On 10/14, Archit Taneja wrote:

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 0000000..e71b4ee --- /dev/null +++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm_8960.c @@ -0,0 +1,529 @@ +/*

• • 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.h>

Is this include used?

+#include <linux/clk-provider.h>

+#include "dsi_pll.h" +#include "dsi.xml.h"

+/*

[..]

+#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,

• 		    u32 nb_tries, u32 timeout_us)
  

Why not use unsigned types for these counts? I don't imagine we care about being precisely 32 bits.

+{

• bool pll_locked = false;
• 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 aready be set
  

s/aready/already/

• * 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);

[..]

+static void dsi_pll_28nm_destroy(struct msm_dsi_pll *pll) +{

• struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll);
• int i;
• msm_dsi_pll_helper_unregister_clks(pll_28nm->pdev,

• 			pll_28nm->clks, pll_28nm->num_clks);
  

• for (i = 0; i < NUM_PROVIDED_CLKS; i++)

• pll_28nm->provided_clks[i] = NULL;
  

• pll_28nm->num_clks = 0;
• pll_28nm->clk_data.clks = NULL;
• pll_28nm->clk_data.clk_num = 0;

Is all this really necessary?

+}

+static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm) +{

• char clk_name[32], parent[32], vco_name[32];
• struct clk_init_data vco_init = {

• .parent_names = (const char *[]){ "pxo" },
  

• .num_parents = 1,
  

• .name = vco_name,
  

• .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;

struct clk_init_data bytediv_init = { };

Just in case we add some new field there?

• int ret, num = 0;
• DBG("%d", pll_28nm->id);
• bytediv = devm_kzalloc(dev, sizeof(*bytediv), GFP_KERNEL);
• if (!bytediv)

• return -ENOMEM;
  

• pll_28nm->bytediv = bytediv;
• snprintf(vco_name, 32, "dsi%dvco_clk", pll_28nm->id);
• 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, 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 *[]) { parent };

Can't we just do &parent instead of this anonymous array?

• bytediv_init.num_parents = 1;
• /* DIV2 */

Add DSI PLL common clock framework clocks for 8960 PHY.

The PLL here is different from the ones found in B family msm chips. As before, the DSI provides two clocks to the outside world. dsixpll and dsixpllbyte (x = 1, 2). dsixpll is a regular clock divider, but dsixpllbyte is modelled as a custom clock divider.

dsixpllbyte is the starting point of the PLL configuration. It is the one that sets up the VCO clock rate. We need the VCO clock rate in the form: F * byteclk, where F is a multiplication factor that varies on the byte clock the DSI driver is trying to set. We use the custom clk_ops for dsixpllbyte to ensure that the parent (VCO) is set at this rate.

An additional divider (POSTDIV1) generates the bitclk. Since bit clock can be derived from byteclock, we calculate it internally, and don't expose it as a clock.

Cc: Stephen Boyd sboyd@codeaurora.org Signed-off-by: Archit Taneja architt@codeaurora.org --- drivers/gpu/drm/msm/Makefile | 1 + drivers/gpu/drm/msm/dsi/pll/dsi_pll.c | 3 + drivers/gpu/drm/msm/dsi/pll/dsi_pll.h | 10 + drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm_8960.c | 533 ++++++++++++++++++++++++ 4 files changed, 547 insertions(+) create mode 100644 drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm_8960.c

diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile index 7523eca..156a93d 100644 --- a/drivers/gpu/drm/msm/Makefile +++ b/drivers/gpu/drm/msm/Makefile @@ -67,6 +67,7 @@ msm-$(CONFIG_DRM_MSM_DSI_28NM_8960_PHY) += dsi/phy/dsi_phy_28nm_8960.o ifeq ($(CONFIG_DRM_MSM_DSI_PLL),y) msm-y += dsi/pll/dsi_pll.o msm-$(CONFIG_DRM_MSM_DSI_28NM_PHY) += dsi/pll/dsi_pll_28nm.o +msm-$(CONFIG_DRM_MSM_DSI_28NM_8960_PHY) += dsi/pll/dsi_pll_28nm_8960.o endif

obj-$(CONFIG_DRM_MSM) += msm.o diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c index 5104fc9..5cd438f 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 063caa2..80b6038 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 0000000..38c90e1 --- /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; +}

Initialize clocks only after we get the DSI host version. This will allow us to get clocks using a pre-defined list based on the DSI major/minor version of the host. This is required since clock requirements of different major DSI revisions(v2 vs 6g) aren't the same.

