Merge branch 'x86/urgent' into x86/apic

Bring in the upstream modifications so we can fixup the silent merge
conflict which is introduced by this merge.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

49 files changed, 794 insertions, 228 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 8ebc5f1eb4c0..700c56baf2de 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -426,6 +426,8 @@ struct amdgpu_mman {
 
         /* custom LRU management */
         struct amdgpu_mman_lru                  log2_size[AMDGPU_TTM_LRU_SIZE];
+        /* guard for log2_size array, don't add anything in between */
+        struct amdgpu_mman_lru                  guard;
 };
 
 int amdgpu_copy_buffer(struct amdgpu_ring *ring,
@@ -646,9 +648,9 @@ int amdgpu_gart_table_vram_pin(struct amdgpu_device *adev);
 void amdgpu_gart_table_vram_unpin(struct amdgpu_device *adev);
 int amdgpu_gart_init(struct amdgpu_device *adev);
 void amdgpu_gart_fini(struct amdgpu_device *adev);
-void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset,
+void amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
                         int pages);
-int amdgpu_gart_bind(struct amdgpu_device *adev, unsigned offset,
+int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
                      int pages, struct page **pagelist,
                      dma_addr_t *dma_addr, uint32_t flags);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index 983175363b06..fe872b82e619 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -321,6 +321,19 @@ bool amdgpu_atombios_get_connector_info_from_object_table(struct amdgpu_device *
                             (le16_to_cpu(path->usConnObjectId) &
                              OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT;
 
+                        /* Skip TV/CV support */
+                        if ((le16_to_cpu(path->usDeviceTag) ==
+                             ATOM_DEVICE_TV1_SUPPORT) ||
+                            (le16_to_cpu(path->usDeviceTag) ==
+                             ATOM_DEVICE_CV_SUPPORT))
+                                continue;
+
+                        if (con_obj_id >= ARRAY_SIZE(object_connector_convert)) {
+                                DRM_ERROR("invalid con_obj_id %d for device tag 0x%04x\n",
+                                          con_obj_id, le16_to_cpu(path->usDeviceTag));
+                                continue;
+                        }
+
                         connector_type =
                                 object_connector_convert[con_obj_id];
                         connector_object_id = con_obj_id;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
index 49de92600074..10b5ddf2c588 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
@@ -200,16 +200,7 @@ static int amdgpu_atpx_validate(struct amdgpu_atpx *atpx)
         atpx->is_hybrid = false;
         if (valid_bits & ATPX_MS_HYBRID_GFX_SUPPORTED) {
                 printk("ATPX Hybrid Graphics\n");
-#if 1
-                /* This is a temporary hack until the D3 cold support
-                 * makes it upstream.  The ATPX power_control method seems
-                 * to still work on even if the system should be using
-                 * the new standardized hybrid D3 cold ACPI interface.
-                 */
-                atpx->functions.power_cntl = true;
-#else
                 atpx->functions.power_cntl = false;
-#endif
                 atpx->is_hybrid = true;
         }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index 921bce2df0b0..0feea347f680 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -221,7 +221,7 @@ void amdgpu_gart_table_vram_free(struct amdgpu_device *adev)
  * Unbinds the requested pages from the gart page table and
  * replaces them with the dummy page (all asics).
  */
-void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset,
+void amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
                         int pages)
 {
         unsigned t;
@@ -268,7 +268,7 @@ void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset,
  * (all asics).
  * Returns 0 for success, -EINVAL for failure.
  */
-int amdgpu_gart_bind(struct amdgpu_device *adev, unsigned offset,
+int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
                      int pages, struct page **pagelist, dma_addr_t *dma_addr,
                      uint32_t flags)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index a31d7ef3032c..ec1282af2479 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -280,7 +280,7 @@ void amdgpu_ib_pool_fini(struct amdgpu_device *adev)
 int amdgpu_ib_ring_tests(struct amdgpu_device *adev)
 {
         unsigned i;
-        int r;
+        int r, ret = 0;
 
         for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
                 struct amdgpu_ring *ring = adev->rings[i];
@@ -301,10 +301,11 @@ int amdgpu_ib_ring_tests(struct amdgpu_device *adev)
                         } else {
                                 /* still not good, but we can live with it */
                                 DRM_ERROR("amdgpu: failed testing IB on ring %d (%d).\n", i, r);
+                                ret = r;
                         }
                 }
         }
-        return 0;
+        return ret;
 }
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 9b61c8ba7aaf..716f2afeb6a9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -251,8 +251,8 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
 
         adev = amdgpu_get_adev(bo->bdev);
         ring = adev->mman.buffer_funcs_ring;
-        old_start = old_mem->start << PAGE_SHIFT;
-        new_start = new_mem->start << PAGE_SHIFT;
+        old_start = (u64)old_mem->start << PAGE_SHIFT;
+        new_start = (u64)new_mem->start << PAGE_SHIFT;
 
         switch (old_mem->mem_type) {
         case TTM_PL_VRAM:
@@ -950,6 +950,8 @@ static struct list_head *amdgpu_ttm_lru_tail(struct ttm_buffer_object *tbo)
         struct list_head *res = lru->lru[tbo->mem.mem_type];
 
         lru->lru[tbo->mem.mem_type] = &tbo->lru;
+        while ((++lru)->lru[tbo->mem.mem_type] == res)
+                lru->lru[tbo->mem.mem_type] = &tbo->lru;
 
         return res;
 }
@@ -960,6 +962,8 @@ static struct list_head *amdgpu_ttm_swap_lru_tail(struct ttm_buffer_object *tbo)
         struct list_head *res = lru->swap_lru;
 
         lru->swap_lru = &tbo->swap;
+        while ((++lru)->swap_lru == res)
+                lru->swap_lru = &tbo->swap;
 
         return res;
 }
@@ -1011,6 +1015,10 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
                 lru->swap_lru = &adev->mman.bdev.glob->swap_lru;
         }
 
+        for (j = 0; j < TTM_NUM_MEM_TYPES; ++j)
+                adev->mman.guard.lru[j] = NULL;
+        adev->mman.guard.swap_lru = NULL;
+
         adev->mman.initialized = true;
         r = ttm_bo_init_mm(&adev->mman.bdev, TTM_PL_VRAM,
                                 adev->mc.real_vram_size >> PAGE_SHIFT);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index b11f4e8868d7..4aa993d19018 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -1187,7 +1187,8 @@ int amdgpu_uvd_ring_test_ib(struct amdgpu_ring *ring, long timeout)
                 r = 0;
         }
 
-error:
         fence_put(fence);
+
+error:
         return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 8e642fc48df4..80120fa4092c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1535,7 +1535,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
         r = amd_sched_entity_init(&ring->sched, &vm->entity,
                                   rq, amdgpu_sched_jobs);
         if (r)
-                return r;
+                goto err;
 
         vm->page_directory_fence = NULL;
 
@@ -1565,6 +1565,9 @@ error_free_page_directory:
 error_free_sched_entity:
         amd_sched_entity_fini(&ring->sched, &vm->entity);
 
+err:
+        drm_free_large(vm->page_tables);
+
         return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index ee6466912497..77fdd9911c3c 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -52,6 +52,7 @@ static void cik_sdma_set_ring_funcs(struct amdgpu_device *adev);
 static void cik_sdma_set_irq_funcs(struct amdgpu_device *adev);
 static void cik_sdma_set_buffer_funcs(struct amdgpu_device *adev);
 static void cik_sdma_set_vm_pte_funcs(struct amdgpu_device *adev);
+static int cik_sdma_soft_reset(void *handle);
 
 MODULE_FIRMWARE("radeon/bonaire_sdma.bin");
 MODULE_FIRMWARE("radeon/bonaire_sdma1.bin");
@@ -1037,6 +1038,8 @@ static int cik_sdma_resume(void *handle)
 {
         struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+        cik_sdma_soft_reset(handle);
+
         return cik_sdma_hw_init(adev);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index d869d058ef24..425413fcaf02 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -2755,8 +2755,7 @@ static int gfx_v7_0_cp_compute_resume(struct amdgpu_device *adev)
         u64 wb_gpu_addr;
         u32 *buf;
         struct bonaire_mqd *mqd;
-
-        gfx_v7_0_cp_compute_enable(adev, true);
+        struct amdgpu_ring *ring;
 
         /* fix up chicken bits */
         tmp = RREG32(mmCP_CPF_DEBUG);
@@ -2791,7 +2790,7 @@ static int gfx_v7_0_cp_compute_resume(struct amdgpu_device *adev)
 
         /* init the queues.  Just two for now. */
         for (i = 0; i < adev->gfx.num_compute_rings; i++) {
-                struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
+                ring = &adev->gfx.compute_ring[i];
 
                 if (ring->mqd_obj == NULL) {
                         r = amdgpu_bo_create(adev,
@@ -2970,6 +2969,13 @@ static int gfx_v7_0_cp_compute_resume(struct amdgpu_device *adev)
                 amdgpu_bo_unreserve(ring->mqd_obj);
 
                 ring->ready = true;
+        }
+
+        gfx_v7_0_cp_compute_enable(adev, true);
+
+        for (i = 0; i < adev->gfx.num_compute_rings; i++) {
+                ring = &adev->gfx.compute_ring[i];
+
                 r = amdgpu_ring_test_ring(ring);
                 if (r)
                         ring->ready = false;
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index 1351c7e834a2..a64715d90503 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -714,7 +714,7 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout)
                 DRM_ERROR("amdgpu: IB test timed out\n");
                 r = -ETIMEDOUT;
                 goto err1;
-        } else if (r) {
+        } else if (r < 0) {
                 DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
                 goto err1;
         }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
index e621eba63126..a7d3cb3fead0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
@@ -184,7 +184,7 @@ u32 __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd,
                                                         sizeof(u32)) + inx;
 
         pr_debug("kfd: get kernel queue doorbell\n"
-                         "     doorbell offset   == 0x%08d\n"
+                         "     doorbell offset   == 0x%08X\n"
                          "     kernel address    == 0x%08lX\n",
                 *doorbell_off, (uintptr_t)(kfd->doorbell_kernel_ptr + inx));
 
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index ef312bb75fda..963a24d46a93 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -405,7 +405,7 @@ void amd_sched_job_recovery(struct amd_gpu_scheduler *sched)
         spin_lock(&sched->job_list_lock);
         s_job = list_first_entry_or_null(&sched->ring_mirror_list,
                                          struct amd_sched_job, node);
-        if (s_job)
+        if (s_job && sched->timeout != MAX_SCHEDULE_TIMEOUT)
                 schedule_delayed_work(&s_job->work_tdr, sched->timeout);
 
         list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index fa3930757972..2a3ded44cf2a 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -475,7 +475,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc,
                                         val,
                                         -1,
                                         &replaced);
-                state->color_mgmt_changed = replaced;
+                state->color_mgmt_changed |= replaced;
                 return ret;
         } else if (property == config->ctm_property) {
                 ret = drm_atomic_replace_property_blob_from_id(crtc,
@@ -483,7 +483,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc,
                                         val,
                                         sizeof(struct drm_color_ctm),
                                         &replaced);
-                state->color_mgmt_changed = replaced;
+                state->color_mgmt_changed |= replaced;
                 return ret;
         } else if (property == config->gamma_lut_property) {
                 ret = drm_atomic_replace_property_blob_from_id(crtc,
@@ -491,7 +491,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc,
                                         val,
                                         -1,
                                         &replaced);
-                state->color_mgmt_changed = replaced;
+                state->color_mgmt_changed |= replaced;
                 return ret;
         } else if (crtc->funcs->atomic_set_property)
                 return crtc->funcs->atomic_set_property(crtc, state, property, val);
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index b1dbb60af99f..ddebe54cd5ca 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -5404,6 +5404,9 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
         struct drm_pending_vblank_event *e = NULL;
         int ret = -EINVAL;
 
+        if (!drm_core_check_feature(dev, DRIVER_MODESET))
+                return -EINVAL;
+
         if (page_flip->flags & ~DRM_MODE_PAGE_FLIP_FLAGS ||
             page_flip->reserved != 0)
                 return -EINVAL;
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index ce54e985d91b..0a06f9120b5a 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -464,7 +464,7 @@ static bool drm_fb_helper_is_bound(struct drm_fb_helper *fb_helper)
 
         /* Sometimes user space wants everything disabled, so don't steal the
          * display if there's a master. */
-        if (lockless_dereference(dev->master))
+        if (READ_ONCE(dev->master))
                 return false;
 
         drm_for_each_crtc(crtc, dev) {
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index 87ef34150d46..b382cf505262 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -1333,8 +1333,6 @@ int etnaviv_gpu_submit(struct etnaviv_gpu *gpu,
         if (ret < 0)
                 return ret;
 
-        mutex_lock(&gpu->lock);
-
         /*
          * TODO
          *
@@ -1348,16 +1346,18 @@ int etnaviv_gpu_submit(struct etnaviv_gpu *gpu,
         if (unlikely(event == ~0U)) {
                 DRM_ERROR("no free event\n");
                 ret = -EBUSY;
-                goto out_unlock;
+                goto out_pm_put;
         }
 
         fence = etnaviv_gpu_fence_alloc(gpu);
         if (!fence) {
                 event_free(gpu, event);
                 ret = -ENOMEM;
-                goto out_unlock;
+                goto out_pm_put;
         }
 
+        mutex_lock(&gpu->lock);
+
         gpu->event[event].fence = fence;
         submit->fence = fence->seqno;
         gpu->active_fence = submit->fence;
@@ -1395,9 +1395,9 @@ int etnaviv_gpu_submit(struct etnaviv_gpu *gpu,
         hangcheck_timer_reset(gpu);
         ret = 0;
 
-out_unlock:
         mutex_unlock(&gpu->lock);
 
+out_pm_put:
         etnaviv_gpu_pm_put(gpu);
 
         return ret;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 21f939074abc..f68c78918d63 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -882,11 +882,12 @@ struct i915_gem_context {
 
         struct i915_ctx_hang_stats hang_stats;
 
-        /* Unique identifier for this context, used by the hw for tracking */
         unsigned long flags;
 #define CONTEXT_NO_ZEROMAP              BIT(0)
 #define CONTEXT_NO_ERROR_CAPTURE        BIT(1)
-        unsigned hw_id;
+
+        /* Unique identifier for this context, used by the hw for tracking */
+        unsigned int hw_id;
         u32 user_handle;
 
         u32 ggtt_alignment;
@@ -1854,6 +1855,7 @@ struct drm_i915_private {
         enum modeset_restore modeset_restore;
         struct mutex modeset_restore_lock;
         struct drm_atomic_state *modeset_restore_state;
+        struct drm_modeset_acquire_ctx reset_ctx;
 
         struct list_head vm_list; /* Global list of all address spaces */
         struct i915_ggtt ggtt; /* VM representing the global address space */
@@ -1962,6 +1964,13 @@ struct drm_i915_private {
         struct i915_suspend_saved_registers regfile;
         struct vlv_s0ix_state vlv_s0ix_state;
 
+        enum {
+                I915_SKL_SAGV_UNKNOWN = 0,
+                I915_SKL_SAGV_DISABLED,
+                I915_SKL_SAGV_ENABLED,
+                I915_SKL_SAGV_NOT_CONTROLLED
+        } skl_sagv_status;
+
         struct {
                 /*
                  * Raw watermark latency values:
@@ -3590,6 +3599,7 @@ int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle);
 /* belongs in i915_gem_gtt.h */
 static inline void i915_gem_chipset_flush(struct drm_i915_private *dev_priv)
 {
+        wmb();
         if (INTEL_GEN(dev_priv) < 6)
                 intel_gtt_chipset_flush();
 }
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 11681501d7b1..a77ce9983f69 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -879,9 +879,12 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data,
         ret = i915_gem_shmem_pread(dev, obj, args, file);
 
         /* pread for non shmem backed objects */
-        if (ret == -EFAULT || ret == -ENODEV)
+        if (ret == -EFAULT || ret == -ENODEV) {
+                intel_runtime_pm_get(to_i915(dev));
                 ret = i915_gem_gtt_pread(dev, obj, args->size,
                                         args->offset, args->data_ptr);
+                intel_runtime_pm_put(to_i915(dev));
+        }
 
 out:
         drm_gem_object_unreference(&obj->base);
@@ -1306,7 +1309,7 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
                  * textures). Fallback to the shmem path in that case. */
         }
 
-        if (ret == -EFAULT) {
+        if (ret == -EFAULT || ret == -ENOSPC) {
                 if (obj->phys_handle)
                         ret = i915_gem_phys_pwrite(obj, args, file);
                 else if (i915_gem_object_has_struct_page(obj))
@@ -3169,6 +3172,8 @@ static void i915_gem_reset_engine_cleanup(struct intel_engine_cs *engine)
         }
 
         intel_ring_init_seqno(engine, engine->last_submitted_seqno);
+
+        engine->i915->gt.active_engines &= ~intel_engine_flag(engine);
 }
 
 void i915_gem_reset(struct drm_device *dev)
@@ -3186,6 +3191,7 @@ void i915_gem_reset(struct drm_device *dev)
 
         for_each_engine(engine, dev_priv)
                 i915_gem_reset_engine_cleanup(engine);
+        mod_delayed_work(dev_priv->wq, &dev_priv->gt.idle_work, 0);
 
         i915_gem_context_reset(dev);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 1978633e7549..b35e5b6475b2 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -943,8 +943,6 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
 {
         const unsigned other_rings = ~intel_engine_flag(req->engine);
         struct i915_vma *vma;
-        uint32_t flush_domains = 0;
-        bool flush_chipset = false;
         int ret;
 
         list_for_each_entry(vma, vmas, exec_list) {
@@ -957,16 +955,11 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
                 }
 
                 if (obj->base.write_domain & I915_GEM_DOMAIN_CPU)
-                        flush_chipset |= i915_gem_clflush_object(obj, false);
-
-                flush_domains |= obj->base.write_domain;
+                        i915_gem_clflush_object(obj, false);
         }
 
-        if (flush_chipset)
-                i915_gem_chipset_flush(req->engine->i915);
-
-        if (flush_domains & I915_GEM_DOMAIN_GTT)
-                wmb();
+        /* Unconditionally flush any chipset caches (for streaming writes). */
+        i915_gem_chipset_flush(req->engine->i915);
 
         /* Unconditionally invalidate gpu caches and ensure that we do flush
          * any residual writes from the previous batch.
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 10f1e32767e6..7a30af79d799 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2873,6 +2873,7 @@ void i915_ggtt_cleanup_hw(struct drm_device *dev)
                 struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
 
                 ppgtt->base.cleanup(&ppgtt->base);
+                kfree(ppgtt);
         }
 
         i915_gem_cleanup_stolen(dev);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index ce14fe09d962..bf2cad3f9e1f 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1536,6 +1536,7 @@ enum skl_disp_power_wells {
 #define BALANCE_LEG_MASK(port)          (7<<(8+3*(port)))
 /* Balance leg disable bits */
 #define BALANCE_LEG_DISABLE_SHIFT       23
+#define BALANCE_LEG_DISABLE(port)       (1 << (23 + (port)))
 
 /*
  * Fence registers
@@ -7144,6 +7145,15 @@ enum {
 
 #define GEN6_PCODE_MAILBOX                      _MMIO(0x138124)
 #define   GEN6_PCODE_READY                      (1<<31)
+#define   GEN6_PCODE_ERROR_MASK                 0xFF
+#define     GEN6_PCODE_SUCCESS                  0x0
+#define     GEN6_PCODE_ILLEGAL_CMD              0x1
+#define     GEN6_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE 0x2
+#define     GEN6_PCODE_TIMEOUT                  0x3
+#define     GEN6_PCODE_UNIMPLEMENTED_CMD        0xFF
+#define     GEN7_PCODE_TIMEOUT                  0x2
+#define     GEN7_PCODE_ILLEGAL_DATA             0x3
+#define     GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE 0x10
 #define   GEN6_PCODE_WRITE_RC6VIDS              0x4
 #define   GEN6_PCODE_READ_RC6VIDS               0x5
 #define     GEN6_ENCODE_RC6_VID(mv)             (((mv) - 245) / 5)
@@ -7165,6 +7175,10 @@ enum {
 #define   HSW_PCODE_DE_WRITE_FREQ_REQ           0x17
 #define   DISPLAY_IPS_CONTROL                   0x19
 #define   HSW_PCODE_DYNAMIC_DUTY_CYCLE_CONTROL  0x1A
+#define   GEN9_PCODE_SAGV_CONTROL               0x21
+#define     GEN9_SAGV_DISABLE                   0x0
+#define     GEN9_SAGV_IS_DISABLED               0x1
+#define     GEN9_SAGV_ENABLE                    0x3
 #define GEN6_PCODE_DATA                         _MMIO(0x138128)
 #define   GEN6_PCODE_FREQ_IA_RATIO_SHIFT        8
 #define   GEN6_PCODE_FREQ_RING_RATIO_SHIFT      16
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index 6700a7be7f78..d32f586f9c05 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -600,6 +600,8 @@ static void i915_audio_component_codec_wake_override(struct device *dev,
         if (!IS_SKYLAKE(dev_priv) && !IS_KABYLAKE(dev_priv))
                 return;
 
+        i915_audio_component_get_power(dev);
+
         /*
          * Enable/disable generating the codec wake signal, overriding the
          * internal logic to generate the codec wake to controller.
@@ -615,6 +617,8 @@ static void i915_audio_component_codec_wake_override(struct device *dev,
                 I915_WRITE(HSW_AUD_CHICKENBIT, tmp);
                 usleep_range(1000, 1500);
         }
+
+        i915_audio_component_put_power(dev);
 }
 
 /* Get CDCLK in kHz  */
@@ -648,6 +652,7 @@ static int i915_audio_component_sync_audio_rate(struct device *dev,
             !IS_HASWELL(dev_priv))
                 return 0;
 
+        i915_audio_component_get_power(dev);
         mutex_lock(&dev_priv->av_mutex);
         /* 1. get the pipe */
         intel_encoder = dev_priv->dig_port_map[port];
@@ -698,6 +703,7 @@ static int i915_audio_component_sync_audio_rate(struct device *dev,
 
  unlock:
         mutex_unlock(&dev_priv->av_mutex);
+        i915_audio_component_put_power(dev);
         return err;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c
index 3edb9580928e..c3b33a10c15c 100644
--- a/drivers/gpu/drm/i915/intel_csr.c
+++ b/drivers/gpu/drm/i915/intel_csr.c
@@ -41,15 +41,15 @@
  * be moved to FW_FAILED.
  */
 
-#define I915_CSR_KBL "i915/kbl_dmc_ver1.bin"
+#define I915_CSR_KBL "i915/kbl_dmc_ver1_01.bin"
 MODULE_FIRMWARE(I915_CSR_KBL);
 #define KBL_CSR_VERSION_REQUIRED        CSR_VERSION(1, 1)
 
-#define I915_CSR_SKL "i915/skl_dmc_ver1.bin"
+#define I915_CSR_SKL "i915/skl_dmc_ver1_26.bin"
 MODULE_FIRMWARE(I915_CSR_SKL);
-#define SKL_CSR_VERSION_REQUIRED        CSR_VERSION(1, 23)
+#define SKL_CSR_VERSION_REQUIRED        CSR_VERSION(1, 26)
 
-#define I915_CSR_BXT "i915/bxt_dmc_ver1.bin"
+#define I915_CSR_BXT "i915/bxt_dmc_ver1_07.bin"
 MODULE_FIRMWARE(I915_CSR_BXT);
 #define BXT_CSR_VERSION_REQUIRED        CSR_VERSION(1, 7)
 
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index dd1d6fe12297..1a7efac65fd5 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -145,7 +145,7 @@ static const struct ddi_buf_trans skl_ddi_translations_dp[] = {
 static const struct ddi_buf_trans skl_u_ddi_translations_dp[] = {
         { 0x0000201B, 0x000000A2, 0x0 },
         { 0x00005012, 0x00000088, 0x0 },
-        { 0x80007011, 0x000000CD, 0x0 },
+        { 0x80007011, 0x000000CD, 0x1 },
         { 0x80009010, 0x000000C0, 0x1 },
         { 0x0000201B, 0x0000009D, 0x0 },
         { 0x80005012, 0x000000C0, 0x1 },
@@ -158,7 +158,7 @@ static const struct ddi_buf_trans skl_u_ddi_translations_dp[] = {
 static const struct ddi_buf_trans skl_y_ddi_translations_dp[] = {
         { 0x00000018, 0x000000A2, 0x0 },
         { 0x00005012, 0x00000088, 0x0 },
-        { 0x80007011, 0x000000CD, 0x0 },
+        { 0x80007011, 0x000000CD, 0x3 },
         { 0x80009010, 0x000000C0, 0x3 },
         { 0x00000018, 0x0000009D, 0x0 },
         { 0x80005012, 0x000000C0, 0x3 },
@@ -388,6 +388,40 @@ skl_get_buf_trans_hdmi(struct drm_i915_private *dev_priv, int *n_entries)
         }
 }
 
+static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port port)
+{
+        int n_hdmi_entries;
+        int hdmi_level;
+        int hdmi_default_entry;
+
+        hdmi_level = dev_priv->vbt.ddi_port_info[port].hdmi_level_shift;
+
+        if (IS_BROXTON(dev_priv))
+                return hdmi_level;
+
+        if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+                skl_get_buf_trans_hdmi(dev_priv, &n_hdmi_entries);
+                hdmi_default_entry = 8;
+        } else if (IS_BROADWELL(dev_priv)) {
+                n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi);
+                hdmi_default_entry = 7;
+        } else if (IS_HASWELL(dev_priv)) {
+                n_hdmi_entries = ARRAY_SIZE(hsw_ddi_translations_hdmi);
+                hdmi_default_entry = 6;
+        } else {
+                WARN(1, "ddi translation table missing\n");
+                n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi);
+                hdmi_default_entry = 7;
+        }
+
+        /* Choose a good default if VBT is badly populated */
+        if (hdmi_level == HDMI_LEVEL_SHIFT_UNKNOWN ||
+            hdmi_level >= n_hdmi_entries)
+                hdmi_level = hdmi_default_entry;
+
+        return hdmi_level;
+}
+
 /*
  * Starting with Haswell, DDI port buffers must be programmed with correct
  * values in advance. The buffer values are different for FDI and DP modes,
@@ -399,7 +433,7 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder)
 {
         struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
         u32 iboost_bit = 0;
-        int i, n_hdmi_entries, n_dp_entries, n_edp_entries, hdmi_default_entry,
+        int i, n_hdmi_entries, n_dp_entries, n_edp_entries,
             size;
         int hdmi_level;
         enum port port;
@@ -410,7 +444,7 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder)
         const struct ddi_buf_trans *ddi_translations;
 
         port = intel_ddi_get_encoder_port(encoder);
-        hdmi_level = dev_priv->vbt.ddi_port_info[port].hdmi_level_shift;
+        hdmi_level = intel_ddi_hdmi_level(dev_priv, port);
 
         if (IS_BROXTON(dev_priv)) {
                 if (encoder->type != INTEL_OUTPUT_HDMI)
@@ -430,7 +464,6 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder)
                                 skl_get_buf_trans_edp(dev_priv, &n_edp_entries);
                 ddi_translations_hdmi =
                                 skl_get_buf_trans_hdmi(dev_priv, &n_hdmi_entries);
-                hdmi_default_entry = 8;
                 /* If we're boosting the current, set bit 31 of trans1 */
                 if (dev_priv->vbt.ddi_port_info[port].hdmi_boost_level ||
                     dev_priv->vbt.ddi_port_info[port].dp_boost_level)
@@ -456,7 +489,6 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder)
 
                 n_dp_entries = ARRAY_SIZE(bdw_ddi_translations_dp);
                 n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi);
-                hdmi_default_entry = 7;
         } else if (IS_HASWELL(dev_priv)) {
                 ddi_translations_fdi = hsw_ddi_translations_fdi;
                 ddi_translations_dp = hsw_ddi_translations_dp;
@@ -464,7 +496,6 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder)
                 ddi_translations_hdmi = hsw_ddi_translations_hdmi;
                 n_dp_entries = n_edp_entries = ARRAY_SIZE(hsw_ddi_translations_dp);
                 n_hdmi_entries = ARRAY_SIZE(hsw_ddi_translations_hdmi);
-                hdmi_default_entry = 6;
         } else {
                 WARN(1, "ddi translation table missing\n");
                 ddi_translations_edp = bdw_ddi_translations_dp;
@@ -474,7 +505,6 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder)
                 n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_edp);
                 n_dp_entries = ARRAY_SIZE(bdw_ddi_translations_dp);
                 n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi);
-                hdmi_default_entry = 7;
         }
 
         switch (encoder->type) {
@@ -505,11 +535,6 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder)
         if (encoder->type != INTEL_OUTPUT_HDMI)
                 return;
 
-        /* Choose a good default if VBT is badly populated */
-        if (hdmi_level == HDMI_LEVEL_SHIFT_UNKNOWN ||
-            hdmi_level >= n_hdmi_entries)
-                hdmi_level = hdmi_default_entry;
-
         /* Entry 9 is for HDMI: */
         I915_WRITE(DDI_BUF_TRANS_LO(port, i),
                    ddi_translations_hdmi[hdmi_level].trans1 | iboost_bit);
@@ -1379,14 +1404,30 @@ void intel_ddi_disable_pipe_clock(struct intel_crtc *intel_crtc)
                            TRANS_CLK_SEL_DISABLED);
 }
 
-static void skl_ddi_set_iboost(struct drm_i915_private *dev_priv,
-                               u32 level, enum port port, int type)
+static void _skl_ddi_set_iboost(struct drm_i915_private *dev_priv,
+                                enum port port, uint8_t iboost)
 {
+        u32 tmp;
+
+        tmp = I915_READ(DISPIO_CR_TX_BMU_CR0);
+        tmp &= ~(BALANCE_LEG_MASK(port) | BALANCE_LEG_DISABLE(port));
+        if (iboost)
+                tmp |= iboost << BALANCE_LEG_SHIFT(port);
+        else
+                tmp |= BALANCE_LEG_DISABLE(port);
+        I915_WRITE(DISPIO_CR_TX_BMU_CR0, tmp);
+}
+
+static void skl_ddi_set_iboost(struct intel_encoder *encoder, u32 level)
+{
+        struct intel_digital_port *intel_dig_port = enc_to_dig_port(&encoder->base);
+        struct drm_i915_private *dev_priv = to_i915(intel_dig_port->base.base.dev);
+        enum port port = intel_dig_port->port;
+        int type = encoder->type;
         const struct ddi_buf_trans *ddi_translations;
         uint8_t iboost;
         uint8_t dp_iboost, hdmi_iboost;
         int n_entries;
-        u32 reg;
 
         /* VBT may override standard boost values */
         dp_iboost = dev_priv->vbt.ddi_port_info[port].dp_boost_level;
@@ -1428,16 +1469,10 @@ static void skl_ddi_set_iboost(struct drm_i915_private *dev_priv,
                 return;
         }
 
-        reg = I915_READ(DISPIO_CR_TX_BMU_CR0);
-        reg &= ~BALANCE_LEG_MASK(port);
-        reg &= ~(1 << (BALANCE_LEG_DISABLE_SHIFT + port));
-
-        if (iboost)
-                reg |= iboost << BALANCE_LEG_SHIFT(port);
-        else
-                reg |= 1 << (BALANCE_LEG_DISABLE_SHIFT + port);
+        _skl_ddi_set_iboost(dev_priv, port, iboost);
 
-        I915_WRITE(DISPIO_CR_TX_BMU_CR0, reg);
+        if (port == PORT_A && intel_dig_port->max_lanes == 4)
+                _skl_ddi_set_iboost(dev_priv, PORT_E, iboost);
 }
 
 static void bxt_ddi_vswing_sequence(struct drm_i915_private *dev_priv,
@@ -1568,7 +1603,7 @@ uint32_t ddi_signal_levels(struct intel_dp *intel_dp)
         level = translate_signal_level(signal_levels);
 
         if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
-                skl_ddi_set_iboost(dev_priv, level, port, encoder->type);
+                skl_ddi_set_iboost(encoder, level);
         else if (IS_BROXTON(dev_priv))
                 bxt_ddi_vswing_sequence(dev_priv, level, port, encoder->type);
 
@@ -1637,6 +1672,10 @@ static void intel_ddi_pre_enable(struct intel_encoder *intel_encoder)
                         intel_dp_stop_link_train(intel_dp);
         } else if (type == INTEL_OUTPUT_HDMI) {
                 struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
+                int level = intel_ddi_hdmi_level(dev_priv, port);
+
+                if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
+                        skl_ddi_set_iboost(intel_encoder, level);
 
                 intel_hdmi->set_infoframes(encoder,
                                            crtc->config->has_hdmi_sink,
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index dcf93b3d4fb6..175595fc3e45 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3093,40 +3093,110 @@ static void intel_update_primary_planes(struct drm_device *dev)
 
         for_each_crtc(dev, crtc) {
                 struct intel_plane *plane = to_intel_plane(crtc->primary);
-                struct intel_plane_state *plane_state;
-
-                drm_modeset_lock_crtc(crtc, &plane->base);
-                plane_state = to_intel_plane_state(plane->base.state);
+                struct intel_plane_state *plane_state =
+                        to_intel_plane_state(plane->base.state);
 
                 if (plane_state->visible)
                         plane->update_plane(&plane->base,
                                             to_intel_crtc_state(crtc->state),
                                             plane_state);
+        }
+}
+
+static int
+__intel_display_resume(struct drm_device *dev,
+                       struct drm_atomic_state *state)
+{
+        struct drm_crtc_state *crtc_state;
+        struct drm_crtc *crtc;
+        int i, ret;
+
+        intel_modeset_setup_hw_state(dev);
+        i915_redisable_vga(dev);
 
-                drm_modeset_unlock_crtc(crtc);
+        if (!state)
+                return 0;
+
+        for_each_crtc_in_state(state, crtc, crtc_state, i) {
+                /*
+                 * Force recalculation even if we restore
+                 * current state. With fast modeset this may not result
+                 * in a modeset when the state is compatible.
+                 */
+                crtc_state->mode_changed = true;
         }
+
+        /* ignore any reset values/BIOS leftovers in the WM registers */
+        to_intel_atomic_state(state)->skip_intermediate_wm = true;
+
+        ret = drm_atomic_commit(state);
+
+        WARN_ON(ret == -EDEADLK);
+        return ret;
 }
 
 void intel_prepare_reset(struct drm_i915_private *dev_priv)
 {
+        struct drm_device *dev = &dev_priv->drm;
+        struct drm_modeset_acquire_ctx *ctx = &dev_priv->reset_ctx;
+        struct drm_atomic_state *state;
+        int ret;
+
         /* no reset support for gen2 */
         if (IS_GEN2(dev_priv))
                 return;
 
-        /* reset doesn't touch the display */
+        /*
+         * Need mode_config.mutex so that we don't
+         * trample ongoing ->detect() and whatnot.
+         */
+        mutex_lock(&dev->mode_config.mutex);
+        drm_modeset_acquire_init(ctx, 0);
+        while (1) {
+                ret = drm_modeset_lock_all_ctx(dev, ctx);
+                if (ret != -EDEADLK)
+                        break;
+
+                drm_modeset_backoff(ctx);
+        }
+
+        /* reset doesn't touch the display, but flips might get nuked anyway, */
         if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv))
                 return;
 
-        drm_modeset_lock_all(&dev_priv->drm);
         /*
          * Disabling the crtcs gracefully seems nicer. Also the
          * g33 docs say we should at least disable all the planes.
          */
-        intel_display_suspend(&dev_priv->drm);
+        state = drm_atomic_helper_duplicate_state(dev, ctx);
+        if (IS_ERR(state)) {
+                ret = PTR_ERR(state);
+                state = NULL;
+                DRM_ERROR("Duplicating state failed with %i\n", ret);
+                goto err;
+        }
+
+        ret = drm_atomic_helper_disable_all(dev, ctx);
+        if (ret) {
+                DRM_ERROR("Suspending crtc's failed with %i\n", ret);
+                goto err;
+        }
+
+        dev_priv->modeset_restore_state = state;
+        state->acquire_ctx = ctx;
+        return;
+
+err:
+        drm_atomic_state_free(state);
 }
 
 void intel_finish_reset(struct drm_i915_private *dev_priv)
 {
+        struct drm_device *dev = &dev_priv->drm;
+        struct drm_modeset_acquire_ctx *ctx = &dev_priv->reset_ctx;
+        struct drm_atomic_state *state = dev_priv->modeset_restore_state;
+        int ret;
+
         /*
          * Flips in the rings will be nuked by the reset,
          * so complete all pending flips so that user space
@@ -3138,6 +3208,8 @@ void intel_finish_reset(struct drm_i915_private *dev_priv)
         if (IS_GEN2(dev_priv))
                 return;
 
+        dev_priv->modeset_restore_state = NULL;
+
         /* reset doesn't touch the display */
         if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv)) {
                 /*
@@ -3149,29 +3221,32 @@ void intel_finish_reset(struct drm_i915_private *dev_priv)
                  * FIXME: Atomic will make this obsolete since we won't schedule
                  * CS-based flips (which might get lost in gpu resets) any more.
                  */
-                intel_update_primary_planes(&dev_priv->drm);
-                return;
-        }
-
-        /*
-         * The display has been reset as well,
-         * so need a full re-initialization.
-         */
-        intel_runtime_pm_disable_interrupts(dev_priv);
-        intel_runtime_pm_enable_interrupts(dev_priv);
+                intel_update_primary_planes(dev);
+        } else {
+                /*
+                 * The display has been reset as well,
+                 * so need a full re-initialization.
+                 */
+                intel_runtime_pm_disable_interrupts(dev_priv);
+                intel_runtime_pm_enable_interrupts(dev_priv);
 
-        intel_modeset_init_hw(&dev_priv->drm);
+                intel_modeset_init_hw(dev);
 
-        spin_lock_irq(&dev_priv->irq_lock);
-        if (dev_priv->display.hpd_irq_setup)
-                dev_priv->display.hpd_irq_setup(dev_priv);
-        spin_unlock_irq(&dev_priv->irq_lock);
+                spin_lock_irq(&dev_priv->irq_lock);
+                if (dev_priv->display.hpd_irq_setup)
+                        dev_priv->display.hpd_irq_setup(dev_priv);
+                spin_unlock_irq(&dev_priv->irq_lock);
 
-        intel_display_resume(&dev_priv->drm);
+                ret = __intel_display_resume(dev, state);
+                if (ret)
+                        DRM_ERROR("Restoring old state failed with %i\n", ret);
 
-        intel_hpd_init(dev_priv);
+                intel_hpd_init(dev_priv);
+        }
 
-        drm_modeset_unlock_all(&dev_priv->drm);
+        drm_modeset_drop_locks(ctx);
+        drm_modeset_acquire_fini(ctx);
+        mutex_unlock(&dev->mode_config.mutex);
 }
 
 static bool intel_crtc_has_pending_flip(struct drm_crtc *crtc)
@@ -13684,6 +13759,13 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
                      intel_state->cdclk_pll_vco != dev_priv->cdclk_pll.vco))
                         dev_priv->display.modeset_commit_cdclk(state);
 
+                /*
+                 * SKL workaround: bspec recommends we disable the SAGV when we
+                 * have more then one pipe enabled
+                 */
+                if (IS_SKYLAKE(dev_priv) && !skl_can_enable_sagv(state))
+                        skl_disable_sagv(dev_priv);
+
                 intel_modeset_verify_disabled(dev);
         }
 
@@ -13757,6 +13839,10 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
                 intel_modeset_verify_crtc(crtc, old_crtc_state, crtc->state);
         }
 
+        if (IS_SKYLAKE(dev_priv) && intel_state->modeset &&
+            skl_can_enable_sagv(state))
+                skl_enable_sagv(dev_priv);
+
         drm_atomic_helper_commit_hw_done(state);
 
         if (intel_state->modeset)
@@ -16156,9 +16242,10 @@ void intel_display_resume(struct drm_device *dev)
         struct drm_atomic_state *state = dev_priv->modeset_restore_state;
         struct drm_modeset_acquire_ctx ctx;
         int ret;
-        bool setup = false;
 
         dev_priv->modeset_restore_state = NULL;
+        if (state)
+                state->acquire_ctx = &ctx;
 
         /*
          * This is a cludge because with real atomic modeset mode_config.mutex
@@ -16169,43 +16256,17 @@ void intel_display_resume(struct drm_device *dev)
         mutex_lock(&dev->mode_config.mutex);
         drm_modeset_acquire_init(&ctx, 0);
 
-retry:
-        ret = drm_modeset_lock_all_ctx(dev, &ctx);
-
-        if (ret == 0 && !setup) {
-                setup = true;
-
-                intel_modeset_setup_hw_state(dev);
-                i915_redisable_vga(dev);
-        }
-
-        if (ret == 0 && state) {
-                struct drm_crtc_state *crtc_state;
-                struct drm_crtc *crtc;
-                int i;
-
-                state->acquire_ctx = &ctx;
-
-                /* ignore any reset values/BIOS leftovers in the WM registers */
-                to_intel_atomic_state(state)->skip_intermediate_wm = true;
-
-                for_each_crtc_in_state(state, crtc, crtc_state, i) {
-                        /*
-                         * Force recalculation even if we restore
-                         * current state. With fast modeset this may not result
-                         * in a modeset when the state is compatible.
-                         */
-                        crtc_state->mode_changed = true;
-                }
-
-                ret = drm_atomic_commit(state);
-        }
+        while (1) {
+                ret = drm_modeset_lock_all_ctx(dev, &ctx);
+                if (ret != -EDEADLK)
+                        break;
 
-        if (ret == -EDEADLK) {
                 drm_modeset_backoff(&ctx);
-                goto retry;
         }
 
+        if (!ret)
+                ret = __intel_display_resume(dev, state);
+
         drm_modeset_drop_locks(&ctx);
         drm_modeset_acquire_fini(&ctx);
         mutex_unlock(&dev->mode_config.mutex);
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index cc937a19b1ba..ff399b9a5c1f 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1716,6 +1716,9 @@ void ilk_wm_get_hw_state(struct drm_device *dev);
 void skl_wm_get_hw_state(struct drm_device *dev);
 void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
                           struct skl_ddb_allocation *ddb /* out */);
+bool skl_can_enable_sagv(struct drm_atomic_state *state);
+int skl_enable_sagv(struct drm_i915_private *dev_priv);
+int skl_disable_sagv(struct drm_i915_private *dev_priv);
 uint32_t ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config);
 bool ilk_disable_lp_wm(struct drm_device *dev);
 int sanitize_rc6_option(struct drm_i915_private *dev_priv, int enable_rc6);
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index 6a7ad3ed1463..3836a1c79714 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -1230,12 +1230,29 @@ static int intel_sanitize_fbc_option(struct drm_i915_private *dev_priv)
         if (i915.enable_fbc >= 0)
                 return !!i915.enable_fbc;
 
+        if (!HAS_FBC(dev_priv))
+                return 0;
+
         if (IS_BROADWELL(dev_priv))
                 return 1;
 
         return 0;
 }
 
+static bool need_fbc_vtd_wa(struct drm_i915_private *dev_priv)
+{
+#ifdef CONFIG_INTEL_IOMMU
+        /* WaFbcTurnOffFbcWhenHyperVisorIsUsed:skl,bxt */
+        if (intel_iommu_gfx_mapped &&
+            (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv))) {
+                DRM_INFO("Disabling framebuffer compression (FBC) to prevent screen flicker with VT-d enabled\n");
+                return true;
+        }
+#endif
+
+        return false;
+}
+
 /**
  * intel_fbc_init - Initialize FBC
  * @dev_priv: the i915 device
@@ -1253,6 +1270,9 @@ void intel_fbc_init(struct drm_i915_private *dev_priv)
         fbc->active = false;
         fbc->work.scheduled = false;
 
+        if (need_fbc_vtd_wa(dev_priv))
+                mkwrite_device_info(dev_priv)->has_fbc = false;
+
         i915.enable_fbc = intel_sanitize_fbc_option(dev_priv);
         DRM_DEBUG_KMS("Sanitized enable_fbc value: %d\n", i915.enable_fbc);
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 97ba6c8cf907..53e13c10e4ea 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2852,6 +2852,7 @@ bool ilk_disable_lp_wm(struct drm_device *dev)
 
 #define SKL_DDB_SIZE            896     /* in blocks */
 #define BXT_DDB_SIZE            512
+#define SKL_SAGV_BLOCK_TIME     30 /* µs */
 
 /*
  * Return the index of a plane in the SKL DDB and wm result arrays.  Primary
@@ -2875,6 +2876,153 @@ skl_wm_plane_id(const struct intel_plane *plane)
         }
 }
 
+/*
+ * SAGV dynamically adjusts the system agent voltage and clock frequencies
+ * depending on power and performance requirements. The display engine access
+ * to system memory is blocked during the adjustment time. Because of the
+ * blocking time, having this enabled can cause full system hangs and/or pipe
+ * underruns if we don't meet all of the following requirements:
+ *
+ *  - <= 1 pipe enabled
+ *  - All planes can enable watermarks for latencies >= SAGV engine block time
+ *  - We're not using an interlaced display configuration
+ */
+int
+skl_enable_sagv(struct drm_i915_private *dev_priv)
+{
+        int ret;
+
+        if (dev_priv->skl_sagv_status == I915_SKL_SAGV_NOT_CONTROLLED ||
+            dev_priv->skl_sagv_status == I915_SKL_SAGV_ENABLED)
+                return 0;
+
+        DRM_DEBUG_KMS("Enabling the SAGV\n");
+        mutex_lock(&dev_priv->rps.hw_lock);
+
+        ret = sandybridge_pcode_write(dev_priv, GEN9_PCODE_SAGV_CONTROL,
+                                      GEN9_SAGV_ENABLE);
+
+        /* We don't need to wait for the SAGV when enabling */
+        mutex_unlock(&dev_priv->rps.hw_lock);
+
+        /*
+         * Some skl systems, pre-release machines in particular,
+         * don't actually have an SAGV.
+         */
+        if (ret == -ENXIO) {
+                DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n");
+                dev_priv->skl_sagv_status = I915_SKL_SAGV_NOT_CONTROLLED;
+                return 0;
+        } else if (ret < 0) {
+                DRM_ERROR("Failed to enable the SAGV\n");
+                return ret;
+        }
+
+        dev_priv->skl_sagv_status = I915_SKL_SAGV_ENABLED;
+        return 0;
+}
+
+static int
+skl_do_sagv_disable(struct drm_i915_private *dev_priv)
+{
+        int ret;
+        uint32_t temp = GEN9_SAGV_DISABLE;
+
+        ret = sandybridge_pcode_read(dev_priv, GEN9_PCODE_SAGV_CONTROL,
+                                     &temp);
+        if (ret)
+                return ret;
+        else
+                return temp & GEN9_SAGV_IS_DISABLED;
+}
+
+int
+skl_disable_sagv(struct drm_i915_private *dev_priv)
+{
+        int ret, result;
+
+        if (dev_priv->skl_sagv_status == I915_SKL_SAGV_NOT_CONTROLLED ||
+            dev_priv->skl_sagv_status == I915_SKL_SAGV_DISABLED)
+                return 0;
+
+        DRM_DEBUG_KMS("Disabling the SAGV\n");
+        mutex_lock(&dev_priv->rps.hw_lock);
+
+        /* bspec says to keep retrying for at least 1 ms */
+        ret = wait_for(result = skl_do_sagv_disable(dev_priv), 1);
+        mutex_unlock(&dev_priv->rps.hw_lock);
+
+        if (ret == -ETIMEDOUT) {
+                DRM_ERROR("Request to disable SAGV timed out\n");
+                return -ETIMEDOUT;
+        }
+
+        /*
+         * Some skl systems, pre-release machines in particular,
+         * don't actually have an SAGV.
+         */
+        if (result == -ENXIO) {
+                DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n");
+                dev_priv->skl_sagv_status = I915_SKL_SAGV_NOT_CONTROLLED;
+                return 0;
+        } else if (result < 0) {
+                DRM_ERROR("Failed to disable the SAGV\n");
+                return result;
+        }
+
+        dev_priv->skl_sagv_status = I915_SKL_SAGV_DISABLED;
+        return 0;
+}
+
+bool skl_can_enable_sagv(struct drm_atomic_state *state)
+{
+        struct drm_device *dev = state->dev;
+        struct drm_i915_private *dev_priv = to_i915(dev);
+        struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
+        struct drm_crtc *crtc;
+        enum pipe pipe;
+        int level, plane;
+
+        /*
+         * SKL workaround: bspec recommends we disable the SAGV when we have
+         * more then one pipe enabled
+         *
+         * If there are no active CRTCs, no additional checks need be performed
+         */
+        if (hweight32(intel_state->active_crtcs) == 0)
+                return true;
+        else if (hweight32(intel_state->active_crtcs) > 1)
+                return false;
+
+        /* Since we're now guaranteed to only have one active CRTC... */
+        pipe = ffs(intel_state->active_crtcs) - 1;
+        crtc = dev_priv->pipe_to_crtc_mapping[pipe];
+
+        if (crtc->state->mode.flags & DRM_MODE_FLAG_INTERLACE)
+                return false;
+
+        for_each_plane(dev_priv, pipe, plane) {
+                /* Skip this plane if it's not enabled */
+                if (intel_state->wm_results.plane[pipe][plane][0] == 0)
+                        continue;
+
+                /* Find the highest enabled wm level for this plane */
+                for (level = ilk_wm_max_level(dev);
+                     intel_state->wm_results.plane[pipe][plane][level] == 0; --level)
+                     { }
+
+                /*
+                 * If any of the planes on this pipe don't enable wm levels
+                 * that incur memory latencies higher then 30µs we can't enable
+                 * the SAGV
+                 */
+                if (dev_priv->wm.skl_latency[level] < SKL_SAGV_BLOCK_TIME)
+                        return false;
+        }
+
+        return true;
+}
+
 static void
 skl_ddb_get_pipe_allocation_limits(struct drm_device *dev,
                                    const struct intel_crtc_state *cstate,
@@ -3107,8 +3255,6 @@ skl_get_total_relative_data_rate(struct intel_crtc_state *intel_cstate)
                 total_data_rate += intel_cstate->wm.skl.plane_y_data_rate[id];
         }
 
-        WARN_ON(cstate->plane_mask && total_data_rate == 0);
-
         return total_data_rate;
 }
 
@@ -3344,6 +3490,8 @@ static uint32_t skl_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal,
                 plane_bytes_per_line *= 4;
                 plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512);
                 plane_blocks_per_line /= 4;
+        } else if (tiling == DRM_FORMAT_MOD_NONE) {
+                plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512) + 1;
         } else {
                 plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512);
         }
@@ -3910,9 +4058,24 @@ skl_compute_ddb(struct drm_atomic_state *state)
          * pretend that all pipes switched active status so that we'll
          * ensure a full DDB recompute.
          */
-        if (dev_priv->wm.distrust_bios_wm)
+        if (dev_priv->wm.distrust_bios_wm) {
+                ret = drm_modeset_lock(&dev->mode_config.connection_mutex,
+                                       state->acquire_ctx);
+                if (ret)
+                        return ret;
+
                 intel_state->active_pipe_changes = ~0;
 
+                /*
+                 * We usually only initialize intel_state->active_crtcs if we
+                 * we're doing a modeset; make sure this field is always
+                 * initialized during the sanitization process that happens
+                 * on the first commit too.
+                 */
+                if (!intel_state->modeset)
+                        intel_state->active_crtcs = dev_priv->active_crtcs;
+        }
+
         /*
          * If the modeset changes which CRTC's are active, we need to
          * recompute the DDB allocation for *all* active pipes, even
@@ -3941,11 +4104,33 @@ skl_compute_ddb(struct drm_atomic_state *state)
                 ret = skl_allocate_pipe_ddb(cstate, ddb);
                 if (ret)
                         return ret;
+
+                ret = drm_atomic_add_affected_planes(state, &intel_crtc->base);
+                if (ret)
+                        return ret;
         }
 
         return 0;
 }
 
+static void
+skl_copy_wm_for_pipe(struct skl_wm_values *dst,
+                     struct skl_wm_values *src,
+                     enum pipe pipe)
+{
+        dst->wm_linetime[pipe] = src->wm_linetime[pipe];
+        memcpy(dst->plane[pipe], src->plane[pipe],
+               sizeof(dst->plane[pipe]));
+        memcpy(dst->plane_trans[pipe], src->plane_trans[pipe],
+               sizeof(dst->plane_trans[pipe]));
+
+        dst->ddb.pipe[pipe] = src->ddb.pipe[pipe];
+        memcpy(dst->ddb.y_plane[pipe], src->ddb.y_plane[pipe],
+               sizeof(dst->ddb.y_plane[pipe]));
+        memcpy(dst->ddb.plane[pipe], src->ddb.plane[pipe],
+               sizeof(dst->ddb.plane[pipe]));
+}
+
 static int
 skl_compute_wm(struct drm_atomic_state *state)
 {
@@ -4018,8 +4203,10 @@ static void skl_update_wm(struct drm_crtc *crtc)
         struct drm_device *dev = crtc->dev;
         struct drm_i915_private *dev_priv = to_i915(dev);
         struct skl_wm_values *results = &dev_priv->wm.skl_results;
+        struct skl_wm_values *hw_vals = &dev_priv->wm.skl_hw;
         struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state);
         struct skl_pipe_wm *pipe_wm = &cstate->wm.skl.optimal;
+        int pipe;
 
         if ((results->dirty_pipes & drm_crtc_mask(crtc)) == 0)
                 return;
@@ -4031,8 +4218,12 @@ static void skl_update_wm(struct drm_crtc *crtc)
         skl_write_wm_values(dev_priv, results);
         skl_flush_wm_values(dev_priv, results);
 
-        /* store the new configuration */
-        dev_priv->wm.skl_hw = *results;
+        /*
+         * Store the new configuration (but only for the pipes that have
+         * changed; the other values weren't recomputed).
+         */
+        for_each_pipe_masked(dev_priv, pipe, results->dirty_pipes)
+                skl_copy_wm_for_pipe(hw_vals, results, pipe);
 
         mutex_unlock(&dev_priv->wm.wm_mutex);
 }
@@ -6574,9 +6765,7 @@ void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
 
 void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv)
 {
-        if (IS_CHERRYVIEW(dev_priv))
-                return;
-        else if (IS_VALLEYVIEW(dev_priv))
+        if (IS_VALLEYVIEW(dev_priv))
                 valleyview_cleanup_gt_powersave(dev_priv);
 
         if (!i915.enable_rc6)
@@ -7658,8 +7847,53 @@ void intel_init_pm(struct drm_device *dev)
         }
 }
 
+static inline int gen6_check_mailbox_status(struct drm_i915_private *dev_priv)
+{
+        uint32_t flags =
+                I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_ERROR_MASK;
+
+        switch (flags) {
+        case GEN6_PCODE_SUCCESS:
+                return 0;
+        case GEN6_PCODE_UNIMPLEMENTED_CMD:
+        case GEN6_PCODE_ILLEGAL_CMD:
+                return -ENXIO;
+        case GEN6_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE:
+                return -EOVERFLOW;
+        case GEN6_PCODE_TIMEOUT:
+                return -ETIMEDOUT;
+        default:
+                MISSING_CASE(flags)
+                return 0;
+        }
+}
+
+static inline int gen7_check_mailbox_status(struct drm_i915_private *dev_priv)
+{
+        uint32_t flags =
+                I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_ERROR_MASK;
+
+        switch (flags) {
+        case GEN6_PCODE_SUCCESS:
+                return 0;
+        case GEN6_PCODE_ILLEGAL_CMD:
+                return -ENXIO;
+        case GEN7_PCODE_TIMEOUT:
+                return -ETIMEDOUT;
+        case GEN7_PCODE_ILLEGAL_DATA:
+                return -EINVAL;
+        case GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE:
+                return -EOVERFLOW;
+        default:
+                MISSING_CASE(flags);
+                return 0;
+        }
+}
+
 int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val)
 {
+        int status;
+
         WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 
         /* GEN6_PCODE_* are outside of the forcewake domain, we can
@@ -7686,12 +7920,25 @@ int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val
         *val = I915_READ_FW(GEN6_PCODE_DATA);
         I915_WRITE_FW(GEN6_PCODE_DATA, 0);
 
+        if (INTEL_GEN(dev_priv) > 6)
+                status = gen7_check_mailbox_status(dev_priv);
+        else
+                status = gen6_check_mailbox_status(dev_priv);
+
+        if (status) {
+                DRM_DEBUG_DRIVER("warning: pcode (read) mailbox access failed: %d\n",
+                                 status);
+                return status;
+        }
+
         return 0;
 }
 
 int sandybridge_pcode_write(struct drm_i915_private *dev_priv,
-                               u32 mbox, u32 val)
+                            u32 mbox, u32 val)
 {
+        int status;
+
         WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 
         /* GEN6_PCODE_* are outside of the forcewake domain, we can
@@ -7716,6 +7963,17 @@ int sandybridge_pcode_write(struct drm_i915_private *dev_priv,
 
         I915_WRITE_FW(GEN6_PCODE_DATA, 0);
 
+        if (INTEL_GEN(dev_priv) > 6)
+                status = gen7_check_mailbox_status(dev_priv);
+        else
+                status = gen6_check_mailbox_status(dev_priv);
+
+        if (status) {
+                DRM_DEBUG_DRIVER("warning: pcode (write) mailbox access failed: %d\n",
+                                 status);
+                return status;
+        }
+
         return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index cca7792f26d5..1d3161bbea24 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1178,8 +1178,8 @@ static int bxt_init_workarounds(struct intel_engine_cs *engine)
                 I915_WRITE(GEN8_L3SQCREG1, L3_GENERAL_PRIO_CREDITS(62) |
                                            L3_HIGH_PRIO_CREDITS(2));
 
-        /* WaInsertDummyPushConstPs:bxt */
-        if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0))
+        /* WaToEnableHwFixForPushConstHWBug:bxt */
+        if (IS_BXT_REVID(dev_priv, BXT_REVID_C0, REVID_FOREVER))
                 WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
                                   GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
 
@@ -1222,8 +1222,8 @@ static int kbl_init_workarounds(struct intel_engine_cs *engine)
                 I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) |
                            GEN8_LQSC_RO_PERF_DIS);
 
-        /* WaInsertDummyPushConstPs:kbl */
-        if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0))
+        /* WaToEnableHwFixForPushConstHWBug:kbl */
+        if (IS_KBL_REVID(dev_priv, KBL_REVID_C0, REVID_FOREVER))
                 WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
                                   GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
 
diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index 9f7dafce3a4c..7bf90e9e6139 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -171,10 +171,34 @@ static void imx_drm_output_poll_changed(struct drm_device *drm)
         drm_fbdev_cma_hotplug_event(imxdrm->fbhelper);
 }
 
+static int imx_drm_atomic_check(struct drm_device *dev,
+                                struct drm_atomic_state *state)
+{
+        int ret;
+
+        ret = drm_atomic_helper_check_modeset(dev, state);
+        if (ret)
+                return ret;
+
+        ret = drm_atomic_helper_check_planes(dev, state);
+        if (ret)
+                return ret;
+
+        /*
+         * Check modeset again in case crtc_state->mode_changed is
+         * updated in plane's ->atomic_check callback.
+         */
+        ret = drm_atomic_helper_check_modeset(dev, state);
+        if (ret)
+                return ret;
+
+        return ret;
+}
+
 static const struct drm_mode_config_funcs imx_drm_mode_config_funcs = {
         .fb_create = drm_fb_cma_create,
         .output_poll_changed = imx_drm_output_poll_changed,
-        .atomic_check = drm_atomic_helper_check,
+        .atomic_check = imx_drm_atomic_check,
         .atomic_commit = drm_atomic_helper_commit,
 };
 
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index 08e188bc10fc..462056e4b9e4 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -76,6 +76,8 @@ static void ipu_crtc_disable(struct drm_crtc *crtc)
                 crtc->state->event = NULL;
         }
         spin_unlock_irq(&crtc->dev->event_lock);
+
+        drm_crtc_vblank_off(crtc);
 }
 
 static void imx_drm_crtc_reset(struct drm_crtc *crtc)
@@ -175,6 +177,8 @@ static int ipu_crtc_atomic_check(struct drm_crtc *crtc,
 static void ipu_crtc_atomic_begin(struct drm_crtc *crtc,
                                   struct drm_crtc_state *old_crtc_state)
 {
+        drm_crtc_vblank_on(crtc);
+
         spin_lock_irq(&crtc->dev->event_lock);
         if (crtc->state->event) {
                 WARN_ON(drm_crtc_vblank_get(crtc));
diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c
index 4ad67d015ec7..29423e757d36 100644
--- a/drivers/gpu/drm/imx/ipuv3-plane.c
+++ b/drivers/gpu/drm/imx/ipuv3-plane.c
@@ -319,13 +319,14 @@ static int ipu_plane_atomic_check(struct drm_plane *plane,
                 return -EINVAL;
 
         /*
-         * since we cannot touch active IDMAC channels, we do not support
-         * resizing the enabled plane or changing its format
+         * We support resizing active plane or changing its format by
+         * forcing CRTC mode change and disabling-enabling plane in plane's
+         * ->atomic_update callback.
          */
         if (old_fb && (state->src_w != old_state->src_w ||
                               state->src_h != old_state->src_h ||
                               fb->pixel_format != old_fb->pixel_format))
-                return -EINVAL;
+                crtc_state->mode_changed = true;
 
         eba = drm_plane_state_to_eba(state);
 
@@ -336,7 +337,7 @@ static int ipu_plane_atomic_check(struct drm_plane *plane,
                 return -EINVAL;
 
         if (old_fb && fb->pitches[0] != old_fb->pitches[0])
-                return -EINVAL;
+                crtc_state->mode_changed = true;
 
         switch (fb->pixel_format) {
         case DRM_FORMAT_YUV420:
@@ -372,7 +373,7 @@ static int ipu_plane_atomic_check(struct drm_plane *plane,
                         return -EINVAL;
 
                 if (old_fb && old_fb->pitches[1] != fb->pitches[1])
-                        return -EINVAL;
+                        crtc_state->mode_changed = true;
         }
 
         return 0;
@@ -392,8 +393,14 @@ static void ipu_plane_atomic_update(struct drm_plane *plane,
         enum ipu_color_space ics;
 
         if (old_state->fb) {
-                ipu_plane_atomic_set_base(ipu_plane, old_state);
-                return;
+                struct drm_crtc_state *crtc_state = state->crtc->state;
+
+                if (!crtc_state->mode_changed) {
+                        ipu_plane_atomic_set_base(ipu_plane, old_state);
+                        return;
+                }
+
+                ipu_disable_plane(plane);
         }
 
         switch (ipu_plane->dp_flow) {
diff --git a/drivers/gpu/drm/mediatek/Kconfig b/drivers/gpu/drm/mediatek/Kconfig
index 23ac8041c562..294de4549922 100644
--- a/drivers/gpu/drm/mediatek/Kconfig
+++ b/drivers/gpu/drm/mediatek/Kconfig
@@ -2,6 +2,9 @@ config DRM_MEDIATEK
         tristate "DRM Support for Mediatek SoCs"
         depends on DRM
         depends on ARCH_MEDIATEK || (ARM && COMPILE_TEST)
+        depends on COMMON_CLK
+        depends on HAVE_ARM_SMCCC
+        depends on OF
         select DRM_GEM_CMA_HELPER
         select DRM_KMS_HELPER
         select DRM_MIPI_DSI
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index b4bc7f1ef717..d0da52f2a806 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -157,6 +157,12 @@ struct msm_drm_private {
         struct shrinker shrinker;
 
         struct msm_vblank_ctrl vblank_ctrl;
+
+        /* task holding struct_mutex.. currently only used in submit path
+         * to detect and reject faults from copy_from_user() for submit
+         * ioctl.
+         */
+        struct task_struct *struct_mutex_task;
 };
 
 struct msm_format {
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 6cd4af443139..85f3047e05ae 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -196,11 +196,20 @@ int msm_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
         struct drm_gem_object *obj = vma->vm_private_data;
         struct drm_device *dev = obj->dev;
+        struct msm_drm_private *priv = dev->dev_private;
         struct page **pages;
         unsigned long pfn;
         pgoff_t pgoff;
         int ret;
 
+        /* This should only happen if userspace tries to pass a mmap'd
+         * but unfaulted gem bo vaddr into submit ioctl, triggering
+         * a page fault while struct_mutex is already held.  This is
+         * not a valid use-case so just bail.
+         */
+        if (priv->struct_mutex_task == current)
+                return VM_FAULT_SIGBUS;
+
         /* Make sure we don't parallel update on a fault, nor move or remove
          * something from beneath our feet
          */
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 9766f9ae4b7d..880d6a9af7c8 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -64,6 +64,14 @@ void msm_gem_submit_free(struct msm_gem_submit *submit)
         kfree(submit);
 }
 
+static inline unsigned long __must_check
+copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
+{
+        if (access_ok(VERIFY_READ, from, n))
+                return __copy_from_user_inatomic(to, from, n);
+        return -EFAULT;
+}
+
 static int submit_lookup_objects(struct msm_gem_submit *submit,
                 struct drm_msm_gem_submit *args, struct drm_file *file)
 {
@@ -71,6 +79,7 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
         int ret = 0;
 
         spin_lock(&file->table_lock);
+        pagefault_disable();
 
         for (i = 0; i < args->nr_bos; i++) {
                 struct drm_msm_gem_submit_bo submit_bo;
@@ -84,10 +93,15 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
                  */
                 submit->bos[i].flags = 0;
 
-                ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo));
-                if (ret) {
-                        ret = -EFAULT;
-                        goto out_unlock;
+                ret = copy_from_user_inatomic(&submit_bo, userptr, sizeof(submit_bo));
+                if (unlikely(ret)) {
+                        pagefault_enable();
+                        spin_unlock(&file->table_lock);
+                        ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo));
+                        if (ret)
+                                goto out;
+                        spin_lock(&file->table_lock);
+                        pagefault_disable();
                 }
 
                 if (submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) {
@@ -127,9 +141,12 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
         }
 
 out_unlock:
-        submit->nr_bos = i;
+        pagefault_enable();
         spin_unlock(&file->table_lock);
 
+out:
+        submit->nr_bos = i;
+
         return ret;
 }
 
@@ -377,6 +394,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
         if (ret)
                 return ret;
 
+        priv->struct_mutex_task = current;
+
         submit = submit_create(dev, gpu, args->nr_bos, args->nr_cmds);
         if (!submit) {
                 ret = -ENOMEM;
@@ -468,6 +487,7 @@ out:
         if (ret)
                 msm_gem_submit_free(submit);
 out_unlock:
+        priv->struct_mutex_task = NULL;
         mutex_unlock(&dev->struct_mutex);
         return ret;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index f2ad17aa33f0..dc57b628e074 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -225,6 +225,17 @@ static bool nouveau_pr3_present(struct pci_dev *pdev)
         if (!parent_pdev)
                 return false;
 
+        if (!parent_pdev->bridge_d3) {
+                /*
+                 * Parent PCI bridge is currently not power managed.
+                 * Since userspace can change these afterwards to be on
+                 * the safe side we stick with _DSM and prevent usage of
+                 * _PR3 from the bridge.
+                 */
+                pci_d3cold_disable(pdev);
+                return false;
+        }
+
         parent_adev = ACPI_COMPANION(&parent_pdev->dev);
         if (!parent_adev)
                 return false;
diff --git a/drivers/gpu/drm/qxl/qxl_fb.c b/drivers/gpu/drm/qxl/qxl_fb.c
index df2657051afd..28c1423049c5 100644
--- a/drivers/gpu/drm/qxl/qxl_fb.c
+++ b/drivers/gpu/drm/qxl/qxl_fb.c
@@ -73,10 +73,12 @@ static void qxl_fb_image_init(struct qxl_fb_image *qxl_fb_image,
         }
 }
 
+#ifdef CONFIG_DRM_FBDEV_EMULATION
 static struct fb_deferred_io qxl_defio = {
         .delay          = QXL_DIRTY_DELAY,
         .deferred_io    = drm_fb_helper_deferred_io,
 };
+#endif
 
 static struct fb_ops qxlfb_ops = {
         .owner = THIS_MODULE,
@@ -313,8 +315,10 @@ static int qxlfb_create(struct qxl_fbdev *qfbdev,
                 goto out_destroy_fbi;
         }
 
+#ifdef CONFIG_DRM_FBDEV_EMULATION
         info->fbdefio = &qxl_defio;
         fb_deferred_io_init(info);
+#endif
 
         qdev->fbdev_info = info;
         qdev->fbdev_qfb = &qfbdev->qfb;
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index a97abc8af657..1dcf39084555 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -627,7 +627,9 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc,
                         if (radeon_crtc->ss.refdiv) {
                                 radeon_crtc->pll_flags |= RADEON_PLL_USE_REF_DIV;
                                 radeon_crtc->pll_reference_div = radeon_crtc->ss.refdiv;
-                                if (rdev->family >= CHIP_RV770)
+                                if (ASIC_IS_AVIVO(rdev) &&
+                                    rdev->family != CHIP_RS780 &&
+                                    rdev->family != CHIP_RS880)
                                         radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV;
                         }
                 }
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index 6de342861202..ddef0d494084 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -198,16 +198,7 @@ static int radeon_atpx_validate(struct radeon_atpx *atpx)
         atpx->is_hybrid = false;
         if (valid_bits & ATPX_MS_HYBRID_GFX_SUPPORTED) {
                 printk("ATPX Hybrid Graphics\n");
-#if 1
-                /* This is a temporary hack until the D3 cold support
-                 * makes it upstream.  The ATPX power_control method seems
-                 * to still work on even if the system should be using
-                 * the new standardized hybrid D3 cold ACPI interface.
-                 */
-                atpx->functions.power_cntl = true;
-#else
                 atpx->functions.power_cntl = false;
-#endif
                 atpx->is_hybrid = true;
         }
 
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 0c00e192c845..c2e0a1ccdfbc 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -263,8 +263,8 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 
         rdev = radeon_get_rdev(bo->bdev);
         ridx = radeon_copy_ring_index(rdev);
-        old_start = old_mem->start << PAGE_SHIFT;
-        new_start = new_mem->start << PAGE_SHIFT;
+        old_start = (u64)old_mem->start << PAGE_SHIFT;
+        new_start = (u64)new_mem->start << PAGE_SHIFT;
 
         switch (old_mem->mem_type) {
         case TTM_PL_VRAM:
diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c
index 3d228ad90e0f..3dea1216bafd 100644
--- a/drivers/gpu/drm/tegra/dsi.c
+++ b/drivers/gpu/drm/tegra/dsi.c
@@ -840,6 +840,21 @@ static const struct drm_encoder_funcs tegra_dsi_encoder_funcs = {
         .destroy = tegra_output_encoder_destroy,
 };
 
+static void tegra_dsi_unprepare(struct tegra_dsi *dsi)
+{
+        int err;
+
+        if (dsi->slave)
+                tegra_dsi_unprepare(dsi->slave);
+
+        err = tegra_mipi_disable(dsi->mipi);
+        if (err < 0)
+                dev_err(dsi->dev, "failed to disable MIPI calibration: %d\n",
+                        err);
+
+        pm_runtime_put(dsi->dev);
+}
+
 static void tegra_dsi_encoder_disable(struct drm_encoder *encoder)
 {
         struct tegra_output *output = encoder_to_output(encoder);
@@ -876,7 +891,26 @@ static void tegra_dsi_encoder_disable(struct drm_encoder *encoder)
 
         tegra_dsi_disable(dsi);
 
-        pm_runtime_put(dsi->dev);
+        tegra_dsi_unprepare(dsi);
+}
+
+static void tegra_dsi_prepare(struct tegra_dsi *dsi)
+{
+        int err;
+
+        pm_runtime_get_sync(dsi->dev);
+
+        err = tegra_mipi_enable(dsi->mipi);
+        if (err < 0)
+                dev_err(dsi->dev, "failed to enable MIPI calibration: %d\n",
+                        err);
+
+        err = tegra_dsi_pad_calibrate(dsi);
+        if (err < 0)
+                dev_err(dsi->dev, "MIPI calibration failed: %d\n", err);
+
+        if (dsi->slave)
+                tegra_dsi_prepare(dsi->slave);
 }
 
 static void tegra_dsi_encoder_enable(struct drm_encoder *encoder)
@@ -887,13 +921,8 @@ static void tegra_dsi_encoder_enable(struct drm_encoder *encoder)
         struct tegra_dsi *dsi = to_dsi(output);
         struct tegra_dsi_state *state;
         u32 value;
-        int err;
-
-        pm_runtime_get_sync(dsi->dev);
 
-        err = tegra_dsi_pad_calibrate(dsi);
-        if (err < 0)
-                dev_err(dsi->dev, "MIPI calibration failed: %d\n", err);
+        tegra_dsi_prepare(dsi);
 
         state = tegra_dsi_get_state(dsi);
 
diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c
index d5df555aeba0..9688bfa92ccd 100644
--- a/drivers/gpu/drm/udl/udl_fb.c
+++ b/drivers/gpu/drm/udl/udl_fb.c
@@ -203,6 +203,7 @@ static int udl_fb_open(struct fb_info *info, int user)
 
         ufbdev->fb_count++;
 
+#ifdef CONFIG_DRM_FBDEV_EMULATION
         if (fb_defio && (info->fbdefio == NULL)) {
                 /* enable defio at last moment if not disabled by client */
 
@@ -218,6 +219,7 @@ static int udl_fb_open(struct fb_info *info, int user)
                 info->fbdefio = fbdefio;
                 fb_deferred_io_init(info);
         }
+#endif
 
         pr_notice("open /dev/fb%d user=%d fb_info=%p count=%d\n",
                   info->node, user, info, ufbdev->fb_count);
@@ -235,12 +237,14 @@ static int udl_fb_release(struct fb_info *info, int user)
 
         ufbdev->fb_count--;
 
+#ifdef CONFIG_DRM_FBDEV_EMULATION
         if ((ufbdev->fb_count == 0) && (info->fbdefio)) {
                 fb_deferred_io_cleanup(info);
                 kfree(info->fbdefio);
                 info->fbdefio = NULL;
                 info->fbops->fb_mmap = udl_fb_mmap;
         }
+#endif
 
         pr_warn("released /dev/fb%d user=%d count=%d\n",
                 info->node, user, ufbdev->fb_count);
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 8b42d31a7f0e..9ecef9385491 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -57,21 +57,21 @@ static int vc4_get_param_ioctl(struct drm_device *dev, void *data,
         switch (args->param) {
         case DRM_VC4_PARAM_V3D_IDENT0:
                 ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev);
-                if (ret)
+                if (ret < 0)
                         return ret;
                 args->value = V3D_READ(V3D_IDENT0);
                 pm_runtime_put(&vc4->v3d->pdev->dev);
                 break;
         case DRM_VC4_PARAM_V3D_IDENT1:
                 ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev);
-                if (ret)
+                if (ret < 0)
                         return ret;
                 args->value = V3D_READ(V3D_IDENT1);
                 pm_runtime_put(&vc4->v3d->pdev->dev);
                 break;
         case DRM_VC4_PARAM_V3D_IDENT2:
                 ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev);
-                if (ret)
+                if (ret < 0)
                         return ret;
                 args->value = V3D_READ(V3D_IDENT2);
                 pm_runtime_put(&vc4->v3d->pdev->dev);
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 489e3de0c050..428e24919ef1 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -321,6 +321,15 @@ vc4_first_render_job(struct vc4_dev *vc4)
                                 struct vc4_exec_info, head);
 }
 
+static inline struct vc4_exec_info *
+vc4_last_render_job(struct vc4_dev *vc4)
+{
+        if (list_empty(&vc4->render_job_list))
+                return NULL;
+        return list_last_entry(&vc4->render_job_list,
+                               struct vc4_exec_info, head);
+}
+
 /**
  * struct vc4_texture_sample_info - saves the offsets into the UBO for texture
  * setup parameters.
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 6155e8aca1c6..b262c5c26f10 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -534,8 +534,8 @@ vc4_cl_lookup_bos(struct drm_device *dev,
                 return -EINVAL;
         }
 
-        exec->bo = kcalloc(exec->bo_count, sizeof(struct drm_gem_cma_object *),
-                           GFP_KERNEL);
+        exec->bo = drm_calloc_large(exec->bo_count,
+                                    sizeof(struct drm_gem_cma_object *));
         if (!exec->bo) {
                 DRM_ERROR("Failed to allocate validated BO pointers\n");
                 return -ENOMEM;
@@ -572,8 +572,8 @@ vc4_cl_lookup_bos(struct drm_device *dev,
         spin_unlock(&file_priv->table_lock);
 
 fail:
-        kfree(handles);
-        return 0;
+        drm_free_large(handles);
+        return ret;
 }
 
 static int
@@ -608,7 +608,7 @@ vc4_get_bcl(struct drm_device *dev, struct vc4_exec_info *exec)
          * read the contents back for validation, and I think the
          * bo->vaddr is uncached access.
          */
-        temp = kmalloc(temp_size, GFP_KERNEL);
+        temp = drm_malloc_ab(temp_size, 1);
         if (!temp) {
                 DRM_ERROR("Failed to allocate storage for copying "
                           "in bin/render CLs.\n");
@@ -675,7 +675,7 @@ vc4_get_bcl(struct drm_device *dev, struct vc4_exec_info *exec)
         ret = vc4_validate_shader_recs(dev, exec);
 
 fail:
-        kfree(temp);
+        drm_free_large(temp);
         return ret;
 }
 
@@ -688,7 +688,7 @@ vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec)
         if (exec->bo) {
                 for (i = 0; i < exec->bo_count; i++)
                         drm_gem_object_unreference_unlocked(&exec->bo[i]->base);
-                kfree(exec->bo);
+                drm_free_large(exec->bo);
         }
 
         while (!list_empty(&exec->unref_list)) {
@@ -942,8 +942,8 @@ vc4_gem_destroy(struct drm_device *dev)
                 vc4->overflow_mem = NULL;
         }
 
-        vc4_bo_cache_destroy(dev);
-
         if (vc4->hang_state)
                 vc4_free_hang_state(dev, vc4->hang_state);
+
+        vc4_bo_cache_destroy(dev);
 }
diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c
index b0104a346a74..094bc6a475c1 100644
--- a/drivers/gpu/drm/vc4/vc4_irq.c
+++ b/drivers/gpu/drm/vc4/vc4_irq.c
@@ -83,8 +83,10 @@ vc4_overflow_mem_work(struct work_struct *work)
 
                 spin_lock_irqsave(&vc4->job_lock, irqflags);
                 current_exec = vc4_first_bin_job(vc4);
+                if (!current_exec)
+                        current_exec = vc4_last_render_job(vc4);
                 if (current_exec) {
-                        vc4->overflow_mem->seqno = vc4->finished_seqno + 1;
+                        vc4->overflow_mem->seqno = current_exec->seqno;
                         list_add_tail(&vc4->overflow_mem->unref_head,
                                       &current_exec->unref_list);
                         vc4->overflow_mem = NULL;
diff --git a/drivers/gpu/host1x/mipi.c b/drivers/gpu/host1x/mipi.c
index 52a6fd224127..e00809d996a2 100644
--- a/drivers/gpu/host1x/mipi.c
+++ b/drivers/gpu/host1x/mipi.c
@@ -242,20 +242,6 @@ struct tegra_mipi_device *tegra_mipi_request(struct device *device)
         dev->pads = args.args[0];
         dev->device = device;
 
-        mutex_lock(&dev->mipi->lock);
-
-        if (dev->mipi->usage_count++ == 0) {
-                err = tegra_mipi_power_up(dev->mipi);
-                if (err < 0) {
-                        dev_err(dev->mipi->dev,
-                                "failed to power up MIPI bricks: %d\n",
-                                err);
-                        return ERR_PTR(err);
-                }
-        }
-
-        mutex_unlock(&dev->mipi->lock);
-
         return dev;
 
 put:
@@ -270,29 +256,42 @@ EXPORT_SYMBOL(tegra_mipi_request);
 
 void tegra_mipi_free(struct tegra_mipi_device *device)
 {
-        int err;
+        platform_device_put(device->pdev);
+        kfree(device);
+}
+EXPORT_SYMBOL(tegra_mipi_free);
 
-        mutex_lock(&device->mipi->lock);
+int tegra_mipi_enable(struct tegra_mipi_device *dev)
+{
+        int err = 0;
 
-        if (--device->mipi->usage_count == 0) {
-                err = tegra_mipi_power_down(device->mipi);
-                if (err < 0) {
-                        /*
-                         * Not much that can be done here, so an error message
-                         * will have to do.
-                         */
-                        dev_err(device->mipi->dev,
-                                "failed to power down MIPI bricks: %d\n",
-                                err);
-                }
-        }
+        mutex_lock(&dev->mipi->lock);
 
-        mutex_unlock(&device->mipi->lock);
+        if (dev->mipi->usage_count++ == 0)
+                err = tegra_mipi_power_up(dev->mipi);
+
+        mutex_unlock(&dev->mipi->lock);
+
+        return err;
 
-        platform_device_put(device->pdev);
-        kfree(device);
 }
-EXPORT_SYMBOL(tegra_mipi_free);
+EXPORT_SYMBOL(tegra_mipi_enable);
+
+int tegra_mipi_disable(struct tegra_mipi_device *dev)
+{
+        int err = 0;
+
+        mutex_lock(&dev->mipi->lock);
+
+        if (--dev->mipi->usage_count == 0)
+                err = tegra_mipi_power_down(dev->mipi);
+
+        mutex_unlock(&dev->mipi->lock);
+
+        return err;
+
+}
+EXPORT_SYMBOL(tegra_mipi_disable);
 
 static int tegra_mipi_wait(struct tegra_mipi *mipi)
 {