drm/i915/gt: Wait for CSB entries on Tigerlake
On Tigerlake, we are seeing a repeat of commitd8f5053117
("drm/i915/icl: Forcibly evict stale csb entries") where, presumably, due to a missing Global Observation Point synchronisation, the write pointer of the CSB ringbuffer is updated _prior_ to the contents of the ringbuffer. That is we see the GPU report more context-switch entries for us to parse, but those entries have not been written, leading us to process stale events, and eventually report a hung GPU. However, this effect appears to be much more severe than we previously saw on Icelake (though it might be best if we try the same approach there as well and measure), and Bruce suggested the good idea of resetting the CSB entry after use so that we can detect when it has been updated by the GPU. By instrumenting how long that may be, we can set a reliable upper bound for how long we should wait for: 513 late, avg of 61 retries (590 ns), max of 1061 retries (10099 ns) Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2045 References:d8f5053117
("drm/i915/icl: Forcibly evict stale csb entries") References: HSDES#22011327657, HSDES#1508287568 Suggested-by: Bruce Chang <yu.bruce.chang@intel.com> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Bruce Chang <yu.bruce.chang@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Cc: stable@vger.kernel.org # v5.4 Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200915134923.30088-2-chris@chris-wilson.co.uk
This commit is contained in:
Родитель
f24a44e52f
Коммит
233c1ae3c8
|
@ -2498,9 +2498,22 @@ invalidate_csb_entries(const u64 *first, const u64 *last)
|
|||
*/
|
||||
static inline bool gen12_csb_parse(const u64 *csb)
|
||||
{
|
||||
u64 entry = READ_ONCE(*csb);
|
||||
bool ctx_away_valid = GEN12_CSB_CTX_VALID(upper_32_bits(entry));
|
||||
bool new_queue =
|
||||
bool ctx_away_valid;
|
||||
bool new_queue;
|
||||
u64 entry;
|
||||
|
||||
/* HSD#22011248461 */
|
||||
entry = READ_ONCE(*csb);
|
||||
if (unlikely(entry == -1)) {
|
||||
preempt_disable();
|
||||
if (wait_for_atomic_us((entry = READ_ONCE(*csb)) != -1, 50))
|
||||
GEM_WARN_ON("50us CSB timeout");
|
||||
preempt_enable();
|
||||
}
|
||||
WRITE_ONCE(*(u64 *)csb, -1);
|
||||
|
||||
ctx_away_valid = GEN12_CSB_CTX_VALID(upper_32_bits(entry));
|
||||
new_queue =
|
||||
lower_32_bits(entry) & GEN12_CTX_STATUS_SWITCHED_TO_NEW_QUEUE;
|
||||
|
||||
/*
|
||||
|
@ -4004,6 +4017,8 @@ static void reset_csb_pointers(struct intel_engine_cs *engine)
|
|||
WRITE_ONCE(*execlists->csb_write, reset_value);
|
||||
wmb(); /* Make sure this is visible to HW (paranoia?) */
|
||||
|
||||
/* Check that the GPU does indeed update the CSB entries! */
|
||||
memset(execlists->csb_status, -1, (reset_value + 1) * sizeof(u64));
|
||||
invalidate_csb_entries(&execlists->csb_status[0],
|
||||
&execlists->csb_status[reset_value]);
|
||||
|
||||
|
|
Загрузка…
Ссылка в новой задаче