Modify dsi_get_version to get the interface clock, and then put it after it is used.

Signed-off-by: Archit Taneja architt@codeaurora.org --- drivers/gpu/drm/msm/dsi/dsi_host.c | 32 ++++++++++++++++++++++---------- 1 file changed, 22 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 8e8fcc7..cbcf8dd 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -177,21 +177,31 @@ 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; @@ -208,9 +218,11 @@ 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: @@ -1420,12 +1432,6 @@ 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__); @@ -1449,6 +1455,12 @@ 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__);

DSIv2 (DSI on older A family chips) has slightly different link clock requirements.

First, we have an extra clock called src_clk (with a dedicated RCG). This is required by the DSI controller to process the pixel data coming from MDP. It needs to be set at the rate "pclk * bytes_per_pixel".

We also need to explicitly configure esc_clk. On DSI6G chips, we don't need to set a rate to esc_clk because its RCG is always sourced from crystal clock (19.2 Mhz in all cases), which is within the escape clock frequency range in the mipi DSI spec. For chips with DSIv2, the crystal clock rate may not be within the required range (27Mhz on APQ8064). Therefore, we derive it from the DSI byte clock. We calculate an esc_clck rate that is within the mipi spec and also divisible by the byte clock rate.

When setting rate and enabling the link clocks, we make sure that byte_clk is configured before esc_clk, and src_clk before pixel_clk. We create two different link_enable funcs for DSI6G and DSIv2 since the sequences are different.

We also obtain two extra source clocks (dsi_src_clk and esc_src_clk) and set their parent to the clocks provided by DSI PLL.

Signed-off-by: Archit Taneja architt@codeaurora.org --- drivers/gpu/drm/msm/dsi/dsi_host.c | 193 ++++++++++++++++++++++++++++++++++++- 1 file changed, 188 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 1da9adb2..6665371 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -113,6 +113,14 @@ 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; @@ -318,7 +326,8 @@ 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; - const struct msm_dsi_config *cfg = msm_host->cfg_hnd->cfg; + 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 */ @@ -377,6 +386,34 @@ static int dsi_clk_init(struct msm_dsi_host *msm_host) 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 = devm_clk_get(dev, "esc_clk_src"); + if (IS_ERR(msm_host->esc_clk_src)) { + ret = PTR_ERR(msm_host->esc_clk_src); + pr_err("%s: can't find esc_clk_src. ret=%d\n", + __func__, ret); + msm_host->esc_clk_src = NULL; + goto exit; + } + + msm_host->dsi_clk_src = devm_clk_get(dev, "dsi_clk_src"); + if (IS_ERR(msm_host->dsi_clk_src)) { + ret = PTR_ERR(msm_host->dsi_clk_src); + pr_err("%s: can't find dsi_clk_src. ret=%d\n", + __func__, ret); + msm_host->dsi_clk_src = NULL; + goto exit; + } + } exit: return ret; } @@ -416,7 +453,7 @@ static void dsi_bus_clk_disable(struct msm_dsi_host *msm_host) 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;

@@ -463,11 +500,98 @@ 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) @@ -502,6 +626,7 @@ 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; @@ -521,6 +646,47 @@ 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; }

@@ -1753,6 +1919,7 @@ 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;

@@ -1778,6 +1945,22 @@ 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; } @@ -1849,7 +2032,7 @@ 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) {

We currently use iommu allocated DMA buffers for sending DSI commands. DSIv2 doesn't have a port connected to the MDP iommu. Therefore, it can't use iommu allocated buffers to fetch DSI commands.

Use a regular contiguous DMA buffer if we are DSIv2.

