Merge tag 'drm-next-2020-01-30' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Davbe Airlie:
 "This is the main pull request for graphics for 5.6. Usual selection of
  changes all over.

  I've got one outstanding vmwgfx pull that touches mm so kept it
  separate until after all of this lands. I'll try and get it to you
  soon after this, but it might be early next week (nothing wrong with
  code, just my schedule is messy)

  This also hits a lot of fbdev drivers with some cleanups.

  Other notables:
   - vulkan timeline semaphore support added to syncobjs
   - nouveau turing secureboot/graphics support
   - Displayport MST display stream compression support

  Detailed summary:

  uapi:
   - dma-buf heaps added (and fixed)
   - command line add support for panel oreientation
   - command line allow overriding penguin count

  drm:
   - mipi dsi definition updates
   - lockdep annotations for dma_resv
   - remove dma-buf kmap/kunmap support
   - constify fb_ops in all fbdev drivers
   - MST fix for daisy chained hotplug-
   - CTA-861-G modes with VIC >= 193 added
   - fix drm_panel_of_backlight export
   - LVDS decoder support
   - more device based logging support
   - scanline alighment for dumb buffers
   - MST DSC helpers

  scheduler:
   - documentation fixes
   - job distribution improvements

  panel:
   - Logic PD type 28 panel support
   - Jimax8729d MIPI-DSI
   - igenic JZ4770
   - generic DSI devicetree bindings
   - sony acx424AKP panel
   - Leadtek LTK500HD1829
   - xinpeng XPP055C272
   - AUO B116XAK01
   - GiantPlus GPM940B0
   - BOE NV140FHM-N49
   - Satoz SAT050AT40H12R2
   - Sharp LS020B1DD01D panels.

  ttm:
   - use blocking WW lock

  i915:
   - hw/uapi state separation
   - Lock annotation improvements
   - selftest improvements
   - ICL/TGL DSI VDSC support
   - VBT parsing improvments
   - Display refactoring
   - DSI updates + fixes
   - HDCP 2.2 for CFL
   - CML PCI ID fixes
   - GLK+ fbc fix
   - PSR fixes
   - GEN/GT refactor improvments
   - DP MST fixes
   - switch context id alloc to xarray
   - workaround updates
   - LMEM debugfs support
   - tiled monitor fixes
   - ICL+ clock gating programming removed
   - DP MST disable sequence fixed
   - LMEM discontiguous object maps
   - prefaulting for discontiguous objects
   - use LMEM for dumb buffers if possible
   - add LMEM mmap support

  amdgpu:
   - enable sync object timelines for vulkan
   - MST atomic routines
   - enable MST DSC support
   - add DMCUB display microengine support
   - DC OEM i2c support
   - Renoir DC fixes
   - Initial HDCP 2.x support
   - BACO support for Arcturus
   - Use BACO for runtime PM power save
   - gfxoff on navi10
   - gfx10 golden updates and fixes
   - DCN support on POWER
   - GFXOFF for raven1 refresh
   - MM engine idle handlers cleanup
   - 10bpc EDP panel fixes
   - renoir watermark fixes
   - SR-IOV fixes
   - Arcturus VCN fixes
   - GDDR6 training fixes
   - freesync fixes
   - Pollock support

  amdkfd:
   - unify more codepath with amdgpu
   - use KIQ to setup HIQ rather than MMIO

  radeon:
   - fix vma fault handler race
   - PPC DMA fix
   - register check fixes for r100/r200

  nouveau:
   - mmap_sem vs dma_resv fix
   - rewrite the ACR secure boot code for Turing
   - TU10x graphics engine support (TU11x pending)
   - Page kind mapping for turing
   - 10-bit LUT support
   - GP10B Tegra fixes
   - HD audio regression fix

  hisilicon/hibmc:
   - use generic fbdev code and helpers

  rockchip:
   - dsi/px30 support

  virtio:
   - fb damage support
   - static some functions

  vc4:
   - use dma_resv lock wrappers

  msm:
   - use dma_resv lock wrappers
   - sc7180 display + DSI support
   - a618 support
   - UBWC support improvements

  vmwgfx:
   - updates + new logging uapi

  exynos:
   - enable/disable callback cleanups

  etnaviv:
   - use dma_resv lock wrappers

  atmel-hlcdc:
   - clock fixes

  mediatek:
   - cmdq support
   - non-smooth cursor fixes
   - ctm property support

  sun4i:
   - suspend support
   - A64 mipi dsi support

  rcar-du:
   - Color management module support
   - LVDS encoder dual-link support
   - R8A77980 support

  analogic:
   - add support for an6345

  ast:
   - atomic modeset support
   - primary plane garbage fix

  arcgpu:
   - fixes for fourcc handling

  tegra:
   - minor fixes and improvments

  mcde:
   - vblank support

  meson:
   - OSD1 plane AFBC commit

  gma500:
   - add pageflip support
   - reomve global drm_dev

  komeda:
   - tweak debugfs output
   - d32 support
   - runtime PM suppotr

  udl:
   - use generic shmem helpers
   - cleanup and fixes"

* tag 'drm-next-2020-01-30' of git://anongit.freedesktop.org/drm/drm: (1998 commits)
  drm/nouveau/fb/gp102-: allow module to load even when scrubber binary is missing
  drm/nouveau/acr: return error when registering LSF if ACR not supported
  drm/nouveau/disp/gv100-: not all channel types support reporting error codes
  drm/nouveau/disp/nv50-: prevent oops when no channel method map provided
  drm/nouveau: support synchronous pushbuf submission
  drm/nouveau: signal pending fences when channel has been killed
  drm/nouveau: reject attempts to submit to dead channels
  drm/nouveau: zero vma pointer even if we only unreference it rather than free
  drm/nouveau: Add HD-audio component notifier support
  drm/nouveau: fix build error without CONFIG_IOMMU_API
  drm/nouveau/kms/nv04: remove set but not used variable 'width'
  drm/nouveau/kms/nv50: remove set but not unused variable 'nv_connector'
  drm/nouveau/mmu: fix comptag memory leak
  drm/nouveau/gr/gp10b: Use gp100_grctx and gp100_gr_zbc
  drm/nouveau/pmu/gm20b,gp10b: Fix Falcon bootstrapping
  drm/exynos: Rename Exynos to lowercase
  drm/exynos: change callback names
  drm/mst: Don't do atomic checks over disabled managers
  drm/amdgpu: add the lost mutex_init back
  drm/amd/display: skip opp blank or unblank if test pattern enabled
  ...

12 files changed, 1125 insertions, 46 deletions

diff --git a/drivers/gpu/drm/meson/Makefile b/drivers/gpu/drm/meson/Makefile
index c389e2399133..28a519cdf66b 100644
--- a/drivers/gpu/drm/meson/Makefile
+++ b/drivers/gpu/drm/meson/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 meson-drm-y := meson_drv.o meson_plane.o meson_crtc.o meson_venc_cvbs.o
 meson-drm-y += meson_viu.o meson_vpp.o meson_venc.o meson_vclk.o meson_overlay.o
+meson-drm-y += meson_rdma.o meson_osd_afbcd.o
 
 obj-$(CONFIG_DRM_MESON) += meson-drm.o
 obj-$(CONFIG_DRM_MESON_DW_HDMI) += meson_dw_hdmi.o
diff --git a/drivers/gpu/drm/meson/meson_crtc.c b/drivers/gpu/drm/meson/meson_crtc.c
index 57ae1c13d1e6..e66b6271ff58 100644
--- a/drivers/gpu/drm/meson/meson_crtc.c
+++ b/drivers/gpu/drm/meson/meson_crtc.c
@@ -23,7 +23,9 @@
 #include "meson_registers.h"
 #include "meson_venc.h"
 #include "meson_viu.h"
+#include "meson_rdma.h"
 #include "meson_vpp.h"
+#include "meson_osd_afbcd.h"
 
 #define MESON_G12A_VIU_OFFSET	0x5ec0
 
@@ -35,7 +37,11 @@ struct meson_crtc {
 	struct meson_drm *priv;
 	void (*enable_osd1)(struct meson_drm *priv);
 	void (*enable_vd1)(struct meson_drm *priv);
+	void (*enable_osd1_afbc)(struct meson_drm *priv);
+	void (*disable_osd1_afbc)(struct meson_drm *priv);
 	unsigned int viu_offset;
+	bool vsync_forced;
+	bool vsync_disabled;
 };
 #define to_meson_crtc(x) container_of(x, struct meson_crtc, base)
 
@@ -46,6 +52,7 @@ static int meson_crtc_enable_vblank(struct drm_crtc *crtc)
 	struct meson_crtc *meson_crtc = to_meson_crtc(crtc);
 	struct meson_drm *priv = meson_crtc->priv;
 
+	meson_crtc->vsync_disabled = false;
 	meson_venc_enable_vsync(priv);
 
 	return 0;
@@ -56,7 +63,10 @@ static void meson_crtc_disable_vblank(struct drm_crtc *crtc)
 	struct meson_crtc *meson_crtc = to_meson_crtc(crtc);
 	struct meson_drm *priv = meson_crtc->priv;
 
-	meson_venc_disable_vsync(priv);
+	if (!meson_crtc->vsync_forced) {
+		meson_crtc->vsync_disabled = true;
+		meson_venc_disable_vsync(priv);
+	}
 }
 
 static const struct drm_crtc_funcs meson_crtc_funcs = {
@@ -236,6 +246,26 @@ static void meson_crtc_enable_osd1(struct meson_drm *priv)
 			    priv->io_base + _REG(VPP_MISC));
 }
 
