lkml.org 
[lkml]   [2009]   [Apr]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [PATCH] [13/16] POISON: The high level memory error handler in the VM
From
Date
On Tue, 2009-04-07 at 17:10 +0200, Andi Kleen wrote:
> This patch adds the high level memory handler that poisons pages.
> It is portable code and lives in mm/memory-failure.c

I think this is an important feature, thanks for doing all this work
Andi.

> Index: linux/mm/memory-failure.c
> ===================================================================
> --- /dev/null 1970-01-01 00:00:00.000000000 +0000
> +++ linux/mm/memory-failure.c 2009-04-07 16:39:39.000000000 +0200
> +
> +/*
> + * Clean (or cleaned) page cache page.
> + */
> +static int me_pagecache_clean(struct page *p)
> +{
> + struct address_space *mapping;
> +
> + if (PagePrivate(p))
> + do_invalidatepage(p, 0);
> + mapping = page_mapping(p);
> + if (mapping) {
> + if (!remove_mapping(mapping, p))
> + return FAILED;
> + }
> + return RECOVERED;
> +}
> +
> +/*
> + * Dirty cache page page
> + * Issues: when the error hit a hole page the error is not properly
> + * propagated.
> + */
> +static int me_pagecache_dirty(struct page *p)
> +{
> + struct address_space *mapping = page_mapping(p);
> +
> + SetPageError(p);
> + /* TBD: print more information about the file. */
> + printk(KERN_ERR "MCE: Hardware memory corruption on dirty file page: write error\n");
> + if (mapping) {
> + /* CHECKME: does that report the error in all cases? */
> + mapping_set_error(mapping, EIO);
> + }
> + if (PagePrivate(p)) {
> + if (try_to_release_page(p, GFP_KERNEL)) {

So, try_to_release_page returns 1 when it works. I know this only
because I have to read it every time to remember ;)

try_to_release_page is also very likely to fail if the page is dirty or
under writeback. At the end of the day, we'll probably need a call into
the FS to tell it a given page isn't coming back, and to clean it at all
cost.

invalidatepage is close, but ext3/reiserfs will keep the buffer heads
and let the page->mapping go to null in an ugly data=ordered corner
case. The buffer heads pin the page and it won't be freed until the IO
is done.

-chris




\
 
 \ /
  Last update: 2009-04-08 19:11    [from the cache]
©2003-2011 Jasper Spaans