i965: Introduce an OUT_RELOC64 macro.

Broadwell uses 48-bit addresses.  The first DWord is the low 32 bits,
and the second DWord is the high 16 bits.

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>

diff --git a/src/mesa/drivers/dri/i965/intel_batchbuffer.c b/src/mesa/drivers/dri/i965/intel_batchbuffer.c
index c420ab9..59d03f6 100644 (file)
--- a/src/mesa/drivers/dri/i965/intel_batchbuffer.c
+++ b/src/mesa/drivers/dri/i965/intel_batchbuffer.c
@@ -397,6 +397,30 @@ intel_batchbuffer_emit_reloc(struct brw_context *brw,
    return true;
 }
 
+bool
+intel_batchbuffer_emit_reloc64(struct brw_context *brw,
+                               drm_intel_bo *buffer,
+                               uint32_t read_domains, uint32_t write_domain,
+                              uint32_t delta)
+{
+   int ret = drm_intel_bo_emit_reloc(brw->batch.bo, 4*brw->batch.used,
+                                     buffer, delta,
+                                     read_domains, write_domain);
+   assert(ret == 0);
+   (void) ret;
+
+   /* Using the old buffer offset, write in what the right data would be, in
+    * case the buffer doesn't move and we can short-circuit the relocation
+    * processing in the kernel
+    */
+   uint64_t offset = buffer->offset64 + delta;
+   intel_batchbuffer_emit_dword(brw, offset);
+   intel_batchbuffer_emit_dword(brw, offset >> 32);
+
+   return true;
+}
+
+
 void
 intel_batchbuffer_data(struct brw_context *brw,
                        const void *data, GLuint bytes, enum brw_gpu_ring ring)

diff --git a/src/mesa/drivers/dri/i965/intel_batchbuffer.h b/src/mesa/drivers/dri/i965/intel_batchbuffer.h
index eff03b3..2b2693f 100644 (file)
--- a/src/mesa/drivers/dri/i965/intel_batchbuffer.h
+++ b/src/mesa/drivers/dri/i965/intel_batchbuffer.h
@@ -59,6 +59,11 @@ bool intel_batchbuffer_emit_reloc(struct brw_context *brw,
                                       uint32_t read_domains,
                                       uint32_t write_domain,
                                       uint32_t offset);
+bool intel_batchbuffer_emit_reloc64(struct brw_context *brw,
+                                    drm_intel_bo *buffer,
+                                    uint32_t read_domains,
+                                    uint32_t write_domain,
+                                    uint32_t offset);
 void intel_batchbuffer_emit_mi_flush(struct brw_context *brw);
 void intel_emit_post_sync_nonzero_flush(struct brw_context *brw);
 void intel_emit_depth_stall_flushes(struct brw_context *brw);
@@ -167,6 +172,11 @@ intel_batchbuffer_advance(struct brw_context *brw)
                                read_domains, write_domain, delta);     \
 } while (0)
 
+/* Handle 48-bit address relocations for Gen8+ */
+#define OUT_RELOC64(buf, read_domains, write_domain, delta) do { \
+   intel_batchbuffer_emit_reloc64(brw, buf, read_domains, write_domain, delta);        \
+} while (0)
+
 #define ADVANCE_BATCH() intel_batchbuffer_advance(brw);
 
 #ifdef __cplusplus