diff mbox series

[v4,8/8] nvdimm: Fix firmware activation deadlock scenarios

Message ID 165074883800.4116052.10737040861825806582.stgit@dwillia2-desk3.amr.corp.intel.com
State Accepted
Commit e6829d1bd3c4b58296ee9e412f7ed4d6cb390192
Headers show
Series None | expand

Commit Message

Dan Williams April 23, 2022, 9:22 p.m. UTC
Lockdep reports the following deadlock scenarios for CXL root device
power-management, device_prepare(), operations, and device_shutdown()
operations for 'nd_region' devices:

---
 Chain exists of:
   &nvdimm_region_key --> &nvdimm_bus->reconfig_mutex --> system_transition_mutex

  Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   lock(system_transition_mutex);
                                lock(&nvdimm_bus->reconfig_mutex);
                                lock(system_transition_mutex);
   lock(&nvdimm_region_key);

--

 Chain exists of:
   &cxl_nvdimm_bridge_key --> acpi_scan_lock --> &cxl_root_key

  Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   lock(&cxl_root_key);
                                lock(acpi_scan_lock);
                                lock(&cxl_root_key);
   lock(&cxl_nvdimm_bridge_key);

---

These stem from holding nvdimm_bus_lock() over hibernate_quiet_exec()
which walks the entire system device topology taking device_lock() along
the way. The nvdimm_bus_lock() is protecting against unregistration,
multiple simultaneous ops callers, and preventing activate_show() from
racing activate_store(). For the first 2, the lock is redundant.
Unregistration already flushes all ops users, and sysfs already prevents
multiple threads to be active in an ops handler at the same time. For
the last userspace should already be waiting for its last
activate_store() to complete, and does not need activate_show() to flush
the write side, so this lock usage can be deleted in these attributes.

Fixes: 48001ea50d17 ("PM, libnvdimm: Add runtime firmware activation support")
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
Changes since v3:
- Remove nvdimm_bus_lock() from all ->capability() invocations (Ira)

 drivers/nvdimm/core.c |    9 ---------
 1 file changed, 9 deletions(-)

Comments

Ira Weiny April 24, 2022, 11:30 p.m. UTC | #1
On Sat, Apr 23, 2022 at 02:22:18PM -0700, Dan Williams wrote:
> Lockdep reports the following deadlock scenarios for CXL root device
> power-management, device_prepare(), operations, and device_shutdown()
> operations for 'nd_region' devices:
> 
> ---
>  Chain exists of:
>    &nvdimm_region_key --> &nvdimm_bus->reconfig_mutex --> system_transition_mutex
> 
>   Possible unsafe locking scenario:
> 
>         CPU0                    CPU1
>         ----                    ----
>    lock(system_transition_mutex);
>                                 lock(&nvdimm_bus->reconfig_mutex);
>                                 lock(system_transition_mutex);
>    lock(&nvdimm_region_key);
> 
> --
> 
>  Chain exists of:
>    &cxl_nvdimm_bridge_key --> acpi_scan_lock --> &cxl_root_key
> 
>   Possible unsafe locking scenario:
> 
>         CPU0                    CPU1
>         ----                    ----
>    lock(&cxl_root_key);
>                                 lock(acpi_scan_lock);
>                                 lock(&cxl_root_key);
>    lock(&cxl_nvdimm_bridge_key);
> 
> ---
> 
> These stem from holding nvdimm_bus_lock() over hibernate_quiet_exec()
> which walks the entire system device topology taking device_lock() along
> the way. The nvdimm_bus_lock() is protecting against unregistration,
> multiple simultaneous ops callers, and preventing activate_show() from
> racing activate_store(). For the first 2, the lock is redundant.
> Unregistration already flushes all ops users, and sysfs already prevents
> multiple threads to be active in an ops handler at the same time. For
> the last userspace should already be waiting for its last
> activate_store() to complete, and does not need activate_show() to flush
> the write side, so this lock usage can be deleted in these attributes.
> 
> Fixes: 48001ea50d17 ("PM, libnvdimm: Add runtime firmware activation support")
> Signed-off-by: Dan Williams <dan.j.williams@intel.com>

