Merge branch 'drm-fixes-4.4' of git://people.freedesktop.org/~agd5f/linux into drm-next

A few more last minute fixes for 4.4 on top of my pull request from
earlier this week.  The big change here is a vblank regression fix due to
commit 4dfd6486 "drm: Use vblank timestamps to guesstimate how many vblanks
were missed".  Beyond that, a hotplug fix and a few VM fixes.

* 'drm-fixes-4.4' of git://people.freedesktop.org/~agd5f/linux:
  drm/amdgpu: Fixup hw vblank counter/ts for new drm_update_vblank_count() (v3)
  drm/radeon: Fixup hw vblank counter/ts for new drm_update_vblank_count() (v2)
  drm/radeon: Retry DDC probing on DVI on failure if we got an HPD interrupt
  drm/amdgpu: add spin lock to protect freed list in vm (v2)
  drm/amdgpu: partially revert "drm/amdgpu: fix VM_CONTEXT*_PAGE_TABLE_END_ADDR" v2
  drm/amdgpu: take a BO reference for the user fence
  drm/amdgpu: take a BO reference in the display code
  drm/amdgpu: set snooped flags only on system addresses v2
  drm/amdgpu: fix race condition in amd_sched_entity_push_job
  drm/amdgpu: add err check for pin userptr
  add blacklist for thinkpad T40p
  drm/amdgpu: fix VM page table reference counting
  drm/amdgpu: fix userptr flags check

1 files changed, 79 insertions, 27 deletions

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;
 }