[Intel-gfx] [PATCH] drm/i915: Disable atomics in L3 for gen9

[Chris Wilson]

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 <jason at jlekstrand.net>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=110998
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Jason Ekstrand <jason at jlekstrand.net>
Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin at 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).
---
 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)
-- 
2.22.0