From: Yifeng Li <tomli@tomli.me> To: Sudip Mukherjee <sudipm.mukherjee@gmail.com>, Teddy Wang <teddy.wang@siliconmotion.com>, linux-kernel@vger.kernel.org Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>, linux-fbdev@vger.kernel.org, dri-devel@lists.freedesktop.org, Yifeng Li <tomli@tomli.me> Subject: [PATCH v2 0/7] implement 2D acceleration, minor cleanups, doc updates. Date: Fri, 22 Mar 2019 13:17:52 +0800 [thread overview] Message-ID: <20190322051759.15007-1-tomli@tomli.me> (raw) v2: - Also implement 2D acceleration for SM720. - Remove writel_relaxed() and an explicit memory barrier, on MIPS, PowerPC and x86, relaxed writes do not have additional performance, and complicates the code. - Document additional issues in the driver. NOTE: - This patchset should be applied after "[PATCH 0/8] fbdev: sm712fb: fix a series of lockups, crashes and gliches" (*), as it contains important fixes for issues in the original driver. - This patchset has been tested by the author for SM712 and SM720, on MIPS and x86 without problem. (*) https://marc.info/?l=linux-fbdev&m=155277512210375&w=2 Previously, in staging/sm7xxfb (now fbdev/sm712fb), 2D acceleration was implemented, but after its submission, a critical bug that causes total system hang was discovered, as a stopgap measure, 2D ops was completele removed in commit 3af805735a25 ("staging: sm7xx: remove the buggy 2D acceleration support") and never implemented again. It created a massive usability problem - on YeeLoong 8089, a notable MIPS platform which uses SM712 - even scrolling a single line of text on the console required an unaccelerated screen redraw, running "dmesg" typically takes 8-11 seconds, and absurdly, printf(), became a significant performance bottleneck that slows down GCC and "make", make the computer largely unusable. So I decided to take a look. Most of the my actual development was done in 2014 in a personal out-of-tree driver, I did not mainline it because 2D acceleration was not working properly in 24-bit color. I discovered the solution in early 2019 and now it's ready to be mainlined. This commit reimplements the 2D acceleration for sm712fb. Unlike the original implementation, which was messy and unnecessarily complicated by calling a 2D acceleration wrapper file with many unneeded functions, this is a minimum and (relatively) clean implementation. My tests have shown that running "dmesg" only takes 0.9 seconds, a performance boost of 950%. System hangs did not occur in my tests. Currently, 2D acceleration is only supported on little-endian CPUs, it's disabled on Big Endian systems as a safety measure, since I code for myself without any monetary or hardware support from any company or OEMs, I don't have the hardware and it's completely untested. I should be also to purchase a Big Endian test platform and add proper support soon. Also, thanks to Miodrag Vallat and other OpenBSD developers, this work would be impossible without their code, that served as a reference implementation for me. Finally, during the development and testing of 2D acceleration, many identified existing issues in driver in general have been documented. Yifeng Li (7): fbdev: sm712fb: use type "u8" for 8-bit I/O. fbdev: sm712fb: add 2D-related I/O headers and functions. fbdev: sm712fb: support 2D acceleration on SM712 w/ Little-Endian CPU. fbdev: sm712fb: add 32-bit color modes, drops some other modes. Documentation: fb: sm712fb: add information mainly about 2D. fbdev: sm712fb: Kconfig: add information about docs. MAINTAINERS: sm712fb: list myself as one maintainer. Documentation/fb/sm712fb.txt | 129 +++++++- MAINTAINERS | 1 + drivers/video/fbdev/Kconfig | 4 + drivers/video/fbdev/sm712.h | 109 ++++++- drivers/video/fbdev/sm712fb.c | 551 +++++++++++++++++++++++++--------- 5 files changed, 642 insertions(+), 152 deletions(-) -- 2.20.1
WARNING: multiple messages have this Message-ID (diff)
From: Yifeng Li <tomli@tomli.me> To: Sudip Mukherjee <sudipm.mukherjee@gmail.com>, Teddy Wang <teddy.wang@siliconmotion.com>, linux-kernel@vger.kernel.org Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>, linux-fbdev@vger.kernel.org, dri-devel@lists.freedesktop.org, Yifeng Li <tomli@tomli.me> Subject: [PATCH v2 0/7] implement 2D acceleration, minor cleanups, doc updates. Date: Fri, 22 Mar 2019 05:17:52 +0000 [thread overview] Message-ID: <20190322051759.15007-1-tomli@tomli.me> (raw) v2: - Also implement 2D acceleration for SM720. - Remove writel_relaxed() and an explicit memory barrier, on MIPS, PowerPC and x86, relaxed writes do not have additional performance, and complicates the code. - Document additional issues in the driver. NOTE: - This patchset should be applied after "[PATCH 0/8] fbdev: sm712fb: fix a series of lockups, crashes and gliches" (*), as it contains important fixes for issues in the original driver. - This patchset has been tested by the author for SM712 and SM720, on MIPS and x86 without problem. (*) https://marc.info/?l=linux-fbdev&m\x155277512210375&w=2 Previously, in staging/sm7xxfb (now fbdev/sm712fb), 2D acceleration was implemented, but after its submission, a critical bug that causes total system hang was discovered, as a stopgap measure, 2D ops was completele removed in commit 3af805735a25 ("staging: sm7xx: remove the buggy 2D acceleration support") and never implemented again. It created a massive usability problem - on YeeLoong 8089, a notable MIPS platform which uses SM712 - even scrolling a single line of text on the console required an unaccelerated screen redraw, running "dmesg" typically takes 8-11 seconds, and absurdly, printf(), became a significant performance bottleneck that slows down GCC and "make", make the computer largely unusable. So I decided to take a look. Most of the my actual development was done in 2014 in a personal out-of-tree driver, I did not mainline it because 2D acceleration was not working properly in 24-bit color. I discovered the solution in early 2019 and now it's ready to be mainlined. This commit reimplements the 2D acceleration for sm712fb. Unlike the original implementation, which was messy and unnecessarily complicated by calling a 2D acceleration wrapper file with many unneeded functions, this is a minimum and (relatively) clean implementation. My tests have shown that running "dmesg" only takes 0.9 seconds, a performance boost of 950%. System hangs did not occur in my tests. Currently, 2D acceleration is only supported on little-endian CPUs, it's disabled on Big Endian systems as a safety measure, since I code for myself without any monetary or hardware support from any company or OEMs, I don't have the hardware and it's completely untested. I should be also to purchase a Big Endian test platform and add proper support soon. Also, thanks to Miodrag Vallat and other OpenBSD developers, this work would be impossible without their code, that served as a reference implementation for me. Finally, during the development and testing of 2D acceleration, many identified existing issues in driver in general have been documented. Yifeng Li (7): fbdev: sm712fb: use type "u8" for 8-bit I/O. fbdev: sm712fb: add 2D-related I/O headers and functions. fbdev: sm712fb: support 2D acceleration on SM712 w/ Little-Endian CPU. fbdev: sm712fb: add 32-bit color modes, drops some other modes. Documentation: fb: sm712fb: add information mainly about 2D. fbdev: sm712fb: Kconfig: add information about docs. MAINTAINERS: sm712fb: list myself as one maintainer. Documentation/fb/sm712fb.txt | 129 +++++++- MAINTAINERS | 1 + drivers/video/fbdev/Kconfig | 4 + drivers/video/fbdev/sm712.h | 109 ++++++- drivers/video/fbdev/sm712fb.c | 551 +++++++++++++++++++++++++--------- 5 files changed, 642 insertions(+), 152 deletions(-) -- 2.20.1
next reply other threads:[~2019-03-22 5:18 UTC|newest] Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top 2019-03-22 5:17 Yifeng Li [this message] 2019-03-22 5:17 ` [PATCH v2 0/7] implement 2D acceleration, minor cleanups, doc updates Yifeng Li 2019-03-22 5:17 ` [PATCH v2 1/7] fbdev: sm712fb: use type "u8" for 8-bit I/O Yifeng Li 2019-03-22 5:17 ` Yifeng Li 2019-03-31 17:16 ` Sudip Mukherjee 2019-03-31 17:16 ` Sudip Mukherjee 2019-03-31 17:16 ` Sudip Mukherjee 2019-03-22 5:17 ` [PATCH v2 2/7] fbdev: sm712fb: add 2D-related I/O headers and functions Yifeng Li 2019-03-22 5:17 ` Yifeng Li 2019-03-31 17:25 ` Sudip Mukherjee 2019-03-31 17:25 ` Sudip Mukherjee 2019-04-01 16:04 ` Tom Li 2019-04-01 16:04 ` Tom Li 2019-03-22 5:17 ` [PATCH v2 3/7] fbdev: sm712fb: support 2D acceleration on SM712 w/ Little-Endian CPU Yifeng Li 2019-03-22 5:17 ` Yifeng Li 2019-03-31 18:09 ` Sudip Mukherjee 2019-03-31 18:09 ` Sudip Mukherjee 2019-04-01 16:26 ` Tom Li 2019-04-01 16:26 ` Tom Li 2019-04-02 20:53 ` Sudip Mukherjee 2019-04-02 20:53 ` Sudip Mukherjee 2019-03-22 5:17 ` [PATCH v2 4/7] fbdev: sm712fb: add 32-bit color modes, drops some other modes Yifeng Li 2019-03-22 5:17 ` Yifeng Li 2019-03-31 18:33 ` Sudip Mukherjee 2019-03-31 18:33 ` Sudip Mukherjee 2019-04-01 16:41 ` Tom Li 2019-04-01 16:41 ` Tom Li 2019-04-02 20:59 ` Sudip Mukherjee 2019-04-02 20:59 ` Sudip Mukherjee 2019-03-22 5:17 ` [PATCH v2 5/7] Documentation: fb: sm712fb: add information mainly about 2D Yifeng Li 2019-03-22 5:17 ` Yifeng Li 2019-03-31 18:54 ` Sudip Mukherjee 2019-03-31 18:54 ` Sudip Mukherjee 2019-03-31 18:54 ` Sudip Mukherjee 2019-04-01 17:30 ` Tom Li 2019-04-01 17:30 ` Tom Li 2019-04-02 21:03 ` Sudip Mukherjee 2019-04-02 21:03 ` Sudip Mukherjee 2019-04-02 21:03 ` Sudip Mukherjee 2019-03-22 5:17 ` [PATCH v2 6/7] fbdev: sm712fb: Kconfig: add information about docs Yifeng Li 2019-03-22 5:17 ` Yifeng Li 2019-03-31 19:01 ` Sudip Mukherjee 2019-03-31 19:01 ` Sudip Mukherjee 2019-04-01 17:33 ` Tom Li 2019-04-01 17:33 ` Tom Li 2019-03-22 5:17 ` [PATCH v2 7/7] MAINTAINERS: sm712fb: list myself as one maintainer Yifeng Li 2019-03-22 5:17 ` Yifeng Li 2019-03-31 19:08 ` Sudip Mukherjee 2019-03-31 19:08 ` Sudip Mukherjee 2019-03-31 19:08 ` Sudip Mukherjee 2019-04-01 17:41 ` Tom Li 2019-04-01 17:41 ` Tom Li 2019-04-02 21:09 ` Sudip Mukherjee 2019-04-02 21:09 ` Sudip Mukherjee 2019-04-02 21:09 ` Sudip Mukherjee 2019-04-03 13:53 ` Bartlomiej Zolnierkiewicz 2019-04-03 13:53 ` Bartlomiej Zolnierkiewicz 2019-04-05 22:11 ` Sudip Mukherjee 2019-04-05 22:11 ` Sudip Mukherjee 2019-04-05 22:11 ` Sudip Mukherjee
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=20190322051759.15007-1-tomli@tomli.me \ --to=tomli@tomli.me \ --cc=b.zolnierkie@samsung.com \ --cc=dri-devel@lists.freedesktop.org \ --cc=linux-fbdev@vger.kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=sudipm.mukherjee@gmail.com \ --cc=teddy.wang@siliconmotion.com \ /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: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.