From b4c66425771ddb910316c7b4cd7fa0614098ec45 Mon Sep 17 00:00:00 2001 From: Vikas Gupta Date: Thu, 3 Nov 2022 19:33:24 -0400 Subject: bnxt_en: refactor bnxt_cancel_reservations() Introduce bnxt_clear_reservations() to clear the reserved attributes only. This will be used in the next patch to fix PCI AER handling. Signed-off-by: Vikas Gupta Signed-off-by: Michael Chan Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 04cf7684f1b0..3743d9755eb4 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -9983,17 +9983,12 @@ static int bnxt_try_recover_fw(struct bnxt *bp) return -ENODEV; } -int bnxt_cancel_reservations(struct bnxt *bp, bool fw_reset) +static void bnxt_clear_reservations(struct bnxt *bp, bool fw_reset) { struct bnxt_hw_resc *hw_resc = &bp->hw_resc; - int rc; if (!BNXT_NEW_RM(bp)) - return 0; /* no resource reservations required */ - - rc = bnxt_hwrm_func_resc_qcaps(bp, true); - if (rc) - netdev_err(bp->dev, "resc_qcaps failed\n"); + return; /* no resource reservations required */ hw_resc->resv_cp_rings = 0; hw_resc->resv_stat_ctxs = 0; @@ -10006,6 +10001,20 @@ int bnxt_cancel_reservations(struct bnxt *bp, bool fw_reset) bp->tx_nr_rings = 0; bp->rx_nr_rings = 0; } +} + +int bnxt_cancel_reservations(struct bnxt *bp, bool fw_reset) +{ + int rc; + + if (!BNXT_NEW_RM(bp)) + return 0; /* no resource reservations required */ + + rc = bnxt_hwrm_func_resc_qcaps(bp, true); + if (rc) + netdev_err(bp->dev, "resc_qcaps failed\n"); + + bnxt_clear_reservations(bp, fw_reset); return rc; } -- cgit From 0cf736a18a1e804037839bd8df9e36f0efdb8745 Mon Sep 17 00:00:00 2001 From: Vikas Gupta Date: Thu, 3 Nov 2022 19:33:25 -0400 Subject: bnxt_en: fix the handling of PCIE-AER Fix the sequence required for PCIE-AER. While slot reset occurs, firmware might not be ready and the driver needs to check for its recovery. We also need to remap the health registers for some chips and clear the resource reservations. The resources will be allocated again during bnxt_io_resume(). Fixes: fb1e6e562b37 ("bnxt_en: Fix AER recovery.") Signed-off-by: Vikas Gupta Signed-off-by: Michael Chan Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 29 +++++++++++++++++++++++++- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 1 + drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c | 3 ++- 3 files changed, 31 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 3743d9755eb4..f44f9367b7fd 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -13922,7 +13922,9 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) pci_ers_result_t result = PCI_ERS_RESULT_DISCONNECT; struct net_device *netdev = pci_get_drvdata(pdev); struct bnxt *bp = netdev_priv(netdev); - int err = 0, off; + int retry = 0; + int err = 0; + int off; netdev_info(bp->dev, "PCI Slot Reset\n"); @@ -13950,11 +13952,36 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) pci_restore_state(pdev); pci_save_state(pdev); + bnxt_inv_fw_health_reg(bp); + bnxt_try_map_fw_health_reg(bp); + + /* In some PCIe AER scenarios, firmware may take up to + * 10 seconds to become ready in the worst case. + */ + do { + err = bnxt_try_recover_fw(bp); + if (!err) + break; + retry++; + } while (retry < BNXT_FW_SLOT_RESET_RETRY); + + if (err) { + dev_err(&pdev->dev, "Firmware not ready\n"); + goto reset_exit; + } + err = bnxt_hwrm_func_reset(bp); if (!err) result = PCI_ERS_RESULT_RECOVERED; + + bnxt_ulp_irq_stop(bp); + bnxt_clear_int_mode(bp); + err = bnxt_init_int_mode(bp); + bnxt_ulp_irq_restart(bp, err); } +reset_exit: + bnxt_clear_reservations(bp, true); rtnl_unlock(); return result; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index b1b17f911300..d5fa43cfe524 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1621,6 +1621,7 @@ struct bnxt_fw_health { #define BNXT_FW_RETRY 5 #define BNXT_FW_IF_RETRY 10 +#define BNXT_FW_SLOT_RESET_RETRY 4 enum board_idx { BCM57301, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c index b01d42928a53..132442f16fe6 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c @@ -476,7 +476,8 @@ static int __hwrm_send(struct bnxt *bp, struct bnxt_hwrm_ctx *ctx) memset(ctx->resp, 0, PAGE_SIZE); req_type = le16_to_cpu(ctx->req->req_type); - if (BNXT_NO_FW_ACCESS(bp) && req_type != HWRM_FUNC_RESET) { + if (BNXT_NO_FW_ACCESS(bp) && + (req_type != HWRM_FUNC_RESET && req_type != HWRM_VER_GET)) { netdev_dbg(bp->dev, "hwrm req_type 0x%x skipped, FW channel down\n", req_type); goto exit; -- cgit From 6d81ea3765dfa6c8a20822613c81edad1c4a16a0 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Thu, 3 Nov 2022 19:33:26 -0400 Subject: bnxt_en: Fix possible crash in bnxt_hwrm_set_coal() During the error recovery sequence, the rtnl_lock is not held for the entire duration and some datastructures may be freed during the sequence. Check for the BNXT_STATE_OPEN flag instead of netif_running() to ensure that the device is fully operational before proceeding to reconfigure the coalescing settings. This will fix a possible crash like this: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 PGD 0 P4D 0 Oops: 0000 [#1] SMP NOPTI CPU: 10 PID: 181276 Comm: ethtool Kdump: loaded Tainted: G IOE --------- - - 4.18.0-348.el8.x86_64 #1 Hardware name: Dell Inc. PowerEdge R740/0F9N89, BIOS 2.3.10 08/15/2019 RIP: 0010:bnxt_hwrm_set_coal+0x1fb/0x2a0 [bnxt_en] Code: c2 66 83 4e 22 08 66 89 46 1c e8 10 cb 00 00 41 83 c6 01 44 39 b3 68 01 00 00 0f 8e a3 00 00 00 48 8b 93 c8 00 00 00 49 63 c6 <48> 8b 2c c2 48 8b 85 b8 02 00 00 48 85 c0 74 2e 48 8b 74 24 08 f6 RSP: 0018:ffffb11c8dcaba50 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff8d168a8b0ac0 RCX: 00000000000000c5 RDX: 0000000000000000 RSI: ffff8d162f72c000 RDI: ffff8d168a8b0b28 RBP: 0000000000000000 R08: b6e1f68a12e9a7eb R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000037 R12: ffff8d168a8b109c R13: ffff8d168a8b10aa R14: 0000000000000000 R15: ffffffffc01ac4e0 FS: 00007f3852e4c740(0000) GS:ffff8d24c0080000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000041b3ee003 CR4: 00000000007706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: ethnl_set_coalesce+0x3ce/0x4c0 genl_family_rcv_msg_doit.isra.15+0x10f/0x150 genl_family_rcv_msg+0xb3/0x160 ? coalesce_fill_reply+0x480/0x480 genl_rcv_msg+0x47/0x90 ? genl_family_rcv_msg+0x160/0x160 netlink_rcv_skb+0x4c/0x120 genl_rcv+0x24/0x40 netlink_unicast+0x196/0x230 netlink_sendmsg+0x204/0x3d0 sock_sendmsg+0x4c/0x50 __sys_sendto+0xee/0x160 ? syscall_trace_enter+0x1d3/0x2c0 ? __audit_syscall_exit+0x249/0x2a0 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x5b/0x1a0 entry_SYSCALL_64_after_hwframe+0x65/0xca RIP: 0033:0x7f38524163bb Fixes: 2151fe0830fd ("bnxt_en: Handle RESET_NOTIFY async event from firmware.") Reviewed-by: Somnath Kotur Signed-off-by: Michael Chan Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index f57e524c7e30..8cad15c458b3 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -162,7 +162,7 @@ static int bnxt_set_coalesce(struct net_device *dev, } reset_coalesce: - if (netif_running(dev)) { + if (test_bit(BNXT_STATE_OPEN, &bp->state)) { if (update_stats) { rc = bnxt_close_nic(bp, true, false); if (!rc) -- cgit From 02597d39145bb0aa81d04bf39b6a913ce9a9d465 Mon Sep 17 00:00:00 2001 From: Alex Barba Date: Thu, 3 Nov 2022 19:33:27 -0400 Subject: bnxt_en: fix potentially incorrect return value for ndo_rx_flow_steer In the bnxt_en driver ndo_rx_flow_steer returns '0' whenever an entry that we are attempting to steer is already found. This is not the correct behavior. The return code should be the value/index that corresponds to the entry. Returning zero all the time causes the RFS records to be incorrect unless entry '0' is the correct one. As flows migrate to different cores this can create entries that are not correct. Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.") Reported-by: Akshay Navgire Signed-off-by: Alex Barba Signed-off-by: Andy Gospodarek Signed-off-by: Michael Chan Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index f44f9367b7fd..c78b6e9dea2c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -12903,8 +12903,8 @@ static int bnxt_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, rcu_read_lock(); hlist_for_each_entry_rcu(fltr, head, hash) { if (bnxt_fltr_match(fltr, new_fltr)) { + rc = fltr->sw_id; rcu_read_unlock(); - rc = 0; goto err_free; } } -- cgit