qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Alejandro Jimenez <alejandro.j.jimenez@oracle.com>
To: Sairaj Kodilkar <sarunkod@amd.com>, qemu-devel@nongnu.org
Cc: pbonzini@redhat.com, richard.henderson@linaro.org,
	eduardo@habkost.net, peterx@redhat.com, david@redhat.com,
	philmd@linaro.org, mst@redhat.com, marcel.apfelbaum@gmail.com,
	alex.williamson@redhat.com, vasant.hegde@amd.com,
	suravee.suthikulpanit@amd.com, santosh.shukla@amd.com,
	Wei.Huang2@amd.com, clement.mathieu--drif@eviden.com,
	ethan.milon@eviden.com, joao.m.martins@oracle.com,
	boris.ostrovsky@oracle.com
Subject: Re: [PATCH v2 19/20] amd_iommu: Do not assume passthrough translation when DTE[TV]=0
Date: Wed, 14 May 2025 17:49:51 -0400	[thread overview]
Message-ID: <26c95126-9305-4e01-8526-f450d91da926@oracle.com> (raw)
In-Reply-To: <8cc41515-73d4-4d7b-b908-679e3fe2e923@amd.com>



On 5/12/25 3:00 AM, Sairaj Kodilkar wrote:
> 
> 
> On 5/2/2025 7:46 AM, Alejandro Jimenez wrote:

>> -    if (pte & AMDVI_DEV_TRANSLATION_VALID) {
>> -        level = get_pte_translation_mode(pte);
>> -        if (level >= 7) {
>> -            trace_amdvi_mode_invalid(level, addr);
>> +    if (!(pte & AMDVI_DEV_TRANSLATION_VALID)) {
>> +        /*
>> +         * A DTE with V=1, TV=0 does not have a valid Page Table Root 
>> Pointer.
>> +         * An IOMMU processing a request that requires a table walk 
>> terminates
>> +         * the walk when it encounters this condition. Do the same 
>> and return
>> +         * instead of assuming that the address is forwarded without 
>> translation
>> +         * i.e. the passthrough case, as it is done for the case 
>> where DTE[V]=0.
>> +         */
>> +        return;
>> +    }
> 
> Above change seems redundant since caller of the amdvi_page_walk(),
> amdvi_do_translate() checks the return value of amdvi_as_to_dte().
> amdvi_do_translate() returns when it encounters -AMDVI_FR_DTE_TV and
> does not call amdvi_page_walk().
> 

It is perhaps redundant at this point for the reason you mention, as we 
are already checking the DTE for all sorts of conditions earlier.

But I would like to leave it in since it serves as a good validation 
that any future callers of amdvi_page_walk(), which might not check or 
care about the return of amdvi_as_to_dte(), are passing a DTE that 
specifically supports a page walk, which is exactly what this function 
needs to proceed. Plus it provides a nice place to place the comment 
detailing the IOMMU behavior in such cases.

If you are concerned about efficiency, this is already not a very fast 
path, and the 5 assembly instructions this check takes (with a non-debug 
build I think is ~2 instructions) will certainly not be what brings the 
performance down :).

