Merge tag 'drm-misc-fixes-2023-12-07' of git://anongit.freedesktop.org/drm/drm-misc into drm-fixes

drm-misc-fixes for v6.7-rc5:
- Document nouveau's GSP-RM.
- Flush vmm harder on nouveau tu102.
- Panfrost fix for imported dma-buf objects, and device frequency.
- Kconfig Build fix for tc358768.
- Call end_fb_access after atomic commit.

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/05a26dc0-8cf1-4b1f-abb6-3bf471fbfc99@linux.intel.com

10 files changed, 207 insertions, 32 deletions

diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig
index ba82a1142adf73..3e6a4e2044c0eb 100644
--- a/drivers/gpu/drm/bridge/Kconfig
+++ b/drivers/gpu/drm/bridge/Kconfig
@@ -313,6 +313,7 @@ config DRM_TOSHIBA_TC358768
 	select REGMAP_I2C
 	select DRM_PANEL
 	select DRM_MIPI_DSI
+	select VIDEOMODE_HELPERS
 	help
 	  Toshiba TC358768AXBG/TC358778XBG DSI bridge chip driver.
 
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 2444fc33dd7c77..68ffcc0b00dca1 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -2012,7 +2012,7 @@ int drm_atomic_helper_commit(struct drm_device *dev,
 			return ret;
 
 		drm_atomic_helper_async_commit(dev, state);
-		drm_atomic_helper_cleanup_planes(dev, state);
+		drm_atomic_helper_unprepare_planes(dev, state);
 
 		return 0;
 	}
@@ -2072,7 +2072,7 @@ int drm_atomic_helper_commit(struct drm_device *dev,
 	return 0;
 
 err:
-	drm_atomic_helper_cleanup_planes(dev, state);
+	drm_atomic_helper_unprepare_planes(dev, state);
 	return ret;
 }
 EXPORT_SYMBOL(drm_atomic_helper_commit);
@@ -2650,6 +2650,39 @@ fail_prepare_fb:
 }
 EXPORT_SYMBOL(drm_atomic_helper_prepare_planes);
 
+/**
+ * drm_atomic_helper_unprepare_planes - release plane resources on aborts
+ * @dev: DRM device
+ * @state: atomic state object with old state structures
+ *
+ * This function cleans up plane state, specifically framebuffers, from the
+ * atomic state. It undoes the effects of drm_atomic_helper_prepare_planes()
+ * when aborting an atomic commit. For cleaning up after a successful commit
+ * use drm_atomic_helper_cleanup_planes().
+ */
+void drm_atomic_helper_unprepare_planes(struct drm_device *dev,
+					struct drm_atomic_state *state)
+{
+	struct drm_plane *plane;
+	struct drm_plane_state *new_plane_state;
+	int i;
+
+	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
+		const struct drm_plane_helper_funcs *funcs = plane->helper_private;
+
+		if (funcs->end_fb_access)
+			funcs->end_fb_access(plane, new_plane_state);
+	}
+
+	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
+		const struct drm_plane_helper_funcs *funcs = plane->helper_private;
+
+		if (funcs->cleanup_fb)
+			funcs->cleanup_fb(plane, new_plane_state);
+	}
+}
+EXPORT_SYMBOL(drm_atomic_helper_unprepare_planes);
+
 static bool plane_crtc_active(const struct drm_plane_state *state)
 {
 	return state->crtc && state->crtc->state->active;
@@ -2784,6 +2817,17 @@ void drm_atomic_helper_commit_planes(struct drm_device *dev,
 
 		funcs->atomic_flush(crtc, old_state);
 	}
+
+	/*
+	 * Signal end of framebuffer access here before hw_done. After hw_done,
+	 * a later commit might have already released the plane state.
+	 */
+	for_each_old_plane_in_state(old_state, plane, old_plane_state, i) {
+		const struct drm_plane_helper_funcs *funcs = plane->helper_private;
+
+		if (funcs->end_fb_access)
+			funcs->end_fb_access(plane, old_plane_state);
+	}
 }
 EXPORT_SYMBOL(drm_atomic_helper_commit_planes);
 
