a ("ice: xsk: Improve AF_XDP ZC Tx and use batching API") Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Tested-by: George Kuruvinakunnel <george.kuruvinakunnel@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2022-09-02ice: Fix DMA mappings leakPrzemyslaw Patynowski1-0/+63
Fix leak, when user changes ring parameters. During reallocation of RX buffers, new DMA mappings are created for those buffers. New buffers with different RX ring count should substitute older ones, but those buffers were freed in ice_vsi_cfg_rxq and reallocated again with ice_alloc_rx_buf. kfree on rx_buf caused leak of already mapped DMA. Reallocate ZC with xdp_buf struct, when BPF program loads. Reallocate back to rx_buf, when BPF program unloads. If BPF program is loaded/unloaded and XSK pools are created, reallocate RX queues accordingly in XDP_SETUP_XSK_POOL handler. Steps for reproduction: while : do for ((i=0; i<=8160; i=i+32)) do ethtool -G enp130s0f0 rx $i tx $i sleep 0.5 ethtool -g enp130s0f0 done done Fixes: 617f3e1b588c ("ice: xsk: allocate separate memory for XDP SW ring") Signed-off-by: Przemyslaw Patynowski <przemyslawx.patynowski@intel.com> Signed-off-by: Mateusz Palczewski <mateusz.palczewski@intel.com> Tested-by: Chandan <chandanx.rout@intel.com> (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2022-08-22ice: xsk: use Rx ring's XDP ring when picking NAPI contextMaciej Fijalkowski1-6/+6
Ice driver allocates per cpu XDP queues so that redirect path can safely use smp_processor_id() as an index to the array. At the same time though, XDP rings are used to pick NAPI context to call napi_schedule() or set NAPIF_STATE_MISSED. When user reduces queue count, say to 8, and num_possible_cpus() of underlying platform is 44, then this means queue vectors with correlated NAPI contexts will carry several XDP queues. This in turn can result in a broken behavior where NAPI context of interest will never be scheduled and AF_XDP socket will not process any traffic. To fix this, let us change the way how XDP rings are assigned to Rx rings and use this information later on when setting ice_tx_ring::xsk_pool pointer. For each Rx ring, grab the associated queue vector and walk through Tx ring's linked list. Once we stumble upon XDP ring in it, assign this ring to ice_rx_ring::xdp_ring. Previous [0] approach of fixing this issue was for txonly scenario because of the described grouping of XDP rings across queue vectors. So, relying on Rx ring meant that NAPI context could be scheduled with a queue vector without XDP ring with associated XSK pool. [0]: https://lore.kernel.org/netdev/20220707161128.54215-1-maciej.fijalkowski@intel.com/ Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Fixes: 22bf877e528f ("ice: introduce XDP_TX fallback path") Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Tested-by: George Kuruvinakunnel <george.kuruvinakunnel@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2022-08-22ice: xsk: prohibit usage of non-balanced queue idMaciej Fijalkowski1-0/+6
Fix the following scenario: 1. ethtool -L $IFACE rx 8 tx 96 2. xdpsock -q 10 -t -z Above refers to a case where user would like to attach XSK socket in txonly mode at a queue id that does not have a corresponding Rx queue. At this moment ice's XSK logic is tightly bound to act on a "queue pair", e.g. both Tx and Rx queues at a given queue id are disabled/enabled and both of them will get XSK pool assigned, which is broken for the presented queue configuration. This results in the splat included at the bottom, which is basically an OOB access to Rx ring array. To fix this, allow using the ids only in scope of "combined" queues reported by ethtool. However, logic should be rewritten to allow such configurations later on, which would end up as a complete rewrite of the control path, so let us go with this temporary fix. [420160.558008] BUG: kernel NULL pointer dereference, address: 0000000000000082 [420160.566359] #PF: supervisor read access in kernel mode [420160.572657] #PF: error_code(0x0000) - not-present page [420160.579002] PGD 0 P4D 0 [420160.582756] Oops: 0000 [#1] PREEMPT SMP NOPTI [420160.588396] CPU: 10 PID: 21232 Comm: xdpsock Tainted: G OE 5.19.0-rc7+ #10 [420160.597893] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0008.031920191559 03/19/2019 [420160.609894] RIP: 0010:ice_xsk_pool_setup+0x44/0x7d0 [ice] [420160.616968] Code: f3 48 83 ec 40 48 8b 4f 20 48 8b 3f 65 48 8b 04 25 28 00 00 00 48 89 44 24 38 31 c0 48 8d 04 ed 00 00 00 00 48 01 c1 48 8b 11 <0f> b7 92 82 00 00 00 48 85 d2 0f 84 2d 75 00 00 48 8d 72 ff 48 85 [420160.639421] RSP: 0018:ffffc9002d2afd48 EFLAGS: 00010282 [420160.646650] RAX: 0000000000000050 RBX: ffff88811d8bdd00 RCX: ffff888112c14ff8 [420160.655893] RDX: 0000000000000000 RSI: ffff88811d8bdd00 RDI: ffff888109861000 [420160.665166] RBP: 000000000000000a R08: 000000000000000a R09: 0000000000000000 [420160.674493] R10: 000000000000889f R11: 0000000000000000 R12: 000000000000000a [420160.683833] R13: 000000000000000a R14: 0000000000000000 R15: ffff888117611828 [420160.693211] FS: 00007fa869fc1f80(0000) GS:ffff8897e0880000(0000) knlGS:0000000000000000 [420160.703645] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [420160.711783] CR2: 0000000000000082 CR3: 00000001d076c001 CR4: 00000000007706e0 [420160.721399] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [420160.731045] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [420160.740707] PKRU: 55555554 [420160.745960] Call Trace: [420160.750962] <TASK> [420160.755597] ? kmalloc_large_node+0x79/0x90 [420160.762703] ? __kmalloc_node+0x3f5/0x4b0 [420160.769341] xp_assign_dev+0xfd/0x210 [420160.775661] ? shmem_file_read_iter+0x29a/0x420 [420160.782896] xsk_bind+0x152/0x490 [420160.788943] __sys_bind+0xd0/0x100 [420160.795097] ? exit_to_user_mode_prepare+0x20/0x120 [420160.802801] __x64_sys_bind+0x16/0x20 [420160.809298] do_syscall_64+0x38/0x90 [420160.815741] entry_SYSCALL_64_after_hwframe+0x63/0xcd [420160.823731] RIP: 0033:0x7fa86a0dd2fb [420160.830264] Code: c3 66 0f 1f 44 00 00 48 8b 15 69 8b 0c 00 f7 d8 64 89 02 b8 ff ff ff ff eb bc 0f 1f 44 00 00 f3 0f 1e fa b8 31 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 3d 8b 0c 00 f7 d8 64 89 01 48 [420160.855410] RSP: 002b:00007ffc1146f618 EFLAGS: 00000246 ORIG_RAX: 0000000000000031 [420160.866366] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fa86a0dd2fb [420160.876957] RDX: 0000000000000010 RSI: 00007ffc1146f680 RDI: 0000000000000003 [420160.887604] RBP: 000055d7113a0520 R08: 00007fa868fb8000 R09: 0000000080000000 [420160.898293] R10: 0000000000008001 R11: 0000000000000246 R12: 000055d7113a04e0 [420160.909038] R13: 000055d7113a0320 R14: 000000000000000a R15: 0000000000000000 [420160.919817] </TASK> [420160.925659] Modules linked in: ice(OE) af_packet binfmt_misc nls_iso8859_1 ipmi_ssif intel_rapl_msr intel_rapl_common x86_pkg_temp_thermal intel_powerclamp mei_me coretemp ioatdma mei ipmi_si wmi ipmi_msghandler acpi_pad acpi_power_meter ip_tables x_tables autofs4 ixgbe i40e crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel crypto_simd cryptd ahci mdio dca libahci lpc_ich [last unloaded: ice] [420160.977576] CR2: 0000000000000082 [420160.985037] ---[ end trace 0000000000000000 ]--- [420161.097724] RIP: 0010:ice_xsk_pool_setup+0x44/0x7d0 [ice] [420161.107341] Code: f3 48 83 ec 40 48 8b 4f 20 48 8b 3f 65 48 8b 04 25 28 00 00 00 48 89 44 24 38 31 c0 48 8d 04 ed 00 00 00 00 48 01 c1 48 8b 11 <0f> b7 92 82 00 00 00 48 85 d2 0f 84 2d 75 00 00 48 8d 72 ff 48 85 [420161.134741] RSP: 0018:ffffc9002d2afd48 EFLAGS: 00010282 [420161.144274] RAX: 0000000000000050 RBX: ffff88811d8bdd00 RCX: ffff888112c14ff8 [420161.155690] RDX: 0000000000000000 RSI: ffff88811d8bdd00 RDI: ffff888109861000 [420161.168088] RBP: 000000000000000a R08: 000000000000000a R09: 0000000000000000 [420161.179295] R10: 000000000000889f R11: 0000000000000000 R12: 000000000000000a [420161.190420] R13: 000000000000000a R14: 0000000000000000 R15: ffff888117611828 [420161.201505] FS: 00007fa869fc1f80(0000) GS:ffff8897e0880000(0000) knlGS:0000000000000000 [420161.213628] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [420161.223413] CR2: 0000000000000082 CR3: 00000001d076c001 CR4: 00000000007706e0 [420161.234653] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [420161.245893] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [420161.257052] PKRU: 55555554 Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Tested-by: George Kuruvinakunnel <george.kuruvinakunnel@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
2022-04-27Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-nextJakub Kicinski1-20/+33
Daniel Borkmann says: ==================== pull-request: bpf-next 2022-04-27 We've added 85 non-merge commits during the last 18 day(s) which contain a total of 163 files changed, 4499 insertions(+), 1521 deletions(-). The main changes are: 1) Teach libbpf to enhance BPF verifier log with human-readable and relevant information about failed CO-RE relocations, from Andrii Nakryiko. 2) Add typed pointer support in BPF maps and enable it for unreferenced pointers (via probe read) and referenced ones that can be passed to in-kernel helpers, from Kumar Kartikeya Dwivedi. 3) Improve xsk to break NAPI loop when rx queue gets full to allow for forward progress to consume descriptors, from Maciej Fijalkowski & Björn Töpel. 4) Fix a small RCU read-side race in BPF_PROG_RUN routines which dereferenced the effective prog array before the rcu_read_lock, from Stanislav Fomichev. 5) Implement BPF atomic operations for RV64 JIT, and add libbpf parsing logic for USDT arguments under riscv{32,64}, from Pu Lehui. 6) Implement libbpf parsing of USDT arguments under aarch64, from Alan Maguire. 7) Enable bpftool build for musl and remove nftw with FTW_ACTIONRETVAL usage so it can be shipped under Alpine which is musl-based, from Dominique Martinet. 8) Clean up {sk,task,inode} local storage trace RCU handling as they do not need to use call_rcu_tasks_trace() barrier, from KP Singh. 9) Improve libbpf API documentation and fix error return handling of various API functions, from Grant Seltzer. 10) Enlarge offset check for bpf_skb_{load,store}_bytes() helpers given data length of frags + frag_list may surpass old offset limit, from Liu Jian. 11) Various improvements to prog_tests in area of logging, test execution and by-name subtest selection, from Mykola Lysenko. 12) Simplify map_btf_id generation for all map types by moving this process to build time with help of resolve_btfids infra, from Menglong Dong. 13) Fix a libbpf bug in probing when falling back to legacy bpf_probe_read*() helpers; the probing caused always to use old helpers, from Runqing Yang. 14) Add support for ARCompact and ARCv2 platforms for libbpf's PT_REGS tracing macros, from Vladimir Isaev. 15) Cleanup BPF selftests to remove old & unneeded rlimit code given kernel switched to memcg-based memory accouting a while ago, from Yafang Shao. 16) Refactor of BPF sysctl handlers to move them to BPF core, from Yan Zhu. 17) Fix BPF selftests in two occasions to work around regressions caused by latest LLVM to unblock CI until their fixes are worked out, from Yonghong Song. 18) Misc cleanups all over the place, from various others. * https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (85 commits) selftests/bpf: Add libbpf's log fixup logic selftests libbpf: Fix up verifier log for unguarded failed CO-RE relos libbpf: Simplify bpf_core_parse_spec() signature libbpf: Refactor CO-RE relo human description formatting routine libbpf: Record subprog-resolved CO-RE relocations unconditionally selftests/bpf: Add CO-RE relos and SEC("?...") to linked_funcs selftests libbpf: Avoid joining .BTF.ext data with BPF programs by section name libbpf: Fix logic for finding matching program for CO-RE relocation libbpf: Drop unhelpful "program too large" guess libbpf: Fix anonymous type check in CO-RE logic bpf: Compute map_btf_id during build time selftests/bpf: Add test for strict BTF type check selftests/bpf: Add verifier tests for kptr selftests/bpf: Add C tests for kptr libbpf: Add kptr type tag macros to bpf_helpers.h bpf: Make BTF type match stricter for release arguments bpf: Teach verifier about kptr_get kfunc helpers bpf: Wire up freeing of referenced kptr bpf: Populate pairs of btf_id and destructor kfunc in btf bpf: Adapt copy_map_value for multiple offset case ... ==================== Link: https://lore.kernel.org/r/20220427224758.20976-1-daniel@iogearbox.net Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-04-15ice, xsk: Avoid refilling single Rx descriptorsMaciej Fijalkowski1-1/+4
Call alloc Rx routine for ZC driver only when the amount of unallocated descriptors exceeds given threshold. Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20220413153015.453864-14-maciej.fijalkowski@intel.com
2022-04-15ice, xsk: Diversify return values from xsk_wakeup call pathsMaciej Fijalkowski1-3/+3
Currently, when debugging AF_XDP workloads, one can correlate the -ENXIO return code as the case that XSK is not in the bound state. Returning same code from ndo_xsk_wakeup can be misleading and simply makes it harder to follow what is going on. Change ENXIOs in ice's ndo_xsk_wakeup() implementation to EINVALs, so that when probing it is clear that something is wrong on the driver side, not the xsk_{recv,send}msg. There is a -ENETDOWN that can happen from both kernel/driver sides though, but I don't have a correct replacement for this on one of the sides, so let's keep it that way. Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20220413153015.453864-9-maciej.fijalkowski@intel.com
2022-04-15ice, xsk: Terminate Rx side of NAPI when XSK Rx queue gets fullMaciej Fijalkowski1-10/+19
When XSK pool uses need_wakeup feature, correlate -ENOBUFS that was returned from xdp_do_redirect() with a XSK Rx queue being full. In such case, terminate the Rx processing that is being done on the current HW Rx ring and let the user space consume descriptors from XSK Rx queue so that there is room that driver can use later on. Introduce new internal return code ICE_XDP_EXIT that will indicate case described above. Note that it does not affect Tx processing that is bound to the same NAPI context, nor the other Rx rings. Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20220413153015.453864-6-maciej.fijalkowski@intel.com
2022-04-15ice, xsk: Decorate ICE_XDP_REDIR with likely()Maciej Fijalkowski1-10/+11
ice_run_xdp_zc() suggests to compiler that XDP_REDIRECT is the most probable action returned from BPF program that AF_XDP has in its pipeline. Let's also bring this suggestion up to the callsite of ice_run_xdp_zc() so that compiler will be able to generate more optimized code which in turn will make branch predictor happy. Suggested-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20220413153015.453864-4-maciej.fijalkowski@intel.com
generated by cgit v1.2.3 (git 2.39.1) at 2025-05-13 08:25:19 +0000