[PATCH V3 1/1] nvme: Add verbose error logging
Alan Adamson
alan.adamson at oracle.com
Wed Jan 5 10:32:49 PST 2022
Improves logging of NVMe errors. If NVME_VERBOSE_ERRORS is configured,
a verbose description of the error is logged, otherwise only status codes/bits
is logged.
Verbose logging example:
nvme0n1: Read @ LBA 2304, 1 blocks, Unrecovered Read Error (sct 0x2 / sc 0x81) DNR
Non-verbose logging example:
nvme0n1: Read @ LBA 2304, 1 blocks, NVME Error (sct 0x2 / sc 0x81) DNR
Signed-off-by: Martin K. Petersen <martin.petersen at oracle.com>
Signed-off-by: Alan Adamson <alan.adamson at oracle.com>
Reviewed-by: Himanshu Madhani <himanshu.madhani at oracle.com>
---
drivers/nvme/host/Kconfig | 8 ++
drivers/nvme/host/Makefile | 2 +-
drivers/nvme/host/core.c | 3 +
drivers/nvme/host/errors.c | 181 +++++++++++++++++++++++++++++++++++++
drivers/nvme/host/nvme.h | 2 +
include/linux/nvme.h | 1 +
6 files changed, 196 insertions(+), 1 deletion(-)
create mode 100644 drivers/nvme/host/errors.c
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index dc0450ca23a3..d6d056963c06 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -24,6 +24,14 @@ config NVME_MULTIPATH
/dev/nvmeXnY device will show up for each NVMe namespace,
even if it is accessible through multiple controllers.
+config NVME_VERBOSE_ERRORS
+ bool "NVMe verbose error reporting"
+ depends on NVME_CORE
+ help
+ This option enables verbose reporting for NVMe errors. The
+ error translation table will grow the kernel image size by
+ about 4 KB.
+
config NVME_HWMON
bool "NVMe hardware monitoring"
depends on (NVME_CORE=y && HWMON=y) || (NVME_CORE=m && HWMON)
diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile
index dfaacd472e5d..ea3d702feb51 100644
--- a/drivers/nvme/host/Makefile
+++ b/drivers/nvme/host/Makefile
@@ -9,7 +9,7 @@ obj-$(CONFIG_NVME_RDMA) += nvme-rdma.o
obj-$(CONFIG_NVME_FC) += nvme-fc.o
obj-$(CONFIG_NVME_TCP) += nvme-tcp.o
-nvme-core-y := core.o ioctl.o
+nvme-core-y := core.o ioctl.o errors.o
nvme-core-$(CONFIG_TRACING) += trace.o
nvme-core-$(CONFIG_NVME_MULTIPATH) += multipath.o
nvme-core-$(CONFIG_BLK_DEV_ZONED) += zns.o
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 1af8a4513708..fda029a55436 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -354,6 +354,9 @@ void nvme_complete_rq(struct request *req)
switch (nvme_decide_disposition(req)) {
case COMPLETE:
+ if (unlikely(nvme_req(req)->status != NVME_SC_SUCCESS))
+ nvme_error_log(req);
+
nvme_end_req(req);
return;
case RETRY:
diff --git a/drivers/nvme/host/errors.c b/drivers/nvme/host/errors.c
new file mode 100644
index 000000000000..2668d2f584e2
--- /dev/null
+++ b/drivers/nvme/host/errors.c
@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVM Express device driver verbose errors
+ * Copyright (c) 2021, Oracle and/or its affiliates
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/blkdev.h>
+#include "nvme.h"
