nvme: allow passthru cmd error logging

Commit d7ac8dca93 ("nvme: quiet user passthrough command errors")
disabled error logging for user passthrough commands.  This commit
adds the ability to opt-in to passthrough admin error logging. IO
commands initiated as passthrough will always be logged.

The logging output for passthrough commands (Admin and IO) has been
changed to include CDWXX fields.

nvme0n1: Read(0x2), LBA Out of Range (sct 0x0 / sc 0x80) DNR cdw10=0x0 cdw11=0x1
        cdw12=0x70000 cdw13=0x0 cdw14=0x0 cdw15=0x0

Add a helper function nvme_log_err_passthru() which allows us to log
error for passthru commands by decoding cdw10-cdw15 values of nvme
command.

Add a new sysfs attr passthru_err_log_enabled that allows user to conditionally
enable passthrough command logging for either passthrough Admin commands sent to
the controller or passthrough IO commands sent to a namespace.

By default, passthrough error logging is disabled.

To enable passthrough admin error logging:
        echo 1 > /sys/class/nvme/nvme0/passthru_err_log_enabled

To disable passthrough admin error logging:
        echo 0 > /sys/class/nvme/nvme0/passthru_err_log_enabled

To enable passthrough io error logging:
        echo 1 > /sys/class/nvme/nvme0/nvme0n1/passthru_err_log_enabled

To disable passthrough io error logging:
        echo 0 > /sys/class/nvme/nvme0/nvme0n1/passthru_err_log_enabled

Signed-off-by: Alan Adamson <alan.adamson@oracle.com>
Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
This commit is contained in:
Alan Adamson 2024-01-29 16:19:38 -08:00 committed by Keith Busch
parent c3a846fe4b
commit 9f079dda14
3 changed files with 113 additions and 7 deletions

View File

@ -338,6 +338,30 @@ static void nvme_log_error(struct request *req)
nr->status & NVME_SC_DNR ? "DNR " : "");
}
static void nvme_log_err_passthru(struct request *req)
{
struct nvme_ns *ns = req->q->queuedata;
struct nvme_request *nr = nvme_req(req);
pr_err_ratelimited("%s: %s(0x%x), %s (sct 0x%x / sc 0x%x) %s%s"
"cdw10=0x%x cdw11=0x%x cdw12=0x%x cdw13=0x%x cdw14=0x%x cdw15=0x%x\n",
ns ? ns->disk->disk_name : dev_name(nr->ctrl->device),
ns ? nvme_get_opcode_str(nr->cmd->common.opcode) :
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 " : "",
nr->cmd->common.cdw10,
nr->cmd->common.cdw11,
nr->cmd->common.cdw12,
nr->cmd->common.cdw13,
nr->cmd->common.cdw14,
nr->cmd->common.cdw14);
}
enum nvme_disposition {
COMPLETE,
RETRY,
@ -385,8 +409,12 @@ static inline void nvme_end_req(struct request *req)
{
blk_status_t status = nvme_error_status(nvme_req(req)->status);
if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET)))
nvme_log_error(req);
if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET))) {
if (blk_rq_is_passthrough(req))
nvme_log_err_passthru(req);
else
nvme_log_error(req);
}
nvme_end_req_zoned(req);
nvme_trace_bio_complete(req);
if (req->cmd_flags & REQ_NVME_MPATH)
@ -679,10 +707,21 @@ static inline void nvme_clear_nvme_request(struct request *req)
/* initialize a passthrough request */
void nvme_init_request(struct request *req, struct nvme_command *cmd)
{
if (req->q->queuedata)
struct nvme_request *nr = nvme_req(req);
bool logging_enabled;
if (req->q->queuedata) {
struct nvme_ns *ns = req->q->disk->private_data;
logging_enabled = ns->passthru_err_log_enabled;
req->timeout = NVME_IO_TIMEOUT;
else /* no queuedata implies admin queue */
} else { /* no queuedata implies admin queue */
logging_enabled = nr->ctrl->passthru_err_log_enabled;
req->timeout = NVME_ADMIN_TIMEOUT;
}
if (!logging_enabled)
req->rq_flags |= RQF_QUIET;
/* passthru commands should let the driver set the SGL flags */
cmd->common.flags &= ~NVME_CMD_SGL_ALL;
@ -691,8 +730,7 @@ void nvme_init_request(struct request *req, struct nvme_command *cmd)
if (req->mq_hctx->type == HCTX_TYPE_POLL)
req->cmd_flags |= REQ_POLLED;
nvme_clear_nvme_request(req);
req->rq_flags |= RQF_QUIET;
memcpy(nvme_req(req)->cmd, cmd, sizeof(*cmd));
memcpy(nr->cmd, cmd, sizeof(*cmd));
}
EXPORT_SYMBOL_GPL(nvme_init_request);
@ -3658,6 +3696,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
ns->disk = disk;
ns->queue = disk->queue;
ns->passthru_err_log_enabled = false;
if (ctrl->opts && ctrl->opts->data_digest)
blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue);
@ -3721,6 +3760,13 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
nvme_mpath_add_disk(ns, info->anagrpid);
nvme_fault_inject_init(&ns->fault_inject, ns->disk->disk_name);
/*
* Set ns->disk->device->driver_data to ns so we can access
* ns->logging_enabled in nvme_passthru_err_log_enabled_store() and
* nvme_passthru_err_log_enabled_show().
*/
dev_set_drvdata(disk_to_dev(ns->disk), ns);
return;
out_cleanup_ns_from_list:
@ -4521,6 +4567,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
int ret;
WRITE_ONCE(ctrl->state, NVME_CTRL_NEW);
ctrl->passthru_err_log_enabled = false;
clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
spin_lock_init(&ctrl->lock);
mutex_init(&ctrl->scan_lock);

View File

@ -263,6 +263,7 @@ enum nvme_ctrl_flags {
struct nvme_ctrl {
bool comp_seen;
bool identified;
bool passthru_err_log_enabled;
enum nvme_ctrl_state state;
spinlock_t lock;
struct mutex scan_lock;
@ -522,7 +523,7 @@ struct nvme_ns {
struct device cdev_device;
struct nvme_fault_inject fault_inject;
bool passthru_err_log_enabled;
};
/* NVMe ns supports metadata actions by the controller (generate/strip) */

View File

@ -35,6 +35,62 @@ static ssize_t nvme_sysfs_rescan(struct device *dev,
}
static DEVICE_ATTR(rescan_controller, S_IWUSR, NULL, nvme_sysfs_rescan);
static ssize_t nvme_adm_passthru_err_log_enabled_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
return sysfs_emit(buf,
ctrl->passthru_err_log_enabled ? "on\n" : "off\n");
}
static ssize_t nvme_adm_passthru_err_log_enabled_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
int err;
bool passthru_err_log_enabled;
err = kstrtobool(buf, &passthru_err_log_enabled);
if (err)
return -EINVAL;
ctrl->passthru_err_log_enabled = passthru_err_log_enabled;
return count;
}
static ssize_t nvme_io_passthru_err_log_enabled_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nvme_ns *n = dev_get_drvdata(dev);
return sysfs_emit(buf, n->passthru_err_log_enabled ? "on\n" : "off\n");
}
static ssize_t nvme_io_passthru_err_log_enabled_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
struct nvme_ns *ns = dev_get_drvdata(dev);
int err;
bool passthru_err_log_enabled;
err = kstrtobool(buf, &passthru_err_log_enabled);
if (err)
return -EINVAL;
ns->passthru_err_log_enabled = passthru_err_log_enabled;
return count;
}
static struct device_attribute dev_attr_adm_passthru_err_log_enabled = \
__ATTR(passthru_err_log_enabled, S_IRUGO | S_IWUSR, \
nvme_adm_passthru_err_log_enabled_show, nvme_adm_passthru_err_log_enabled_store);
static struct device_attribute dev_attr_io_passthru_err_log_enabled = \
__ATTR(passthru_err_log_enabled, S_IRUGO | S_IWUSR, \
nvme_io_passthru_err_log_enabled_show, nvme_io_passthru_err_log_enabled_store);
static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
{
struct gendisk *disk = dev_to_disk(dev);
@ -208,6 +264,7 @@ static struct attribute *nvme_ns_attrs[] = {
&dev_attr_ana_grpid.attr,
&dev_attr_ana_state.attr,
#endif
&dev_attr_io_passthru_err_log_enabled.attr,
NULL,
};
@ -655,6 +712,7 @@ static struct attribute *nvme_dev_attrs[] = {
#ifdef CONFIG_NVME_TCP_TLS
&dev_attr_tls_key.attr,
#endif
&dev_attr_adm_passthru_err_log_enabled.attr,
NULL
};