From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
To: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Yinghai Lu <yinghai@kernel.org>,
Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@elte.hu>,
"H. Peter Anvin" <hpa@zytor.com>,
Andrew Morton <akpm@linux-foundation.org>,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH v7 24/27] x86: Add swiotlb force off support
Date: Fri, 21 Dec 2012 22:10:19 -0500 [thread overview]
Message-ID: <20121222031019.GA4120@phenom.dumpdata.com> (raw)
In-Reply-To: <87bodmhkns.fsf@xmission.com>
On Fri, Dec 21, 2012 at 06:42:47PM -0800, Eric W. Biederman wrote:
> Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> writes:
>
> > On Mon, Dec 17, 2012 at 11:15:56PM -0800, Yinghai Lu wrote:
> >> So use could disable swiotlb from command line, even swiotlb support
> >> is compiled in. Just like we have intel_iommu=on and intel_iommu=off.
> >
> > You really need to spell out why this is useful.
>
> YH why can't we safely autodetect that the swiotlb is unusable when
> there is no memory below 4G free?
I am not sure what 'YH' stands for (Yeah?).
However we could turn SWIOTLB off altogether if it cannot allocate
_some_ memory. It could try first 64MB, then 32MB, lastly 16MB. And
if all that fails - print a nice warning and continue on.
Later in the late initialization phase, when pci_swiotlb_late_init
is called - it can then figure out whether 'iommu' has been set
and it iself was never able to allocate. At that point it can try
the dynamic allocation (swiotlb_late_init_with_default_size)
... and if that fails give up and panic.
next prev parent reply other threads:[~2012-12-22 3:10 UTC|newest]
Thread overview: 78+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-12-18 7:15 [PATCH v7 00/27] x86, boot, 64bit: Add support for loading ramdisk and bzImage above 4G Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 01/27] x86, mm: Fix page table early allocation offset checking Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 02/27] x86, mm: make pgd next calculation consistent with pud/pmd Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 03/27] x86, realmode: set real_mode permissions early Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 04/27] x86, realmode: use init_level4_pgt to set trapmoline_pgt directly Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 05/27] x86, realmode: Separate real_mode reserve and setup Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 06/27] x86, 64bit: early #PF handler set page table Yinghai Lu
2012-12-18 20:43 ` Yinghai Lu
2012-12-18 20:49 ` H. Peter Anvin
2012-12-18 20:55 ` Yinghai Lu
2012-12-18 21:07 ` H. Peter Anvin
2012-12-20 16:56 ` Yinghai Lu
2012-12-25 0:16 ` H. Peter Anvin
2012-12-25 4:04 ` Yinghai Lu
2012-12-25 11:20 ` Borislav Petkov
2012-12-25 20:51 ` Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 07/27] x86, 64bit: Print init kernel lowmap correctly Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 08/27] x86: Merge early_reserve_initrd for 32bit and 64bit Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 09/27] x86: add get_ramdisk_image/size() Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 10/27] x86, boot: add get_cmd_line_ptr() Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 11/27] x86, boot: move checking of cmd_line_ptr out of common path Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 12/27] x86, boot: pass cmd_line_ptr with unsigned long Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 13/27] x86, boot: move verify_cpu.S and no_longmode after 0x200 Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 14/27] x86, boot: Move lldt/ltr out of 64bit code section Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 15/27] x86, kexec: remove 1024G limitation for kexec buffer on 64bit Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 16/27] x86, kexec: set ident mapping for kernel that is above max_pfn Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 17/27] x86, kexec: Merge ident_mapping_init and init_level4_page Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 18/27] x86, kexec: only set ident mapping for ram Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 19/27] x86, boot: add fields to support load bzImage and ramdisk above 4G Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 20/27] x86, boot: update comments about entries for 64bit image Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 21/27] x86, boot: Not need to check setup_header version Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 22/27] mm: Add alloc_bootmem_low_pages_nopanic() Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 23/27] x86: Don't panic if can not alloc buffer for swiotlb Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 24/27] x86: Add swiotlb force off support Yinghai Lu
2012-12-22 2:37 ` Konrad Rzeszutek Wilk
2012-12-22 2:42 ` Eric W. Biederman
2012-12-22 3:10 ` Konrad Rzeszutek Wilk [this message]
2012-12-22 3:23 ` Eric W. Biederman
2012-12-22 3:25 ` H. Peter Anvin
2012-12-22 5:11 ` Yinghai Lu
2012-12-24 23:34 ` H. Peter Anvin
2012-12-24 23:55 ` Yinghai Lu
2012-12-22 13:21 ` Konrad Rzeszutek Wilk
2012-12-22 5:10 ` Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 25/27] x86, kdump: remove crashkernel range find limit for 64bit Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 26/27] x86: add Crash kernel low reservation Yinghai Lu
2012-12-19 17:22 ` Borislav Petkov
2012-12-19 17:36 ` Yinghai Lu
2012-12-18 7:15 ` [PATCH v7 27/27] x86: Merge early kernel reserve for 32bit and 64bit Yinghai Lu
2012-12-18 22:43 ` [PATCH v7 00/27] x86, boot, 64bit: Add support for loading ramdisk and bzImage above 4G Borislav Petkov
2012-12-18 23:08 ` Yinghai Lu
2012-12-18 23:22 ` Borislav Petkov
2012-12-22 2:42 ` Konrad Rzeszutek Wilk
2012-12-22 3:01 ` H. Peter Anvin
2012-12-22 13:24 ` Konrad Rzeszutek Wilk
2012-12-23 7:29 ` Yinghai Lu
2012-12-23 14:33 ` H. Peter Anvin
2012-12-23 18:00 ` Yinghai Lu
2012-12-23 18:45 ` Borislav Petkov
2012-12-24 4:54 ` H. Peter Anvin
2012-12-24 10:04 ` Borislav Petkov
2012-12-24 18:44 ` Yinghai Lu
2012-12-24 4:55 ` H. Peter Anvin
2012-12-24 23:56 ` H. Peter Anvin
2012-12-25 20:57 ` Yinghai Lu
2012-12-25 1:06 ` H. Peter Anvin
2012-12-25 11:52 ` Borislav Petkov
2012-12-25 15:51 ` H. Peter Anvin
2013-01-08 21:08 ` Borislav Petkov
2013-01-08 21:15 ` H. Peter Anvin
2013-01-08 21:19 ` Borislav Petkov
2013-01-08 23:17 ` H. Peter Anvin
2013-01-08 23:25 ` Borislav Petkov
2012-12-22 5:20 ` Yinghai Lu
2012-12-22 13:32 ` Konrad Rzeszutek Wilk
2012-12-22 10:38 ` Yinghai Lu
2012-12-22 13:25 ` Konrad Rzeszutek Wilk
2012-12-22 13:47 ` Konrad Rzeszutek Wilk
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=20121222031019.GA4120@phenom.dumpdata.com \
--to=konrad.wilk@oracle.com \
--cc=akpm@linux-foundation.org \
--cc=ebiederm@xmission.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=tglx@linutronix.de \
--cc=yinghai@kernel.org \
/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.