Merge tag 'drm-intel-fixes-2014-09-10' of git://anongit.freedesktop.org/drm-intel into drm-fixes

more fixes for 3.17, almost all Cc: stable material.

* tag 'drm-intel-fixes-2014-09-10' of git://anongit.freedesktop.org/drm-intel:
  drm/i915: Wait for vblank before enabling the TV encoder
  drm/i915: Evict CS TLBs between batches
  drm/i915: Fix irq enable tracking in driver load
  drm/i915: Fix EIO/wedged handling in gem fault handler
  drm/i915: Prevent recursive deadlock on releasing a busy userptr

drivers/gpu/drm/i915/i915_dma.c

@@ -1336,12 +1336,17 @@ static int i915_load_modeset_init(struct drm_device *dev)
 
 	intel_power_domains_init_hw(dev_priv);
 
+	/*
+	 * We enable some interrupt sources in our postinstall hooks, so mark
+	 * interrupts as enabled _before_ actually enabling them to avoid
+	 * special cases in our ordering checks.
+	 */
+	dev_priv->pm._irqs_disabled = false;
+
 	ret = drm_irq_install(dev, dev->pdev->irq);
 	if (ret)
 		goto cleanup_gem_stolen;
 
-	dev_priv->pm._irqs_disabled = false;
-
 	/* Important: The output setup functions called by modeset_init need
 	 * working irqs for e.g. gmbus and dp aux transfers. */
 	intel_modeset_init(dev);

drivers/gpu/drm/i915/i915_drv.h

@@ -184,6 +184,7 @@ enum hpd_pin {
 		if ((1 << (domain)) & (mask))
 
 struct drm_i915_private;
+struct i915_mm_struct;
 struct i915_mmu_object;
 
 enum intel_dpll_id {
@@ -1506,9 +1507,8 @@ struct drm_i915_private {
 	struct i915_gtt gtt; /* VM representing the global address space */
 
 	struct i915_gem_mm mm;
-#if defined(CONFIG_MMU_NOTIFIER)
-	DECLARE_HASHTABLE(mmu_notifiers, 7);
-#endif
+	DECLARE_HASHTABLE(mm_structs, 7);
+	struct mutex mm_lock;
 
 	/* Kernel Modesetting */
 
@@ -1814,8 +1814,8 @@ struct drm_i915_gem_object {
 			unsigned workers :4;
 #define I915_GEM_USERPTR_MAX_WORKERS 15
 
-			struct mm_struct *mm;
-			struct i915_mmu_object *mn;
+			struct i915_mm_struct *mm;
+			struct i915_mmu_object *mmu_object;
 			struct work_struct *work;
 		} userptr;
 	};

drivers/gpu/drm/i915/i915_gem.c

@@ -1590,10 +1590,13 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 out:
 	switch (ret) {
 	case -EIO:
-		/* If this -EIO is due to a gpu hang, give the reset code a
-		 * chance to clean up the mess. Otherwise return the proper
-		 * SIGBUS. */
-		if (i915_terminally_wedged(&dev_priv->gpu_error)) {
+		/*
+		 * We eat errors when the gpu is terminally wedged to avoid
+		 * userspace unduly crashing (gl has no provisions for mmaps to
+		 * fail). But any other -EIO isn't ours (e.g. swap in failure)
+		 * and so needs to be reported.
+		 */
+		if (!i915_terminally_wedged(&dev_priv->gpu_error)) {
 			ret = VM_FAULT_SIGBUS;
 			break;
 		}

drivers/gpu/drm/i915/i915_reg.h

@@ -334,16 +334,20 @@
 #define GFX_OP_DESTBUFFER_INFO	 ((0x3<<29)|(0x1d<<24)|(0x8e<<16)|1)
 #define GFX_OP_DRAWRECT_INFO     ((0x3<<29)|(0x1d<<24)|(0x80<<16)|(0x3))
 #define GFX_OP_DRAWRECT_INFO_I965  ((0x7900<<16)|0x2)
+
+#define COLOR_BLT_CMD			(2<<29 | 0x40<<22 | (5-2))
 #define SRC_COPY_BLT_CMD		((2<<29)|(0x43<<22)|4)
 #define XY_SRC_COPY_BLT_CMD		((2<<29)|(0x53<<22)|6)
 #define XY_MONO_SRC_COPY_IMM_BLT	((2<<29)|(0x71<<22)|5)
-#define XY_SRC_COPY_BLT_WRITE_ALPHA	(1<<21)
-#define XY_SRC_COPY_BLT_WRITE_RGB	(1<<20)
+#define   BLT_WRITE_A			(2<<20)
+#define   BLT_WRITE_RGB			(1<<20)
+#define   BLT_WRITE_RGBA		(BLT_WRITE_RGB | BLT_WRITE_A)
 #define   BLT_DEPTH_8			(0<<24)
 #define   BLT_DEPTH_16_565		(1<<24)
 #define   BLT_DEPTH_16_1555		(2<<24)
 #define   BLT_DEPTH_32			(3<<24)
-#define   BLT_ROP_GXCOPY		(0xcc<<16)
+#define   BLT_ROP_SRC_COPY		(0xcc<<16)
+#define   BLT_ROP_COLOR_COPY		(0xf0<<16)
 #define XY_SRC_COPY_BLT_SRC_TILED	(1<<15) /* 965+ only */
 #define XY_SRC_COPY_BLT_DST_TILED	(1<<11) /* 965+ only */
 #define CMD_OP_DISPLAYBUFFER_INFO ((0x0<<29)|(0x14<<23)|2)

