* RE: [PATCH 4/5] fb: Add DCU framebuffer driver for Vybrid VF610 platform
From: Wang Huan-B18965 @ 2013-08-06 7:20 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <1375712322.4276.12.camel@weser.hi.pengutronix.de>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^ permalink raw reply
* RE: [PATCH 4/5] fb: Add DCU framebuffer driver for Vybrid VF610 platform
From: Wang Huan-B18965 @ 2013-08-06 3:42 UTC (permalink / raw)
To: linux-arm-kernel
In-Reply-To: <20130805100630.GQ26614@pengutronix.de>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^ permalink raw reply
* Re: [PATCH] fbdev: suppress warning when assigning vga-save/restore base
From: David Miller @ 2013-08-05 22:29 UTC (permalink / raw)
To: santiago
Cc: hpa, dh.herrmann, linux-fbdev, linux-kernel, plagnioj,
tomi.valkeinen, linux
In-Reply-To: <20130805202955.GH22789@localhost>
From: Ondrej Zajicek <santiago@crfreenet.org>
Date: Mon, 5 Aug 2013 22:29:55 +0200
> On Sun, Aug 04, 2013 at 06:51:46PM -0700, David Miller wrote:
>> From: "H. Peter Anvin" <hpa@zytor.com>
>> Date: Sun, 04 Aug 2013 10:33:46 -0700
>>
>> > Anyone who can dig backwards and summarize? In other words:
>> >
>> > Where in the current code do we stuff a physical address in a pointer,
>> > or a virtual address into a non-pointer?
>>
>> The VGA register accessors try to accomodate iomem and ioport
>> accesses.
>>
>> If they are given a non-NULL iomem pointer 'regbase' they use
>> iomem accesses, otherwise they do direct ISA port poking.
>>
>> And yes the drivers in question are making some brash assumptions.
>> I suspect they should be using ioremap() or similar.
>
> Well, these drivers were written without MMIO (port IO only with NULL
> instead of 'vgabase' for VGA register accessors). They were converted in
> patches 94c322c30bd14ae6cdd369cb4a1f94c5c3809ac9,
> f8645933513c65ac55f23c63b2649097289795c6 and a few others (from David
> Miller) to potentially use MMIO by using 'vgabase' instead of NULL:
>
> pcibios_bus_to_resource(dev, &vga_res, &bus_reg);
> par->state.vgabase = (void __iomem *) vga_res.start;
>
> How this could even work? AFAIK these cards have to be explicitly programmed
> to enable MMIO (which was not done in the patches). These patches claim that
> it is for multi-domain PCI. I would guess that vgabase is NULL in common
> configurations but if it is non-NULL, it probably wouldn't work, unless
> there is some hardware magic that transparently converts MMIO (from CPU PoV)
> to port IO (from card/PCI PoV).
>
> Note that there are some later patches (86c0f043a737dadf034a4e6f29aefb074f4a1146)
> from Ondrej Zary that independently enable MMIO, but they use par->mmio
> field instead of par->state.vgabase .
Ok, so the correct fix would be to make them pass NULL again and to simply
ignore the resources.
^ permalink raw reply
* [PATCH v3 20/20] video: da8xx-fb: adding am33xx as dependency
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
Updating Kconfig to allow am33xx to include lcdc fbdev driver
including some extra dependencies needed by device tree mods.
v2: must add FB_MODE_HELPERS as VIDEOMODE_HELPERS alone doesn't
get the correct functions from fbmon.c built in.
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/Kconfig | 8 +++++---
1 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index 2e937bd..f36c2f7 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -2226,15 +2226,17 @@ config FB_SH7760
panels <= 320 pixel horizontal resolution.
config FB_DA8XX
- tristate "DA8xx/OMAP-L1xx Framebuffer support"
- depends on FB && ARCH_DAVINCI_DA8XX
+ tristate "DA8xx/OMAP-L1xx/AM335x Framebuffer support"
+ depends on FB && (ARCH_DAVINCI_DA8XX || SOC_AM33XX)
select FB_CFB_FILLRECT
select FB_CFB_COPYAREA
select FB_CFB_IMAGEBLIT
select FB_CFB_REV_PIXELS_IN_BYTE
+ select FB_MODE_HELPERS
+ select VIDEOMODE_HELPERS
---help---
This is the frame buffer device driver for the TI LCD controller
- found on DA8xx/OMAP-L1xx SoCs.
+ found on DA8xx/OMAP-L1xx/AM335x SoCs.
If unsure, say N.
config FB_VIRTUAL
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 19/20] video: da8xx-fb: let compiler decide what to inline
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
Remove use of explicit inline compiler directive and let the compiler
make the decision as per Documentation/CodingStyle.
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/da8xx-fb.c | 17 ++++++++---------
1 files changed, 8 insertions(+), 9 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index 8c0ca11..ea9771f 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -141,12 +141,12 @@ static irq_handler_t lcdc_irq_handler;
static wait_queue_head_t frame_done_wq;
static int frame_done_flag;
-static inline unsigned int lcdc_read(unsigned int addr)
+static unsigned int lcdc_read(unsigned int addr)
{
return (unsigned int)__raw_readl(da8xx_fb_reg_base + (addr));
}
-static inline void lcdc_write(unsigned int val, unsigned int addr)
+static void lcdc_write(unsigned int val, unsigned int addr)
{
__raw_writel(val, da8xx_fb_reg_base + (addr));
}
@@ -245,13 +245,13 @@ static struct fb_videomode known_lcd_panels[] = {
},
};
-static inline bool da8xx_fb_is_raster_enabled(void)
+static bool da8xx_fb_is_raster_enabled(void)
{
return !!(lcdc_read(LCD_RASTER_CTRL_REG) & LCD_RASTER_ENABLE);
}
/* Enable the Raster Engine of the LCD Controller */
-static inline void lcd_enable_raster(void)
+static void lcd_enable_raster(void)
{
u32 reg;
@@ -273,8 +273,7 @@ static inline void lcd_enable_raster(void)
}
/* Disable the Raster Engine of the LCD Controller */
-static inline void lcd_disable_raster(enum da8xx_frame_complete
- wait_for_frame_done)
+static void lcd_disable_raster(enum da8xx_frame_complete wait_for_frame_done)
{
u32 reg;
int ret;
@@ -750,7 +749,7 @@ static int da8xx_fb_calc_config_clk_divider(struct da8xx_fb_par *par,
return da8xx_fb_config_clk_divider(par, lcdc_clk_div, lcdc_clk_rate);
}
-static inline unsigned da8xx_fb_round_clk(struct da8xx_fb_par *par,
+static unsigned da8xx_fb_round_clk(struct da8xx_fb_par *par,
unsigned pixclock)
{
unsigned lcdc_clk_div, lcdc_clk_rate;
@@ -1043,7 +1042,7 @@ static int lcd_da8xx_cpufreq_transition(struct notifier_block *nb,
return 0;
}
-static inline int lcd_da8xx_cpufreq_register(struct da8xx_fb_par *par)
+static int lcd_da8xx_cpufreq_register(struct da8xx_fb_par *par)
{
par->freq_transition.notifier_call = lcd_da8xx_cpufreq_transition;
@@ -1051,7 +1050,7 @@ static inline int lcd_da8xx_cpufreq_register(struct da8xx_fb_par *par)
CPUFREQ_TRANSITION_NOTIFIER);
}
-static inline void lcd_da8xx_cpufreq_deregister(struct da8xx_fb_par *par)
+static void lcd_da8xx_cpufreq_deregister(struct da8xx_fb_par *par)
{
cpufreq_unregister_notifier(&par->freq_transition,
CPUFREQ_TRANSITION_NOTIFIER);
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 18/20] video: da8xx-fb: make clock naming consistent
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
Clean up the code, so that the names of the various clock variables
are consistent to it is clear what variable is associated with what
clock.
