[PATCH V2 1/1] nvme: Add verbose error logging
From: Alan Adamson <hidden>
Date: 2021-12-23 21:58:29
Subsystem:
nvm express driver, the rest · Maintainers:
Keith Busch, Jens Axboe, Christoph Hellwig, Sagi Grimberg, Linus Torvalds
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@oracle.com> Signed-off-by: Alan Adamson <redacted> Reviewed-by: Himanshu Madhani <redacted> --- drivers/nvme/host/Kconfig | 8 ++ drivers/nvme/host/Makefile | 2 +- drivers/nvme/host/core.c | 3 + drivers/nvme/host/errors.c | 202 +++++++++++++++++++++++++++++++++++++ drivers/nvme/host/nvme.h | 2 + include/linux/nvme.h | 1 + 6 files changed, 217 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..3183b2e728d4
--- /dev/null
+++ b/drivers/nvme/host/errors.c@@ -0,0 +1,202 @@ +// 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 +#define TEN_NULLS NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL + +static const char * const nvme_errors[] = { + "Success", + "Invalid Command Opcode", + "Invalid Field in Command", + "Command ID Conflict", + "Data Transfer Error", + "Commands Aborted due to Power Loss Notification", + "Internal Error", + "Command Abort Requested", + "Command Aborted due to SQ Deletion", + "Command Aborted due to Failed Fused Command", + "Command Aborted due to Missing Fused Command", + "Invalid Namespace or Format", + "Command Sequence Error", + "Invalid SGL Segment Descriptor", + "Invalid Number of SGL Descriptors", + "Data SGL Length Invalid", + "Metadata SGL Length Invalid", + "SGL Descriptor Type Invalid", + "Invalid Use of Controller Memory Buffer", + "PRP Offset Invalid", + "Atomic Write Unit Exceeded", + "Operation Denied", + "SGL Offset Invalid", + "Reserved", + "Host Identifier Inconsistent Format", + "Keep Alive Timeout Expired", + "Keep Alive Timeout Invalid", + "Command Aborted due to Preempt and Abort", + "Sanitize Failed", + "Sanitize In Progress", + "SGL Data Block Granularity Invalid", + "Command Not Supported for Queue in CMB", + "Namespace is Write Protected", + "Command Interrupted", + "Transient Transport Error", + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + "Invalid IO Command Set", + TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, + NULL, NULL, NULL, + "LBA Out of Range", + "Capacity Exceeded", + "Namespace Not Ready", + "Reservation Conflict", + "Format In Progress", + TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, + TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, NULL, NULL, NULL, + "Completion Queue Invalid", + "Invalid Queue Identifier", + "Invalid Queue Size", + "Abort Command Limit Exceeded", + "Reserved", + "Asynchronous Event Request Limit Exceeded", + "Invalid Firmware Slot", + "Invalid Firmware Image", + "Invalid Interrupt Vector", + "Invalid Log Page", + "Invalid Format", + "Firmware Activation Requires Conventional Reset", + "Invalid Queue Deletion", + "Feature Identifier Not Saveable", + "Feature Not Changeable", + "Feature Not Namespace Specific", + "Firmware Activation Requires NVM Subsystem Reset", + "Firmware Activation Requires Reset", + "Firmware Activation Requires Maximum Time Violation", + "Firmware Activation Prohibited", + "Overlapping Range", + "Namespace Insufficient Capacity", + "Namespace Identifier Unavailable", + NULL, + "Namespace Already Attached", + "Namespace Is Private", + "Namespace Not Attached", + "Thin Provisioning Not Supported", + "Controller List Invalid", + "Device Self-test In Progress", + "Boot Partition Write Prohibited", + "Invalid Controller Identifier", + "Invalid Secondary Controller State", + "Invalid Number of Controller Resources", + "Invalid Resource Identifier", + "Sanitize Prohibited", + "ANA Group Identifier Invalid", + "ANA Attach Failed", + TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, + TEN_NULLS, TEN_NULLS, TEN_NULLS, + "Conflicting Attributes", + "Invalid Protection Information", + "Attempted Write to Read Only Range", + "ONCS Not Supported", + TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, NULL, NULL, + "Zoned Boundary Error", + "Zone Is Full", + "Zone Is Read Only", + "Zone Is Offline", + "Zone Invalid Write", + "Too Many Active Zones", + "Too Many Open Zones", + "Invalid Zone State Transition", + TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, + TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, + TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, + TEN_NULLS, NULL, NULL, + "Write Fault", + "Unrecovered Read Error", + "End-to-end Guard Check Error", + "End-to-end Application Tag Check Error", + "End-to-end Reference Tag Check Error", + "Compare Failure", + "Access Denied", + "Deallocated or Unwritten Logical Block", + TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, + TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, + NULL, + "Asymmetric Access Persistent Loss", + "Asymmetric Access Inaccessible", + "Asymmetric Access Transition", + TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, + TEN_NULLS, TEN_NULLS, TEN_NULLS, TEN_NULLS, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + "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