nvme-pci: support device coredump
Subsystems (3)
v4 cover nvme-pci: support device coredump
This enables to collect snapshot of controller information via device coredump mechanism. The nvme device coredump is triggered when command timeout occurs, and can also be triggered by writing sysfs attribute.
After finishing the nvme device coredump, the following files are created.
- regs: NVMe controller registers (00h to 4Fh)
- sq<qid>: Submission queue
- cq<qid>: Completion queue
- telemetry-ctrl-log: Telemetry controller-initiated log (if available)
- data: Empty
The device coredump mechanism currently allows drivers to create only a single coredump file, so this also provides a new function that allows drivers to create several device coredump files in one crashed device.
* v4
- Add Reviewed-by tags
- Add nvme_get_telemetry_log() to nvme core module.
- Copy struct nvme_telemetry_log_page_hdr from the latest nvme-cli
- Use bio_vec instead of sg_table to store telemetry log page
- Make nvme_coredump_logs() return error if the device didn't produce a response.
- Abandon the reset if nvme_coredump_logs() returns error code
* v3
- Merge 'add telemetry log page definisions' patch and 'add facility to check log page attributes' patch
- Copy struct nvme_telemetry_log_page_hdr from the latest nvme-cli
- Add BUILD_BUG_ON for the size of struct nvme_telemetry_log_page_hdr
- Fix typo s/machanism/mechanism/ in commit log
- Fix max transfer size calculation for get log page
- Add function comments
- Extract 'enable to trigger device coredump by hand' patch
- Don't try to get telemetry log when admin queue is not available
- Avoid deadlock in .coredump callback
* v2
- Add Reviewed-by tag.
- Add patch to fix typo in comment
- Remove unneeded braces.
- Allocate device_entry followed by an array of devcd_file elements.
- Add telemetry log page definisions
- Add facility to check log page attributes
- Exclude the doorbell registers from register dump.
- Save controller registers in a binary format instead of a text format.
- Create an empty 'data' file in the device coredump.
- Save telemetry controller-initiated log if available
- Make coredump procedure into two phases (before resetting controller and after resetting as soon as admin queue is available).
Akinobu Mita (7):
devcoredump: use memory_read_from_buffer
devcoredump: fix typo in comment
devcoredump: allow to create several coredump files in one device
nvme: add basic facilities to get telemetry log page
nvme-pci: add device coredump infrastructure
nvme-pci: trigger device coredump on command timeout
nvme-pci: enable to trigger device coredump by hand
drivers/base/devcoredump.c | 168 ++++++++++------ drivers/nvme/host/Kconfig | 1 + drivers/nvme/host/core.c | 59 ++++++ drivers/nvme/host/nvme.h | 3 + drivers/nvme/host/pci.c | 473 ++++++++++++++++++++++++++++++++++++++++++-- include/linux/devcoredump.h | 33 ++++ include/linux/nvme.h | 32 +++ 7 files changed, 696 insertions(+), 73 deletions(-)
Signature · 1 line
2.7.4
PATCH v4 1/7 devcoredump: use memory_read_from_buffer
Use memory_read_from_buffer() to simplify devcd_readv().
---
* v4
- Add Reviewed-by tag
drivers/base/devcoredump.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-)
drivers/base/devcoredump.c +1 -10
@@ -164,16 +164,7 @@ static struct class devcd_class = {static ssize_t devcd_readv (char *buffer,loff_t offset,size_t count,void *data,size_t datalen) { -if (offset > datalen) -return -EINVAL ; - -if (offset + count > datalen) - count = datalen - offset; - -if (count) -memcpy (buffer, ((u8 *)data) + offset, count); - -return count; +return memory_read_from_buffer (buffer, count, &offset, data, datalen); }static void devcd_freev (void *data)
Signature · 1 line
2.7.4
PATCH v4 2/7 devcoredump: fix typo in comment
In reply to Akinobu Mitas/dev_coredumpmsg/dev_coredumpsg/
---
* v4
- Add Reviewed-by tag
drivers/base/devcoredump.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/base/devcoredump.c +1 -1
@@ -314,7 +314,7 @@ void dev_coredumpm(struct device *dev, struct module *owner,EXPORT_SYMBOL_GPL (dev_coredumpm);/** -* dev_coredumpmsg - create device coredump that uses scatterlist as data +* dev_coredumpsg - create device coredump that uses scatterlist as data * parameter * @dev: the struct device for the crashed device * @table: the dump data
Signature · 1 line
2.7.4
PATCH v4 3/7 devcoredump: allow to create several coredump files in one device
In reply to Akinobu MitaThe device coredump mechanism currently allows drivers to create only a single coredump file. If there are several binary blobs to dump, we need to define a binary format or conver to text format in order to put them into a single coredump file.
