Merge branch 'drm-intel-fixes' into drm-intel-next

Apply the trivial conflicting regression fixes, but keep GPU semaphores
enabled.

Conflicts:
	drivers/gpu/drm/i915/i915_drv.h
	drivers/gpu/drm/i915/i915_gem_execbuffer.c

9 files changed, 70 insertions, 40 deletions

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index d659f36419af..09e0327fc6ce 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -873,7 +873,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
                 int max_freq;
 
                 /* RPSTAT1 is in the GT power well */
-                __gen6_force_wake_get(dev_priv);
+                __gen6_gt_force_wake_get(dev_priv);
 
                 rpstat = I915_READ(GEN6_RPSTAT1);
                 rpupei = I915_READ(GEN6_RP_CUR_UP_EI);
@@ -918,7 +918,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
                 seq_printf(m, "Max non-overclocked (RP0) frequency: %dMHz\n",
                            max_freq * 100);
 
-                __gen6_force_wake_put(dev_priv);
+                __gen6_gt_force_wake_put(dev_priv);
         } else {
                 seq_printf(m, "no P-state info available\n");
         }
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index bdf4ceb1049d..3dba19f28e44 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -49,6 +49,9 @@ module_param_named(panel_ignore_lid, i915_panel_ignore_lid, int, 0600);
 unsigned int i915_powersave = 1;
 module_param_named(powersave, i915_powersave, int, 0600);
 
+unsigned int i915_semaphores = 1;
+module_param_named(semaphores, i915_semaphores, int, 0600);
+
 unsigned int i915_enable_rc6 = 0;
 module_param_named(i915_enable_rc6, i915_enable_rc6, int, 0600);
 
@@ -260,7 +263,7 @@ void intel_detect_pch (struct drm_device *dev)
         }
 }
 
-void __gen6_force_wake_get(struct drm_i915_private *dev_priv)
+void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
 {
         int count;
 
@@ -276,12 +279,22 @@ void __gen6_force_wake_get(struct drm_i915_private *dev_priv)
                 udelay(10);
 }
 
-void __gen6_force_wake_put(struct drm_i915_private *dev_priv)
+void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
 {
         I915_WRITE_NOTRACE(FORCEWAKE, 0);
         POSTING_READ(FORCEWAKE);
 }
 
+void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
+{
+        int loop = 500;
+        u32 fifo = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES);
+        while (fifo < 20 && loop--) {
+                udelay(10);
+                fifo = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES);
+        }
+}
+
 static int i915_drm_freeze(struct drm_device *dev)
 {
         struct drm_i915_private *dev_priv = dev->dev_private;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 9f3650c9882a..b68abf19bce8 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -961,6 +961,7 @@ extern int i915_max_ioctl;
 extern unsigned int i915_fbpercrtc;
 extern int i915_panel_ignore_lid;
 extern unsigned int i915_powersave;
+extern unsigned int i915_semaphores;
 extern unsigned int i915_lvds_downclock;
 extern unsigned int i915_panel_use_ssc;
 extern int i915_vbt_sdvo_panel_type;
@@ -1172,6 +1173,9 @@ void i915_gem_detach_phys_object(struct drm_device *dev,
 void i915_gem_free_all_phys_object(struct drm_device *dev);
 void i915_gem_release(struct drm_device *dev, struct drm_file *file);
 
+uint32_t
+i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj);
+
 /* i915_gem_gtt.c */
 void i915_gem_restore_gtt_mappings(struct drm_device *dev);
 int __must_check i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj);
@@ -1348,20 +1352,29 @@ __i915_write(64, q)
  * must be set to prevent GT core from power down and stale values being
  * returned.
  */
-void __gen6_force_wake_get(struct drm_i915_private *dev_priv);
-void __gen6_force_wake_put (struct drm_i915_private *dev_priv);
-static inline u32 i915_safe_read(struct drm_i915_private *dev_priv, u32 reg)
+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_force_wake_get(dev_priv);
+                __gen6_gt_force_wake_get(dev_priv);
                 val = I915_READ(reg);
-                __gen6_force_wake_put(dev_priv);
+                __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/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index ac23dcf084be..950a5ab921ad 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1404,7 +1404,7 @@ i915_gem_get_gtt_alignment(struct drm_i915_gem_object *obj)
  * Return the required GTT alignment for an object, only taking into account
  * unfenced tiled surface requirements.
  */
-static uint32_t
+uint32_t
 i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj)
 {
         struct drm_device *dev = obj->base.dev;
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 8513c04dc892..7ff7f933ddf1 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -748,7 +748,8 @@ i915_gem_execbuffer_sync_rings(struct drm_i915_gem_object *obj,
         if (from == NULL || to == from)
                 return 0;
 
-        if (INTEL_INFO(obj->base.dev)->gen < 6)
+        /* XXX gpu semaphores are implicated in various hard hangs on SNB */
+        if (INTEL_INFO(obj->base.dev)->gen < 6 || !i915_semaphores)
                 return i915_gem_object_wait_rendering(obj);
 
         idx = intel_ring_sync_index(from, to);
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index 1f45019e6da3..281ad3d6115d 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -184,7 +184,7 @@ i915_gem_detect_bit_6_swizzle(struct drm_device *dev)
 static bool
 i915_tiling_ok(struct drm_device *dev, int stride, int size, int tiling_mode)
 {
-        int tile_width, tile_height;
+        int tile_width;
 
         /* Linear is always fine */
         if (tiling_mode == I915_TILING_NONE)
@@ -215,20 +215,6 @@ i915_tiling_ok(struct drm_device *dev, int stride, int size, int tiling_mode)
                 }
         }
 
-        if (IS_GEN2(dev) ||
-            (tiling_mode == I915_TILING_Y && HAS_128_BYTE_Y_TILING(dev)))
-                tile_height = 32;
-        else
-                tile_height = 8;
-        /* i8xx is strange: It has 2 interleaved rows of tiles, so needs an even
-         * number of tile rows. */
-        if (IS_GEN2(dev))
-                tile_height *= 2;
-
-        /* Size needs to be aligned to a full tile row */
-        if (size & (tile_height * stride - 1))
-                return false;
-
         /* 965+ just needs multiples of tile width */
         if (INTEL_INFO(dev)->gen >= 4) {
                 if (stride & (tile_width - 1))
@@ -298,6 +284,7 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
         struct drm_i915_gem_set_tiling *args = data;
         drm_i915_private_t *dev_priv = dev->dev_private;
         struct drm_i915_gem_object *obj;
+        int ret = 0;
 
         obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle));
         if (&obj->base == NULL)
@@ -358,14 +345,27 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
                         (obj->gtt_offset + obj->base.size <= dev_priv->mm.gtt_mappable_end &&
                          i915_gem_object_fence_ok(obj, args->tiling_mode));
 
-                obj->tiling_changed = true;
-                obj->tiling_mode = args->tiling_mode;
-                obj->stride = args->stride;
+                /* Rebind if we need a change of alignment */
+                if (!obj->map_and_fenceable) {
+                        u32 unfenced_alignment =
+                                i915_gem_get_unfenced_gtt_alignment(obj);
+                        if (obj->gtt_offset & (unfenced_alignment - 1))
+                                ret = i915_gem_object_unbind(obj);
+                }
+
+                if (ret == 0) {
+                        obj->tiling_changed = true;
+                        obj->tiling_mode = args->tiling_mode;
+                        obj->stride = args->stride;
+                }
         }
+        /* we have to maintain this existing ABI... */
+        args->stride = obj->stride;
+        args->tiling_mode = obj->tiling_mode;
         drm_gem_object_unreference(&obj->base);
         mutex_unlock(&dev->struct_mutex);
 
-        return 0;
+        return ret;
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 368819a23f73..363f66ca5d33 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3318,6 +3318,8 @@
 #define  FORCEWAKE                              0xA18C
 #define  FORCEWAKE_ACK                          0x130090
 
+#define  GT_FIFO_FREE_ENTRIES                   0x120008
+
 #define GEN6_RPNSWREQ                           0xA008
 #define   GEN6_TURBO_DISABLE                    (1<<31)
 #define   GEN6_FREQUENCY(x)                     ((x)<<25)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 4a392b4a5ae9..3106c0dc8389 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1825,7 +1825,7 @@ static void sandybridge_blit_fbc_update(struct drm_device *dev)
         u32 blt_ecoskpd;
 
         /* Make sure blitter notifies FBC of writes */
-        __gen6_force_wake_get(dev_priv);
+        __gen6_gt_force_wake_get(dev_priv);
         blt_ecoskpd = I915_READ(GEN6_BLITTER_ECOSKPD);
         blt_ecoskpd |= GEN6_BLITTER_FBC_NOTIFY <<
                 GEN6_BLITTER_LOCK_SHIFT;
@@ -1836,7 +1836,7 @@ static void sandybridge_blit_fbc_update(struct drm_device *dev)
                          GEN6_BLITTER_LOCK_SHIFT);
         I915_WRITE(GEN6_BLITTER_ECOSKPD, blt_ecoskpd);
         POSTING_READ(GEN6_BLITTER_ECOSKPD);
-        __gen6_force_wake_put(dev_priv);
+        __gen6_gt_force_wake_put(dev_priv);
 }
 
 static void ironlake_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
@@ -6856,7 +6856,7 @@ void gen6_enable_rps(struct drm_i915_private *dev_priv)
          * userspace...
          */
         I915_WRITE(GEN6_RC_STATE, 0);
-        __gen6_force_wake_get(dev_priv);
+        __gen6_gt_force_wake_get(dev_priv);
 
         /* disable the counters and set deterministic thresholds */
         I915_WRITE(GEN6_RC_CONTROL, 0);
@@ -6954,7 +6954,7 @@ void gen6_enable_rps(struct drm_i915_private *dev_priv)
         /* enable all PM interrupts */
         I915_WRITE(GEN6_PMINTRMSK, 0);
 
-        __gen6_force_wake_put(dev_priv);
+        __gen6_gt_force_wake_put(dev_priv);
 }
 
 void intel_enable_clock_gating(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index bd6a5fbfa929..f23cc5f037a6 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -14,22 +14,23 @@ struct  intel_hw_status_page {
         struct          drm_i915_gem_object *obj;
 };
 
-#define I915_RING_READ(reg) i915_safe_read(dev_priv, reg)
+#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_RING_READ(RING_TAIL((ring)->mmio_base))
-#define I915_WRITE_TAIL(ring, val) I915_WRITE(RING_TAIL((ring)->mmio_base), val)
+#define I915_WRITE_TAIL(ring, val) I915_RING_WRITE(RING_TAIL((ring)->mmio_base), val)
 
 #define I915_READ_START(ring) I915_RING_READ(RING_START((ring)->mmio_base))
-#define I915_WRITE_START(ring, val) I915_WRITE(RING_START((ring)->mmio_base), val)
+#define I915_WRITE_START(ring, val) I915_RING_WRITE(RING_START((ring)->mmio_base), val)
 
 #define I915_READ_HEAD(ring)  I915_RING_READ(RING_HEAD((ring)->mmio_base))
-#define I915_WRITE_HEAD(ring, val) I915_WRITE(RING_HEAD((ring)->mmio_base), val)
+#define I915_WRITE_HEAD(ring, val) I915_RING_WRITE(RING_HEAD((ring)->mmio_base), val)
 
 #define I915_READ_CTL(ring) I915_RING_READ(RING_CTL((ring)->mmio_base))
-#define I915_WRITE_CTL(ring, val) I915_WRITE(RING_CTL((ring)->mmio_base), val)
+#define I915_WRITE_CTL(ring, val) I915_RING_WRITE(RING_CTL((ring)->mmio_base), val)
 
-#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))