+
+struct nvme_string_table {
+ unsigned int code;
+ const unsigned char *string;
+};
+
+static const struct nvme_string_table nvme_ops[] = {
+ { REQ_OP_READ, "Read" },
+ { REQ_OP_WRITE, "Write" },
+ { REQ_OP_FLUSH, "Flush" },
+ { REQ_OP_DISCARD, "Deallocate (DSM)" },
+ { REQ_OP_WRITE_ZEROES, "Write Zeroes" },
+ { REQ_OP_ZONE_RESET_ALL, "Zone Reset All" },
+ { REQ_OP_ZONE_RESET, "Zone Reset" },
+ { REQ_OP_ZONE_OPEN, "Zone Open" },
+ { REQ_OP_ZONE_CLOSE, "Zone Close" },
+ { REQ_OP_ZONE_FINISH, "Zone Finish" },
+ { REQ_OP_ZONE_APPEND, "Zone Append" },
+};
+#define NVME_OPS_SIZE ARRAY_SIZE(nvme_ops)
+
+#ifdef CONFIG_NVME_VERBOSE_ERRORS
+static const char * const nvme_errors[] = {
+ [NVME_SC_SUCCESS] = "Success",
+ [NVME_SC_INVALID_OPCODE] = "Invalid Command Opcode",
+ [NVME_SC_INVALID_FIELD] = "Invalid Field in Command",
+ [NVME_SC_CMDID_CONFLICT] = "Command ID Conflict",
+ [NVME_SC_DATA_XFER_ERROR] = "Data Transfer Error",
+ [NVME_SC_POWER_LOSS] = "Commands Aborted due to Power Loss Notification",
+ [NVME_SC_INTERNAL] = "Internal Error",
+ [NVME_SC_ABORT_REQ] = "Command Abort Requested",
+ [NVME_SC_ABORT_QUEUE] = "Command Aborted due to SQ Deletion",
+ [NVME_SC_FUSED_FAIL] = "Command Aborted due to Failed Fused Command",
+ [NVME_SC_FUSED_MISSING] = "Command Aborted due to Missing Fused Command",
+ [NVME_SC_INVALID_NS] = "Invalid Namespace or Format",
+ [NVME_SC_CMD_SEQ_ERROR] = "Command Sequence Error",
+ [NVME_SC_SGL_INVALID_LAST] = "Invalid SGL Segment Descriptor",
+ [NVME_SC_SGL_INVALID_COUNT] = "Invalid Number of SGL Descriptors",
+ [NVME_SC_SGL_INVALID_DATA] = "Data SGL Length Invalid",
+ [NVME_SC_SGL_INVALID_METADATA] = "Metadata SGL Length Invalid",
+ [NVME_SC_SGL_INVALID_TYPE] = "SGL Descriptor Type Invalid",
+ [NVME_SC_CMB_INVALID_USE] = "Invalid Use of Controller Memory Buffer",
+ [NVME_SC_PRP_INVALID_OFFSET] = "PRP Offset Invalid",
+ [NVME_SC_ATOMIC_WU_EXCEEDED] = "Atomic Write Unit Exceeded",
+ [NVME_SC_OP_DENIED] = "Operation Denied",
+ [NVME_SC_SGL_INVALID_OFFSET] = "SGL Offset Invalid",
+ [NVME_SC_RESERVED] = "Reserved",
+ [NVME_SC_HOST_ID_INCONSIST] = "Host Identifier Inconsistent Format",
+ [NVME_SC_KA_TIMEOUT_EXPIRED] = "Keep Alive Timeout Expired",
+ [NVME_SC_KA_TIMEOUT_INVALID] = "Keep Alive Timeout Invalid",
+ [NVME_SC_ABORTED_PREEMPT_ABORT] = "Command Aborted due to Preempt and Abort",
+ [NVME_SC_SANITIZE_FAILED] = "Sanitize Failed",
+ [NVME_SC_SANITIZE_IN_PROGRESS] = "Sanitize In Progress",
+ [NVME_SC_SGL_INVALID_GRANULARITY] = "SGL Data Block Granularity Invalid",
+ [NVME_SC_CMD_NOT_SUP_CMB_QUEUE] = "Command Not Supported for Queue in CMB",
+ [NVME_SC_NS_WRITE_PROTECTED] = "Namespace is Write Protected",
+ [NVME_SC_CMD_INTERRUPTED] = "Command Interrupted",
+ [NVME_SC_TRANSIENT_TR_ERR] = "Transient Transport Error",
+ [NVME_SC_INVALID_IO_CMD_SET] = "Invalid IO Command Set",
+ [NVME_SC_LBA_RANGE] = "LBA Out of Range",
