From: Michael Chan <michael.chan@broadcom.com>
To: davem@davemloft.net
Cc: netdev@vger.kernel.org, vasundhara-v.volam@broadcom.com,
ray.jui@broadcom.com
Subject: [PATCH net-next v2 10/22] bnxt_en: Discover firmware error recovery capabilities.
Date: Thu, 29 Aug 2019 23:54:53 -0400 [thread overview]
Message-ID: <1567137305-5853-11-git-send-email-michael.chan@broadcom.com> (raw)
In-Reply-To: <1567137305-5853-1-git-send-email-michael.chan@broadcom.com>
Call the new firmware API HWRM_ERROR_RECOVERY_QCFG if it is supported
to discover the firmware health and recovery capabilities and settings.
This feature allows the driver to reset the chip if firmware crashes and
becomes unresponsive.
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 77 +++++++++++++++++++++++++++++++
drivers/net/ethernet/broadcom/bnxt/bnxt.h | 38 +++++++++++++++
2 files changed, 115 insertions(+)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 303933b..825a7f9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6847,6 +6847,8 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
bp->fw_cap |= BNXT_FW_CAP_PCIE_STATS_SUPPORTED;
if (flags & FUNC_QCAPS_RESP_FLAGS_EXT_STATS_SUPPORTED)
bp->fw_cap |= BNXT_FW_CAP_EXT_STATS_SUPPORTED;
+ if (flags & FUNC_QCAPS_RESP_FLAGS_ERROR_RECOVERY_CAPABLE)
+ bp->fw_cap |= BNXT_FW_CAP_ERROR_RECOVERY;
bp->tx_push_thresh = 0;
if (flags & FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED)
@@ -6948,6 +6950,74 @@ static int bnxt_hwrm_cfa_adv_flow_mgnt_qcaps(struct bnxt *bp)
return rc;
}
+static int bnxt_hwrm_error_recovery_qcfg(struct bnxt *bp)
+{
+ struct hwrm_error_recovery_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
+ struct bnxt_fw_health *fw_health = bp->fw_health;
+ struct hwrm_error_recovery_qcfg_input req = {0};
+ int rc, i;
+
+ if (!(bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY))
+ return 0;
+
+ bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_ERROR_RECOVERY_QCFG, -1, -1);
+ mutex_lock(&bp->hwrm_cmd_lock);
+ rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+ if (rc)
+ goto err_recovery_out;
+ if (!fw_health) {
+ fw_health = kzalloc(sizeof(*fw_health), GFP_KERNEL);
+ bp->fw_health = fw_health;
+ if (!fw_health) {
+ rc = -ENOMEM;
+ goto err_recovery_out;
+ }
+ }
+ fw_health->flags = le32_to_cpu(resp->flags);
+ if ((fw_health->flags & ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU) &&
+ !(bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL)) {
+ rc = -EINVAL;
+ goto err_recovery_out;
+ }
+ fw_health->polling_dsecs = le32_to_cpu(resp->driver_polling_freq);
+ fw_health->master_func_wait_dsecs =
+ le32_to_cpu(resp->master_func_wait_period);
+ fw_health->normal_func_wait_dsecs =
+ le32_to_cpu(resp->normal_func_wait_period);
+ fw_health->post_reset_wait_dsecs =
+ le32_to_cpu(resp->master_func_wait_period_after_reset);
+ fw_health->post_reset_max_wait_dsecs =
+ le32_to_cpu(resp->max_bailout_time_after_reset);
+ fw_health->regs[BNXT_FW_HEALTH_REG] =
+ le32_to_cpu(resp->fw_health_status_reg);
+ fw_health->regs[BNXT_FW_HEARTBEAT_REG] =
+ le32_to_cpu(resp->fw_heartbeat_reg);
+ fw_health->regs[BNXT_FW_RESET_CNT_REG] =
+ le32_to_cpu(resp->fw_reset_cnt_reg);
+ fw_health->regs[BNXT_FW_RESET_INPROG_REG] =
