[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAE9FiQUPJixU2e0T2DWJN1Uz5zLYJPzWZRryqG388d7A1Me6LQ@mail.gmail.com>
Date: Fri, 4 Jan 2013 14:34:28 -0800
From: Yinghai Lu <yinghai@...nel.org>
To: Shuah Khan <shuahkhan@...il.com>
Cc: Thomas Gleixner <tglx@...utronix.de>, Ingo Molnar <mingo@...e.hu>,
"H. Peter Anvin" <hpa@...or.com>,
"Eric W. Biederman" <ebiederm@...ssion.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Borislav Petkov <bp@...en8.de>, Jan Kiszka <jan.kiszka@....de>,
Jason Wessel <jason.wessel@...driver.com>,
linux-kernel@...r.kernel.org,
Konrad Rzeszutek Wilk <konrad.wilk@...cle.com>,
Joerg Roedel <joro@...tes.org>
Subject: Re: [PATCH v7u1 26/31] x86: Don't enable swiotlb if there is not
enough ram for it
On Fri, Jan 4, 2013 at 2:26 PM, Shuah Khan <shuahkhan@...il.com> wrote:
> However, I think regression on existing behavior with a
> panic is a bit of a big hammer. Thie change causes panic on systems
> even when kdump is not enabled, if I understand it correctly.
I don't think so.
+static bool __init enough_mem_for_swiotlb(void)
+{
+ /* do we have less than 1M RAM under 4G ? */
+ return memblock_mem_size(1ULL<<(32-PAGE_SHIFT)) > (1ULL<<20);
+}
enough_mem_for_swiotlb could return false for them?
and
int __init pci_swiotlb_detect_override(void)
{
- int use_swiotlb = swiotlb | swiotlb_force;
-
if (swiotlb_force)
swiotlb = 1;
+ else if (!enough_mem_for_swiotlb())
+ swiotlb = 0;
- return use_swiotlb;
+ return swiotlb;
}
it only disable swiotlb when there is less 1M mem under 4G.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists