From: "Manjunathappa, Prakash" <prakash.pm@ti.com>
To: linux-fbdev@vger.kernel.org
Subject: [PATCH RESEND] video: da8xx-fb: fix flicker due to 1 frame delay in updated frame
Date: Wed, 18 Jul 2012 15:43:56 +0000 [thread overview]
Message-ID: <1342625516-7185-1-git-send-email-prakash.pm@ti.com> (raw)
Flicker/tearing effect is observed with current FB driver.
Issue is because of 2 active DMA channels ping ponging among them
along with usage of 2 DDR ping pong buffers in driver. Application
unaware of active DMA channel keeps updating frame being displayed,
this leads to tearing effect.
Below steps describes the issue:
1)Initially assume both buffers FB0 and FB1 are programmed for buffer-0.
2)On EOF0: Program FB0 for buffer-1, indicate(wake up) application
to fill up buffer-0. As FB1 is active and continues to DMA buffer-0
(which is being filled), leading to tearing/flickering issue.
3)On EOF1: Program FB1 for buffer-0, indicate(wake up) application to
fill up buffer-1. As FB0 is active and continues to DMA buffer-1(which
is being filled), leading to tearing/flickering issue.
4)On EOF0: Program FB0 for buffer-1, indicate(wake up) application to
fill up buffer-0. As FB1 is active and continues to DMA buffer-0(which is
being filled), leading to tearing/flickering issue.
...
Above steps depict that issue is because of 1 frame delay in frame
panned by application.
Patch fixes the issue by keeping track free DMA channel and configures
it in drivers PAN callback so that panned frame from application gets
displayed in next frame period.
Wiki below describes the issue in detail and it also has link to
application with which issue can be reproduced.
http://processors.wiki.ti.com/index.php/DA8xx_LCDC_Linux_FB_FAQs
Signed-off-by: Nellutla, Aditya <aditya.n@ti.com>
Signed-off-by: Manjunathappa, Prakash <prakash.pm@ti.com>
---
Resending as my earlier patch seems like not reached fbdev mailing list.
drivers/video/da8xx-fb.c | 30 ++++++++++++++++++++++++++++++
1 files changed, 30 insertions(+), 0 deletions(-)
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index e9d2f6e..183366d 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -30,6 +30,7 @@
#include <linux/clk.h>
#include <linux/cpufreq.h>
#include <linux/console.h>
+#include <linux/spinlock.h>
#include <linux/slab.h>
#include <video/da8xx-fb.h>
#include <asm/div64.h>
@@ -161,6 +162,13 @@ struct da8xx_fb_par {
wait_queue_head_t vsync_wait;
int vsync_flag;
int vsync_timeout;
+ spinlock_t lock_for_chan_update;
+
+ /*
+ * LCDC has 2 ping pong DMA channels, channel 0
+ * and channel 1.
+ */
+ unsigned int which_dma_channel_done;
#ifdef CONFIG_CPU_FREQ
struct notifier_block freq_transition;
unsigned int lcd_fck_rate;
@@ -741,6 +749,7 @@ static irqreturn_t lcdc_irq_handler_rev02(int irq, void *arg)
lcdc_write(stat, LCD_MASKED_STAT_REG);
if (stat & LCD_END_OF_FRAME0) {
+ par->which_dma_channel_done = 0;
lcdc_write(par->dma_start,
LCD_DMA_FRM_BUF_BASE_ADDR_0_REG);
lcdc_write(par->dma_end,
@@ -750,6 +759,7 @@ static irqreturn_t lcdc_irq_handler_rev02(int irq, void *arg)
}
if (stat & LCD_END_OF_FRAME1) {
+ par->which_dma_channel_done = 1;
lcdc_write(par->dma_start,
LCD_DMA_FRM_BUF_BASE_ADDR_1_REG);
lcdc_write(par->dma_end,
@@ -796,6 +806,7 @@ static irqreturn_t lcdc_irq_handler_rev01(int irq, void *arg)
lcdc_write(stat, LCD_STAT_REG);
if (stat & LCD_END_OF_FRAME0) {
+ par->which_dma_channel_done = 0;
lcdc_write(par->dma_start,
LCD_DMA_FRM_BUF_BASE_ADDR_0_REG);
lcdc_write(par->dma_end,
@@ -805,6 +816,7 @@ static irqreturn_t lcdc_irq_handler_rev01(int irq, void *arg)
}
if (stat & LCD_END_OF_FRAME1) {
+ par->which_dma_channel_done = 1;
lcdc_write(par->dma_start,
LCD_DMA_FRM_BUF_BASE_ADDR_1_REG);
lcdc_write(par->dma_end,
@@ -1050,6 +1062,7 @@ static int da8xx_pan_display(struct fb_var_screeninfo *var,
struct fb_fix_screeninfo *fix = &fbi->fix;
unsigned int end;
unsigned int start;
+ unsigned long irq_flags;
if (var->xoffset != fbi->var.xoffset ||
var->yoffset != fbi->var.yoffset) {
@@ -1067,6 +1080,21 @@ static int da8xx_pan_display(struct fb_var_screeninfo *var,
end = start + fbi->var.yres * fix->line_length - 1;
par->dma_start = start;
par->dma_end = end;
+ spin_lock_irqsave(&par->lock_for_chan_update,
+ irq_flags);
+ if (par->which_dma_channel_done = 0) {
+ 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);
+ } else if (par->which_dma_channel_done = 1) {
+ 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);
+ }
+ spin_unlock_irqrestore(&par->lock_for_chan_update,
+ irq_flags);
}
}
@@ -1294,6 +1322,8 @@ static int __devinit fb_probe(struct platform_device *device)
/* initialize the vsync wait queue */
init_waitqueue_head(&par->vsync_wait);
par->vsync_timeout = HZ / 5;
+ par->which_dma_channel_done = -1;
+ spin_lock_init(&par->lock_for_chan_update);
/* Register the Frame Buffer */
if (register_framebuffer(da8xx_fb_info) < 0) {
--
1.7.1
next reply other threads:[~2012-07-18 15:43 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-07-18 15:43 Manjunathappa, Prakash [this message]
2012-07-29 21:06 ` [PATCH RESEND] video: da8xx-fb: fix flicker due to 1 frame delay in updated frame Florian Tobias Schandinat
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1342625516-7185-1-git-send-email-prakash.pm@ti.com \
--to=prakash.pm@ti.com \
--cc=linux-fbdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).