Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for 4.5.  I don't think I've missed
  anything too major, I'm mostly back at work now but I'll probably get
  some sleep in 5 years time.

  Summary:

  New drivers:
   - etnaviv:

     GPU driver for the 3D core on the Vivante core used in numerous
     ARM boards.

  Highlights:

  Core:
   - Atomic suspend/resume helpers
   - Move the headers to using userspace friendlier types.
   - Documentation updates
   - Lots of struct_mutex removal.
   - Bunch of DP MST fixes from AMD.

  Panel:
   - More DSI helpers
   - Support for some new basic panels

  i915:
   - Basic Kabylake support
   - DP link training and detect code refactoring
   - fbc/psr fixes
   - FIFO underrun fixes
   - SDE interrupt handling fixes
   - dma-buf/fence support in pageflip path.
   - GPU side for MST audio support

  radeon/amdgpu:
   - Drop UMS support
   - GPUVM/Scheduler optimisations
   - Initial Powerplay support for Tonga/Fiji/CZ/ST
   - ACP audio prerequisites

  nouveau:
   - GK20a instmem improvements
   - PCIE link speed change support

  msm:
   - DSI support for msm8960/apq8064

  tegra:
   - Host1X support for Tegra210 SoC

  vc4:
   - 3D acceleration support

  armada:
   - Get rid of struct mutex

  tda998x:
   - Atomic modesetting support
   - TMDS clock limitations

  omapdrm:
   - Atomic modesetting support
   - improved TILER performance

  rockchip:
   - RK3036 VOP support
   - Atomic modesetting support
   - Synopsys DW MIPI DSI support

  exynos:
   - Runtime PM support
   - of_graph binding for DP panels
   - Cleanup of IPP code
   - Configurable plane support
   - Kernel panic fixes at release time"

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (711 commits)
  drm/fb_cma_helper: Remove implicit call to disable_unused_functions
  drm/amdgpu: add missing irq.h include
  drm/vmwgfx: Fix a width / pitch mismatch on framebuffer updates
  drm/vmwgfx: Fix an incorrect lock check
  drm: nouveau: fix nouveau_debugfs_init prototype
  drm/nouveau/pci: fix check in nvkm_pcie_set_link
  drm/amdgpu: validate duplicates first
  drm/amdgpu: move VM page tables to the LRU end on CS v2
  drm/ttm: add ttm_bo_move_to_lru_tail function v2
  drm/ttm: fix adding foreign BOs to the swap LRU
  drm/ttm: fix adding foreign BOs to the LRU during init v2
  drm/radeon: use kobj_to_dev()
  drm/amdgpu: use kobj_to_dev()
  drm/amdgpu/cz: force vce clocks when sclks are forced
  drm/amdgpu/cz: force uvd clocks when sclks are forced
  drm/amdgpu/cz: add code to enable forcing VCE clocks
  drm/amdgpu/cz: add code to enable forcing UVD clocks
  drm/amdgpu: fix lost sync_to if scheduler is enabled.
  drm/amd/powerplay: fix static checker warning for return meaningless value.
  drm/sysfs: use kobj_to_dev()
  ...

11 files changed, 1160 insertions, 145 deletions

diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h
index 5f5a3732cdf6..749fbb28ec3d 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.h
+++ b/drivers/gpu/drm/msm/dsi/dsi.h
@@ -31,10 +31,12 @@ enum msm_dsi_phy_type {
 	MSM_DSI_PHY_28NM_HPM,
 	MSM_DSI_PHY_28NM_LP,
 	MSM_DSI_PHY_20NM,
+	MSM_DSI_PHY_28NM_8960,
 	MSM_DSI_PHY_MAX
 };
 
 #define DSI_DEV_REGULATOR_MAX	8
+#define DSI_BUS_CLK_MAX		4
 
 /* Regulators for DSI devices */
 struct dsi_reg_entry {
@@ -89,7 +91,7 @@ int msm_dsi_manager_phy_enable(int id,
 		u32 *clk_pre, u32 *clk_post);
 void msm_dsi_manager_phy_disable(int id);
 int msm_dsi_manager_cmd_xfer(int id, const struct mipi_dsi_msg *msg);
-bool msm_dsi_manager_cmd_xfer_trigger(int id, u32 iova, u32 len);
+bool msm_dsi_manager_cmd_xfer_trigger(int id, u32 dma_base, u32 len);
 int msm_dsi_manager_register(struct msm_dsi *msm_dsi);
 void msm_dsi_manager_unregister(struct msm_dsi *msm_dsi);
 
@@ -143,7 +145,7 @@ int msm_dsi_host_cmd_tx(struct mipi_dsi_host *host,
 int msm_dsi_host_cmd_rx(struct mipi_dsi_host *host,
 					const struct mipi_dsi_msg *msg);
 void msm_dsi_host_cmd_xfer_commit(struct mipi_dsi_host *host,
-					u32 iova, u32 len);
+					u32 dma_base, u32 len);
 int msm_dsi_host_enable(struct mipi_dsi_host *host);
 int msm_dsi_host_disable(struct mipi_dsi_host *host);
 int msm_dsi_host_power_on(struct mipi_dsi_host *host);
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
index 5872d5e5934f..2a827d8093a2 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
@@ -13,9 +13,26 @@
 
 #include "dsi_cfg.h"
 
-/* DSI v2 has not been supported by now */
-static const struct msm_dsi_config dsi_v2_cfg = {
+static const char * const dsi_v2_bus_clk_names[] = {
+	"core_mmss_clk", "iface_clk", "bus_clk",
+};
+
+static const struct msm_dsi_config apq8064_dsi_cfg = {
 	.io_offset = 0,
+	.reg_cfg = {
+		.num = 3,
+		.regs = {
+			{"vdda", 1200000, 1200000, 100000, 100},
+			{"avdd", 3000000, 3000000, 110000, 100},
+			{"vddio", 1800000, 1800000, 100000, 100},
+		},
+	},
+	.bus_clk_names = dsi_v2_bus_clk_names,
+	.num_bus_clks = ARRAY_SIZE(dsi_v2_bus_clk_names),
+};
+
+static const char * const dsi_6g_bus_clk_names[] = {
+	"mdp_core_clk", "iface_clk", "bus_clk", "core_mmss_clk",
 };
 
 static const struct msm_dsi_config msm8974_apq8084_dsi_cfg = {
@@ -29,6 +46,12 @@ static const struct msm_dsi_config msm8974_apq8084_dsi_cfg = {
 			{"vddio", 1800000, 1800000, 100000, 100},
 		},
 	},
+	.bus_clk_names = dsi_6g_bus_clk_names,
+	.num_bus_clks = ARRAY_SIZE(dsi_6g_bus_clk_names),
+};
+
+static const char * const dsi_8916_bus_clk_names[] = {
+	"mdp_core_clk", "iface_clk", "bus_clk",
 };
 
 static const struct msm_dsi_config msm8916_dsi_cfg = {
@@ -42,6 +65,8 @@ static const struct msm_dsi_config msm8916_dsi_cfg = {
 			{"vddio", 1800000, 1800000, 100000, 100},
 		},
 	},
+	.bus_clk_names = dsi_8916_bus_clk_names,
+	.num_bus_clks = ARRAY_SIZE(dsi_8916_bus_clk_names),
 };
 
 static const struct msm_dsi_config msm8994_dsi_cfg = {
@@ -57,11 +82,13 @@ static const struct msm_dsi_config msm8994_dsi_cfg = {
 			{"lab_reg", -1, -1, -1, -1},
 			{"ibb_reg", -1, -1, -1, -1},
 		},
-	}
+	},
+	.bus_clk_names = dsi_6g_bus_clk_names,
+	.num_bus_clks = ARRAY_SIZE(dsi_6g_bus_clk_names),
 };
 
 static const struct msm_dsi_cfg_handler dsi_cfg_handlers[] = {
-	{MSM_DSI_VER_MAJOR_V2, U32_MAX, &dsi_v2_cfg},
+	{MSM_DSI_VER_MAJOR_V2, MSM_DSI_V2_VER_MINOR_8064, &apq8064_dsi_cfg},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_0,
 						&msm8974_apq8084_dsi_cfg},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_1,
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.h b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
index 4cf887240177..a68c836744a3 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.h
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
@@ -25,11 +25,15 @@
 #define MSM_DSI_6G_VER_MINOR_V1_3	0x10030000
 #define MSM_DSI_6G_VER_MINOR_V1_3_1	0x10030001
 