+ [NVME_SC_CAP_EXCEEDED] = "Capacity Exceeded",
+ [NVME_SC_NS_NOT_READY] = "Namespace Not Ready",
+ [NVME_SC_RESERVATION_CONFLICT] = "Reservation Conflict",
+ [NVME_SC_FORMAT_IN_PROGRESS] = "Format In Progress",
+ [NVME_SC_CQ_INVALID] = "Completion Queue Invalid",
+ [NVME_SC_QID_INVALID] = "Invalid Queue Identifier",
+ [NVME_SC_QUEUE_SIZE] = "Invalid Queue Size",
+ [NVME_SC_ABORT_LIMIT] = "Abort Command Limit Exceeded",
+ [NVME_SC_ABORT_MISSING] = "Reserved", /* XXX */
+ [NVME_SC_ASYNC_LIMIT] = "Asynchronous Event Request Limit Exceeded",
+ [NVME_SC_FIRMWARE_SLOT] = "Invalid Firmware Slot",
+ [NVME_SC_FIRMWARE_IMAGE] = "Invalid Firmware Image",
+ [NVME_SC_INVALID_VECTOR] = "Invalid Interrupt Vector",
+ [NVME_SC_INVALID_LOG_PAGE] = "Invalid Log Page",
+ [NVME_SC_INVALID_FORMAT] = "Invalid Format",
+ [NVME_SC_FW_NEEDS_CONV_RESET] = "Firmware Activation Requires Conventional Reset",
+ [NVME_SC_INVALID_QUEUE] = "Invalid Queue Deletion",
+ [NVME_SC_FEATURE_NOT_SAVEABLE] = "Feature Identifier Not Saveable",
+ [NVME_SC_FEATURE_NOT_CHANGEABLE] = "Feature Not Changeable",
+ [NVME_SC_FEATURE_NOT_PER_NS] = "Feature Not Namespace Specific",
+ [NVME_SC_FW_NEEDS_SUBSYS_RESET] = "Firmware Activation Requires NVM Subsystem Reset",
+ [NVME_SC_FW_NEEDS_RESET] = "Firmware Activation Requires Reset",
+ [NVME_SC_FW_NEEDS_MAX_TIME] = "Firmware Activation Requires Maximum Time Violation",
+ [NVME_SC_FW_ACTIVATE_PROHIBITED] = "Firmware Activation Prohibited",
+ [NVME_SC_OVERLAPPING_RANGE] = "Overlapping Range",
+ [NVME_SC_NS_INSUFFICIENT_CAP] = "Namespace Insufficient Capacity",
+ [NVME_SC_NS_ID_UNAVAILABLE] = "Namespace Identifier Unavailable",
+ [NVME_SC_NS_ALREADY_ATTACHED] = "Namespace Already Attached",
+ [NVME_SC_NS_IS_PRIVATE] = "Namespace Is Private",
+ [NVME_SC_NS_NOT_ATTACHED] = "Namespace Not Attached",
+ [NVME_SC_THIN_PROV_NOT_SUPP] = "Thin Provisioning Not Supported",
+ [NVME_SC_CTRL_LIST_INVALID] = "Controller List Invalid",
+ [NVME_SC_SELT_TEST_IN_PROGRESS] = "Device Self-test In Progress",
+ [NVME_SC_BP_WRITE_PROHIBITED] = "Boot Partition Write Prohibited",
+ [NVME_SC_CTRL_ID_INVALID] = "Invalid Controller Identifier",
+ [NVME_SC_SEC_CTRL_STATE_INVALID] = "Invalid Secondary Controller State",
+ [NVME_SC_CTRL_RES_NUM_INVALID] = "Invalid Number of Controller Resources",
+ [NVME_SC_RES_ID_INVALID] = "Invalid Resource Identifier",
+ [NVME_SC_PMR_SAN_PROHIBITED] = "Sanitize Prohibited",
+ [NVME_SC_ANA_GROUP_ID_INVALID] = "ANA Group Identifier Invalid",
+ [NVME_SC_ANA_ATTACH_FAILED] = "ANA Attach Failed",
+ [NVME_SC_BAD_ATTRIBUTES] = "Conflicting Attributes",
+ [NVME_SC_INVALID_PI] = "Invalid Protection Information",
+ [NVME_SC_READ_ONLY] = "Attempted Write to Read Only Range",
+ [NVME_SC_ONCS_NOT_SUPPORTED] = "ONCS Not Supported",
+ [NVME_SC_ZONE_BOUNDARY_ERROR] = "Zoned Boundary Error",
+ [NVME_SC_ZONE_FULL] = "Zone Is Full",
+ [NVME_SC_ZONE_READ_ONLY] = "Zone Is Read Only",