This provides a new function that allows drivers to create several device coredump files in one crashed device.
---
* v4
- No change since v2
drivers/base/devcoredump.c | 155 ++++++++++++++++++++++++++++++-------------- include/linux/devcoredump.h | 33 ++++++++++ 2 files changed, 139 insertions(+), 49 deletions(-)
drivers/base/devcoredump.c +106 -49
@@ -25,16 +25,20 @@ static bool devcd_disabled;/* if data isn't read by userspace after 5 minutes then delete it */ #define DEVCD_TIMEOUT (HZ * 60 * 5) -struct devcd_entry { -struct device devcd_dev; -void *data; -size_t datalen; -struct module *owner; +struct devcd_file { +struct bin_attribute bin_attr;ssize_t (*read)(char *buffer,loff_t offset,size_t count,void *data,size_t datalen);void (*free)(void *data); +}; + +struct devcd_entry { +struct device devcd_dev; +struct module *owner;struct delayed_work del_wk;struct device *failing_dev; +int num_files; +struct devcd_file files[]; };static struct devcd_entry *dev_to_devcd (struct device *dev)
@@ -45,8 +49,14 @@ static struct devcd_entry *dev_to_devcd(struct device *dev)static void devcd_dev_release (struct device *dev) {struct devcd_entry *devcd =dev_to_devcd (dev); +int i; + +for (i =0 ; i < devcd->num_files; i++) { +struct devcd_file *file = &devcd->files[i]; + + file->free (file->bin_attr.private); + } - devcd->free (devcd->data);module_put (devcd->owner);/*
@@ -64,9 +74,14 @@ static void devcd_dev_release(struct device *dev)static void devcd_del (struct work_struct *wk) {struct devcd_entry *devcd; +int i; devcd = container_of(wk, struct devcd_entry, del_wk.work); +for (i =0 ; i < devcd->num_files; i++) +device_remove_bin_file (&devcd->devcd_dev, + &devcd->files[i].bin_attr); +device_del (&devcd->devcd_dev);put_device (&devcd->devcd_dev); }
@@ -75,10 +90,11 @@ static ssize_t devcd_data_read(struct file *filp, struct kobject *kobj,struct bin_attribute *bin_attr, char *buffer, loff_t offset, size_t count) { - struct device *dev = kobj_to_dev(kobj); -struct devcd_entry *devcd =dev_to_devcd (dev); + struct devcd_file *file = + container_of(bin_attr, struct devcd_file, bin_attr); -return devcd->read (buffer, offset, count, devcd->data, devcd->datalen); +return file->read (buffer, offset, count, bin_attr->private, + bin_attr->size); } static ssize_t devcd_data_write(struct file *filp, struct kobject *kobj,
@@ -93,25 +109,6 @@ static ssize_t devcd_data_write(struct file *filp, struct kobject *kobj,return count; } -static struct bin_attribute devcd_attr_data = { - .attr = { .name ="data" , .mode =S_IRUSR |S_IWUSR , }, - .size =0 , - .read = devcd_data_read, - .write = devcd_data_write, -}; - -static struct bin_attribute *devcd_dev_bin_attrs[] = { - &devcd_attr_data,NULL , -}; - -static const struct attribute_group devcd_dev_group = { - .bin_attrs = devcd_dev_bin_attrs, -}; - -static const struct attribute_group *devcd_dev_groups[] = { - &devcd_dev_group,NULL , -}; -static int devcd_free (struct device *dev,void *data) {struct devcd_entry *devcd =dev_to_devcd (dev);
@@ -157,7 +154,6 @@ static struct class devcd_class = { .name = "devcoredump", .owner = THIS_MODULE, .dev_release = devcd_dev_release, - .dev_groups = devcd_dev_groups, .class_groups = devcd_class_groups, };
