[PATCH V7 1/1] nvme-core: Add verbose error logging
Chaitanya Kulkarni
chaitanyak at nvidia.com
Thu Feb 3 00:11:53 PST 2022
From: Chaitanya Kulkarni <kch at nvidia.com>
From: Alan Adamson <alan.adamson at oracle.com>
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.
Signed-off-by: Chaitanya Kulkarni <kch at nvidia.com>
[kch]: fix several nits, cosmetics, and trim down code.
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>
Reviewed-by: Keith Busch <kbusch at kernel.org>
---
drivers/nvme/host/Kconfig | 8 ++
drivers/nvme/host/Makefile | 2 +-
drivers/nvme/host/constants.c | 185 ++++++++++++++++++++++++++++++++++
drivers/nvme/host/core.c | 34 +++++++
drivers/nvme/host/nvme.h | 19 ++++
include/linux/nvme.h | 1 +
6 files changed, 248 insertions(+), 1 deletion(-)
create mode 100644 drivers/nvme/host/constants.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..476c5c988496 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-$(CONFIG_NVME_TCP) += nvme-tcp.o
-nvme-core-y := core.o ioctl.o
+nvme-core-y := core.o ioctl.o constants.o
nvme-core-$(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/constants.c b/drivers/nvme/host/constants.c
new file mode 100644
index 000000000000..7d49eb34b348
--- /dev/null
+++ b/drivers/nvme/host/constants.c
@@ -0,0 +1,185 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVM Express device driver verbose errors
+ * Copyright (c) 2022, Oracle and/or its affiliates
+ */
+
+#include <linux/blkdev.h>
+#include "nvme.h"
+
+#ifdef CONFIG_NVME_VERBOSE_ERRORS
+static const char * const nvme_ops[] = {
+ [nvme_cmd_flush] = "Flush",
+ [nvme_cmd_write] = "Write",
+ [nvme_cmd_read] = "Read",
+ [nvme_cmd_write_uncor] = "Write Uncorrectable",
+ [nvme_cmd_compare] = "Compare",
+ [nvme_cmd_write_zeroes] = "Write Zeros",
+ [nvme_cmd_dsm] = "Dataset Management",
+ [nvme_cmd_verify] = "Verify",
+ [nvme_cmd_resv_register] = "Reservation Register",
+ [nvme_cmd_resv_report] = "Reservation Report",
+ [nvme_cmd_resv_acquire] = "Reservation Acquire",
+ [nvme_cmd_resv_release] = "Reservation Release",
+ [nvme_cmd_zone_mgmt_send] = "Zone Management Send",
+ [nvme_cmd_zone_mgmt_recv] = "Zone Management Receive",
+ [nvme_cmd_zone_append] = "Zone Management Append",
+};
+
+static const char * const nvme_admin_ops[] = {
+ [nvme_admin_delete_sq] = "Delete SQ",
+ [nvme_admin_create_sq] = "Create SQ",
+ [nvme_admin_get_log_page] = "Get Log Page",
+ [nvme_admin_delete_cq] = "Delete CQ",
+ [nvme_admin_create_cq] = "Create CQ",
+ [nvme_admin_identify] = "Identify",
+ [nvme_admin_abort_cmd] = "Abort Command",
+ [nvme_admin_set_features] = "Set Features",
+ [nvme_admin_get_features] = "Get Features",
+ [nvme_admin_async_event] = "Async Event",
+ [nvme_admin_ns_mgmt] = "Namespace Management",
+ [nvme_admin_activate_fw] = "Activate Firmware",
+ [nvme_admin_download_fw] = "Download Firmware",
+ [nvme_admin_dev_self_test] = "Device Self Test",
+ [nvme_admin_ns_attach] = "Namespace Attach",
+ [nvme_admin_keep_alive] = "Keep Alive",
+ [nvme_admin_directive_send] = "Directive Send",
+ [nvme_admin_directive_recv] = "Directive Receive",
+ [nvme_admin_virtual_mgmt] = "Virtual Management",
+ [nvme_admin_nvme_mi_send] = "NVMe Send MI",
+ [nvme_admin_nvme_mi_recv] = "NVMe Receive MI",
+ [nvme_admin_dbbuf] = "Doorbell Buffer Config",
+ [nvme_admin_format_nvm] = "Format NVM",
+ [nvme_admin_security_send] = "Security Send",
+ [nvme_admin_security_recv] = "Security Receive",
+ [nvme_admin_sanitize_nvm] = "Sanitize NVM",
+ [nvme_admin_get_lba_status] = "Get LBA Status",
+};
+
+static const char * const nvme_statuses[] = {
+ [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",
+};
+
+const unsigned char *nvme_get_error_status_str(u16 status)
+{
+ status &= 0x7ff;
+ if (status < ARRAY_SIZE(nvme_statuses) && nvme_statuses[status])
+ return nvme_statuses[status & 0x7ff];
+ return "Unknown";
+}
+
+const unsigned char *nvme_get_opcode_str(u8 opcode)
+{
+ if (opcode < ARRAY_SIZE(nvme_ops) && nvme_ops[opcode])
+ return nvme_ops[opcode];
+ return "Unknown";
+}
+
+const unsigned char *nvme_get_admin_opcode_str(u8 opcode)
+{
+ if (opcode < ARRAY_SIZE(nvme_admin_ops) && nvme_admin_ops[opcode])
+ return nvme_admin_ops[opcode];
+ return "Unknown";
+}
+#endif /* CONFIG_NVME_VERBOSE_ERRORS */
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 37eca20006e0..2054e8855f74 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -299,6 +299,37 @@ static void nvme_retry_req(struct request *req)
blk_mq_delay_kick_requeue_list(req->q, delay);
}
+static void nvme_log_error(struct request *req)
+{
+ struct nvme_ns *ns = req->q->queuedata;
+ struct nvme_request *nr = nvme_req(req);
+
+ if (ns) {
+ pr_err_ratelimited("%s: %s(0x%x) @ LBA %llu, %llu blocks, %s (sct 0x%x / sc 0x%x) %s%s\n",
+ ns->disk ? ns->disk->disk_name : "?",
+ nvme_get_opcode_str(nr->cmd->common.opcode),
+ nr->cmd->common.opcode,
+ (unsigned long long)nvme_sect_to_lba(ns, blk_rq_pos(req)),
+ (unsigned long long)blk_rq_bytes(req) >> ns->lba_shift,
+ nvme_get_error_status_str(nr->status),
+ nr->status >> 8 & 7, /* Status Code Type */
+ nr->status & 0xff, /* Status Code */
+ nr->status & NVME_SC_MORE ? "MORE " : "",
+ nr->status & NVME_SC_DNR ? "DNR " : "");
+ return;
+ }
+
+ pr_err_ratelimited("%s: %s(0x%x), %s (sct 0x%x / sc 0x%x) %s%s\n",
+ dev_name(nr->ctrl->device),
+ nvme_get_admin_opcode_str(nr->cmd->common.opcode),
+ nr->cmd->common.opcode,
+ nvme_get_error_status_str(nr->status),
+ nr->status >> 8 & 7, /* Status Code Type */
+ nr->status & 0xff, /* Status Code */
+ nr->status & NVME_SC_MORE ? "MORE " : "",
+ nr->status & NVME_SC_DNR ? "DNR " : "");
+}
+
enum nvme_disposition {
COMPLETE,
RETRY,
@@ -354,6 +385,9 @@ void nvme_complete_rq(struct request *req)
switch (nvme_decide_disposition(req)) {
case COMPLETE:
+ if (unlikely(nvme_req(req)->status != NVME_SC_SUCCESS))
+ nvme_log_error(req);
+
nvme_end_req(req);
return;
case RETRY:
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index a162f6c6da6e..5b50ba4eb309 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -930,4 +930,23 @@ static inline bool nvme_multi_css(struct nvme_ctrl *ctrl)
return (ctrl->ctrl_config & NVME_CC_CSS_MASK) == NVME_CC_CSS_CSI;
}
+#ifdef CONFIG_NVME_VERBOSE_ERRORS
+const unsigned char *nvme_get_error_status_str(u16 status);
+const unsigned char *nvme_get_opcode_str(u8 opcode);
+const unsigned char *nvme_get_admin_opcode_str(u8 opcode);
+#else /* CONFIG_NVME_VERBOSE_ERRORS */
+static inline const unsigned char *nvme_get_error_status_str(u16 status)
+{
+ return "I/O Error";
+}
+static inline const unsigned char *nvme_get_opcode_str(u8 opcode)
+{
+ return "I/O Cmd";
+}
+static inline const unsigned char *nvme_get_admin_opcode_str(u8 opcode)
+{
+ return "Admin Cmd";
+}
+#endif /* CONFIG_NVME_VERBOSE_ERRORS */
+
#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,
};
--
2.29.0
More information about the Linux-nvme
mailing list