bnxt_en: add support for storing crash dump into host memory

Newer firmware supports automatic DMA of crash dump to host memory
when it crashes.  If the feature is supported, allocate the required
memory using the existing context memory infrastructure.  Communicate
the page table containing the DMA addresses to the firmware.
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Vikas Gupta <vikas.gupta@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20240828183235.128948-2-michael.chan@broadcom.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -69,6 +69,7 @@
 #include "bnxt_tc.h"
 #include "bnxt_devlink.h"
 #include "bnxt_debugfs.h"
+#include "bnxt_coredump.h"
 #include "bnxt_hwmon.h"
 
 #define BNXT_TX_TIMEOUT		(5 * HZ)
@@ -8946,6 +8947,80 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	return 0;
 }
 
+static int bnxt_hwrm_crash_dump_mem_cfg(struct bnxt *bp)
+{
+	struct hwrm_dbg_crashdump_medium_cfg_input *req;
+	u16 page_attr;
+	int rc;
+
+	if (!(bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR))
+		return 0;
+
+	rc = hwrm_req_init(bp, req, HWRM_DBG_CRASHDUMP_MEDIUM_CFG);
+	if (rc)
+		return rc;
+
+	if (BNXT_PAGE_SIZE == 0x2000)
+		page_attr = DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_8K;
+	else if (BNXT_PAGE_SIZE == 0x10000)
+		page_attr = DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_64K;
+	else
+		page_attr = DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_4K;
+	req->pg_size_lvl = cpu_to_le16(page_attr |
+				       bp->fw_crash_mem->ring_mem.depth);
+	req->pbl = cpu_to_le64(bp->fw_crash_mem->ring_mem.pg_tbl_map);
+	req->size = cpu_to_le32(bp->fw_crash_len);
+	req->output_dest_flags = cpu_to_le16(BNXT_DBG_CR_DUMP_MDM_CFG_DDR);
+	return hwrm_req_send(bp, req);
+}
+
+static void bnxt_free_crash_dump_mem(struct bnxt *bp)
+{
+	if (bp->fw_crash_mem) {
+		bnxt_free_ctx_pg_tbls(bp, bp->fw_crash_mem);
+		kfree(bp->fw_crash_mem);
+		bp->fw_crash_mem = NULL;
+	}
+}
+
+static int bnxt_alloc_crash_dump_mem(struct bnxt *bp)
+{
+	u32 mem_size = 0;
+	int rc;
+
+	if (!(bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR))
+		return 0;
+
+	rc = bnxt_hwrm_get_dump_len(bp, BNXT_DUMP_CRASH, &mem_size);
+	if (rc)
+		return rc;
+
+	mem_size = round_up(mem_size, 4);
+
+	/* keep and use the existing pages */
+	if (bp->fw_crash_mem &&
+	    mem_size <= bp->fw_crash_mem->nr_pages * BNXT_PAGE_SIZE)
+		goto alloc_done;
+
+	if (bp->fw_crash_mem)
+		bnxt_free_ctx_pg_tbls(bp, bp->fw_crash_mem);
+	else
+		bp->fw_crash_mem = kzalloc(sizeof(*bp->fw_crash_mem),
+					   GFP_KERNEL);
+	if (!bp->fw_crash_mem)
+		return -ENOMEM;
+
+	rc = bnxt_alloc_ctx_pg_tbls(bp, bp->fw_crash_mem, mem_size, 1, NULL);
+	if (rc) {
+		bnxt_free_crash_dump_mem(bp);
+		return rc;
+	}
+
+alloc_done:
+	bp->fw_crash_len = mem_size;
+	return 0;
+}
+
 int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all)
 {
 	struct hwrm_func_resource_qcaps_output *resp;
@@ -13986,6 +14061,19 @@ static int bnxt_fw_init_one_p2(struct bnxt *bp)
 	if (rc)
 		return -ENODEV;
 
+	rc = bnxt_alloc_crash_dump_mem(bp);
+	if (rc)
+		netdev_warn(bp->dev, "crash dump mem alloc failure rc: %d\n",
+			    rc);
+	if (!rc) {
+		rc = bnxt_hwrm_crash_dump_mem_cfg(bp);
+		if (rc) {
+			bnxt_free_crash_dump_mem(bp);
+			netdev_warn(bp->dev,
+				    "hwrm crash dump mem failure rc: %d\n", rc);
+		}
+	}
+
 	if (bnxt_fw_pre_resv_vnics(bp))
 		bp->fw_cap |= BNXT_FW_CAP_PRE_RESV_VNICS;
 