+ le32_to_cpu(resp->reset_inprogress_reg);
+ fw_health->fw_reset_inprog_reg_mask =
+ le32_to_cpu(resp->reset_inprogress_reg_mask);
+ fw_health->fw_reset_seq_cnt = resp->reg_array_cnt;
+ if (fw_health->fw_reset_seq_cnt >= 16) {
+ rc = -EINVAL;
+ goto err_recovery_out;
+ }
+ for (i = 0; i < fw_health->fw_reset_seq_cnt; i++) {
+ fw_health->fw_reset_seq_regs[i] =
+ le32_to_cpu(resp->reset_reg[i]);
+ fw_health->fw_reset_seq_vals[i] =
+ le32_to_cpu(resp->reset_reg_val[i]);
+ fw_health->fw_reset_seq_delay_msec[i] =
+ resp->delay_after_reset[i];
+ }
+err_recovery_out:
+ mutex_unlock(&bp->hwrm_cmd_lock);
+ if (rc)
+ bp->fw_cap &= ~BNXT_FW_CAP_ERROR_RECOVERY;
+ return rc;
+}
+
static int bnxt_hwrm_func_reset(struct bnxt *bp)
{
struct hwrm_func_reset_input req = {0};
@@ -10058,6 +10128,11 @@ static int bnxt_fw_init_one_p2(struct bnxt *bp)
netdev_warn(bp->dev, "hwrm query adv flow mgnt failure rc: %d\n",
rc);
+ rc = bnxt_hwrm_error_recovery_qcfg(bp);
+ if (rc)
+ netdev_warn(bp->dev, "hwrm query error recovery failure rc: %d\n",
+ rc);
+
rc = bnxt_hwrm_func_drv_rgtr(bp);
if (rc)
return -ENODEV;
@@ -11238,6 +11313,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
bnxt_free_ctx_mem(bp);
kfree(bp->ctx);
bp->ctx = NULL;
+ kfree(bp->fw_health);
+ bp->fw_health = NULL;
bnxt_cleanup_pci(bp);
init_err_free:
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 3e0fcc2..ce535e5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1333,6 +1333,41 @@ struct bnxt_ctx_mem_info {
struct bnxt_ctx_pg_info *tqm_mem[9];
};
+struct bnxt_fw_health {
+ u32 flags;
+ u32 polling_dsecs;
+ u32 master_func_wait_dsecs;
+ u32 normal_func_wait_dsecs;
+ u32 post_reset_wait_dsecs;
+ u32 post_reset_max_wait_dsecs;
+ u32 regs[4];
+ u32 mapped_regs[4];
+#define BNXT_FW_HEALTH_REG 0
+#define BNXT_FW_HEARTBEAT_REG 1
+#define BNXT_FW_RESET_CNT_REG 2
+#define BNXT_FW_RESET_INPROG_REG 3
+ u32 fw_reset_inprog_reg_mask;
+ u32 last_fw_heartbeat;
+ u32 last_fw_reset_cnt;
+ u8 enabled:1;
+ u8 master:1;
+ u8 tmr_multiplier;
+ u8 tmr_counter;
+ u8 fw_reset_seq_cnt;
+ u32 fw_reset_seq_regs[16];
+ u32 fw_reset_seq_vals[16];
+ u32 fw_reset_seq_delay_msec[16];
+};
+
+#define BNXT_FW_HEALTH_REG_TYPE_MASK 3
+#define BNXT_FW_HEALTH_REG_TYPE_CFG 0
+#define BNXT_FW_HEALTH_REG_TYPE_GRC 1
+#define BNXT_FW_HEALTH_REG_TYPE_BAR0 2
+#define BNXT_FW_HEALTH_REG_TYPE_BAR1 3
+
+#define BNXT_FW_HEALTH_REG_TYPE(reg) ((reg) & BNXT_FW_HEALTH_REG_TYPE_MASK)
+#define BNXT_FW_HEALTH_REG_OFF(reg) ((reg) & ~BNXT_FW_HEALTH_REG_TYPE_MASK)
+
struct bnxt {
void __iomem *bar0;
void __iomem *bar1;
@@ -1581,6 +1616,7 @@ struct bnxt {
#define BNXT_FW_CAP_KONG_MB_CHNL 0x00000080
#define BNXT_FW_CAP_OVS_64BIT_HANDLE 0x00000400
#define BNXT_FW_CAP_TRUSTED_VF 0x00000800
+ #define BNXT_FW_CAP_ERROR_RECOVERY 0x00002000
#define BNXT_FW_CAP_PKG_VER 0x00004000
#define BNXT_FW_CAP_CFA_ADV_FLOW 0x00008000
#define BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX 0x00010000
@@ -1666,6 +1702,8 @@ struct bnxt {
#define BNXT_UPDATE_PHY_SP_EVENT 16
#define BNXT_RING_COAL_NOW_SP_EVENT 17
+ struct bnxt_fw_health *fw_health;
+
struct bnxt_hw_resc hw_resc;
struct bnxt_pf_info pf;
struct bnxt_ctx_mem_info *ctx;
