From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 24 Apr 2018 09:16:00 +0100
Subject: drm/i915: Don't dump umpteen thousand requests
Git-commit: 56021f48dbea69a00b96a53d6450b0950f9c811f
Patch-mainline: v4.18-rc1
References: FATE#326289 FATE#326079 FATE#326049 FATE#322398 FATE#326166
If we have more than a few, possibly several thousand request in the
queue, don't show the central portion, just the first few and the last
being executed and/or queued. The first few should be enough to help
identify a problem in execution, and most often comparing the first/last
in the queue is enough to identify problems in the scheduling.
We may need some fine tuning to set MAX_REQUESTS_TO_SHOW for common
debug scenarios, but for the moment if we can avoiding spending more
than a few seconds dumping the GPU state that will avoid a nasty
livelock (where hangcheck spends so long dumping the state, it fires
again and starts to dump the state again in parallel, ad infinitum).
v2: Remember to print last not the stale rq iter after the loop.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180424081600.27544-1-chris@chris-wilson.co.uk
Acked-by: Petr Tesarik <ptesarik@suse.com>
---
drivers/gpu/drm/i915/intel_engine_cs.c | 43 +++++++++++++++++++++++++++++----
1 file changed, 38 insertions(+), 5 deletions(-)
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1307,11 +1307,13 @@ void intel_engine_dump(struct intel_engi
struct drm_printer *m,
const char *header, ...)
{
+ const int MAX_REQUESTS_TO_SHOW = 8;
struct intel_breadcrumbs * const b = &engine->breadcrumbs;
const struct intel_engine_execlists * const execlists = &engine->execlists;
struct i915_gpu_error * const error = &engine->i915->gpu_error;
- struct i915_request *rq;
+ struct i915_request *rq, *last;
struct rb_node *rb;
+ int count;
if (header) {
va_list ap;
@@ -1378,16 +1380,47 @@ void intel_engine_dump(struct intel_engi
}
spin_lock_irq(&engine->timeline->lock);
- list_for_each_entry(rq, &engine->timeline->requests, link)
- print_request(m, rq, "\t\tE ");
+
+ last = NULL;
+ count = 0;
+ list_for_each_entry(rq, &engine->timeline->requests, link) {
+ if (count++ < MAX_REQUESTS_TO_SHOW - 1)
+ print_request(m, rq, "\t\tE ");
+ else
+ last = rq;
+ }
+ if (last) {
+ if (count > MAX_REQUESTS_TO_SHOW) {
+ drm_printf(m,
+ "\t\t...skipping %d executing requests...\n",
+ count - MAX_REQUESTS_TO_SHOW);
+ }
+ print_request(m, last, "\t\tE ");
+ }
+
+ last = NULL;
+ count = 0;
drm_printf(m, "\t\tQueue priority: %d\n", execlists->queue_priority);
for (rb = execlists->first; rb; rb = rb_next(rb)) {
struct i915_priolist *p =
rb_entry(rb, typeof(*p), node);
- list_for_each_entry(rq, &p->requests, sched.link)
- print_request(m, rq, "\t\tQ ");
+ list_for_each_entry(rq, &p->requests, sched.link) {
+ if (count++ < MAX_REQUESTS_TO_SHOW - 1)
+ print_request(m, rq, "\t\tQ ");
+ else
+ last = rq;
+ }
+ }
+ if (last) {
+ if (count > MAX_REQUESTS_TO_SHOW) {
+ drm_printf(m,
+ "\t\t...skipping %d queued requests...\n",
+ count - MAX_REQUESTS_TO_SHOW);
+ }
+ print_request(m, last, "\t\tQ ");
}
+
spin_unlock_irq(&engine->timeline->lock);
spin_lock_irq(&b->rb_lock);