@@ -2911,40 +2955,22 @@ EXPORT_SYMBOL(drm_atomic_helper_disable_planes_on_crtc);
  * configuration. Hence the old configuration must be perserved in @old_state to
  * be able to call this function.
  *
- * This function must also be called on the new state when the atomic update
- * fails at any point after calling drm_atomic_helper_prepare_planes().
+ * This function may not be called on the new state when the atomic update
+ * fails at any point after calling drm_atomic_helper_prepare_planes(). Use
+ * drm_atomic_helper_unprepare_planes() in this case.
  */
 void drm_atomic_helper_cleanup_planes(struct drm_device *dev,
 				      struct drm_atomic_state *old_state)
 {
 	struct drm_plane *plane;
-	struct drm_plane_state *old_plane_state, *new_plane_state;
+	struct drm_plane_state *old_plane_state;
 	int i;
 
-	for_each_oldnew_plane_in_state(old_state, plane, old_plane_state, new_plane_state, i) {
+	for_each_old_plane_in_state(old_state, plane, old_plane_state, i) {
 		const struct drm_plane_helper_funcs *funcs = plane->helper_private;
 
-		if (funcs->end_fb_access)
-			funcs->end_fb_access(plane, new_plane_state);
-	}
-
-	for_each_oldnew_plane_in_state(old_state, plane, old_plane_state, new_plane_state, i) {
-		const struct drm_plane_helper_funcs *funcs;
-		struct drm_plane_state *plane_state;
-
-		/*
-		 * This might be called before swapping when commit is aborted,
-		 * in which case we have to cleanup the new state.
-		 */
-		if (old_plane_state == plane->state)
-			plane_state = new_plane_state;
-		else
-			plane_state = old_plane_state;
-
-		funcs = plane->helper_private;
-
 		if (funcs->cleanup_fb)
-			funcs->cleanup_fb(plane, plane_state);
+			funcs->cleanup_fb(plane, old_plane_state);
 	}
 }
 EXPORT_SYMBOL(drm_atomic_helper_cleanup_planes);
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 4ee7d569b379cb..63ba4d54a71529 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -7488,7 +7488,7 @@ int intel_atomic_commit(struct drm_device *dev, struct drm_atomic_state *_state,
 		for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i)
 			intel_color_cleanup_commit(new_crtc_state);
 
-		drm_atomic_helper_cleanup_planes(dev, &state->base);
+		drm_atomic_helper_unprepare_planes(dev, &state->base);
 		intel_runtime_pm_put(&dev_priv->runtime_pm, state->wakeref);
 		return ret;
 	}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 7840b6428afbe4..118807e38422b6 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -2474,7 +2474,7 @@ nv50_disp_atomic_commit(struct drm_device *dev,
 
 err_cleanup:
 	if (ret)
-		drm_atomic_helper_cleanup_planes(dev, state);
+		drm_atomic_helper_unprepare_planes(dev, state);
 done:
 	pm_runtime_put_autosuspend(dev->dev);
 	return ret;
diff --git a/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/common/shared/msgq/inc/msgq/msgq_priv.h b/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/common/shared/msgq/inc/msgq/msgq_priv.h
index 5a2f273d95c8cf..0e32e71e123f37 100644
--- a/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/common/shared/msgq/inc/msgq/msgq_priv.h
+++ b/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/common/shared/msgq/inc/msgq/msgq_priv.h
@@ -26,6 +26,49 @@
  * DEALINGS IN THE SOFTWARE.
  */
 
+/**
+ * msgqTxHeader -- TX queue data structure
+ * @version: the version of this structure, must be 0
+ * @size: the size of the entire queue, including this header
+ * @msgSize: the padded size of queue element, 16 is minimum
+ * @msgCount: the number of elements in this queue
+ * @writePtr: head index of this queue
+ * @flags: 1 = swap the RX pointers
+ * @rxHdrOff: offset of readPtr in this structure
+ * @entryOff: offset of beginning of queue (msgqRxHeader), relative to
+ *          beginning of this structure
+ *
+ * The command queue is a queue of RPCs that are sent from the driver to the
+ * GSP.  The status queue is a queue of messages/responses from GSP-RM to the
+ * driver.  Although the driver allocates memory for both queues, the command
+ * queue is owned by the driver and the status queue is owned by GSP-RM.  In
+ * addition, the headers of the two queues must not share the same 4K page.
+ *
+ * Each queue is prefixed with this data structure.  The idea is that a queue
+ * and its header are written to only by their owner.  That is, only the
+ * driver writes to the command queue and command queue header, and only the
+ * GSP writes to the status (receive) queue and its header.
+ *
+ * This is enforced by the concept of "swapping" the RX pointers.  This is
+ * why the 'flags' field must be set to 1.  'rxHdrOff' is how the GSP knows
+ * where the where the tail pointer of its status queue.
+ *
+ * When the driver writes a new RPC to the command queue, it updates writePtr.
+ * When it reads a new message from the status queue, it updates readPtr.  In
+ * this way, the GSP knows when a new command is in the queue (it polls
+ * writePtr) and it knows how much free space is in the status queue (it
+ * checks readPtr).  The driver never cares about how much free space is in
+ * the status queue.
+ *
+ * As usual, producers write to the head pointer, and consumers read from the
+ * tail pointer.  When head == tail, the queue is empty.
+ *
+ * So to summarize:
+ * command.writePtr = head of command queue
+ * command.readPtr = tail of status queue
+ * status.writePtr = head of status queue
+ * status.readPtr = tail of command queue
+ */
 typedef struct
 {
     NvU32 version;   // queue version
@@ -38,6 +81,14 @@ typedef struct
     NvU32 entryOff;  // Offset of entries from start of backing store.
 } msgqTxHeader;
 
+/**
+ * msgqRxHeader - RX queue data structure
+ * @readPtr: tail index of the other queue
+ *
+ * Although this is a separate struct, it could easily be merged into
+ * msgqTxHeader.  msgqTxHeader.rxHdrOff is simply the offset of readPtr
+ * from the beginning of msgqTxHeader.
+ */
 typedef struct
 {
     NvU32 readPtr; // message id of last message read
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index f6725a5f5bfb8a..44fb86841c058a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -1377,6 +1377,13 @@ r535_gsp_msg_post_event(void *priv, u32 fn, void *repv, u32 repc)
 	return 0;
 }
 
+/**
+ * r535_gsp_msg_run_cpu_sequencer() -- process I/O commands from the GSP
+ *
+ * The GSP sequencer is a list of I/O commands that the GSP can send to
+ * the driver to perform for various purposes.  The most common usage is to
+ * perform a special mid-initialization reset.
+ */
 static int
 r535_gsp_msg_run_cpu_sequencer(void *priv, u32 fn, void *repv, u32 repc)
 {
@@ -1716,6 +1723,23 @@ r535_gsp_libos_id8(const char *name)
 	return id;
 }
 
+/**
+ * create_pte_array() - creates a PTE array of a physically contiguous buffer
+ * @ptes: pointer to the array
+ * @addr: base address of physically contiguous buffer (GSP_PAGE_SIZE aligned)
+ * @size: size of the buffer
+ *
+ * GSP-RM sometimes expects physically-contiguous buffers to have an array of
+ * "PTEs" for each page in that buffer.  Although in theory that allows for
+ * the buffer to be physically discontiguous, GSP-RM does not currently
+ * support that.
+ *
+ * In this case, the PTEs are DMA addresses of each page of the buffer.  Since
+ * the buffer is physically contiguous, calculating all the PTEs is simple
+ * math.
+ *
+ * See memdescGetPhysAddrsForGpu()
+ */
 static void create_pte_array(u64 *ptes, dma_addr_t addr, size_t size)
 {
 	unsigned int num_pages = DIV_ROUND_UP_ULL(size, GSP_PAGE_SIZE);
@@ -1725,6 +1749,35 @@ static void create_pte_array(u64 *ptes, dma_addr_t addr, size_t size)
 		ptes[i] = (u64)addr + (i << GSP_PAGE_SHIFT);
 }
 
+/**
+ * r535_gsp_libos_init() -- create the libos arguments structure
+ *
+ * The logging buffers are byte queues that contain encoded printf-like
+ * messages from GSP-RM.  They need to be decoded by a special application
+ * that can parse the buffers.
+ *
+ * The 'loginit' buffer contains logs from early GSP-RM init and
+ * exception dumps.  The 'logrm' buffer contains the subsequent logs. Both are
+ * written to directly by GSP-RM and can be any multiple of GSP_PAGE_SIZE.
+ *
+ * The physical address map for the log buffer is stored in the buffer
+ * itself, starting with offset 1. Offset 0 contains the "put" pointer.
+ *
+ * The GSP only understands 4K pages (GSP_PAGE_SIZE), so even if the kernel is
+ * configured for a larger page size (e.g. 64K pages), we need to give
+ * the GSP an array of 4K pages. Fortunately, since the buffer is
+ * physically contiguous, it's simple math to calculate the addresses.
+ *
+ * The buffers must be a multiple of GSP_PAGE_SIZE.  GSP-RM also currently
+ * ignores the @kind field for LOGINIT, LOGINTR, and LOGRM, but expects the
+ * buffers to be physically contiguous anyway.
+ *
+ * The memory allocated for the arguments must remain until the GSP sends the
+ * init_done RPC.
+ *
+ * See _kgspInitLibosLoggingStructures (allocates memory for buffers)
+ * See kgspSetupLibosInitArgs_IMPL (creates pLibosInitArgs[] array)
+ */
 static int
 r535_gsp_libos_init(struct nvkm_gsp *gsp)
 {
@@ -1835,6 +1888,35 @@ nvkm_gsp_radix3_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_radix3 *rx3)
 		nvkm_gsp_mem_dtor(gsp, &rx3->mem[i]);
 }
 
+/**
+ * nvkm_gsp_radix3_sg - build a radix3 table from a S/G list
+ *
+ * The GSP uses a three-level page table, called radix3, to map the firmware.
+ * Each 64-bit "pointer" in the table is either the bus address of an entry in
+ * the next table (for levels 0 and 1) or the bus address of the next page in
+ * the GSP firmware image itself.
+ *
+ * Level 0 contains a single entry in one page that points to the first page
+ * of level 1.
+ *
+ * Level 1, since it's also only one page in size, contains up to 512 entries,
+ * one for each page in Level 2.
+ *
+ * Level 2 can be up to 512 pages in size, and each of those entries points to
+ * the next page of the firmware image.  Since there can be up to 512*512
+ * pages, that limits the size of the firmware to 512*512*GSP_PAGE_SIZE = 1GB.
+ *
+ * Internally, the GSP has its window into system memory, but the base
+ * physical address of the aperture is not 0.  In fact, it varies depending on
+ * the GPU architecture.  Since the GPU is a PCI device, this window is
+ * accessed via DMA and is therefore bound by IOMMU translation.  The end
+ * result is that GSP-RM must translate the bus addresses in the table to GSP
+ * physical addresses.  All this should happen transparently.
+ *
+ * Returns 0 on success, or negative error code
+ *
+ * See kgspCreateRadix3_IMPL
+ */
 static int
 nvkm_gsp_radix3_sg(struct nvkm_device *device, struct sg_table *sgt, u64 size,
 		   struct nvkm_gsp_radix3 *rx3)
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c
index e34bc60764010f..8379e72d77ab2b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c
@@ -31,7 +31,7 @@ tu102_vmm_flush(struct nvkm_vmm *vmm, int depth)
 
 	type |= 0x00000001; /* PAGE_ALL */
 	if (atomic_read(&vmm->engref[NVKM_SUBDEV_BAR]))
-		type |= 0x00000004; /* HUB_ONLY */
+		type |= 0x00000006; /* HUB_ONLY | ALL PDB (hack) */
 
 	mutex_lock(&vmm->mmu->mutex);
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
index f59c82ea887013..2d30da38c2c3e4 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
@@ -29,14 +29,20 @@ static void panfrost_devfreq_update_utilization(struct panfrost_devfreq *pfdevfr
 static int panfrost_devfreq_target(struct device *dev, unsigned long *freq,
 				   u32 flags)
 {
+	struct panfrost_device *ptdev = dev_get_drvdata(dev);
 	struct dev_pm_opp *opp;
+	int err;
 
 	opp = devfreq_recommended_opp(dev, freq, flags);
 	if (IS_ERR(opp))
 		return PTR_ERR(opp);
 	dev_pm_opp_put(opp);
 
-	return dev_pm_opp_set_rate(dev, *freq);
+	err =  dev_pm_opp_set_rate(dev, *freq);
+	if (!err)
+		ptdev->pfdevfreq.current_frequency = *freq;
+
+	return err;
 }
 
 static void panfrost_devfreq_reset(struct panfrost_devfreq *pfdevfreq)
@@ -58,7 +64,6 @@ static int panfrost_devfreq_get_dev_status(struct device *dev,
 	spin_lock_irqsave(&pfdevfreq->lock, irqflags);
 
 	panfrost_devfreq_update_utilization(pfdevfreq);
-	pfdevfreq->current_frequency = status->current_frequency;
 
 	status->total_time = ktime_to_ns(ktime_add(pfdevfreq->busy_time,
 						   pfdevfreq->idle_time));
@@ -165,6 +170,14 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev)
 	panfrost_devfreq_profile.initial_freq = cur_freq;
 
 	/*
+	 * We could wait until panfrost_devfreq_target() to set this value, but
+	 * since the simple_ondemand governor works asynchronously, there's a
+	 * chance by the time someone opens the device's fdinfo file, current
+	 * frequency hasn't been updated yet, so let's just do an early set.
+	 */
+	pfdevfreq->current_frequency = cur_freq;
+
+	/*
 	 * Set the recommend OPP this will enable and configure the regulator
 	 * if any and will avoid a switch off by regulator_late_cleanup()
 	 */
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c
index 0cf64456e29a4f..d47b40b82b0bc4 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.c
@@ -200,7 +200,7 @@ static enum drm_gem_object_status panfrost_gem_status(struct drm_gem_object *obj
 	struct panfrost_gem_object *bo = to_panfrost_bo(obj);
 	enum drm_gem_object_status res = 0;
 
-	if (bo->base.pages)
+	if (bo->base.base.import_attach || bo->base.pages)
 		res |= DRM_GEM_OBJECT_RESIDENT;
 
 	if (bo->base.madv == PANFROST_MADV_DONTNEED)
diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h
index 536a0b0091c3a9..006b5c977ad772 100644
--- a/include/drm/drm_atomic_helper.h
+++ b/include/drm/drm_atomic_helper.h
@@ -97,6 +97,8 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev,
 
 int drm_atomic_helper_prepare_planes(struct drm_device *dev,
 				     struct drm_atomic_state *state);
+void drm_atomic_helper_unprepare_planes(struct drm_device *dev,
+					struct drm_atomic_state *state);
 
 #define DRM_PLANE_COMMIT_ACTIVE_ONLY			BIT(0)
 #define DRM_PLANE_COMMIT_NO_DISABLE_AFTER_MODESET	BIT(1)