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

8 files changed, 53 insertions, 21 deletions

diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 3dadfa2a8528..28d1d3c24d65 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -164,8 +164,10 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc)
          * available. In that case we can't account for this and just
          * hope for the best.
          */
-        if ((vblrc > 0) && (abs(diff_ns) > 1000000))
+        if ((vblrc > 0) && (abs64(diff_ns) > 1000000)) {
                 atomic_inc(&dev->_vblank_count[crtc]);
+                smp_mb__after_atomic_inc();
+        }
 
         /* Invalidate all timestamps while vblank irq's are off. */
         clear_vblank_timestamps(dev, crtc);
@@ -491,6 +493,12 @@ void drm_calc_timestamping_constants(struct drm_crtc *crtc)
         /* Dot clock in Hz: */
         dotclock = (u64) crtc->hwmode.clock * 1000;
 
+        /* Fields of interlaced scanout modes are only halve a frame duration.
+         * Double the dotclock to get halve the frame-/line-/pixelduration.
+         */
+        if (crtc->hwmode.flags & DRM_MODE_FLAG_INTERLACE)
+                dotclock *= 2;
+
         /* Valid dotclock? */
         if (dotclock > 0) {
                 /* Convert scanline length in pixels and video dot clock to
@@ -603,14 +611,6 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, int crtc,
                 return -EAGAIN;
         }
 
-        /* Don't know yet how to handle interlaced or
-         * double scan modes. Just no-op for now.
-         */
-        if (mode->flags & (DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLSCAN)) {
-                DRM_DEBUG("crtc %d: Noop due to unsupported mode.\n", crtc);
-                return -ENOTSUPP;
-        }
-
         /* Get current scanout position with system timestamp.
          * Repeat query up to DRM_TIMESTAMP_MAXRETRIES times
          * if single query takes longer than max_error nanoseconds.
@@ -858,10 +858,11 @@ static void drm_update_vblank_count(struct drm_device *dev, int crtc)
         if (rc) {
                 tslot = atomic_read(&dev->_vblank_count[crtc]) + diff;
                 vblanktimestamp(dev, crtc, tslot) = t_vblank;
-                smp_wmb();
         }
 
+        smp_mb__before_atomic_inc();
         atomic_add(diff, &dev->_vblank_count[crtc]);
+        smp_mb__after_atomic_inc();
 }
 
 /**
@@ -1011,7 +1012,8 @@ int drm_modeset_ctl(struct drm_device *dev, void *data,
                     struct drm_file *file_priv)
 {
         struct drm_modeset_ctl *modeset = data;
-        int crtc, ret = 0;
+        int ret = 0;
+        unsigned int crtc;
 
         /* If drm_vblank_init() hasn't been called yet, just no-op */
         if (!dev->num_crtcs)
@@ -1293,15 +1295,16 @@ bool drm_handle_vblank(struct drm_device *dev, int crtc)
          * e.g., due to spurious vblank interrupts. We need to
          * ignore those for accounting.
          */
-        if (abs(diff_ns) > DRM_REDUNDANT_VBLIRQ_THRESH_NS) {
+        if (abs64(diff_ns) > DRM_REDUNDANT_VBLIRQ_THRESH_NS) {
                 /* Store new timestamp in ringbuffer. */
                 vblanktimestamp(dev, crtc, vblcount + 1) = tvblank;
-                smp_wmb();
 
                 /* Increment cooked vblank count. This also atomically commits
                  * the timestamp computed above.
                  */
+                smp_mb__before_atomic_inc();
                 atomic_inc(&dev->_vblank_count[crtc]);
+                smp_mb__after_atomic_inc();
         } else {
                 DRM_DEBUG("crtc %d: Redundant vblirq ignored. diff_ns = %d\n",
                           crtc, (int) diff_ns);
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 51150692af2d..8924b4bc7369 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1900,6 +1900,17 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
         if (IS_GEN2(dev))
                 dma_set_coherent_mask(&dev->pdev->dev, DMA_BIT_MASK(30));
 
