All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Howells <dhowells@redhat.com>
To: Mike Frysinger <vapier.adi@gmail.com>
Cc: dhowells@redhat.com, Paul Mundt <lethal@linux-sh.org>,
	Bernd Schmidt <bernds_cb1@t-online.de>,
	Jie Zhang <jie.zhang@analog.com>,
	Linux kernel mailing list <linux-kernel@vger.kernel.org>,
	uclinux-dist-devel <uclinux-dist-devel@blackfin.uclinux.org>
Subject: Re: avoiding duplicate icache flushing of shared maps on nommu
Date: Wed, 02 Dec 2009 14:15:30 +0000	[thread overview]
Message-ID: <15859.1259763330@redhat.com> (raw)
In-Reply-To: <8bd0f97a0911280740p24ad49bal64b924a427abfa39@mail.gmail.com>

Mike Frysinger <vapier.adi@gmail.com> wrote:

> (yes, this now does the icache flush while holding the
> nommu_region_sem, but i'm interested if the _idea_ is OK)

Yes...  But it's not quite as simple as you think.  The first mapping made of
a file could be PROT_READ only, in which case a second, executable mapping
made that shares it would not get flushed from the icache.

How about the attached patch?

David
---
From: Mike Frysinger <vapier.adi@gmail.com>
Subject: [PATCH] NOMMU: Avoiding duplicate icache flushes of shared maps

When working with FDPIC, there are many shared mappings of read-only code
regions between applications (the C library, applet packages like busybox,
etc.), but the current do_mmap_pgoff() function will issue an icache flush
whenever a VMA is added to an MM instead of only doing it when the map is
initially created.

The flush can instead be done when a region is first mmapped PROT_EXEC.  Note
that we may not rely on the first mapping of a region being executable - it's
possible for it to be PROT_READ only, so we have to remember whether we've
flushed the region or not, and then flush the entire region when a bit of it is
made executable.

Signed-off-by: David Howells <dhowells@redhat.com>
---

 include/linux/mm_types.h |    2 ++
 mm/nommu.c               |   11 ++++++++---
 2 files changed, 10 insertions(+), 3 deletions(-)


diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 84a524a..84d020b 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -123,6 +123,8 @@ struct vm_region {
 	struct file	*vm_file;	/* the backing file or NULL */
 
 	atomic_t	vm_usage;	/* region usage count */
+	bool		vm_icache_flushed : 1; /* true if the icache has been flushed for
+						* this region */
 };
 
 /*
diff --git a/mm/nommu.c b/mm/nommu.c
index 969392c..95159a1 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1353,10 +1353,15 @@ unsigned long do_mmap_pgoff(struct file *file,
 share:
 	add_vma_to_mm(current->mm, vma);
 
-	up_write(&nommu_region_sem);
+	/* we flush the region from the icache only when the first executable
+	 * mapping of it is made  */
+	if (vma->vm_flags & VM_EXEC && !region->vm_icache_flushed) {
+		flush_icache_range(region->vm_start,
+				   region->vm_end - region->vm_start);
+		region->vm_icache_flushed = true;
+	}
 
-	if (prot & PROT_EXEC)
-		flush_icache_range(result, result + len);
+	up_write(&nommu_region_sem);
 
 	kleave(" = %lx", result);
 	return result;


  parent reply	other threads:[~2009-12-02 14:16 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-11-28 15:40 avoiding duplicate icache flushing of shared maps on nommu Mike Frysinger
2009-11-28 18:53 ` Mike Frysinger
2009-11-30  3:18 ` Jie Zhang
2009-12-02 14:15 ` David Howells [this message]
2009-12-02 21:40   ` Mike Frysinger
2009-12-02 23:51     ` David Howells
2009-12-02 22:41   ` Mike Frysinger
2009-12-03 16:14     ` David Howells

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=15859.1259763330@redhat.com \
    --to=dhowells@redhat.com \
    --cc=bernds_cb1@t-online.de \
    --cc=jie.zhang@analog.com \
    --cc=lethal@linux-sh.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=uclinux-dist-devel@blackfin.uclinux.org \
    --cc=vapier.adi@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 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.