+#define MSM_DSI_V2_VER_MINOR_8064	0x0
+
 #define DSI_6G_REG_SHIFT	4
 
 struct msm_dsi_config {
 	u32 io_offset;
 	struct dsi_reg_config reg_cfg;
+	const char * const *bus_clk_names;
+	const int num_bus_clks;
 };
 
 struct msm_dsi_cfg_handler {
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 4c49868efcda..48f9967b4a1b 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -24,26 +24,36 @@
 #include <linux/of_graph.h>
 #include <linux/regulator/consumer.h>
 #include <linux/spinlock.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 #include <video/mipi_display.h>
 
 #include "dsi.h"
 #include "dsi.xml.h"
+#include "sfpb.xml.h"
 #include "dsi_cfg.h"
 
 static int dsi_get_version(const void __iomem *base, u32 *major, u32 *minor)
 {
 	u32 ver;
-	u32 ver_6g;
 
 	if (!major || !minor)
 		return -EINVAL;
 
-	/* From DSI6G(v3), addition of a 6G_HW_VERSION register at offset 0
+	/*
+	 * From DSI6G(v3), addition of a 6G_HW_VERSION register at offset 0
 	 * makes all other registers 4-byte shifted down.
+	 *
+	 * In order to identify between DSI6G(v3) and beyond, and DSIv2 and
+	 * older, we read the DSI_VERSION register without any shift(offset
+	 * 0x1f0). In the case of DSIv2, this hast to be a non-zero value. In
+	 * the case of DSI6G, this has to be zero (the offset points to a
+	 * scratch register which we never touch)
 	 */
-	ver_6g = msm_readl(base + REG_DSI_6G_HW_VERSION);
-	if (ver_6g == 0) {
-		ver = msm_readl(base + REG_DSI_VERSION);
+
+	ver = msm_readl(base + REG_DSI_VERSION);
+	if (ver) {
+		/* older dsi host, there is no register shift */
 		ver = FIELD(ver, DSI_VERSION_MAJOR);
 		if (ver <= MSM_DSI_VER_MAJOR_V2) {
 			/* old versions */
@@ -54,12 +64,17 @@ static int dsi_get_version(const void __iomem *base, u32 *major, u32 *minor)
 			return -EINVAL;
 		}
 	} else {
+		/*
+		 * newer host, offset 0 has 6G_HW_VERSION, the rest of the
+		 * registers are shifted down, read DSI_VERSION again with
+		 * the shifted offset
+		 */
 		ver = msm_readl(base + DSI_6G_REG_SHIFT + REG_DSI_VERSION);
 		ver = FIELD(ver, DSI_VERSION_MAJOR);
 		if (ver == MSM_DSI_VER_MAJOR_6G) {
 			/* 6G version */
 			*major = ver;
-			*minor = ver_6g;
+			*minor = msm_readl(base + REG_DSI_6G_HW_VERSION);
 			return 0;
 		} else {
 			return -EINVAL;
@@ -91,10 +106,9 @@ struct msm_dsi_host {
 
 	void __iomem *ctrl_base;
 	struct regulator_bulk_data supplies[DSI_DEV_REGULATOR_MAX];
-	struct clk *mdp_core_clk;
-	struct clk *ahb_clk;
-	struct clk *axi_clk;
-	struct clk *mmss_misc_ahb_clk;
+
+	struct clk *bus_clks[DSI_BUS_CLK_MAX];
+
 	struct clk *byte_clk;
 	struct clk *esc_clk;
 	struct clk *pixel_clk;
@@ -102,6 +116,14 @@ struct msm_dsi_host {
 	struct clk *pixel_clk_src;
 
 	u32 byte_clk_rate;
+	u32 esc_clk_rate;
+
+	/* DSI v2 specific clocks */
+	struct clk *src_clk;
+	struct clk *esc_clk_src;
+	struct clk *dsi_clk_src;
+
+	u32 src_clk_rate;
 
 	struct gpio_desc *disp_en_gpio;
 	struct gpio_desc *te_gpio;
@@ -119,9 +141,19 @@ struct msm_dsi_host {
 	struct work_struct err_work;
 	struct workqueue_struct *workqueue;
 
+	/* DSI 6G TX buffer*/
 	struct drm_gem_object *tx_gem_obj;
+
+	/* DSI v2 TX buffer */
+	void *tx_buf;
+	dma_addr_t tx_buf_paddr;
+
+	int tx_size;
+
 	u8 *rx_buf;
 
+	struct regmap *sfpb;
+
 	struct drm_display_mode *mode;
 
 	/* connected device info */
@@ -165,21 +197,31 @@ static const struct msm_dsi_cfg_handler *dsi_get_config(
 						struct msm_dsi_host *msm_host)
 {
 	const struct msm_dsi_cfg_handler *cfg_hnd = NULL;
+	struct device *dev = &msm_host->pdev->dev;
 	struct regulator *gdsc_reg;
+	struct clk *ahb_clk;
 	int ret;
 	u32 major = 0, minor = 0;
 
-	gdsc_reg = regulator_get(&msm_host->pdev->dev, "gdsc");
+	gdsc_reg = regulator_get(dev, "gdsc");
 	if (IS_ERR(gdsc_reg)) {
 		pr_err("%s: cannot get gdsc\n", __func__);
 		goto exit;
 	}
+
+	ahb_clk = clk_get(dev, "iface_clk");
+	if (IS_ERR(ahb_clk)) {
+		pr_err("%s: cannot get interface clock\n", __func__);
+		goto put_gdsc;
+	}
+
 	ret = regulator_enable(gdsc_reg);
 	if (ret) {
 		pr_err("%s: unable to enable gdsc\n", __func__);
-		goto put_gdsc;
+		goto put_clk;
 	}
-	ret = clk_prepare_enable(msm_host->ahb_clk);
+
+	ret = clk_prepare_enable(ahb_clk);
 	if (ret) {
 		pr_err("%s: unable to enable ahb_clk\n", __func__);
 		goto disable_gdsc;
@@ -196,9 +238,11 @@ static const struct msm_dsi_cfg_handler *dsi_get_config(
 	DBG("%s: Version %x:%x\n", __func__, major, minor);
 
 disable_clks:
-	clk_disable_unprepare(msm_host->ahb_clk);
+	clk_disable_unprepare(ahb_clk);
 disable_gdsc:
 	regulator_disable(gdsc_reg);
+put_clk:
+	clk_put(ahb_clk);
 put_gdsc:
 	regulator_put(gdsc_reg);
 exit:
@@ -295,40 +339,23 @@ static int dsi_regulator_init(struct msm_dsi_host *msm_host)
 static int dsi_clk_init(struct msm_dsi_host *msm_host)
 {
 	struct device *dev = &msm_host->pdev->dev;
-	int ret = 0;
-
-	msm_host->mdp_core_clk = devm_clk_get(dev, "mdp_core_clk");
-	if (IS_ERR(msm_host->mdp_core_clk)) {
-		ret = PTR_ERR(msm_host->mdp_core_clk);
-		pr_err("%s: Unable to get mdp core clk. ret=%d\n",
-			__func__, ret);
-		goto exit;
-	}
-
-	msm_host->ahb_clk = devm_clk_get(dev, "iface_clk");
-	if (IS_ERR(msm_host->ahb_clk)) {
-		ret = PTR_ERR(msm_host->ahb_clk);
-		pr_err("%s: Unable to get mdss ahb clk. ret=%d\n",
-			__func__, ret);
-		goto exit;
-	}
-
-	msm_host->axi_clk = devm_clk_get(dev, "bus_clk");
-	if (IS_ERR(msm_host->axi_clk)) {
-		ret = PTR_ERR(msm_host->axi_clk);
-		pr_err("%s: Unable to get axi bus clk. ret=%d\n",
-			__func__, ret);
-		goto exit;
-	}
-
-	msm_host->mmss_misc_ahb_clk = devm_clk_get(dev, "core_mmss_clk");
-	if (IS_ERR(msm_host->mmss_misc_ahb_clk)) {
-		ret = PTR_ERR(msm_host->mmss_misc_ahb_clk);
-		pr_err("%s: Unable to get mmss misc ahb clk. ret=%d\n",
-			__func__, ret);
-		goto exit;
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
+	const struct msm_dsi_config *cfg = cfg_hnd->cfg;
+	int i, ret = 0;
+
+	/* get bus clocks */
+	for (i = 0; i < cfg->num_bus_clks; i++) {
+		msm_host->bus_clks[i] = devm_clk_get(dev,
+						cfg->bus_clk_names[i]);
+		if (IS_ERR(msm_host->bus_clks[i])) {
+			ret = PTR_ERR(msm_host->bus_clks[i]);
+			pr_err("%s: Unable to get %s, ret = %d\n",
+				__func__, cfg->bus_clk_names[i], ret);
+			goto exit;
+		}
 	}
 
+	/* get link and source clocks */
 	msm_host->byte_clk = devm_clk_get(dev, "byte_clk");
 	if (IS_ERR(msm_host->byte_clk)) {
 		ret = PTR_ERR(msm_host->byte_clk);
@@ -356,80 +383,85 @@ static int dsi_clk_init(struct msm_dsi_host *msm_host)
 		goto exit;
 	}
 
-	msm_host->byte_clk_src = devm_clk_get(dev, "byte_clk_src");
-	if (IS_ERR(msm_host->byte_clk_src)) {
-		ret = PTR_ERR(msm_host->byte_clk_src);
+	msm_host->byte_clk_src = clk_get_parent(msm_host->byte_clk);
+	if (!msm_host->byte_clk_src) {
+		ret = -ENODEV;
 		pr_err("%s: can't find byte_clk_src. ret=%d\n", __func__, ret);
-		msm_host->byte_clk_src = NULL;
 		goto exit;
 	}
 
-	msm_host->pixel_clk_src = devm_clk_get(dev, "pixel_clk_src");
-	if (IS_ERR(msm_host->pixel_clk_src)) {
-		ret = PTR_ERR(msm_host->pixel_clk_src);
+	msm_host->pixel_clk_src = clk_get_parent(msm_host->pixel_clk);
+	if (!msm_host->pixel_clk_src) {
+		ret = -ENODEV;
 		pr_err("%s: can't find pixel_clk_src. ret=%d\n", __func__, ret);
-		msm_host->pixel_clk_src = NULL;
 		goto exit;
 	}
 
+	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_V2) {
+		msm_host->src_clk = devm_clk_get(dev, "src_clk");
+		if (IS_ERR(msm_host->src_clk)) {
+			ret = PTR_ERR(msm_host->src_clk);
+			pr_err("%s: can't find dsi_src_clk. ret=%d\n",
+				__func__, ret);
+			msm_host->src_clk = NULL;
+			goto exit;
+		}
+
+		msm_host->esc_clk_src = clk_get_parent(msm_host->esc_clk);
+		if (!msm_host->esc_clk_src) {
+			ret = -ENODEV;
+			pr_err("%s: can't get esc_clk_src. ret=%d\n",
+				__func__, ret);
+			goto exit;
+		}
+
+		msm_host->dsi_clk_src = clk_get_parent(msm_host->src_clk);
+		if (!msm_host->dsi_clk_src) {
+			ret = -ENODEV;
+			pr_err("%s: can't get dsi_clk_src. ret=%d\n",
+				__func__, ret);
+		}
+	}
 exit:
 	return ret;
 }
 
 static int dsi_bus_clk_enable(struct msm_dsi_host *msm_host)
 {
-	int ret;
+	const struct msm_dsi_config *cfg = msm_host->cfg_hnd->cfg;
+	int i, ret;
 
 	DBG("id=%d", msm_host->id);
 
-	ret = clk_prepare_enable(msm_host->mdp_core_clk);
-	if (ret) {
-		pr_err("%s: failed to enable mdp_core_clock, %d\n",
-							 __func__, ret);
-		goto core_clk_err;
-	}
-
-	ret = clk_prepare_enable(msm_host->ahb_clk);
-	if (ret) {
-		pr_err("%s: failed to enable ahb clock, %d\n", __func__, ret);
-		goto ahb_clk_err;
-	}
-
-	ret = clk_prepare_enable(msm_host->axi_clk);
-	if (ret) {
-		pr_err("%s: failed to enable ahb clock, %d\n", __func__, ret);
-		goto axi_clk_err;
-	}
-
-	ret = clk_prepare_enable(msm_host->mmss_misc_ahb_clk);
-	if (ret) {
-		pr_err("%s: failed to enable mmss misc ahb clk, %d\n",
-			__func__, ret);
-		goto misc_ahb_clk_err;
+	for (i = 0; i < cfg->num_bus_clks; i++) {
+		ret = clk_prepare_enable(msm_host->bus_clks[i]);
+		if (ret) {
+			pr_err("%s: failed to enable bus clock %d ret %d\n",
+				__func__, i, ret);
+			goto err;
+		}
 	}
 
 	return 0;
+err:
+	for (; i > 0; i--)
+		clk_disable_unprepare(msm_host->bus_clks[i]);
 
-misc_ahb_clk_err:
-	clk_disable_unprepare(msm_host->axi_clk);
-axi_clk_err:
-	clk_disable_unprepare(msm_host->ahb_clk);
-ahb_clk_err:
-	clk_disable_unprepare(msm_host->mdp_core_clk);
-core_clk_err:
 	return ret;
 }
 
 static void dsi_bus_clk_disable(struct msm_dsi_host *msm_host)
 {
+	const struct msm_dsi_config *cfg = msm_host->cfg_hnd->cfg;
+	int i;
+
 	DBG("");
-	clk_disable_unprepare(msm_host->mmss_misc_ahb_clk);
-	clk_disable_unprepare(msm_host->axi_clk);
-	clk_disable_unprepare(msm_host->ahb_clk);
-	clk_disable_unprepare(msm_host->mdp_core_clk);
+
+	for (i = cfg->num_bus_clks - 1; i >= 0; i--)
+		clk_disable_unprepare(msm_host->bus_clks[i]);
 }
 
-static int dsi_link_clk_enable(struct msm_dsi_host *msm_host)
+static int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host)
 {
 	int ret;
 
@@ -476,11 +508,98 @@ error:
 	return ret;
 }
 
-static void dsi_link_clk_disable(struct msm_dsi_host *msm_host)
+static int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host)
 {
+	int ret;
+
+	DBG("Set clk rates: pclk=%d, byteclk=%d, esc_clk=%d, dsi_src_clk=%d",
+		msm_host->mode->clock, msm_host->byte_clk_rate,
+		msm_host->esc_clk_rate, msm_host->src_clk_rate);
+
+	ret = clk_set_rate(msm_host->byte_clk, msm_host->byte_clk_rate);
+	if (ret) {
+		pr_err("%s: Failed to set rate byte clk, %d\n", __func__, ret);
+		goto error;
+	}
+
+	ret = clk_set_rate(msm_host->esc_clk, msm_host->esc_clk_rate);
+	if (ret) {
+		pr_err("%s: Failed to set rate esc clk, %d\n", __func__, ret);
+		goto error;
+	}
+
+	ret = clk_set_rate(msm_host->src_clk, msm_host->src_clk_rate);
+	if (ret) {
+		pr_err("%s: Failed to set rate src clk, %d\n", __func__, ret);
+		goto error;
+	}
+
+	ret = clk_set_rate(msm_host->pixel_clk, msm_host->mode->clock * 1000);
+	if (ret) {
+		pr_err("%s: Failed to set rate pixel clk, %d\n", __func__, ret);
+		goto error;
+	}
+
+	ret = clk_prepare_enable(msm_host->byte_clk);
+	if (ret) {
+		pr_err("%s: Failed to enable dsi byte clk\n", __func__);
+		goto error;
+	}
+
+	ret = clk_prepare_enable(msm_host->esc_clk);
+	if (ret) {
+		pr_err("%s: Failed to enable dsi esc clk\n", __func__);
+		goto esc_clk_err;
+	}
+
+	ret = clk_prepare_enable(msm_host->src_clk);
+	if (ret) {
+		pr_err("%s: Failed to enable dsi src clk\n", __func__);
+		goto src_clk_err;
+	}
+
+	ret = clk_prepare_enable(msm_host->pixel_clk);
+	if (ret) {
+		pr_err("%s: Failed to enable dsi pixel clk\n", __func__);
+		goto pixel_clk_err;
+	}
+
+	return 0;
+
+pixel_clk_err:
+	clk_disable_unprepare(msm_host->src_clk);
+src_clk_err:
 	clk_disable_unprepare(msm_host->esc_clk);
-	clk_disable_unprepare(msm_host->pixel_clk);
+esc_clk_err:
 	clk_disable_unprepare(msm_host->byte_clk);
+error:
+	return ret;
+}
+
+static int dsi_link_clk_enable(struct msm_dsi_host *msm_host)
+{
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
+
+	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G)
+		return dsi_link_clk_enable_6g(msm_host);
+	else
+		return dsi_link_clk_enable_v2(msm_host);
+}
+
+static void dsi_link_clk_disable(struct msm_dsi_host *msm_host)
+{
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
+
+	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
+		clk_disable_unprepare(msm_host->esc_clk);
+		clk_disable_unprepare(msm_host->pixel_clk);
+		clk_disable_unprepare(msm_host->byte_clk);
+	} else {
+		clk_disable_unprepare(msm_host->pixel_clk);
+		clk_disable_unprepare(msm_host->src_clk);
+		clk_disable_unprepare(msm_host->esc_clk);
+		clk_disable_unprepare(msm_host->byte_clk);
+	}
 }
 
 static int dsi_clk_ctrl(struct msm_dsi_host *msm_host, bool enable)
@@ -515,6 +634,7 @@ unlock_ret:
 static int dsi_calc_clk_rate(struct msm_dsi_host *msm_host)
 {
 	struct drm_display_mode *mode = msm_host->mode;
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	u8 lanes = msm_host->lanes;
 	u32 bpp = dsi_get_bpp(msm_host->format);
 	u32 pclk_rate;
@@ -534,6 +654,47 @@ static int dsi_calc_clk_rate(struct msm_dsi_host *msm_host)
 