@@ -234,30 +230,55 @@ static ssize_t devcd_read_from_sgtable(char *buffer, loff_t offset, offset); } +static struct devcd_entry *devcd_alloc (struct dev_coredumpm_bulk_data *files, +int num_files,gfp_t gfp) +{ +struct devcd_entry *devcd; +int i; + + devcd =kzalloc (struct_size (devcd, files, num_files), gfp); +if (!devcd) +return NULL ; + + devcd->num_files = num_files; + +for (i =0 ; i < devcd->num_files; i++) { +struct devcd_file *file = &devcd->files[i]; + +sysfs_bin_attr_init (&file->bin_attr); + file->bin_attr.attr.name = files[i].name; + + file->bin_attr.attr.mode =0600 ; + file->bin_attr.size = files[i].datalen; + file->bin_attr.private = files[i].data; + file->bin_attr.read = devcd_data_read; + file->bin_attr.write = devcd_data_write; + + file->read = files[i].read; + file->free = files[i].free; + } + +return devcd; +} +/** -* dev_coredumpm - create device coredump with read/free methods +* dev_coredumpm_bulk - create a number of device coredump files * @dev: the struct device for the crashed device * @owner: the module that contains the read/free functions, use %THIS_MODULE -* @data: data cookie for the @read/@free functions -* @datalen: length of the data * @gfp: allocation flags -* @read: function to read from the given buffer -* @free: function to free the given buffer +* @files: the configuration of device coredump files +* @num_files: the number of device coredump files to create * -* Creates a new device coredump for the given device. If a previous one hasn't -* been read yet, the new coredump is discarded. The data lifetime is determined -* by the device coredump framework and when it is no longer needed the @free -* function will be called to free the data. +* This function allows drivers to create several device coredump files in +* one crashed device. */ -void dev_coredumpm (struct device *dev,struct module *owner, -void *data,size_t datalen,gfp_t gfp, -ssize_t (*read)(char *buffer,loff_t offset,size_t count, -void *data,size_t datalen), -void (*free)(void *data)) +void dev_coredumpm_bulk (struct device *dev,struct module *owner,gfp_t gfp, +struct dev_coredumpm_bulk_data *files,int num_files) {static atomic_t devcd_count =ATOMIC_INIT (0 );struct devcd_entry *devcd;struct device *existing; +int i;if (devcd_disabled) goto free;
@@ -272,15 +293,11 @@ void dev_coredumpm(struct device *dev, struct module *owner,if (!try_module_get (owner)) goto free; - devcd =kzalloc (sizeof (*devcd), gfp); + devcd =devcd_alloc (files, num_files, gfp);if (!devcd) goto put_module; devcd->owner = owner; - devcd->data = data; - devcd->datalen = datalen; - devcd->read = read; - devcd->free = free; devcd->failing_dev =get_device (dev);device_initialize (&devcd->devcd_dev);
@@ -292,6 +309,12 @@ void dev_coredumpm(struct device *dev, struct module *owner,if (device_add (&devcd->devcd_dev)) goto put_device; +for (i =0 ; i < devcd->num_files; i++) { +if (device_create_bin_file (&devcd->devcd_dev, + &devcd->files[i].bin_attr)) +/* nothing - some files will be missing */ ; + } +if (sysfs_create_link (&devcd->devcd_dev.kobj, &dev->kobj,"failing_device" ))/* nothing - symlink will be missing */ ;
