From e102db780e1c14f10c70dafa7684af22a745b51d Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Tue, 27 Apr 2021 21:52:09 +0200 Subject: ice: track AF_XDP ZC enabled queues in bitmap Commit c7a219048e45 ("ice: Remove xsk_buff_pool from VSI structure") silently introduced a regression and broke the Tx side of AF_XDP in copy mode. xsk_pool on ice_ring is set only based on the existence of the XDP prog on the VSI which in turn picks ice_clean_tx_irq_zc to be executed. That is not something that should happen for copy mode as it should use the regular data path ice_clean_tx_irq. This results in a following splat when xdpsock is run in txonly or l2fwd scenarios in copy mode: [ 106.050195] BUG: kernel NULL pointer dereference, address: 0000000000000030 [ 106.057269] #PF: supervisor read access in kernel mode [ 106.062493] #PF: error_code(0x0000) - not-present page [ 106.067709] PGD 0 P4D 0 [ 106.070293] Oops: 0000 [#1] PREEMPT SMP NOPTI [ 106.074721] CPU: 61 PID: 0 Comm: swapper/61 Not tainted 5.12.0-rc2+ #45 [ 106.081436] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0008.031920191559 03/19/2019 [ 106.092027] RIP: 0010:xp_raw_get_dma+0x36/0x50 [ 106.096551] Code: 74 14 48 b8 ff ff ff ff ff ff 00 00 48 21 f0 48 c1 ee 30 48 01 c6 48 8b 87 90 00 00 00 48 89 f2 81 e6 ff 0f 00 00 48 c1 ea 0c <48> 8b 04 d0 48 83 e0 fe 48 01 f0 c3 66 66 2e 0f 1f 84 00 00 00 00 [ 106.115588] RSP: 0018:ffffc9000d694e50 EFLAGS: 00010206 [ 106.120893] RAX: 0000000000000000 RBX: ffff88984b8c8a00 RCX: ffff889852581800 [ 106.128137] RDX: 0000000000000006 RSI: 0000000000000000 RDI: ffff88984cd8b800 [ 106.135383] RBP: ffff888123b50001 R08: ffff889896800000 R09: 0000000000000800 [ 106.142628] R10: 0000000000000000 R11: ffffffff826060c0 R12: 00000000000000ff [ 106.149872] R13: 0000000000000000 R14: 0000000000000040 R15: ffff888123b50018 [ 106.157117] FS: 0000000000000000(0000) GS:ffff8897e0f40000(0000) knlGS:0000000000000000 [ 106.165332] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 106.171163] CR2: 0000000000000030 CR3: 000000000560a004 CR4: 00000000007706e0 [ 106.178408] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 106.185653] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 106.192898] PKRU: 55555554 [ 106.195653] Call Trace: [ 106.198143] [ 106.200196] ice_clean_tx_irq_zc+0x183/0x2a0 [ice] [ 106.205087] ice_napi_poll+0x3e/0x590 [ice] [ 106.209356] __napi_poll+0x2a/0x160 [ 106.212911] net_rx_action+0xd6/0x200 [ 106.216634] __do_softirq+0xbf/0x29b [ 106.220274] irq_exit_rcu+0x88/0xc0 [ 106.223819] common_interrupt+0x7b/0xa0 [ 106.227719] [ 106.229857] asm_common_interrupt+0x1e/0x40 Fix this by introducing the bitmap of queues that are zero-copy enabled, where each bit, corresponding to a queue id that xsk pool is being configured on, will be set/cleared within ice_xsk_pool_{en,dis}able and checked within ice_xsk_pool(). The latter is a function used for deciding which napi poll routine is executed. Idea is being taken from our other drivers such as i40e and ixgbe. Fixes: c7a219048e45 ("ice: Remove xsk_buff_pool from VSI structure") Signed-off-by: Maciej Fijalkowski Tested-by: Kiran Bhandare Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_lib.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'drivers/net/ethernet/intel/ice/ice_lib.c') diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 82e2ce23df3d..7f7653906fce 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -105,8 +105,14 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi) if (!vsi->q_vectors) goto err_vectors; + vsi->af_xdp_zc_qps = bitmap_zalloc(max_t(int, vsi->alloc_txq, vsi->alloc_rxq), GFP_KERNEL); + if (!vsi->af_xdp_zc_qps) + goto err_zc_qps; + return 0; +err_zc_qps: + devm_kfree(dev, vsi->q_vectors); err_vectors: devm_kfree(dev, vsi->rxq_map); err_rxq_map: @@ -288,6 +294,10 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi) dev = ice_pf_to_dev(pf); + if (vsi->af_xdp_zc_qps) { + bitmap_free(vsi->af_xdp_zc_qps); + vsi->af_xdp_zc_qps = NULL; + } /* free the ring and vector containers */ if (vsi->q_vectors) { devm_kfree(dev, vsi->q_vectors); -- cgit v1.2.3 From f0457690af56673cb0c47af6e25430389a149225 Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Fri, 26 Feb 2021 13:19:20 -0800 Subject: ice: Fix allowing VF to request more/less queues via virtchnl Commit 12bb018c538c ("ice: Refactor VF reset") caused a regression that removes the ability for a VF to request a different amount of queues via VIRTCHNL_OP_REQUEST_QUEUES. This prevents VF drivers to either increase or decrease the number of queue pairs they are allocated. Fix this by using the variable vf->num_req_qs when determining the vf->num_vf_qs during VF VSI creation. Fixes: 12bb018c538c ("ice: Refactor VF reset") Signed-off-by: Brett Creeley Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_lib.