On 20/07/2019 15:31, Chris Wilson wrote:
Enabling atomic operations in L3 leads to unrecoverable GPU hangs, as
the machine stops responding milliseconds after receipt of the reset
request [GDRT]. By disabling the cached atomics, the hang do not occur
and we presume the GPU would reset normally for similar hangs.

Reported-by: Jason Ekstrand <ja...@jlekstrand.net>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=110998
Signed-off-by: Chris Wilson <ch...@chris-wilson.co.uk>
Cc: Jason Ekstrand <ja...@jlekstrand.net>
Cc: Mika Kuoppala <mika.kuopp...@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursu...@linux.intel.com>
---
Jason reports that Windows is not clearing L3SQCREG4:22 and does not
suffer the same GPU hang so it is likely some other w/a that interacts
badly. Fwiw, these 3 are the only registers I could find that mention
atomic ops (and appear to be part of the same chain for memory access).

Bit-toggling itself looks fine to me and matches what I could find in the docs. (All three bits across three registers should be equal.)

What I am curious about is what are the other consequences of disabling L3 atomics? Performance drop somewhere?

Regards,

Tvrtko


---
  drivers/gpu/drm/i915/gt/intel_workarounds.c | 8 ++++++++
  drivers/gpu/drm/i915/i915_reg.h             | 7 +++++++
  2 files changed, 15 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c 
b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 704ace01e7f5..ac94ed3ba7b6 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -1349,6 +1349,14 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, 
struct i915_wa_list *wal)
                wa_write_or(wal,
                            GEN8_L3SQCREG4,
                            GEN8_LQSC_FLUSH_COHERENT_LINES);
+
+               /* Disable atomics in L3 to prevent unrecoverable hangs */
+               wa_write_masked_or(wal, GEN9_SCRATCH_LNCF1,
+                                  GEN9_LNCF_NONIA_COHERENT_ATOMICS_ENABLE, 0);
+               wa_write_masked_or(wal, GEN8_L3SQCREG4,
+                                  GEN8_LQSQ_NONIA_COHERENT_ATOMICS_ENABLE, 0);
+               wa_write_masked_or(wal, GEN9_SCRATCH1,
+                                  EVICTION_PERF_FIX_ENABLE, 0);
        }
  }
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 24f2a52a2b42..e23b2200e7fc 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7728,6 +7728,7 @@ enum {
  #define  GEN11_LQSC_CLEAN_EVICT_DISABLE               (1 << 6)
  #define  GEN8_LQSC_RO_PERF_DIS                        (1 << 27)
  #define  GEN8_LQSC_FLUSH_COHERENT_LINES               (1 << 21)
+#define  GEN8_LQSQ_NONIA_COHERENT_ATOMICS_ENABLE REG_BIT(22)
/* GEN8 chicken */
  #define HDC_CHICKEN0                          _MMIO(0x7300)
@@ -11202,6 +11203,12 @@ enum skl_power_gate {
  /* Media decoder 2 MOCS registers */
  #define GEN11_MFX2_MOCS(i)    _MMIO(0x10000 + (i) * 4)
+#define GEN9_SCRATCH_LNCF1 _MMIO(0xb008)
+#define   GEN9_LNCF_NONIA_COHERENT_ATOMICS_ENABLE REG_BIT(0)
+
+#define GEN9_SCRATCH1                  _MMIO(0xb11c)
+#define   EVICTION_PERF_FIX_ENABLE     REG_BIT(8)
+
  #define GEN10_SCRATCH_LNCF2           _MMIO(0xb0a0)
  #define   PMFLUSHDONE_LNICRSDROP      (1 << 20)
  #define   PMFLUSH_GAPL3UNBLOCK                (1 << 21)

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Reply via email to