drm/i915/gt: Use a mmio read of the CSB in case of failure

If we find the GPU didn't update the CSB within 50us, we currently fail
and eventually reset the GPU. Lets report the value from the mmio space
as a last resort, it may just stave off an unnecessary GPU reset.

References: HSDES#22011327657
Suggested-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200915134923.30088-4-chris@chris-wilson.co.uk

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index fcb6ec3..0d57b54 100644 (file)
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2528,19 +2528,42 @@ static inline bool gen8_csb_parse(const u64 csb)
        return csb & (GEN8_CTX_STATUS_IDLE_ACTIVE | GEN8_CTX_STATUS_PREEMPTED);
 }
 
-static noinline u64 wa_csb_read(u64 * const csb)
+static noinline u64
+wa_csb_read(const struct intel_engine_cs *engine, u64 * const csb)
 {
        u64 entry;
 
+       /*
+        * Reading from the HWSP has one particular advantage: we can detect
+        * a stale entry. Since the write into HWSP is broken, we have no reason
+        * to trust the HW at all, the mmio entry may equally be unordered, so
+        * we prefer the path that is self-checking and as a last resort,
+        * return the mmio value.
+        *
+        * tgl,dg1:HSDES#22011327657
+        */
        preempt_disable();
-       if (wait_for_atomic_us((entry = READ_ONCE(*csb)) != -1, 50))
-               GEM_WARN_ON("50us CSB timeout");
+       if (wait_for_atomic_us((entry = READ_ONCE(*csb)) != -1, 10)) {
+               int idx = csb - engine->execlists.csb_status;
+               int status;
+
+               status = GEN8_EXECLISTS_STATUS_BUF;
+               if (idx >= 6) {
+                       status = GEN11_EXECLISTS_STATUS_BUF2;
+                       idx -= 6;
+               }
+               status += sizeof(u64) * idx;
+
+               entry = intel_uncore_read64(engine->uncore,
+                                           _MMIO(engine->mmio_base + status));
+       }
        preempt_enable();
 
        return entry;
 }
 
-static inline u64 csb_read(u64 * const csb)
+static inline u64
+csb_read(const struct intel_engine_cs *engine, u64 * const csb)
 {
        u64 entry = READ_ONCE(*csb);
 
@@ -2556,7 +2579,7 @@ static inline u64 csb_read(u64 * const csb)
         * tgl:HSDES#22011248461
         */
        if (unlikely(entry == -1))
-               entry = wa_csb_read(csb);
+               entry = wa_csb_read(engine, csb);
 
        /* Consume this entry so that we can spot its future reuse. */
        WRITE_ONCE(*csb, -1);
@@ -2649,7 +2672,7 @@ static void process_csb(struct intel_engine_cs *engine)
                 * status notifier.
                 */
 
-               csb = csb_read(buf + head);
+               csb = csb_read(engine, buf + head);
                ENGINE_TRACE(engine, "csb[%d]: status=0x%08x:0x%08x\n",
                             head, upper_32_bits(csb), lower_32_bits(csb));
 

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
index 93cb6c4..1b51f7b 100644 (file)
--- a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
@@ -49,4 +49,7 @@
 #define GEN11_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT      0x1A
 #define GEN12_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT      0xD
 
+#define GEN8_EXECLISTS_STATUS_BUF 0x370
+#define GEN11_EXECLISTS_STATUS_BUF2 0x3c0
+
 #endif /* _INTEL_LRC_REG_H_ */