drm/i915: proper use of forcewake

Moved the macros around to properly do reads and writes for the given
GPU. This is to address special requirements for gen6 (SNB) reads and
writes.

Registers in the range 0-0x40000 on gen6 platforms require special
handling. Instead of relying on the callers to pick the registers
correctly, move the logic into the read and write functions.

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

2 files changed, 37 insertions, 46 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 4b862f366904..083644ef8f31 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1325,10 +1325,30 @@ extern void intel_display_print_error_state(struct seq_file *m,
                 LOCK_TEST_WITH_RETURN(dev, file);                       \
 } while (0)
 
+/* On SNB platform, before reading ring registers forcewake bit
+ * must be set to prevent GT core from power down and stale values being
+ * returned.
+ */
+void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv);
+void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv);
+void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv);
+
+/* We give fast paths for the really cool registers */
+#define NEEDS_FORCE_WAKE(dev_priv, reg) \
+        (((dev_priv)->info->gen >= 6) && \
+        ((reg) < 0x40000) && \
+        ((reg) != FORCEWAKE))
 
 #define __i915_read(x, y) \
 static inline u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg) { \
-        u##x val = read##y(dev_priv->regs + reg); \
+        u##x val = 0; \
+        if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
+                __gen6_gt_force_wake_get(dev_priv); \
+                val = read##y(dev_priv->regs + reg); \
+                __gen6_gt_force_wake_put(dev_priv); \
+        } else { \
+                val = read##y(dev_priv->regs + reg); \
+        } \
         trace_i915_reg_rw(false, reg, val, sizeof(val)); \
         return val; \
 }
@@ -1341,6 +1361,9 @@ __i915_read(64, q)
 #define __i915_write(x, y) \
 static inline void i915_write##x(struct drm_i915_private *dev_priv, u32 reg, u##x val) { \
         trace_i915_reg_rw(true, reg, val, sizeof(val)); \
+        if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
+                __gen6_gt_wait_for_fifo(dev_priv); \
+        } \
         write##y(val, dev_priv->regs + reg); \
 }
 __i915_write(8, b)
@@ -1369,33 +1392,4 @@ __i915_write(64, q)
 #define POSTING_READ16(reg)     (void)I915_READ16_NOTRACE(reg)
 
 
-/* On SNB platform, before reading ring registers forcewake bit
- * must be set to prevent GT core from power down and stale values being
- * returned.
- */
-void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv);
-void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv);
-void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv);
-
-static inline u32 i915_gt_read(struct drm_i915_private *dev_priv, u32 reg)
-{
-        u32 val;
-
-        if (dev_priv->info->gen >= 6) {
-                __gen6_gt_force_wake_get(dev_priv);
-                val = I915_READ(reg);
-                __gen6_gt_force_wake_put(dev_priv);
-        } else
-                val = I915_READ(reg);
-
-        return val;
-}
-
-static inline void i915_gt_write(struct drm_i915_private *dev_priv,
-                                u32 reg, u32 val)
-{
-        if (dev_priv->info->gen >= 6)
-                __gen6_gt_wait_for_fifo(dev_priv);
-        I915_WRITE(reg, val);
-}
 #endif
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 16cb125eb117..c0e0ee63fbf4 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -14,27 +14,24 @@ struct  intel_hw_status_page {
         struct          drm_i915_gem_object *obj;
 };
 
-#define I915_RING_READ(reg) i915_gt_read(dev_priv, reg)
-#define I915_RING_WRITE(reg, val) i915_gt_write(dev_priv, reg, val)
+#define I915_READ_TAIL(ring) I915_READ(RING_TAIL((ring)->mmio_base))
+#define I915_WRITE_TAIL(ring, val) I915_WRITE(RING_TAIL((ring)->mmio_base), val)
 
-#define I915_READ_TAIL(ring) I915_RING_READ(RING_TAIL((ring)->mmio_base))
-#define I915_WRITE_TAIL(ring, val) I915_RING_WRITE(RING_TAIL((ring)->mmio_base), val)
+#define I915_READ_START(ring) I915_READ(RING_START((ring)->mmio_base))
+#define I915_WRITE_START(ring, val) I915_WRITE(RING_START((ring)->mmio_base), val)
 
-#define I915_READ_START(ring) I915_RING_READ(RING_START((ring)->mmio_base))
-#define I915_WRITE_START(ring, val) I915_RING_WRITE(RING_START((ring)->mmio_base), val)
+#define I915_READ_HEAD(ring)  I915_READ(RING_HEAD((ring)->mmio_base))
+#define I915_WRITE_HEAD(ring, val) I915_WRITE(RING_HEAD((ring)->mmio_base), val)
 
-#define I915_READ_HEAD(ring)  I915_RING_READ(RING_HEAD((ring)->mmio_base))
-#define I915_WRITE_HEAD(ring, val) I915_RING_WRITE(RING_HEAD((ring)->mmio_base), val)
+#define I915_READ_CTL(ring) I915_READ(RING_CTL((ring)->mmio_base))
+#define I915_WRITE_CTL(ring, val) I915_WRITE(RING_CTL((ring)->mmio_base), val)
 
-#define I915_READ_CTL(ring) I915_RING_READ(RING_CTL((ring)->mmio_base))
-#define I915_WRITE_CTL(ring, val) I915_RING_WRITE(RING_CTL((ring)->mmio_base), val)
+#define I915_READ_IMR(ring) I915_READ(RING_IMR((ring)->mmio_base))
+#define I915_WRITE_IMR(ring, val) I915_WRITE(RING_IMR((ring)->mmio_base), val)
 
-#define I915_READ_IMR(ring) I915_RING_READ(RING_IMR((ring)->mmio_base))
-#define I915_WRITE_IMR(ring, val) I915_RING_WRITE(RING_IMR((ring)->mmio_base), val)
-
-#define I915_READ_NOPID(ring) I915_RING_READ(RING_NOPID((ring)->mmio_base))
-#define I915_READ_SYNC_0(ring) I915_RING_READ(RING_SYNC_0((ring)->mmio_base))
-#define I915_READ_SYNC_1(ring) I915_RING_READ(RING_SYNC_1((ring)->mmio_base))
+#define I915_READ_NOPID(ring) I915_READ(RING_NOPID((ring)->mmio_base))
+#define I915_READ_SYNC_0(ring) I915_READ(RING_SYNC_0((ring)->mmio_base))
+#define I915_READ_SYNC_1(ring) I915_READ(RING_SYNC_1((ring)->mmio_base))
 
 struct  intel_ring_buffer {
         const char      *name;