All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ralf Baechle <ralf@linux-mips.org>
To: Lars Persson <lars.persson@axis.com>
Cc: Paul Burton <paul.burton@imgtec.com>,
	"Steven J. Hill" <sjhill@realitydiluted.com>,
	"linux-mips@linux-mips.org" <linux-mips@linux-mips.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 1/4] MIPS: Flush dcache for flush_kernel_dcache_page
Date: Tue, 29 Mar 2016 10:29:12 +0200	[thread overview]
Message-ID: <20160329082911.GC11282@linux-mips.org> (raw)
In-Reply-To: <B1BD883F-CC3D-4C02-9C5C-350DB487329B@axis.com>

On Fri, Mar 04, 2016 at 03:09:00PM +0000, Lars Persson wrote:

> > 1 mars 2016 kl. 03:38 Paul Burton <paul.burton@imgtec.com>:
> > 
> > The flush_kernel_dcache_page function was previously essentially a nop.
> > This is incorrect for MIPS, where if a page has been modified & either
> > it aliases or it's executable & the icache doesn't fill from dcache then
> > the content needs to be written back from dcache to the next level of
> > the cache hierarchy (which is shared with the icache).
> > 
> > Implement this by simply calling flush_dcache_page, treating this
> > kmapped cache flush function (flush_kernel_dcache_page) exactly the same
> > as its non-kmapped counterpart (flush_dcache_page).
> > 
> > Signed-off-by: Paul Burton <paul.burton@imgtec.com>
> > ---
> > 
> > arch/mips/include/asm/cacheflush.h | 1 +
> > 1 file changed, 1 insertion(+)
> > 
> > diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h
> > index 723229f..7e9f468 100644
> > --- a/arch/mips/include/asm/cacheflush.h
> > +++ b/arch/mips/include/asm/cacheflush.h
> > @@ -132,6 +132,7 @@ static inline void kunmap_noncoherent(void)
> > static inline void flush_kernel_dcache_page(struct page *page)
> > {
> >    BUG_ON(cpu_has_dc_aliases && PageHighMem(page));
> > +    flush_dcache_page(page);
> 
> Should we use instead __flush_dcache_page() that flushes immediately for mapped pages ? Steven J Hill's old patch set for highmem had done it like this.

Delayed flushing should be ok for lowmem where each page has a permanent
virtual address.  With highmem the temporary address assigned by the kmap_*
function may change so the flush needs to be performed immediately.
Special case highmem without cache aliases - the exact virtual address
doesn't matter, so this should be fine.

Cache flushes are expensive so delaying if possible is always a good thing.

Steven's patches afair were trying to tackle the highmem with aliases case
so an immediately flush was required.

  Ralf

  reply	other threads:[~2016-03-29  8:29 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-03-01  2:37 [PATCH 0/4] MIPS cache & highmem fixes Paul Burton
2016-03-01  2:37 ` Paul Burton
2016-03-01  2:37 ` [PATCH 1/4] MIPS: Flush dcache for flush_kernel_dcache_page Paul Burton
2016-03-01  2:37   ` Paul Burton
2016-03-04 15:09   ` Lars Persson
2016-03-29  8:29     ` Ralf Baechle [this message]
2016-03-01  2:37 ` [PATCH 2/4] MIPS: Flush highmem pages in __flush_dcache_page Paul Burton
2016-03-01  2:37   ` Paul Burton
2016-03-29  8:35   ` Ralf Baechle
2016-03-29  8:55     ` Paul Burton
2016-03-29  8:55       ` Paul Burton
2016-03-01  2:37 ` [PATCH 3/4] MIPS: Handle highmem pages in __update_cache Paul Burton
2016-03-01  2:37   ` Paul Burton
2016-03-29  8:39   ` Ralf Baechle
2016-03-01  2:37 ` [PATCH 4/4] MIPS: Sync icache & dcache in set_pte_at Paul Burton
2016-03-01  2:37   ` Paul Burton
2016-03-01  9:44   ` Lars Persson
2016-03-01  9:44     ` Lars Persson
2016-03-01 17:13   ` David Daney
2016-03-01 17:13     ` David Daney
2016-03-01 17:19     ` Paul Burton
2016-03-01 17:19       ` Paul Burton
2016-03-02 14:12       ` Ralf Baechle
2016-03-02 14:24         ` Paul Burton
2016-03-02 14:24           ` Paul Burton
2016-03-04 17:43       ` David Daney
2016-03-04 17:43         ` David Daney
2016-03-04 17:47         ` Paul Burton
2016-03-04 17:47           ` Paul Burton
2016-03-03  3:03   ` [4/4] " Leonid Yegoshin
2016-03-03  3:03     ` Leonid Yegoshin
2016-03-04 10:37     ` Paul Burton
2016-03-04 10:37       ` Paul Burton
2016-03-04 15:20       ` Lars Persson
2016-03-04 21:01       ` Leonid Yegoshin
2016-03-04 21:01         ` Leonid Yegoshin
2016-03-04 21:21         ` Leonid Yegoshin
2016-03-04 21:21           ` Leonid Yegoshin
2016-03-05  1:06         ` Leonid Yegoshin
2016-03-05  1:06           ` Leonid Yegoshin
2016-03-04 19:02   ` [PATCH 4/4] " Lars Persson
2016-03-05  0:21     ` Paul Burton
2016-03-05  0:27       ` Paul Burton
2016-03-02 11:39 ` [PATCH 0/4] MIPS cache & highmem fixes Harvey Hunt
2016-03-02 11:39   ` Harvey Hunt

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=20160329082911.GC11282@linux-mips.org \
    --to=ralf@linux-mips.org \
    --cc=lars.persson@axis.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mips@linux-mips.org \
    --cc=paul.burton@imgtec.com \
    --cc=sjhill@realitydiluted.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 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.