Re: 2.6.4-mm2

[Andrew Morton]

Chris Mason <mason@xxxxxxxx> wrote:
>
> On Wed, 2004-03-17 at 18:51, Andrew Morton wrote:
> > Chris Mason <mason@xxxxxxxx> wrote:
> > >
> > > Looks good, but I'm still having problems convincing pagevec_lookup_tag
> > > to return anything other than 0 when called from
> > > wait_on_page_writeback_range (ext2, ext3, reiserfs).  Any ideas?
> > 
> > This might help.  I'm testing this path now, so there may be more changes..
> > 
> 
> Well, that's certainly a lot slower ;-)

For once, that's good.

> I've got a direct_read_under
> round going.  While you're at it, there's one more bug.
> 
> The wbc struct used by filemap_fdatawrite doesn't initialize
> wbc.nonblocking to zero.  stack magic might give us a 1 there, leading
> to an early exit from mpage_writepages even when doing a WB_SYNC_ALL.

I hope not.

static int __filemap_fdatawrite(struct address_space *mapping, int sync_mode)
{
	int ret;
	struct writeback_control wbc = {
		.sync_mode = sync_mode,
		.nr_to_write = mapping->nrpages * 2,
	};

When you initialise some of the structure in this way the compiler will
zero out all the other fields.

(gets worried)

yup.


struct thing {
	int a;
	int b[1000];
};

foo()
{
	int a[1000];

	memset(a, 1, sizeof(a));
}

bar()
{
	struct thing t = {
		.a = 1
	};
	int i;

	for (i = 0; i < 1000; i++) {
		if (t.b[i]) {
			printf("bad\n");
			return;
		}
	}
}

zot()
{
	struct thing t;
	int i;

	for (i = 0; i < 1000; i++) {
		if (t.b[i]) {
			printf("good\n");
			return;
		}
	}
}

main()
{
	foo();
	bar();
	foo();
	zot();
}


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/