From: Arun Iyengar <[email protected]>

While a reset is pending, panfrost_job_hw_submit() puts the job in
pfdev->jobs[] without starting it; the reset resubmits it. But
reset.pending is set, by a timeout or a job fault, before
panfrost_reset() masks the job interrupt. If such a job waits behind a
running one that completes in that window, panfrost_jm_handle_irq()
finds both subslots inactive and takes the waiting job for done as well.
Its fence is signalled and its jc cleared, so it is never run.

Mark a job as started when JS_COMMAND_START is written for it, and leave
a job that was not started to the reset.

Found by code review (Sashiko). Not reproduced.

Fixes: 030761e097b4 ("drm/panfrost: Queue jobs on the hardware")
Cc: [email protected]
Reported-by: Sashiko <[email protected]>
Closes: https://lore.kernel.org/all/[email protected]/
Signed-off-by: Arun Iyengar <[email protected]>
---
 drivers/gpu/drm/panfrost/panfrost_job.c | 8 ++++++--
 drivers/gpu/drm/panfrost/panfrost_job.h | 2 ++
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c 
b/drivers/gpu/drm/panfrost/panfrost_job.c
index df7fcc436..1b7becf7b 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -261,6 +261,7 @@ static int panfrost_job_hw_submit(struct panfrost_job *job, 
int js)
 
        spin_lock(&pfdev->js->job_lock);
        subslot = panfrost_enqueue_job(pfdev, js, job);
+       job->started = false;
        /* Don't queue the job if a reset is in progress */
        if (!atomic_read(&pfdev->reset.pending)) {
                job->is_profiled = pfdev->profile_mode;
@@ -276,6 +277,7 @@ static int panfrost_job_hw_submit(struct panfrost_job *job, 
int js)
                        job->start_cycles = panfrost_cycle_counter_read(pfdev);
                }
 
+               job->started = true;
                job_write(pfdev, JS_COMMAND_NEXT(js), JS_COMMAND_START);
                dev_dbg(pfdev->base.dev,
                        "JS: Submitting atom %p to js[%d][%d] with head=0x%llx 
AS %d",
@@ -586,7 +588,8 @@ static void panfrost_jm_handle_irq(struct panfrost_device 
*pfdev, u32 status)
 
                if (failed[j]) {
                        panfrost_job_handle_err(pfdev, failed[j], j);
-               } else if (pfdev->jobs[j][0] && !(js_state & MK_JS_MASK(j))) {
+               } else if (pfdev->jobs[j][0] && pfdev->jobs[j][0]->started &&
+                          !(js_state & MK_JS_MASK(j))) {
                        /* When the current job doesn't fail, the JM dequeues
                         * the next job without waiting for an ACK, this means
                         * we can have 2 jobs dequeued and only catch the
@@ -594,7 +597,8 @@ static void panfrost_jm_handle_irq(struct panfrost_device 
*pfdev, u32 status)
                         * are inactive, but one job remains in pfdev->jobs[j],
                         * consider it done. Of course that doesn't apply if a
                         * failure happened since we cancelled execution of the
-                        * job in _NEXT (see above).
+                        * job in _NEXT (see above), or if the job was queued
+                        * while a reset was pending and never started.
                         */
                        if (WARN_ON(!done[j][0]))
                                done[j][0] = panfrost_dequeue_job(pfdev, j);
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.h 
b/drivers/gpu/drm/panfrost/panfrost_job.h
index cd82d7930..4d1c54243 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.h
+++ b/drivers/gpu/drm/panfrost/panfrost_job.h
@@ -38,6 +38,8 @@ struct panfrost_job {
        bool is_profiled;
        /* Holds a reference on the cycle counter */
        bool cycle_counter_ref;
+       /* JS_COMMAND_START was written for this submission */
+       bool started;
        ktime_t start_time;
        u64 start_cycles;
 };

-- 
2.55.0


Reply via email to