diff options
-rw-r--r-- | drivers/misc/habanalabs/common/device.c | 6 | ||||
-rw-r--r-- | drivers/misc/habanalabs/common/habanalabs.h | 11 |
2 files changed, 12 insertions, 5 deletions
diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c index 0650e511a0f5..63d0cb7087e8 100644 --- a/drivers/misc/habanalabs/common/device.c +++ b/drivers/misc/habanalabs/common/device.c @@ -2300,14 +2300,16 @@ void hl_device_fini(struct hl_device *hdev) */ dev_info(hdev->dev, "Waiting for all processes to exit (timeout of %u seconds)", - HL_PENDING_RESET_LONG_SEC); + HL_WAIT_PROCESS_KILL_ON_DEVICE_FINI); - rc = device_kill_open_processes(hdev, HL_PENDING_RESET_LONG_SEC, false); + hdev->process_kill_trial_cnt = 0; + rc = device_kill_open_processes(hdev, HL_WAIT_PROCESS_KILL_ON_DEVICE_FINI, false); if (rc) { dev_crit(hdev->dev, "Failed to kill all open processes\n"); device_disable_open_processes(hdev, false); } + hdev->process_kill_trial_cnt = 0; rc = device_kill_open_processes(hdev, 0, true); if (rc) { dev_crit(hdev->dev, "Failed to kill all control device open processes\n"); diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index 0781b8698f74..e7f89868428d 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -50,9 +50,14 @@ struct hl_fpriv; #define HL_MMAP_OFFSET_VALUE_MASK (0x1FFFFFFFFFFFull >> PAGE_SHIFT) #define HL_MMAP_OFFSET_VALUE_GET(off) (off & HL_MMAP_OFFSET_VALUE_MASK) -#define HL_PENDING_RESET_PER_SEC 10 -#define HL_PENDING_RESET_MAX_TRIALS 60 /* 10 minutes */ -#define HL_PENDING_RESET_LONG_SEC 60 +#define HL_PENDING_RESET_PER_SEC 10 +#define HL_PENDING_RESET_MAX_TRIALS 60 /* 10 minutes */ +#define HL_PENDING_RESET_LONG_SEC 60 +/* + * In device fini, wait 10 minutes for user processes to be terminated after we kill them. + * This is needed to prevent situation of clearing resources while user processes are still alive. + */ +#define HL_WAIT_PROCESS_KILL_ON_DEVICE_FINI 600 #define HL_HARD_RESET_MAX_TIMEOUT 120 #define HL_PLDM_HARD_RESET_MAX_TIMEOUT (HL_HARD_RESET_MAX_TIMEOUT * 3) |