 	DBG("pclk=%d, bclk=%d", pclk_rate, msm_host->byte_clk_rate);
 
+	msm_host->esc_clk_rate = clk_get_rate(msm_host->esc_clk);
+
+	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_V2) {
+		unsigned int esc_mhz, esc_div;
+		unsigned long byte_mhz;
+
+		msm_host->src_clk_rate = (pclk_rate * bpp) / 8;
+
+		/*
+		 * esc clock is byte clock followed by a 4 bit divider,
+		 * we need to find an escape clock frequency within the
+		 * mipi DSI spec range within the maximum divider limit
+		 * We iterate here between an escape clock frequencey
+		 * between 20 Mhz to 5 Mhz and pick up the first one
+		 * that can be supported by our divider
+		 */
+
+		byte_mhz = msm_host->byte_clk_rate / 1000000;
+
+		for (esc_mhz = 20; esc_mhz >= 5; esc_mhz--) {
+			esc_div = DIV_ROUND_UP(byte_mhz, esc_mhz);
+
+			/*
+			 * TODO: Ideally, we shouldn't know what sort of divider
+			 * is available in mmss_cc, we're just assuming that
+			 * it'll always be a 4 bit divider. Need to come up with
+			 * a better way here.
+			 */
+			if (esc_div >= 1 && esc_div <= 16)
+				break;
+		}
+
+		if (esc_mhz < 5)
+			return -EINVAL;
+
+		msm_host->esc_clk_rate = msm_host->byte_clk_rate / esc_div;
+
+		DBG("esc=%d, src=%d", msm_host->esc_clk_rate,
+			msm_host->src_clk_rate);
+	}
+
 	return 0;
 }
 
@@ -835,29 +996,46 @@ static void dsi_wait4video_eng_busy(struct msm_dsi_host *msm_host)
 static int dsi_tx_buf_alloc(struct msm_dsi_host *msm_host, int size)
 {
 	struct drm_device *dev = msm_host->dev;
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	int ret;
 	u32 iova;
 
-	mutex_lock(&dev->struct_mutex);
-	msm_host->tx_gem_obj = msm_gem_new(dev, size, MSM_BO_UNCACHED);
-	if (IS_ERR(msm_host->tx_gem_obj)) {
-		ret = PTR_ERR(msm_host->tx_gem_obj);
-		pr_err("%s: failed to allocate gem, %d\n", __func__, ret);
-		msm_host->tx_gem_obj = NULL;
+	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
+		mutex_lock(&dev->struct_mutex);
+		msm_host->tx_gem_obj = msm_gem_new(dev, size, MSM_BO_UNCACHED);
+		if (IS_ERR(msm_host->tx_gem_obj)) {
+			ret = PTR_ERR(msm_host->tx_gem_obj);
+			pr_err("%s: failed to allocate gem, %d\n",
+				__func__, ret);
+			msm_host->tx_gem_obj = NULL;
+			mutex_unlock(&dev->struct_mutex);
+			return ret;
+		}
+
+		ret = msm_gem_get_iova_locked(msm_host->tx_gem_obj, 0, &iova);
 		mutex_unlock(&dev->struct_mutex);
-		return ret;
-	}
+		if (ret) {
+			pr_err("%s: failed to get iova, %d\n", __func__, ret);
+			return ret;
+		}
 
-	ret = msm_gem_get_iova_locked(msm_host->tx_gem_obj, 0, &iova);
-	if (ret) {
-		pr_err("%s: failed to get iova, %d\n", __func__, ret);
-		return ret;
-	}
-	mutex_unlock(&dev->struct_mutex);
+		if (iova & 0x07) {
+			pr_err("%s: buf NOT 8 bytes aligned\n", __func__);
+			return -EINVAL;
+		}
 
-	if (iova & 0x07) {
-		pr_err("%s: buf NOT 8 bytes aligned\n", __func__);
-		return -EINVAL;
+		msm_host->tx_size = msm_host->tx_gem_obj->size;
+	} else {
+		msm_host->tx_buf = dma_alloc_coherent(dev->dev, size,
+					&msm_host->tx_buf_paddr, GFP_KERNEL);
+		if (!msm_host->tx_buf) {
+			ret = -ENOMEM;
+			pr_err("%s: failed to allocate tx buf, %d\n",
+				__func__, ret);
+			return ret;
+		}
+
+		msm_host->tx_size = size;
 	}
 
 	return 0;
@@ -874,14 +1052,19 @@ static void dsi_tx_buf_free(struct msm_dsi_host *msm_host)
 		msm_host->tx_gem_obj = NULL;
 		mutex_unlock(&dev->struct_mutex);
 	}
+
+	if (msm_host->tx_buf)
+		dma_free_coherent(dev->dev, msm_host->tx_size, msm_host->tx_buf,
+			msm_host->tx_buf_paddr);
 }
 
 /*
  * prepare cmd buffer to be txed
  */
-static int dsi_cmd_dma_add(struct drm_gem_object *tx_gem,
-			const struct mipi_dsi_msg *msg)
+static int dsi_cmd_dma_add(struct msm_dsi_host *msm_host,
+			   const struct mipi_dsi_msg *msg)
 {
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	struct mipi_dsi_packet packet;
 	int len;
 	int ret;
@@ -894,17 +1077,20 @@ static int dsi_cmd_dma_add(struct drm_gem_object *tx_gem,
 	}
 	len = (packet.size + 3) & (~0x3);
 
-	if (len > tx_gem->size) {
+	if (len > msm_host->tx_size) {
 		pr_err("%s: packet size is too big\n", __func__);
 		return -EINVAL;
 	}
 
-	data = msm_gem_vaddr(tx_gem);
-
-	if (IS_ERR(data)) {
-		ret = PTR_ERR(data);
-		pr_err("%s: get vaddr failed, %d\n", __func__, ret);
-		return ret;
+	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
+		data = msm_gem_vaddr(msm_host->tx_gem_obj);
+		if (IS_ERR(data)) {
+			ret = PTR_ERR(data);
+			pr_err("%s: get vaddr failed, %d\n", __func__, ret);
+			return ret;
+		}
+	} else {
+		data = msm_host->tx_buf;
 	}
 
 	/* MSM specific command format in memory */
@@ -970,17 +1156,21 @@ static int dsi_long_read_resp(u8 *buf, const struct mipi_dsi_msg *msg)
 	return msg->rx_len;
 }
 
-
 static int dsi_cmd_dma_tx(struct msm_dsi_host *msm_host, int len)
 {
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	int ret;
-	u32 iova;
+	u32 dma_base;
 	bool triggered;
 
-	ret = msm_gem_get_iova(msm_host->tx_gem_obj, 0, &iova);
-	if (ret) {
-		pr_err("%s: failed to get iova: %d\n", __func__, ret);
-		return ret;
+	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
+		ret = msm_gem_get_iova(msm_host->tx_gem_obj, 0, &dma_base);
+		if (ret) {
+			pr_err("%s: failed to get iova: %d\n", __func__, ret);
+			return ret;
+		}
+	} else {
+		dma_base = msm_host->tx_buf_paddr;
 	}
 
 	reinit_completion(&msm_host->dma_comp);
@@ -988,7 +1178,7 @@ static int dsi_cmd_dma_tx(struct msm_dsi_host *msm_host, int len)
 	dsi_wait4video_eng_busy(msm_host);
 
 	triggered = msm_dsi_manager_cmd_xfer_trigger(
-						msm_host->id, iova, len);
+						msm_host->id, dma_base, len);
 	if (triggered) {
 		ret = wait_for_completion_timeout(&msm_host->dma_comp,
 					msecs_to_jiffies(200));
@@ -1060,7 +1250,7 @@ static int dsi_cmds2buf_tx(struct msm_dsi_host *msm_host,
 	int bllp_len = msm_host->mode->hdisplay *
 			dsi_get_bpp(msm_host->format) / 8;
 
