From: Arun Iyengar <[email protected]>

panfrost_reset() soft-stops the slots and waits for them to go idle by
polling JOB_INT_JS_STATE. That register is a snapshot of the slot states
taken when JOB_INT_CLEAR was last written (Arm driver: "status==active
and _next == busy snapshot from last JOB_IRQ_CLEAR"). For a job started
into an idle slot, the usual case for an OpenCL queue that submits one
kernel at a time, it shows the slot idle and the wait ends at once.

The GPU reset that follows hides this by killing the job. With the job
resumed instead (next patch), it was removed from pfdev->jobs[] and
resubmitted while its first run was still stopping. When the first run
reported DONE, the handler signalled the resubmission's fence, the job
manager started the resubmission from _NEXT, and its completion found no
job on the slot (Mali-G31, OpenCL CTS Integer Ops):

  Unable to handle kernel NULL pointer dereference at virtual address 
00000000000000f8
  pc : panfrost_dequeue_job+0x2c/0xd8 [panfrost]
  lr : panfrost_jm_handle_irqs+0x268/0x570 [panfrost]

Wait until no JS_STATUS register reads ACTIVE instead, so that the
pending DONE or STOPPED interrupt is handled before the queues are
touched. Also make panfrost_dequeue_job() return NULL for a slot without
a job: every caller copes with it, so a stray event is a WARN, not an
Oops.

Fixes: 030761e097b4 ("drm/panfrost: Queue jobs on the hardware")
Signed-off-by: Arun Iyengar <[email protected]>
---
 drivers/gpu/drm/panfrost/panfrost_job.c | 41 +++++++++++++++------------------
 1 file changed, 19 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c 
b/drivers/gpu/drm/panfrost/panfrost_job.c
index 1b7becf7b..8235d182d 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -173,7 +173,8 @@ panfrost_dequeue_job(struct panfrost_device *pfdev, int 
slot)
 {
        struct panfrost_job *job = pfdev->jobs[slot][0];
 
-       WARN_ON(!job);
+       if (WARN_ON(!job))
+               return NULL;
 
        if (job->is_profiled && job->engine_usage) {
                job->engine_usage->elapsed_ns[slot] +=
@@ -647,25 +648,20 @@ static void panfrost_jm_handle_irqs(struct 
panfrost_device *pfdev)
        }
 }
 
-static u32 panfrost_active_slots(struct panfrost_device *pfdev,
-                                u32 *js_state_mask, u32 js_state)
+/* Reads the live JS_STATUS: JOB_INT_JS_STATE is a snapshot from the last
+ * JOB_INT_CLEAR write and can show a busy slot as idle.
+ */
+static bool panfrost_slots_idle(struct panfrost_device *pfdev)
 {
-       u32 rawstat;
-
-       if (!(js_state & *js_state_mask))
-               return 0;
-
-       rawstat = job_read(pfdev, JOB_INT_RAWSTAT);
-       if (rawstat) {
-               unsigned int i;
+       unsigned int i;
 
-               for (i = 0; i < NUM_JOB_SLOTS; i++) {
-                       if (rawstat & MK_JS_MASK(i))
-                               *js_state_mask &= ~MK_JS_MASK(i);
-               }
+       for (i = 0; i < NUM_JOB_SLOTS; i++) {
+               if (job_read(pfdev, JS_STATUS(i)) ==
+                   DRM_PANFROST_EXCEPTION_ACTIVE)
+                       return false;
        }
 
-       return js_state & *js_state_mask;
+       return true;
 }
 
 static void
@@ -673,9 +669,8 @@ panfrost_reset(struct panfrost_device *pfdev,
               struct drm_sched_job *bad)
 {
        struct panfrost_job *evicted[NUM_JOB_SLOTS] = {};
-       u32 js_state, js_state_mask = 0xffffffff;
        unsigned int i, j;
-       bool cookie;
+       bool cookie, idle;
        int ret;
 
        if (!atomic_read(&pfdev->reset.pending))
@@ -728,10 +723,12 @@ panfrost_reset(struct panfrost_device *pfdev,
        }
        spin_unlock(&pfdev->js->job_lock);
 
-       /* Wait at most 10ms for soft-stops to complete */
-       ret = readl_poll_timeout(pfdev->iomem + JOB_INT_JS_STATE, js_state,
-                                !panfrost_active_slots(pfdev, &js_state_mask, 
js_state),
-                                10, 10000);
+       /* Wait at most 10ms for soft-stops to complete. No slot may be active
+        * when we touch the queues: a late interrupt would find the wrong job,
+        * or none, in pfdev->jobs[].
+        */
+       ret = read_poll_timeout(panfrost_slots_idle, idle, idle, 10, 10000,
+                               false, pfdev);
 
        if (ret)
                dev_err(pfdev->base.dev, "Soft-stop failed\n");

-- 
2.55.0


Reply via email to