30 files changed, 387 insertions, 91 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 251b14736de9..5a5f04d0902d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -539,6 +539,7 @@ struct amdgpu_bo {
         /* Constant after initialization */
         struct amdgpu_device            *adev;
         struct drm_gem_object           gem_base;
+        struct amdgpu_bo                *parent;
 
         struct ttm_bo_kmap_obj          dma_buf_vmap;
         pid_t                           pid;
@@ -955,6 +956,8 @@ struct amdgpu_vm {
         struct amdgpu_vm_id     ids[AMDGPU_MAX_RINGS];
         /* for interval tree */
         spinlock_t              it_lock;
+        /* protecting freed */
+        spinlock_t              freed_lock;
 };
 
 struct amdgpu_vm_manager {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 1d44d508d4d4..4f352ec9dec4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -222,6 +222,8 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
                                 }
 
                                 p->uf.bo = gem_to_amdgpu_bo(gobj);
+                                amdgpu_bo_ref(p->uf.bo);
+                                drm_gem_object_unreference_unlocked(gobj);
                                 p->uf.offset = fence_data->offset;
                         } else {
                                 ret = -EINVAL;
@@ -487,7 +489,7 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, bo
                         amdgpu_ib_free(parser->adev, &parser->ibs[i]);
         kfree(parser->ibs);
         if (parser->uf.bo)
-                drm_gem_object_unreference_unlocked(&parser->uf.bo->gem_base);
+                amdgpu_bo_unref(&parser->uf.bo);
 }
 
 static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p,
@@ -776,7 +778,7 @@ static int amdgpu_cs_free_job(struct amdgpu_job *job)
                         amdgpu_ib_free(job->adev, &job->ibs[i]);
         kfree(job->ibs);
         if (job->uf.bo)
-                drm_gem_object_unreference_unlocked(&job->uf.bo->gem_base);
+                amdgpu_bo_unref(&job->uf.bo);
         return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index e173a5a02f0d..5580d3420c3a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -73,6 +73,8 @@ static void amdgpu_flip_work_func(struct work_struct *__work)
         struct drm_crtc *crtc = &amdgpuCrtc->base;
         unsigned long flags;
         unsigned i;
+        int vpos, hpos, stat, min_udelay;
+        struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id];
 
         amdgpu_flip_wait_fence(adev, &work->excl);
         for (i = 0; i < work->shared_count; ++i)
@@ -81,6 +83,41 @@ static void amdgpu_flip_work_func(struct work_struct *__work)
         /* We borrow the event spin lock for protecting flip_status */
         spin_lock_irqsave(&crtc->dev->event_lock, flags);
 
+        /* If this happens to execute within the "virtually extended" vblank
+         * interval before the start of the real vblank interval then it needs
+         * to delay programming the mmio flip until the real vblank is entered.
+         * This prevents completing a flip too early due to the way we fudge
+         * our vblank counter and vblank timestamps in order to work around the
+         * problem that the hw fires vblank interrupts before actual start of
+         * vblank (when line buffer refilling is done for a frame). It
+         * complements the fudging logic in amdgpu_get_crtc_scanoutpos() for
+         * timestamping and amdgpu_get_vblank_counter_kms() for vblank counts.
+         *
+         * In practice this won't execute very often unless on very fast
+         * machines because the time window for this to happen is very small.
+         */
+        for (;;) {
+                /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank
+                 * start in hpos, and to the "fudged earlier" vblank start in
+                 * vpos.
+                 */
+                stat = amdgpu_get_crtc_scanoutpos(adev->ddev, work->crtc_id,
+                                                  GET_DISTANCE_TO_VBLANKSTART,
+                                                  &vpos, &hpos, NULL, NULL,
+                                                  &crtc->hwmode);
+
+                if ((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) !=
+                    (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE) ||
+                    !(vpos >= 0 && hpos <= 0))
+                        break;
+
+                /* Sleep at least until estimated real start of hw vblank */
+                spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+                min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5);
+                usleep_range(min_udelay, 2 * min_udelay);
+                spin_lock_irqsave(&crtc->dev->event_lock, flags);
+        };
+
         /* do the flip (mmio) */
         adev->mode_info.funcs->page_flip(adev, work->crtc_id, work->base);
         /* set the flip status */
@@ -109,7 +146,7 @@ static void amdgpu_unpin_work_func(struct work_struct *__work)
         } else
                 DRM_ERROR("failed to reserve buffer after flip\n");
 
-        drm_gem_object_unreference_unlocked(&work->old_rbo->gem_base);
+        amdgpu_bo_unref(&work->old_rbo);
         kfree(work->shared);
         kfree(work);
 }
@@ -148,8 +185,8 @@ int amdgpu_crtc_page_flip(struct drm_crtc *crtc,
         obj = old_amdgpu_fb->obj;
 
         /* take a reference to the old object */
-        drm_gem_object_reference(obj);
         work->old_rbo = gem_to_amdgpu_bo(obj);
+        amdgpu_bo_ref(work->old_rbo);
 
         new_amdgpu_fb = to_amdgpu_framebuffer(fb);
         obj = new_amdgpu_fb->obj;
@@ -222,7 +259,7 @@ pflip_cleanup:
         amdgpu_bo_unreserve(new_rbo);
 
 cleanup:
-        drm_gem_object_unreference_unlocked(&work->old_rbo->gem_base);
+        amdgpu_bo_unref(&work->old_rbo);
         fence_put(work->excl);
         for (i = 0; i < work->shared_count; ++i)
                 fence_put(work->shared[i]);
@@ -712,6 +749,15 @@ bool amdgpu_crtc_scaling_mode_fixup(struct drm_crtc *crtc,
  * \param dev Device to query.
  * \param pipe Crtc to query.
  * \param flags Flags from caller (DRM_CALLED_FROM_VBLIRQ or 0).
+ *              For driver internal use only also supports these flags:
+ *
+ *              USE_REAL_VBLANKSTART to use the real start of vblank instead
+ *              of a fudged earlier start of vblank.
+ *
+ *              GET_DISTANCE_TO_VBLANKSTART to return distance to the
+ *              fudged earlier start of vblank in *vpos and the distance
+ *              to true start of vblank in *hpos.
+ *
  * \param *vpos Location where vertical scanout position should be stored.
  * \param *hpos Location where horizontal scanout position should go.
  * \param *stime Target location for timestamp taken immediately before
@@ -776,10 +822,40 @@ int amdgpu_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
                 vbl_end = 0;
         }
 
+        /* Called from driver internal vblank counter query code? */
+        if (flags & GET_DISTANCE_TO_VBLANKSTART) {
+            /* Caller wants distance from real vbl_start in *hpos */
+            *hpos = *vpos - vbl_start;
+        }
+
+        /* Fudge vblank to start a few scanlines earlier to handle the
+         * problem that vblank irqs fire a few scanlines before start
+         * of vblank. Some driver internal callers need the true vblank
+         * start to be used and signal this via the USE_REAL_VBLANKSTART flag.
+         *
+         * The cause of the "early" vblank irq is that the irq is triggered
+         * by the line buffer logic when the line buffer read position enters
+         * the vblank, whereas our crtc scanout position naturally lags the
+         * line buffer read position.
+         */
+        if (!(flags & USE_REAL_VBLANKSTART))
+                vbl_start -= adev->mode_info.crtcs[pipe]->lb_vblank_lead_lines;
+
         /* Test scanout position against vblank region. */
         if ((*vpos < vbl_start) && (*vpos >= vbl_end))
                 in_vbl = false;
 
+        /* In vblank? */
+        if (in_vbl)
+            ret |= DRM_SCANOUTPOS_IN_VBLANK;
+
+        /* Called from driver internal vblank counter query code? */
+        if (flags & GET_DISTANCE_TO_VBLANKSTART) {
+                /* Caller wants distance from fudged earlier vbl_start */
+                *vpos -= vbl_start;
+                return ret;
+        }
+
         /* Check if inside vblank area and apply corrective offsets:
          * vpos will then be >=0 in video scanout area, but negative
          * within vblank area, counting down the number of lines until
@@ -795,32 +871,6 @@ int amdgpu_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
         /* Correct for shifted end of vbl at vbl_end. */
         *vpos = *vpos - vbl_end;
 
-        /* In vblank? */
-        if (in_vbl)
-                ret |= DRM_SCANOUTPOS_IN_VBLANK;
-
-        /* Is vpos outside nominal vblank area, but less than
-         * 1/100 of a frame height away from start of vblank?
-         * If so, assume this isn't a massively delayed vblank
-         * interrupt, but a vblank interrupt that fired a few
-         * microseconds before true start of vblank. Compensate
-         * by adding a full frame duration to the final timestamp.
-         * Happens, e.g., on ATI R500, R600.
-         *
-         * We only do this if DRM_CALLED_FROM_VBLIRQ.
-         */
-        if ((flags & DRM_CALLED_FROM_VBLIRQ) && !in_vbl) {
-                vbl_start = mode->crtc_vdisplay;
-                vtotal = mode->crtc_vtotal;
-
-                if (vbl_start - *vpos < vtotal / 100) {
-                        *vpos -= vtotal;
-
-                        /* Signal this correction as "applied". */
-                        ret |= 0x8;
-                }
-        }
-
         return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index fc32fc01a64b..f6ea4b43a60c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -235,8 +235,9 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
             AMDGPU_GEM_USERPTR_REGISTER))
                 return -EINVAL;
 
-        if (!(args->flags & AMDGPU_GEM_USERPTR_ANONONLY) ||
-                   !(args->flags & AMDGPU_GEM_USERPTR_REGISTER)) {
+        if (!(args->flags & AMDGPU_GEM_USERPTR_READONLY) && (
+             !(args->flags & AMDGPU_GEM_USERPTR_ANONONLY) ||
+             !(args->flags & AMDGPU_GEM_USERPTR_REGISTER))) {
 
                 /* if we want to write to it we must require anonymous
                    memory and install a MMU notifier */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 1618e2294a16..e23843f4d877 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -611,13 +611,59 @@ void amdgpu_driver_preclose_kms(struct drm_device *dev,
 u32 amdgpu_get_vblank_counter_kms(struct drm_device *dev, unsigned int pipe)
 {
         struct amdgpu_device *adev = dev->dev_private;
+        int vpos, hpos, stat;
+        u32 count;
 
         if (pipe >= adev->mode_info.num_crtc) {
                 DRM_ERROR("Invalid crtc %u\n", pipe);
                 return -EINVAL;
         }
 
-        return amdgpu_display_vblank_get_counter(adev, pipe);
+        /* The hw increments its frame counter at start of vsync, not at start
+         * of vblank, as is required by DRM core vblank counter handling.
+         * Cook the hw count here to make it appear to the caller as if it
+         * incremented at start of vblank. We measure distance to start of
+         * vblank in vpos. vpos therefore will be >= 0 between start of vblank
+         * and start of vsync, so vpos >= 0 means to bump the hw frame counter
+         * result by 1 to give the proper appearance to caller.
+         */
+        if (adev->mode_info.crtcs[pipe]) {
+                /* Repeat readout if needed to provide stable result if
+                 * we cross start of vsync during the queries.
+                 */
+                do {
+                        count = amdgpu_display_vblank_get_counter(adev, pipe);
+                        /* Ask amdgpu_get_crtc_scanoutpos to return vpos as
+                         * distance to start of vblank, instead of regular
+                         * vertical scanout pos.
+                         */
+                        stat = amdgpu_get_crtc_scanoutpos(
+                                dev, pipe, GET_DISTANCE_TO_VBLANKSTART,
+                                &vpos, &hpos, NULL, NULL,
+                                &adev->mode_info.crtcs[pipe]->base.hwmode);
+                } while (count != amdgpu_display_vblank_get_counter(adev, pipe));
+
+                if (((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) !=
+                    (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE))) {
+                        DRM_DEBUG_VBL("Query failed! stat %d\n", stat);
+                } else {
+                        DRM_DEBUG_VBL("crtc %d: dist from vblank start %d\n",
+                                      pipe, vpos);
+
+                        /* Bump counter if we are at >= leading edge of vblank,
+                         * but before vsync where vpos would turn negative and
+                         * the hw counter really increments.
+                         */
+                        if (vpos >= 0)
+                                count++;
+                }
+        } else {
+                /* Fallback to use value as is. */
+                count = amdgpu_display_vblank_get_counter(adev, pipe);
+                DRM_DEBUG_VBL("NULL mode info! Returned count may be wrong.\n");
+        }
+
+        return count;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index b62c1710cab6..064ebb347074 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -407,6 +407,7 @@ struct amdgpu_crtc {
         u32 line_time;
         u32 wm_low;
         u32 wm_high;
+        u32 lb_vblank_lead_lines;
         struct drm_display_mode hw_mode;
 };
 
@@ -528,6 +529,10 @@ struct amdgpu_framebuffer {
 #define ENCODER_MODE_IS_DP(em) (((em) == ATOM_ENCODER_MODE_DP) || \
                                 ((em) == ATOM_ENCODER_MODE_DP_MST))
 
+/* Driver internal use only flags of amdgpu_get_crtc_scanoutpos() */
+#define USE_REAL_VBLANKSTART            (1 << 30)
+#define GET_DISTANCE_TO_VBLANKSTART     (1 << 31)
+
 void amdgpu_link_encoder_connector(struct drm_device *dev);
 
 struct drm_connector *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 0d524384ff79..c3ce103b6a33 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -100,6 +100,7 @@ static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
         list_del_init(&bo->list);
         mutex_unlock(&bo->adev->gem.mutex);
         drm_gem_object_release(&bo->gem_base);
+        amdgpu_bo_unref(&bo->parent);
         kfree(bo->metadata);
         kfree(bo);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index d4bac5f49939..8a1752ff3d8e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -587,9 +587,13 @@ static int amdgpu_ttm_backend_bind(struct ttm_tt *ttm,
         uint32_t flags = amdgpu_ttm_tt_pte_flags(gtt->adev, ttm, bo_mem);
         int r;
 
-        if (gtt->userptr)
-                amdgpu_ttm_tt_pin_userptr(ttm);
-
+        if (gtt->userptr) {
+                r = amdgpu_ttm_tt_pin_userptr(ttm);
+                if (r) {
+                        DRM_ERROR("failed to pin userptr\n");
+                        return r;
+                }
+        }
         gtt->offset = (unsigned long)(bo_mem->start << PAGE_SHIFT);
         if (!ttm->num_pages) {
                 WARN(1, "nothing to bind %lu pages for mreg %p back %p!\n",
@@ -797,11 +801,12 @@ uint32_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm,
         if (mem && mem->mem_type != TTM_PL_SYSTEM)
                 flags |= AMDGPU_PTE_VALID;
 
-        if (mem && mem->mem_type == TTM_PL_TT)
+        if (mem && mem->mem_type == TTM_PL_TT) {
                 flags |= AMDGPU_PTE_SYSTEM;
 
-        if (!ttm || ttm->caching_state == tt_cached)
-                flags |= AMDGPU_PTE_SNOOPED;
+                if (ttm->caching_state == tt_cached)
+                        flags |= AMDGPU_PTE_SNOOPED;
+        }
 
         if (adev->asic_type >= CHIP_TOPAZ)
                 flags |= AMDGPU_PTE_EXECUTABLE;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index ae037e5b6ad0..b53d273eb7a1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -885,17 +885,21 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
         struct amdgpu_bo_va_mapping *mapping;
         int r;
 
+        spin_lock(&vm->freed_lock);
         while (!list_empty(&vm->freed)) {
                 mapping = list_first_entry(&vm->freed,
                         struct amdgpu_bo_va_mapping, list);
                 list_del(&mapping->list);
-
+                spin_unlock(&vm->freed_lock);
                 r = amdgpu_vm_bo_update_mapping(adev, vm, mapping, 0, 0, NULL);
                 kfree(mapping);
                 if (r)
                         return r;
 
+                spin_lock(&vm->freed_lock);
         }
+        spin_unlock(&vm->freed_lock);
+
         return 0;
 
 }
@@ -1079,6 +1083,11 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
                 if (r)
                         goto error_free;
 
+                /* Keep a reference to the page table to avoid freeing
+                 * them up in the wrong order.
+                 */
+                pt->parent = amdgpu_bo_ref(vm->page_directory);
+
                 r = amdgpu_vm_clear_bo(adev, pt);
                 if (r) {
                         amdgpu_bo_unref(&pt);
@@ -1150,10 +1159,13 @@ int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
         spin_unlock(&vm->it_lock);
         trace_amdgpu_vm_bo_unmap(bo_va, mapping);
 
-        if (valid)
+        if (valid) {
+                spin_lock(&vm->freed_lock);
                 list_add(&mapping->list, &vm->freed);
-        else
+                spin_unlock(&vm->freed_lock);
+        } else {
                 kfree(mapping);
+        }
 
         return 0;
 }
@@ -1186,7 +1198,9 @@ void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
                 interval_tree_remove(&mapping->it, &vm->va);
                 spin_unlock(&vm->it_lock);
                 trace_amdgpu_vm_bo_unmap(bo_va, mapping);
+                spin_lock(&vm->freed_lock);
                 list_add(&mapping->list, &vm->freed);
+                spin_unlock(&vm->freed_lock);
         }
         list_for_each_entry_safe(mapping, next, &bo_va->invalids, list) {
                 list_del(&mapping->list);
@@ -1247,6 +1261,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
         INIT_LIST_HEAD(&vm->cleared);
         INIT_LIST_HEAD(&vm->freed);
         spin_lock_init(&vm->it_lock);
+        spin_lock_init(&vm->freed_lock);
         pd_size = amdgpu_vm_directory_size(adev);
         pd_entries = amdgpu_vm_num_pdes(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index cb0f7747e3dc..4dcc8fba5792 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -1250,7 +1250,7 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev,
         u32 pixel_period;
         u32 line_time = 0;
         u32 latency_watermark_a = 0, latency_watermark_b = 0;
-        u32 tmp, wm_mask;
+        u32 tmp, wm_mask, lb_vblank_lead_lines = 0;
 
         if (amdgpu_crtc->base.enabled && num_heads && mode) {
                 pixel_period = 1000000 / (u32)mode->clock;
@@ -1333,6 +1333,7 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev,
                     (adev->mode_info.disp_priority == 2)) {
                         DRM_DEBUG_KMS("force priority to high\n");
                 }
+                lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
         }
 
         /* select wm A */
@@ -1357,6 +1358,8 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev,
         amdgpu_crtc->line_time = line_time;
         amdgpu_crtc->wm_high = latency_watermark_a;
         amdgpu_crtc->wm_low = latency_watermark_b;
+        /* Save number of lines the linebuffer leads before the scanout */
+        amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index 5af3721851d6..8f1e51128b33 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -1238,7 +1238,7 @@ static void dce_v11_0_program_watermarks(struct amdgpu_device *adev,
         u32 pixel_period;
         u32 line_time = 0;
         u32 latency_watermark_a = 0, latency_watermark_b = 0;
-        u32 tmp, wm_mask;
+        u32 tmp, wm_mask, lb_vblank_lead_lines = 0;
 
         if (amdgpu_crtc->base.enabled && num_heads && mode) {
                 pixel_period = 1000000 / (u32)mode->clock;
@@ -1321,6 +1321,7 @@ static void dce_v11_0_program_watermarks(struct amdgpu_device *adev,
                     (adev->mode_info.disp_priority == 2)) {
                         DRM_DEBUG_KMS("force priority to high\n");
                 }
+                lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
         }
 
         /* select wm A */
@@ -1345,6 +1346,8 @@ static void dce_v11_0_program_watermarks(struct amdgpu_device *adev,
         amdgpu_crtc->line_time = line_time;
         amdgpu_crtc->wm_high = latency_watermark_a;
         amdgpu_crtc->wm_low = latency_watermark_b;
+        /* Save number of lines the linebuffer leads before the scanout */
+        amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 4f7b49a6dc50..42d954dc436d 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -1193,7 +1193,7 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev,
         u32 pixel_period;
         u32 line_time = 0;
         u32 latency_watermark_a = 0, latency_watermark_b = 0;
-        u32 tmp, wm_mask;
+        u32 tmp, wm_mask, lb_vblank_lead_lines = 0;
 
         if (amdgpu_crtc->base.enabled && num_heads && mode) {
                 pixel_period = 1000000 / (u32)mode->clock;
@@ -1276,6 +1276,7 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev,
                     (adev->mode_info.disp_priority == 2)) {
                         DRM_DEBUG_KMS("force priority to high\n");
                 }
+                lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
         }
 
         /* select wm A */
@@ -1302,6 +1303,8 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev,
         amdgpu_crtc->line_time = line_time;
         amdgpu_crtc->wm_high = latency_watermark_a;
         amdgpu_crtc->wm_low = latency_watermark_b;
+        /* Save number of lines the linebuffer leads before the scanout */
+        amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 7427d8cd4c43..ed8abb58a785 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -513,7 +513,7 @@ static int gmc_v7_0_gart_enable(struct amdgpu_device *adev)
         WREG32(mmVM_L2_CNTL3, tmp);
         /* setup context0 */
         WREG32(mmVM_CONTEXT0_PAGE_TABLE_START_ADDR, adev->mc.gtt_start >> 12);
-        WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, (adev->mc.gtt_end >> 12) - 1);
+        WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, adev->mc.gtt_end >> 12);
         WREG32(mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR, adev->gart.table_addr >> 12);
         WREG32(mmVM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR,
                         (u32)(adev->dummy_page.addr >> 12));
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index cb0e50ebb528..d39028440814 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -657,7 +657,7 @@ static int gmc_v8_0_gart_enable(struct amdgpu_device *adev)
         WREG32(mmVM_L2_CNTL4, tmp);
         /* setup context0 */
         WREG32(mmVM_CONTEXT0_PAGE_TABLE_START_ADDR, adev->mc.gtt_start >> 12);
-        WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, (adev->mc.gtt_end >> 12) - 1);
+        WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, adev->mc.gtt_end >> 12);
         WREG32(mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR, adev->gart.table_addr >> 12);
         WREG32(mmVM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR,
                         (u32)(adev->dummy_page.addr >> 12));
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index 651129f2ec1d..3a4820e863ec 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -288,6 +288,7 @@ amd_sched_entity_pop_job(struct amd_sched_entity *entity)
  */
 static bool amd_sched_entity_in(struct amd_sched_job *sched_job)
 {
+        struct amd_gpu_scheduler *sched = sched_job->sched;
         struct amd_sched_entity *entity = sched_job->s_entity;
         bool added, first = false;
 
@@ -302,7 +303,7 @@ static bool amd_sched_entity_in(struct amd_sched_job *sched_job)
 
         /* first job wakes up scheduler */
         if (first)
-                amd_sched_wakeup(sched_job->sched);
+                amd_sched_wakeup(sched);
 
         return added;
 }
@@ -318,9 +319,9 @@ void amd_sched_entity_push_job(struct amd_sched_job *sched_job)
 {
         struct amd_sched_entity *entity = sched_job->s_entity;
 
+        trace_amd_sched_job(sched_job);
         wait_event(entity->sched->job_scheduled,
                    amd_sched_entity_in(sched_job));
-        trace_amd_sched_job(sched_job);
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 248953d2fdb7..0154db43860c 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -8472,7 +8472,7 @@ restart_ih:
         if (queue_dp)
                 schedule_work(&rdev->dp_work);
         if (queue_hotplug)
-                schedule_work(&rdev->hotplug_work);
+                schedule_delayed_work(&rdev->hotplug_work, 0);
         if (queue_reset) {
                 rdev->needs_reset = true;
                 wake_up_all(&rdev->fence_queue);
@@ -9630,6 +9630,9 @@ static void dce8_program_watermarks(struct radeon_device *rdev,
                     (rdev->disp_priority == 2)) {
                         DRM_DEBUG_KMS("force priority to high\n");
                 }
+
+                /* Save number of lines the linebuffer leads before the scanout */
+                radeon_crtc->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
         }
 
         /* select wm A */
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 7f33767d7ed6..2ad462896896 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2372,6 +2372,9 @@ static void evergreen_program_watermarks(struct radeon_device *rdev,
                 c.full = dfixed_div(c, a);
                 priority_b_mark = dfixed_trunc(c);
                 priority_b_cnt |= priority_b_mark & PRIORITY_MARK_MASK;
+
+                /* Save number of lines the linebuffer leads before the scanout */
+                radeon_crtc->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
         }
 
         /* select wm A */
@@ -5344,7 +5347,7 @@ restart_ih:
         if (queue_dp)
                 schedule_work(&rdev->dp_work);
         if (queue_hotplug)
-                schedule_work(&rdev->hotplug_work);
+                schedule_delayed_work(&rdev->hotplug_work, 0);
         if (queue_hdmi)
                 schedule_work(&rdev->audio_work);
         if (queue_thermal && rdev->pm.dpm_enabled)
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 238b13f045c1..9e7e2bf03b81 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -806,7 +806,7 @@ int r100_irq_process(struct radeon_device *rdev)
                 status = r100_irq_ack(rdev);
         }
         if (queue_hotplug)
-                schedule_work(&rdev->hotplug_work);
+                schedule_delayed_work(&rdev->hotplug_work, 0);
         if (rdev->msi_enabled) {
                 switch (rdev->family) {
                 case CHIP_RS400:
@@ -3217,6 +3217,9 @@ void r100_bandwidth_update(struct radeon_device *rdev)
         uint32_t pixel_bytes1 = 0;
         uint32_t pixel_bytes2 = 0;
 
+        /* Guess line buffer size to be 8192 pixels */
+        u32 lb_size = 8192;
+
         if (!rdev->mode_info.mode_config_initialized)
                 return;
 
@@ -3631,6 +3634,13 @@ void r100_bandwidth_update(struct radeon_device *rdev)
                 DRM_DEBUG_KMS("GRPH2_BUFFER_CNTL from to %x\n",
                           (unsigned int)RREG32(RADEON_GRPH2_BUFFER_CNTL));
         }
+
+        /* Save number of lines the linebuffer leads before the scanout */
+        if (mode1)
+            rdev->mode_info.crtcs[0]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode1->crtc_hdisplay);
+
+        if (mode2)
+            rdev->mode_info.crtcs[1]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode2->crtc_hdisplay);
 }
 
 int r100_ring_test(struct radeon_device *rdev, struct radeon_ring *ring)
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 4ea5b10ff5f4..cc2fdf0be37a 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -4276,7 +4276,7 @@ restart_ih:
                 WREG32(IH_RB_RPTR, rptr);
         }
         if (queue_hotplug)
-                schedule_work(&rdev->hotplug_work);
+                schedule_delayed_work(&rdev->hotplug_work, 0);
         if (queue_hdmi)
                 schedule_work(&rdev->audio_work);
         if (queue_thermal && rdev->pm.dpm_enabled)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index b6cbd816537e..87db64983ea8 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -2414,7 +2414,7 @@ struct radeon_device {
         struct r600_ih ih; /* r6/700 interrupt ring */
         struct radeon_rlc rlc;
         struct radeon_mec mec;
-        struct work_struct hotplug_work;
+        struct delayed_work hotplug_work;
         struct work_struct dp_work;
         struct work_struct audio_work;
         int num_crtc; /* number of crtcs */
diff --git a/drivers/gpu/drm/radeon/radeon_agp.c b/drivers/gpu/drm/radeon/radeon_agp.c
index fe994aac3b04..c77d349c561c 100644
--- a/drivers/gpu/drm/radeon/radeon_agp.c
+++ b/drivers/gpu/drm/radeon/radeon_agp.c
@@ -54,6 +54,9 @@ static struct radeon_agpmode_quirk radeon_agpmode_quirk_list[] = {
         /* Intel 82855PM host bridge / Mobility 9600 M10 RV350 Needs AGPMode 1 (lp #195051) */
         { PCI_VENDOR_ID_INTEL, 0x3340, PCI_VENDOR_ID_ATI, 0x4e50,
                 PCI_VENDOR_ID_IBM, 0x0550, 1},
+        /* Intel 82855PM host bridge / RV250/M9 GL [Mobility FireGL 9000/Radeon 9000] needs AGPMode 1 (Thinkpad T40p) */
+        { PCI_VENDOR_ID_INTEL, 0x3340, PCI_VENDOR_ID_ATI, 0x4c66,
+                PCI_VENDOR_ID_IBM, 0x054d, 1},
         /* Intel 82855PM host bridge / Mobility M7 needs AGPMode 1 */
         { PCI_VENDOR_ID_INTEL, 0x3340, PCI_VENDOR_ID_ATI, 0x4c57,
                 PCI_VENDOR_ID_IBM, 0x0530, 1},
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 5a2cafb4f1bc..340f3f549f29 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1234,13 +1234,32 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
         if (r < 0)
                 return connector_status_disconnected;
 
+        if (radeon_connector->detected_hpd_without_ddc) {
+                force = true;
+                radeon_connector->detected_hpd_without_ddc = false;
+        }
+
         if (!force && radeon_check_hpd_status_unchanged(connector)) {
                 ret = connector->status;
                 goto exit;
         }
 
-        if (radeon_connector->ddc_bus)
+        if (radeon_connector->ddc_bus) {
                 dret = radeon_ddc_probe(radeon_connector, false);
+
+                /* Sometimes the pins required for the DDC probe on DVI
+                 * connectors don't make contact at the same time that the ones
+                 * for HPD do. If the DDC probe fails even though we had an HPD
+                 * signal, try again later */
+                if (!dret && !force &&
+                    connector->status != connector_status_connected) {
+                        DRM_DEBUG_KMS("hpd detected without ddc, retrying in 1 second\n");
+                        radeon_connector->detected_hpd_without_ddc = true;
+                        schedule_delayed_work(&rdev->hotplug_work,
+                                              msecs_to_jiffies(1000));
+                        goto exit;
+                }
+        }
         if (dret) {
                 radeon_connector->detected_by_load = false;
                 radeon_connector_free_edid(connector);
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index a8d9927ed9eb..1eca0acac016 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -322,7 +322,9 @@ void radeon_crtc_handle_vblank(struct radeon_device *rdev, int crtc_id)
          * to complete in this vblank?
          */
         if (update_pending &&
-            (DRM_SCANOUTPOS_VALID & radeon_get_crtc_scanoutpos(rdev->ddev, crtc_id, 0,
+            (DRM_SCANOUTPOS_VALID & radeon_get_crtc_scanoutpos(rdev->ddev,
+                                                               crtc_id,
+                                                               USE_REAL_VBLANKSTART,
                                                                &vpos, &hpos, NULL, NULL,
                                                                &rdev->mode_info.crtcs[crtc_id]->base.hwmode)) &&
             ((vpos >= (99 * rdev->mode_info.crtcs[crtc_id]->base.hwmode.crtc_vdisplay)/100) ||
@@ -401,6 +403,8 @@ static void radeon_flip_work_func(struct work_struct *__work)
         struct drm_crtc *crtc = &radeon_crtc->base;
         unsigned long flags;
         int r;
+        int vpos, hpos, stat, min_udelay;
+        struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id];
 
         down_read(&rdev->exclusive_lock);
         if (work->fence) {
@@ -437,6 +441,41 @@ static void radeon_flip_work_func(struct work_struct *__work)
         /* set the proper interrupt */
         radeon_irq_kms_pflip_irq_get(rdev, radeon_crtc->crtc_id);
 
+        /* If this happens to execute within the "virtually extended" vblank
+         * interval before the start of the real vblank interval then it needs
+         * to delay programming the mmio flip until the real vblank is entered.
+         * This prevents completing a flip too early due to the way we fudge
+         * our vblank counter and vblank timestamps in order to work around the
+         * problem that the hw fires vblank interrupts before actual start of
+         * vblank (when line buffer refilling is done for a frame). It
+         * complements the fudging logic in radeon_get_crtc_scanoutpos() for
+         * timestamping and radeon_get_vblank_counter_kms() for vblank counts.
+         *
+         * In practice this won't execute very often unless on very fast
+         * machines because the time window for this to happen is very small.
+         */
+        for (;;) {
+                /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank
+                 * start in hpos, and to the "fudged earlier" vblank start in
+                 * vpos.
+                 */
+                stat = radeon_get_crtc_scanoutpos(rdev->ddev, work->crtc_id,
+                                                  GET_DISTANCE_TO_VBLANKSTART,
+                                                  &vpos, &hpos, NULL, NULL,
+                                                  &crtc->hwmode);
+
+                if ((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) !=
+                    (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE) ||
+                    !(vpos >= 0 && hpos <= 0))
+                        break;
+
+                /* Sleep at least until estimated real start of hw vblank */
+                spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+                min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5);
+                usleep_range(min_udelay, 2 * min_udelay);
+                spin_lock_irqsave(&crtc->dev->event_lock, flags);
+        };
+
         /* do the flip (mmio) */
         radeon_page_flip(rdev, radeon_crtc->crtc_id, work->base);
 
@@ -1768,6 +1807,15 @@ bool radeon_crtc_scaling_mode_fixup(struct drm_crtc *crtc,
  * \param dev Device to query.
  * \param crtc Crtc to query.
  * \param flags Flags from caller (DRM_CALLED_FROM_VBLIRQ or 0).
+ *              For driver internal use only also supports these flags:
+ *
+ *              USE_REAL_VBLANKSTART to use the real start of vblank instead
+ *              of a fudged earlier start of vblank.
+ *
+ *              GET_DISTANCE_TO_VBLANKSTART to return distance to the
+ *              fudged earlier start of vblank in *vpos and the distance
+ *              to true start of vblank in *hpos.
+ *
  * \param *vpos Location where vertical scanout position should be stored.
  * \param *hpos Location where horizontal scanout position should go.
  * \param *stime Target location for timestamp taken immediately before
@@ -1911,10 +1959,40 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
                 vbl_end = 0;
         }
 
+        /* Called from driver internal vblank counter query code? */
+        if (flags & GET_DISTANCE_TO_VBLANKSTART) {
+            /* Caller wants distance from real vbl_start in *hpos */
+            *hpos = *vpos - vbl_start;
+        }
+
+        /* Fudge vblank to start a few scanlines earlier to handle the
+         * problem that vblank irqs fire a few scanlines before start
+         * of vblank. Some driver internal callers need the true vblank
+         * start to be used and signal this via the USE_REAL_VBLANKSTART flag.
+         *
+         * The cause of the "early" vblank irq is that the irq is triggered
+         * by the line buffer logic when the line buffer read position enters
+         * the vblank, whereas our crtc scanout position naturally lags the
+         * line buffer read position.
+         */
+        if (!(flags & USE_REAL_VBLANKSTART))
+                vbl_start -= rdev->mode_info.crtcs[pipe]->lb_vblank_lead_lines;
+
         /* Test scanout position against vblank region. */
         if ((*vpos < vbl_start) && (*vpos >= vbl_end))
                 in_vbl = false;
 
+        /* In vblank? */
+        if (in_vbl)
+            ret |= DRM_SCANOUTPOS_IN_VBLANK;
+
+        /* Called from driver internal vblank counter query code? */
+        if (flags & GET_DISTANCE_TO_VBLANKSTART) {
+                /* Caller wants distance from fudged earlier vbl_start */
+                *vpos -= vbl_start;
+                return ret;
+        }
+
         /* Check if inside vblank area and apply corrective offsets:
          * vpos will then be >=0 in video scanout area, but negative
          * within vblank area, counting down the number of lines until
@@ -1930,31 +2008,5 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
         /* Correct for shifted end of vbl at vbl_end. */
         *vpos = *vpos - vbl_end;
 
-        /* In vblank? */
-        if (in_vbl)
-                ret |= DRM_SCANOUTPOS_IN_VBLANK;
-
-        /* Is vpos outside nominal vblank area, but less than
-         * 1/100 of a frame height away from start of vblank?
-         * If so, assume this isn't a massively delayed vblank
-         * interrupt, but a vblank interrupt that fired a few
-         * microseconds before true start of vblank. Compensate
-         * by adding a full frame duration to the final timestamp.
-         * Happens, e.g., on ATI R500, R600.
-         *
-         * We only do this if DRM_CALLED_FROM_VBLIRQ.
-         */
-        if ((flags & DRM_CALLED_FROM_VBLIRQ) && !in_vbl) {
-                vbl_start = mode->crtc_vdisplay;
-                vtotal = mode->crtc_vtotal;
-
-                if (vbl_start - *vpos < vtotal / 100) {
-                        *vpos -= vtotal;
-
-                        /* Signal this correction as "applied". */
-                        ret |= 0x8;
-                }
-        }
-
         return ret;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c
index 171d3e43c30c..979f3bf65f2c 100644
--- a/drivers/gpu/drm/radeon/radeon_irq_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c
@@ -74,7 +74,7 @@ irqreturn_t radeon_driver_irq_handler_kms(int irq, void *arg)
 static void radeon_hotplug_work_func(struct work_struct *work)
 {
         struct radeon_device *rdev = container_of(work, struct radeon_device,
-                                                  hotplug_work);
+                                                  hotplug_work.work);
         struct drm_device *dev = rdev->ddev;
         struct drm_mode_config *mode_config = &dev->mode_config;
         struct drm_connector *connector;
@@ -302,7 +302,7 @@ int radeon_irq_kms_init(struct radeon_device *rdev)
                 }
         }
 
-        INIT_WORK(&rdev->hotplug_work, radeon_hotplug_work_func);
+        INIT_DELAYED_WORK(&rdev->hotplug_work, radeon_hotplug_work_func);
         INIT_WORK(&rdev->dp_work, radeon_dp_work_func);
         INIT_WORK(&rdev->audio_work, r600_audio_update_hdmi);
 
@@ -310,7 +310,7 @@ int radeon_irq_kms_init(struct radeon_device *rdev)
         r = drm_irq_install(rdev->ddev, rdev->ddev->pdev->irq);
         if (r) {
                 rdev->irq.installed = false;
-                flush_work(&rdev->hotplug_work);
+                flush_delayed_work(&rdev->hotplug_work);
                 return r;
         }
 
@@ -333,7 +333,7 @@ void radeon_irq_kms_fini(struct radeon_device *rdev)
                 rdev->irq.installed = false;
                 if (rdev->msi_enabled)
                         pci_disable_msi(rdev->pdev);
-                flush_work(&rdev->hotplug_work);
+                flush_delayed_work(&rdev->hotplug_work);
         }
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 0ec6fcca16d3..d290a8a09036 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -755,6 +755,8 @@ void radeon_driver_preclose_kms(struct drm_device *dev,
  */
 u32 radeon_get_vblank_counter_kms(struct drm_device *dev, int crtc)
 {
+        int vpos, hpos, stat;
+        u32 count;
         struct radeon_device *rdev = dev->dev_private;
 
         if (crtc < 0 || crtc >= rdev->num_crtc) {
@@ -762,7 +764,53 @@ u32 radeon_get_vblank_counter_kms(struct drm_device *dev, int crtc)
                 return -EINVAL;
         }
 
-        return radeon_get_vblank_counter(rdev, crtc);
+        /* The hw increments its frame counter at start of vsync, not at start
+         * of vblank, as is required by DRM core vblank counter handling.
+         * Cook the hw count here to make it appear to the caller as if it
+         * incremented at start of vblank. We measure distance to start of
+         * vblank in vpos. vpos therefore will be >= 0 between start of vblank
+         * and start of vsync, so vpos >= 0 means to bump the hw frame counter
+         * result by 1 to give the proper appearance to caller.
+         */
+        if (rdev->mode_info.crtcs[crtc]) {
+                /* Repeat readout if needed to provide stable result if
+                 * we cross start of vsync during the queries.
+                 */
+                do {
+                        count = radeon_get_vblank_counter(rdev, crtc);
+                        /* Ask radeon_get_crtc_scanoutpos to return vpos as
+                         * distance to start of vblank, instead of regular
+                         * vertical scanout pos.
+                         */
+                        stat = radeon_get_crtc_scanoutpos(
+                                dev, crtc, GET_DISTANCE_TO_VBLANKSTART,
+                                &vpos, &hpos, NULL, NULL,
+                                &rdev->mode_info.crtcs[crtc]->base.hwmode);
+                } while (count != radeon_get_vblank_counter(rdev, crtc));
+
+                if (((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) !=
+                    (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE))) {
+                        DRM_DEBUG_VBL("Query failed! stat %d\n", stat);
+                }
+                else {
+                        DRM_DEBUG_VBL("crtc %d: dist from vblank start %d\n",
+                                      crtc, vpos);
+
+                        /* Bump counter if we are at >= leading edge of vblank,
+                         * but before vsync where vpos would turn negative and
+                         * the hw counter really increments.
+                         */
+                        if (vpos >= 0)
+                                count++;
+                }
+        }
+        else {
+            /* Fallback to use value as is. */
+            count = radeon_get_vblank_counter(rdev, crtc);
+            DRM_DEBUG_VBL("NULL mode info! Returned count may be wrong.\n");
+        }
+
+        return count;
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index 830e171c3a9e..bba112628b47 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -367,6 +367,7 @@ struct radeon_crtc {
         u32 line_time;
         u32 wm_low;
         u32 wm_high;
+        u32 lb_vblank_lead_lines;
         struct drm_display_mode hw_mode;
         enum radeon_output_csc output_csc;
 };
@@ -553,6 +554,7 @@ struct radeon_connector {
         void *con_priv;
         bool dac_load_detect;
         bool detected_by_load; /* if the connection status was determined by load */
+        bool detected_hpd_without_ddc; /* if an HPD signal was detected on DVI, but ddc probing failed */
         uint16_t connector_object_id;
         struct radeon_hpd hpd;
         struct radeon_router router;
@@ -686,6 +688,9 @@ struct atom_voltage_table
         struct atom_voltage_table_entry entries[MAX_VOLTAGE_ENTRIES];
 };
 
+/* Driver internal use only flags of radeon_get_crtc_scanoutpos() */
+#define USE_REAL_VBLANKSTART            (1 << 30)
+#define GET_DISTANCE_TO_VBLANKSTART     (1 << 31)
 
 extern void
 radeon_add_atom_connector(struct drm_device *dev,
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index f4f03dcc1530..59abebd6b5dc 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -1756,7 +1756,9 @@ static bool radeon_pm_in_vbl(struct radeon_device *rdev)
          */
         for (crtc = 0; (crtc < rdev->num_crtc) && in_vbl; crtc++) {
                 if (rdev->pm.active_crtcs & (1 << crtc)) {
-                        vbl_status = radeon_get_crtc_scanoutpos(rdev->ddev, crtc, 0,
+                        vbl_status = radeon_get_crtc_scanoutpos(rdev->ddev,
+                                                                crtc,
+                                                                USE_REAL_VBLANKSTART,
                                                                 &vpos, &hpos, NULL, NULL,
                                                                 &rdev->mode_info.crtcs[crtc]->base.hwmode);
                         if ((vbl_status & DRM_SCANOUTPOS_VALID) &&
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 97a904835759..6244f4e44e9a 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -813,7 +813,7 @@ int rs600_irq_process(struct radeon_device *rdev)
                 status = rs600_irq_ack(rdev);
         }
         if (queue_hotplug)
-                schedule_work(&rdev->hotplug_work);
+                schedule_delayed_work(&rdev->hotplug_work, 0);
         if (queue_hdmi)
                 schedule_work(&rdev->audio_work);
         if (rdev->msi_enabled) {
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index 516ca27cfa12..6bc44c24e837 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -207,6 +207,9 @@ void rs690_line_buffer_adjust(struct radeon_device *rdev,
 {
         u32 tmp;
 
+        /* Guess line buffer size to be 8192 pixels */
+        u32 lb_size = 8192;
+
         /*
          * Line Buffer Setup
          * There is a single line buffer shared by both display controllers.
@@ -243,6 +246,13 @@ void rs690_line_buffer_adjust(struct radeon_device *rdev,
                 tmp |= V_006520_DC_LB_MEMORY_SPLIT_D1_1Q_D2_3Q;
         }
         WREG32(R_006520_DC_LB_MEMORY_SPLIT, tmp);
+
+        /* Save number of lines the linebuffer leads before the scanout */
+        if (mode1)
+                rdev->mode_info.crtcs[0]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode1->crtc_hdisplay);
+
+        if (mode2)
+                rdev->mode_info.crtcs[1]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode2->crtc_hdisplay);
 }
 
 struct rs690_watermark {
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 07037e32dea3..f878d6962da5 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2376,6 +2376,9 @@ static void dce6_program_watermarks(struct radeon_device *rdev,
                 c.full = dfixed_div(c, a);
                 priority_b_mark = dfixed_trunc(c);
                 priority_b_cnt |= priority_b_mark & PRIORITY_MARK_MASK;
+
+                /* Save number of lines the linebuffer leads before the scanout */
+                radeon_crtc->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
         }
 
         /* select wm A */
@@ -6848,7 +6851,7 @@ restart_ih:
         if (queue_dp)
                 schedule_work(&rdev->dp_work);
         if (queue_hotplug)
-                schedule_work(&rdev->hotplug_work);
+                schedule_delayed_work(&rdev->hotplug_work, 0);
         if (queue_thermal && rdev->pm.dpm_enabled)
                 schedule_work(&rdev->pm.dpm.thermal.work);
         rdev->ih.rptr = rptr;