-	len = dsi_cmd_dma_add(msm_host->tx_gem_obj, msg);
+	len = dsi_cmd_dma_add(msm_host, msg);
 	if (!len) {
 		pr_err("%s: failed to add cmd type = 0x%x\n",
 			__func__,  msg->type);
@@ -1383,6 +1573,16 @@ static int dsi_host_parse_dt(struct msm_dsi_host *msm_host)
 
 	msm_host->device_node = device_node;
 
+	if (of_property_read_bool(np, "syscon-sfpb")) {
+		msm_host->sfpb = syscon_regmap_lookup_by_phandle(np,
+					"syscon-sfpb");
+		if (IS_ERR(msm_host->sfpb)) {
+			dev_err(dev, "%s: failed to get sfpb regmap\n",
+				__func__);
+			return PTR_ERR(msm_host->sfpb);
+		}
+	}
+
 	return 0;
 }
 
@@ -1408,12 +1608,6 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi)
 		goto fail;
 	}
 
-	ret = dsi_clk_init(msm_host);
-	if (ret) {
-		pr_err("%s: unable to initialize dsi clks\n", __func__);
-		goto fail;
-	}
-
 	msm_host->ctrl_base = msm_ioremap(pdev, "dsi_ctrl", "DSI CTRL");
 	if (IS_ERR(msm_host->ctrl_base)) {
 		pr_err("%s: unable to map Dsi ctrl base\n", __func__);
@@ -1437,6 +1631,12 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi)
 		goto fail;
 	}
 
+	ret = dsi_clk_init(msm_host);
+	if (ret) {
+		pr_err("%s: unable to initialize dsi clks\n", __func__);
+		goto fail;
+	}
+
 	msm_host->rx_buf = devm_kzalloc(&pdev->dev, SZ_4K, GFP_KERNEL);
 	if (!msm_host->rx_buf) {
 		pr_err("%s: alloc rx temp buf failed\n", __func__);
@@ -1750,11 +1950,12 @@ int msm_dsi_host_cmd_rx(struct mipi_dsi_host *host,
 	return ret;
 }
 
-void msm_dsi_host_cmd_xfer_commit(struct mipi_dsi_host *host, u32 iova, u32 len)
+void msm_dsi_host_cmd_xfer_commit(struct mipi_dsi_host *host, u32 dma_base,
+				  u32 len)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
 
-	dsi_write(msm_host, REG_DSI_DMA_BASE, iova);
+	dsi_write(msm_host, REG_DSI_DMA_BASE, dma_base);
 	dsi_write(msm_host, REG_DSI_DMA_LEN, len);
 	dsi_write(msm_host, REG_DSI_TRIG_DMA, 1);
 
@@ -1766,6 +1967,7 @@ int msm_dsi_host_set_src_pll(struct mipi_dsi_host *host,
 	struct msm_dsi_pll *src_pll)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	struct clk *byte_clk_provider, *pixel_clk_provider;
 	int ret;
 
@@ -1791,6 +1993,22 @@ int msm_dsi_host_set_src_pll(struct mipi_dsi_host *host,
 		goto exit;
 	}
 
+	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_V2) {
+		ret = clk_set_parent(msm_host->dsi_clk_src, pixel_clk_provider);
+		if (ret) {
+			pr_err("%s: can't set parent to dsi_clk_src. ret=%d\n",
+				__func__, ret);
+			goto exit;
+		}
+
+		ret = clk_set_parent(msm_host->esc_clk_src, byte_clk_provider);
+		if (ret) {
+			pr_err("%s: can't set parent to esc_clk_src. ret=%d\n",
+				__func__, ret);
+			goto exit;
+		}
+	}
+
 exit:
 	return ret;
 }
@@ -1828,6 +2046,20 @@ int msm_dsi_host_disable(struct mipi_dsi_host *host)
 	return 0;
 }
 
+static void msm_dsi_sfpb_config(struct msm_dsi_host *msm_host, bool enable)
+{
+	enum sfpb_ahb_arb_master_port_en en;
+
+	if (!msm_host->sfpb)
+		return;
+
+	en = enable ? SFPB_MASTER_PORT_ENABLE : SFPB_MASTER_PORT_DISABLE;
+
+	regmap_update_bits(msm_host->sfpb, REG_SFPB_GPREG,
+			SFPB_GPREG_MASTER_PORT_EN__MASK,
+			SFPB_GPREG_MASTER_PORT_EN(en));
+}
+
 int msm_dsi_host_power_on(struct mipi_dsi_host *host)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
@@ -1840,6 +2072,8 @@ int msm_dsi_host_power_on(struct mipi_dsi_host *host)
 		goto unlock_ret;
 	}
 
+	msm_dsi_sfpb_config(msm_host, true);
+
 	ret = dsi_calc_clk_rate(msm_host);
 	if (ret) {
 		pr_err("%s: unable to calc clk rate, %d\n", __func__, ret);
@@ -1862,7 +2096,7 @@ int msm_dsi_host_power_on(struct mipi_dsi_host *host)
 	dsi_phy_sw_reset(msm_host);
 	ret = msm_dsi_manager_phy_enable(msm_host->id,
 					msm_host->byte_clk_rate * 8,
-					clk_get_rate(msm_host->esc_clk),
+					msm_host->esc_clk_rate,
 					&clk_pre, &clk_post);
 	dsi_bus_clk_disable(msm_host);
 	if (ret) {
@@ -1927,6 +2161,8 @@ int msm_dsi_host_power_off(struct mipi_dsi_host *host)
 
 	dsi_host_regulator_disable(msm_host);
 
+	msm_dsi_sfpb_config(msm_host, false);
+
 	DBG("-");
 
 	msm_host->power_on = false;
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index 0455ff75074a..58ba7ec17f51 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -774,7 +774,7 @@ restore_host0:
 	return ret;
 }
 
-bool msm_dsi_manager_cmd_xfer_trigger(int id, u32 iova, u32 len)
+bool msm_dsi_manager_cmd_xfer_trigger(int id, u32 dma_base, u32 len)
 {
 	struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
 	struct msm_dsi *msm_dsi0 = dsi_mgr_get_dsi(DSI_0);
@@ -784,9 +784,9 @@ bool msm_dsi_manager_cmd_xfer_trigger(int id, u32 iova, u32 len)
 		return false;
 
 	if (IS_SYNC_NEEDED() && msm_dsi0)
-		msm_dsi_host_cmd_xfer_commit(msm_dsi0->host, iova, len);
+		msm_dsi_host_cmd_xfer_commit(msm_dsi0->host, dma_base, len);
 
-	msm_dsi_host_cmd_xfer_commit(host, iova, len);
+	msm_dsi_host_cmd_xfer_commit(host, dma_base, len);
 
 	return true;
 }
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
index f1f955f571fa..91a95fb04a4a 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
@@ -277,6 +277,10 @@ static const struct of_device_id dsi_phy_dt_match[] = {
 	{ .compatible = "qcom,dsi-phy-20nm",
 	  .data = &dsi_phy_20nm_cfgs },
 #endif
+#ifdef CONFIG_DRM_MSM_DSI_28NM_8960_PHY
+	{ .compatible = "qcom,dsi-phy-28nm-8960",
+	  .data = &dsi_phy_28nm_8960_cfgs },
+#endif
 	{}
 };
 
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
index 0456b253239f..0d54ed00386d 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
@@ -43,6 +43,7 @@ struct msm_dsi_phy_cfg {
 extern const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_cfgs;
 extern const struct msm_dsi_phy_cfg dsi_phy_28nm_lp_cfgs;
 extern const struct msm_dsi_phy_cfg dsi_phy_20nm_cfgs;
+extern const struct msm_dsi_phy_cfg dsi_phy_28nm_8960_cfgs;
 