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/da8xx-fb.c | 24 ++++++++++++------------
1 files changed, 12 insertions(+), 12 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index dfe7572..8c0ca11 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -177,7 +177,7 @@ struct da8xx_fb_par {
#ifdef CONFIG_CPU_FREQ
struct notifier_block freq_transition;
#endif
- unsigned int lcd_fck_rate;
+ unsigned int lcdc_clk_rate;
void (*panel_power_ctrl)(int);
u32 pseudo_palette[16];
struct fb_videomode mode;
@@ -693,7 +693,7 @@ static int da8xx_fb_config_clk_divider(struct da8xx_fb_par *par,
{
int ret;
- if (par->lcd_fck_rate != lcdc_clk_rate) {
+ if (par->lcdc_clk_rate != lcdc_clk_rate) {
ret = clk_set_rate(par->lcdc_clk, lcdc_clk_rate);
if (IS_ERR_VALUE(ret)) {
dev_err(par->dev,
@@ -701,7 +701,7 @@ static int da8xx_fb_config_clk_divider(struct da8xx_fb_par *par,
lcdc_clk_rate);
return ret;
}
- par->lcd_fck_rate = clk_get_rate(par->lcdc_clk);
+ par->lcdc_clk_rate = clk_get_rate(par->lcdc_clk);
}
/* Configure the LCD clock divisor. */
@@ -723,7 +723,7 @@ static unsigned int da8xx_fb_calc_clk_divider(struct da8xx_fb_par *par,
pixclock = PICOS2KHZ(pixclock) * 1000;
- *lcdc_clk_rate = par->lcd_fck_rate;
+ *lcdc_clk_rate = par->lcdc_clk_rate;
if (pixclock < (*lcdc_clk_rate / CLK_MAX_DIV)) {
*lcdc_clk_rate = clk_round_rate(par->lcdc_clk,
@@ -1031,8 +1031,8 @@ static int lcd_da8xx_cpufreq_transition(struct notifier_block *nb,
par = container_of(nb, struct da8xx_fb_par, freq_transition);
if (val = CPUFREQ_POSTCHANGE) {
- if (par->lcd_fck_rate != clk_get_rate(par->lcdc_clk)) {
- par->lcd_fck_rate = clk_get_rate(par->lcdc_clk);
+ if (par->lcdc_clk_rate != clk_get_rate(par->lcdc_clk)) {
+ par->lcdc_clk_rate = clk_get_rate(par->lcdc_clk);
lcd_disable_raster(DA8XX_FRAME_WAIT);
da8xx_fb_calc_config_clk_divider(par, &par->mode);
if (par->blank = FB_BLANK_UNBLANK)
@@ -1327,8 +1327,8 @@ static int fb_probe(struct platform_device *device)
struct lcd_ctrl_config *lcd_cfg;
struct fb_videomode *lcdc_info;
struct fb_info *da8xx_fb_info;
- struct clk *fb_clk = NULL;
struct da8xx_fb_par *par;
+ struct clk *tmp_lcdc_clk;
int ret;
unsigned long ulcm;
@@ -1346,10 +1346,10 @@ static int fb_probe(struct platform_device *device)
if (IS_ERR(da8xx_fb_reg_base))
return PTR_ERR(da8xx_fb_reg_base);
- fb_clk = devm_clk_get(&device->dev, "fck");
- if (IS_ERR(fb_clk)) {
+ tmp_lcdc_clk = devm_clk_get(&device->dev, "fck");
+ if (IS_ERR(tmp_lcdc_clk)) {
dev_err(&device->dev, "Can not get device clock\n");
- return PTR_ERR(fb_clk);
+ return PTR_ERR(tmp_lcdc_clk);
}
pm_runtime_enable(&device->dev);
@@ -1389,8 +1389,8 @@ static int fb_probe(struct platform_device *device)
par = da8xx_fb_info->par;
par->dev = &device->dev;
- par->lcdc_clk = fb_clk;
- par->lcd_fck_rate = clk_get_rate(fb_clk);
+ par->lcdc_clk = tmp_lcdc_clk;
+ par->lcdc_clk_rate = clk_get_rate(par->lcdc_clk);
if (fb_pdata->panel_power_ctrl) {
par->panel_power_ctrl = fb_pdata->panel_power_ctrl;
par->panel_power_ctrl(1);
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 17/20] video: da8xx-fb: set upstream clock rate (if reqd)
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
Based on original patch by: Afzal Mohammed <afzal@ti.com>
LCDC IP has a clock divider to adjust pixel clock, this limits pixel
clock range to fck/255 - fck/2(fck - rate of input clock to LCDC IP).
In the case of AM335x, where this IP is present, default fck is not
sufficient to provide normal pixel clock rates, hence rendering this
driver unusable on AM335x.
If input clock too is configurable, allowable range of pixel clock
would increase. Here initially it is checked whether with present fck,
divider in IP could be configured to obtain required rate, if not,
fck is adjusted. This makes it usable on AM335x.
Note:
Another solution would be to model an inherited basic clock divider of
CCF, an advantage would be a better possible resolution for pixel clk.
And trying to instantiate a CCF clock would mean that to be consistent,
3 bits being turned on to enable clocks of LCDC IP would have to be
modeled as gate clocks. Now that would bring in a total of 4 clocks,
including necessity to create a new inherited divider clock, and that
mean a branch of clock tree would be present in LCDC driver. This
would add complexity to LCDC driver bringing in considerable amount
of clock handling code, and this would not bring in much advantage
for existing use cases other than providing a higher resolution of
pixel clock. And existing use cases work without relying on clock
modeling. Another fact is that out of the two platform's using this
driver DaVinci is not yet converted to CCF. In future if higher
resolution of pixel clock is required, and probably after DaVinci is
CCF'ed, modeling clock nodes inside driver may be considered.
