Merge branch 'sched/urgent' into sched/core

Merge reason: Add fixes before applying dependent patches.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

9 files changed, 142 insertions, 31 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 17bd766f2081..e33d9be7df3b 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1895,6 +1895,17 @@ 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 22a32b9932c5..79a04fde69b5 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/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 97f946dcc1aa..8a9e08bf1cf7 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -316,6 +316,8 @@ static void i915_hotplug_work_func(struct work_struct *work)
         struct drm_mode_config *mode_config = &dev->mode_config;
         struct intel_encoder *encoder;
 
+        DRM_DEBUG_KMS("running encoder hotplug functions\n");
+
         list_for_each_entry(encoder, &mode_config->encoder_list, base.head)
                 if (encoder->hot_plug)
                         encoder->hot_plug(encoder);
@@ -1649,9 +1651,7 @@ static int ironlake_irq_postinstall(struct drm_device *dev)
         } else {
                 hotplug_mask = SDE_CRT_HOTPLUG | SDE_PORTB_HOTPLUG |
                                SDE_PORTC_HOTPLUG | SDE_PORTD_HOTPLUG;
-                hotplug_mask |= SDE_AUX_MASK | SDE_FDI_MASK | SDE_TRANS_MASK;
-                I915_WRITE(FDI_RXA_IMR, 0);
-                I915_WRITE(FDI_RXB_IMR, 0);
+                hotplug_mask |= SDE_AUX_MASK;
         }
 
         dev_priv->pch_irq_mask = ~hotplug_mask;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 3b006536b3d2..e79b25bbee6c 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1630,19 +1630,19 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
                 struct drm_i915_gem_object *obj = to_intel_framebuffer(old_fb)->obj;
 
                 wait_event(dev_priv->pending_flip_queue,
+                           atomic_read(&dev_priv->mm.wedged) ||
                            atomic_read(&obj->pending_flip) == 0);
 
                 /* Big Hammer, we also need to ensure that any pending
                  * MI_WAIT_FOR_EVENT inside a user batch buffer on the
                  * current scanout is retired before unpinning the old
                  * framebuffer.
+                 *
+                 * This should only fail upon a hung GPU, in which case we
+                 * can safely continue.
                  */
                 ret = i915_gem_object_flush_gpu(obj, false);
-                if (ret) {
-                        i915_gem_object_unpin(to_intel_framebuffer(crtc->fb)->obj);
-                        mutex_unlock(&dev->struct_mutex);
-                        return ret;
-                }
+                (void) ret;
         }
 
         ret = intel_pipe_set_base_atomic(crtc, crtc->fb, x, y,
@@ -2045,6 +2045,31 @@ static void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc)
                    atomic_read(&obj->pending_flip) == 0);
 }
 
+static bool intel_crtc_driving_pch(struct drm_crtc *crtc)
+{
+        struct drm_device *dev = crtc->dev;
+        struct drm_mode_config *mode_config = &dev->mode_config;
+        struct intel_encoder *encoder;
+
+        /*
+         * If there's a non-PCH eDP on this crtc, it must be DP_A, and that
+         * must be driven by its own crtc; no sharing is possible.
+         */
+        list_for_each_entry(encoder, &mode_config->encoder_list, base.head) {
+                if (encoder->base.crtc != crtc)
+                        continue;
+
+                switch (encoder->type) {
+                case INTEL_OUTPUT_EDP:
+                        if (!intel_encoder_is_pch_edp(&encoder->base))
+                                return false;
+                        continue;
+                }
+        }
+
+        return true;
+}
+
 static void ironlake_crtc_enable(struct drm_crtc *crtc)
 {
         struct drm_device *dev = crtc->dev;
@@ -2053,6 +2078,7 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
         int pipe = intel_crtc->pipe;
         int plane = intel_crtc->plane;
         u32 reg, temp;
+        bool is_pch_port = false;
 
         if (intel_crtc->active)
                 return;
@@ -2066,7 +2092,56 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
                         I915_WRITE(PCH_LVDS, temp | LVDS_PORT_EN);
         }
 
-        ironlake_fdi_enable(crtc);
+        is_pch_port = intel_crtc_driving_pch(crtc);
+
+        if (is_pch_port)
+                ironlake_fdi_enable(crtc);
+        else {
+                /* disable CPU FDI tx and PCH FDI rx */
+                reg = FDI_TX_CTL(pipe);
+                temp = I915_READ(reg);
+                I915_WRITE(reg, temp & ~FDI_TX_ENABLE);
+                POSTING_READ(reg);
+
+                reg = FDI_RX_CTL(pipe);
+                temp = I915_READ(reg);
+                temp &= ~(0x7 << 16);
+                temp |= (I915_READ(PIPECONF(pipe)) & PIPE_BPC_MASK) << 11;
+                I915_WRITE(reg, temp & ~FDI_RX_ENABLE);
+
+                POSTING_READ(reg);
+                udelay(100);
+
+                /* Ironlake workaround, disable clock pointer after downing FDI */
+                if (HAS_PCH_IBX(dev))
+                        I915_WRITE(FDI_RX_CHICKEN(pipe),
+                                   I915_READ(FDI_RX_CHICKEN(pipe) &
+                                             ~FDI_RX_PHASE_SYNC_POINTER_ENABLE));
+
+                /* still set train pattern 1 */
+                reg = FDI_TX_CTL(pipe);
+                temp = I915_READ(reg);
+                temp &= ~FDI_LINK_TRAIN_NONE;
+                temp |= FDI_LINK_TRAIN_PATTERN_1;
+                I915_WRITE(reg, temp);
+
+                reg = FDI_RX_CTL(pipe);
+                temp = I915_READ(reg);
+                if (HAS_PCH_CPT(dev)) {
+                        temp &= ~FDI_LINK_TRAIN_PATTERN_MASK_CPT;
+                        temp |= FDI_LINK_TRAIN_PATTERN_1_CPT;
+                } else {
+                        temp &= ~FDI_LINK_TRAIN_NONE;
+                        temp |= FDI_LINK_TRAIN_PATTERN_1;
+                }
+                /* BPC in FDI rx is consistent with that in PIPECONF */
+                temp &= ~(0x07 << 16);
+                temp |= (I915_READ(PIPECONF(pipe)) & PIPE_BPC_MASK) << 11;
+                I915_WRITE(reg, temp);
+
+                POSTING_READ(reg);
+                udelay(100);
+        }
 
         /* Enable panel fitting for LVDS */
         if (dev_priv->pch_pf_size &&
@@ -2100,6 +2175,10 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
                 intel_flush_display_plane(dev, plane);
         }
 
+        /* Skip the PCH stuff if possible */
+        if (!is_pch_port)
+                goto done;
+
         /* For PCH output, training FDI link */
         if (IS_GEN6(dev))
                 gen6_fdi_link_train(crtc);
@@ -2184,7 +2263,7 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
         I915_WRITE(reg, temp | TRANS_ENABLE);
         if (wait_for(I915_READ(reg) & TRANS_STATE_ENABLE, 100))
                 DRM_ERROR("failed to enable transcoder %d\n", pipe);
-
+done:
         intel_crtc_load_lut(crtc);
         intel_update_fbc(dev);
         intel_crtc_update_cursor(crtc, true);
@@ -6496,7 +6575,7 @@ 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,