 struct msm_dsi_dphy_timing {
 	u32 clk_pre;
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c
new file mode 100644
index 000000000000..197b039ca1f1
--- /dev/null
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c
@@ -0,0 +1,195 @@
+/*
+ * Copyright (c) 2012-2015, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dsi_phy.h"
+#include "dsi.xml.h"
+
+static void dsi_28nm_dphy_set_timing(struct msm_dsi_phy *phy,
+		struct msm_dsi_dphy_timing *timing)
+{
+	void __iomem *base = phy->base;
+
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_0,
+		DSI_28nm_8960_PHY_TIMING_CTRL_0_CLK_ZERO(timing->clk_zero));
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_1,
+		DSI_28nm_8960_PHY_TIMING_CTRL_1_CLK_TRAIL(timing->clk_trail));
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_2,
+		DSI_28nm_8960_PHY_TIMING_CTRL_2_CLK_PREPARE(timing->clk_prepare));
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_3, 0x0);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_4,
+		DSI_28nm_8960_PHY_TIMING_CTRL_4_HS_EXIT(timing->hs_exit));
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_5,
+		DSI_28nm_8960_PHY_TIMING_CTRL_5_HS_ZERO(timing->hs_zero));
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_6,
+		DSI_28nm_8960_PHY_TIMING_CTRL_6_HS_PREPARE(timing->hs_prepare));
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_7,
+		DSI_28nm_8960_PHY_TIMING_CTRL_7_HS_TRAIL(timing->hs_trail));
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_8,
+		DSI_28nm_8960_PHY_TIMING_CTRL_8_HS_RQST(timing->hs_rqst));
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_9,
+		DSI_28nm_8960_PHY_TIMING_CTRL_9_TA_GO(timing->ta_go) |
+		DSI_28nm_8960_PHY_TIMING_CTRL_9_TA_SURE(timing->ta_sure));
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_10,
+		DSI_28nm_8960_PHY_TIMING_CTRL_10_TA_GET(timing->ta_get));
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_11,
+		DSI_28nm_8960_PHY_TIMING_CTRL_11_TRIG3_CMD(0));
+}
+
+static void dsi_28nm_phy_regulator_init(struct msm_dsi_phy *phy)
+{
+	void __iomem *base = phy->reg_base;
+
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_REGULATOR_CTRL_0, 0x3);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_REGULATOR_CTRL_1, 1);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_REGULATOR_CTRL_2, 1);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_REGULATOR_CTRL_3, 0);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_REGULATOR_CTRL_4,
+		0x100);
+}
+
+static void dsi_28nm_phy_regulator_ctrl(struct msm_dsi_phy *phy)
+{
+	void __iomem *base = phy->reg_base;
+
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_REGULATOR_CTRL_0, 0x3);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_REGULATOR_CTRL_1, 0xa);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_REGULATOR_CTRL_2, 0x4);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_REGULATOR_CTRL_3, 0x0);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_REGULATOR_CTRL_4, 0x20);
+}
+
+static void dsi_28nm_phy_calibration(struct msm_dsi_phy *phy)
+{
+	void __iomem *base = phy->reg_base;
+	u32 status;
+	int i = 5000;
+
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_REGULATOR_CAL_PWR_CFG,
+			0x3);
+
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_CAL_SW_CFG_2, 0x0);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_CAL_HW_CFG_1, 0x5a);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_CAL_HW_CFG_3, 0x10);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_CAL_HW_CFG_4, 0x1);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_CAL_HW_CFG_0, 0x1);
+
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_CAL_HW_TRIGGER, 0x1);
+	usleep_range(5000, 6000);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_CAL_HW_TRIGGER, 0x0);
+
+	do {
+		status = dsi_phy_read(base +
+				REG_DSI_28nm_8960_PHY_MISC_CAL_STATUS);
+
+		if (!(status & DSI_28nm_8960_PHY_MISC_CAL_STATUS_CAL_BUSY))
+			break;
+
+		udelay(1);
+	} while (--i > 0);
+}
+
+static void dsi_28nm_phy_lane_config(struct msm_dsi_phy *phy)
+{
+	void __iomem *base = phy->base;
+	int i;
+
+	for (i = 0; i < 4; i++) {
+		dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LN_CFG_0(i), 0x80);
+		dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LN_CFG_1(i), 0x45);
+		dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LN_CFG_2(i), 0x00);
+		dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LN_TEST_DATAPATH(i),
+			0x00);
+		dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LN_TEST_STR_0(i),
+			0x01);
+		dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LN_TEST_STR_1(i),
+			0x66);
+	}
+
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LNCK_CFG_0, 0x40);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LNCK_CFG_1, 0x67);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LNCK_CFG_2, 0x0);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LNCK_TEST_DATAPATH, 0x0);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LNCK_TEST_STR0, 0x1);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LNCK_TEST_STR1, 0x88);
+}
+
+static int dsi_28nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id,
+		const unsigned long bit_rate, const unsigned long esc_rate)
+{
+	struct msm_dsi_dphy_timing *timing = &phy->timing;
+	void __iomem *base = phy->base;
+
+	DBG("");
+
+	if (msm_dsi_dphy_timing_calc(timing, bit_rate, esc_rate)) {
+		dev_err(&phy->pdev->dev,
+			"%s: D-PHY timing calculation failed\n", __func__);
+		return -EINVAL;
+	}
+
+	dsi_28nm_phy_regulator_init(phy);
+
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LDO_CTRL, 0x04);
+
+	/* strength control */
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_STRENGTH_0, 0xff);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_STRENGTH_1, 0x00);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_STRENGTH_2, 0x06);
+
+	/* phy ctrl */
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_CTRL_0, 0x5f);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_CTRL_1, 0x00);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_CTRL_2, 0x00);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_CTRL_3, 0x10);
+
+	dsi_28nm_phy_regulator_ctrl(phy);
+
+	dsi_28nm_phy_calibration(phy);
+
+	dsi_28nm_phy_lane_config(phy);
+
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_BIST_CTRL_4, 0x0f);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_BIST_CTRL_1, 0x03);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_BIST_CTRL_0, 0x03);
+	dsi_phy_write(base + REG_DSI_28nm_8960_PHY_BIST_CTRL_4, 0x0);
+
+	dsi_28nm_dphy_set_timing(phy, timing);
+
+	return 0;
+}
+
+static void dsi_28nm_phy_disable(struct msm_dsi_phy *phy)
+{
+	dsi_phy_write(phy->base + REG_DSI_28nm_8960_PHY_CTRL_0, 0x0);
+
+	/*
+	 * Wait for the registers writes to complete in order to
+	 * ensure that the phy is completely disabled
+	 */
+	wmb();
+}
+
+const struct msm_dsi_phy_cfg dsi_phy_28nm_8960_cfgs = {
+	.type = MSM_DSI_PHY_28NM_8960,
+	.src_pll_truthtable = { {true, true}, {false, true} },
+	.reg_cfg = {
+		.num = 1,
+		.regs = {
+			{"vddio", 1800000, 1800000, 100000, 100},
+		},
+	},
+	.ops = {
+		.enable = dsi_28nm_phy_enable,
+		.disable = dsi_28nm_phy_disable,
+	},
+};
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c
index 5104fc9f9a53..5cd438f91afe 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c
@@ -151,6 +151,9 @@ struct msm_dsi_pll *msm_dsi_pll_init(struct platform_device *pdev,
 	case MSM_DSI_PHY_28NM_LP:
 		pll = msm_dsi_pll_28nm_init(pdev, type, id);
 		break;
+	case MSM_DSI_PHY_28NM_8960:
+		pll = msm_dsi_pll_28nm_8960_init(pdev, id);
+		break;
 	default:
 		pll = ERR_PTR(-ENXIO);
 		break;
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h
index 063caa2c5740..80b6038334a6 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h
@@ -93,6 +93,16 @@ static inline struct msm_dsi_pll *msm_dsi_pll_28nm_init(
 	return ERR_PTR(-ENODEV);
 }
 #endif
+#ifdef CONFIG_DRM_MSM_DSI_28NM_8960_PHY
+struct msm_dsi_pll *msm_dsi_pll_28nm_8960_init(struct platform_device *pdev,
+					       int id);
+#else
+struct msm_dsi_pll *msm_dsi_pll_28nm_8960_init(struct platform_device *pdev,
+					       int id)
+{
+	return ERR_PTR(-ENODEV);
+}
+#endif
 
