Merge tag 'drm-misc-next-2018-02-13' of git://anongit.freedesktop.org/drm/drm-misc into drm-next

drm-misc-next for 4.17:

UAPI Changes:
- drm/vc4: Expose performance counters to userspace (Boris)

Cross-subsystem Changes:
- MAINTAINERS: Linus to maintain panel-arm-versatile in -misc (Linus)

Core Changes:
- Only use swiotlb when necessary (Chunming)

Driver Changes:
- drm/panel: Add support for ARM Versatile panels (Linus)
- pl111: Improvements around versatile panel support (Linus)

----------------------------------------
Tagged on 2018-02-06:
drm-misc-next for 4.17:

UAPI Changes:
- Validate mode flags + type (Ville)
- Deprecate unused mode flags PIXMUX, BCAST (Ville)
- Deprecate unused mode types BUILTIN, CRTC_C, CLOCK_C, DEFAULT (Ville)

Cross-subsystem Changes:
- MAINTAINERS: s/Daniel/Maarten/ for drm-misc (Daniel)

Core Changes:
- gem: Export gem functions for drivers to use (Samuel)
- bridge: Introduce bridge timings in drm_bridge (Linus)
- dma-buf: Allow exclusive fence to be bundled in fence array when
	   calling reservation_object_get_fences_rcu (Christian)
- dp: Add training pattern 4 and HBR3 support to dp helpers (Manasi)
- fourcc: Add alpha bit to formats to avoid driver format LUTs (Maxime)
- mode: Various cleanups + add new device-wide .mode_valid hook (Ville)
- atomic: Fix state leak when non-blocking commits fail (Leo)
	  NOTE: IIRC, this was cross-picked to -fixes so it might fall out
- crc: Allow polling on the data fd (Maarten)

Driver Changes:
- bridge/vga-dac: Add THS8134* support (Linus)
- tinydrm: Various MIPI DBI improvements/cleanups (Noralf)
- bridge/dw-mipi-dsi: Cleanups + use create_packet helper (Brian)
- drm/sun4i: Add Display Engine frontend support (Maxime)
- drm/sun4i: Add zpos support + increase num planes from 2 to 4 (Maxime)
- various: Use drm_mode_get_hv_timing() to fill plane clip rectangle (Ville)
- stm: Add 8-bit clut support, add dsi phy v1.31 support, +fixes (Phillipe)

Cc: Boris Brezillon <boris.brezillon@free-electrons.com>
Cc: Chunming Zhou <david1.zhou@amd.com>
Cc: Samuel Li <Samuel.Li@amd.com>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Noralf Trønnes <noralf@tronnes.org>
Cc: Brian Norris <briannorris@chromium.org>
Cc: Maxime Ripard <maxime.ripard@free-electrons.com>
Cc: Ville Syrjala <ville.syrjala@linux.intel.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Manasi Navare <manasi.d.navare@intel.com>
Cc: Philippe Cornu <philippe.cornu@st.com>
Cc: Leo (Sunpeng) Li <sunpeng.li@amd.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>

* tag 'drm-misc-next-2018-02-13' of git://anongit.freedesktop.org/drm/drm-misc: (115 commits)
  drm/radeon: only enable swiotlb path when need v2
  drm/amdgpu: only enable swiotlb alloc when need v2
  drm: add func to get max iomem address v2
  drm/vc4: Expose performance counters to userspace
  drm: Print the pid when debug logging an ioctl error.
  drm/stm: ltdc: remove non-alpha color formats on layer 2 for older hw
  drm/stm: ltdc: add non-alpha color formats
  drm/bridge/synopsys: dsi: Add 1.31 version support
  drm/bridge/synopsys: dsi: Add read feature
  drm/pl111: Support multiple endpoints on the CLCD
  drm/pl111: Support variants with broken VBLANK
  drm/pl111: Support variants with broken clock divider
  drm/pl111: Handle the Versatile RGB/BGR565 mode
  drm/pl111: Properly detect the ARM PL110 variants
  drm/panel: Add support for ARM Versatile panels
  drm/panel: Device tree bindings for ARM Versatile panels
  drm/bridge: Rename argument from crtc to bridge
  drm/crc: Add support for polling on the data fd.
  drm/sun4i: Use drm_mode_get_hv_timing() to populate plane clip rectangle
  drm/rcar-du: Use drm_mode_get_hv_timing() to populate plane clip rectangle
  ...

