From: Joerg Roedel <joro-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
To: Baoquan He <bhe-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Cc: iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org
Subject: Re: [Patch v2 3/9] iommu/amd: make several functions globally seen
Date: Fri, 27 Nov 2015 12:06:09 +0100 [thread overview]
Message-ID: <20151127110609.GB24300@8bytes.org> (raw)
In-Reply-To: <1446811851-20623-4-git-send-email-bhe-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
On Fri, Nov 06, 2015 at 08:10:45PM +0800, Baoquan He wrote:
> They will be called later when copy old dev/irq tables. It's better to use them
> then call iommu_flush_all_caches() since iommu_flush_all_caches() will
> iterate many empty table entries.
You only flush all table entries on old AMD IOMMUs. Newer ones have a
flush_all command that is used when available. Besides that, the AMD
IOMMU hardware is usually fast so that even flushing all dte entries is
not a bottleneck (it is done during suspend/resume, for example).
Have you made different experiences?
Joerg
next prev parent reply other threads:[~2015-11-27 11:06 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-11-06 12:10 [Patch v2 0/9] Fix AMD IOMMU faults in kdump kernel Baoquan He
[not found] ` <1446811851-20623-1-git-send-email-bhe-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-11-06 12:10 ` [Patch v2 1/9] iommu/amd: Use standard bitmap operation to set bitmap Baoquan He
2015-11-06 12:10 ` [Patch v2 2/9] iommu/amd: Detect pre enabled translation Baoquan He
[not found] ` <1446811851-20623-3-git-send-email-bhe-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-11-27 11:03 ` Joerg Roedel
[not found] ` <20151127110312.GA24300-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
2015-11-30 11:18 ` Baoquan He
2015-11-06 12:10 ` [Patch v2 3/9] iommu/amd: make several functions globally seen Baoquan He
[not found] ` <1446811851-20623-4-git-send-email-bhe-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-11-27 11:06 ` Joerg Roedel [this message]
[not found] ` <20151127110609.GB24300-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
2015-11-30 11:31 ` Baoquan He
2015-11-06 12:10 ` [Patch v2 4/9] iommu/amd: add copy_irq_table function Baoquan He
[not found] ` <1446811851-20623-5-git-send-email-bhe-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-11-27 11:13 ` Joerg Roedel
[not found] ` <20151127111312.GC24300-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
2015-11-30 11:49 ` Baoquan He
2015-11-06 12:10 ` [Patch v2 5/9] iommu/amd: Add function copy_dev_tables Baoquan He
[not found] ` <1446811851-20623-6-git-send-email-bhe-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-11-27 11:21 ` Joerg Roedel
[not found] ` <20151127112152.GD24300-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
2015-11-30 11:59 ` Baoquan He
2015-11-06 12:10 ` [Patch v2 6/9] iommu/amd: Add functions copy_command_buffer/copy_event_buffer Baoquan He
[not found] ` <1446811851-20623-7-git-send-email-bhe-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-11-27 11:24 ` Joerg Roedel
[not found] ` <20151127112446.GE24300-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
2015-11-30 12:02 ` Baoquan He
2015-11-06 12:10 ` [Patch v2 7/9] iommu/amd: copy old tables and do not update dev tables before driver init Baoquan He
[not found] ` <1446811851-20623-8-git-send-email-bhe-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-11-27 11:35 ` Joerg Roedel
[not found] ` <20151127113517.GF24300-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
2015-11-30 12:13 ` Baoquan He
2015-12-13 1:19 ` Baoquan He
[not found] ` <20151213011929.GA2490-ejN7fcUYdH/by3iVrkZq2A@public.gmane.org>
2015-12-16 15:51 ` Joerg Roedel
2015-11-06 12:10 ` [Patch v2 8/9] iommu/amd: Do not update the information of domain to devtables before device " Baoquan He
2015-11-06 12:10 ` [Patch v2 9/9] iommu/amd: Clear the iommu pre enabled setting Baoquan He
2015-11-06 12:14 ` [Patch v2 0/9] Fix AMD IOMMU faults in kdump kernel Baoquan He
2015-11-18 6:14 ` Baoquan He
2015-11-27 11:38 ` Joerg Roedel
[not found] ` <20151127113816.GG24300-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
2015-11-30 11:16 ` Baoquan He
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=20151127110609.GB24300@8bytes.org \
--to=joro-zlv9swrftaidnm+yrofe0a@public.gmane.org \
--cc=bhe-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
--cc=iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.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.