msm: kgsl: Detect long running IBs
When expired global timestamp is not progressing,
check if an IB is talking more than 2 seconds
with no update in GPU read pointer, IB1 base
IB1 size, IB2 base, IB2 size and detect it as a
long running IB. Invalidate the context of the IB
and do not attempt fault tolerance on this context.
Change-Id: I7e9780f5aed73a5c8807069aa506bec16a1576b4
Signed-off-by: Tarun Karra <tkarra@codeaurora.org>
diff --git a/drivers/gpu/msm/adreno_ringbuffer.c b/drivers/gpu/msm/adreno_ringbuffer.c
index 6fda86d..d3e5dea 100644
--- a/drivers/gpu/msm/adreno_ringbuffer.c
+++ b/drivers/gpu/msm/adreno_ringbuffer.c
@@ -64,7 +64,7 @@
unsigned long wait_time;
unsigned long wait_timeout = msecs_to_jiffies(ADRENO_IDLE_TIMEOUT);
unsigned long wait_time_part;
- unsigned int prev_reg_val[hang_detect_regs_count];
+ unsigned int prev_reg_val[ft_detect_regs_count];
memset(prev_reg_val, 0, sizeof(prev_reg_val));
@@ -109,7 +109,7 @@
if (time_after(jiffies, wait_time_part)) {
wait_time_part = jiffies +
msecs_to_jiffies(KGSL_TIMEOUT_PART);
- if ((adreno_hang_detect(rb->device,
+ if ((adreno_ft_detect(rb->device,
prev_reg_val))){
KGSL_DRV_ERR(rb->device,
"Hang detected while waiting for freespace in"
@@ -982,17 +982,17 @@
drawctxt = context->devctxt;
if (drawctxt->flags & CTXT_FLAGS_GPU_HANG) {
- KGSL_CTXT_ERR(device, "Context %p failed fault tolerance"
+ KGSL_CTXT_ERR(device, "proc %s failed fault tolerance"
" will not accept commands for context %d\n",
- drawctxt, drawctxt->id);
+ drawctxt->pid_name, drawctxt->id);
return -EDEADLK;
}
if (drawctxt->flags & CTXT_FLAGS_SKIP_EOF) {
KGSL_CTXT_ERR(device,
- "Context %p triggered fault tolerance"
+ "proc %s triggered fault tolerance"
" skipping commands for context till EOF %d\n",
- drawctxt, drawctxt->id);
+ drawctxt->pid_name, drawctxt->id);
if (flags & KGSL_CMD_FLAGS_EOF)
drawctxt->flags &= ~CTXT_FLAGS_SKIP_EOF;
numibs = 0;