Signed-off-by: Archit Taneja architt@codeaurora.org --- drivers/gpu/drm/msm/dsi/dsi.h | 4 +- drivers/gpu/drm/msm/dsi/dsi_host.c | 110 +++++++++++++++++++++++----------- drivers/gpu/drm/msm/dsi/dsi_manager.c | 6 +- 3 files changed, 79 insertions(+), 41 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h index 7336b55..749fbb2 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.h +++ b/drivers/gpu/drm/msm/dsi/dsi.h @@ -91,7 +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);

@@ -145,7 +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_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 6665371..afc2546 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -138,7 +138,15 @@ 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 drm_display_mode *mode; @@ -988,29 +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); + if (ret) { + pr_err("%s: failed to get iova, %d\n", __func__, ret); + return ret; + } mutex_unlock(&dev->struct_mutex); - 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; @@ -1027,14 +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; @@ -1047,17 +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 */ @@ -1123,17 +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); @@ -1141,7 +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)); @@ -1213,7 +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); @@ -1903,11 +1940,12 @@ 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);

diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c index 0455ff7..58ba7ec 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; }

Add additional property info needed for DSIv2 DT.

Signed-off-by: Archit Taneja architt@codeaurora.org --- Documentation/devicetree/bindings/display/msm/dsi.txt | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/display/msm/dsi.txt b/Documentation/devicetree/bindings/display/msm/dsi.txt index f344b9e..ca65a34 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi.txt +++ b/Documentation/devicetree/bindings/display/msm/dsi.txt @@ -13,18 +13,25 @@ Required properties: - power-domains: Should be <&mmcc MDSS_GDSC>. - clocks: device clocks See Documentation/devicetree/bindings/clocks/clock-bindings.txt for details. -- clock-names: the following clocks are required: +- clock-names: these vary based on the DSI version. For DSI6G: * "bus_clk" * "byte_clk" + * "byte_clk_src * "core_clk" * "core_mmss_clk" * "iface_clk" * "mdp_core_clk" * "pixel_clk" + * "pixel_clk_src" + For DSIv2, we need a few more: + * "dsi_clk_src" + * "esc_clk_src" + * "src_clk" - vdd-supply: phandle to vdd regulator device node - vddio-supply: phandle to vdd-io regulator device node - vdda-supply: phandle to vdda regulator device node - qcom,dsi-phy: phandle to DSI PHY device node +- syscon-sfpb: A phandle to mmss_sfpb syscon node (only for DSIv2)

Optional properties: - panel@0: Node of panel connected to this DSI controller. @@ -51,6 +58,7 @@ Required properties: * "qcom,dsi-phy-28nm-hpm" * "qcom,dsi-phy-28nm-lp" * "qcom,dsi-phy-20nm" + * "qcom,dsi-phy-28nm-8960" - reg: Physical base address and length of the registers of PLL, PHY and PHY regulator - reg-names: The names of register regions. The following regions are required:

Hi Rob,

On 11/18/2015 6:48 PM, Rob Herring wrote:

+dt list

On Wed, Nov 18, 2015 at 4:55 AM, Archit Taneja architt@codeaurora.org wrote:

...

Add additional property info needed for DSIv2 DT.

Please use get_maintainers.pl.

Sorry about that, missed out doing that posting this time.

...

Signed-off-by: Archit Taneja architt@codeaurora.org

Documentation/devicetree/bindings/display/msm/dsi.txt | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/display/msm/dsi.txt b/Documentation/devicetree/bindings/display/msm/dsi.txt index f344b9e..ca65a34 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi.txt +++ b/Documentation/devicetree/bindings/display/msm/dsi.txt @@ -13,18 +13,25 @@ Required properties:

• power-domains: Should be <&mmcc MDSS_GDSC>.
• clocks: device clocks See Documentation/devicetree/bindings/clocks/clock-bindings.txt for details.

-- clock-names: the following clocks are required: +- clock-names: these vary based on the DSI version. For DSI6G: * "bus_clk" * "byte_clk"

• • "byte_clk_src

This sounds like the parent of byte_clk. Is that really a clock within the block?

byte_clk_src isn't in the block, but byte_clk_src's parent is one of the PLLs in this block. We take this clock so that we can re-parent it to an appropriate PLL. The decision of what PLL to choose needs to be done by the DSI block's driver.

...

* "core_clk"
* "core_mmss_clk"
* "iface_clk"
* "mdp_core_clk"
* "pixel_clk"

• • "pixel_clk_src"
• For DSIv2, we need a few more:

What is the overall order of clocks? As listed?

Order in which the driver does clk_get? It uses the clock name to get each one individually, so the order doesn't matter as such.

I don't think it the order of clk_get in the driver is the same as what's been listed here. I can fix it if that's the norm.

Thanks, Archit

...