+static void meson_crtc_g12a_enable_osd1_afbc(struct meson_drm *priv)
+{
+	writel_relaxed(priv->viu.osd1_blk2_cfg4,
+		       priv->io_base + _REG(VIU_OSD1_BLK2_CFG_W4));
+
+	writel_bits_relaxed(OSD_MEM_LINEAR_ADDR, OSD_MEM_LINEAR_ADDR,
+			    priv->io_base + _REG(VIU_OSD1_CTRL_STAT));
+
+	writel_relaxed(priv->viu.osd1_blk1_cfg4,
+		       priv->io_base + _REG(VIU_OSD1_BLK1_CFG_W4));
+
+	meson_viu_g12a_enable_osd1_afbc(priv);
+
+	writel_bits_relaxed(OSD_MEM_LINEAR_ADDR, OSD_MEM_LINEAR_ADDR,
+			    priv->io_base + _REG(VIU_OSD1_CTRL_STAT));
+
+	writel_bits_relaxed(OSD_MALI_SRC_EN, OSD_MALI_SRC_EN,
+			    priv->io_base + _REG(VIU_OSD1_BLK0_CFG_W0));
+}
+
 static void meson_g12a_crtc_enable_osd1(struct meson_drm *priv)
 {
 	writel_relaxed(priv->viu.osd_blend_din0_scope_h,
@@ -281,6 +311,8 @@ void meson_crtc_irq(struct meson_drm *priv)
 	if (priv->viu.osd1_enabled && priv->viu.osd1_commit) {
 		writel_relaxed(priv->viu.osd1_ctrl_stat,
 				priv->io_base + _REG(VIU_OSD1_CTRL_STAT));
+		writel_relaxed(priv->viu.osd1_ctrl_stat2,
+				priv->io_base + _REG(VIU_OSD1_CTRL_STAT2));
 		writel_relaxed(priv->viu.osd1_blk0_cfg[0],
 				priv->io_base + _REG(VIU_OSD1_BLK0_CFG_W0));
 		writel_relaxed(priv->viu.osd1_blk0_cfg[1],
@@ -291,6 +323,20 @@ void meson_crtc_irq(struct meson_drm *priv)
 				priv->io_base + _REG(VIU_OSD1_BLK0_CFG_W3));
 		writel_relaxed(priv->viu.osd1_blk0_cfg[4],
 				priv->io_base + _REG(VIU_OSD1_BLK0_CFG_W4));
+
+		if (priv->viu.osd1_afbcd) {
+			if (meson_crtc->enable_osd1_afbc)
+				meson_crtc->enable_osd1_afbc(priv);
+		} else {
+			if (meson_crtc->disable_osd1_afbc)
+				meson_crtc->disable_osd1_afbc(priv);
+			if (priv->afbcd.ops) {
+				priv->afbcd.ops->reset(priv);
+				priv->afbcd.ops->disable(priv);
+			}
+			meson_crtc->vsync_forced = false;
+		}
+
 		writel_relaxed(priv->viu.osd_sc_ctrl0,
 				priv->io_base + _REG(VPP_OSD_SC_CTRL0));
 		writel_relaxed(priv->viu.osd_sc_i_wh_m1,
@@ -312,15 +358,25 @@ void meson_crtc_irq(struct meson_drm *priv)
 		writel_relaxed(priv->viu.osd_sc_v_ctrl0,
 				priv->io_base + _REG(VPP_OSD_VSC_CTRL0));
 
-		meson_canvas_config(priv->canvas, priv->canvas_id_osd1,
-				priv->viu.osd1_addr, priv->viu.osd1_stride,
-				priv->viu.osd1_height, MESON_CANVAS_WRAP_NONE,
-				MESON_CANVAS_BLKMODE_LINEAR, 0);
+		if (!priv->viu.osd1_afbcd)
+			meson_canvas_config(priv->canvas, priv->canvas_id_osd1,
+					    priv->viu.osd1_addr,
+					    priv->viu.osd1_stride,
+					    priv->viu.osd1_height,
+					    MESON_CANVAS_WRAP_NONE,
+					    MESON_CANVAS_BLKMODE_LINEAR, 0);
 
 		/* Enable OSD1 */
 		if (meson_crtc->enable_osd1)
 			meson_crtc->enable_osd1(priv);
 
+		if (priv->viu.osd1_afbcd) {
+			priv->afbcd.ops->reset(priv);
+			priv->afbcd.ops->setup(priv);
+			priv->afbcd.ops->enable(priv);
+			meson_crtc->vsync_forced = true;
+		}
+
 		priv->viu.osd1_commit = false;
 	}
 
@@ -357,7 +413,7 @@ void meson_crtc_irq(struct meson_drm *priv)
 					    MESON_CANVAS_WRAP_NONE,
 					    MESON_CANVAS_BLKMODE_LINEAR,
 					    MESON_CANVAS_ENDIAN_SWAP64);
-		};
+		}
 
 		writel_relaxed(priv->viu.vd1_if0_gen_reg,
 				priv->io_base + meson_crtc->viu_offset +
@@ -543,6 +599,9 @@ void meson_crtc_irq(struct meson_drm *priv)
 		priv->viu.vd1_commit = false;
 	}
 
+	if (meson_crtc->vsync_disabled)
+		return;
+
 	drm_crtc_handle_vblank(priv->crtc);
 
 	spin_lock_irqsave(&priv->drm->event_lock, flags);
@@ -579,10 +638,20 @@ int meson_crtc_create(struct meson_drm *priv)
 		meson_crtc->enable_osd1 = meson_g12a_crtc_enable_osd1;
 		meson_crtc->enable_vd1 = meson_g12a_crtc_enable_vd1;
 		meson_crtc->viu_offset = MESON_G12A_VIU_OFFSET;
+		meson_crtc->enable_osd1_afbc =
+					meson_crtc_g12a_enable_osd1_afbc;
+		meson_crtc->disable_osd1_afbc =
+					meson_viu_g12a_disable_osd1_afbc;
 		drm_crtc_helper_add(crtc, &meson_g12a_crtc_helper_funcs);
 	} else {
 		meson_crtc->enable_osd1 = meson_crtc_enable_osd1;
 		meson_crtc->enable_vd1 = meson_crtc_enable_vd1;
+		if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM)) {
+			meson_crtc->enable_osd1_afbc =
+					meson_viu_gxm_enable_osd1_afbc;
+			meson_crtc->disable_osd1_afbc =
+					meson_viu_gxm_disable_osd1_afbc;
+		}
 		drm_crtc_helper_add(crtc, &meson_crtc_helper_funcs);
 	}
 
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index 397c33182f4f..b5f5eb7b4bb9 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -28,10 +28,12 @@
 #include "meson_drv.h"
 #include "meson_overlay.h"
 #include "meson_plane.h"
+#include "meson_osd_afbcd.h"
 #include "meson_registers.h"
 #include "meson_venc_cvbs.h"
 #include "meson_viu.h"
 #include "meson_vpp.h"
+#include "meson_rdma.h"
 
 #define DRIVER_NAME "meson"
 #define DRIVER_DESC "Amlogic Meson DRM driver"
@@ -184,6 +186,7 @@ static void meson_remove_framebuffers(void)
 static int meson_drv_bind_master(struct device *dev, bool has_components)
 {
 	struct platform_device *pdev = to_platform_device(dev);
+	const struct meson_drm_match_data *match;
 	struct meson_drm *priv;
 	struct drm_device *drm;
 	struct resource *res;
@@ -196,6 +199,10 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
 		return -ENODEV;
 	}
 
+	match = of_device_get_match_data(dev);
+	if (!match)
+		return -ENODEV;
+
 	drm = drm_dev_alloc(&meson_driver, dev);
 	if (IS_ERR(drm))
 		return PTR_ERR(drm);
@@ -208,8 +215,8 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
 	drm->dev_private = priv;
 	priv->drm = drm;
 	priv->dev = dev;
-
-	priv->compat = (enum vpu_compatible)of_device_get_match_data(priv->dev);
+	priv->compat = match->compat;
+	priv->afbcd.ops = match->afbcd_ops;
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "vpu");
 	regs = devm_ioremap_resource(dev, res);
@@ -289,6 +296,11 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
 	meson_venc_init(priv);
 	meson_vpp_init(priv);
 	meson_viu_init(priv);
+	if (priv->afbcd.ops) {
+		ret = priv->afbcd.ops->init(priv);
+		if (ret)
+			return ret;
+	}
 
 	/* Encoder Initialization */
 
@@ -359,12 +371,16 @@ static void meson_drv_unbind(struct device *dev)
 		meson_canvas_free(priv->canvas, priv->canvas_id_vd1_2);
 	}
 
+	if (priv->afbcd.ops) {
+		priv->afbcd.ops->reset(priv);
+		meson_rdma_free(priv);
+	}
+
 	drm_dev_unregister(drm);
 	drm_irq_uninstall(drm);
 	drm_kms_helper_poll_fini(drm);
 	drm_mode_config_cleanup(drm);
 	drm_dev_put(drm);
-
 }
 
 static const struct component_master_ops meson_drv_master_ops = {
@@ -393,6 +409,8 @@ static int __maybe_unused meson_drv_pm_resume(struct device *dev)
 	meson_venc_init(priv);
 	meson_vpp_init(priv);
 	meson_viu_init(priv);
+	if (priv->afbcd.ops)
+		priv->afbcd.ops->init(priv);
 
 	drm_mode_config_helper_resume(priv->drm);
 
@@ -481,15 +499,33 @@ static int meson_drv_probe(struct platform_device *pdev)
 	return 0;
 };
 
+static struct meson_drm_match_data meson_drm_gxbb_data = {
+	.compat = VPU_COMPATIBLE_GXBB,
+};
+
+static struct meson_drm_match_data meson_drm_gxl_data = {
+	.compat = VPU_COMPATIBLE_GXL,
+};
+
+static struct meson_drm_match_data meson_drm_gxm_data = {
+	.compat = VPU_COMPATIBLE_GXM,
+	.afbcd_ops = &meson_afbcd_gxm_ops,
+};
+
+static struct meson_drm_match_data meson_drm_g12a_data = {
+	.compat = VPU_COMPATIBLE_G12A,
+	.afbcd_ops = &meson_afbcd_g12a_ops,
+};
+
 static const struct of_device_id dt_match[] = {
 	{ .compatible = "amlogic,meson-gxbb-vpu",
-	  .data       = (void *)VPU_COMPATIBLE_GXBB },
+	  .data       = (void *)&meson_drm_gxbb_data },
 	{ .compatible = "amlogic,meson-gxl-vpu",
-	  .data       = (void *)VPU_COMPATIBLE_GXL },
+	  .data       = (void *)&meson_drm_gxl_data },
 	{ .compatible = "amlogic,meson-gxm-vpu",
-	  .data       = (void *)VPU_COMPATIBLE_GXM },
+	  .data       = (void *)&meson_drm_gxm_data },
 	{ .compatible = "amlogic,meson-g12a-vpu",
-	  .data       = (void *)VPU_COMPATIBLE_G12A },
+	  .data       = (void *)&meson_drm_g12a_data },
 	{}
 };
 MODULE_DEVICE_TABLE(of, dt_match);
diff --git a/drivers/gpu/drm/meson/meson_drv.h b/drivers/gpu/drm/meson/meson_drv.h
index 820d07bdd42a..04fdf3826643 100644
--- a/drivers/gpu/drm/meson/meson_drv.h
+++ b/drivers/gpu/drm/meson/meson_drv.h
@@ -16,6 +16,7 @@ struct drm_crtc;
 struct drm_device;
 struct drm_plane;
 struct meson_drm;
+struct meson_afbcd_ops;
 
 enum vpu_compatible {
 	VPU_COMPATIBLE_GXBB = 0,
@@ -24,6 +25,11 @@ enum vpu_compatible {
 	VPU_COMPATIBLE_G12A = 3,
 };
 
+struct meson_drm_match_data {
+	enum vpu_compatible compat;
+	struct meson_afbcd_ops *afbcd_ops;
+};
+
 struct meson_drm {
 	struct device *dev;
 	enum vpu_compatible compat;
@@ -47,11 +53,16 @@ struct meson_drm {
 		bool osd1_enabled;
 		bool osd1_interlace;
 		bool osd1_commit;
+		bool osd1_afbcd;
 		uint32_t osd1_ctrl_stat;
+		uint32_t osd1_ctrl_stat2;
 		uint32_t osd1_blk0_cfg[5];
+		uint32_t osd1_blk1_cfg4;
+		uint32_t osd1_blk2_cfg4;
 		uint32_t osd1_addr;
 		uint32_t osd1_stride;
 		uint32_t osd1_height;
+		uint32_t osd1_width;
 		uint32_t osd_sc_ctrl0;
 		uint32_t osd_sc_i_wh_m1;
 		uint32_t osd_sc_o_h_start_end;
@@ -122,6 +133,18 @@ struct meson_drm {
 		bool venc_repeat;
 		bool hdmi_use_enci;
 	} venc;
+
+	struct {
+		dma_addr_t addr_dma;
+		uint32_t *addr;
+		unsigned int offset;
+	} rdma;
+
+	struct {
+		struct meson_afbcd_ops *ops;
+		u64 modifier;
+		u32 format;
+	} afbcd;
 };
 
 static inline int meson_vpu_is_compatible(struct meson_drm *priv,
diff --git a/drivers/gpu/drm/meson/meson_osd_afbcd.c b/drivers/gpu/drm/meson/meson_osd_afbcd.c
new file mode 100644
index 000000000000..f12e0271f166
--- /dev/null
+++ b/drivers/gpu/drm/meson/meson_osd_afbcd.c
@@ -0,0 +1,389 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019 BayLibre, SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+#include <linux/bitfield.h>
+
+#include <drm/drm_print.h>
+#include <drm/drm_fourcc.h>
+
+#include "meson_drv.h"
+#include "meson_registers.h"
+#include "meson_viu.h"
+#include "meson_rdma.h"
+#include "meson_osd_afbcd.h"
+
+/*
+ * DOC: Driver for the ARM FrameBuffer Compression Decoders
+ *
+ * The Amlogic GXM and G12A SoC families embeds an AFBC Decoder,
+ * to decode compressed buffers generated by the ARM Mali GPU.
+ *
+ * For the GXM Family, Amlogic designed their own Decoder, named in
+ * the vendor source as "MESON_AFBC", and a single decoder is available
+ * for the 2 OSD planes.
+ * This decoder is compatible with the AFBC 1.0 specifications and the
+ * Mali T820 GPU capabilities.
+ * It supports :
+ * - basic AFBC buffer for RGB32 only, thus YTR feature is mandatory
+ * - SPARSE layout and SPLIT layout
+ * - only 16x16 superblock
+ *
+ * The decoder reads the data from the SDRAM, decodes and sends the
+ * decoded pixel stream to the OSD1 Plane pixel composer.
+ *
+ * For the G12A Family, Amlogic integrated an ARM AFBC Decoder, named
+ * in the vendor source as "MALI_AFBC", and the decoder can decode up
+ * to 4 surfaces, one for each of the 4 available OSDs.
+ * This decoder is compatible with the AFBC 1.2 specifications for the
+ * Mali G31 and G52 GPUs.
+ * Is supports :
+ * - basic AFBC buffer for multiple RGB and YUV pixel formats
+ * - SPARSE layout and SPLIT layout
+ * - 16x16 and 32x8 "wideblk" superblocks
+ * - Tiled header
+ *
+ * The ARM AFBC Decoder independent from the VPU Pixel Pipeline, so
+ * the ARM AFBC Decoder reads the data from the SDRAM then decodes
+ * into a private internal physical address where the OSD1 Plane pixel
+ * composer unpacks the decoded data.
+ */
+
+/* Amlogic AFBC Decoder for GXM Family */
+
+#define OSD1_AFBCD_RGB32	0x15
+
+static int meson_gxm_afbcd_pixel_fmt(u64 modifier, uint32_t format)
+{
+	switch (format) {
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+		return OSD1_AFBCD_RGB32;
+	/* TOFIX support mode formats */
+	default:
+		DRM_DEBUG("unsupported afbc format[%08x]\n", format);
+		return -EINVAL;
+	}
+}
+
+static bool meson_gxm_afbcd_supported_fmt(u64 modifier, uint32_t format)
+{
+	if (modifier & AFBC_FORMAT_MOD_BLOCK_SIZE_32x8)
+		return false;
+
+	if (!(modifier & AFBC_FORMAT_MOD_YTR))
+		return false;
+
+	return meson_gxm_afbcd_pixel_fmt(modifier, format) >= 0;
+}
+
+static int meson_gxm_afbcd_init(struct meson_drm *priv)
+{
+	return 0;
+}
+
+static int meson_gxm_afbcd_reset(struct meson_drm *priv)
+{
+	writel_relaxed(VIU_SW_RESET_OSD1_AFBCD,
+		       priv->io_base + _REG(VIU_SW_RESET));
+	writel_relaxed(0, priv->io_base + _REG(VIU_SW_RESET));
+
+	return 0;
+}
+
+static int meson_gxm_afbcd_enable(struct meson_drm *priv)
+{
+	writel_relaxed(FIELD_PREP(OSD1_AFBCD_ID_FIFO_THRD, 0x40) |
+		       OSD1_AFBCD_DEC_ENABLE,
+		       priv->io_base + _REG(OSD1_AFBCD_ENABLE));
+
+	return 0;
+}
+
+static int meson_gxm_afbcd_disable(struct meson_drm *priv)
+{
+	writel_bits_relaxed(OSD1_AFBCD_DEC_ENABLE, 0,
+			    priv->io_base + _REG(OSD1_AFBCD_ENABLE));
+
+	return 0;
+}
+
+static int meson_gxm_afbcd_setup(struct meson_drm *priv)
+{
+	u32 conv_lbuf_len;
+	u32 mode = FIELD_PREP(OSD1_AFBCD_MIF_URGENT, 3) |
+		   FIELD_PREP(OSD1_AFBCD_HOLD_LINE_NUM, 4) |
+		   FIELD_PREP(OSD1_AFBCD_RGBA_EXCHAN_CTRL, 0x34) |
+		   meson_gxm_afbcd_pixel_fmt(priv->afbcd.modifier,
+					     priv->afbcd.format);
+
+	if (priv->afbcd.modifier & AFBC_FORMAT_MOD_SPARSE)
+		mode |= OSD1_AFBCD_HREG_HALF_BLOCK;
+
+	if (priv->afbcd.modifier & AFBC_FORMAT_MOD_SPLIT)
+		mode |= OSD1_AFBCD_HREG_BLOCK_SPLIT;
+
+	writel_relaxed(mode, priv->io_base + _REG(OSD1_AFBCD_MODE));
+
+	writel_relaxed(FIELD_PREP(OSD1_AFBCD_HREG_VSIZE_IN,
+				  priv->viu.osd1_width) |
+		       FIELD_PREP(OSD1_AFBCD_HREG_HSIZE_IN,
+				  priv->viu.osd1_height),
+		       priv->io_base + _REG(OSD1_AFBCD_SIZE_IN));
+
+	writel_relaxed(priv->viu.osd1_addr >> 4,
+		       priv->io_base + _REG(OSD1_AFBCD_HDR_PTR));
+	writel_relaxed(priv->viu.osd1_addr >> 4,
+		       priv->io_base + _REG(OSD1_AFBCD_FRAME_PTR));
+	/* TOFIX: bits 31:24 are not documented, nor the meaning of 0xe4 */
+	writel_relaxed((0xe4 << 24) | (priv->viu.osd1_addr & 0xffffff),
+		       priv->io_base + _REG(OSD1_AFBCD_CHROMA_PTR));
+
+	if (priv->viu.osd1_width <= 128)
+		conv_lbuf_len = 32;
+	else if (priv->viu.osd1_width <= 256)
+		conv_lbuf_len = 64;
+	else if (priv->viu.osd1_width <= 512)
+		conv_lbuf_len = 128;
+	else if (priv->viu.osd1_width <= 1024)
+		conv_lbuf_len = 256;
+	else if (priv->viu.osd1_width <= 2048)
+		conv_lbuf_len = 512;
+	else
+		conv_lbuf_len = 1024;
+
+	writel_relaxed(conv_lbuf_len,
+		       priv->io_base + _REG(OSD1_AFBCD_CONV_CTRL));
+
+	writel_relaxed(FIELD_PREP(OSD1_AFBCD_DEC_PIXEL_BGN_H, 0) |
+		       FIELD_PREP(OSD1_AFBCD_DEC_PIXEL_END_H,
+				  priv->viu.osd1_width - 1),
+		       priv->io_base + _REG(OSD1_AFBCD_PIXEL_HSCOPE));
+
+	writel_relaxed(FIELD_PREP(OSD1_AFBCD_DEC_PIXEL_BGN_V, 0) |
+		       FIELD_PREP(OSD1_AFBCD_DEC_PIXEL_END_V,
+				  priv->viu.osd1_height - 1),
+		       priv->io_base + _REG(OSD1_AFBCD_PIXEL_VSCOPE));
+
+	return 0;
+}
+
+struct meson_afbcd_ops meson_afbcd_gxm_ops = {
+	.init = meson_gxm_afbcd_init,
+	.reset = meson_gxm_afbcd_reset,
+	.enable = meson_gxm_afbcd_enable,
+	.disable = meson_gxm_afbcd_disable,
+	.setup = meson_gxm_afbcd_setup,
+	.supported_fmt = meson_gxm_afbcd_supported_fmt,
+};
+
+/* ARM AFBC Decoder for G12A Family */
+
+/* Amlogic G12A Mali AFBC Decoder supported formats */
+enum {
+	MAFBC_FMT_RGB565 = 0,
+	MAFBC_FMT_RGBA5551,
+	MAFBC_FMT_RGBA1010102,
+	MAFBC_FMT_YUV420_10B,
+	MAFBC_FMT_RGB888,
+	MAFBC_FMT_RGBA8888,
+	MAFBC_FMT_RGBA4444,
+	MAFBC_FMT_R8,
+	MAFBC_FMT_RG88,
+	MAFBC_FMT_YUV420_8B,
+	MAFBC_FMT_YUV422_8B = 11,
+	MAFBC_FMT_YUV422_10B = 14,
+};
+
+static int meson_g12a_afbcd_pixel_fmt(u64 modifier, uint32_t format)
+{
+	switch (format) {
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
+		/* YTR is forbidden for non XBGR formats */
+		if (modifier & AFBC_FORMAT_MOD_YTR)
+			return -EINVAL;
+	/* fall through */
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+		return MAFBC_FMT_RGBA8888;
+	case DRM_FORMAT_RGB888:
+		/* YTR is forbidden for non XBGR formats */
+		if (modifier & AFBC_FORMAT_MOD_YTR)
+			return -EINVAL;
+		return MAFBC_FMT_RGB888;
+	case DRM_FORMAT_RGB565:
+		/* YTR is forbidden for non XBGR formats */
+		if (modifier & AFBC_FORMAT_MOD_YTR)
+			return -EINVAL;
+		return MAFBC_FMT_RGB565;
+	/* TOFIX support mode formats */
+	default:
+		DRM_DEBUG("unsupported afbc format[%08x]\n", format);
+		return -EINVAL;
+	}
+}
+
+static int meson_g12a_afbcd_bpp(uint32_t format)
+{
+	switch (format) {
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+		return 32;
+	case DRM_FORMAT_RGB888:
+		return 24;
+	case DRM_FORMAT_RGB565:
+		return 16;
+	/* TOFIX support mode formats */
+	default:
+		DRM_ERROR("unsupported afbc format[%08x]\n", format);
+		return 0;
+	}
+}
+
+static int meson_g12a_afbcd_fmt_to_blk_mode(u64 modifier, uint32_t format)
+{
+	switch (format) {
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+		return OSD_MALI_COLOR_MODE_RGBA8888;
+	case DRM_FORMAT_RGB888:
+		return OSD_MALI_COLOR_MODE_RGB888;
+	case DRM_FORMAT_RGB565:
+		return OSD_MALI_COLOR_MODE_RGB565;
+	/* TOFIX support mode formats */
+	default:
+		DRM_DEBUG("unsupported afbc format[%08x]\n", format);
+		return -EINVAL;
+	}
+}
+
+static bool meson_g12a_afbcd_supported_fmt(u64 modifier, uint32_t format)
+{
+	return meson_g12a_afbcd_pixel_fmt(modifier, format) >= 0;
+}
+
+static int meson_g12a_afbcd_init(struct meson_drm *priv)
+{
+	int ret;
+
+	ret = meson_rdma_init(priv);
+	if (ret)
+		return ret;
+
+	meson_rdma_setup(priv);
+
+	/* Handle AFBC Decoder reset manually */
+	writel_bits_relaxed(MALI_AFBCD_MANUAL_RESET, MALI_AFBCD_MANUAL_RESET,
+			    priv->io_base + _REG(MALI_AFBCD_TOP_CTRL));
+
+	return 0;
+}
+
+static int meson_g12a_afbcd_reset(struct meson_drm *priv)
+{
+	meson_rdma_reset(priv);
+
+	meson_rdma_writel_sync(priv, VIU_SW_RESET_G12A_AFBC_ARB |
+			       VIU_SW_RESET_G12A_OSD1_AFBCD,
+			       VIU_SW_RESET);
+	meson_rdma_writel_sync(priv, 0, VIU_SW_RESET);
+
+	return 0;
+}
+
+static int meson_g12a_afbcd_enable(struct meson_drm *priv)
+{
+	meson_rdma_writel_sync(priv, VPU_MAFBC_IRQ_SURFACES_COMPLETED |
+			       VPU_MAFBC_IRQ_CONFIGURATION_SWAPPED |
+			       VPU_MAFBC_IRQ_DECODE_ERROR |
+			       VPU_MAFBC_IRQ_DETILING_ERROR,
+			       VPU_MAFBC_IRQ_MASK);
+
+	meson_rdma_writel_sync(priv, VPU_MAFBC_S0_ENABLE,
+			       VPU_MAFBC_SURFACE_CFG);
+
+	meson_rdma_writel_sync(priv, VPU_MAFBC_DIRECT_SWAP,
+			       VPU_MAFBC_COMMAND);
+
+	/* This will enable the RDMA replaying the register writes on vsync */
+	meson_rdma_flush(priv);
+
+	return 0;
+}
+
+static int meson_g12a_afbcd_disable(struct meson_drm *priv)
+{
+	writel_bits_relaxed(VPU_MAFBC_S0_ENABLE, 0,
+			    priv->io_base + _REG(VPU_MAFBC_SURFACE_CFG));
+
+	return 0;
+}
+
+static int meson_g12a_afbcd_setup(struct meson_drm *priv)
+{
+	u32 format = meson_g12a_afbcd_pixel_fmt(priv->afbcd.modifier,
+						priv->afbcd.format);
+
+	if (priv->afbcd.modifier & AFBC_FORMAT_MOD_YTR)
+		format |= VPU_MAFBC_YUV_TRANSFORM;
+
+	if (priv->afbcd.modifier & AFBC_FORMAT_MOD_SPLIT)
+		format |= VPU_MAFBC_BLOCK_SPLIT;
+
+	if (priv->afbcd.modifier & AFBC_FORMAT_MOD_TILED)
+		format |= VPU_MAFBC_TILED_HEADER_EN;
+
+	if ((priv->afbcd.modifier & AFBC_FORMAT_MOD_BLOCK_SIZE_MASK) ==
+		AFBC_FORMAT_MOD_BLOCK_SIZE_32x8)
+		format |= FIELD_PREP(VPU_MAFBC_SUPER_BLOCK_ASPECT, 1);
+
+	meson_rdma_writel_sync(priv, format,
+			       VPU_MAFBC_FORMAT_SPECIFIER_S0);
+
+	meson_rdma_writel_sync(priv, priv->viu.osd1_addr,
+			       VPU_MAFBC_HEADER_BUF_ADDR_LOW_S0);
+	meson_rdma_writel_sync(priv, 0,
+			       VPU_MAFBC_HEADER_BUF_ADDR_HIGH_S0);
+
+	meson_rdma_writel_sync(priv, priv->viu.osd1_width,
+			       VPU_MAFBC_BUFFER_WIDTH_S0);
+	meson_rdma_writel_sync(priv, ALIGN(priv->viu.osd1_height, 32),
+			       VPU_MAFBC_BUFFER_HEIGHT_S0);
+
+	meson_rdma_writel_sync(priv, 0,
+			       VPU_MAFBC_BOUNDING_BOX_X_START_S0);
+	meson_rdma_writel_sync(priv, priv->viu.osd1_width - 1,
+			       VPU_MAFBC_BOUNDING_BOX_X_END_S0);
+	meson_rdma_writel_sync(priv, 0,
+			       VPU_MAFBC_BOUNDING_BOX_Y_START_S0);
+	meson_rdma_writel_sync(priv, priv->viu.osd1_height - 1,
+			       VPU_MAFBC_BOUNDING_BOX_Y_END_S0);
+
+	meson_rdma_writel_sync(priv, MESON_G12A_AFBCD_OUT_ADDR,
+			       VPU_MAFBC_OUTPUT_BUF_ADDR_LOW_S0);
+	meson_rdma_writel_sync(priv, 0,
+			       VPU_MAFBC_OUTPUT_BUF_ADDR_HIGH_S0);
+
+	meson_rdma_writel_sync(priv, priv->viu.osd1_width *
+			       (meson_g12a_afbcd_bpp(priv->afbcd.format) / 8),
+			       VPU_MAFBC_OUTPUT_BUF_STRIDE_S0);
+
+	return 0;
+}
+
+struct meson_afbcd_ops meson_afbcd_g12a_ops = {
+	.init = meson_g12a_afbcd_init,
+	.reset = meson_g12a_afbcd_reset,
+	.enable = meson_g12a_afbcd_enable,
+	.disable = meson_g12a_afbcd_disable,
+	.setup = meson_g12a_afbcd_setup,
+	.fmt_to_blk_mode = meson_g12a_afbcd_fmt_to_blk_mode,
+	.supported_fmt = meson_g12a_afbcd_supported_fmt,
+};
diff --git a/drivers/gpu/drm/meson/meson_osd_afbcd.h b/drivers/gpu/drm/meson/meson_osd_afbcd.h
new file mode 100644
index 000000000000..5e5523304f42
--- /dev/null
+++ b/drivers/gpu/drm/meson/meson_osd_afbcd.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (C) 2019 BayLibre, SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+#ifndef __MESON_OSD_AFBCD_H
+#define __MESON_OSD_AFBCD_H
+
+#include "meson_drv.h"
+
+/* This is an internal address used to transfer pixel from AFBC to the VIU */
+#define MESON_G12A_AFBCD_OUT_ADDR	0x1000000
+
+struct meson_afbcd_ops {
+	int (*init)(struct meson_drm *priv);
+	int (*reset)(struct meson_drm *priv);
+	int (*enable)(struct meson_drm *priv);
+	int (*disable)(struct meson_drm *priv);
+	int (*setup)(struct meson_drm *priv);
+	int (*fmt_to_blk_mode)(u64 modifier, uint32_t format);
+	bool (*supported_fmt)(u64 modifier, uint32_t format);
+};
+
+extern struct meson_afbcd_ops meson_afbcd_gxm_ops;
+extern struct meson_afbcd_ops meson_afbcd_g12a_ops;
+
+#endif /* __MESON_OSD_AFBCD_H */
diff --git a/drivers/gpu/drm/meson/meson_plane.c b/drivers/gpu/drm/meson/meson_plane.c
index ed543227b00d..d5cbc47835bf 100644
--- a/drivers/gpu/drm/meson/meson_plane.c
+++ b/drivers/gpu/drm/meson/meson_plane.c
@@ -23,6 +23,7 @@
 #include "meson_plane.h"
 #include "meson_registers.h"
 #include "meson_viu.h"
+#include "meson_osd_afbcd.h"
 
 /* OSD_SCI_WH_M1 */
 #define SCI_WH_M1_W(w)			FIELD_PREP(GENMASK(28, 16), w)
@@ -92,12 +93,38 @@ static int meson_plane_atomic_check(struct drm_plane *plane,
 						   false, true);
 }
 
+#define MESON_MOD_AFBC_VALID_BITS (AFBC_FORMAT_MOD_BLOCK_SIZE_16x16 |	\
+				   AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |	\
+				   AFBC_FORMAT_MOD_YTR |		\
+				   AFBC_FORMAT_MOD_SPARSE |		\
+				   AFBC_FORMAT_MOD_SPLIT)
+
 /* Takes a fixed 16.16 number and converts it to integer. */
 static inline int64_t fixed16_to_int(int64_t value)
 {
 	return value >> 16;
 }
 
+static u32 meson_g12a_afbcd_line_stride(struct meson_drm *priv)
+{
+	u32 line_stride = 0;
+
+	switch (priv->afbcd.format) {
+	case DRM_FORMAT_RGB565:
+		line_stride = ((priv->viu.osd1_width << 4) + 127) >> 7;
+		break;
+	case DRM_FORMAT_RGB888:
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+		line_stride = ((priv->viu.osd1_width << 5) + 127) >> 7;
+		break;
+	}
+
+	return ((line_stride + 1) >> 1) << 1;
+}
+
 static void meson_plane_atomic_update(struct drm_plane *plane,
 				      struct drm_plane_state *old_state)
 {
@@ -126,59 +153,91 @@ static void meson_plane_atomic_update(struct drm_plane *plane,
 	 */
 	spin_lock_irqsave(&priv->drm->event_lock, flags);
 
+	/* Check if AFBC decoder is required for this buffer */
+	if ((meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM) ||
+	     meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) &&
+	    fb->modifier & DRM_FORMAT_MOD_ARM_AFBC(MESON_MOD_AFBC_VALID_BITS))
+		priv->viu.osd1_afbcd = true;
+	else
+		priv->viu.osd1_afbcd = false;
+
 	/* Enable OSD and BLK0, set max global alpha */
 	priv->viu.osd1_ctrl_stat = OSD_ENABLE |
 				   (0xFF << OSD_GLOBAL_ALPHA_SHIFT) |
 				   OSD_BLK0_ENABLE;
 
+	priv->viu.osd1_ctrl_stat2 = readl(priv->io_base +
+					  _REG(VIU_OSD1_CTRL_STAT2));
+
 	canvas_id_osd1 = priv->canvas_id_osd1;
 
 	/* Set up BLK0 to point to the right canvas */
-	priv->viu.osd1_blk0_cfg[0] = ((canvas_id_osd1 << OSD_CANVAS_SEL) |
-				      OSD_ENDIANNESS_LE);
+	priv->viu.osd1_blk0_cfg[0] = canvas_id_osd1 << OSD_CANVAS_SEL;
+
+	if (priv->viu.osd1_afbcd) {
+		if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) {
+			/* This is the internal decoding memory address */
+			priv->viu.osd1_blk1_cfg4 = MESON_G12A_AFBCD_OUT_ADDR;
+			priv->viu.osd1_blk0_cfg[0] |= OSD_ENDIANNESS_BE;
+			priv->viu.osd1_ctrl_stat2 |= OSD_PENDING_STAT_CLEAN;
+			priv->viu.osd1_ctrl_stat |= VIU_OSD1_CFG_SYN_EN;
+		}
+
+		if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM)) {
+			priv->viu.osd1_blk0_cfg[0] |= OSD_ENDIANNESS_LE;
+			priv->viu.osd1_ctrl_stat2 |= OSD_DPATH_MALI_AFBCD;
+		}
+	} else {
+		priv->viu.osd1_blk0_cfg[0] |= OSD_ENDIANNESS_LE;
+
+		if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM))
+			priv->viu.osd1_ctrl_stat2 &= ~OSD_DPATH_MALI_AFBCD;
+	}
 
 	/* On GXBB, Use the old non-HDR RGB2YUV converter */
 	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXBB))
 		priv->viu.osd1_blk0_cfg[0] |= OSD_OUTPUT_COLOR_RGB;
 
+	if (priv->viu.osd1_afbcd &&
+	    meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) {
+		priv->viu.osd1_blk0_cfg[0] |= OSD_MALI_SRC_EN |
+			priv->afbcd.ops->fmt_to_blk_mode(fb->modifier,
+							  fb->format->format);
+	} else {
+		switch (fb->format->format) {
+		case DRM_FORMAT_XRGB8888:
+		case DRM_FORMAT_ARGB8888:
+			priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_32 |
+						OSD_COLOR_MATRIX_32_ARGB;
+			break;
+		case DRM_FORMAT_XBGR8888:
+		case DRM_FORMAT_ABGR8888:
+			priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_32 |
+						OSD_COLOR_MATRIX_32_ABGR;
+			break;
+		case DRM_FORMAT_RGB888:
+			priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_24 |
+						OSD_COLOR_MATRIX_24_RGB;
+			break;
+		case DRM_FORMAT_RGB565:
+			priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_16 |
+						OSD_COLOR_MATRIX_16_RGB565;
+			break;
+		};
+	}
+
 	switch (fb->format->format) {
 	case DRM_FORMAT_XRGB8888:
-		/* For XRGB, replace the pixel's alpha by 0xFF */
-		writel_bits_relaxed(OSD_REPLACE_EN, OSD_REPLACE_EN,
-				    priv->io_base + _REG(VIU_OSD1_CTRL_STAT2));
-		priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_32 |
-					      OSD_COLOR_MATRIX_32_ARGB;
-		break;
 	case DRM_FORMAT_XBGR8888:
 		/* For XRGB, replace the pixel's alpha by 0xFF */
-		writel_bits_relaxed(OSD_REPLACE_EN, OSD_REPLACE_EN,
-				    priv->io_base + _REG(VIU_OSD1_CTRL_STAT2));
-		priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_32 |
-					      OSD_COLOR_MATRIX_32_ABGR;
+		priv->viu.osd1_ctrl_stat2 |= OSD_REPLACE_EN;
 		break;
 	case DRM_FORMAT_ARGB8888:
-		/* For ARGB, use the pixel's alpha */
-		writel_bits_relaxed(OSD_REPLACE_EN, 0,
-				    priv->io_base + _REG(VIU_OSD1_CTRL_STAT2));
-		priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_32 |
-					      OSD_COLOR_MATRIX_32_ARGB;
-		break;
 	case DRM_FORMAT_ABGR8888:
 		/* For ARGB, use the pixel's alpha */
-		writel_bits_relaxed(OSD_REPLACE_EN, 0,
-				    priv->io_base + _REG(VIU_OSD1_CTRL_STAT2));
-		priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_32 |
-					      OSD_COLOR_MATRIX_32_ABGR;
+		priv->viu.osd1_ctrl_stat2 &= ~OSD_REPLACE_EN;
 		break;
-	case DRM_FORMAT_RGB888:
-		priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_24 |
-					      OSD_COLOR_MATRIX_24_RGB;
-		break;
-	case DRM_FORMAT_RGB565:
-		priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_16 |
-					      OSD_COLOR_MATRIX_16_RGB565;
-		break;
-	};
+	}
 
 	/* Default scaler parameters */
 	vsc_bot_rcv_num = 0;
@@ -305,6 +364,17 @@ static void meson_plane_atomic_update(struct drm_plane *plane,
 	priv->viu.osd1_addr = gem->paddr;
 	priv->viu.osd1_stride = fb->pitches[0];
 	priv->viu.osd1_height = fb->height;
+	priv->viu.osd1_width = fb->width;
+
+	if (priv->viu.osd1_afbcd) {
+		priv->afbcd.modifier = fb->modifier;
+		priv->afbcd.format = fb->format->format;
+
+		/* Calculate decoder write stride */
+		if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
+			priv->viu.osd1_blk2_cfg4 =
+				meson_g12a_afbcd_line_stride(priv);
+	}
 
 	if (!meson_plane->enabled) {
 		/* Reset OSD1 before enabling it on GXL+ SoCs */
@@ -326,6 +396,11 @@ static void meson_plane_atomic_disable(struct drm_plane *plane,
 	struct meson_plane *meson_plane = to_meson_plane(plane);
 	struct meson_drm *priv = meson_plane->priv;
 
+	if (priv->afbcd.ops) {
+		priv->afbcd.ops->reset(priv);
+		priv->afbcd.ops->disable(priv);
+	}
+
 	/* Disable OSD1 */
 	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
 		writel_bits_relaxed(VIU_OSD1_POSTBLD_SRC_OSD1, 0,
@@ -345,6 +420,42 @@ static const struct drm_plane_helper_funcs meson_plane_helper_funcs = {
 	.prepare_fb	= drm_gem_fb_prepare_fb,
 };
 
+static bool meson_plane_format_mod_supported(struct drm_plane *plane,
+					     u32 format, u64 modifier)
+{
+	struct meson_plane *meson_plane = to_meson_plane(plane);
+	struct meson_drm *priv = meson_plane->priv;
+	int i;
+
+	if (modifier == DRM_FORMAT_MOD_INVALID)
+		return false;
+
+	if (modifier == DRM_FORMAT_MOD_LINEAR)
+		return true;
+
+	if (!meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM) &&
+	    !meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
+		return false;
+
+	if (modifier & ~DRM_FORMAT_MOD_ARM_AFBC(MESON_MOD_AFBC_VALID_BITS))
+		return false;
+
+	for (i = 0 ; i < plane->modifier_count ; ++i)
+		if (plane->modifiers[i] == modifier)
+			break;
+
+	if (i == plane->modifier_count) {
+		DRM_DEBUG_KMS("Unsupported modifier\n");
+		return false;
+	}
+
+	if (priv->afbcd.ops && priv->afbcd.ops->supported_fmt)
+		return priv->afbcd.ops->supported_fmt(modifier, format);
+
+	DRM_DEBUG_KMS("AFBC Unsupported\n");
+	return false;
+}
+
 static const struct drm_plane_funcs meson_plane_funcs = {
 	.update_plane		= drm_atomic_helper_update_plane,
 	.disable_plane		= drm_atomic_helper_disable_plane,
@@ -352,6 +463,7 @@ static const struct drm_plane_funcs meson_plane_funcs = {
 	.reset			= drm_atomic_helper_plane_reset,
 	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
 	.atomic_destroy_state	= drm_atomic_helper_plane_destroy_state,
+	.format_mod_supported   = meson_plane_format_mod_supported,
 };
 
 static const uint32_t supported_drm_formats[] = {
@@ -363,10 +475,60 @@ static const uint32_t supported_drm_formats[] = {
 	DRM_FORMAT_RGB565,
 };
 
+static const uint64_t format_modifiers_afbc_gxm[] = {
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_16x16 |
+				AFBC_FORMAT_MOD_SPARSE |
+				AFBC_FORMAT_MOD_YTR),
+	/* SPLIT mandates SPARSE, RGB modes mandates YTR */
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_16x16 |
+				AFBC_FORMAT_MOD_YTR |
+				AFBC_FORMAT_MOD_SPARSE |
+				AFBC_FORMAT_MOD_SPLIT),
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID,
+};
+
+static const uint64_t format_modifiers_afbc_g12a[] = {
+	/*
+	 * - TOFIX Support AFBC modifiers for YUV formats (16x16 + TILED)
+	 * - SPLIT is mandatory for performances reasons when in 16x16
+	 *   block size
+	 * - 32x8 block size + SPLIT is mandatory with 4K frame size
+	 *   for performances reasons
+	 */
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_16x16 |
+				AFBC_FORMAT_MOD_SPARSE |
+				AFBC_FORMAT_MOD_SPLIT),
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_16x16 |
+				AFBC_FORMAT_MOD_YTR |
+				AFBC_FORMAT_MOD_SPARSE |
+				AFBC_FORMAT_MOD_SPLIT),
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |
+				AFBC_FORMAT_MOD_SPARSE),
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |
+				AFBC_FORMAT_MOD_YTR |
+				AFBC_FORMAT_MOD_SPARSE),
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |
+				AFBC_FORMAT_MOD_SPARSE |
+				AFBC_FORMAT_MOD_SPLIT),
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |
+				AFBC_FORMAT_MOD_YTR |
+				AFBC_FORMAT_MOD_SPARSE |
+				AFBC_FORMAT_MOD_SPLIT),
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID,
+};
+
+static const uint64_t format_modifiers_default[] = {
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID,
+};
+
 int meson_plane_create(struct meson_drm *priv)
 {
 	struct meson_plane *meson_plane;
 	struct drm_plane *plane;
+	const uint64_t *format_modifiers = format_modifiers_default;
 
 	meson_plane = devm_kzalloc(priv->drm->dev, sizeof(*meson_plane),
 				   GFP_KERNEL);
@@ -376,11 +538,16 @@ int meson_plane_create(struct meson_drm *priv)
 	meson_plane->priv = priv;
 	plane = &meson_plane->base;
 
+	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM))
+		format_modifiers = format_modifiers_afbc_gxm;
+	else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
+		format_modifiers = format_modifiers_afbc_g12a;
+
 	drm_universal_plane_init(priv->drm, plane, 0xFF,
 				 &meson_plane_funcs,
 				 supported_drm_formats,
 				 ARRAY_SIZE(supported_drm_formats),
-				 NULL,
+				 format_modifiers,
 				 DRM_PLANE_TYPE_PRIMARY, "meson_primary_plane");
 
 	drm_plane_helper_add(plane, &meson_plane_helper_funcs);
diff --git a/drivers/gpu/drm/meson/meson_rdma.c b/drivers/gpu/drm/meson/meson_rdma.c
new file mode 100644
index 000000000000..130382178c63
--- /dev/null
+++ b/drivers/gpu/drm/meson/meson_rdma.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019 BayLibre, SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/dma-mapping.h>
+
+#include "meson_drv.h"
+#include "meson_registers.h"
+#include "meson_rdma.h"
+
+/*
+ * The VPU embeds a "Register DMA" that can write a sequence of registers
+ * on the VPU AHB bus, either manually or triggered by an internal IRQ
+ * event like VSYNC or a line input counter.
+ * The initial implementation handles a single channel (over 8), triggered
+ * by the VSYNC irq and does not handle the RDMA irq.
+ */
+
+#define RDMA_DESC_SIZE	(sizeof(uint32_t) * 2)
+
+int meson_rdma_init(struct meson_drm *priv)
+{
+	if (!priv->rdma.addr) {
+		/* Allocate a PAGE buffer */
+		priv->rdma.addr =
+			dma_alloc_coherent(priv->dev, SZ_4K,
+					   &priv->rdma.addr_dma,
+					   GFP_KERNEL);
+		if (!priv->rdma.addr)
+			return -ENOMEM;
+	}
+
+	priv->rdma.offset = 0;
+
+	writel_relaxed(RDMA_CTRL_SW_RESET,
+		       priv->io_base + _REG(RDMA_CTRL));
+	writel_relaxed(RDMA_DEFAULT_CONFIG |
+		       FIELD_PREP(RDMA_CTRL_AHB_WR_BURST, 3) |
+		       FIELD_PREP(RDMA_CTRL_AHB_RD_BURST, 0),
+		       priv->io_base + _REG(RDMA_CTRL));
+
+	return 0;
+}
+
+void meson_rdma_free(struct meson_drm *priv)
+{
+	if (!priv->rdma.addr && !priv->rdma.addr_dma)
+		return;
+
+	meson_rdma_stop(priv);
+
+	dma_free_coherent(priv->dev, SZ_4K,
+			  priv->rdma.addr, priv->rdma.addr_dma);
+
+	priv->rdma.addr = NULL;
+	priv->rdma.addr_dma = (dma_addr_t)0;
+}
+
+void meson_rdma_setup(struct meson_drm *priv)
+{
+	/* Channel 1: Write Flag, No Address Increment */
+	writel_bits_relaxed(RDMA_ACCESS_RW_FLAG_CHAN1 |
+			    RDMA_ACCESS_ADDR_INC_CHAN1,
+			    RDMA_ACCESS_RW_FLAG_CHAN1,
+			    priv->io_base + _REG(RDMA_ACCESS_AUTO));
+}
+
+void meson_rdma_stop(struct meson_drm *priv)
+{
+	writel_bits_relaxed(RDMA_IRQ_CLEAR_CHAN1,
+			    RDMA_IRQ_CLEAR_CHAN1,
+			    priv->io_base + _REG(RDMA_CTRL));
+
+	/* Stop Channel 1 */
+	writel_bits_relaxed(RDMA_ACCESS_TRIGGER_CHAN1,
+			    FIELD_PREP(RDMA_ACCESS_ADDR_INC_CHAN1,
+				       RDMA_ACCESS_TRIGGER_STOP),
+			    priv->io_base + _REG(RDMA_ACCESS_AUTO));
+}
+
+void meson_rdma_reset(struct meson_drm *priv)
+{
+	meson_rdma_stop(priv);
+
+	priv->rdma.offset = 0;
+}
+
+static void meson_rdma_writel(struct meson_drm *priv, uint32_t val,
+			      uint32_t reg)
+{
+	if (priv->rdma.offset >= (SZ_4K / RDMA_DESC_SIZE)) {
+		dev_warn_once(priv->dev, "%s: overflow\n", __func__);
+		return;
+	}
+
+	priv->rdma.addr[priv->rdma.offset++] = reg;
+	priv->rdma.addr[priv->rdma.offset++] = val;
+}
+
+/*
+ * This will add the register to the RDMA buffer and write it to the
+ * hardware at the same time.
+ * When meson_rdma_flush is called, the RDMA will replay the register
+ * writes in order.
+ */
+void meson_rdma_writel_sync(struct meson_drm *priv, uint32_t val, uint32_t reg)
+{
+	meson_rdma_writel(priv, val, reg);
+
+	writel_relaxed(val, priv->io_base + _REG(reg));
+}
+
+void meson_rdma_flush(struct meson_drm *priv)
+{
+	meson_rdma_stop(priv);
+
+	/* Start of Channel 1 register writes buffer */
+	writel(priv->rdma.addr_dma,
+	       priv->io_base + _REG(RDMA_AHB_START_ADDR_1));
+
+	/* Last byte on Channel 1 register writes buffer */
+	writel(priv->rdma.addr_dma + (priv->rdma.offset * RDMA_DESC_SIZE) - 1,
+	       priv->io_base + _REG(RDMA_AHB_END_ADDR_1));
+
+	/* Trigger Channel 1 on VSYNC event */
+	writel_bits_relaxed(RDMA_ACCESS_TRIGGER_CHAN1,
+			    FIELD_PREP(RDMA_ACCESS_TRIGGER_CHAN1,
+				       RDMA_ACCESS_TRIGGER_VSYNC),
+			    priv->io_base + _REG(RDMA_ACCESS_AUTO));
+
+	priv->rdma.offset = 0;
+}
diff --git a/drivers/gpu/drm/meson/meson_rdma.h b/drivers/gpu/drm/meson/meson_rdma.h
new file mode 100644
index 000000000000..3870bff7b47f
--- /dev/null
+++ b/drivers/gpu/drm/meson/meson_rdma.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (C) 2019 BayLibre, SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+#ifndef __MESON_RDMA_H
+#define __MESON_RDMA_H
+
+#include "meson_drv.h"
+
+int meson_rdma_init(struct meson_drm *priv);
+void meson_rdma_free(struct meson_drm *priv);
+void meson_rdma_setup(struct meson_drm *priv);
+void meson_rdma_reset(struct meson_drm *priv);
+void meson_rdma_stop(struct meson_drm *priv);
+
+void meson_rdma_writel_sync(struct meson_drm *priv, uint32_t val, uint32_t reg);
+void meson_rdma_flush(struct meson_drm *priv);
+
+#endif /* __MESON_RDMA_H */
diff --git a/drivers/gpu/drm/meson/meson_registers.h b/drivers/gpu/drm/meson/meson_registers.h
index 05fce48ceee0..8ea00546cd4e 100644
--- a/drivers/gpu/drm/meson/meson_registers.h
+++ b/drivers/gpu/drm/meson/meson_registers.h
@@ -138,19 +138,25 @@
 #define VIU_ADDR_START 0x1a00
 #define VIU_ADDR_END 0x1aff
 #define VIU_SW_RESET 0x1a01
+#define		VIU_SW_RESET_OSD1_AFBCD		BIT(31)
+#define		VIU_SW_RESET_G12A_OSD1_AFBCD	BIT(21)
+#define		VIU_SW_RESET_G12A_AFBC_ARB	BIT(19)
 #define		VIU_SW_RESET_OSD1               BIT(0)
 #define VIU_MISC_CTRL0 0x1a06
 #define		VIU_CTRL0_VD1_AFBC_MASK         0x170000
 #define VIU_MISC_CTRL1 0x1a07
+#define		MALI_AFBC_MISC			GENMASK(15, 8)
 #define D2D3_INTF_LENGTH 0x1a08
 #define D2D3_INTF_CTRL0 0x1a09
 #define VIU_OSD1_CTRL_STAT 0x1a10
 #define		VIU_OSD1_OSD_BLK_ENABLE         BIT(0)
+#define		VIU_OSD1_OSD_MEM_MODE_LINEAR	BIT(2)
 #define		VIU_OSD1_POSTBLD_SRC_VD1        (1 << 8)
 #define		VIU_OSD1_POSTBLD_SRC_VD2        (2 << 8)
 #define		VIU_OSD1_POSTBLD_SRC_OSD1       (3 << 8)
 #define		VIU_OSD1_POSTBLD_SRC_OSD2       (4 << 8)
 #define		VIU_OSD1_OSD_ENABLE             BIT(21)
+#define		VIU_OSD1_CFG_SYN_EN             BIT(31)
 #define VIU_OSD1_CTRL_STAT2 0x1a2d
 #define VIU_OSD1_COLOR_ADDR 0x1a11
 #define VIU_OSD1_COLOR 0x1a12
@@ -181,6 +187,16 @@
 #define VIU_OSD1_FIFO_CTRL_STAT 0x1a2b
 #define VIU_OSD1_TEST_RDDATA 0x1a2c
 #define VIU_OSD1_PROT_CTRL 0x1a2e
+#define VIU_OSD1_MALI_UNPACK_CTRL 0x1a2f
+#define		VIU_OSD1_MALI_UNPACK_EN		BIT(31)
+#define		VIU_OSD1_MALI_AFBCD_R_REORDER	GENMASK(15, 12)
+#define		VIU_OSD1_MALI_AFBCD_G_REORDER	GENMASK(11, 8)
+#define		VIU_OSD1_MALI_AFBCD_B_REORDER	GENMASK(7, 4)
+#define		VIU_OSD1_MALI_AFBCD_A_REORDER	GENMASK(3, 0)
+#define		VIU_OSD1_MALI_REORDER_R		1
+#define		VIU_OSD1_MALI_REORDER_G		2
+#define		VIU_OSD1_MALI_REORDER_B		3
+#define		VIU_OSD1_MALI_REORDER_A		4
 #define VIU_OSD2_CTRL_STAT 0x1a30
 #define VIU_OSD2_CTRL_STAT2 0x1a4d
 #define VIU_OSD2_COLOR_ADDR 0x1a31
@@ -1195,11 +1211,59 @@
 #define RDMA_AHB_START_ADDR_7 0x110e
 #define RDMA_AHB_END_ADDR_7 0x110f
 #define RDMA_ACCESS_AUTO 0x1110
+#define		RDMA_ACCESS_TRIGGER_CHAN3	GENMASK(31, 24)
+#define		RDMA_ACCESS_TRIGGER_CHAN2	GENMASK(23, 16)
+#define		RDMA_ACCESS_TRIGGER_CHAN1	GENMASK(15, 8)
+#define		RDMA_ACCESS_TRIGGER_STOP	0
+#define		RDMA_ACCESS_TRIGGER_VSYNC	1
+#define		RDMA_ACCESS_TRIGGER_LINE	32
+#define		RDMA_ACCESS_RW_FLAG_CHAN3	BIT(7)
+#define		RDMA_ACCESS_RW_FLAG_CHAN2	BIT(6)
+#define		RDMA_ACCESS_RW_FLAG_CHAN1	BIT(5)
+#define		RDMA_ACCESS_ADDR_INC_CHAN3	BIT(3)
+#define		RDMA_ACCESS_ADDR_INC_CHAN2	BIT(2)
+#define		RDMA_ACCESS_ADDR_INC_CHAN1	BIT(1)
 #define RDMA_ACCESS_AUTO2 0x1111
+#define		RDMA_ACCESS_RW_FLAG_CHAN7	BIT(7)
+#define		RDMA_ACCESS_RW_FLAG_CHAN6	BIT(6)
+#define		RDMA_ACCESS_RW_FLAG_CHAN5	BIT(5)
+#define		RDMA_ACCESS_RW_FLAG_CHAN4	BIT(4)
+#define		RDMA_ACCESS_ADDR_INC_CHAN7	BIT(3)
+#define		RDMA_ACCESS_ADDR_INC_CHAN6	BIT(2)
+#define		RDMA_ACCESS_ADDR_INC_CHAN5	BIT(1)
+#define		RDMA_ACCESS_ADDR_INC_CHAN4	BIT(0)
 #define RDMA_ACCESS_AUTO3 0x1112
+#define		RDMA_ACCESS_TRIGGER_CHAN7	GENMASK(31, 24)
+#define		RDMA_ACCESS_TRIGGER_CHAN6	GENMASK(23, 16)
+#define		RDMA_ACCESS_TRIGGER_CHAN5	GENMASK(15, 8)
+#define		RDMA_ACCESS_TRIGGER_CHAN4	GENMASK(7, 0)
 #define RDMA_ACCESS_MAN 0x1113
+#define		RDMA_ACCESS_MAN_RW_FLAG		BIT(2)
+#define		RDMA_ACCESS_MAN_ADDR_INC	BIT(1)
+#define		RDMA_ACCESS_MAN_START		BIT(0)
 #define RDMA_CTRL 0x1114
+#define		RDMA_IRQ_CLEAR_CHAN7	BIT(31)
+#define		RDMA_IRQ_CLEAR_CHAN6	BIT(30)
+#define		RDMA_IRQ_CLEAR_CHAN5	BIT(29)
+#define		RDMA_IRQ_CLEAR_CHAN4	BIT(28)
+#define		RDMA_IRQ_CLEAR_CHAN3	BIT(27)
+#define		RDMA_IRQ_CLEAR_CHAN2	BIT(26)
+#define		RDMA_IRQ_CLEAR_CHAN1	BIT(25)
+#define		RDMA_IRQ_CLEAR_CHAN_MAN	BIT(24)
+#define		RDMA_DEFAULT_CONFIG	(BIT(7) | BIT(6))
+#define		RDMA_CTRL_AHB_WR_BURST	GENMASK(5, 4)
+#define		RDMA_CTRL_AHB_RD_BURST	GENMASK(3, 2)
+#define		RDMA_CTRL_SW_RESET	BIT(1)
+#define		RDMA_CTRL_FREE_CLK_EN	BIT(0)
 #define RDMA_STATUS 0x1115
+#define		RDMA_IRQ_STAT_CHAN7	BIT(31)
+#define		RDMA_IRQ_STAT_CHAN6	BIT(30)
+#define		RDMA_IRQ_STAT_CHAN5	BIT(29)
+#define		RDMA_IRQ_STAT_CHAN4	BIT(28)
+#define		RDMA_IRQ_STAT_CHAN3	BIT(27)
+#define		RDMA_IRQ_STAT_CHAN2	BIT(26)
+#define		RDMA_IRQ_STAT_CHAN1	BIT(25)
+#define		RDMA_IRQ_STAT_CHAN_MAN	BIT(24)
 #define RDMA_STATUS2 0x1116
 #define RDMA_STATUS3 0x1117
 #define L_GAMMA_CNTL_PORT 0x1400
@@ -1595,15 +1659,33 @@
 
 /* osd afbcd on gxtvbb */
 #define OSD1_AFBCD_ENABLE 0x31a0
+#define		OSD1_AFBCD_ID_FIFO_THRD			GENMASK(15, 9)
+#define		OSD1_AFBCD_DEC_ENABLE			BIT(8)
+#define		OSD1_AFBCD_FRM_START			BIT(0)
 #define OSD1_AFBCD_MODE 0x31a1
+#define		OSD1_AFBCD_SOFT_RESET			BIT(31)
+#define		OSD1_AFBCD_AXI_REORDER_MODE		BIT(28)
+#define		OSD1_AFBCD_MIF_URGENT			GENMASK(25, 24)
+#define		OSD1_AFBCD_HOLD_LINE_NUM		GENMASK(22, 16)
+#define		OSD1_AFBCD_RGBA_EXCHAN_CTRL		GENMASK(15, 8)
+#define		OSD1_AFBCD_HREG_BLOCK_SPLIT		BIT(6)
+#define		OSD1_AFBCD_HREG_HALF_BLOCK		BIT(5)
+#define		OSD1_AFBCD_HREG_PIXEL_PACKING_FMT	GENMASK(4, 0)
 #define OSD1_AFBCD_SIZE_IN 0x31a2
+#define		OSD1_AFBCD_HREG_VSIZE_IN		GENMASK(31, 16)
+#define		OSD1_AFBCD_HREG_HSIZE_IN		GENMASK(15, 0)
 #define OSD1_AFBCD_HDR_PTR 0x31a3
 #define OSD1_AFBCD_FRAME_PTR 0x31a4
 #define OSD1_AFBCD_CHROMA_PTR 0x31a5
 #define OSD1_AFBCD_CONV_CTRL 0x31a6
+#define		OSD1_AFBCD_CONV_LBUF_LEN		GENMASK(15, 0)
 #define OSD1_AFBCD_STATUS 0x31a8
 #define OSD1_AFBCD_PIXEL_HSCOPE 0x31a9
+#define		OSD1_AFBCD_DEC_PIXEL_BGN_H		GENMASK(31, 16)
+#define		OSD1_AFBCD_DEC_PIXEL_END_H		GENMASK(15, 0)
 #define OSD1_AFBCD_PIXEL_VSCOPE 0x31aa
+#define		OSD1_AFBCD_DEC_PIXEL_BGN_V		GENMASK(31, 16)
+#define		OSD1_AFBCD_DEC_PIXEL_END_V		GENMASK(15, 0)
 
 /* add for gxm and 962e dv core2 */
 #define DOLBY_CORE2A_SWAP_CTRL1	0x3434
@@ -1615,12 +1697,34 @@
 #define VPU_MAFBC_IRQ_CLEAR 0x3a02
 #define VPU_MAFBC_IRQ_MASK 0x3a03
 #define VPU_MAFBC_IRQ_STATUS 0x3a04
+#define		VPU_MAFBC_IRQ_SECURE_ID_ERROR		BIT(5)
+#define		VPU_MAFBC_IRQ_AXI_ERROR			BIT(4)
+#define		VPU_MAFBC_IRQ_DETILING_ERROR		BIT(3)
+#define		VPU_MAFBC_IRQ_DECODE_ERROR		BIT(2)
+#define		VPU_MAFBC_IRQ_CONFIGURATION_SWAPPED	BIT(1)
+#define		VPU_MAFBC_IRQ_SURFACES_COMPLETED	BIT(0)
 #define VPU_MAFBC_COMMAND 0x3a05
+#define		VPU_MAFBC_PENDING_SWAP	BIT(1)
+#define		VPU_MAFBC_DIRECT_SWAP	BIT(0)
 #define VPU_MAFBC_STATUS 0x3a06
+#define		VPU_MAFBC_ERROR		BIT(2)
+#define		VPU_MAFBC_SWAPPING	BIT(1)
+#define		VPU_MAFBC_ACTIVE	BIT(0)
 #define VPU_MAFBC_SURFACE_CFG 0x3a07
+#define		VPU_MAFBC_CONTINUOUS_DECODING_ENABLE	BIT(16)
+#define		VPU_MAFBC_S3_ENABLE			BIT(3)
+#define		VPU_MAFBC_S2_ENABLE			BIT(2)
+#define		VPU_MAFBC_S1_ENABLE			BIT(1)
+#define		VPU_MAFBC_S0_ENABLE			BIT(0)
 #define VPU_MAFBC_HEADER_BUF_ADDR_LOW_S0 0x3a10
 #define VPU_MAFBC_HEADER_BUF_ADDR_HIGH_S0 0x3a11
 #define VPU_MAFBC_FORMAT_SPECIFIER_S0 0x3a12
+#define		VPU_MAFBC_PAYLOAD_LIMIT_EN	BIT(19)
+#define		VPU_MAFBC_TILED_HEADER_EN	BIT(18)
+#define		VPU_MAFBC_SUPER_BLOCK_ASPECT	GENMASK(17, 16)
+#define		VPU_MAFBC_BLOCK_SPLIT		BIT(9)
+#define		VPU_MAFBC_YUV_TRANSFORM		BIT(8)
+#define		VPU_MAFBC_PIXEL_FORMAT		GENMASK(3, 0)
 #define VPU_MAFBC_BUFFER_WIDTH_S0 0x3a13
 #define VPU_MAFBC_BUFFER_HEIGHT_S0 0x3a14
 #define VPU_MAFBC_BOUNDING_BOX_X_START_S0 0x3a15
@@ -1631,6 +1735,8 @@
 #define VPU_MAFBC_OUTPUT_BUF_ADDR_HIGH_S0 0x3a1a
 #define VPU_MAFBC_OUTPUT_BUF_STRIDE_S0 0x3a1b
 #define VPU_MAFBC_PREFETCH_CFG_S0 0x3a1c
+#define		VPU_MAFBC_PREFETCH_READ_DIRECTION_Y	BIT(1)
+#define		VPU_MAFBC_PREFETCH_READ_DIRECTION_X	BIT(0)
 
 #define VPU_MAFBC_HEADER_BUF_ADDR_LOW_S1 0x3a30
 #define VPU_MAFBC_HEADER_BUF_ADDR_HIGH_S1 0x3a31
@@ -1677,7 +1783,11 @@
 #define DOLBY_PATH_CTRL 0x1a0c
 #define		DOLBY_BYPASS_EN(val)            (val & 0xf)
 #define OSD_PATH_MISC_CTRL 0x1a0e
+#define		OSD_PATH_OSD_AXI_SEL_OSD1_AFBCD	BIT(4)
+#define		OSD_PATH_OSD_AXI_SEL_OSD2_AFBCD	BIT(5)
+#define		OSD_PATH_OSD_AXI_SEL_OSD3_AFBCD	BIT(6)
 #define MALI_AFBCD_TOP_CTRL 0x1a0f
+#define		MALI_AFBCD_MANUAL_RESET		BIT(23)
 
 #define VIU_OSD_BLEND_CTRL 0x39b0
 #define		VIU_OSD_BLEND_REORDER(dest, src)      ((src) << (dest * 4))
diff --git a/drivers/gpu/drm/meson/meson_viu.c b/drivers/gpu/drm/meson/meson_viu.c
index 68cf2c2eca5f..304f8ff1339c 100644
--- a/drivers/gpu/drm/meson/meson_viu.c
+++ b/drivers/gpu/drm/meson/meson_viu.c
@@ -7,6 +7,9 @@
  */
 
 #include <linux/export.h>
+#include <linux/bitfield.h>
+
+#include <drm/drm_fourcc.h>
 
 #include "meson_drv.h"
 #include "meson_viu.h"
@@ -335,6 +338,79 @@ void meson_viu_osd1_reset(struct meson_drm *priv)
 	meson_viu_load_matrix(priv);
 }
 
+#define OSD1_MALI_ORDER_ABGR				\
+	(FIELD_PREP(VIU_OSD1_MALI_AFBCD_A_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_A) |		\
+	 FIELD_PREP(VIU_OSD1_MALI_AFBCD_B_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_B) |		\
+	 FIELD_PREP(VIU_OSD1_MALI_AFBCD_G_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_G) |		\
+	 FIELD_PREP(VIU_OSD1_MALI_AFBCD_R_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_R))
+
+#define OSD1_MALI_ORDER_ARGB				\
+	(FIELD_PREP(VIU_OSD1_MALI_AFBCD_A_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_A) |		\
+	 FIELD_PREP(VIU_OSD1_MALI_AFBCD_B_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_R) |		\
+	 FIELD_PREP(VIU_OSD1_MALI_AFBCD_G_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_G) |		\
+	 FIELD_PREP(VIU_OSD1_MALI_AFBCD_R_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_B))
+
+void meson_viu_g12a_enable_osd1_afbc(struct meson_drm *priv)
+{
+	u32 afbc_order = OSD1_MALI_ORDER_ARGB;
+
+	/* Enable Mali AFBC Unpack */
+	writel_bits_relaxed(VIU_OSD1_MALI_UNPACK_EN,
+			    VIU_OSD1_MALI_UNPACK_EN,
+			    priv->io_base + _REG(VIU_OSD1_MALI_UNPACK_CTRL));
+
+	switch (priv->afbcd.format) {
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+		afbc_order = OSD1_MALI_ORDER_ABGR;
+		break;
+	}
+
+	/* Setup RGBA Reordering */
+	writel_bits_relaxed(VIU_OSD1_MALI_AFBCD_A_REORDER |
+			    VIU_OSD1_MALI_AFBCD_B_REORDER |
+			    VIU_OSD1_MALI_AFBCD_G_REORDER |
+			    VIU_OSD1_MALI_AFBCD_R_REORDER,
+			    afbc_order,
+			    priv->io_base + _REG(VIU_OSD1_MALI_UNPACK_CTRL));
+
+	/* Select AFBCD path for OSD1 */
+	writel_bits_relaxed(OSD_PATH_OSD_AXI_SEL_OSD1_AFBCD,
+			    OSD_PATH_OSD_AXI_SEL_OSD1_AFBCD,
+			    priv->io_base + _REG(OSD_PATH_MISC_CTRL));
+}
+
+void meson_viu_g12a_disable_osd1_afbc(struct meson_drm *priv)
+{
+	/* Disable AFBCD path for OSD1 */
+	writel_bits_relaxed(OSD_PATH_OSD_AXI_SEL_OSD1_AFBCD, 0,
+			    priv->io_base + _REG(OSD_PATH_MISC_CTRL));
+
+	/* Disable AFBCD unpack */
+	writel_bits_relaxed(VIU_OSD1_MALI_UNPACK_EN, 0,
+			    priv->io_base + _REG(VIU_OSD1_MALI_UNPACK_CTRL));
+}
+
+void meson_viu_gxm_enable_osd1_afbc(struct meson_drm *priv)
+{
+	writel_bits_relaxed(MALI_AFBC_MISC, FIELD_PREP(MALI_AFBC_MISC, 0x90),
+			    priv->io_base + _REG(VIU_MISC_CTRL1));
+}
+
+void meson_viu_gxm_disable_osd1_afbc(struct meson_drm *priv)
+{
+	writel_bits_relaxed(MALI_AFBC_MISC, FIELD_PREP(MALI_AFBC_MISC, 0x00),
+			    priv->io_base + _REG(VIU_MISC_CTRL1));
+}
+
 static inline uint32_t meson_viu_osd_burst_length_reg(uint32_t length)
 {
 	uint32_t val = (((length & 0x80) % 24) / 12);
@@ -362,7 +438,7 @@ void meson_viu_init(struct meson_drm *priv)
 
 	/* Initialize OSD1 fifo control register */
 	reg = VIU_OSD_DDR_PRIORITY_URGENT |
-		VIU_OSD_HOLD_FIFO_LINES(4) |
+		VIU_OSD_HOLD_FIFO_LINES(31) |
 		VIU_OSD_FIFO_DEPTH_VAL(32) | /* fifo_depth_val: 32*8=256 */
 		VIU_OSD_WORDS_PER_BURST(4) | /* 4 words in 1 burst */
 		VIU_OSD_FIFO_LIMITS(2);      /* fifo_lim: 2*16=32 */
@@ -420,8 +496,13 @@ void meson_viu_init(struct meson_drm *priv)
 
 		writel_bits_relaxed(DOLBY_BYPASS_EN(0xc), DOLBY_BYPASS_EN(0xc),
 				    priv->io_base + _REG(DOLBY_PATH_CTRL));
+
+		meson_viu_g12a_disable_osd1_afbc(priv);
 	}
 
+	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM))
+		meson_viu_gxm_disable_osd1_afbc(priv);
+
 	priv->viu.osd1_enabled = false;
 	priv->viu.osd1_commit = false;
 	priv->viu.osd1_interlace = false;
diff --git a/drivers/gpu/drm/meson/meson_viu.h b/drivers/gpu/drm/meson/meson_viu.h
index a112e8d18850..e4a2f24d7c38 100644
--- a/drivers/gpu/drm/meson/meson_viu.h
+++ b/drivers/gpu/drm/meson/meson_viu.h
@@ -10,6 +10,8 @@
 #define __MESON_VIU_H
 
 /* OSDx_BLKx_CFG */
+#define OSD_MALI_SRC_EN		BIT(30)
+
 #define OSD_CANVAS_SEL		16
 
 #define OSD_ENDIANNESS_LE	BIT(15)
@@ -33,21 +35,38 @@
 #define OSD_COLOR_MATRIX_16_RGB655	(0x00 << 2)
 #define OSD_COLOR_MATRIX_16_RGB565	(0x04 << 2)
 
+#define OSD_MALI_COLOR_MODE_R8		(0 << 8)
+#define OSD_MALI_COLOR_MODE_YUV422	(1 << 8)
+#define OSD_MALI_COLOR_MODE_RGB565	(2 << 8)
+#define OSD_MALI_COLOR_MODE_RGBA5551	(3 << 8)
+#define OSD_MALI_COLOR_MODE_RGBA4444	(4 << 8)
+#define OSD_MALI_COLOR_MODE_RGBA8888	(5 << 8)
+#define OSD_MALI_COLOR_MODE_RGB888	(7 << 8)
+#define OSD_MALI_COLOR_MODE_YUV422_10B	(8 << 8)
+#define OSD_MALI_COLOR_MODE_RGBA1010102	(9 << 8)
+
 #define OSD_INTERLACE_ENABLED	BIT(1)
 #define OSD_INTERLACE_ODD	BIT(0)
 #define OSD_INTERLACE_EVEN	(0)
 
 /* OSDx_CTRL_STAT */
 #define OSD_ENABLE		BIT(21)
+#define OSD_MEM_LINEAR_ADDR	BIT(2)
 #define OSD_BLK0_ENABLE		BIT(0)
 
 #define OSD_GLOBAL_ALPHA_SHIFT	12
 
 /* OSDx_CTRL_STAT2 */
+#define OSD_DPATH_MALI_AFBCD	BIT(15)
 #define OSD_REPLACE_EN		BIT(14)
 #define OSD_REPLACE_SHIFT	6
+#define OSD_PENDING_STAT_CLEAN	BIT(1)
 
 void meson_viu_osd1_reset(struct meson_drm *priv);
+void meson_viu_g12a_enable_osd1_afbc(struct meson_drm *priv);
+void meson_viu_g12a_disable_osd1_afbc(struct meson_drm *priv);
+void meson_viu_gxm_enable_osd1_afbc(struct meson_drm *priv);
+void meson_viu_gxm_disable_osd1_afbc(struct meson_drm *priv);
 void meson_viu_init(struct meson_drm *priv);
 
 #endif /* __MESON_VIU_H */