habanalabs: perform accounting for active CS

This patch adds accounting for active CS. Active means that the CS was
submitted to the H/W queues and was not completed yet.

This is necessary to support suspend operation. Because the device will be
reset upon suspend, we can only suspend after all active CS have been
completed. Hence, we need to perform accounting on their number.

Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c
index 3525236..19c8421 100644 (file)
--- a/drivers/misc/habanalabs/command_submission.c
+++ b/drivers/misc/habanalabs/command_submission.c
@@ -179,6 +179,12 @@ static void cs_do_release(struct kref *ref)
 
        /* We also need to update CI for internal queues */
        if (cs->submitted) {
+               int cs_cnt = atomic_dec_return(&hdev->cs_active_cnt);
+
+               WARN_ONCE((cs_cnt < 0),
+                       "hl%d: error in CS active cnt %d\n",
+                       hdev->id, cs_cnt);
+
                hl_int_hw_queue_update_ci(cs);
 
                spin_lock(&hdev->hw_queues_mirror_lock);

diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c
index 93d6798..470d800 100644 (file)
--- a/drivers/misc/habanalabs/device.c
+++ b/drivers/misc/habanalabs/device.c
@@ -218,6 +218,7 @@ static int device_early_init(struct hl_device *hdev)
        spin_lock_init(&hdev->hw_queues_mirror_lock);
        atomic_set(&hdev->in_reset, 0);
        atomic_set(&hdev->fd_open_cnt, 0);
+       atomic_set(&hdev->cs_active_cnt, 0);
 
        return 0;
 

diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h
index 806f0a5..a8ee52c 100644 (file)
--- a/drivers/misc/habanalabs/habanalabs.h
+++ b/drivers/misc/habanalabs/habanalabs.h
@@ -1056,13 +1056,15 @@ struct hl_device_reset_work {
  * @cb_pool_lock: protects the CB pool.
  * @user_ctx: current user context executing.
  * @dram_used_mem: current DRAM memory consumption.
- * @in_reset: is device in reset flow.
- * @curr_pll_profile: current PLL profile.
- * @fd_open_cnt: number of open user processes.
  * @timeout_jiffies: device CS timeout value.
  * @max_power: the max power of the device, as configured by the sysadmin. This
  *             value is saved so in case of hard-reset, KMD will restore this
  *             value and update the F/W after the re-initialization
+ * @in_reset: is device in reset flow.
+ * @curr_pll_profile: current PLL profile.
+ * @fd_open_cnt: number of open user processes.
+ * @cs_active_cnt: number of active command submissions on this device (active
+ *                 means already in H/W queues)
  * @major: habanalabs KMD major.
  * @high_pll: high PLL profile frequency.
  * @soft_reset_cnt: number of soft reset since KMD loading.
@@ -1128,11 +1130,12 @@ struct hl_device {
        struct hl_ctx                   *user_ctx;
 
        atomic64_t                      dram_used_mem;
+       u64                             timeout_jiffies;
+       u64                             max_power;
        atomic_t                        in_reset;
        atomic_t                        curr_pll_profile;
        atomic_t                        fd_open_cnt;
-       u64                             timeout_jiffies;
-       u64                             max_power;
+       atomic_t                        cs_active_cnt;
        u32                             major;
        u32                             high_pll;
        u32                             soft_reset_cnt;

diff --git a/drivers/misc/habanalabs/hw_queue.c b/drivers/misc/habanalabs/hw_queue.c
index 67bece2..ef3bb69 100644 (file)
--- a/drivers/misc/habanalabs/hw_queue.c
+++ b/drivers/misc/habanalabs/hw_queue.c
@@ -370,12 +370,13 @@ int hl_hw_queue_schedule_cs(struct hl_cs *cs)
                spin_unlock(&hdev->hw_queues_mirror_lock);
        }
 
-       list_for_each_entry_safe(job, tmp, &cs->job_list, cs_node) {
+       atomic_inc(&hdev->cs_active_cnt);
+
+       list_for_each_entry_safe(job, tmp, &cs->job_list, cs_node)
                if (job->ext_queue)
                        ext_hw_queue_schedule_job(job);
                else
                        int_hw_queue_schedule_job(job);
-       }
 
        cs->submitted = true;