@@ -15294,6 +15382,7 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	bp->fw_health = NULL;
 	bnxt_cleanup_pci(bp);
 	bnxt_free_ctx_mem(bp);
+	bnxt_free_crash_dump_mem(bp);
 	kfree(bp->rss_indir_tbl);
 	bp->rss_indir_tbl = NULL;
 	bnxt_free_port_stats(bp);
@@ -15933,6 +16022,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	bp->fw_health = NULL;
 	bnxt_cleanup_pci(bp);
 	bnxt_free_ctx_mem(bp);
+	bnxt_free_crash_dump_mem(bp);
 	kfree(bp->rss_indir_tbl);
 	bp->rss_indir_tbl = NULL;
 
@@ -16024,6 +16114,8 @@ static int bnxt_resume(struct device *device)
 		rc = -ENODEV;
 		goto resume_exit;
 	}
+	if (bp->fw_crash_mem)
+		bnxt_hwrm_crash_dump_mem_cfg(bp);
 
 	bnxt_get_wol_settings(bp);
 	if (netif_running(dev)) {

drivers/net/ethernet/broadcom/bnxt/bnxt.h

@@ -2649,6 +2649,9 @@ struct bnxt {
 #endif
 	u32			thermal_threshold_type;
 	enum board_idx		board_idx;
+
+	struct bnxt_ctx_pg_info	*fw_crash_mem;
+	u32			fw_crash_len;
 };
 
 #define BNXT_NUM_RX_RING_STATS			8

drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c

@@ -385,7 +385,7 @@ int bnxt_get_coredump(struct bnxt *bp, u16 dump_type, void *buf, u32 *dump_len)
 	}
 }
 
-static int bnxt_hwrm_get_dump_len(struct bnxt *bp, u16 dump_type, u32 *dump_len)
+int bnxt_hwrm_get_dump_len(struct bnxt *bp, u16 dump_type, u32 *dump_len)
 {
 	struct hwrm_dbg_qcfg_output *resp;
 	struct hwrm_dbg_qcfg_input *req;
@@ -395,7 +395,8 @@ static int bnxt_hwrm_get_dump_len(struct bnxt *bp, u16 dump_type, u32 *dump_len)
 		return -EOPNOTSUPP;
 
 	if (dump_type == BNXT_DUMP_CRASH &&
-	    !(bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR))
+	    !(bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR ||
+	     (bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR)))
 		return -EOPNOTSUPP;
 
 	rc = hwrm_req_init(bp, req, HWRM_DBG_QCFG);
@@ -403,8 +404,12 @@ static int bnxt_hwrm_get_dump_len(struct bnxt *bp, u16 dump_type, u32 *dump_len)
 		return rc;
 
 	req->fid = cpu_to_le16(0xffff);
-	if (dump_type == BNXT_DUMP_CRASH)
-		req->flags = cpu_to_le16(DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_SOC_DDR);
+	if (dump_type == BNXT_DUMP_CRASH) {
+		if (bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR)
+			req->flags = cpu_to_le16(BNXT_DBG_FL_CR_DUMP_SIZE_SOC);
+		else
+			req->flags = cpu_to_le16(BNXT_DBG_FL_CR_DUMP_SIZE_HOST);
+	}
 
 	resp = hwrm_req_hold(bp, req);
 	rc = hwrm_req_send(bp, req);
@@ -412,7 +417,10 @@ static int bnxt_hwrm_get_dump_len(struct bnxt *bp, u16 dump_type, u32 *dump_len)
 		goto get_dump_len_exit;
 
 	if (dump_type == BNXT_DUMP_CRASH) {
-		*dump_len = le32_to_cpu(resp->crashdump_size);
+		if (bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR)
+			*dump_len = BNXT_CRASH_DUMP_LEN;
+		else
+			*dump_len = le32_to_cpu(resp->crashdump_size);
 	} else {
 		/* Driver adds coredump header and "HWRM_VER_GET response"
 		 * segment additionally to coredump.

drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h

@@ -111,7 +111,15 @@ struct hwrm_dbg_cmn_output {
 	#define HWRM_DBG_CMN_FLAGS_MORE	1
 };
 
+#define BNXT_DBG_FL_CR_DUMP_SIZE_SOC	\
+	DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_SOC_DDR
+#define BNXT_DBG_FL_CR_DUMP_SIZE_HOST	\
+	DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_HOST_DDR
+#define BNXT_DBG_CR_DUMP_MDM_CFG_DDR	\
+	DBG_CRASHDUMP_MEDIUM_CFG_REQ_TYPE_DDR
+
 int bnxt_get_coredump(struct bnxt *bp, u16 dump_type, void *buf, u32 *dump_len);
+int bnxt_hwrm_get_dump_len(struct bnxt *bp, u16 dump_type, u32 *dump_len);
 u32 bnxt_get_coredump_length(struct bnxt *bp, u16 dump_type);
 
 #endif