Alejandro

> Regards
> Sairaj Kodilkar
> 
> 
> 



  reply	other threads:[~2025-05-14 21:51 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-05-02  2:15 [PATCH v2 00/20] AMD vIOMMU: DMA remapping support for VFIO devices Alejandro Jimenez
2025-05-02  2:15 ` [PATCH v2 01/20] memory: Adjust event ranges to fit within notifier boundaries Alejandro Jimenez
2025-05-11 18:31   ` Michael S. Tsirkin
2025-05-12  8:02   ` David Hildenbrand
2025-05-12 17:29     ` Peter Xu
2025-06-12  6:54   ` Vasant Hegde
2025-06-12 21:49     ` Alejandro Jimenez
2025-05-02  2:15 ` [PATCH v2 02/20] amd_iommu: Document '-device amd-iommu' common options Alejandro Jimenez
2025-05-02  2:15 ` [PATCH v2 03/20] amd_iommu: Reorder device and page table helpers Alejandro Jimenez
2025-05-02  2:15 ` [PATCH v2 04/20] amd_iommu: Helper to decode size of page invalidation command Alejandro Jimenez
2025-05-02  2:15 ` [PATCH v2 05/20] amd_iommu: Add helper function to extract the DTE Alejandro Jimenez
2025-05-12  6:45   ` Sairaj Kodilkar
2025-05-14 20:23     ` Alejandro Jimenez
2025-05-20 10:18   ` Ethan MILON
2025-05-21 14:49     ` Alejandro Jimenez
2025-06-12  8:31       ` Ethan MILON
2025-05-02  2:15 ` [PATCH v2 06/20] amd_iommu: Return an error when unable to read PTE from guest memory Alejandro Jimenez
2025-06-12 10:37   ` Vasant Hegde
2025-06-13 17:44     ` Alejandro Jimenez
2025-05-02  2:15 ` [PATCH v2 07/20] amd_iommu: Add helpers to walk AMD v1 Page Table format Alejandro Jimenez
2025-05-02  2:15 ` [PATCH v2 08/20] amd_iommu: Add a page walker to sync shadow page tables on invalidation Alejandro Jimenez
2025-05-02  2:15 ` [PATCH v2 09/20] amd_iommu: Add basic structure to support IOMMU notifier updates Alejandro Jimenez
2025-05-12  6:52   ` Sairaj Kodilkar
2025-06-23 10:53   ` Sairaj Kodilkar
2025-05-02  2:15 ` [PATCH v2 10/20] amd_iommu: Sync shadow page tables on page invalidation Alejandro Jimenez
2025-05-02  2:15 ` [PATCH v2 11/20] amd_iommu: Use iova_tree records to determine large page size on UNMAP Alejandro Jimenez
2025-06-11  8:29   ` Sairaj Kodilkar
2025-06-13 21:50     ` Alejandro Jimenez
2025-05-02  2:15 ` [PATCH v2 12/20] amd_iommu: Unmap all address spaces under the AMD IOMMU on reset Alejandro Jimenez
2025-05-02  2:15 ` [PATCH v2 13/20] amd_iommu: Add replay callback Alejandro Jimenez
2025-05-02  2:15 ` [PATCH v2 14/20] amd_iommu: Invalidate address translations on INVALIDATE_IOMMU_ALL Alejandro Jimenez
2025-05-02  2:16 ` [PATCH v2 15/20] amd_iommu: Toggle memory regions based on address translation mode Alejandro Jimenez
2025-05-12  6:52   ` Sairaj Kodilkar
2025-05-02  2:16 ` [PATCH v2 16/20] amd_iommu: Set all address spaces to default translation mode on reset Alejandro Jimenez
2025-05-29  6:16   ` Sairaj Kodilkar
2025-05-30 21:30     ` Alejandro Jimenez
2025-06-13  8:46       ` Sairaj Kodilkar
2025-06-23 22:08         ` Alejandro Jimenez
2025-05-02  2:16 ` [PATCH v2 17/20] amd_iommu: Add dma-remap property to AMD vIOMMU device Alejandro Jimenez
2025-05-02  2:16 ` [PATCH v2 18/20] amd_iommu: Toggle address translation mode on devtab entry invalidation Alejandro Jimenez
2025-06-12  8:27   ` Ethan MILON
2025-06-12 11:23     ` Sairaj Kodilkar
2025-05-02  2:16 ` [PATCH v2 19/20] amd_iommu: Do not assume passthrough translation when DTE[TV]=0 Alejandro Jimenez
2025-05-12  7:00   ` Sairaj Kodilkar
2025-05-14 21:49     ` Alejandro Jimenez [this message]
2025-05-16  8:14       ` Sairaj Kodilkar
2025-05-02  2:16 ` [PATCH v2 20/20] amd_iommu: Refactor amdvi_page_walk() to use common code for page walk Alejandro Jimenez
2025-05-11 18:34 ` [PATCH v2 00/20] AMD vIOMMU: DMA remapping support for VFIO devices Michael S. Tsirkin
2025-05-16  8:07 ` Sairaj Kodilkar
2025-05-21  2:35   ` Alejandro Jimenez
2025-05-21  6:21     ` Sairaj Kodilkar
2025-05-30 11:41 ` Michael S. Tsirkin
2025-05-30 14:39   ` Alejandro Jimenez
2025-06-02  4:49     ` Sairaj Kodilkar

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=26c95126-9305-4e01-8526-f450d91da926@oracle.com \
    --to=alejandro.j.jimenez@oracle.com \
    --cc=Wei.Huang2@amd.com \
    --cc=alex.williamson@redhat.com \
    --cc=boris.ostrovsky@oracle.com \
    --cc=clement.mathieu--drif@eviden.com \
    --cc=david@redhat.com \
    --cc=eduardo@habkost.net \
    --cc=ethan.milon@eviden.com \
    --cc=joao.m.martins@oracle.com \
    --cc=marcel.apfelbaum@gmail.com \
    --cc=mst@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=philmd@linaro.org \
    --cc=qemu-devel@nongnu.org \
    --cc=richard.henderson@linaro.org \
    --cc=santosh.shukla@amd.com \
    --cc=sarunkod@amd.com \
    --cc=suravee.suthikulpanit@amd.com \
    --cc=vasant.hegde@amd.com \
    /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).