Reviewed-by: Ira Weiny <ira.weiny@intel.com>

> ---
> Changes since v3:
> - Remove nvdimm_bus_lock() from all ->capability() invocations (Ira)
> 
>  drivers/nvdimm/core.c |    9 ---------
>  1 file changed, 9 deletions(-)
> 
> diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
> index 144926b7451c..d91799b71d23 100644
> --- a/drivers/nvdimm/core.c
> +++ b/drivers/nvdimm/core.c
> @@ -368,9 +368,7 @@ static ssize_t capability_show(struct device *dev,
>  	if (!nd_desc->fw_ops)
>  		return -EOPNOTSUPP;
>  
> -	nvdimm_bus_lock(dev);
>  	cap = nd_desc->fw_ops->capability(nd_desc);
> -	nvdimm_bus_unlock(dev);
>  
>  	switch (cap) {
>  	case NVDIMM_FWA_CAP_QUIESCE:
> @@ -395,10 +393,8 @@ static ssize_t activate_show(struct device *dev,
>  	if (!nd_desc->fw_ops)
>  		return -EOPNOTSUPP;
>  
> -	nvdimm_bus_lock(dev);
>  	cap = nd_desc->fw_ops->capability(nd_desc);
>  	state = nd_desc->fw_ops->activate_state(nd_desc);
> -	nvdimm_bus_unlock(dev);
>  
>  	if (cap < NVDIMM_FWA_CAP_QUIESCE)
>  		return -EOPNOTSUPP;
> @@ -443,7 +439,6 @@ static ssize_t activate_store(struct device *dev,
>  	else
>  		return -EINVAL;
>  
> -	nvdimm_bus_lock(dev);
>  	state = nd_desc->fw_ops->activate_state(nd_desc);
>  
>  	switch (state) {
> @@ -461,7 +456,6 @@ static ssize_t activate_store(struct device *dev,
>  	default:
>  		rc = -ENXIO;
>  	}
> -	nvdimm_bus_unlock(dev);
>  
>  	if (rc == 0)
>  		rc = len;
> @@ -484,10 +478,7 @@ static umode_t nvdimm_bus_firmware_visible(struct kobject *kobj, struct attribut
>  	if (!nd_desc->fw_ops)
>  		return 0;
>  
> -	nvdimm_bus_lock(dev);
>  	cap = nd_desc->fw_ops->capability(nd_desc);
> -	nvdimm_bus_unlock(dev);
> -
>  	if (cap < NVDIMM_FWA_CAP_QUIESCE)
>  		return 0;
>  
>
diff mbox series

Patch

diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
index 144926b7451c..d91799b71d23 100644
--- a/drivers/nvdimm/core.c
+++ b/drivers/nvdimm/core.c
@@ -368,9 +368,7 @@  static ssize_t capability_show(struct device *dev,
 	if (!nd_desc->fw_ops)
 		return -EOPNOTSUPP;
 
-	nvdimm_bus_lock(dev);
 	cap = nd_desc->fw_ops->capability(nd_desc);
-	nvdimm_bus_unlock(dev);
 
 	switch (cap) {
 	case NVDIMM_FWA_CAP_QUIESCE:
@@ -395,10 +393,8 @@  static ssize_t activate_show(struct device *dev,
 	if (!nd_desc->fw_ops)
 		return -EOPNOTSUPP;
 
-	nvdimm_bus_lock(dev);
 	cap = nd_desc->fw_ops->capability(nd_desc);
 	state = nd_desc->fw_ops->activate_state(nd_desc);
-	nvdimm_bus_unlock(dev);
 
 	if (cap < NVDIMM_FWA_CAP_QUIESCE)
 		return -EOPNOTSUPP;
@@ -443,7 +439,6 @@  static ssize_t activate_store(struct device *dev,
 	else
 		return -EINVAL;
 
-	nvdimm_bus_lock(dev);
 	state = nd_desc->fw_ops->activate_state(nd_desc);
 
 	switch (state) {
@@ -461,7 +456,6 @@  static ssize_t activate_store(struct device *dev,
 	default:
 		rc = -ENXIO;
 	}
-	nvdimm_bus_unlock(dev);
 
 	if (rc == 0)
 		rc = len;
@@ -484,10 +478,7 @@  static umode_t nvdimm_bus_firmware_visible(struct kobject *kobj, struct attribut
 	if (!nd_desc->fw_ops)
 		return 0;
 
-	nvdimm_bus_lock(dev);
 	cap = nd_desc->fw_ops->capability(nd_desc);
-	nvdimm_bus_unlock(dev);
-
 	if (cap < NVDIMM_FWA_CAP_QUIESCE)
 		return 0;