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -1363,53 +1363,65 @@ i965_dispatch_execbuffer(struct intel_engine_cs *ring,
 
 /* Just userspace ABI convention to limit the wa batch bo to a resonable size */
 #define I830_BATCH_LIMIT (256*1024)
+#define I830_TLB_ENTRIES (2)
+#define I830_WA_SIZE max(I830_TLB_ENTRIES*4096, I830_BATCH_LIMIT)
 static int
 i830_dispatch_execbuffer(struct intel_engine_cs *ring,
 				u64 offset, u32 len,
 				unsigned flags)
 {
+	u32 cs_offset = ring->scratch.gtt_offset;
 	int ret;
 
-	if (flags & I915_DISPATCH_PINNED) {
-		ret = intel_ring_begin(ring, 4);
+	ret = intel_ring_begin(ring, 6);
 	if (ret)
 		return ret;
 
-		intel_ring_emit(ring, MI_BATCH_BUFFER);
-		intel_ring_emit(ring, offset | (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE));
-		intel_ring_emit(ring, offset + len - 8);
+	/* Evict the invalid PTE TLBs */
+	intel_ring_emit(ring, COLOR_BLT_CMD | BLT_WRITE_RGBA);
+	intel_ring_emit(ring, BLT_DEPTH_32 | BLT_ROP_COLOR_COPY | 4096);
+	intel_ring_emit(ring, I830_TLB_ENTRIES << 16 | 4); /* load each page */
+	intel_ring_emit(ring, cs_offset);
+	intel_ring_emit(ring, 0xdeadbeef);
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_advance(ring);
-	} else {
-		u32 cs_offset = ring->scratch.gtt_offset;
 
+	if ((flags & I915_DISPATCH_PINNED) == 0) {
 		if (len > I830_BATCH_LIMIT)
 			return -ENOSPC;
 
-		ret = intel_ring_begin(ring, 9+3);
+		ret = intel_ring_begin(ring, 6 + 2);
 		if (ret)
 			return ret;
-		/* Blit the batch (which has now all relocs applied) to the stable batch
-		 * scratch bo area (so that the CS never stumbles over its tlb
-		 * invalidation bug) ... */
-		intel_ring_emit(ring, XY_SRC_COPY_BLT_CMD |
-				XY_SRC_COPY_BLT_WRITE_ALPHA |
-				XY_SRC_COPY_BLT_WRITE_RGB);
-		intel_ring_emit(ring, BLT_DEPTH_32 | BLT_ROP_GXCOPY | 4096);
-		intel_ring_emit(ring, 0);
-		intel_ring_emit(ring, (DIV_ROUND_UP(len, 4096) << 16) | 1024);
+
+		/* Blit the batch (which has now all relocs applied) to the
+		 * stable batch scratch bo area (so that the CS never
+		 * stumbles over its tlb invalidation bug) ...
+		 */
+		intel_ring_emit(ring, SRC_COPY_BLT_CMD | BLT_WRITE_RGBA);
+		intel_ring_emit(ring, BLT_DEPTH_32 | BLT_ROP_SRC_COPY | 4096);
+		intel_ring_emit(ring, DIV_ROUND_UP(len, 4096) << 16 | 1024);
 		intel_ring_emit(ring, cs_offset);
-		intel_ring_emit(ring, 0);
 		intel_ring_emit(ring, 4096);
 		intel_ring_emit(ring, offset);
+
 		intel_ring_emit(ring, MI_FLUSH);
+		intel_ring_emit(ring, MI_NOOP);
+		intel_ring_advance(ring);
 
 		/* ... and execute it. */
+		offset = cs_offset;
+	}
+
+	ret = intel_ring_begin(ring, 4);
+	if (ret)
+		return ret;
+
 	intel_ring_emit(ring, MI_BATCH_BUFFER);
-		intel_ring_emit(ring, cs_offset | (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE));
-		intel_ring_emit(ring, cs_offset + len - 8);
+	intel_ring_emit(ring, offset | (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE));
+	intel_ring_emit(ring, offset + len - 8);
+	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_advance(ring);
-	}
 
 	return 0;
 }
@@ -2200,7 +2212,7 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 
 	/* Workaround batchbuffer to combat CS tlb bug. */
 	if (HAS_BROKEN_CS_TLB(dev)) {
-		obj = i915_gem_alloc_object(dev, I830_BATCH_LIMIT);
+		obj = i915_gem_alloc_object(dev, I830_WA_SIZE);
 		if (obj == NULL) {
 			DRM_ERROR("Failed to allocate batch bo\n");
 			return -ENOMEM;

drivers/gpu/drm/i915/intel_tv.c

@@ -854,6 +854,10 @@ intel_enable_tv(struct intel_encoder *encoder)
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	/* Prevents vblank waits from timing out in intel_tv_detect_type() */
+	intel_wait_for_vblank(encoder->base.dev,
+			      to_intel_crtc(encoder->base.crtc)->pipe);
+
 	I915_WRITE(TV_CTL, I915_READ(TV_CTL) | TV_ENC_ENABLE);
 }