+ [NVME_SC_ZONE_OFFLINE] = "Zone Is Offline",
+ [NVME_SC_ZONE_INVALID_WRITE] = "Zone Invalid Write",
+ [NVME_SC_ZONE_TOO_MANY_ACTIVE] = "Too Many Active Zones",
+ [NVME_SC_ZONE_TOO_MANY_OPEN] = "Too Many Open Zones",
+ [NVME_SC_ZONE_INVALID_TRANSITION] = "Invalid Zone State Transition",
+ [NVME_SC_WRITE_FAULT] = "Write Fault",
+ [NVME_SC_READ_ERROR] = "Unrecovered Read Error",
+ [NVME_SC_GUARD_CHECK] = "End-to-end Guard Check Error",
+ [NVME_SC_APPTAG_CHECK] = "End-to-end Application Tag Check Error",
+ [NVME_SC_REFTAG_CHECK] = "End-to-end Reference Tag Check Error",
+ [NVME_SC_COMPARE_FAILED] = "Compare Failure",
+ [NVME_SC_ACCESS_DENIED] = "Access Denied",
+ [NVME_SC_UNWRITTEN_BLOCK] = "Deallocated or Unwritten Logical Block",
+ [NVME_SC_ANA_PERSISTENT_LOSS] = "Asymmetric Access Persistent Loss",
+ [NVME_SC_ANA_INACCESSIBLE] = "Asymmetric Access Inaccessible",
+ [NVME_SC_ANA_TRANSITION] = "Asymmetric Access Transition",
+ [NVME_SC_HOST_PATH_ERROR] = "Host Pathing Error",
+};
+#define NVME_ERRORS_SIZE ARRAY_SIZE(nvme_errors)
+#endif /* CONFIG_NVME_VERBOSE_ERRORS */
+
+void nvme_error_log(struct request *req)
+{
+ struct nvme_ns *ns = req->q->queuedata;
+ struct nvme_request *nr = nvme_req(req);
+ const struct nvme_string_table *entry;
+ const unsigned char *op_str = "Unknown";
+ const unsigned char *err_str = NULL;
+ unsigned int i;
+
+ if (!ns)
+ return;
+
+ for (i = 0, entry = nvme_ops ; i < NVME_OPS_SIZE ; i++)
+ if (entry[i].code == (req->cmd_flags & REQ_OP_MASK))
+ op_str = entry[i].string;
+
+#ifdef CONFIG_NVME_VERBOSE_ERRORS
+ if ((nr->status & 0x7ff) <= NVME_ERRORS_SIZE)
+ err_str = nvme_errors[nr->status & 0x7ff];
+#endif
+ if (err_str == NULL)
+ err_str = "NVME Error";
+
+ pr_err_ratelimited("%s: %s @ LBA %llu, %llu blocks, %s (sct 0x%x / sc 0x%x) %s%s\n",
+ req->rq_disk ? req->rq_disk->disk_name : "?",
+ op_str,
+ (unsigned long long)nvme_sect_to_lba(ns, blk_rq_pos(req)),
+ (unsigned long long)blk_rq_bytes(req) >> ns->lba_shift,
+ err_str,
+ nr->status >> 8 & 7, /* Status Code Type */
+ nr->status & 0xff, /* Status Code */
+ nr->status & NVME_SC_MORE ? "MORE " : "",
+ nr->status & NVME_SC_DNR ? "DNR " : "");
+}
+EXPORT_SYMBOL_GPL(nvme_error_log);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 9b095ee01364..7edd67b92a6b 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -922,4 +922,6 @@ static inline bool nvme_multi_css(struct nvme_ctrl *ctrl)
return (ctrl->ctrl_config & NVME_CC_CSS_MASK) == NVME_CC_CSS_CSI;
}
+extern void nvme_error_log(struct request *req);
+
#endif /* _NVME_H */
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 855dd9b3e84b..1f946e5bf7c1 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -1636,6 +1636,7 @@ enum {
NVME_SC_HOST_ABORTED_CMD = 0x371,
NVME_SC_CRD = 0x1800,
+ NVME_SC_MORE = 0x2000,
NVME_SC_DNR = 0x4000,
};
--
2.27.0
More information about the Linux-nvme
mailing list