This patch changes the location of taking a mutex lock and releasing it during the hard-reset process of the ASIC.
The only place we need to protect is when we dereference pointers that may go away in case the user process aborts/closes the FD. That way, we allow the user process to actually close its FD in case we tell him that an error occurred. Signed-off-by: Oded Gabbay <[email protected]> --- drivers/misc/habanalabs/device.c | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c index 5400e65ba5fa..471506b54217 100644 --- a/drivers/misc/habanalabs/device.c +++ b/drivers/misc/habanalabs/device.c @@ -574,20 +574,21 @@ static void device_kill_open_processes(struct hl_device *hdev) else pending_total = HL_PENDING_RESET_PER_SEC; - pending_cnt = pending_total; - /* Flush all processes that are inside hl_open */ mutex_lock(&hdev->fpriv_list_lock); + mutex_unlock(&hdev->fpriv_list_lock); - while ((!list_empty(&hdev->fpriv_list)) && (pending_cnt)) { - - pending_cnt--; - - dev_info(hdev->dev, - "Can't HARD reset, waiting for user to close FD\n"); + /* Giving time for user to close FD, and for processes that are inside + * hl_device_open to finish + */ + if (!list_empty(&hdev->fpriv_list)) ssleep(1); - } + mutex_lock(&hdev->fpriv_list_lock); + + /* This section must be protected because we are dereferencing + * pointers that are freed if the process exits + */ if (!list_empty(&hdev->fpriv_list)) { task = get_pid_task(hdev->compute_ctx->hpriv->taskpid, PIDTYPE_PID); @@ -600,6 +601,8 @@ static void device_kill_open_processes(struct hl_device *hdev) } } + mutex_unlock(&hdev->fpriv_list_lock); + /* We killed the open users, but because the driver cleans up after the * user contexts are closed (e.g. mmu mappings), we need to wait again * to make sure the cleaning phase is finished before continuing with @@ -609,6 +612,8 @@ static void device_kill_open_processes(struct hl_device *hdev) pending_cnt = pending_total; while ((!list_empty(&hdev->fpriv_list)) && (pending_cnt)) { + dev_info(hdev->dev, + "Waiting for all unmap operations to finish before hard reset\n"); pending_cnt--; @@ -618,9 +623,6 @@ static void device_kill_open_processes(struct hl_device *hdev) if (!list_empty(&hdev->fpriv_list)) dev_crit(hdev->dev, "Going to hard reset with open user contexts\n"); - - mutex_unlock(&hdev->fpriv_list_lock); - } static void device_hard_reset_pending(struct work_struct *work) -- 2.17.1
