From: "Jiang, Dave" <dave.jiang@intel.com>
To: "cem@FreeBSD.org" <cem@FreeBSD.org>
Cc: "allen.hubbe@emc.com" <allen.hubbe@emc.com>,
"jdmason@kudzu.us" <jdmason@kudzu.us>,
"linux-ntb@googlegroups.com" <linux-ntb@googlegroups.com>
Subject: Re: [PATCH] NTB: Clear property bits in BAR value
Date: Thu, 19 Nov 2015 20:54:46 +0000 [thread overview]
Message-ID: <1447966484.83864.268.camel@intel.com> (raw)
In-Reply-To: <CAG6CVpXqKnRfOR_WKmrnScB0t1w7nGOFsgfYPGFrYh9Hv4LFvg@mail.gmail.com>
On Thu, 2015-11-19 at 12:50 -0800, Conrad Meyer wrote:
> Looks fine to me. Isn't unsigned long 64 bits on Linux amd64?
> (Should NTB_BAR_MASK_32 just be ~(0xfu)?)
Good catch! I'll fix that.
>
> Best,
> Conrad
>
> On Thu, Nov 19, 2015 at 12:47 PM, Dave Jiang <dave.jiang@intel.com>
> wrote:
> > The lower bits read from a BAR register will contain property bits
> > that we do not care about. Clear those so that we can use the BAR
> > values for limit and xlat registers.
> >
> > Reported-by: Conrad Meyer <cem@freebsd.org>
> > Signed-off-by: Dave Jiang <dave.jiang@intel.com>
> > ---
> > drivers/ntb/hw/intel/ntb_hw_intel.c | 4 ++--
> > drivers/ntb/hw/intel/ntb_hw_intel.h | 3 +++
> > 2 files changed, 5 insertions(+), 2 deletions(-)
> >
> > diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.c
> > b/drivers/ntb/hw/intel/ntb_hw_intel.c
> > index a198f82..40d04ef 100644
> > --- a/drivers/ntb/hw/intel/ntb_hw_intel.c
> > +++ b/drivers/ntb/hw/intel/ntb_hw_intel.c
> > @@ -875,7 +875,7 @@ static int intel_ntb_mw_set_trans(struct
> > ntb_dev *ntb, int idx,
> > limit_reg = bar2_off(ndev->xlat_reg->bar2_limit, bar);
> >
> > if (bar < 4 || !ndev->bar4_split) {
> > - base = ioread64(mmio + base_reg);
> > + base = ioread64(mmio + base_reg) & NTB_BAR_MASK_64;
> >
> > /* Set the limit if supported, if size is not
> > mw_size */
> > if (limit_reg && size != mw_size)
> > @@ -906,7 +906,7 @@ static int intel_ntb_mw_set_trans(struct
> > ntb_dev *ntb, int idx,
> > if ((addr + size) & (~0ull << 32))
> > return -EINVAL;
> >
> > - base = ioread32(mmio + base_reg);
> > + base = ioread32(mmio + base_reg) & NTB_BAR_MASK_32;
> >
> > /* Set the limit if supported, if size is not
> > mw_size */
> > if (limit_reg && size != mw_size)
> > diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.h
> > b/drivers/ntb/hw/intel/ntb_hw_intel.h
> > index 2eb4add..a257c7c 100644
> > --- a/drivers/ntb/hw/intel/ntb_hw_intel.h
> > +++ b/drivers/ntb/hw/intel/ntb_hw_intel.h
> > @@ -245,6 +245,9 @@
> > #define NTB_UNSAFE_DB BIT_ULL(0)
> > #define NTB_UNSAFE_SPAD BIT_ULL(1)
> >
> > +#define NTB_BAR_MASK_64 ~(0xfull)
> > +#define NTB_BAR_MASK_32 ~(0xful)
> > +
> > struct intel_ntb_dev;
> >
> > struct intel_ntb_reg {
> >
>
prev parent reply other threads:[~2015-11-19 20:54 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-11-19 20:47 [PATCH] NTB: Clear property bits in BAR value Dave Jiang
2015-11-19 20:50 ` Conrad Meyer
2015-11-19 20:54 ` Jiang, Dave [this message]
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=1447966484.83864.268.camel@intel.com \
--to=dave.jiang@intel.com \
--cc=allen.hubbe@emc.com \
--cc=cem@FreeBSD.org \
--cc=jdmason@kudzu.us \
--cc=linux-ntb@googlegroups.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