2007-01-22 16:47:22

by Hugh Dickins

[permalink] [raw]
Subject: revert "Fix up" of mmap_kmem

Please revert 2.6.19's 99a10a60ba9bedcf5d70ef81414d3e03816afa3f (shown
below) for 2.6.20. Nadia Derbey has reported that mmap of /dev/kmem no
longer works with the kernel virtual address as offset, and Franck has
confirmed that his patch came from a misunderstanding of what an offset
means to /dev/kmem - whereas his patch description seems to say that he
was correcting the offset on a few plaforms, there was no such problem
to correct, and his patch was in fact changing its API on all platforms.

Suggested-by: Hugh Dickins <[email protected]>
---
From: Franck Bui-Huu <[email protected]>
Date: Thu, 12 Oct 2006 19:06:33 +0000 (+0200)
Subject: [PATCH] Fix up mmap_kmem
X-Git-Tag: v2.6.19-rc2^0~6
X-Git-Url: http://127.0.0.1:1234/?p=.git;a=commitdiff_plain;h=99a10a60ba9bedcf5d70ef81414d3e03816afa3f;hp=a5344a9555fffd045218aced89afd6ca0f884e10

[PATCH] Fix up mmap_kmem

vma->vm_pgoff is an pfn _offset_ relatif to the begining
of the memory start. The previous code was doing at first:

vma->vm_pgoff << PAGE_SHIFT

which results into a wrong physical address since some
platforms have a physical mem start that can be different
from 0. After that the previous call __pa() on this
wrong physical address, however __pa() is used to convert
a _virtual_ address into a physical one.

This patch rewrites this convertion. It calculates the
pfn of PAGE_OFFSET which is the pfn of the mem start
then it adds the vma->vm_pgoff to it.

It also uses virt_to_phys() instead of __pa() since the
latter shouldn't be used by drivers.

Signed-off-by: Franck Bui-Huu <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
---

diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 6511012..a89cb52 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -292,8 +292,8 @@ static int mmap_kmem(struct file * file,
{
unsigned long pfn;

- /* Turn a kernel-virtual address into a physical page frame */
- pfn = __pa((u64)vma->vm_pgoff << PAGE_SHIFT) >> PAGE_SHIFT;
+ /* Turn a pfn offset into an absolute pfn */
+ pfn = PFN_DOWN(virt_to_phys((void *)PAGE_OFFSET)) + vma->vm_pgoff;

/*
* RED-PEN: on some architectures there is more mapped memory


Subject: Re: revert "Fix up" of mmap_kmem

On 1/22/07, Hugh Dickins <[email protected]> wrote:
> Please revert 2.6.19's 99a10a60ba9bedcf5d70ef81414d3e03816afa3f (shown
> below) for 2.6.20. Nadia Derbey has reported that mmap of /dev/kmem no
> longer works with the kernel virtual address as offset, and Franck has
> confirmed that his patch came from a misunderstanding of what an offset
> means to /dev/kmem - whereas his patch description seems to say that he
> was correcting the offset on a few plaforms, there was no such problem
> to correct, and his patch was in fact changing its API on all platforms.
>

Yes I confirm, sorry for the confusion.
--
Franck