@@ -309,7 +332,41 @@ void dev_coredumpm(struct device *dev, struct module *owner, put_module:module_put (owner); free: -free (data); +for (i =0 ; i < num_files; i++) + files[i].free (files[i].data); +} +EXPORT_SYMBOL_GPL (dev_coredumpm_bulk); + +/** +* dev_coredumpm - create device coredump with read/free methods +* @dev: the struct device for the crashed device +* @owner: the module that contains the read/free functions, use %THIS_MODULE +* @data: data cookie for the @read/@free functions +* @datalen: length of the data +* @gfp: allocation flags +* @read: function to read from the given buffer +* @free: function to free the given buffer +* +* Creates a new device coredump for the given device. If a previous one hasn't +* been read yet, the new coredump is discarded. The data lifetime is determined +* by the device coredump framework and when it is no longer needed the @free +* function will be called to free the data. +*/ +void dev_coredumpm (struct device *dev,struct module *owner, +void *data,size_t datalen,gfp_t gfp, +ssize_t (*read)(char *buffer,loff_t offset,size_t count, +void *data,size_t datalen), +void (*free)(void *data)) +{ +struct dev_coredumpm_bulk_data bulk_data = { + .name ="data" , + .data = data, + .datalen = datalen, + .read = read, + .free = free, + }; + +dev_coredumpm_bulk (dev, owner, gfp, &bulk_data,1 ); }EXPORT_SYMBOL_GPL (dev_coredumpm);
include/linux/devcoredump.h +33 -0
@@ -65,6 +65,26 @@ static inline void _devcd_free_sgtable(struct scatterlist *table)kfree (delete_iter); } +/** +* struct dev_coredumpm_bulk_data - Data used for dev_coredumpm_bulk +* +* @name: coredump file name +* @data: data cookie for the @read/@free functions +* @datalen: length of the data +* @read: function to read from the given buffer +* @free: function to free the given buffer +* +* An array of this structure is passed as argument to dev_coredumpm_bulk, and +* used to describe each device coredump. +*/ +struct dev_coredumpm_bulk_data { +char *name; +void *data; +size_t datalen; +ssize_t (*read)(char *buffer,loff_t offset,size_t count, +void *data,size_t datalen); +void (*free)(void *data); +};#ifdef CONFIG_DEV_COREDUMP void dev_coredumpv(struct device *dev, void *data, size_t datalen,
@@ -76,6 +96,9 @@ void dev_coredumpm(struct device *dev, struct module *owner, void *data, size_t datalen), void (*free)(void *data)); +void dev_coredumpm_bulk (struct device *dev,struct module *owner,gfp_t gfp, +struct dev_coredumpm_bulk_data *files,int num_files); +void dev_coredumpsg (struct device *dev,struct scatterlist *table,size_t datalen,gfp_t gfp);#else
@@ -95,6 +118,16 @@ dev_coredumpm(struct device *dev, struct module *owner,free (data); } +static inline +void dev_coredumpm_bulk (struct device *dev,struct module *owner,gfp_t gfp, +struct dev_coredumpm_bulk_data *files,int num_files) +{ +int i; + +for (i =0 ; i < num_files; i++) + files[i].free (files[i].data); +} +static inline void dev_coredumpsg (struct device *dev,struct scatterlist *table,size_t datalen,gfp_t gfp) {
Signature · 1 line
2.7.4
PATCH v4 4/7 nvme: add basic facilities to get telemetry log page
In reply to Akinobu MitaThis adds the required facilities to get telemetry log page. The telemetry log page structure and identifier are copied from nvme-cli.
We need a facility to check log page attributes in order to know the controller supports the telemetry log pages and log page offset field for the Get Log Page command. The telemetry data area could be larger than maximum data transfer size, so we may need to split into multiple transfers with incremental page offset.
---
* v4
- Add nvme_get_telemetry_log() to nvme core module.
