From 73d4c23f5361928b12e7827e872612273cc1175a Mon Sep 17 00:00:00 2001 From: Mario Kleiner Date: Sat, 17 Sep 2016 14:25:38 +0200 Subject: drm/radeon: Slightly more robust flip completion handling for < DCE-4 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Pre DCE4 hardware doesn't have (reliable) pageflip completion irqs, therefore we have to use the old polling method for flip completion handling in vblank irq. As vblank irqs fire a bit before start of vblank (when the linebuffer fifo read position reaches end of scanout), we have some fudge for flip completion handling in the last lines of active scanout. Old code assumed the threshold to be 99% of active scanout height, a ballpark estimate which worked ok. Since we know since a while how to calculate the actual threshold from linebuffer size, lets make use of it to get a more accurate threshold. This completion path is still prone to some races in corner cases, especially on pre-AVIVO hardware, so document them a bit better in the code comments. Acked-by: Michel Dänzer Signed-off-by: Mario Kleiner Signed-off-by: Alex Deucher --- drivers/gpu/drm/radeon/radeon_display.c | 30 ++++++++++++++++++++++-------- 1 file changed, 22 insertions(+), 8 deletions(-) (limited to 'drivers/gpu/drm/radeon') diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 890171f08987..50706464d456 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -321,16 +321,30 @@ void radeon_crtc_handle_vblank(struct radeon_device *rdev, int crtc_id) update_pending = radeon_page_flip_pending(rdev, crtc_id); /* Has the pageflip already completed in crtc, or is it certain - * to complete in this vblank? + * to complete in this vblank? GET_DISTANCE_TO_VBLANKSTART provides + * distance to start of "fudged earlier" vblank in vpos, distance to + * start of real vblank in hpos. vpos >= 0 && hpos < 0 means we are in + * the last few scanlines before start of real vblank, where the vblank + * irq can fire, so we have sampled update_pending a bit too early and + * know the flip will complete at leading edge of the upcoming real + * vblank. On pre-AVIVO hardware, flips also complete inside the real + * vblank, not only at leading edge, so if update_pending for hpos >= 0 + * == inside real vblank, the flip will complete almost immediately. + * Note that this method of completion handling is still not 100% race + * free, as we could execute before the radeon_flip_work_func managed + * to run and set the RADEON_FLIP_SUBMITTED status, thereby we no-op, + * but the flip still gets programmed into hw and completed during + * vblank, leading to a delayed emission of the flip completion event. + * This applies at least to pre-AVIVO hardware, where flips are always + * completing inside vblank, not only at leading edge of vblank. */ if (update_pending && - (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) || - (vpos < 0 && !ASIC_IS_AVIVO(rdev)))) { + (DRM_SCANOUTPOS_VALID & + radeon_get_crtc_scanoutpos(rdev->ddev, crtc_id, + GET_DISTANCE_TO_VBLANKSTART, + &vpos, &hpos, NULL, NULL, + &rdev->mode_info.crtcs[crtc_id]->base.hwmode)) && + ((vpos >= 0 && hpos < 0) || (hpos >= 0 && !ASIC_IS_AVIVO(rdev)))) { /* crtc didn't flip in this target vblank interval, * but flip is pending in crtc. Based on the current * scanout position we know that the current frame is -- cgit v1.2.1 From 363926dc9ef65a3813fa778e85f85dd756c8652f Mon Sep 17 00:00:00 2001 From: Mario Kleiner Date: Sat, 17 Sep 2016 14:25:39 +0200 Subject: drm/radeon: Prevent races on pre DCE4 between flip submission and completion. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Pre DCE4 hw doesn't have reliable pageflip completion interrupts, so instead polling for flip completion is used from within the vblank irq handler to complete page flips. This causes a race if pageflip ioctl is called close to vblank: 1. pageflip ioctl queues execution of radeon_flip_work_func. 2. vblank irq fires, radeon_crtc_handle_vblank checks for flip_status == FLIP_SUBMITTED finds none, no-ops. 3. radeon_flip_work_func runs inside vblank, decides to set flip_status == FLIP_SUBMITTED and programs the flip into hw. 4. hw executes flip immediately (because in vblank), but as 2 already happened, the flip completion routine only emits the flip completion event one refresh later -> wrong vblank count/timestamp for completion and no performance gain, as instead of delaying the flip until next vblank, we now delay the next flip by 1 refresh while waiting for the delayed flip completion event. Given we often don't gain anything due to this race, but lose precision, prevent the programmed flip from executing in vblank on pre DCE4 asics to avoid this race. On pre-AVIVO hw we can't program the hw for edge-triggered flips, they always execute anywhere in vblank. Therefore delay the actual flip programming until after vblank on pre-AVIVO. Reviewed-by: Michel Dänzer Signed-off-by: Mario Kleiner Signed-off-by: Alex Deucher --- drivers/gpu/drm/radeon/atombios_crtc.c | 4 ++-- drivers/gpu/drm/radeon/radeon_display.c | 17 ++++++++++------- drivers/gpu/drm/radeon/rv515.c | 3 ++- 3 files changed, 14 insertions(+), 10 deletions(-) (limited to 'drivers/gpu/drm/radeon') diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index a4e9f35da3a2..74f99bac08b1 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -1638,8 +1638,8 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc, WREG32(AVIVO_D1MODE_VIEWPORT_SIZE + radeon_crtc->crtc_offset, (viewport_w << 16) | viewport_h); - /* set pageflip to happen anywhere in vblank interval */ - WREG32(AVIVO_D1MODE_MASTER_UPDATE_MODE + radeon_crtc->crtc_offset, 0); + /* set pageflip to happen only at start of vblank interval (front porch) */ + WREG32(AVIVO_D1MODE_MASTER_UPDATE_MODE + radeon_crtc->crtc_offset, 3); if (!atomic && fb && fb != crtc->primary->fb) { radeon_fb = to_radeon_framebuffer(fb); diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 50706464d456..b8ab30a7dd6d 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -452,16 +452,19 @@ static void radeon_flip_work_func(struct work_struct *__work) } /* Wait until we're out of the vertical blank period before the one - * targeted by the flip + * targeted by the flip. Always wait on pre DCE4 to avoid races with + * flip completion handling from vblank irq, as these old asics don't + * have reliable pageflip completion interrupts. */ while (radeon_crtc->enabled && - (radeon_get_crtc_scanoutpos(dev, work->crtc_id, 0, - &vpos, &hpos, NULL, NULL, - &crtc->hwmode) + (radeon_get_crtc_scanoutpos(dev, work->crtc_id, 0, + &vpos, &hpos, NULL, NULL, + &crtc->hwmode) & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_IN_VBLANK)) == - (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_IN_VBLANK) && - (int)(work->target_vblank - - dev->driver->get_vblank_counter(dev, work->crtc_id)) > 0) + (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_IN_VBLANK) && + (!ASIC_IS_AVIVO(rdev) || + ((int) (work->target_vblank - + dev->driver->get_vblank_counter(dev, work->crtc_id)) > 0))) usleep_range(1000, 2000); /* We borrow the event spin lock for protecting flip_status */ diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c index 76c55c5d11ec..c55d653aaf5f 100644 --- a/drivers/gpu/drm/radeon/rv515.c +++ b/drivers/gpu/drm/radeon/rv515.c @@ -406,8 +406,9 @@ void rv515_mc_resume(struct radeon_device *rdev, struct rv515_mc_save *save) for (i = 0; i < rdev->num_crtc; i++) { if (save->crtc_enabled[i]) { tmp = RREG32(AVIVO_D1MODE_MASTER_UPDATE_MODE + crtc_offsets[i]); - if ((tmp & 0x7) != 0) { + if ((tmp & 0x7) != 3) { tmp &= ~0x7; + tmp |= 0x3; WREG32(AVIVO_D1MODE_MASTER_UPDATE_MODE + crtc_offsets[i], tmp); } tmp = RREG32(AVIVO_D1GRPH_UPDATE + crtc_offsets[i]); -- cgit v1.2.1