 #endif /* __DSI_PLL_H__ */
 
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm_8960.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm_8960.c
new file mode 100644
index 000000000000..38c90e1eb002
--- /dev/null
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm_8960.c
@@ -0,0 +1,533 @@
+/*
+ * Copyright (c) 2012-2015, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+
+#include "dsi_pll.h"
+#include "dsi.xml.h"
+
+/*
+ * DSI PLL 28nm (8960/A family) - clock diagram (eg: DSI1):
+ *
+ *
+ *                        +------+
+ *  dsi1vco_clk ----o-----| DIV1 |---dsi1pllbit (not exposed as clock)
+ *  F * byte_clk    |     +------+
+ *                  | bit clock divider (F / 8)
+ *                  |
+ *                  |     +------+
+ *                  o-----| DIV2 |---dsi0pllbyte---o---> To byte RCG
+ *                  |     +------+                 | (sets parent rate)
+ *                  | byte clock divider (F)       |
+ *                  |                              |
+ *                  |                              o---> To esc RCG
+ *                  |                                (doesn't set parent rate)
+ *                  |
+ *                  |     +------+
+ *                  o-----| DIV3 |----dsi0pll------o---> To dsi RCG
+ *                        +------+                 | (sets parent rate)
+ *                  dsi clock divider (F * magic)  |
+ *                                                 |
+ *                                                 o---> To pixel rcg
+ *                                                  (doesn't set parent rate)
+ */
+
+#define POLL_MAX_READS		8000
+#define POLL_TIMEOUT_US		1
+
+#define NUM_PROVIDED_CLKS	2
+
+#define VCO_REF_CLK_RATE	27000000
+#define VCO_MIN_RATE		600000000
+#define VCO_MAX_RATE		1200000000
+
+#define DSI_BYTE_PLL_CLK	0
+#define DSI_PIXEL_PLL_CLK	1
+
+#define VCO_PREF_DIV_RATIO	27
+
+struct pll_28nm_cached_state {
+	unsigned long vco_rate;
+	u8 postdiv3;
+	u8 postdiv2;
+	u8 postdiv1;
+};
+
+struct clk_bytediv {
+	struct clk_hw hw;
+	void __iomem *reg;
+};
+
+struct dsi_pll_28nm {
+	struct msm_dsi_pll base;
+
+	int id;
+	struct platform_device *pdev;
+	void __iomem *mmio;
+
+	/* custom byte clock divider */
+	struct clk_bytediv *bytediv;
+
+	/* private clocks: */
+	struct clk *clks[NUM_DSI_CLOCKS_MAX];
+	u32 num_clks;
+
+	/* clock-provider: */
+	struct clk *provided_clks[NUM_PROVIDED_CLKS];
+	struct clk_onecell_data clk_data;
+
+	struct pll_28nm_cached_state cached_state;
+};
+
+#define to_pll_28nm(x)	container_of(x, struct dsi_pll_28nm, base)
+
+static bool pll_28nm_poll_for_ready(struct dsi_pll_28nm *pll_28nm,
+				    int nb_tries, int timeout_us)
+{
+	bool pll_locked = false;
+	u32 val;
+
+	while (nb_tries--) {
+		val = pll_read(pll_28nm->mmio + REG_DSI_28nm_8960_PHY_PLL_RDY);
+		pll_locked = !!(val & DSI_28nm_8960_PHY_PLL_RDY_PLL_RDY);
+
+		if (pll_locked)
+			break;
+
+		udelay(timeout_us);
+	}
+	DBG("DSI PLL is %slocked", pll_locked ? "" : "*not* ");
+
+	return pll_locked;
+}
+
+/*
+ * Clock Callbacks
+ */
+static int dsi_pll_28nm_clk_set_rate(struct clk_hw *hw, unsigned long rate,
+				     unsigned long parent_rate)
+{
+	struct msm_dsi_pll *pll = hw_clk_to_pll(hw);
+	struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll);
+	void __iomem *base = pll_28nm->mmio;
+	u32 val, temp, fb_divider;
+
+	DBG("rate=%lu, parent's=%lu", rate, parent_rate);
+
+	temp = rate / 10;
+	val = VCO_REF_CLK_RATE / 10;
+	fb_divider = (temp * VCO_PREF_DIV_RATIO) / val;
+	fb_divider = fb_divider / 2 - 1;
+	pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_1,
+			fb_divider & 0xff);
+
+	val = pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_2);
+
+	val |= (fb_divider >> 8) & 0x07;
+
+	pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_2,
+			val);
+
+	val = pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_3);
+
+	val |= (VCO_PREF_DIV_RATIO - 1) & 0x3f;
+
+	pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_3,
+			val);
+
+	pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_6,
+			0xf);
+
+	val = pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8);
+	val |= 0x7 << 4;
+	pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8,
+			val);
+
+	return 0;
+}
+
+static int dsi_pll_28nm_clk_is_enabled(struct clk_hw *hw)
+{
+	struct msm_dsi_pll *pll = hw_clk_to_pll(hw);
+	struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll);
+
+	return pll_28nm_poll_for_ready(pll_28nm, POLL_MAX_READS,
+					POLL_TIMEOUT_US);
+}
+
+static unsigned long dsi_pll_28nm_clk_recalc_rate(struct clk_hw *hw,
+						  unsigned long parent_rate)
+{
+	struct msm_dsi_pll *pll = hw_clk_to_pll(hw);
+	struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll);
+	void __iomem *base = pll_28nm->mmio;
+	unsigned long vco_rate;
+	u32 status, fb_divider, temp, ref_divider;
+
+	VERB("parent_rate=%lu", parent_rate);
+
+	status = pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_0);
+
+	if (status & DSI_28nm_8960_PHY_PLL_CTRL_0_ENABLE) {
+		fb_divider = pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_1);
+		fb_divider &= 0xff;
+		temp = pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_2) & 0x07;
+		fb_divider = (temp << 8) | fb_divider;
+		fb_divider += 1;
+
+		ref_divider = pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_3);
+		ref_divider &= 0x3f;
+		ref_divider += 1;
+
+		/* multiply by 2 */
+		vco_rate = (parent_rate / ref_divider) * fb_divider * 2;
+	} else {
+		vco_rate = 0;
+	}
+
+	DBG("returning vco rate = %lu", vco_rate);
+
+	return vco_rate;
+}
+
+static const struct clk_ops clk_ops_dsi_pll_28nm_vco = {
+	.round_rate = msm_dsi_pll_helper_clk_round_rate,
+	.set_rate = dsi_pll_28nm_clk_set_rate,
+	.recalc_rate = dsi_pll_28nm_clk_recalc_rate,
+	.prepare = msm_dsi_pll_helper_clk_prepare,
+	.unprepare = msm_dsi_pll_helper_clk_unprepare,
+	.is_enabled = dsi_pll_28nm_clk_is_enabled,
+};
+
+/*
+ * Custom byte clock divier clk_ops
+ *
+ * This clock is the entry point to configuring the PLL. The user (dsi host)
+ * will set this clock's rate to the desired byte clock rate. The VCO lock
+ * frequency is a multiple of the byte clock rate. The multiplication factor
+ * (shown as F in the diagram above) is a function of the byte clock rate.
+ *
+ * This custom divider clock ensures that its parent (VCO) is set to the
+ * desired rate, and that the byte clock postdivider (POSTDIV2) is configured
+ * accordingly
+ */
+#define to_clk_bytediv(_hw) container_of(_hw, struct clk_bytediv, hw)
+
+static unsigned long clk_bytediv_recalc_rate(struct clk_hw *hw,
+		unsigned long parent_rate)
+{
+	struct clk_bytediv *bytediv = to_clk_bytediv(hw);
+	unsigned int div;
+
+	div = pll_read(bytediv->reg) & 0xff;
+
+	return parent_rate / (div + 1);
+}
+
+/* find multiplication factor(wrt byte clock) at which the VCO should be set */
+static unsigned int get_vco_mul_factor(unsigned long byte_clk_rate)
+{
+	unsigned long bit_mhz;
+
+	/* convert to bit clock in Mhz */
+	bit_mhz = (byte_clk_rate * 8) / 1000000;
+
+	if (bit_mhz < 125)
+		return 64;
+	else if (bit_mhz < 250)
+		return 32;
+	else if (bit_mhz < 600)
+		return 16;
+	else
+		return 8;
+}
+
+static long clk_bytediv_round_rate(struct clk_hw *hw, unsigned long rate,
+				   unsigned long *prate)
+{
+	unsigned long best_parent;
+	unsigned int factor;
+
+	factor = get_vco_mul_factor(rate);
+
+	best_parent = rate * factor;
+	*prate = clk_hw_round_rate(clk_hw_get_parent(hw), best_parent);
+
+	return *prate / factor;