- Copy struct nvme_telemetry_log_page_hdr from the latest nvme-cli
drivers/nvme/host/core.c | 59 ++++++++++++++++++++++++++++++++++++++++++++++++ drivers/nvme/host/nvme.h | 3 +++ include/linux/nvme.h | 32 ++++++++++++++++++++++++++ 3 files changed, 94 insertions(+)
drivers/nvme/host/core.c +59 -0
@@ -2464,6 +2464,7 @@ int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,return nvme_submit_sync_cmd (ctrl->admin_q, &c, log, size); } +EXPORT_SYMBOL_GPL (nvme_get_log);static int nvme_get_effects_log (struct nvme_ctrl *ctrl) {
@@ -2484,6 +2485,62 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl)return ret; } +static int nvme_get_log_blocks (struct nvme_ctrl *ctrl,u32 nsid,u8 log_page, +u8 lsp,void *buf,size_t bytes,loff_t offset) +{ +loff_t pos =0 ; +u32 chunk_size; + +if (check_mul_overflow (ctrl->max_hw_sectors,512u , &chunk_size)) + chunk_size =UINT_MAX ; + +while (pos < bytes) { +size_t size =min_t (size_t, bytes - pos, chunk_size); +int ret; + +if ((offset + pos) && + !(ctrl->lpa &NVME_CTRL_LPA_EXTENDED_DATA )) +return -EINVAL ; + + ret =nvme_get_log (ctrl, nsid, log_page, lsp, buf + pos, size, + offset + pos); +if (ret) +return ret; + + pos += size; + } + +return 0 ; +} + +int nvme_get_telemetry_log (struct nvme_ctrl *ctrl,struct bio_vec *bvecs, +size_t bytes) +{ +struct bvec_iter iter = { + .bi_size = bytes, + }; +size_t offset =0 ; + +while (iter.bi_size) { +struct bio_vec bvec =mp_bvec_iter_bvec (bvecs, iter); +size_t size =min (iter.bi_size, bvec.bv_len); +void *buf =page_address (bvec.bv_page) + bvec.bv_offset; +int ret; + + ret =nvme_get_log_blocks (ctrl,NVME_NSID_ALL , +NVME_LOG_TELEMETRY_CTRL ,0 , buf, size, + offset); +if (ret) +return ret; + + offset += size; +bvec_iter_advance (bvecs, &iter, size); + } + +return 0 ; +} +EXPORT_SYMBOL_GPL (nvme_get_telemetry_log); +/* * Initialize the cached copies of the Identify data and various controller * register in our nvme_ctrl structure. This should be called as soon as
@@ -2587,6 +2644,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) }else ctrl->shutdown_timeout = shutdown_timeout; + ctrl->lpa = id->lpa; ctrl->npss = id->npss; ctrl->apsta = id->apsta; prev_apst_enabled = ctrl->apst_enabled;
@@ -3899,6 +3957,7 @@ static inline void _nvme_check_size(void)BUILD_BUG_ON (sizeof (struct nvme_id_ctrl ) !=NVME_IDENTIFY_DATA_SIZE );BUILD_BUG_ON (sizeof (struct nvme_id_ns ) !=NVME_IDENTIFY_DATA_SIZE );BUILD_BUG_ON (sizeof (struct nvme_lba_range_type ) !=64 ); +BUILD_BUG_ON (sizeof (struct nvme_telemetry_log_page_hdr ) !=512 );BUILD_BUG_ON (sizeof (struct nvme_smart_log ) !=512 );BUILD_BUG_ON (sizeof (struct nvme_dbbuf ) !=64 );BUILD_BUG_ON (sizeof (struct nvme_directive_cmd ) !=64 );
drivers/nvme/host/nvme.h +3 -0
@@ -195,6 +195,7 @@ struct nvme_ctrl {u32 vs;u32 sgls;u16 kas; +u8 lpa;u8 npss;u8 apsta;u32 oaes;
@@ -466,6 +467,8 @@ int nvme_delete_ctrl(struct nvme_ctrl *ctrl);int nvme_get_log (struct nvme_ctrl *ctrl,u32 nsid,u8 log_page,u8 lsp,void *log,size_t size,u64 offset); +int nvme_get_telemetry_log (struct nvme_ctrl *ctrl,struct bio_vec *bvecs, +size_t bytes);extern const struct attribute_group *nvme_ns_id_attr_groups[];extern const struct block_device_operations nvme_ns_head_ops;
include/linux/nvme.h +32 -0
@@ -294,6 +294,8 @@ enum {NVME_CTRL_OACS_DIRECTIVES =1 <<5 ,NVME_CTRL_OACS_DBBUF_SUPP =1 <<8 ,NVME_CTRL_LPA_CMD_EFFECTS_LOG =1 <<1 , +NVME_CTRL_LPA_EXTENDED_DATA =1 <<2 , + NVME_CTRL_LPA_TELEMETRY_LOG = 1 << 3, }; struct nvme_lbaf {
@@ -396,6 +398,35 @@ enum { NVME_NIDT_UUID = 0x03, }; +/** +* struct nvme_telemetry_log_page_hdr - structure for telemetry log page +* @lpi: Log page identifier +* @iee_oui: IEEE OUI Identifier +* @dalb1: Data area 1 last block +* @dalb2: Data area 2 last block +* @dalb3: Data area 3 last block +* @ctrlavail: Controller initiated data available +* @ctrldgn: Controller initiated telemetry Data Generation Number +* @rsnident: Reason Identifier +* @telemetry_dataarea: Contains telemetry data block +* +* This structure can be used for both telemetry host-initiated log page +* and controller-initiated log page. +*/ +struct nvme_telemetry_log_page_hdr { +__u8 lpi; +__u8 rsvd[4 ]; +__u8 iee_oui[3 ]; +__le16 dalb1; +__le16 dalb2; +__le16 dalb3; +__u8 rsvd1[368 ]; +__u8 ctrlavail; +__u8 ctrldgn; +__u8 rsnident[128 ]; +__u8 telemetry_dataarea[0 ]; +}; +struct nvme_smart_log {__u8 critical_warning;__u8 temperature[2 ];
@@ -832,6 +863,7 @@ enum {NVME_LOG_FW_SLOT =0x03 ,NVME_LOG_CHANGED_NS =0x04 ,NVME_LOG_CMD_EFFECTS =0x05 , +NVME_LOG_TELEMETRY_CTRL =0x08 ,NVME_LOG_ANA =0x0c ,NVME_LOG_DISC =0x70 , NVME_LOG_RESERVATION = 0x80,
Signature · 1 line
2.7.4
PATCH v4 5/7 nvme-pci: add device coredump infrastructure
In reply to Akinobu MitaThis provides three functions to implement the device coredump for nvme driver.
nvme_coredump_init() - This function is called when the driver determines to start collecting device coredump. The snapshots of the controller registers, and admin and IO queues are captured by this.
nvme_coredump_logs() - This function is called as soon as the device is recovered from the crash and admin queue becomes available. If the device coredump has already been started by nvme_coredump_init(), the telemetry controller-initiated data will be collected. Otherwise do nothing.
nvme_coredump_complete() - This functions is called when the driver determines that there is nothing to collect device coredump anymore. All collected coredumps are exported via device coredump mechanism.
After finishing the nvme device coredump, the following files are created.
- regs: NVMe controller registers (00h to 4Fh)
- sq<qid>: Submission queue
- cq<qid>: Completion queue
- telemetry-ctrl-log: Telemetry controller-initiated log (if available)
- data: Empty
The reason for an empty 'data' file is to provide a uniform way to notify the device coredump is no longer needed by writing the 'data' file.
Since all existing drivers using the device coredump provide a 'data' file if the nvme device coredump doesn't provide it, the userspace programs need to know which driver provides what coredump file.
---
* v4
- Move nvme_get_telemetry_log() to nvme core module.
- Use bio_vec instead of sg_table to store telemetry log page
- Make nvme_coredump_logs() return error if the device didn't produce a response.
drivers/nvme/host/Kconfig | 1 + drivers/nvme/host/pci.c | 425 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 426 insertions(+)
drivers/nvme/host/Kconfig +1 -0
@@ -5,6 +5,7 @@ config BLK_DEV_NVME tristate "NVM Express block device" depends on PCI && BLOCK select NVME_CORE + select WANT_DEV_COREDUMP ---help--- The NVM Express driver is for solid state drives directly connected to the PCI or PCI Express bus. If you know you
drivers/nvme/host/pci.c +425 -0
449 lines not on this page · raw message
Signature · 1 line
2.7.4
PATCH v4 6/7 nvme-pci: trigger device coredump on command timeout
In reply to Akinobu MitaThis enables the nvme driver to trigger a device coredump when command timeout occurs, and it helps diagnose and debug issues.
This can be tested with fail_io_timeout fault injection.
# echo 1 > /sys/kernel/debug/fail_io_timeout/probability # echo 1 > /sys/kernel/debug/fail_io_timeout/times # echo 1 > /sys/block/nvme0n1/io-timeout-fail # dd if=/dev/nvme0n1 of=/dev/null
---
* v4
- Abandon the reset if nvme_coredump_logs() returns error code
drivers/nvme/host/pci.c | 41 +++++++++++++++++++++++++---------------- 1 file changed, 25 insertions(+), 16 deletions(-)
drivers/nvme/host/pci.c +25 -16
@@ -87,12 +87,12 @@ MODULE_PARM_DESC(poll_queues, "Number of queues to use for polled IO.");struct nvme_dev ;struct nvme_queue ; -static void nvme_dev_disable (struct nvme_dev *dev,bool shutdown); +static void nvme_dev_disable (struct nvme_dev *dev,bool shutdown,bool dump);static bool __nvme_disable_io_queues (struct nvme_dev *dev,u8 opcode); -static void __maybe_unused nvme_coredump_init (struct nvme_dev *dev); -static int __maybe_unused nvme_coredump_logs (struct nvme_dev *dev); -static void __maybe_unused nvme_coredump_complete (struct nvme_dev *dev); +static void nvme_coredump_init (struct nvme_dev *dev); +static int nvme_coredump_logs (struct nvme_dev *dev); +static void nvme_coredump_complete (struct nvme_dev *dev);/* * Represents an NVM Express device. Each nvme_dev is a PCI function.
@@ -1280,7 +1280,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)*/ if (nvme_should_reset (dev, csts)) {nvme_warn_reset (dev, csts); -nvme_dev_disable (dev, false); +nvme_dev_disable (dev, false, true);nvme_reset_ctrl (&dev->ctrl);return BLK_EH_DONE ; }
@@ -1310,7 +1310,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)dev_warn_ratelimited (dev->ctrl.device,"I/O %d QID %d timeout, disable controller\n" , req->tag, nvmeq->qid); -nvme_dev_disable (dev, shutdown); +nvme_dev_disable (dev, shutdown, true);nvme_req (req)->flags |=NVME_REQ_CANCELLED ;return BLK_EH_DONE ;default :
@@ -1326,7 +1326,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)dev_warn (dev->ctrl.device,"I/O %d QID %d timeout, reset controller\n" , req->tag, nvmeq->qid); -nvme_dev_disable (dev, false); +nvme_dev_disable (dev, false, true);nvme_reset_ctrl (&dev->ctrl);nvme_req (req)->flags |=NVME_REQ_CANCELLED ;
@@ -2382,7 +2382,7 @@ static void nvme_pci_disable(struct nvme_dev *dev) } } -static void nvme_dev_disable (struct nvme_dev *dev,bool shutdown) +static void nvme_dev_disable (struct nvme_dev *dev,bool shutdown,bool dump) {bool dead = true;struct pci_dev *pdev =to_pci_dev (dev->dev);
@@ -2407,6 +2407,9 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)nvme_wait_freeze_timeout (&dev->ctrl,NVME_IO_TIMEOUT ); } +if (dump) +nvme_coredump_init (dev); +nvme_stop_queues (&dev->ctrl);if (!dead && dev->ctrl.queue_count >0 ) {
@@ -2477,7 +2480,7 @@ static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status)dev_warn (dev->ctrl.device,"Removing after probe failure status: %d\n" , status);nvme_get_ctrl (&dev->ctrl); -nvme_dev_disable (dev, false); +nvme_dev_disable (dev, false, false);nvme_kill_queues (&dev->ctrl);if (!queue_work (nvme_wq, &dev->remove_work))nvme_put_ctrl (&dev->ctrl);
@@ -2499,7 +2502,7 @@ static void nvme_reset_work(struct work_struct *work)* moving on. */ if (dev->ctrl.ctrl_config &NVME_CC_ENABLE ) -nvme_dev_disable (dev, false); +nvme_dev_disable (dev, false, false);mutex_lock (&dev->shutdown_lock); result =nvme_pci_enable (dev);
@@ -2536,6 +2539,11 @@ static void nvme_reset_work(struct work_struct *work)if (result) goto out; + result =nvme_coredump_logs (dev); +if (result) + goto out; +nvme_coredump_complete (dev); +if (dev->ctrl.oacs &NVME_CTRL_OACS_SEC_SUPP ) {if (!dev->ctrl.opal_dev) dev->ctrl.opal_dev =
@@ -2598,6 +2606,7 @@ static void nvme_reset_work(struct work_struct *work) out_unlock:mutex_unlock (&dev->shutdown_lock); out: +nvme_coredump_complete (dev);nvme_remove_dead_ctrl (dev, result); }
@@ -2788,7 +2797,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)static void nvme_reset_prepare (struct pci_dev *pdev) {struct nvme_dev *dev =pci_get_drvdata (pdev); -nvme_dev_disable (dev, false); +nvme_dev_disable (dev, false, false); }static void nvme_reset_done (struct pci_dev *pdev)
@@ -2800,7 +2809,7 @@ static void nvme_reset_done(struct pci_dev *pdev)static void nvme_shutdown (struct pci_dev *pdev) {struct nvme_dev *dev =pci_get_drvdata (pdev); -nvme_dev_disable (dev, true); +nvme_dev_disable (dev, true, false); }/*
@@ -2817,14 +2826,14 @@ static void nvme_remove(struct pci_dev *pdev)if (!pci_device_is_present (pdev)) {nvme_change_ctrl_state (&dev->ctrl,NVME_CTRL_DEAD ); -nvme_dev_disable (dev, true); +nvme_dev_disable (dev, true, false);nvme_dev_remove_admin (dev); }flush_work (&dev->ctrl.reset_work);nvme_stop_ctrl (&dev->ctrl);nvme_remove_namespaces (&dev->ctrl); -nvme_dev_disable (dev, true); +nvme_dev_disable (dev, true, false);nvme_release_cmb (dev);nvme_free_host_mem (dev);nvme_dev_remove_admin (dev);
@@ -2841,7 +2850,7 @@ static int nvme_suspend(struct device *dev)struct pci_dev *pdev =to_pci_dev (dev);struct nvme_dev *ndev =pci_get_drvdata (pdev); -nvme_dev_disable (ndev, true); +nvme_dev_disable (ndev, true, false);return 0 ; }
@@ -3290,7 +3299,7 @@ static pci_ers_result_t nvme_error_detected(struct pci_dev *pdev,case pci_channel_io_frozen:dev_warn (dev->ctrl.device,"frozen state error detected, reset controller\n" ); -nvme_dev_disable (dev, false); +nvme_dev_disable (dev, false, false);return PCI_ERS_RESULT_NEED_RESET ;case pci_channel_io_perm_failure: dev_warn(dev->ctrl.device,
Signature · 1 line
2.7.4
PATCH v4 7/7 nvme-pci: enable to trigger device coredump by hand
In reply to Akinobu MitaThis provides a way to trigger the nvme device coredump by writing anything to /sys/devices/.../coredump attribute.
---
* v4
- No change since v3
drivers/nvme/host/pci.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)
drivers/nvme/host/pci.c +13 -0
@@ -3266,6 +3266,14 @@ static void nvme_coredump_complete(struct nvme_dev *dev) nvme_coredump_clear(dev); } +static void nvme_coredump (struct device *dev) +{ +struct nvme_dev *ndev =dev_get_drvdata (dev); + +nvme_dev_disable (ndev, false, true); +nvme_reset_ctrl_sync (&ndev->ctrl); +} +#else static void nvme_coredump_init (struct nvme_dev *dev)
@@ -3281,6 +3289,10 @@ static void nvme_coredump_complete(struct nvme_dev *dev) { } +static void nvme_coredump (struct device *dev) +{ +} +#endif /* CONFIG_DEV_COREDUMP */ static pci_ers_result_t nvme_error_detected(struct pci_dev *pdev,
@@ -3388,6 +3400,7 @@ static struct pci_driver nvme_driver = { .shutdown = nvme_shutdown, .driver = { .pm = &nvme_dev_pm_ops, + .coredump = nvme_coredump, }, .sriov_configure = pci_sriov_configure_simple, .err_handler = &nvme_err_handler,
Signature · 1 line
2.7.4