v2: purely cosmetic changes to try and clarify what variables are
being used for in the clock rate / divider calculations
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/da8xx-fb.c | 85 +++++++++++++++++++++++++++++++++++-----------
1 files changed, 65 insertions(+), 20 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index d8b295a..dfe7572 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -132,6 +132,9 @@
#define WSI_TIMEOUT 50
#define PALETTE_SIZE 256
+#define CLK_MIN_DIV 2
+#define CLK_MAX_DIV 255
+
static void __iomem *da8xx_fb_reg_base;
static unsigned int lcd_revision;
static irq_handler_t lcdc_irq_handler;
@@ -684,38 +687,76 @@ static void da8xx_fb_lcd_reset(void)
}
}
-static inline unsigned da8xx_fb_calc_clk_divider(struct da8xx_fb_par *par,
- unsigned pixclock)
-{
- return par->lcd_fck_rate / (PICOS2KHZ(pixclock) * 1000);
-}
-
-static inline unsigned da8xx_fb_round_clk(struct da8xx_fb_par *par,
- unsigned pixclock)
+static int da8xx_fb_config_clk_divider(struct da8xx_fb_par *par,
+ unsigned lcdc_clk_div,
+ unsigned lcdc_clk_rate)
{
- unsigned div;
+ int ret;
- div = da8xx_fb_calc_clk_divider(par, pixclock);
- return KHZ2PICOS(par->lcd_fck_rate / (1000 * div));
-}
+ if (par->lcd_fck_rate != lcdc_clk_rate) {
+ ret = clk_set_rate(par->lcdc_clk, lcdc_clk_rate);
+ if (IS_ERR_VALUE(ret)) {
+ dev_err(par->dev,
+ "unable to set clock rate at %u\n",
+ lcdc_clk_rate);
+ return ret;
+ }
+ par->lcd_fck_rate = clk_get_rate(par->lcdc_clk);
+ }
-static inline void da8xx_fb_config_clk_divider(unsigned div)
-{
/* Configure the LCD clock divisor. */
- lcdc_write(LCD_CLK_DIVISOR(div) |
+ lcdc_write(LCD_CLK_DIVISOR(lcdc_clk_div) |
(LCD_RASTER_MODE & 0x1), LCD_CTRL_REG);
if (lcd_revision = LCD_VERSION_2)
lcdc_write(LCD_V2_DMA_CLK_EN | LCD_V2_LIDD_CLK_EN |
LCD_V2_CORE_CLK_EN, LCD_CLK_ENABLE_REG);
+
+ return 0;
+}
+
+static unsigned int da8xx_fb_calc_clk_divider(struct da8xx_fb_par *par,
+ unsigned pixclock,
+ unsigned *lcdc_clk_rate)
+{
+ unsigned lcdc_clk_div;
+
+ pixclock = PICOS2KHZ(pixclock) * 1000;
+
+ *lcdc_clk_rate = par->lcd_fck_rate;
+
+ if (pixclock < (*lcdc_clk_rate / CLK_MAX_DIV)) {
+ *lcdc_clk_rate = clk_round_rate(par->lcdc_clk,
+ pixclock * CLK_MAX_DIV);
+ lcdc_clk_div = CLK_MAX_DIV;
+ } else if (pixclock > (*lcdc_clk_rate / CLK_MIN_DIV)) {
+ *lcdc_clk_rate = clk_round_rate(par->lcdc_clk,
+ pixclock * CLK_MIN_DIV);
+ lcdc_clk_div = CLK_MIN_DIV;
+ } else {
+ lcdc_clk_div = *lcdc_clk_rate / pixclock;
+ }
+
+ return lcdc_clk_div;
}
-static inline void da8xx_fb_calc_config_clk_divider(struct da8xx_fb_par *par,
- struct fb_videomode *mode)
+static int da8xx_fb_calc_config_clk_divider(struct da8xx_fb_par *par,
+ struct fb_videomode *mode)
{
- unsigned div = da8xx_fb_calc_clk_divider(par, mode->pixclock);
+ unsigned lcdc_clk_rate;
+ unsigned lcdc_clk_div = da8xx_fb_calc_clk_divider(par, mode->pixclock,
+ &lcdc_clk_rate);
- da8xx_fb_config_clk_divider(div);
+ return da8xx_fb_config_clk_divider(par, lcdc_clk_div, lcdc_clk_rate);
+}
+
+static inline unsigned da8xx_fb_round_clk(struct da8xx_fb_par *par,
+ unsigned pixclock)
+{
+ unsigned lcdc_clk_div, lcdc_clk_rate;
+
+ lcdc_clk_div = da8xx_fb_calc_clk_divider(par, pixclock, &lcdc_clk_rate);
+ return KHZ2PICOS(lcdc_clk_rate / (1000 * lcdc_clk_div));
}
static int lcd_init(struct da8xx_fb_par *par, const struct lcd_ctrl_config *cfg,
@@ -724,7 +765,11 @@ static int lcd_init(struct da8xx_fb_par *par, const struct lcd_ctrl_config *cfg,
u32 bpp;
int ret = 0;
- da8xx_fb_calc_config_clk_divider(par, panel);
+ ret = da8xx_fb_calc_config_clk_divider(par, panel);
+ if (IS_ERR_VALUE(ret)) {
+ dev_err(par->dev, "unable to configure clock\n");
+ return ret;
+ }
if (panel->sync & FB_SYNC_CLK_INVERT)
lcdc_write((lcdc_read(LCD_RASTER_TIMING_2_REG) |
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 16/20] video: da8xx-fb: reorganize panel detection
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
From: Afzal Mohammed <afzal@ti.com>
Move panel detection to a separate function, this helps in readability
as well as makes DT support cleaner.
Signed-off-by: Afzal Mohammed <afzal@ti.com>
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/da8xx-fb.c | 42 ++++++++++++++++++++++++++----------------
1 files changed, 26 insertions(+), 16 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index dec2777..d8b295a 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -1253,6 +1253,27 @@ static struct fb_ops da8xx_fb_ops = {
.fb_blank = cfb_blank,
};
+static struct fb_videomode *da8xx_fb_get_videomode(struct platform_device *dev)
+{
+ struct da8xx_lcdc_platform_data *fb_pdata = dev->dev.platform_data;
+ struct fb_videomode *lcdc_info;
+ int i;
+
+ for (i = 0, lcdc_info = known_lcd_panels;
+ i < ARRAY_SIZE(known_lcd_panels); i++, lcdc_info++) {
+ if (strcmp(fb_pdata->type, lcdc_info->name) = 0)
+ break;
+ }
+
+ if (i = ARRAY_SIZE(known_lcd_panels)) {
+ dev_err(&dev->dev, "no panel found\n");
+ return NULL;
+ }
+ dev_info(&dev->dev, "found %s panel\n", lcdc_info->name);
+
+ return lcdc_info;
+}
+
static int fb_probe(struct platform_device *device)
{
struct da8xx_lcdc_platform_data *fb_pdata @@ -1263,7 +1284,7 @@ static int fb_probe(struct platform_device *device)
struct fb_info *da8xx_fb_info;
struct clk *fb_clk = NULL;
struct da8xx_fb_par *par;
- int ret, i;
+ int ret;
unsigned long ulcm;
if (fb_pdata = NULL) {
@@ -1271,6 +1292,10 @@ static int fb_probe(struct platform_device *device)
return -ENOENT;
}
+ lcdc_info = da8xx_fb_get_videomode(device);
+ if (lcdc_info = NULL)
+ return -ENODEV;
+
lcdc_regs = platform_get_resource(device, IORESOURCE_MEM, 0);
da8xx_fb_reg_base = devm_ioremap_resource(&device->dev, lcdc_regs);
if (IS_ERR(da8xx_fb_reg_base))
@@ -1302,21 +1327,6 @@ static int fb_probe(struct platform_device *device)
break;
}
- for (i = 0, lcdc_info = known_lcd_panels;
- i < ARRAY_SIZE(known_lcd_panels);
- i++, lcdc_info++) {
- if (strcmp(fb_pdata->type, lcdc_info->name) = 0)
- break;
- }
-
- if (i = ARRAY_SIZE(known_lcd_panels)) {
- dev_err(&device->dev, "GLCD: No valid panel found\n");
- ret = -ENODEV;
- goto err_pm_runtime_disable;
- } else
- dev_info(&device->dev, "GLCD: Found %s panel\n",
- fb_pdata->type);
-
lcd_cfg = (struct lcd_ctrl_config *)fb_pdata->controller_data;
if (!lcd_cfg) {
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 15/20] video: da8xx-fb: ensure non-null cfg in pdata
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
From: Afzal Mohammed <afzal@ti.com>
Ensure that platform data contains pointer for lcd_ctrl_config.
