From 2a5dc090b92cfa5270e20056074241c6db5c9cdd Mon Sep 17 00:00:00 2001 From: Larysa Zaremba Date: Fri, 23 Aug 2024 11:59:26 +0200 Subject: ice: move netif_queue_set_napi to rtnl-protected sections Currently, netif_queue_set_napi() is called from ice_vsi_rebuild() that is not rtnl-locked when called from the reset. This creates the need to take the rtnl_lock just for a single function and complicates the synchronization with .ndo_bpf. At the same time, there no actual need to fill napi-to-queue information at this exact point. Fill napi-to-queue information when opening the VSI and clear it when the VSI is being closed. Those routines are already rtnl-locked. Also, rewrite napi-to-queue assignment in a way that prevents inclusion of XDP queues, as this leads to out-of-bounds writes, such as one below. [ +0.000004] BUG: KASAN: slab-out-of-bounds in netif_queue_set_napi+0x1c2/0x1e0 [ +0.000012] Write of size 8 at addr ffff889881727c80 by task bash/7047 [ +0.000006] CPU: 24 PID: 7047 Comm: bash Not tainted 6.10.0-rc2+ #2 [ +0.000004] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0014.082620210524 08/26/2021 [ +0.000003] Call Trace: [ +0.000003] [ +0.000002] dump_stack_lvl+0x60/0x80 [ +0.000007] print_report+0xce/0x630 [ +0.000007] ? __pfx__raw_spin_lock_irqsave+0x10/0x10 [ +0.000007] ? __virt_addr_valid+0x1c9/0x2c0 [ +0.000005] ? netif_queue_set_napi+0x1c2/0x1e0 [ +0.000003] kasan_report+0xe9/0x120 [ +0.000004] ? netif_queue_set_napi+0x1c2/0x1e0 [ +0.000004] netif_queue_set_napi+0x1c2/0x1e0 [ +0.000005] ice_vsi_close+0x161/0x670 [ice] [ +0.000114] ice_dis_vsi+0x22f/0x270 [ice] [ +0.000095] ice_pf_dis_all_vsi.constprop.0+0xae/0x1c0 [ice] [ +0.000086] ice_prepare_for_reset+0x299/0x750 [ice] [ +0.000087] pci_dev_save_and_disable+0x82/0xd0 [ +0.000006] pci_reset_function+0x12d/0x230 [ +0.000004] reset_store+0xa0/0x100 [ +0.000006] ? __pfx_reset_store+0x10/0x10 [ +0.000002] ? __pfx_mutex_lock+0x10/0x10 [ +0.000004] ? __check_object_size+0x4c1/0x640 [ +0.000007] kernfs_fop_write_iter+0x30b/0x4a0 [ +0.000006] vfs_write+0x5d6/0xdf0 [ +0.000005] ? fd_install+0x180/0x350 [ +0.000005] ? __pfx_vfs_write+0x10/0xA10 [ +0.000004] ? do_fcntl+0x52c/0xcd0 [ +0.000004] ? kasan_save_track+0x13/0x60 [ +0.000003] ? kasan_save_free_info+0x37/0x60 [ +0.000006] ksys_write+0xfa/0x1d0 [ +0.000003] ? __pfx_ksys_write+0x10/0x10 [ +0.000002] ? __x64_sys_fcntl+0x121/0x180 [ +0.000004] ? _raw_spin_lock+0x87/0xe0 [ +0.000005] do_syscall_64+0x80/0x170 [ +0.000007] ? _raw_spin_lock+0x87/0xe0 [ +0.000004] ? __pfx__raw_spin_lock+0x10/0x10 [ +0.000003] ? file_close_fd_locked+0x167/0x230 [ +0.000005] ? syscall_exit_to_user_mode+0x7d/0x220 [ +0.000005] ? do_syscall_64+0x8c/0x170 [ +0.000004] ? do_syscall_64+0x8c/0x170 [ +0.000003] ? do_syscall_64+0x8c/0x170 [ +0.000003] ? fput+0x1a/0x2c0 [ +0.000004] ? filp_close+0x19/0x30 [ +0.000004] ? do_dup2+0x25a/0x4c0 [ +0.000004] ? __x64_sys_dup2+0x6e/0x2e0 [ +0.000002] ? syscall_exit_to_user_mode+0x7d/0x220 [ +0.000004] ? do_syscall_64+0x8c/0x170 [ +0.000003] ? __count_memcg_events+0x113/0x380 [ +0.000005] ? handle_mm_fault+0x136/0x820 [ +0.000005] ? do_user_addr_fault+0x444/0xa80 [ +0.000004] ? clear_bhb_loop+0x25/0x80 [ +0.000004] ? clear_bhb_loop+0x25/0x80 [ +0.000002] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ +0.000005] RIP: 0033:0x7f2033593154 Fixes: 080b0c8d6d26 ("ice: Fix ASSERT_RTNL() warning during certain scenarios") Fixes: 91fdbce7e8d6 ("ice: Add support in the driver for associating queue with napi") Reviewed-by: Wojciech Drewek Reviewed-by: Jacob Keller Reviewed-by: Amritha Nambiar Signed-off-by: Larysa Zaremba Reviewed-by: Maciej Fijalkowski Tested-by: George Kuruvinakunnel Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_base.c | 11 +-- drivers/net/ethernet/intel/ice/ice_lib.c | 129 +++++++----------------------- drivers/net/ethernet/intel/ice/ice_lib.h | 10 +-- drivers/net/ethernet/intel/ice/ice_main.c | 17 +++- 4 files changed, 49 insertions(+), 118 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index f448d3a84564..c158749a80e0 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -190,16 +190,11 @@ static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx) } q_vector = vsi->q_vectors[v_idx]; - ice_for_each_tx_ring(tx_ring, q_vector->tx) { - ice_queue_set_napi(vsi, tx_ring->q_index, NETDEV_QUEUE_TYPE_TX, - NULL); + ice_for_each_tx_ring(tx_ring, vsi->q_vectors[v_idx]->tx) tx_ring->q_vector = NULL; - } - ice_for_each_rx_ring(rx_ring, q_vector->rx) { - ice_queue_set_napi(vsi, rx_ring->q_index, NETDEV_QUEUE_TYPE_RX, - NULL); + + ice_for_each_rx_ring(rx_ring, vsi->q_vectors[v_idx]->rx) rx_ring->q_vector = NULL; - } /* only VSI with an associated netdev is set up with NAPI */ if (vsi->netdev) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index f559e60992fa..6676596df88b 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2286,9 +2286,6 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi) ice_vsi_map_rings_to_vectors(vsi); - /* Associate q_vector rings to napi */ - ice_vsi_set_napi_queues(vsi); - vsi->stat_offsets_loaded = false; /* ICE_VSI_CTRL does not need RSS so skip RSS processing */ @@ -2628,6 +2625,7 @@ void ice_vsi_close(struct ice_vsi *vsi) if (!test_and_set_bit(ICE_VSI_DOWN, vsi->state)) ice_down(vsi); + ice_vsi_clear_napi_queues(vsi); ice_vsi_free_irq(vsi); ice_vsi_free_tx_rings(vsi); ice_vsi_free_rx_rings(vsi); @@ -2694,120 +2692,55 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked) } /** - * __ice_queue_set_napi - Set the napi instance for the queue - * @dev: device to which NAPI and queue belong - * @queue_index: Index of queue - * @type: queue type as RX or TX - * @napi: NAPI context - * @locked: is the rtnl_lock already held - * - * Set the napi instance for the queue. Caller indicates the lock status. - */ -static void -__ice_queue_set_napi(struct net_device *dev, unsigned int queue_index, - enum netdev_queue_type type, struct napi_struct *napi, - bool locked) -{ - if (!locked) - rtnl_lock(); - netif_queue_set_napi(dev, queue_index, type, napi); - if (!locked) - rtnl_unlock(); -} - -/** - * ice_queue_set_napi - Set the napi instance for the queue - * @vsi: VSI being configured - * @queue_index: Index of queue - * @type: queue type as RX or TX - * @napi: NAPI context + * ice_vsi_set_napi_queues - associate netdev queues with napi + * @vsi: VSI pointer * - * Set the napi instance for the queue. The rtnl lock state is derived from the - * execution path. + * Associate queue[s] with napi for all vectors. + * The caller must hold rtnl_lock. */ -void -ice_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index, - enum netdev_queue_type type, struct napi_struct *napi) +void ice_vsi_set_napi_queues(struct ice_vsi *vsi) { - struct ice_pf *pf = vsi->back; + struct net_device *netdev = vsi->netdev; + int q_idx, v_idx; - if (!vsi->netdev) + if (!netdev) return; - if (current_work() == &pf->serv_task || - test_bit(ICE_PREPARED_FOR_RESET, pf->state) || - test_bit(ICE_DOWN, pf->state) || - test_bit(ICE_SUSPENDED, pf->state)) - __ice_queue_set_napi(vsi->netdev, queue_index, type, napi, - false); - else - __ice_queue_set_napi(vsi->netdev, queue_index, type, napi, - true); -} + ice_for_each_rxq(vsi, q_idx) + netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX, + &vsi->rx_rings[q_idx]->q_vector->napi); -/** - * __ice_q_vector_set_napi_queues - Map queue[s] associated with the napi - * @q_vector: q_vector pointer - * @locked: is the rtnl_lock already held - * - * Associate the q_vector napi with all the queue[s] on the vector. - * Caller indicates the lock status. - */ -void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked) -{ - struct ice_rx_ring *rx_ring; - struct ice_tx_ring *tx_ring; - - ice_for_each_rx_ring(rx_ring, q_vector->rx) - __ice_queue_set_napi(q_vector->vsi->netdev, rx_ring->q_index, - NETDEV_QUEUE_TYPE_RX, &q_vector->napi, - locked); - - ice_for_each_tx_ring(tx_ring, q_vector->tx) - __ice_queue_set_napi(q_vector->vsi->netdev, tx_ring->q_index, - NETDEV_QUEUE_TYPE_TX, &q_vector->napi, - locked); + ice_for_each_txq(vsi, q_idx) + netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, + &vsi->tx_rings[q_idx]->q_vector->napi); /* Also set the interrupt number for the NAPI */ - netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq); -} + ice_for_each_q_vector(vsi, v_idx) { + struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; -/** - * ice_q_vector_set_napi_queues - Map queue[s] associated with the napi - * @q_vector: q_vector pointer - * - * Associate the q_vector napi with all the queue[s] on the vector - */ -void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector) -{ - struct ice_rx_ring *rx_ring; - struct ice_tx_ring *tx_ring; - - ice_for_each_rx_ring(rx_ring, q_vector->rx) - ice_queue_set_napi(q_vector->vsi, rx_ring->q_index, - NETDEV_QUEUE_TYPE_RX, &q_vector->napi); - - ice_for_each_tx_ring(tx_ring, q_vector->tx) - ice_queue_set_napi(q_vector->vsi, tx_ring->q_index, - NETDEV_QUEUE_TYPE_TX, &q_vector->napi); - /* Also set the interrupt number for the NAPI */ - netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq); + netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq); + } } /** - * ice_vsi_set_napi_queues + * ice_vsi_clear_napi_queues - dissociate netdev queues from napi * @vsi: VSI pointer * - * Associate queue[s] with napi for all vectors + * Clear the association between all VSI queues queue[s] and napi. + * The caller must hold rtnl_lock. */ -void ice_vsi_set_napi_queues(struct ice_vsi *vsi) +void ice_vsi_clear_napi_queues(struct ice_vsi *vsi) { - int i; + struct net_device *netdev = vsi->netdev; + int q_idx; - if (!vsi->netdev) + if (!netdev) return; - ice_for_each_q_vector(vsi, i) - ice_q_vector_set_napi_queues(vsi->q_vectors[i]); + ice_for_each_txq(vsi, q_idx) + netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, NULL); + + ice_for_each_rxq(vsi, q_idx) + netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX, NULL); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 94ce8964dda6..36d86535695d 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -44,16 +44,10 @@ void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc); struct ice_vsi * ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params); -void -ice_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index, - enum netdev_queue_type type, struct napi_struct *napi); - -void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked); - -void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector); - void ice_vsi_set_napi_queues(struct ice_vsi *vsi); +void ice_vsi_clear_napi_queues(struct ice_vsi *vsi); + int ice_vsi_release(struct ice_vsi *vsi); void ice_vsi_close(struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 46d3c5a34d6a..263833346d3a 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3558,11 +3558,9 @@ static void ice_napi_add(struct ice_vsi *vsi) if (!vsi->netdev) return; - ice_for_each_q_vector(vsi, v_idx) { + ice_for_each_q_vector(vsi, v_idx) netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi, ice_napi_poll); - __ice_q_vector_set_napi_queues(vsi->q_vectors[v_idx], false); - } } /** @@ -5540,7 +5538,9 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf) if (ret) goto err_reinit; ice_vsi_map_rings_to_vectors(pf->vsi[v]); + rtnl_lock(); ice_vsi_set_napi_queues(pf->vsi[v]); + rtnl_unlock(); } ret = ice_req_irq_msix_misc(pf); @@ -5554,8 +5554,12 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf) err_reinit: while (v--) - if (pf->vsi[v]) + if (pf->vsi[v]) { + rtnl_lock(); + ice_vsi_clear_napi_queues(pf->vsi[v]); + rtnl_unlock(); ice_vsi_free_q_vectors(pf->vsi[v]); + } return ret; } @@ -5620,6 +5624,9 @@ static int ice_suspend(struct device *dev) ice_for_each_vsi(pf, v) { if (!pf->vsi[v]) continue; + rtnl_lock(); + ice_vsi_clear_napi_queues(pf->vsi[v]); + rtnl_unlock(); ice_vsi_free_q_vectors(pf->vsi[v]); } ice_clear_interrupt_scheme(pf); @@ -7455,6 +7462,8 @@ int ice_vsi_open(struct ice_vsi *vsi) err = netif_set_real_num_rx_queues(vsi->netdev, vsi->num_rxq); if (err) goto err_set_qs; + + ice_vsi_set_napi_queues(vsi); } err = ice_up_complete(vsi); -- cgit v1.2.3 From 2504b8405768a57a71e660dbfd5abd59f679a03f Mon Sep 17 00:00:00 2001 From: Larysa Zaremba Date: Fri, 23 Aug 2024 11:59:27 +0200 Subject: ice: protect XDP configuration with a mutex 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] [ +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] 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 Reviewed-by: Jacob Keller Tested-by: Chandan Kumar Rout Signed-off-by: Larysa Zaremba Reviewed-by: Maciej Fijalkowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice.h | 2 ++ drivers/net/ethernet/intel/ice/ice_lib.c | 34 +++++++++++++++++++------------ drivers/net/ethernet/intel/ice/ice_main.c | 19 ++++++++++++----- drivers/net/ethernet/intel/ice/ice_xsk.c | 3 ++- 4 files changed, 39 insertions(+), 19 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index caaa10157909..ce8b5505b16d 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -318,6 +318,7 @@ enum ice_vsi_state { ICE_VSI_UMAC_FLTR_CHANGED, ICE_VSI_MMAC_FLTR_CHANGED, ICE_VSI_PROMISC_CHANGED, + ICE_VSI_REBUILD_PENDING, ICE_VSI_STATE_NBITS /* must be last */ }; @@ -411,6 +412,7 @@ struct ice_vsi { struct ice_tx_ring **xdp_rings; /* XDP ring array */ u16 num_xdp_txq; /* Used XDP queues */ u8 xdp_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */ + struct mutex xdp_state_lock; struct net_device **target_netdevs; diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 6676596df88b..c1c1b63d9701 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -447,6 +447,7 @@ static void ice_vsi_free(struct ice_vsi *vsi) ice_vsi_free_stats(vsi); ice_vsi_free_arrays(vsi); + mutex_destroy(&vsi->xdp_state_lock); mutex_unlock(&pf->sw_mutex); devm_kfree(dev, vsi); } @@ -626,6 +627,8 @@ static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf) pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi, pf->next_vsi); + mutex_init(&vsi->xdp_state_lock); + unlock_pf: mutex_unlock(&pf->sw_mutex); return vsi; @@ -2972,19 +2975,23 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags) if (WARN_ON(vsi->type == ICE_VSI_VF && !vsi->vf)) return -EINVAL; + mutex_lock(&vsi->xdp_state_lock); + ret = ice_vsi_realloc_stat_arrays(vsi); if (ret) - goto err_vsi_cfg; + goto unlock; ice_vsi_decfg(vsi); ret = ice_vsi_cfg_def(vsi); if (ret) - goto err_vsi_cfg; + goto unlock; coalesce = kcalloc(vsi->num_q_vectors, sizeof(struct ice_coalesce_stored), GFP_KERNEL); - if (!coalesce) - return -ENOMEM; + if (!coalesce) { + ret = -ENOMEM; + goto decfg; + } prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, coalesce); @@ -2992,22 +2999,23 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags) if (ret) { if (vsi_flags & ICE_VSI_FLAG_INIT) { ret = -EIO; - goto err_vsi_cfg_tc_lan; + goto free_coalesce; } - kfree(coalesce); - return ice_schedule_reset(pf, ICE_RESET_PFR); + ret = ice_schedule_reset(pf, ICE_RESET_PFR); + goto free_coalesce; } ice_vsi_rebuild_set_coalesce(vsi, coalesce, prev_num_q_vectors); - kfree(coalesce); + clear_bit(ICE_VSI_REBUILD_PENDING, vsi->state); - return 0; - -err_vsi_cfg_tc_lan: - ice_vsi_decfg(vsi); +free_coalesce: kfree(coalesce); -err_vsi_cfg: +decfg: + if (ret) + ice_vsi_decfg(vsi); +unlock: + mutex_unlock(&vsi->xdp_state_lock); return ret; } diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 263833346d3a..4edaddcba3b4 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -616,6 +616,7 @@ skip: /* clear SW filtering DB */ ice_clear_hw_tbls(hw); /* disable the VSIs and their queues that are not already DOWN */ + set_bit(ICE_VSI_REBUILD_PENDING, ice_get_main_vsi(pf)->state); ice_pf_dis_all_vsi(pf, false); if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) @@ -3016,7 +3017,8 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, } /* hot swap progs and avoid toggling link */ - if (ice_is_xdp_ena_vsi(vsi) == !!prog) { + if (ice_is_xdp_ena_vsi(vsi) == !!prog || + test_bit(ICE_VSI_REBUILD_PENDING, vsi->state)) { ice_vsi_assign_bpf_prog(vsi, prog); return 0; } @@ -3088,21 +3090,28 @@ static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp) { struct ice_netdev_priv *np = netdev_priv(dev); struct ice_vsi *vsi = np->vsi; + int ret; if (vsi->type != ICE_VSI_PF) { NL_SET_ERR_MSG_MOD(xdp->extack, "XDP can be loaded only on PF VSI"); return -EINVAL; } + mutex_lock(&vsi->xdp_state_lock); + switch (xdp->command) { case XDP_SETUP_PROG: - return ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack); + ret = ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack); + break; case XDP_SETUP_XSK_POOL: - return ice_xsk_pool_setup(vsi, xdp->xsk.pool, - xdp->xsk.queue_id); + ret = ice_xsk_pool_setup(vsi, xdp->xsk.pool, xdp->xsk.queue_id); + break; default: - return -EINVAL; + ret = -EINVAL; } + + mutex_unlock(&vsi->xdp_state_lock); + return ret; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 240a7bec242b..a659951fa987 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -390,7 +390,8 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) goto failure; } - if_running = netif_running(vsi->netdev) && ice_is_xdp_ena_vsi(vsi); + if_running = !test_bit(ICE_VSI_DOWN, vsi->state) && + ice_is_xdp_ena_vsi(vsi); if (if_running) { struct ice_rx_ring *rx_ring = vsi->rx_rings[qid]; -- cgit v1.2.3 From f50c68763436bc8f805712a7c5ceaf58cfcf5f07 Mon Sep 17 00:00:00 2001 From: Larysa Zaremba Date: Fri, 23 Aug 2024 11:59:28 +0200 Subject: ice: check for XDP rings instead of bpf program when unconfiguring 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 Reviewed-by: Jacob Keller Tested-by: Chandan Kumar Rout Acked-by: Maciej Fijalkowski Signed-off-by: Larysa Zaremba Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_lib.c | 4 ++-- drivers/net/ethernet/intel/ice/ice_main.c | 4 ++-- drivers/net/ethernet/intel/ice/ice_xsk.c | 6 +++--- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index c1c1b63d9701..3dccfaba024c 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2426,7 +2426,7 @@ void ice_vsi_decfg(struct ice_vsi *vsi) dev_err(ice_pf_to_dev(pf), "Failed to remove RDMA scheduler config for VSI %u, err %d\n", vsi->vsi_num, err); - if (ice_is_xdp_ena_vsi(vsi)) + if (vsi->xdp_rings) /* return value check can be skipped here, it always returns * 0 if reset is in progress */ @@ -2528,7 +2528,7 @@ static void ice_vsi_release_msix(struct ice_vsi *vsi) for (q = 0; q < q_vector->num_ring_tx; q++) { ice_write_itr(&q_vector->tx, 0); wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), 0); - if (ice_is_xdp_ena_vsi(vsi)) { + if (vsi->xdp_rings) { u32 xdp_txq = txq + vsi->num_xdp_txq; wr32(hw, QINT_TQCTL(vsi->txq_map[xdp_txq]), 0); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 4edaddcba3b4..22b8ef5faf8d 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -7249,7 +7249,7 @@ int ice_down(struct ice_vsi *vsi) if (tx_err) netdev_err(vsi->netdev, "Failed stop Tx rings, VSI %d error %d\n", vsi->vsi_num, tx_err); - if (!tx_err && ice_is_xdp_ena_vsi(vsi)) { + if (!tx_err && vsi->xdp_rings) { tx_err = ice_vsi_stop_xdp_tx_rings(vsi); if (tx_err) netdev_err(vsi->netdev, "Failed stop XDP rings, VSI %d error %d\n", @@ -7266,7 +7266,7 @@ int ice_down(struct ice_vsi *vsi) ice_for_each_txq(vsi, i) ice_clean_tx_ring(vsi->tx_rings[i]); - if (ice_is_xdp_ena_vsi(vsi)) + if (vsi->xdp_rings) ice_for_each_xdp_txq(vsi, i) ice_clean_tx_ring(vsi->xdp_rings[i]); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index a659951fa987..8693509efbe7 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -39,7 +39,7 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx) sizeof(vsi_stat->rx_ring_stats[q_idx]->rx_stats)); memset(&vsi_stat->tx_ring_stats[q_idx]->stats, 0, sizeof(vsi_stat->tx_ring_stats[q_idx]->stats)); - if (ice_is_xdp_ena_vsi(vsi)) + if (vsi->xdp_rings) memset(&vsi->xdp_rings[q_idx]->ring_stats->stats, 0, sizeof(vsi->xdp_rings[q_idx]->ring_stats->stats)); } @@ -52,7 +52,7 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx) static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx) { ice_clean_tx_ring(vsi->tx_rings[q_idx]); - if (ice_is_xdp_ena_vsi(vsi)) + if (vsi->xdp_rings) ice_clean_tx_ring(vsi->xdp_rings[q_idx]); ice_clean_rx_ring(vsi->rx_rings[q_idx]); } @@ -194,7 +194,7 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, tx_ring, &txq_meta); if (!fail) fail = err; - if (ice_is_xdp_ena_vsi(vsi)) { + if (vsi->xdp_rings) { struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx]; memset(&txq_meta, 0, sizeof(txq_meta)); -- cgit v1.2.3 From d8c40b9d3a6cef61eb5a0c58c34a3090ea938d89 Mon Sep 17 00:00:00 2001 From: Larysa Zaremba Date: Fri, 23 Aug 2024 11:59:29 +0200 Subject: ice: check ICE_VSI_DOWN under rtnl_lock when preparing for reset Consider the following scenario: .ndo_bpf() | ice_prepare_for_reset() | ________________________|_______________________________________| rtnl_lock() | | ice_down() | | | test_bit(ICE_VSI_DOWN) - true | | ice_dis_vsi() returns | ice_up() | | | proceeds to rebuild a running VSI | .ndo_bpf() is not the only rtnl-locked callback that toggles the interface to apply new configuration. Another example is .set_channels(). To avoid the race condition above, act only after reading ICE_VSI_DOWN under rtnl_lock. Fixes: 0f9d5027a749 ("ice: Refactor VSI allocation, deletion and rebuild flow") Reviewed-by: Wojciech Drewek Reviewed-by: Jacob Keller Tested-by: Chandan Kumar Rout Signed-off-by: Larysa Zaremba Reviewed-by: Maciej Fijalkowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_lib.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 3dccfaba024c..737c00b02dd0 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2672,8 +2672,7 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked) */ void ice_dis_vsi(struct ice_vsi *vsi, bool locked) { - if (test_bit(ICE_VSI_DOWN, vsi->state)) - return; + bool already_down = test_bit(ICE_VSI_DOWN, vsi->state); set_bit(ICE_VSI_NEEDS_RESTART, vsi->state); @@ -2681,15 +2680,16 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked) if (netif_running(vsi->netdev)) { if (!locked) rtnl_lock(); - - ice_vsi_close(vsi); + already_down = test_bit(ICE_VSI_DOWN, vsi->state); + if (!already_down) + ice_vsi_close(vsi); if (!locked) rtnl_unlock(); - } else { + } else if (!already_down) { ice_vsi_close(vsi); } - } else if (vsi->type == ICE_VSI_CTRL) { + } else if (vsi->type == ICE_VSI_CTRL && !already_down) { ice_vsi_close(vsi); } } -- cgit v1.2.3 From 7e3b407ccbea3259b8583ccc34807622025e390f Mon Sep 17 00:00:00 2001 From: Larysa Zaremba Date: Fri, 23 Aug 2024 11:59:30 +0200 Subject: ice: remove ICE_CFG_BUSY locking from AF_XDP code 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 Reviewed-by: Jacob Keller Tested-by: Chandan Kumar Rout Reviewed-by: Maciej Fijalkowski Signed-off-by: Larysa Zaremba Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_xsk.c | 9 --------- 1 file changed, 9 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 8693509efbe7..5dee829bfc47 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -165,7 +165,6 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) struct ice_q_vector *q_vector; struct ice_tx_ring *tx_ring; struct ice_rx_ring *rx_ring; - int timeout = 50; int fail = 0; int err; @@ -176,13 +175,6 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) rx_ring = vsi->rx_rings[q_idx]; q_vector = rx_ring->q_vector; - while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) { - timeout--; - if (!timeout) - return -EBUSY; - usleep_range(1000, 2000); - } - synchronize_net(); netif_carrier_off(vsi->netdev); netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); @@ -261,7 +253,6 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); netif_carrier_on(vsi->netdev); } - clear_bit(ICE_CFG_BUSY, vsi->state); return fail; } -- cgit v1.2.3 From 04c7e14e5b0b6227e7b00d7a96ca2f2426ab9171 Mon Sep 17 00:00:00 2001 From: Larysa Zaremba Date: Fri, 23 Aug 2024 11:59:31 +0200 Subject: ice: do not bring the VSI up, if it was down before the XDP setup After XDP configuration is completed, we bring the interface up unconditionally, regardless of its state before the call to .ndo_bpf(). Preserve the information whether the interface had to be brought down and later bring it up only in such case. Fixes: efc2214b6047 ("ice: Add support for XDP") Reviewed-by: Wojciech Drewek Reviewed-by: Jacob Keller Tested-by: Chandan Kumar Rout Acked-by: Maciej Fijalkowski Signed-off-by: Larysa Zaremba Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_main.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 22b8ef5faf8d..c7db88b517da 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3005,8 +3005,8 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, struct netlink_ext_ack *extack) { unsigned int frame_size = vsi->netdev->mtu + ICE_ETH_PKT_HDR_PAD; - bool if_running = netif_running(vsi->netdev); int ret = 0, xdp_ring_err = 0; + bool if_running; if (prog && !prog->aux->xdp_has_frags) { if (frame_size > ice_max_xdp_frame_size(vsi)) { @@ -3023,8 +3023,11 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, return 0; } + if_running = netif_running(vsi->netdev) && + !test_and_set_bit(ICE_VSI_DOWN, vsi->state); + /* need to stop netdev while setting up the program for Rx rings */ - if (if_running && !test_and_set_bit(ICE_VSI_DOWN, vsi->state)) { + if (if_running) { ret = ice_down(vsi); if (ret) { NL_SET_ERR_MSG_MOD(extack, "Preparing device for XDP attach failed"); -- cgit v1.2.3