1 files changed, 43 insertions, 5 deletions

diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index c94cce96544c..2107b0daf8ef 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -467,14 +467,30 @@ again:
 
 	vc4_flush_caches(dev);
 
+	/* Only start the perfmon if it was not already started by a previous
+	 * job.
+	 */
+	if (exec->perfmon && vc4->active_perfmon != exec->perfmon)
+		vc4_perfmon_start(vc4, exec->perfmon);
+
 	/* Either put the job in the binner if it uses the binner, or
 	 * immediately move it to the to-be-rendered queue.
 	 */
 	if (exec->ct0ca != exec->ct0ea) {
 		submit_cl(dev, 0, exec->ct0ca, exec->ct0ea);
 	} else {
+		struct vc4_exec_info *next;
+
 		vc4_move_job_to_render(dev, exec);
-		goto again;
+		next = vc4_first_bin_job(vc4);
+
+		/* We can't start the next bin job if the previous job had a
+		 * different perfmon instance attached to it. The same goes
+		 * if one of them had a perfmon attached to it and the other
+		 * one doesn't.
+		 */
+		if (next && next->perfmon == exec->perfmon)
+			goto again;
 	}
 }
 
@@ -642,6 +658,7 @@ vc4_queue_submit(struct drm_device *dev, struct vc4_exec_info *exec,
 		 struct ww_acquire_ctx *acquire_ctx)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_exec_info *renderjob;
 	uint64_t seqno;
 	unsigned long irqflags;
 	struct vc4_fence *fence;
@@ -667,11 +684,14 @@ vc4_queue_submit(struct drm_device *dev, struct vc4_exec_info *exec,
 
 	list_add_tail(&exec->head, &vc4->bin_job_list);
 
-	/* If no job was executing, kick ours off.  Otherwise, it'll
-	 * get started when the previous job's flush done interrupt
-	 * occurs.
+	/* If no bin job was executing and if the render job (if any) has the
+	 * same perfmon as our job attached to it (or if both jobs don't have
+	 * perfmon activated), then kick ours off.  Otherwise, it'll get
+	 * started when the previous job's flush/render done interrupt occurs.
 	 */
-	if (vc4_first_bin_job(vc4) == exec) {
+	renderjob = vc4_first_render_job(vc4);
+	if (vc4_first_bin_job(vc4) == exec &&
+	    (!renderjob || renderjob->perfmon == exec->perfmon)) {
 		vc4_submit_next_bin_job(dev);
 		vc4_queue_hangcheck(dev);
 	}
@@ -936,6 +956,9 @@ vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec)
 	vc4->bin_alloc_used &= ~exec->bin_slots;
 	spin_unlock_irqrestore(&vc4->job_lock, irqflags);
 
+	/* Release the reference we had on the perf monitor. */
+	vc4_perfmon_put(exec->perfmon);
+
 	mutex_lock(&vc4->power_lock);
 	if (--vc4->power_refcount == 0) {
 		pm_runtime_mark_last_busy(&vc4->v3d->pdev->dev);
@@ -1088,6 +1111,7 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 		    struct drm_file *file_priv)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_file *vc4file = file_priv->driver_priv;
 	struct drm_vc4_submit_cl *args = data;
 	struct vc4_exec_info *exec;
 	struct ww_acquire_ctx acquire_ctx;
@@ -1101,6 +1125,11 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
+	if (args->pad2 != 0) {
+		DRM_DEBUG("->pad2 must be set to zero\n");
+		return -EINVAL;
+	}
+
 	exec = kcalloc(1, sizeof(*exec), GFP_KERNEL);
 	if (!exec) {
 		DRM_ERROR("malloc failure on exec struct\n");
@@ -1126,6 +1155,15 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		goto fail;
 
+	if (args->perfmonid) {
+		exec->perfmon = vc4_perfmon_find(vc4file,
+						 args->perfmonid);
+		if (!exec->perfmon) {
+			ret = -ENOENT;
+			goto fail;
+		}
+	}
+
 	if (exec->args->bin_cl_size != 0) {
 		ret = vc4_get_bcl(dev, exec);
 		if (ret)