• • "dsi_clk_src"
• • "esc_clk_src"
• • "src_clk"
  • vdd-supply: phandle to vdd regulator device node
  • vddio-supply: phandle to vdd-io regulator device node
  • vdda-supply: phandle to vdda regulator device node
  • qcom,dsi-phy: phandle to DSI PHY device node

+- syscon-sfpb: A phandle to mmss_sfpb syscon node (only for DSIv2)

Optional properties:

• panel@0: Node of panel connected to this DSI controller.

@@ -51,6 +58,7 @@ Required properties: * "qcom,dsi-phy-28nm-hpm" * "qcom,dsi-phy-28nm-lp" * "qcom,dsi-phy-20nm"

• • "qcom,dsi-phy-28nm-8960"
  • reg: Physical base address and length of the registers of PLL, PHY and PHY
  regulator
  • reg-names: The names of register regions. The following regions are required:

-- The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum, hosted by The Linux Foundation

---

dri-devel mailing list dri-devel@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/dri-devel

On 11/21/2015 1:29 AM, Rob Herring wrote:

+Stephen

On Wed, Nov 18, 2015 at 9:24 AM, Archit Taneja architt@codeaurora.org wrote:

...

Hi Rob,

On 11/18/2015 6:48 PM, Rob Herring wrote:

...

+dt list

On Wed, Nov 18, 2015 at 4:55 AM, Archit Taneja architt@codeaurora.org wrote:

...

Add additional property info needed for DSIv2 DT.

Please use get_maintainers.pl.

Sorry about that, missed out doing that posting this time.

...

...

Signed-off-by: Archit Taneja architt@codeaurora.org

Documentation/devicetree/bindings/display/msm/dsi.txt | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/display/msm/dsi.txt b/Documentation/devicetree/bindings/display/msm/dsi.txt index f344b9e..ca65a34 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi.txt +++ b/Documentation/devicetree/bindings/display/msm/dsi.txt @@ -13,18 +13,25 @@ Required properties:

• power-domains: Should be <&mmcc MDSS_GDSC>.
• clocks: device clocks See Documentation/devicetree/bindings/clocks/clock-bindings.txt for

details. -- clock-names: the following clocks are required: +- clock-names: these vary based on the DSI version. For DSI6G: * "bus_clk" * "byte_clk"

• • "byte_clk_src

This sounds like the parent of byte_clk. Is that really a clock within the block?

byte_clk_src isn't in the block, but byte_clk_src's parent is one of the PLLs in this block. We take this clock so that we can re-parent it to an appropriate PLL. The decision of what PLL to choose needs to be done by the DSI block's driver.

Seems like abuse to me. The list of clocks should match what are inputs to the block, not what the driver happens to need. Without a full understanding of the clock tree here, I don't have a suggestion. Maybe Stephen does.

We don't need specify byte_clk_src (and other xyz_clk_src clocks) via DT. There is a static link set up between byte_clk and byte_clk_src by our clock driver that never changes. We can retrieve it in the driver itself using clk_get_parent(byte_clk). This way we stick to only input clocks.

Stephen, does that sound okay?

...

...

...

 * "core_clk"
 * "core_mmss_clk"
 * "iface_clk"
 * "mdp_core_clk"
 * "pixel_clk"

• • "pixel_clk_src"
• For DSIv2, we need a few more:

What is the overall order of clocks? As listed?

Order in which the driver does clk_get? It uses the clock name to get each one individually, so the order doesn't matter as such.

The order in DT. You may use the names, but the order should still be specified.

Okay. I'll cross check and make sure the order is as in our DT files.

Archit

Rob

To unsubscribe from this list: send the line "unsubscribe linux-arm-msm" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html

On 12/02/2015 01:50 PM, Stephen Boyd wrote:

On 11/23, Archit Taneja wrote:

...

On 11/21/2015 1:29 AM, Rob Herring wrote:

...

+Stephen

On Wed, Nov 18, 2015 at 9:24 AM, Archit Taneja architt@codeaurora.org wrote:

...

Hi Rob,

On 11/18/2015 6:48 PM, Rob Herring wrote:

...

+dt list

On Wed, Nov 18, 2015 at 4:55 AM, Archit Taneja architt@codeaurora.org wrote:

...

Add additional property info needed for DSIv2 DT.

Please use get_maintainers.pl.

Sorry about that, missed out doing that posting this time.

...

...

Signed-off-by: Archit Taneja architt@codeaurora.org

Documentation/devicetree/bindings/display/msm/dsi.txt | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/display/msm/dsi.txt b/Documentation/devicetree/bindings/display/msm/dsi.txt index f344b9e..ca65a34 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi.txt +++ b/Documentation/devicetree/bindings/display/msm/dsi.txt @@ -13,18 +13,25 @@ Required properties:

• power-domains: Should be <&mmcc MDSS_GDSC>.
• clocks: device clocks See Documentation/devicetree/bindings/clocks/clock-bindings.txt for

details. -- clock-names: the following clocks are required: +- clock-names: these vary based on the DSI version. For DSI6G: * "bus_clk" * "byte_clk"

• • "byte_clk_src

This sounds like the parent of byte_clk. Is that really a clock within the block?

byte_clk_src isn't in the block, but byte_clk_src's parent is one of the PLLs in this block. We take this clock so that we can re-parent it to an appropriate PLL. The decision of what PLL to choose needs to be done by the DSI block's driver.

Seems like abuse to me. The list of clocks should match what are inputs to the block, not what the driver happens to need. Without a full understanding of the clock tree here, I don't have a suggestion. Maybe Stephen does.

We don't need specify byte_clk_src (and other xyz_clk_src clocks) via DT. There is a static link set up between byte_clk and byte_clk_src by our clock driver that never changes. We can retrieve it in the driver itself using clk_get_parent(byte_clk). This way we stick to only input clocks.

Stephen, does that sound okay?

I guess so. From the DT perspective it's "correct" so sure.

It would be nice if we could use assigned-clock-parents though. As far as I can recall that's hard because the clock tree looks like a cyclic graph when we take a clock provider level view. The display block consumes the byte_clk and provides the source of it too. So if we used assigned parents we would need to wait for both clocks to be registered with the framework before we can reconfigure the parent of byte_clk_src to be the PLL that the display clock outputs. Unfortunately, of_clk_set_defaults() is called during device driver probe, which in the display driver case would be before the PLL is registered.

My only thought there would be to make of_clk_set_defaults() wait until both clocks are registered before it does any parent setting. But only in the case where the assigned parents contains a clock that is provided by the node being processed. I suppose the simplest thing to do would be to skip it during the device driver probe and handle it when the clk provider is registered.

The assigned-clock-parents stuff you mentioned is needed to set a default link between the one of the DSI PLLs and the RCG, right? I just wanted to make clear if we were still discussing the same issue.

From what I understand, we don't need the assigned-clock-parents stuff to establish a link between byte_clk_src(RCG clock) and byte_clk(branch clock). That's a fixed link set up by the clock structs provided in the gcc driver and doesn't need to be specially assigned, and just a clk_get_parent in the driver does the job there.

About assigning a parent to the RCG, wouldn't that be xo by default, and changed by the drm/msm driver to one of the PLLs when the need arrives? I didn't get why we need to establish that beforehand in DT?

Archit

We retrieve the byte and pixel source clocks (RCG clocks) in the dsi driver via DT. These are needed so that we can re-parent these source clocks if we want to drive it using a different DSI PLL.

We shouldn't get these via DT because they aren't clocks that directly serve as inputs to the dsi host.

Fortunately, there is a static parent-child link between the byte_clk_src/pixel_clk_src and byte_clk/pixel_clk clocks. So, we can retrieve the source clocks via clk_get_parent.

Do this instead of retrieving via DT.

Cc: Rob Herring robh@kernel.org Cc: Stephen Boyd sboyd@codeaurora.org Signed-off-by: Archit Taneja architt@codeaurora.org --- drivers/gpu/drm/msm/dsi/dsi_host.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 4c49868..aec97c8 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -356,20 +356,17 @@ 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; }

exit:

Add DSI PLL common clock framework clocks for 8960 PHY.

The PLL here is different from the ones found in B family msm chips. As before, the DSI provides two clocks to the outside world. dsixpll and dsixpllbyte (x = 1, 2). dsixpll is a regular clock divider, but dsixpllbyte is modelled as a custom clock divider.

dsixpllbyte is the starting point of the PLL configuration. It is the one that sets up the VCO clock rate. We need the VCO clock rate in the form: F * byteclk, where F is a multiplication factor that varies on the byte clock the DSI driver is trying to set. We use the custom clk_ops for dsixpllbyte to ensure that the parent (VCO) is set at this rate.

An additional divider (POSTDIV1) generates the bitclk. Since bit clock can be derived from byteclock, we calculate it internally, and don't expose it as a clock.

Cc: Stephen Boyd sboyd@codeaurora.org Signed-off-by: Archit Taneja architt@codeaurora.org --- drivers/gpu/drm/msm/Makefile | 1 + drivers/gpu/drm/msm/dsi/pll/dsi_pll.c | 3 + drivers/gpu/drm/msm/dsi/pll/dsi_pll.h | 10 + drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm_8960.c | 533 ++++++++++++++++++++++++ 4 files changed, 547 insertions(+) create mode 100644 drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm_8960.c

diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile index 1888fd3..065ad41 100644 --- a/drivers/gpu/drm/msm/Makefile +++ b/drivers/gpu/drm/msm/Makefile @@ -68,6 +68,7 @@ msm-$(CONFIG_DRM_MSM_DSI_28NM_8960_PHY) += dsi/phy/dsi_phy_28nm_8960.o ifeq ($(CONFIG_DRM_MSM_DSI_PLL),y) msm-y += dsi/pll/dsi_pll.o msm-$(CONFIG_DRM_MSM_DSI_28NM_PHY) += dsi/pll/dsi_pll_28nm.o +msm-$(CONFIG_DRM_MSM_DSI_28NM_8960_PHY) += dsi/pll/dsi_pll_28nm_8960.o endif

obj-$(CONFIG_DRM_MSM) += msm.o diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c index 5104fc9..5cd438f 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 063caa2..80b6038 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 0000000..38c90e1 --- /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; +}

Initialize clocks only after we get the DSI host version. This will allow us to get clocks using a pre-defined list based on the DSI major/minor version of the host. This is required since clock requirements of different major DSI revisions(v2 vs 6g) aren't the same.

Modify dsi_get_version to get the interface clock, and then put it after it is used.

Signed-off-by: Archit Taneja architt@codeaurora.org --- drivers/gpu/drm/msm/dsi/dsi_host.c | 32 ++++++++++++++++++++++---------- 1 file changed, 22 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 7a365df..f787024 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -177,21 +177,31 @@ 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; @@ -208,9 +218,11 @@ 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: @@ -1417,12 +1429,6 @@ 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__); @@ -1446,6 +1452,12 @@ 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__);

DSIv2 (DSI on older A family chips) has slightly different link clock requirements.

First, we have an extra clock called src_clk (with a dedicated RCG). This is required by the DSI controller to process the pixel data coming from MDP. It needs to be set at the rate "pclk * bytes_per_pixel".

We also need to explicitly configure esc_clk. On DSI6G chips, we don't need to set a rate to esc_clk because its RCG is always sourced from crystal clock (19.2 Mhz in all cases), which is within the escape clock frequency range in the mipi DSI spec. For chips with DSIv2, the crystal clock rate may not be within the required range (27Mhz on APQ8064). Therefore, we derive it from the DSI byte clock. We calculate an esc_clck rate that is within the mipi spec and also divisible by the byte clock rate.

When setting rate and enabling the link clocks, we make sure that byte_clk is configured before esc_clk, and src_clk before pixel_clk. We create two different link_enable funcs for DSI6G and DSIv2 since the sequences are different.

We also obtain two extra source clocks (dsi_src_clk and esc_src_clk) and set their parent to the clocks provided by DSI PLL.

Signed-off-by: Archit Taneja architt@codeaurora.org --- drivers/gpu/drm/msm/dsi/dsi_host.c | 191 ++++++++++++++++++++++++++++++++++++- 1 file changed, 186 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 56c7535..6ec2178 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -113,6 +113,14 @@ 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; @@ -318,7 +326,8 @@ 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; - const struct msm_dsi_config *cfg = msm_host->cfg_hnd->cfg; + 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 */ @@ -372,8 +381,34 @@ static int dsi_clk_init(struct msm_dsi_host *msm_host) if (!msm_host->pixel_clk_src) { ret = -ENODEV; pr_err("%s: can't find pixel_clk_src. ret=%d\n", __func__, ret); + 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; } @@ -413,7 +448,7 @@ static void dsi_bus_clk_disable(struct msm_dsi_host *msm_host) 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;

@@ -460,11 +495,98 @@ 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) @@ -499,6 +621,7 @@ 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; @@ -518,6 +641,47 @@ 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; }

@@ -1750,6 +1914,7 @@ 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;

@@ -1775,6 +1940,22 @@ 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; } @@ -1846,7 +2027,7 @@ 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) {

We currently use iommu allocated DMA buffers for sending DSI commands. DSIv2 doesn't have a port connected to the MDP iommu. Therefore, it can't use iommu allocated buffers to fetch DSI commands.

Use a regular contiguous DMA buffer if we are DSIv2.

Signed-off-by: Archit Taneja architt@codeaurora.org --- drivers/gpu/drm/msm/dsi/dsi.h | 4 +- drivers/gpu/drm/msm/dsi/dsi_host.c | 110 +++++++++++++++++++++++----------- drivers/gpu/drm/msm/dsi/dsi_manager.c | 6 +- 3 files changed, 79 insertions(+), 41 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h index 7336b55..749fbb2 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.h +++ b/drivers/gpu/drm/msm/dsi/dsi.h @@ -91,7 +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);

@@ -145,7 +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_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 6ec2178..bbf7f72 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -138,7 +138,15 @@ 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 drm_display_mode *mode; @@ -983,29 +991,46 @@ 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); + if (ret) { + pr_err("%s: failed to get iova, %d\n", __func__, ret); + return ret; + } mutex_unlock(&dev->struct_mutex); - 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; @@ -1022,14 +1047,19 @@ 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; @@ -1042,17 +1072,20 @@ 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 */ @@ -1118,17 +1151,21 @@ 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); @@ -1136,7 +1173,7 @@ 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)); @@ -1208,7 +1245,7 @@ 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); @@ -1898,11 +1935,12 @@ 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);

diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c index 0455ff7..58ba7ec 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; }

List the clocks in the order that's used in DT. We don't have mdp/dsi DT nodes for any SoC in upstream yet, but we align with the order we intend to use.

Cc: devicetree@vger.kernel.org Cc: Rob Herring robh@kernel.org

Signed-off-by: Archit Taneja architt@codeaurora.org --- Documentation/devicetree/bindings/display/msm/dsi.txt | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/display/msm/dsi.txt b/Documentation/devicetree/bindings/display/msm/dsi.txt index f344b9e..e097955 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi.txt +++ b/Documentation/devicetree/bindings/display/msm/dsi.txt @@ -14,13 +14,13 @@ Required properties: - clocks: device clocks See Documentation/devicetree/bindings/clocks/clock-bindings.txt for details. - clock-names: the following clocks are required: + * "mdp_core_clk" + * "iface_clk" * "bus_clk" - * "byte_clk" - * "core_clk" * "core_mmss_clk" - * "iface_clk" - * "mdp_core_clk" + * "byte_clk" * "pixel_clk" + * "core_clk" - vdd-supply: phandle to vdd regulator device node - vddio-supply: phandle to vdd-io regulator device node - vdda-supply: phandle to vdda regulator device node

Add additional property info needed for DSIv2 DT.

Cc: devicetree@vger.kernel.org Cc: Rob Herring robh@kernel.org

Signed-off-by: Archit Taneja architt@codeaurora.org --- Documentation/devicetree/bindings/display/msm/dsi.txt | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/display/msm/dsi.txt b/Documentation/devicetree/bindings/display/msm/dsi.txt index e097955..e7423be 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi.txt +++ b/Documentation/devicetree/bindings/display/msm/dsi.txt @@ -21,10 +21,13 @@ Required properties: * "byte_clk" * "pixel_clk" * "core_clk" + For DSIv2, we need an additional clock: + * "src_clk" - vdd-supply: phandle to vdd regulator device node - vddio-supply: phandle to vdd-io regulator device node - vdda-supply: phandle to vdda regulator device node - qcom,dsi-phy: phandle to DSI PHY device node +- syscon-sfpb: A phandle to mmss_sfpb syscon node (only for DSIv2)

Optional properties: - panel@0: Node of panel connected to this DSI controller. @@ -51,6 +54,7 @@ Required properties: * "qcom,dsi-phy-28nm-hpm" * "qcom,dsi-phy-28nm-lp" * "qcom,dsi-phy-20nm" + * "qcom,dsi-phy-28nm-8960" - reg: Physical base address and length of the registers of PLL, PHY and PHY regulator - reg-names: The names of register regions. The following regions are required: