From: "Winkler, Tomas" <tomas.winkler@intel.com>
To: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: "gregkh@linuxfoundation.org" <gregkh@linuxfoundation.org>,
"arnd@arndb.de" <arnd@arndb.de>,
"alan@linux.intel.com" <alan@linux.intel.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Stanislaw Gruszka <sgruszka@redhat.com>
Subject: RE: [char-misc-next 07/15] mei: use wrietl/readl instead of io wrappers
Date: Tue, 4 Dec 2012 15:28:23 +0000 [thread overview]
Message-ID: <5B8DA87D05A7694D9FA63FD143655C1B01E9DED6@HASMSX106.ger.corp.intel.com> (raw)
In-Reply-To: <20121204143151.1cce530a@pyramind.ukuu.org.uk>
> >
> > /**
> > @@ -451,7 +451,7 @@ static inline u32 mei_reg_read(const struct
> > mei_device *dev, static inline void mei_reg_write(const struct mei_device
> *dev,
> > unsigned long offset, u32 value) {
> > - iowrite32(value, dev->mem_addr + offset);
> > + writel(value, dev->mem_addr + offset);
>
> ioremap should match readl/writel
> iomap iowrite32/ioread32
Thanks, I can replace pci_iomap with pci_ioremap_bar although in low level it is doing just the same.
> so you need to tweak the map/unmap if you do this.
>
> As to overhead. I'd love to see a measurement that can detect the
> difference. Do you have a benchmark that shows it ?
Don't have any numbers but it seems reasonable to me.
I did following this example
commit 05f5b97ee0013fefbd9139cf8c3eda5f2a88c04a
Author: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Wed Mar 7 09:52:26 2012 -0800
iwlwifi: use writeb,writel,readl directly
That change will save us some CPU cycles at run time. Having port-based
I/O seems to be not possible for PCIe devices.
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Thanks
Tomas
next prev parent reply other threads:[~2012-12-04 15:28 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-12-04 14:04 [char-misc-next 01/15] mei: drop redundant length paramter from mei_write_message function Tomas Winkler
2012-12-04 14:04 ` [char-misc-next 02/15] mei: use unified format for printing mei message header Tomas Winkler
2012-12-04 14:04 ` [char-misc-next 03/15] mei: move internal host clients ids to mei_dev.h from hw.h Tomas Winkler
2012-12-04 14:04 ` [char-misc-next 04/15] mei: extarct device dependent constants into hw-mei.h Tomas Winkler
2012-12-04 14:04 ` [char-misc-next 05/15] mei: inlude local headers after the system ones Tomas Winkler
2012-12-04 14:04 ` [char-misc-next 06/15] mei: kill not used BAR0 length and base variables Tomas Winkler
2012-12-04 14:04 ` [char-misc-next 07/15] mei: use wrietl/readl instead of io wrappers Tomas Winkler
2012-12-04 14:31 ` Alan Cox
2012-12-04 15:28 ` Winkler, Tomas [this message]
2012-12-04 15:37 ` Alan Cox
2012-12-04 16:02 ` Winkler, Tomas
2012-12-04 16:06 ` Alan Cox
2012-12-04 14:04 ` [char-misc-next 08/15] mei: mei_me_client is not hw API move to mei_dev.h Tomas Winkler
2012-12-04 14:04 ` [char-misc-next 09/15] mei: move hw dependent constructs to interface.c Tomas Winkler
2012-12-04 14:04 ` [char-misc-next 10/15] mei: move host bus message handling to hbm.c Tomas Winkler
2012-12-04 14:04 ` [char-misc-next 11/15] mei: drop non existent function prototype Tomas Winkler
2012-12-04 14:04 ` [char-misc-next 12/15] mei: simplify preparing client host bus messages Tomas Winkler
2012-12-04 14:04 ` [char-misc-next 13/15] mei: use structured buffer for write buffer Tomas Winkler
2012-12-04 14:04 ` [char-misc-next 14/15] mei: add common prefix to hbm function Tomas Winkler
2012-12-04 14:04 ` [char-misc-next 15/15] mei: move hbm responses from interrupt.c to hbm.c Tomas Winkler
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=5B8DA87D05A7694D9FA63FD143655C1B01E9DED6@HASMSX106.ger.corp.intel.com \
--to=tomas.winkler@intel.com \
--cc=alan@linux.intel.com \
--cc=alan@lxorguk.ukuu.org.uk \
--cc=arnd@arndb.de \
--cc=gregkh@linuxfoundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=sgruszka@redhat.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).