From: "Tian, Kevin" <kevin.tian@intel.com>
To: "Xu, Quan" <quan.xu@intel.com>,
"xen-devel@lists.xen.org" <xen-devel@lists.xen.org>
Cc: Keir Fraser <keir@xen.org>,
"dario.faggioli@citrix.com" <dario.faggioli@citrix.com>,
"Wu, Feng" <feng.wu@intel.com>, Jan Beulich <jbeulich@suse.com>,
Andrew Cooper <andrew.cooper3@citrix.com>
Subject: Re: [PATCH v7 09/11] vt-d: fix the IOMMU flush issue
Date: Sun, 12 Jun 2016 07:32:55 +0000 [thread overview]
Message-ID: <AADFC41AFE54684AB9EE6CBC0274A5D15F8A4C87@SHSMSX101.ccr.corp.intel.com> (raw)
In-Reply-To: <1465376344-28290-10-git-send-email-quan.xu@intel.com>
> From: Xu, Quan
> Sent: Wednesday, June 08, 2016 4:59 PM
> @@ -545,18 +549,42 @@ static int __must_check iommu_flush_all(void)
> {
> struct acpi_drhd_unit *drhd;
> struct iommu *iommu;
> - int flush_dev_iotlb;
> + int rc = 0;
>
> flush_all_cache();
> for_each_drhd_unit ( drhd )
> {
> iommu = drhd->iommu;
> - iommu_flush_context_global(iommu, 0);
> - flush_dev_iotlb = find_ats_dev_drhd(iommu) ? 1 : 0;
> - iommu_flush_iotlb_global(iommu, 0, flush_dev_iotlb);
> + /*
> + * The current logic for rc returns:
> + * - positive invoke iommu_flush_write_buffer to flush cache.
> + * - zero on success.
> + * - negative on failure. Continue to flush IOMMU IOTLB on a
> + * best effort basis.
> + *
> + * Moreover, IOMMU flush handlers flush_context_qi and flush_iotlb_qi
> + * (or flush_context_reg and flush_iotlb_reg, deep functions in the
> + * call trees of iommu_flush_context_global and iommu_flush_iotlb_global)
> + * are with the same logic to bubble up positive return value.
> + */
> + rc = iommu_flush_context_global(iommu, 0);
> + if ( rc <= 0 )
> + {
> + int flush_dev_iotlb = find_ats_dev_drhd(iommu) ? 1 : 0;
> + int ret = iommu_flush_iotlb_global(iommu, 0, flush_dev_iotlb);
> +
> + ASSERT(ret <= 0);
> + if ( !rc )
> + rc = ret;
I'm dubious about the assertion here. Why can't above call
return 1 upon error on earlier flush? I digged back your
earlier reply like:
> Yes, the iommu_flush_iotlb_dsi() can also return 1.
> Look at the call tree, at the beginning of
> flush_context_qi()/flush_iotlb_qi(), or
> flush_context_reg()/flush_iotlb_reg()..
>
> If rc was negative when we call iommu_flush_context_device(), it is
> impossible to return 1 for iommu_flush_iotlb_dsi().
But I don't think it a good idea of making so much assumptions
about internal implementations of those low level interfaces.
Also flush_context may fail for one specific reason which doesn't
block flush_iotlb which could get 1 returned when caching mode
is disabled. We'd better have return-1 case correctly handled here.
Thanks
Kevin
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel
next prev parent reply other threads:[~2016-06-12 7:32 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-06-08 8:58 [PATCH v7 00/11] Check VT-d Device-TLB flush error Xu, Quan
2016-06-08 8:58 ` [PATCH v7 01/11] IOMMU: handle IOMMU mapping and unmapping failures Xu, Quan
2016-06-08 8:58 ` [PATCH v7 02/11] IOMMU/MMU: enhance the call trees of IOMMU unmapping and mapping Xu, Quan
2016-06-08 14:40 ` Jan Beulich
[not found] ` <57584D8602000078000F32D0@prv-mh.provo.novell.com>
[not found] ` <421857ad-4f6b-e99c-1e81-034b19effdfb@amd.com>
2016-06-10 6:56 ` Jan Beulich
2016-06-12 6:41 ` Tian, Kevin
2016-06-08 8:58 ` [PATCH v7 03/11] IOMMU: propagate IOMMU Device-TLB flush error up to IOMMU unmapping (top level ones) Xu, Quan
2016-06-08 14:42 ` Jan Beulich
2016-06-08 14:54 ` Jan Beulich
2016-06-09 19:30 ` Suravee Suthikulanit
2016-06-09 10:28 ` Julien Grall
2016-06-08 8:58 ` [PATCH v7 04/11] IOMMU: propagate IOMMU Device-TLB flush error up to IOMMU mapping " Xu, Quan
2016-06-08 14:43 ` Jan Beulich
2016-06-09 18:45 ` Suravee Suthikulanit
2016-06-09 10:30 ` Julien Grall
2016-06-08 8:58 ` [PATCH v7 05/11] IOMMU/MMU: propagate IOMMU Device-TLB flush error up to iommu_iotlb_flush{, _all} " Xu, Quan
2016-06-09 11:12 ` Julien Grall
2016-06-09 11:45 ` Jan Beulich
2016-06-09 12:03 ` Julien Grall
2016-06-09 12:08 ` Julien Grall
2016-06-09 12:15 ` Jan Beulich
2016-06-09 12:24 ` Julien Grall
2016-06-09 12:32 ` Jan Beulich
2016-06-09 12:39 ` Julien Grall
2016-06-12 6:55 ` Tian, Kevin
2016-06-12 7:02 ` Xu, Quan
2016-06-12 15:35 ` Julien Grall
2016-06-09 12:14 ` Jan Beulich
2016-06-12 6:46 ` Tian, Kevin
2016-06-08 8:58 ` [PATCH v7 06/11] propagate IOMMU Device-TLB flush error up to EPT update " Xu, Quan
2016-06-08 8:59 ` [PATCH v7 07/11] IOMMU: propagate IOMMU Device-TLB flush error up to IOMMU suspending " Xu, Quan
2016-06-08 14:51 ` Jan Beulich
2016-06-12 7:42 ` Xu, Quan
2016-06-13 9:25 ` Jan Beulich
2016-06-09 18:58 ` Suravee Suthikulanit
2016-06-12 6:58 ` Tian, Kevin
2016-06-08 8:59 ` [PATCH v7 08/11] IOMMU: propagate IOMMU Device-TLB flush error (leaf ones) Xu, Quan
2016-06-08 8:59 ` [PATCH v7 09/11] vt-d: fix the IOMMU flush issue Xu, Quan
2016-06-12 7:32 ` Tian, Kevin [this message]
2016-06-12 9:27 ` Xu, Quan
2016-06-13 8:50 ` Xu, Quan
2016-06-08 8:59 ` [PATCH v7 10/11] vt-d: propagate the IOMMU Device-TLB flush error up to ME phantom functions Xu, Quan
2016-06-12 7:34 ` Tian, Kevin
2016-06-08 8:59 ` [PATCH v7 11/11] vt-d: add __must_check annotation to IOMMU flush pointers and handlers Xu, Quan
2016-06-12 7:35 ` Tian, Kevin
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=AADFC41AFE54684AB9EE6CBC0274A5D15F8A4C87@SHSMSX101.ccr.corp.intel.com \
--to=kevin.tian@intel.com \
--cc=andrew.cooper3@citrix.com \
--cc=dario.faggioli@citrix.com \
--cc=feng.wu@intel.com \
--cc=jbeulich@suse.com \
--cc=keir@xen.org \
--cc=quan.xu@intel.com \
--cc=xen-devel@lists.xen.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).