+}
+
+static int clk_bytediv_set_rate(struct clk_hw *hw, unsigned long rate,
+				unsigned long parent_rate)
+{
+	struct clk_bytediv *bytediv = to_clk_bytediv(hw);
+	u32 val;
+	unsigned int factor;
+
+	factor = get_vco_mul_factor(rate);
+
+	val = pll_read(bytediv->reg);
+	val |= (factor - 1) & 0xff;
+	pll_write(bytediv->reg, val);
+
+	return 0;
+}
+
+/* Our special byte clock divider ops */
+static const struct clk_ops clk_bytediv_ops = {
+	.round_rate = clk_bytediv_round_rate,
+	.set_rate = clk_bytediv_set_rate,
+	.recalc_rate = clk_bytediv_recalc_rate,
+};
+
+/*
+ * PLL Callbacks
+ */
+static int dsi_pll_28nm_enable_seq(struct msm_dsi_pll *pll)
+{
+	struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll);
+	struct device *dev = &pll_28nm->pdev->dev;
+	void __iomem *base = pll_28nm->mmio;
+	bool locked;
+	unsigned int bit_div, byte_div;
+	int max_reads = 1000, timeout_us = 100;
+	u32 val;
+
+	DBG("id=%d", pll_28nm->id);
+
+	/*
+	 * before enabling the PLL, configure the bit clock divider since we
+	 * don't expose it as a clock to the outside world
+	 * 1: read back the byte clock divider that should already be set
+	 * 2: divide by 8 to get bit clock divider
+	 * 3: write it to POSTDIV1
+	 */
+	val = pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_9);
+	byte_div = val + 1;
+	bit_div = byte_div / 8;
+
+	val = pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8);
+	val &= ~0xf;
+	val |= (bit_div - 1);
+	pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8, val);
+
+	/* enable the PLL */
+	pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_0,
+			DSI_28nm_8960_PHY_PLL_CTRL_0_ENABLE);
+
+	locked = pll_28nm_poll_for_ready(pll_28nm, max_reads, timeout_us);
+
+	if (unlikely(!locked))
+		dev_err(dev, "DSI PLL lock failed\n");
+	else
+		DBG("DSI PLL lock success");
+
+	return locked ? 0 : -EINVAL;
+}
+
+static void dsi_pll_28nm_disable_seq(struct msm_dsi_pll *pll)
+{
+	struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll);
+
+	DBG("id=%d", pll_28nm->id);
+	pll_write(pll_28nm->mmio + REG_DSI_28nm_8960_PHY_PLL_CTRL_0, 0x00);
+}
+
+static void dsi_pll_28nm_save_state(struct msm_dsi_pll *pll)
+{
+	struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll);
+	struct pll_28nm_cached_state *cached_state = &pll_28nm->cached_state;
+	void __iomem *base = pll_28nm->mmio;
+
+	cached_state->postdiv3 =
+			pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_10);
+	cached_state->postdiv2 =
+			pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_9);
+	cached_state->postdiv1 =
+			pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8);
+
+	cached_state->vco_rate = clk_hw_get_rate(&pll->clk_hw);
+}
+
+static int dsi_pll_28nm_restore_state(struct msm_dsi_pll *pll)
+{
+	struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll);
+	struct pll_28nm_cached_state *cached_state = &pll_28nm->cached_state;
+	void __iomem *base = pll_28nm->mmio;
+	int ret;
+
+	ret = dsi_pll_28nm_clk_set_rate(&pll->clk_hw,
+					cached_state->vco_rate, 0);
+	if (ret) {
+		dev_err(&pll_28nm->pdev->dev,
+			"restore vco rate failed. ret=%d\n", ret);
+		return ret;
+	}
+
+	pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_10,
+			cached_state->postdiv3);
+	pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_9,
+			cached_state->postdiv2);
+	pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8,
+			cached_state->postdiv1);
+
+	return 0;
+}
+
+static int dsi_pll_28nm_get_provider(struct msm_dsi_pll *pll,
+				struct clk **byte_clk_provider,
+				struct clk **pixel_clk_provider)
+{
+	struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll);
+
+	if (byte_clk_provider)
+		*byte_clk_provider = pll_28nm->provided_clks[DSI_BYTE_PLL_CLK];
+	if (pixel_clk_provider)
+		*pixel_clk_provider =
+				pll_28nm->provided_clks[DSI_PIXEL_PLL_CLK];
+
+	return 0;
+}
+
+static void dsi_pll_28nm_destroy(struct msm_dsi_pll *pll)
+{
+	struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll);
+
+	msm_dsi_pll_helper_unregister_clks(pll_28nm->pdev,
+					pll_28nm->clks, pll_28nm->num_clks);
+}
+
+static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm)
+{
+	char *clk_name, *parent_name, *vco_name;
+	struct clk_init_data vco_init = {
+		.parent_names = (const char *[]){ "pxo" },
+		.num_parents = 1,
+		.ops = &clk_ops_dsi_pll_28nm_vco,
+	};
+	struct device *dev = &pll_28nm->pdev->dev;
+	struct clk **clks = pll_28nm->clks;
+	struct clk **provided_clks = pll_28nm->provided_clks;
+	struct clk_bytediv *bytediv;
+	struct clk_init_data bytediv_init = { };
+	int ret, num = 0;
+
+	DBG("%d", pll_28nm->id);
+
+	bytediv = devm_kzalloc(dev, sizeof(*bytediv), GFP_KERNEL);
+	if (!bytediv)
+		return -ENOMEM;
+
+	vco_name = devm_kzalloc(dev, 32, GFP_KERNEL);
+	if (!vco_name)
+		return -ENOMEM;
+
+	parent_name = devm_kzalloc(dev, 32, GFP_KERNEL);
+	if (!parent_name)
+		return -ENOMEM;
+
+	clk_name = devm_kzalloc(dev, 32, GFP_KERNEL);
+	if (!clk_name)
+		return -ENOMEM;
+
+	pll_28nm->bytediv = bytediv;
+
+	snprintf(vco_name, 32, "dsi%dvco_clk", pll_28nm->id);
+	vco_init.name = vco_name;
+
+	pll_28nm->base.clk_hw.init = &vco_init;
+
+	clks[num++] = clk_register(dev, &pll_28nm->base.clk_hw);
+
+	/* prepare and register bytediv */
+	bytediv->hw.init = &bytediv_init;
+	bytediv->reg = pll_28nm->mmio + REG_DSI_28nm_8960_PHY_PLL_CTRL_9;
+
+	snprintf(parent_name, 32, "dsi%dvco_clk", pll_28nm->id);
+	snprintf(clk_name, 32, "dsi%dpllbyte", pll_28nm->id);
+
+	bytediv_init.name = clk_name;
+	bytediv_init.ops = &clk_bytediv_ops;
+	bytediv_init.flags = CLK_SET_RATE_PARENT;
+	bytediv_init.parent_names = (const char * const *) &parent_name;
+	bytediv_init.num_parents = 1;
+
+	/* DIV2 */
+	clks[num++] = provided_clks[DSI_BYTE_PLL_CLK] =
+			clk_register(dev, &bytediv->hw);
+
+	snprintf(clk_name, 32, "dsi%dpll", pll_28nm->id);
+	/* DIV3 */
+	clks[num++] = provided_clks[DSI_PIXEL_PLL_CLK] =
+			clk_register_divider(dev, clk_name,
+				parent_name, 0, pll_28nm->mmio +
+				REG_DSI_28nm_8960_PHY_PLL_CTRL_10,
+				0, 8, 0, NULL);
+
+	pll_28nm->num_clks = num;
+
+	pll_28nm->clk_data.clk_num = NUM_PROVIDED_CLKS;
+	pll_28nm->clk_data.clks = provided_clks;
+
+	ret = of_clk_add_provider(dev->of_node,
+			of_clk_src_onecell_get, &pll_28nm->clk_data);
+	if (ret) {
+		dev_err(dev, "failed to register clk provider: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+struct msm_dsi_pll *msm_dsi_pll_28nm_8960_init(struct platform_device *pdev,
+					       int id)
+{
+	struct dsi_pll_28nm *pll_28nm;
+	struct msm_dsi_pll *pll;
+	int ret;
+
+	if (!pdev)
+		return ERR_PTR(-ENODEV);
+
+	pll_28nm = devm_kzalloc(&pdev->dev, sizeof(*pll_28nm), GFP_KERNEL);
+	if (!pll_28nm)
+		return ERR_PTR(-ENOMEM);
+
+	pll_28nm->pdev = pdev;
+	pll_28nm->id = id + 1;
+
+	pll_28nm->mmio = msm_ioremap(pdev, "dsi_pll", "DSI_PLL");
+	if (IS_ERR_OR_NULL(pll_28nm->mmio)) {
+		dev_err(&pdev->dev, "%s: failed to map pll base\n", __func__);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	pll = &pll_28nm->base;
+	pll->min_rate = VCO_MIN_RATE;
+	pll->max_rate = VCO_MAX_RATE;
+	pll->get_provider = dsi_pll_28nm_get_provider;
+	pll->destroy = dsi_pll_28nm_destroy;
+	pll->disable_seq = dsi_pll_28nm_disable_seq;
+	pll->save_state = dsi_pll_28nm_save_state;
+	pll->restore_state = dsi_pll_28nm_restore_state;
+
+	pll->en_seq_cnt = 1;
+	pll->enable_seqs[0] = dsi_pll_28nm_enable_seq;
+
+	ret = pll_28nm_register(pll_28nm);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to register PLL: %d\n", ret);
+		return ERR_PTR(ret);
+	}
+
+	return pll;
+}