From b340dc680ed48dcc05b56e1ebe1b9535813c3ee0 Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Sat, 5 Sep 2020 22:55:36 -0400 Subject: bnxt_en: Avoid sending firmware messages when AER error is detected. When the driver goes through PCIe AER reset in error state, all firmware messages will timeout because the PCIe bus is no longer accessible. This can lead to AER reset taking many minutes to complete as each firmware command takes time to timeout. Define a new macro BNXT_NO_FW_ACCESS() to skip these firmware messages when either firmware is in fatal error state or when pci_channel_offline() is true. It now takes a more reasonable 20 to 30 seconds to complete AER recovery. Fixes: b4fff2079d10 ("bnxt_en: Do not send firmware messages if firmware is in error state.") Signed-off-by: Vasundhara Volam Signed-off-by: Michael Chan Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 +++--- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 4 ++++ 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index b167066af450..619eb556683d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4305,7 +4305,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM; u16 dst = BNXT_HWRM_CHNL_CHIMP; - if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) + if (BNXT_NO_FW_ACCESS(bp)) return -EBUSY; if (msg_len > BNXT_HWRM_MAX_REQ_LEN) { @@ -5723,7 +5723,7 @@ static int hwrm_ring_free_send_msg(struct bnxt *bp, struct hwrm_ring_free_output *resp = bp->hwrm_cmd_resp_addr; u16 error_code; - if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) + if (BNXT_NO_FW_ACCESS(bp)) return 0; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_FREE, cmpl_ring_id, -1); @@ -7817,7 +7817,7 @@ static int bnxt_set_tpa(struct bnxt *bp, bool set_tpa) if (set_tpa) tpa_flags = bp->flags & BNXT_FLAG_TPA; - else if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) + else if (BNXT_NO_FW_ACCESS(bp)) return 0; for (i = 0; i < bp->nr_vnics; i++) { rc = bnxt_hwrm_vnic_set_tpa(bp, i, tpa_flags); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 5a13eb66beda..0ef89dabfd61 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1737,6 +1737,10 @@ struct bnxt { #define BNXT_STATE_FW_FATAL_COND 6 #define BNXT_STATE_DRV_REGISTERED 7 +#define BNXT_NO_FW_ACCESS(bp) \ + (test_bit(BNXT_STATE_FW_FATAL_COND, &(bp)->state) || \ + pci_channel_offline((bp)->pdev)) + struct bnxt_irq *irq_tbl; int total_irqs; u8 mac_addr[ETH_ALEN]; -- cgit v1.2.3 From b16939b59cc00231a75d224fd058d22c9d064976 Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Sat, 5 Sep 2020 22:55:37 -0400 Subject: bnxt_en: Fix NULL ptr dereference crash in bnxt_fw_reset_task() bnxt_fw_reset_task() which runs from a workqueue can race with bnxt_remove_one(). For example, if firmware reset and VF FLR are happening at about the same time. bnxt_remove_one() already cancels the workqueue and waits for it to finish, but we need to do this earlier before the devlink reporters are destroyed. This will guarantee that the devlink reporters will always be valid when bnxt_fw_reset_task() is still running. Fixes: b148bb238c02 ("bnxt_en: Fix possible crash in bnxt_fw_reset_task().") Reviewed-by: Edwin Peer Signed-off-by: Vasundhara Volam Signed-off-by: Michael Chan Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 619eb556683d..8eb73fe39e84 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11779,6 +11779,10 @@ static void bnxt_remove_one(struct pci_dev *pdev) if (BNXT_PF(bp)) bnxt_sriov_disable(bp); + clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); + bnxt_cancel_sp_work(bp); + bp->sp_event = 0; + bnxt_dl_fw_reporters_destroy(bp, true); if (BNXT_PF(bp)) devlink_port_type_clear(&bp->dl_port); @@ -11786,9 +11790,6 @@ static void bnxt_remove_one(struct pci_dev *pdev) unregister_netdev(dev); bnxt_dl_unregister(bp); bnxt_shutdown_tc(bp); - clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); - bnxt_cancel_sp_work(bp); - bp->sp_event = 0; bnxt_clear_int_mode(bp); bnxt_hwrm_func_drv_unrgtr(bp); -- cgit v1.2.3