1 files changed, 88 insertions, 92 deletions

diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 95069bb16821..221d8e01d539 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -5,6 +5,7 @@
 #ifndef _VC4_DRV_H_
 #define _VC4_DRV_H_
 
+#include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/of.h>
 #include <linux/refcount.h>
@@ -14,6 +15,7 @@
 #include <drm/drm_debugfs.h>
 #include <drm/drm_device.h>
 #include <drm/drm_encoder.h>
+#include <drm/drm_fourcc.h>
 #include <drm/drm_gem_dma_helper.h>
 #include <drm/drm_managed.h>
 #include <drm/drm_mm.h>
@@ -76,14 +78,21 @@ struct vc4_perfmon {
 	 * Note that counter values can't be reset, but you can fake a reset by
 	 * destroying the perfmon and creating a new one.
 	 */
-	u64 counters[];
+	u64 counters[] __counted_by(ncounters);
+};
+
+enum vc4_gen {
+	VC4_GEN_4,
+	VC4_GEN_5,
+	VC4_GEN_6_C,
+	VC4_GEN_6_D,
 };
 
 struct vc4_dev {
 	struct drm_device base;
 	struct device *dev;
 
-	bool is_vc5;
+	enum vc4_gen gen;
 
 	unsigned int irq;
 
@@ -177,11 +186,6 @@ struct vc4_dev {
 	 */
 	struct vc4_perfmon *active_perfmon;
 
-	/* List of struct vc4_seqno_cb for callbacks to be made from a
-	 * workqueue when the given seqno is passed.
-	 */
-	struct list_head seqno_cb_list;
-
 	/* The memory used for storing binner tile alloc, tile state,
 	 * and overflow memory allocations.  This is freed when V3D
 	 * powers down.
@@ -232,25 +236,12 @@ struct vc4_dev {
 	struct kref bin_bo_kref;
 };
 
-static inline struct vc4_dev *
-to_vc4_dev(const struct drm_device *dev)
-{
-	return container_of(dev, struct vc4_dev, base);
-}
+#define to_vc4_dev(_dev)			\
+	container_of_const(_dev, struct vc4_dev, base)
 
 struct vc4_bo {
 	struct drm_gem_dma_object base;
 
-	/* seqno of the last job to render using this BO. */
-	uint64_t seqno;
-
-	/* seqno of the last job to use the RCL to write to this BO.
-	 *
-	 * Note that this doesn't include binner overflow memory
-	 * writes.
-	 */
-	uint64_t write_seqno;
-
 	bool t_format;
 
 	/* List entry for the BO's position in either
@@ -285,11 +276,8 @@ struct vc4_bo {
 	struct mutex madv_lock;
 };
 
-static inline struct vc4_bo *
-to_vc4_bo(const struct drm_gem_object *bo)
-{
-	return container_of(to_drm_gem_dma_obj(bo), struct vc4_bo, base);
-}
+#define to_vc4_bo(_bo)							\
+	container_of_const(to_drm_gem_dma_obj(_bo), struct vc4_bo, base)
 
 struct vc4_fence {
 	struct dma_fence base;
@@ -298,17 +286,8 @@ struct vc4_fence {
 	uint64_t seqno;
 };
 
-static inline struct vc4_fence *
-to_vc4_fence(const struct dma_fence *fence)
-{
-	return container_of(fence, struct vc4_fence, base);
-}
-
-struct vc4_seqno_cb {
-	struct work_struct work;
-	uint64_t seqno;
-	void (*func)(struct vc4_seqno_cb *cb);
-};
+#define to_vc4_fence(_fence)					\
+	container_of_const(_fence, struct vc4_fence, base)
 
 struct vc4_v3d {
 	struct vc4_dev *vc4;
@@ -318,13 +297,30 @@ struct vc4_v3d {
 	struct debugfs_regset32 regset;
 };
 
+#define VC4_NUM_UPM_HANDLES 32
+struct vc4_upm_refcounts {
+	refcount_t refcount;
+
+	/* Allocation size */
+	size_t size;
+	/* Our allocation in UPM for prefetching. */
+	struct drm_mm_node upm;
+
+	/* Pointer back to the HVS structure */
+	struct vc4_hvs *hvs;
+};
+
+#define HVS_NUM_CHANNELS 3
+
 struct vc4_hvs {
 	struct vc4_dev *vc4;
 	struct platform_device *pdev;
 	void __iomem *regs;
 	u32 __iomem *dlist;
+	unsigned int dlist_mem_size;
 
 	struct clk *core_clk;
+	struct clk *disp_clk;
 
 	unsigned long max_core_rate;
 
@@ -332,8 +328,15 @@ struct vc4_hvs {
 	 * list.  Units are dwords.
 	 */
 	struct drm_mm dlist_mm;
+
 	/* Memory manager for the LBM memory used by HVS scaling. */
 	struct drm_mm lbm_mm;
+
+	/* Memory manager for the UPM memory used for prefetching. */
+	struct drm_mm upm_mm;
+	struct ida upm_handles;
+	struct vc4_upm_refcounts upm_refcounts[VC4_NUM_UPM_HANDLES + 1];
+
 	spinlock_t mm_lock;
 
 	struct drm_mm_node mitchell_netravali_filter;
@@ -356,6 +359,7 @@ struct vc4_hvs {
 };
 
 #define HVS_NUM_CHANNELS 3
+#define HVS_UBM_WORD_SIZE 256
 
 struct vc4_hvs_state {
 	struct drm_private_state base;
@@ -368,11 +372,8 @@ struct vc4_hvs_state {
 	} fifo_state[HVS_NUM_CHANNELS];
 };
 
-static inline struct vc4_hvs_state *
-to_vc4_hvs_state(const struct drm_private_state *priv)
-{
-	return container_of(priv, struct vc4_hvs_state, base);
-}
+#define to_vc4_hvs_state(_state)				\
+	container_of_const(_state, struct vc4_hvs_state, base)
 
 struct vc4_hvs_state *vc4_hvs_get_global_state(struct drm_atomic_state *state);
 struct vc4_hvs_state *vc4_hvs_get_old_global_state(const struct drm_atomic_state *state);
@@ -382,11 +383,8 @@ struct vc4_plane {
 	struct drm_plane base;
 };
 
-static inline struct vc4_plane *
-to_vc4_plane(const struct drm_plane *plane)
-{
-	return container_of(plane, struct vc4_plane, base);
-}
+#define to_vc4_plane(_plane)					\
+	container_of_const(_plane, struct vc4_plane, base)
 
 enum vc4_scaling_mode {
 	VC4_SCALING_NONE,
@@ -408,7 +406,7 @@ struct vc4_plane_state {
 	 */
 	u32 pos0_offset;
 	u32 pos2_offset;
-	u32 ptr0_offset;
+	u32 ptr0_offset[DRM_FORMAT_MAX_PLANES];
 	u32 lbm_offset;
 
 	/* Offset where the plane's dlist was last stored in the
@@ -418,7 +416,7 @@ struct vc4_plane_state {
 
 	/* Clipped coordinates of the plane on the display. */
 	int crtc_x, crtc_y, crtc_w, crtc_h;
-	/* Clipped area being scanned from in the FB. */
+	/* Clipped area being scanned from in the FB in u16.16 format */
 	u32 src_x, src_y;
 
 	u32 src_w[2], src_h[2];
@@ -428,14 +426,15 @@ struct vc4_plane_state {
 	bool is_unity;
 	bool is_yuv;
 
-	/* Offset to start scanning out from the start of the plane's
-	 * BO.
-	 */
-	u32 offsets[3];
-
 	/* Our allocation in LBM for temporary storage during scaling. */
 	struct drm_mm_node lbm;
 
+	/* The Unified Pre-Fetcher Handle */
+	unsigned int upm_handle[DRM_FORMAT_MAX_PLANES];
+
+	/* Number of lines to pre-fetch */
+	unsigned int upm_buffer_lines;
+
 	/* Set when the plane has per-pixel alpha content or does not cover
 	 * the entire screen. This is a hint to the CRTC that it might need
 	 * to enable background color fill.
@@ -458,11 +457,8 @@ struct vc4_plane_state {
 	u64 membus_load;
 };
 
-static inline struct vc4_plane_state *
-to_vc4_plane_state(const struct drm_plane_state *state)
-{
-	return container_of(state, struct vc4_plane_state, base);
-}
+#define to_vc4_plane_state(_state)				\
+	container_of_const(_state, struct vc4_plane_state, base)
 
 enum vc4_encoder_type {
 	VC4_ENCODER_TYPE_NONE,
@@ -473,7 +469,8 @@ enum vc4_encoder_type {
 	VC4_ENCODER_TYPE_DSI1,
 	VC4_ENCODER_TYPE_SMI,
 	VC4_ENCODER_TYPE_DPI,
-	VC4_ENCODER_TYPE_TXP,
+	VC4_ENCODER_TYPE_TXP0,
+	VC4_ENCODER_TYPE_TXP1,
 };
 
 struct vc4_encoder {
@@ -489,11 +486,8 @@ struct vc4_encoder {
 	void (*post_crtc_powerdown)(struct drm_encoder *encoder, struct drm_atomic_state *state);
 };
 
-static inline struct vc4_encoder *
-to_vc4_encoder(const struct drm_encoder *encoder)
-{
-	return container_of(encoder, struct vc4_encoder, base);
-}
+#define to_vc4_encoder(_encoder)				\
+	container_of_const(_encoder, struct vc4_encoder, base)
 
 static inline
 struct drm_encoder *vc4_find_encoder_by_type(struct drm_device *drm,
@@ -523,7 +517,16 @@ struct vc4_crtc_data {
 	int hvs_output;
 };
 
-extern const struct vc4_crtc_data vc4_txp_crtc_data;
+struct vc4_txp_data {
+	struct vc4_crtc_data	base;
+	enum vc4_encoder_type encoder_type;
+	unsigned int high_addr_ptr_reg;
+	unsigned int has_byte_enable:1;
+	unsigned int size_minus_one:1;
+	unsigned int supports_40bit_addresses:1;
+};
+
+extern const struct vc4_txp_data bcm2835_txp_data;
 
 struct vc4_pv_data {
 	struct vc4_crtc_data	base;
@@ -545,6 +548,8 @@ extern const struct vc4_pv_data bcm2711_pv1_data;
 extern const struct vc4_pv_data bcm2711_pv2_data;
 extern const struct vc4_pv_data bcm2711_pv3_data;
 extern const struct vc4_pv_data bcm2711_pv4_data;
+extern const struct vc4_pv_data bcm2712_pv0_data;
+extern const struct vc4_pv_data bcm2712_pv1_data;
 
 struct vc4_crtc {
 	struct drm_crtc base;
@@ -591,11 +596,8 @@ struct vc4_crtc {
 	unsigned int current_hvs_channel;
 };
 
-static inline struct vc4_crtc *
-to_vc4_crtc(const struct drm_crtc *crtc)
-{
-	return container_of(crtc, struct vc4_crtc, base);
-}
+#define to_vc4_crtc(_crtc)					\
+	container_of_const(_crtc, struct vc4_crtc, base)
 
 static inline const struct vc4_crtc_data *
 vc4_crtc_to_vc4_crtc_data(const struct vc4_crtc *crtc)
@@ -608,7 +610,7 @@ vc4_crtc_to_vc4_pv_data(const struct vc4_crtc *crtc)
 {
 	const struct vc4_crtc_data *data = vc4_crtc_to_vc4_crtc_data(crtc);
 
-	return container_of(data, struct vc4_pv_data, base);
+	return container_of_const(data, struct vc4_pv_data, base);
 }
 
 struct drm_encoder *vc4_get_crtc_encoder(struct drm_crtc *crtc,
@@ -621,12 +623,7 @@ struct vc4_crtc_state {
 	bool txp_armed;
 	unsigned int assigned_channel;
 
-	struct {
-		unsigned int left;
-		unsigned int right;
-		unsigned int top;
-		unsigned int bottom;
-	} margins;
+	struct drm_connector_tv_margins margins;
 
 	unsigned long hvs_load;
 
@@ -636,11 +633,8 @@ struct vc4_crtc_state {
 
 #define VC4_HVS_CHANNEL_DISABLED ((unsigned int)-1)
 
-static inline struct vc4_crtc_state *
-to_vc4_crtc_state(const struct drm_crtc_state *crtc_state)
-{
-	return container_of(crtc_state, struct vc4_crtc_state, base);
-}
+#define to_vc4_crtc_state(_state)				\
+	container_of_const(_state, struct vc4_crtc_state, base)
 
 #define V3D_READ(offset)								\
 	({										\
@@ -666,6 +660,12 @@ to_vc4_crtc_state(const struct drm_crtc_state *crtc_state)
 		writel(val, hvs->regs + (offset));					\
 	} while (0)
 
+#define HVS_READ6(offset) \
+	HVS_READ(hvs->vc4->gen == VC4_GEN_6_C ? SCALER6_ ## offset : SCALER6D_ ## offset)
+
+#define HVS_WRITE6(offset, val) \
+	HVS_WRITE(hvs->vc4->gen == VC4_GEN_6_C ? SCALER6_ ## offset : SCALER6D_ ## offset, val)
+
 #define VC4_REG32(reg) { .name = #reg, .offset = reg }
 
 struct vc4_exec_info {
@@ -674,9 +674,6 @@ struct vc4_exec_info {
 	/* Sequence number for this bin/render job. */
 	uint64_t seqno;
 
-	/* Latest write_seqno of any BO that binning depends on. */
-	uint64_t bin_dep_seqno;
-
 	struct dma_fence *fence;
 
 	/* Last current addresses the hardware was processing when the
@@ -690,7 +687,7 @@ struct vc4_exec_info {
 	/* This is the array of BOs that were looked up at the start of exec.
 	 * Command validation will use indices into this array.
 	 */
-	struct drm_gem_dma_object **bo;
+	struct drm_gem_object **bo;
 	uint32_t bo_count;
 
 	/* List of BOs that are being written by the RCL.  Other than
@@ -1004,9 +1001,6 @@ void vc4_move_job_to_render(struct drm_device *dev, struct vc4_exec_info *exec);
 int vc4_wait_for_seqno(struct drm_device *dev, uint64_t seqno,
 		       uint64_t timeout_ns, bool interruptible);
 void vc4_job_handle_completed(struct vc4_dev *vc4);
-int vc4_queue_seqno_cb(struct drm_device *dev,
-		       struct vc4_seqno_cb *cb, uint64_t seqno,
-		       void (*func)(struct vc4_seqno_cb *cb));
 int vc4_gem_madvise_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *file_priv);
 
@@ -1028,7 +1022,9 @@ void vc4_irq_reset(struct drm_device *dev);
 
 /* vc4_hvs.c */
 extern struct platform_driver vc4_hvs_driver;
-struct vc4_hvs *__vc4_hvs_alloc(struct vc4_dev *vc4, struct platform_device *pdev);
+struct vc4_hvs *__vc4_hvs_alloc(struct vc4_dev *vc4,
+				void __iomem *regs,
+				struct platform_device *pdev);
 void vc4_hvs_stop_channel(struct vc4_hvs *hvs, unsigned int output);
 int vc4_hvs_get_fifo_from_output(struct vc4_hvs *hvs, unsigned int output);
 u8 vc4_hvs_get_fifo_frame_count(struct vc4_hvs *hvs, unsigned int fifo);