+        /* 965GM sometimes incorrectly writes to hardware status page (HWS)
+         * using 32bit addressing, overwriting memory if HWS is located
+         * above 4GB.
+         *
+         * The documentation also mentions an issue with undefined
+         * behaviour if any general state is accessed within a page above 4GB,
+         * which also needs to be handled carefully.
+         */
+        if (IS_BROADWATER(dev) || IS_CRESTLINE(dev))
+                dma_set_coherent_mask(&dev->pdev->dev, DMA_BIT_MASK(32));
+
         mmio_bar = IS_GEN2(dev) ? 1 : 0;
         dev_priv->regs = pci_iomap(dev->pdev, mmio_bar, 0);
         if (!dev_priv->regs) {
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index 0a8969392829..1f45019e6da3 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;
+        int tile_width, tile_height;
 
         /* Linear is always fine */
         if (tiling_mode == I915_TILING_NONE)
@@ -215,6 +215,20 @@ 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))
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index c19e974c0019..4a392b4a5ae9 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -7148,7 +7148,7 @@ static void ironlake_disable_rc6(struct drm_device *dev)
                 POSTING_READ(RSTDBYCTL);
         }
 
-        ironlake_disable_rc6(dev);
+        ironlake_teardown_rc6(dev);
 }
 
 static int ironlake_setup_rc6(struct drm_device *dev)
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index d38a4d9f9b0b..a52184007f5f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -49,7 +49,10 @@ nouveau_bo_del_ttm(struct ttm_buffer_object *bo)
                 DRM_ERROR("bo %p still attached to GEM object\n", bo);
 
         nv10_mem_put_tile_region(dev, nvbo->tile, NULL);
-        nouveau_vm_put(&nvbo->vma);
+        if (nvbo->vma.node) {
+                nouveau_vm_unmap(&nvbo->vma);
+                nouveau_vm_put(&nvbo->vma);
+        }
         kfree(nvbo);
 }
 
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 56deae5bf02e..93fa735c8c1a 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -3490,7 +3490,7 @@ void r100_cs_track_clear(struct radeon_device *rdev, struct r100_cs_track *track
                 track->num_texture = 16;
                 track->maxy = 4096;
                 track->separate_cube = 0;
-                track->aaresolve = true;
+                track->aaresolve = false;
                 track->aa.robj = NULL;
         }
 
@@ -3801,8 +3801,6 @@ static int r100_startup(struct radeon_device *rdev)
         r100_mc_program(rdev);
         /* Resume clock */
         r100_clock_startup(rdev);
-        /* Initialize GPU configuration (# pipes, ...) */
-//      r100_gpu_init(rdev);
         /* Initialize GART (initialize after TTM so we can allocate
          * memory through TTM but finalize after TTM) */
         r100_enable_bm(rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 0e657095de7c..3e7e7f9eb781 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -971,7 +971,7 @@ void radeon_compute_pll_legacy(struct radeon_pll *pll,
                 max_fractional_feed_div = pll->max_frac_feedback_div;
         }
 
-        for (post_div = min_post_div; post_div <= max_post_div; ++post_div) {
+        for (post_div = max_post_div; post_div >= min_post_div; --post_div) {
                 uint32_t ref_div;
 
                 if ((pll->flags & RADEON_PLL_NO_ODD_POST_DIV) && (post_div & 1))
diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c
index 66324b5bb5ba..cc44bdfec80f 100644
--- a/drivers/gpu/drm/radeon/radeon_fb.c
+++ b/drivers/gpu/drm/radeon/radeon_fb.c
@@ -113,11 +113,14 @@ static int radeonfb_create_pinned_object(struct radeon_fbdev *rfbdev,
         u32 tiling_flags = 0;
         int ret;
         int aligned_size, size;
+        int height = mode_cmd->height;
 
         /* need to align pitch with crtc limits */
         mode_cmd->pitch = radeon_align_pitch(rdev, mode_cmd->width, mode_cmd->bpp, fb_tiled) * ((mode_cmd->bpp + 1) / 8);
 
-        size = mode_cmd->pitch * mode_cmd->height;
+        if (rdev->family >= CHIP_R600)
+                height = ALIGN(mode_cmd->height, 8);
+        size = mode_cmd->pitch * height;
         aligned_size = ALIGN(size, PAGE_SIZE);
         ret = radeon_gem_object_create(rdev, aligned_size, 0,
                                        RADEON_GEM_DOMAIN_VRAM,