--
2.5.1
next prev parent reply other threads:[~2019-08-30 3:56 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-08-30 3:54 [PATCH net-next v2 00/22] bnxt_en: health and error recovery Michael Chan
2019-08-30 3:54 ` [PATCH net-next v2 01/22] bnxt_en: Use a common function to print the same ethtool -f error message Michael Chan
2019-08-30 3:54 ` [PATCH net-next v2 02/22] bnxt_en: Remove the -1 error return code from bnxt_hwrm_do_send_msg() Michael Chan
2019-08-30 3:54 ` [PATCH net-next v2 03/22] bnxt_en: Convert error code in firmware message response to standard code Michael Chan
2019-08-30 3:54 ` [PATCH net-next v2 04/22] bnxt_en: Simplify error checking in the SR-IOV message forwarding functions Michael Chan
2019-08-30 3:54 ` [PATCH net-next v2 05/22] bnxt_en: Suppress all error messages in hwrm_do_send_msg() in silent mode Michael Chan
2019-08-30 3:54 ` [PATCH net-next v2 06/22] bnxt_en: Prepare bnxt_init_one() to be called multiple times Michael Chan
2019-08-30 3:54 ` [PATCH net-next v2 07/22] bnxt_en: Refactor bnxt_sriov_enable() Michael Chan
2019-08-30 3:54 ` [PATCH net-next v2 08/22] bnxt_en: Register buffers for VFs before reserving resources Michael Chan
2019-08-30 3:54 ` [PATCH net-next v2 09/22] bnxt_en: Handle firmware reset status during IF_UP Michael Chan
2019-08-30 3:54 ` Michael Chan [this message]
2019-08-30 3:54 ` [PATCH net-next v2 11/22] bnxt_en: Pre-map the firmware health monitoring registers Michael Chan
2019-08-30 3:54 ` [PATCH net-next v2 12/22] bnxt_en: Enable health monitoring Michael Chan
2019-08-30 3:54 ` [PATCH net-next v2 13/22] bnxt_en: Add BNXT_STATE_IN_FW_RESET state Michael Chan
2019-08-30 3:54 ` [PATCH net-next v2 14/22] bnxt_en: Add new FW devlink_health_reporter Michael Chan
2019-10-07 9:56 ` Jiri Pirko
2019-10-09 4:55 ` Vasundhara Volam
2019-10-09 7:04 ` Jiri Pirko
2019-08-30 3:54 ` [PATCH net-next v2 15/22] bnxt_en: Handle RESET_NOTIFY async event from firmware Michael Chan
2019-08-30 3:54 ` [PATCH net-next v2 16/22] bnxt_en: Handle firmware reset Michael Chan
2019-08-30 17:56 ` kbuild test robot
2019-08-30 3:55 ` [PATCH net-next v2 17/22] bnxt_en: Add devlink health reset reporter Michael Chan
2019-08-30 3:55 ` [PATCH net-next v2 18/22] bnxt_en: Retain user settings on a VF after RESET_NOTIFY event Michael Chan
2019-08-30 3:55 ` [PATCH net-next v2 19/22] bnxt_en: Do not send firmware messages if firmware is in error state Michael Chan
2019-08-30 3:55 ` [PATCH net-next v2 20/22] bnxt_en: Add RESET_FW state logic to bnxt_fw_reset_task() Michael Chan
2019-08-30 3:55 ` [PATCH net-next v2 21/22] bnxt_en: Add bnxt_fw_exception() to handle fatal firmware errors Michael Chan
2019-08-30 3:55 ` [PATCH net-next v2 22/22] bnxt_en: Add FW fatal devlink_health_reporter Michael Chan
2019-08-30 21:02 ` [PATCH net-next v2 00/22] bnxt_en: health and error recovery David Miller
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1567137305-5853-11-git-send-email-michael.chan@broadcom.com \
--to=michael.chan@broadcom.com \
--cc=davem@davemloft.net \
--cc=netdev@vger.kernel.org \
--cc=ray.jui@broadcom.com \
--cc=vasundhara-v.volam@broadcom.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).