Signed-off-by: Afzal Mohammed <afzal@ti.com>
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/da8xx-fb.c | 5 +++++
1 files changed, 5 insertions(+), 0 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index c620a32..dec2777 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -1319,6 +1319,11 @@ static int fb_probe(struct platform_device *device)
lcd_cfg = (struct lcd_ctrl_config *)fb_pdata->controller_data;
+ if (!lcd_cfg) {
+ ret = -EINVAL;
+ goto err_pm_runtime_disable;
+ }
+
da8xx_fb_info = framebuffer_alloc(sizeof(struct da8xx_fb_par),
&device->dev);
if (!da8xx_fb_info) {
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 14/20] video: da8xx-fb: use devres
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
Replace existing resource handling in the driver with managed device
resource.
v2: implement some changes as recommended by
Prabhakar Lad <prabhakar.csengg@gmail.com>
Signed-off-by: Lad, Prabhakar <prabhakar.csengg@gmail.com>
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/da8xx-fb.c | 41 ++++++++---------------------------------
1 files changed, 8 insertions(+), 33 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index 8384455..c620a32 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -133,7 +133,6 @@
#define PALETTE_SIZE 256
static void __iomem *da8xx_fb_reg_base;
-static struct resource *lcdc_regs;
static unsigned int lcd_revision;
static irq_handler_t lcdc_irq_handler;
static wait_queue_head_t frame_done_wq;
@@ -1039,12 +1038,9 @@ static int fb_remove(struct platform_device *dev)
par->p_palette_base);
dma_free_coherent(NULL, par->vram_size, par->vram_virt,
par->vram_phys);
- free_irq(par->irq, par);
pm_runtime_put_sync(&dev->dev);
pm_runtime_disable(&dev->dev);
framebuffer_release(info);
- iounmap(da8xx_fb_reg_base);
- release_mem_region(lcdc_regs->start, resource_size(lcdc_regs));
}
return 0;
@@ -1261,12 +1257,12 @@ static int fb_probe(struct platform_device *device)
{
struct da8xx_lcdc_platform_data *fb_pdata device->dev.platform_data;
+ static struct resource *lcdc_regs;
struct lcd_ctrl_config *lcd_cfg;
struct fb_videomode *lcdc_info;
struct fb_info *da8xx_fb_info;
struct clk *fb_clk = NULL;
struct da8xx_fb_par *par;
- resource_size_t len;
int ret, i;
unsigned long ulcm;
@@ -1276,29 +1272,14 @@ static int fb_probe(struct platform_device *device)
}
lcdc_regs = platform_get_resource(device, IORESOURCE_MEM, 0);
- if (!lcdc_regs) {
- dev_err(&device->dev,
- "Can not get memory resource for LCD controller\n");
- return -ENOENT;
- }
-
- len = resource_size(lcdc_regs);
-
- lcdc_regs = request_mem_region(lcdc_regs->start, len, lcdc_regs->name);
- if (!lcdc_regs)
- return -EBUSY;
+ da8xx_fb_reg_base = devm_ioremap_resource(&device->dev, lcdc_regs);
+ if (IS_ERR(da8xx_fb_reg_base))
+ return PTR_ERR(da8xx_fb_reg_base);
- da8xx_fb_reg_base = ioremap(lcdc_regs->start, len);
- if (!da8xx_fb_reg_base) {
- ret = -EBUSY;
- goto err_request_mem;
- }
-
- fb_clk = clk_get(&device->dev, "fck");
+ fb_clk = devm_clk_get(&device->dev, "fck");
if (IS_ERR(fb_clk)) {
dev_err(&device->dev, "Can not get device clock\n");
- ret = -ENODEV;
- goto err_ioremap;
+ return PTR_ERR(fb_clk);
}
pm_runtime_enable(&device->dev);
@@ -1459,8 +1440,8 @@ static int fb_probe(struct platform_device *device)
lcdc_irq_handler = lcdc_irq_handler_rev02;
}
- ret = request_irq(par->irq, lcdc_irq_handler, 0,
- DRIVER_NAME, par);
+ ret = devm_request_irq(&device->dev, par->irq, lcdc_irq_handler, 0,
+ DRIVER_NAME, par);
if (ret)
goto irq_freq;
return 0;
@@ -1489,12 +1470,6 @@ err_pm_runtime_disable:
pm_runtime_put_sync(&device->dev);
pm_runtime_disable(&device->dev);
-err_ioremap:
- iounmap(da8xx_fb_reg_base);
-
-err_request_mem:
- release_mem_region(lcdc_regs->start, len);
-
return ret;
}
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 13/20] video: da8xx-fb: enable sync lost intr for v2 ip
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
From: Afzal Mohammed <afzal@ti.com>
The interrupt handler explicitly has code that handles the sync lost
interrupt. However the sync lost interrupt is never actually being
enabled in the LCD controller, therefore this interrupt code path is not
being exercised. This fix simply enables the generation of the sync
lost interrupt by the LCD controller so it can be dealt with
appropriately by the interrupt handler.
Signed-off-by: Afzal Mohammed <afzal@ti.com>
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/da8xx-fb.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index 893aefe..8384455 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -320,7 +320,7 @@ static void lcd_blit(int load_mode, struct da8xx_fb_par *par)
reg_int = lcdc_read(LCD_INT_ENABLE_SET_REG) |
LCD_V2_END_OF_FRAME0_INT_ENA |
LCD_V2_END_OF_FRAME1_INT_ENA |
- LCD_FRAME_DONE;
+ LCD_FRAME_DONE | LCD_SYNC_LOST;
lcdc_write(reg_int, LCD_INT_ENABLE_SET_REG);
}
reg_dma |= LCD_DUAL_FRAME_BUFFER_ENABLE;
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 12/20] video: da8xx-fb: fix 24bpp raster configuration
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
Based on original patch by: Manjunathappa, Prakash <prakash.pm@ti.com>
and Afzal Mohammed <afzal@ti.com>
Set only LCD_V2_TFT_24BPP_MODE bit for 24bpp and LCD_V2_TFT_24BPP_UNPACK
bit along with LCD_V2_TFT_24BPP_MODE for 32bpp configuration.
Patch is tested on am335x-evm for 24bpp and da850-evm for 16bpp
configurations.
v2: removes confusing fall through in case statement for pixel
depth configuration.
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/da8xx-fb.c | 3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index 9375382..893aefe 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -554,10 +554,11 @@ static int lcd_cfg_frame_buffer(struct da8xx_fb_par *par, u32 width, u32 height,
break;
case 24:
reg |= LCD_V2_TFT_24BPP_MODE;
+ break;
case 32:
+ reg |= LCD_V2_TFT_24BPP_MODE;
reg |= LCD_V2_TFT_24BPP_UNPACK;
break;
-
case 8:
par->palette_sz = 256 * 2;
break;
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 11/20] video: da8xx-fb: improve readability of code
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
Change the lcd_disable_raster funtion from using a bool to an enum
as the function is very confusing with the current api. This helps
make it clearer what the parameter is really doing.
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/da8xx-fb.c | 24 +++++++++++++-----------
include/video/da8xx-fb.h | 5 +++++
2 files changed, 18 insertions(+), 11 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index 6beb88d..9375382 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -271,7 +271,8 @@ static inline void lcd_enable_raster(void)
}
/* Disable the Raster Engine of the LCD Controller */
-static inline void lcd_disable_raster(bool wait_for_frame_done)
+static inline void lcd_disable_raster(enum da8xx_frame_complete
+ wait_for_frame_done)
{
u32 reg;
int ret;
@@ -283,7 +284,8 @@ static inline void lcd_disable_raster(bool wait_for_frame_done)
/* return if already disabled */
return;
- if ((wait_for_frame_done = true) && (lcd_revision = LCD_VERSION_2)) {
+ if ((wait_for_frame_done = DA8XX_FRAME_WAIT) &&
+ (lcd_revision = LCD_VERSION_2)) {
frame_done_flag = 0;
ret = wait_event_interruptible_timeout(frame_done_wq,
frame_done_flag != 0,
@@ -771,7 +773,7 @@ static irqreturn_t lcdc_irq_handler_rev02(int irq, void *arg)
u32 stat = lcdc_read(LCD_MASKED_STAT_REG);
if ((stat & LCD_SYNC_LOST) && (stat & LCD_FIFO_UNDERFLOW)) {
- lcd_disable_raster(false);
+ lcd_disable_raster(DA8XX_FRAME_NOWAIT);
lcdc_write(stat, LCD_MASKED_STAT_REG);
lcd_enable_raster();
} else if (stat & LCD_PL_LOAD_DONE) {
@@ -781,7 +783,7 @@ static irqreturn_t lcdc_irq_handler_rev02(int irq, void *arg)
* interrupt via the following write to the status register. If
* this is done after then one gets multiple PL done interrupts.
*/
- lcd_disable_raster(false);
+ lcd_disable_raster(DA8XX_FRAME_NOWAIT);
lcdc_write(stat, LCD_MASKED_STAT_REG);
@@ -834,7 +836,7 @@ static irqreturn_t lcdc_irq_handler_rev01(int irq, void *arg)
u32 reg_ras;
if ((stat & LCD_SYNC_LOST) && (stat & LCD_FIFO_UNDERFLOW)) {
- lcd_disable_raster(false);
+ lcd_disable_raster(DA8XX_FRAME_NOWAIT);
lcdc_write(stat, LCD_STAT_REG);
lcd_enable_raster();
} else if (stat & LCD_PL_LOAD_DONE) {
@@ -844,7 +846,7 @@ static irqreturn_t lcdc_irq_handler_rev01(int irq, void *arg)
* interrupt via the following write to the status register. If
* this is done after then one gets multiple PL done interrupts.
*/
- lcd_disable_raster(false);
+ lcd_disable_raster(DA8XX_FRAME_NOWAIT);
lcdc_write(stat, LCD_STAT_REG);
@@ -986,7 +988,7 @@ static int lcd_da8xx_cpufreq_transition(struct notifier_block *nb,
if (val = CPUFREQ_POSTCHANGE) {
if (par->lcd_fck_rate != clk_get_rate(par->lcdc_clk)) {
par->lcd_fck_rate = clk_get_rate(par->lcdc_clk);
- lcd_disable_raster(true);
+ lcd_disable_raster(DA8XX_FRAME_WAIT);
da8xx_fb_calc_config_clk_divider(par, &par->mode);
if (par->blank = FB_BLANK_UNBLANK)
lcd_enable_raster();
@@ -1024,7 +1026,7 @@ static int fb_remove(struct platform_device *dev)
if (par->panel_power_ctrl)
par->panel_power_ctrl(0);
- lcd_disable_raster(true);
+ lcd_disable_raster(DA8XX_FRAME_WAIT);
lcdc_write(0, LCD_RASTER_CTRL_REG);
/* disable DMA */
@@ -1140,7 +1142,7 @@ static int cfb_blank(int blank, struct fb_info *info)
if (par->panel_power_ctrl)
par->panel_power_ctrl(0);
- lcd_disable_raster(true);
+ lcd_disable_raster(DA8XX_FRAME_WAIT);
break;
default:
ret = -EINVAL;
@@ -1208,7 +1210,7 @@ static int da8xxfb_set_par(struct fb_info *info)
bool raster = da8xx_fb_is_raster_enabled();
if (raster)
- lcd_disable_raster(true);
+ lcd_disable_raster(DA8XX_FRAME_WAIT);
fb_var_to_videomode(&par->mode, &info->var);
@@ -1569,7 +1571,7 @@ static int fb_suspend(struct platform_device *dev, pm_message_t state)
par->panel_power_ctrl(0);
fb_set_suspend(info, 1);
- lcd_disable_raster(true);
+ lcd_disable_raster(DA8XX_FRAME_WAIT);
lcd_context_save();
pm_runtime_put_sync(&dev->dev);
console_unlock();
diff --git a/include/video/da8xx-fb.h b/include/video/da8xx-fb.h
index f888259..efed3c3 100644
--- a/include/video/da8xx-fb.h
+++ b/include/video/da8xx-fb.h
@@ -23,6 +23,11 @@ enum raster_load_mode {
LOAD_PALETTE,
};
+enum da8xx_frame_complete {
+ DA8XX_FRAME_WAIT,
+ DA8XX_FRAME_NOWAIT,
+};
+
struct da8xx_lcdc_platform_data {
const char manu_name[10];
void *controller_data;
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 10/20] video: da8xx-fb: fb_set_par support
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
v1: original from Afzal Mohammed <afzal@ti.com>
fb_set_par helps in runtime configuration of lcd controller like
changing resolution, pixel clock etc. (eg. using fbset utility)
Reconfigure lcd controller based on information passed by framework.
Enable raster back if it was already enabled.
As fb_set_par would get invoked indirectly from probe via fb_set_var,
remove existing lcdc initialization in probe and do lcdc reset in
probe so that reset happens only at the begining.
v2: changes from Darren Etheridge <detheridge@ti.com>
remove unnecessary conditional branch where we attempt to disable
something that we already checked to see if it was disabled.
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/da8xx-fb.c | 58 +++++++++++++++++++++++++++++++++++++--------
1 files changed, 47 insertions(+), 11 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index 8d73730..6beb88d 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -243,6 +243,11 @@ static struct fb_videomode known_lcd_panels[] = {
},
};
+static inline bool da8xx_fb_is_raster_enabled(void)
+{
+ return !!(lcdc_read(LCD_RASTER_CTRL_REG) & LCD_RASTER_ENABLE);
+}
+
/* Enable the Raster Engine of the LCD Controller */
static inline void lcd_enable_raster(void)
{
@@ -665,9 +670,6 @@ static int fb_setcolreg(unsigned regno, unsigned red, unsigned green,
static void da8xx_fb_lcd_reset(void)
{
- /* Disable the Raster if previously Enabled */
- lcd_disable_raster(false);
-
/* DMA has to be disabled */
lcdc_write(0, LCD_DMA_CTRL_REG);
lcdc_write(0, LCD_RASTER_CTRL_REG);
@@ -720,8 +722,6 @@ static int lcd_init(struct da8xx_fb_par *par, const struct lcd_ctrl_config *cfg,
u32 bpp;
int ret = 0;
- da8xx_fb_lcd_reset();
-
da8xx_fb_calc_config_clk_divider(par, panel);
if (panel->sync & FB_SYNC_CLK_INVERT)
@@ -1201,9 +1201,50 @@ static int da8xx_pan_display(struct fb_var_screeninfo *var,
return ret;
}
+static int da8xxfb_set_par(struct fb_info *info)
+{
+ struct da8xx_fb_par *par = info->par;
+ int ret;
+ bool raster = da8xx_fb_is_raster_enabled();
+
+ if (raster)
+ lcd_disable_raster(true);
+
+ fb_var_to_videomode(&par->mode, &info->var);
+
+ par->cfg.bpp = info->var.bits_per_pixel;
+
+ info->fix.visual = (par->cfg.bpp <= 8) ?
+ FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_TRUECOLOR;
+ info->fix.line_length = (par->mode.xres * par->cfg.bpp) / 8;
+
+ ret = lcd_init(par, &par->cfg, &par->mode);
+ if (ret < 0) {
+ dev_err(par->dev, "lcd init failed\n");
+ return ret;
+ }
+
+ par->dma_start = info->fix.smem_start +
+ info->var.yoffset * info->fix.line_length +
+ info->var.xoffset * info->var.bits_per_pixel / 8;
+ par->dma_end = par->dma_start +
+ info->var.yres * info->fix.line_length - 1;
+
+ lcdc_write(par->dma_start, LCD_DMA_FRM_BUF_BASE_ADDR_0_REG);
+ lcdc_write(par->dma_end, LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG);
+ lcdc_write(par->dma_start, LCD_DMA_FRM_BUF_BASE_ADDR_1_REG);
+ lcdc_write(par->dma_end, LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG);
+
+ if (raster)
+ lcd_enable_raster();
+
+ return 0;
+}
+
static struct fb_ops da8xx_fb_ops = {
.owner = THIS_MODULE,
.fb_check_var = fb_check_var,
+ .fb_set_par = da8xxfb_set_par,
.fb_setcolreg = fb_setcolreg,
.fb_pan_display = da8xx_pan_display,
.fb_ioctl = fb_ioctl,
@@ -1312,14 +1353,9 @@ static int fb_probe(struct platform_device *device)
}
fb_videomode_to_var(&da8xx_fb_var, lcdc_info);
- fb_var_to_videomode(&par->mode, &da8xx_fb_var);
par->cfg = *lcd_cfg;
- if (lcd_init(par, lcd_cfg, lcdc_info) < 0) {
- dev_err(&device->dev, "lcd_init failed\n");
- ret = -EFAULT;
- goto err_release_fb;
- }
+ da8xx_fb_lcd_reset();
/* allocate frame buffer */
par->vram_size = lcdc_info->xres * lcdc_info->yres * lcd_cfg->bpp;
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 09/20] video: da8xx-fb: report correct pixclock
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
From: Afzal Mohammed <afzal@ti.com>
Update "var" pixclock with the value that is configurable in hardware.
This lets user know the actual pixclock.
Signed-off-by: Afzal Mohammed <afzal@ti.com>
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/da8xx-fb.c | 11 +++++++++++
1 files changed, 11 insertions(+), 0 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index 7db1097..8d73730 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -686,6 +686,15 @@ static inline unsigned da8xx_fb_calc_clk_divider(struct da8xx_fb_par *par,
return par->lcd_fck_rate / (PICOS2KHZ(pixclock) * 1000);
}
+static inline unsigned da8xx_fb_round_clk(struct da8xx_fb_par *par,
+ unsigned pixclock)
+{
+ unsigned div;
+
+ div = da8xx_fb_calc_clk_divider(par, pixclock);
+ return KHZ2PICOS(par->lcd_fck_rate / (1000 * div));
+}
+
static inline void da8xx_fb_config_clk_divider(unsigned div)
{
/* Configure the LCD clock divisor. */
@@ -962,6 +971,8 @@ static int fb_check_var(struct fb_var_screeninfo *var,
if (var->yres + var->yoffset > var->yres_virtual)
var->yoffset = var->yres_virtual - var->yres;
+ var->pixclock = da8xx_fb_round_clk(par, var->pixclock);
+
return err;
}
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 08/20] video: da8xx-fb: store struct device *
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
From: Afzal Mohammed <afzal@ti.com>
store struct device pointer so that dev_dbg/err can be used outside
of probe.
Signed-off-by: Afzal Mohammed <afzal@ti.com>
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/da8xx-fb.c | 2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index 0fac1a0..7db1097 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -150,6 +150,7 @@ static inline void lcdc_write(unsigned int val, unsigned int addr)
}
struct da8xx_fb_par {
+ struct device *dev;
resource_size_t p_palette_base;
unsigned char *v_palette_base;
dma_addr_t vram_phys;
@@ -1291,6 +1292,7 @@ static int fb_probe(struct platform_device *device)
}
par = da8xx_fb_info->par;
+ par->dev = &device->dev;
par->lcdc_clk = fb_clk;
par->lcd_fck_rate = clk_get_rate(fb_clk);
if (fb_pdata->panel_power_ctrl) {
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 07/20] video: da8xx-fb: pix clk and clk div handling cleanup
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
Based on original patch by: Afzal Mohammed <afzal@ti.com>
Use the new modedb field to store pix clk. Reorganize existing clock
divider functions with names now corresponding to what they do, add
common function prefix.
Fix existing panel modedb pixclock to be in ps instead of Hz. This
needed a change in the way clock divider is calculated. As modedb
pixclock information is now in ps, override on "var" pixclock over
modedb to var conversion is removed.
v2:
Changed pixel clock configuration to use KHZ2PICOS macro
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/da8xx-fb.c | 48 +++++++++++++++++----------------------------
1 files changed, 18 insertions(+), 30 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index f1d88ac..0fac1a0 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -160,7 +160,6 @@ struct da8xx_fb_par {
struct clk *lcdc_clk;
int irq;
unsigned int palette_sz;
- unsigned int pxl_clk;
int blank;
wait_queue_head_t vsync_wait;
int vsync_flag;
@@ -201,7 +200,7 @@ static struct fb_videomode known_lcd_panels[] = {
.name = "Sharp_LCD035Q3DG01",
.xres = 320,
.yres = 240,
- .pixclock = 4608000,
+ .pixclock = KHZ2PICOS(4607),
.left_margin = 6,
.right_margin = 8,
.upper_margin = 2,
@@ -216,7 +215,7 @@ static struct fb_videomode known_lcd_panels[] = {
.name = "Sharp_LK043T1DG01",
.xres = 480,
.yres = 272,
- .pixclock = 7833600,
+ .pixclock = KHZ2PICOS(7833),
.left_margin = 2,
.right_margin = 2,
.upper_margin = 2,
@@ -231,7 +230,7 @@ static struct fb_videomode known_lcd_panels[] = {
.name = "SP10Q010",
.xres = 320,
.yres = 240,
- .pixclock = 7833600,
+ .pixclock = KHZ2PICOS(7833),
.left_margin = 10,
.right_margin = 10,
.upper_margin = 10,
@@ -680,13 +679,14 @@ static void da8xx_fb_lcd_reset(void)
}
}
-static void lcd_calc_clk_divider(struct da8xx_fb_par *par)
+static inline unsigned da8xx_fb_calc_clk_divider(struct da8xx_fb_par *par,
+ unsigned pixclock)
{
- unsigned int lcd_clk, div;
-
- lcd_clk = clk_get_rate(par->lcdc_clk);
- div = lcd_clk / par->pxl_clk;
+ return par->lcd_fck_rate / (PICOS2KHZ(pixclock) * 1000);
+}
+static inline void da8xx_fb_config_clk_divider(unsigned div)
+{
/* Configure the LCD clock divisor. */
lcdc_write(LCD_CLK_DIVISOR(div) |
(LCD_RASTER_MODE & 0x1), LCD_CTRL_REG);
@@ -694,7 +694,14 @@ static void lcd_calc_clk_divider(struct da8xx_fb_par *par)
if (lcd_revision = LCD_VERSION_2)
lcdc_write(LCD_V2_DMA_CLK_EN | LCD_V2_LIDD_CLK_EN |
LCD_V2_CORE_CLK_EN, LCD_CLK_ENABLE_REG);
+}
+
+static inline void da8xx_fb_calc_config_clk_divider(struct da8xx_fb_par *par,
+ struct fb_videomode *mode)
+{
+ unsigned div = da8xx_fb_calc_clk_divider(par, mode->pixclock);
+ da8xx_fb_config_clk_divider(div);
}
static int lcd_init(struct da8xx_fb_par *par, const struct lcd_ctrl_config *cfg,
@@ -705,8 +712,7 @@ static int lcd_init(struct da8xx_fb_par *par, const struct lcd_ctrl_config *cfg,
da8xx_fb_lcd_reset();
- /* Calculate the divider */
- lcd_calc_clk_divider(par);
+ da8xx_fb_calc_config_clk_divider(par, panel);
if (panel->sync & FB_SYNC_CLK_INVERT)
lcdc_write((lcdc_read(LCD_RASTER_TIMING_2_REG) |
@@ -969,7 +975,7 @@ static int lcd_da8xx_cpufreq_transition(struct notifier_block *nb,
if (par->lcd_fck_rate != clk_get_rate(par->lcdc_clk)) {
par->lcd_fck_rate = clk_get_rate(par->lcdc_clk);
lcd_disable_raster(true);
- lcd_calc_clk_divider(par);
+ da8xx_fb_calc_config_clk_divider(par, &par->mode);
if (par->blank = FB_BLANK_UNBLANK)
lcd_enable_raster();
}
@@ -1195,22 +1201,6 @@ static struct fb_ops da8xx_fb_ops = {
.fb_blank = cfb_blank,
};
-/* Calculate and return pixel clock period in pico seconds */
-static unsigned int da8xxfb_pixel_clk_period(struct da8xx_fb_par *par)
-{
- unsigned int lcd_clk, div;
- unsigned int configured_pix_clk;
- unsigned long long pix_clk_period_picosec = 1000000000000ULL;
-
- lcd_clk = clk_get_rate(par->lcdc_clk);
- div = lcd_clk / par->pxl_clk;
- configured_pix_clk = (lcd_clk / div);
-
- do_div(pix_clk_period_picosec, configured_pix_clk);
-
- return pix_clk_period_picosec;
-}
-
static int fb_probe(struct platform_device *device)
{
struct da8xx_lcdc_platform_data *fb_pdata @@ -1303,7 +1293,6 @@ static int fb_probe(struct platform_device *device)
par = da8xx_fb_info->par;
par->lcdc_clk = fb_clk;
par->lcd_fck_rate = clk_get_rate(fb_clk);
- par->pxl_clk = lcdc_info->pixclock;
if (fb_pdata->panel_power_ctrl) {
par->panel_power_ctrl = fb_pdata->panel_power_ctrl;
par->panel_power_ctrl(1);
@@ -1368,7 +1357,6 @@ static int fb_probe(struct platform_device *device)
da8xx_fb_var.grayscale lcd_cfg->panel_shade = MONOCHROME ? 1 : 0;
da8xx_fb_var.bits_per_pixel = lcd_cfg->bpp;
- da8xx_fb_var.pixclock = da8xxfb_pixel_clk_period(par);
/* Initialize fbinfo */
da8xx_fb_info->flags = FBINFO_FLAG_DEFAULT;
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 06/20] video: da8xx-fb: store clk rate even if !CPUFREQ
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
From: Afzal Mohammed <afzal@ti.com>
store lcd clk rate always, i.e. irrespective of whether CPUFREQ is
enabled or not. This can be used to get clk rate directly instead of
enquiring with clock framework with clk handle every time.
Signed-off-by: Afzal Mohammed <afzal@ti.com>
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/da8xx-fb.c | 4 +---
1 files changed, 1 insertions(+), 3 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index d060f14..f1d88ac 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -174,8 +174,8 @@ struct da8xx_fb_par {
unsigned int which_dma_channel_done;
#ifdef CONFIG_CPU_FREQ
struct notifier_block freq_transition;
- unsigned int lcd_fck_rate;
#endif
+ unsigned int lcd_fck_rate;
void (*panel_power_ctrl)(int);
u32 pseudo_palette[16];
struct fb_videomode mode;
@@ -1302,9 +1302,7 @@ static int fb_probe(struct platform_device *device)
par = da8xx_fb_info->par;
par->lcdc_clk = fb_clk;
-#ifdef CONFIG_CPU_FREQ
par->lcd_fck_rate = clk_get_rate(fb_clk);
-#endif
par->pxl_clk = lcdc_info->pixclock;
if (fb_pdata->panel_power_ctrl) {
par->panel_power_ctrl = fb_pdata->panel_power_ctrl;
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 05/20] video: da8xx-fb: store current display information
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
From: Afzal Mohammed <afzal@ti.com>
store current videomode and controller data so that reconfiguring can
be done easily. Reconfiguring would be required in fb_set_par, which
is going to be added soon.
If these details are not stored, the work probe does to retrieve these
information would have to repeated at the place of reconfiguring and
modifying platform data would be necessary to handle controller data
changes like bpp.
Signed-off-by: Afzal Mohammed <afzal@ti.com>
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/da8xx-fb.c | 4 ++++
1 files changed, 4 insertions(+), 0 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index 18834fa..d060f14 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -178,6 +178,8 @@ struct da8xx_fb_par {
#endif
void (*panel_power_ctrl)(int);
u32 pseudo_palette[16];
+ struct fb_videomode mode;
+ struct lcd_ctrl_config cfg;
};
static struct fb_var_screeninfo da8xx_fb_var;
@@ -1310,6 +1312,8 @@ static int fb_probe(struct platform_device *device)
}
fb_videomode_to_var(&da8xx_fb_var, lcdc_info);
+ fb_var_to_videomode(&par->mode, &da8xx_fb_var);
+ par->cfg = *lcd_cfg;
if (lcd_init(par, lcd_cfg, lcdc_info) < 0) {
dev_err(&device->dev, "lcd_init failed\n");
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 04/20] video: da8xx-fb: remove unneeded "var" initialization
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
From: Afzal Mohammed <afzal@ti.com>
modedb helper now updates "var" information based on the detected
panel, remove the unnecessary initialization.
Signed-off-by: Afzal Mohammed <afzal@ti.com>
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/da8xx-fb.c | 22 +---------------------
1 files changed, 1 insertions(+), 21 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index a1f6544..18834fa 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -131,10 +131,6 @@
#define WSI_TIMEOUT 50
#define PALETTE_SIZE 256
-#define LEFT_MARGIN 64
-#define RIGHT_MARGIN 64
-#define UPPER_MARGIN 32
-#define LOWER_MARGIN 32
static void __iomem *da8xx_fb_reg_base;
static struct resource *lcdc_regs;
@@ -184,23 +180,7 @@ struct da8xx_fb_par {
u32 pseudo_palette[16];
};
-/* Variable Screen Information */
-static struct fb_var_screeninfo da8xx_fb_var = {
- .xoffset = 0,
- .yoffset = 0,
- .transp = {0, 0, 0},
- .nonstd = 0,
- .activate = 0,
- .height = -1,
- .width = -1,
- .accel_flags = 0,
- .left_margin = LEFT_MARGIN,
- .right_margin = RIGHT_MARGIN,
- .upper_margin = UPPER_MARGIN,
- .lower_margin = LOWER_MARGIN,
- .sync = 0,
- .vmode = FB_VMODE_NONINTERLACED
-};
+static struct fb_var_screeninfo da8xx_fb_var;
static struct fb_fix_screeninfo da8xx_fb_fix = {
.id = "DA8xx FB Drv",
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 03/20] video: da8xx-fb: use modedb helper to update var
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
From: Afzal Mohammed <afzal@ti.com>
modedb structure is now used to store panel information, run modedb
helper over it for initial update of "var" information instead of
equating each fields.
While at it, remove redundant update of bits_per_pixel.
Note: pixclock is overridden with proper value using an existing code
as currently modedb is having it in Hz instead of ps, this would be
fixed in a later change and this overide would be removed.
Signed-off-by: Afzal Mohammed <afzal@ti.com>
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/da8xx-fb.c | 18 ++----------------
1 files changed, 2 insertions(+), 16 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index 52977b1..a1f6544 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -1329,6 +1329,8 @@ static int fb_probe(struct platform_device *device)
par->panel_power_ctrl(1);
}
+ fb_videomode_to_var(&da8xx_fb_var, lcdc_info);
+
if (lcd_init(par, lcd_cfg, lcdc_info) < 0) {
dev_err(&device->dev, "lcd_init failed\n");
ret = -EFAULT;
@@ -1381,25 +1383,9 @@ static int fb_probe(struct platform_device *device)
goto err_release_pl_mem;
}
- /* Initialize par */
- da8xx_fb_info->var.bits_per_pixel = lcd_cfg->bpp;
-
- da8xx_fb_var.xres = lcdc_info->xres;
- da8xx_fb_var.xres_virtual = lcdc_info->xres;
-
- da8xx_fb_var.yres = lcdc_info->yres;
- da8xx_fb_var.yres_virtual = lcdc_info->yres * LCD_NUM_BUFFERS;
-
da8xx_fb_var.grayscale lcd_cfg->panel_shade = MONOCHROME ? 1 : 0;
da8xx_fb_var.bits_per_pixel = lcd_cfg->bpp;
-
- da8xx_fb_var.hsync_len = lcdc_info->hsync_len;
- da8xx_fb_var.vsync_len = lcdc_info->vsync_len;
- da8xx_fb_var.right_margin = lcdc_info->right_margin;
- da8xx_fb_var.left_margin = lcdc_info->left_margin;
- da8xx_fb_var.lower_margin = lcdc_info->lower_margin;
- da8xx_fb_var.upper_margin = lcdc_info->upper_margin;
da8xx_fb_var.pixclock = da8xxfb_pixel_clk_period(par);
/* Initialize fbinfo */
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 02/20] video: da8xx-fb: simplify lcd_reset
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
From: Afzal Mohammed <afzal@ti.com>
lcd_reset function doesn't require any arguement, remove it.
Signed-off-by: Afzal Mohammed <afzal@ti.com>
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/da8xx-fb.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index d00dd17..52977b1 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -681,7 +681,7 @@ static int fb_setcolreg(unsigned regno, unsigned red, unsigned green,
}
#undef CNVT_TOHW
-static void lcd_reset(struct da8xx_fb_par *par)
+static void da8xx_fb_lcd_reset(void)
{
/* Disable the Raster if previously Enabled */
lcd_disable_raster(false);
@@ -721,7 +721,7 @@ static int lcd_init(struct da8xx_fb_par *par, const struct lcd_ctrl_config *cfg,
u32 bpp;
int ret = 0;
- lcd_reset(par);
+ da8xx_fb_lcd_reset();
/* Calculate the divider */
lcd_calc_clk_divider(par);
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 01/20] video: da8xx-fb: fb_check_var enhancement
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
From: Afzal Mohammed <afzal@ti.com>
Check whether "struct fb_var_screeninfo" fields are sane, if not
update it to be within allowed limits.
If user sends down buggy "var" values, this will bring those within
allowable limits. And fb_set_par is not supposed to change "var"
values, fb_check_var has to ensure that values are proper.
Signed-off-by: Afzal Mohammed <afzal@ti.com>
Signed-off-by: Darren Etheridge <detheridge@ti.com>
---
drivers/video/da8xx-fb.c | 18 ++++++++++++++++++
1 files changed, 18 insertions(+), 0 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index 0810939..d00dd17 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -888,6 +888,9 @@ static int fb_check_var(struct fb_var_screeninfo *var,
struct fb_info *info)
{
int err = 0;
+ struct da8xx_fb_par *par = info->par;
+ int bpp = var->bits_per_pixel >> 3;
+ unsigned long line_size = var->xres_virtual * bpp;
if (var->bits_per_pixel > 16 && lcd_revision = LCD_VERSION_1)
return -EINVAL;
@@ -955,6 +958,21 @@ static int fb_check_var(struct fb_var_screeninfo *var,
var->green.msb_right = 0;
var->blue.msb_right = 0;
var->transp.msb_right = 0;
+
+ if (line_size * var->yres_virtual > par->vram_size)
+ var->yres_virtual = par->vram_size / line_size;
+
+ if (var->yres > var->yres_virtual)
+ var->yres = var->yres_virtual;
+
+ if (var->xres > var->xres_virtual)
+ var->xres = var->xres_virtual;
+
+ if (var->xres + var->xoffset > var->xres_virtual)
+ var->xoffset = var->xres_virtual - var->xres;
+ if (var->yres + var->yoffset > var->yres_virtual)
+ var->yoffset = var->yres_virtual - var->yres;
+
return err;
}
--
1.7.0.4
^ permalink raw reply related
* [PATCH v3 00/20] video: da8xx-fb: driver enhance to support TI am335x SoC
From: Darren Etheridge @ 2013-08-05 22:02 UTC (permalink / raw)
To: linux-fbdev
Changes in v3:
Address the patch authorship requirements
Pull out the DT changes into a separate series
Fix an issue where FB_MODE_HELPERS was not included in build
but is a dependency.
Include the devm_ changes and error reporting that Prabhakar Lad
had pushed a patch for,
A few more cosmetic changes
Add a patch to remove the use on inline from a number of functions
Changes in v2:
Addressing review comments from Tomi Valkeinen:
Dropped readl/writel patch as it is not necessary for non-cached,
non-buffered memory.
Many cosmetic changes to make code easier to understand
This is primarily a resend of a series of patches that were original
submitted to linux-fbdev back in January of 2013 for 3.8 by Afzal
Mohammed. I have rebased them on 3.10 and also made sure they
apply cleanly to the 'for-next' branch of linux-fbdev git.
The patches enable use of the current mainline da8xx-fb driver on the
TI AM335x SOC along with some bug fixes and cleanup.
The original patch series can be found here:
https://patchwork.kernel.org/project/linux-fbdev/list/?submitter9101
if you want to see the history.
Afzal Mohammed (11):
video: da8xx-fb: fb_check_var enhancement
video: da8xx-fb: simplify lcd_reset
video: da8xx-fb: use modedb helper to update var
video: da8xx-fb: remove unneeded "var" initialization
video: da8xx-fb: store current display information
video: da8xx-fb: store clk rate even if !CPUFREQ
video: da8xx-fb: store struct device *
video: da8xx-fb: report correct pixclock
video: da8xx-fb: enable sync lost intr for v2 ip
video: da8xx-fb: ensure non-null cfg in pdata
video: da8xx-fb: reorganize panel detection
Darren Etheridge (9):
video: da8xx-fb: pix clk and clk div handling cleanup
video: da8xx-fb: fb_set_par support
video: da8xx-fb: improve readability of code
video: da8xx-fb: fix 24bpp raster configuration
video: da8xx-fb: use devres
video: da8xx-fb: set upstream clock rate (if reqd)
video: da8xx-fb: make clock naming consistent
video: da8xx-fb: let compiler decide what to inline
video: da8xx-fb: adding am33xx as dependency
drivers/video/Kconfig | 8 +-
drivers/video/da8xx-fb.c | 352 +++++++++++++++++++++++++++-------------------
include/video/da8xx-fb.h | 5 +
3 files changed, 216 insertions(+), 149 deletions(-)
^ permalink raw reply
* Re: [PATCH] fbdev: suppress warning when assigning vga-save/restore base
From: H. Peter Anvin @ 2013-08-05 21:14 UTC (permalink / raw)
To: Ondrej Zajicek
Cc: David Miller, dh.herrmann, linux-fbdev, linux-kernel, plagnioj,
tomi.valkeinen, Ondrej Zary
In-Reply-To: <520012D4.7020701@zytor.com>
On 08/05/2013 02:02 PM, H. Peter Anvin wrote:
> On 08/05/2013 01:29 PM, Ondrej Zajicek wrote:
>>
>> How this could even work? AFAIK these cards have to be explicitly programmed
>> to enable MMIO (which was not done in the patches). These patches claim that
>> it is for multi-domain PCI. I would guess that vgabase is NULL in common
>> configurations but if it is non-NULL, it probably wouldn't work, unless
>> there is some hardware magic that transparently converts MMIO (from CPU PoV)
>> to port IO (from card/PCI PoV).
>>
>
> They presumably use iowrite/ioread, which use either I/O instructions or
> memory instructions depending on the address.
>
So the confusion really is in the iowrite interface, which can take
either a physical port address or a virtual memory address...
-hpa
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox