From: "Marc Marí" <markmb@redhat.com>
To: linux-kernel@vger.kernel.org, qemu-devel@nongnu.org, seabios@seabios.org
Cc: "Mark Rutland" <mark.rutland@arm.com>,
"Rob Herring" <rob.herring@linaro.org>, Drew <drjones@redhat.com>,
"Arnd Bergmann" <arnd@arndb.de>,
devicetree@vger.kernel.org,
"Stefan Hajnoczi" <stefanha@gmail.com>,
"Alexander Graf" <agraf@suse.de>,
"Kevin O'Connor" <kevin@koconnor.net>,
"Gerd Hoffmann" <kraxel@redhat.com>,
"Marc Marí" <markmb@redhat.com>, Laszlo <lersek@redhat.com>
Subject: [Qemu-devel] QEMU fw_cfg DMA interface
Date: Mon, 31 Aug 2015 11:08:53 +0200 [thread overview]
Message-ID: <1441012133-8154-1-git-send-email-markmb@redhat.com> (raw)
Implementation of the FW CFG DMA interface.
When running a Linux guest on top of QEMU, using the -kernel options, this
is the timing improvement for x86:
QEMU commit 090d0bf and SeaBIOS commit 2fc20dc
QEMU startup time: .078
BIOS startup time: .060
Kernel setup time: .578
Total time: .716
QEMU with this patch series and SeaBIOS with this patch series
QEMU startup time: .080
BIOS startup time: .039
Kernel setup time: .002
Total time: .121
QEMU startup time is the time between the start and the first kvm_entry.
BIOS startup time is the time between the first kvm_entry and the start of
function do_boot, in SeaBIOS.
Kernel setup time is the time between the start of the function do_boot in
SeaBIOS and the jump to the Linux kernel.
As you can see, both the BIOS (because of ACPI tables and other configurations)
and the Linux kernel boot (because of the copy to memory) are greatly
improved with this new interface.
Also, this new interface is an addon to the old interface. Both interfaces
are compatible and interchangeable.
Changes from v1:
- Take into account order of fields in the FWCfgDmaAccess structure
- Check and change endianness of FWCfgDmaAccess fields
- Change order of fields in the FWCfgDmaAccess structure
- Add FW_CFG_DMA_CTL_SKIP feature for control field
- Split FW_CFG_SIZE in QEMU
- Make FW_CFG_ID a bitmap of features
- Add 64 bit address support for the transfer. Trigger when writing the low
address, and address is 0 by default and at the end of each transfer.
- Align ports and addresses.
- Preserve old fw_cfg_comb_valid behaviour in QEMU
- Update documentation to reflect all these changes
next reply other threads:[~2015-08-31 9:09 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-08-31 9:08 Marc Marí [this message]
2015-08-31 9:10 ` [Qemu-devel] [PATCH v2 0/5] fw_cfg DMA interface Marc Marí
2015-08-31 9:10 ` [Qemu-devel] [PATCH v2 1/5] fw_cfg: document fw_cfg_modify_iXX() update functions Marc Marí
2015-09-01 17:33 ` Peter Maydell
2015-09-01 17:45 ` Gabriel L. Somlo
2015-09-01 18:45 ` Peter Maydell
2015-09-01 19:13 ` Gabriel L. Somlo
2015-09-01 20:10 ` Peter Maydell
2015-09-01 20:27 ` Gabriel L. Somlo
2015-09-01 20:30 ` Peter Maydell
2015-09-02 8:08 ` Gerd Hoffmann
2015-09-02 9:21 ` Laszlo Ersek
2015-08-31 9:10 ` [Qemu-devel] [PATCH v2 2/5] fw_cfg DMA interface documentation Marc Marí
2015-08-31 15:36 ` Kevin O'Connor
2015-09-01 17:47 ` Peter Maydell
2015-09-01 17:56 ` Peter Maydell
2015-08-31 9:10 ` [Qemu-devel] [PATCH v2 3/5] Implement fw_cfg DMA interface Marc Marí
2015-08-31 15:58 ` Kevin O'Connor
2015-09-01 18:35 ` Peter Maydell
2015-08-31 9:10 ` [Qemu-devel] [PATCH v2 4/5] Enable fw_cfg DMA interface for ARM Marc Marí
2015-09-01 18:02 ` Peter Maydell
2015-08-31 9:10 ` [Qemu-devel] [PATCH v2 5/5] Enable fw_cfg DMA interface for x86 Marc Marí
-- strict thread matches above, loose matches on Subject: below --
2015-10-01 12:14 [Qemu-devel] QEMU fw_cfg DMA interface Marc Marí
2015-10-01 16:03 ` Eric Blake
2015-10-01 16:11 ` Eric Blake
2015-10-01 16:19 ` Laszlo Ersek
2015-10-01 16:17 ` Laszlo Ersek
2015-10-01 16:21 ` Eric Blake
2015-10-01 16:34 ` Laszlo Ersek
2015-09-18 8:58 Marc Marí
2015-08-06 11:00 Marc Marí
2015-08-06 12:27 ` Stefan Hajnoczi
2015-08-06 12:37 ` Marc Marí
2015-08-06 12:40 ` Stefan Hajnoczi
2015-08-06 15:30 ` Kevin O'Connor
2015-08-06 15:53 ` Marc Marí
2015-08-07 4:30 ` Kevin O'Connor
2015-08-17 22:08 ` Gerd Hoffmann
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=1441012133-8154-1-git-send-email-markmb@redhat.com \
--to=markmb@redhat.com \
--cc=agraf@suse.de \
--cc=arnd@arndb.de \
--cc=devicetree@vger.kernel.org \
--cc=drjones@redhat.com \
--cc=kevin@koconnor.net \
--cc=kraxel@redhat.com \
--cc=lersek@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=qemu-devel@nongnu.org \
--cc=rob.herring@linaro.org \
--cc=seabios@seabios.org \
--cc=stefanha@gmail.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: 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).