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/net/ethernet/intel/ice/ice_lib.c') diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 7f7653906fce..d70ee573fde5 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -200,6 +200,8 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id) break; case ICE_VSI_VF: vf = &pf->vf[vsi->vf_id]; + if (vf->num_req_qs) + vf->num_vf_qs = vf->num_req_qs; vsi->alloc_txq = vf->num_vf_qs; vsi->alloc_rxq = vf->num_vf_qs; /* pf->num_msix_per_vf includes (VF miscellaneous vector + -- cgit v1.2.3 From 2e84f6b3773f43263124c76499c0c4ec3f40aa9b Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Thu, 20 May 2021 08:35:00 +0200 Subject: ice: parameterize functions responsible for Tx ring management Commit ae15e0ba1b33 ("ice: Change number of XDP Tx queues to match number of Rx queues") tried to address the incorrect setting of XDP queue count that was based on the Tx queue count, whereas in theory we should provide the XDP queue per Rx queue. However, the routines that setup and destroy the set of Tx resources are still based on the vsi->num_txq. Ice supports the asynchronous Tx/Rx queue count, so for a setup where vsi->num_txq > vsi->num_rxq, ice_vsi_stop_tx_rings and ice_vsi_cfg_txqs will be accessing the vsi->xdp_rings out of the bounds. Parameterize two mentioned functions so they get the size of Tx resources array as the input. Fixes: ae15e0ba1b33 ("ice: Change number of XDP Tx queues to match number of Rx queues") Signed-off-by: Maciej Fijalkowski Tested-by: Kiran Bhandare Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_lib.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'drivers/net/ethernet/intel/ice/ice_lib.c') diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index d70ee573fde5..27f9dac8719c 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1717,12 +1717,13 @@ setup_rings: * ice_vsi_cfg_txqs - Configure the VSI for Tx * @vsi: the VSI being configured * @rings: Tx ring array to be configured + * @count: number of Tx ring array elements * * Return 0 on success and a negative value on error * Configure the Tx VSI for operation. */ static int -ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings) +ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings, u16 count) { struct ice_aqc_add_tx_qgrp *qg_buf; u16 q_idx = 0; @@ -1734,7 +1735,7 @@ ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings) qg_buf->num_txqs = 1; - for (q_idx = 0; q_idx < vsi->num_txq; q_idx++) { + for (q_idx = 0; q_idx < count; q_idx++) { err = ice_vsi_cfg_txq(vsi, rings[q_idx], qg_buf); if (err) goto err_cfg_txqs; @@ -1754,7 +1755,7 @@ err_cfg_txqs: */ int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi) { - return ice_vsi_cfg_txqs(vsi, vsi->tx_rings); + return ice_vsi_cfg_txqs(vsi, vsi->tx_rings, vsi->num_txq); } /** @@ -1769,7 +1770,7 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi) int ret; int i; - ret = ice_vsi_cfg_txqs(vsi, vsi->xdp_rings); + ret = ice_vsi_cfg_txqs(vsi, vsi->xdp_rings, vsi->num_xdp_txq); if (ret) return ret; @@ -2009,17 +2010,18 @@ int ice_vsi_stop_all_rx_rings(struct ice_vsi *vsi) * @rst_src: reset source * @rel_vmvf_num: Relative ID of VF/VM * @rings: Tx ring array to be stopped + * @count: number of Tx ring array elements */ static int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, - u16 rel_vmvf_num, struct ice_ring **rings) + u16 rel_vmvf_num, struct ice_ring **rings, u16 count) { u16 q_idx; if (vsi->num_txq > ICE_LAN_TXQ_MAX_QDIS) return -EINVAL; - for (q_idx = 0; q_idx < vsi->num_txq; q_idx++) { + for (q_idx = 0; q_idx < count; q_idx++) { struct ice_txq_meta txq_meta = { }; int status; @@ -2047,7 +2049,7 @@ int ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, u16 rel_vmvf_num) { - return ice_vsi_stop_tx_rings(vsi, rst_src, rel_vmvf_num, vsi->tx_rings); + return ice_vsi_stop_tx_rings(vsi, rst_src, rel_vmvf_num, vsi->tx_rings, vsi->num_txq); } /** @@ -2056,7 +2058,7 @@ ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, */ int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi) { - return ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0, vsi->xdp_rings); + return ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0, vsi->xdp_rings, vsi->num_xdp_txq); } /** -- cgit v1.2.3