patches.lists.linux.dev archive mirror
 help / color / mirror / Atom feed
From: Nicolin Chen <nicolinc@nvidia.com>
To: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>, <iommu@lists.linux.dev>,
	Joerg Roedel <joro@8bytes.org>,
	Justin Stitt <justinstitt@google.com>,
	Kevin Tian <kevin.tian@intel.com>, <linux-doc@vger.kernel.org>,
	<linux-kselftest@vger.kernel.org>, <llvm@lists.linux.dev>,
	Bill Wendling <morbo@google.com>,
	Nathan Chancellor <nathan@kernel.org>,
	Nick Desaulniers <nick.desaulniers+lkml@gmail.com>,
	Miguel Ojeda <ojeda@kernel.org>,
	"Robin Murphy" <robin.murphy@arm.com>,
	Shuah Khan <shuah@kernel.org>,
	"Suravee Suthikulpanit" <suravee.suthikulpanit@amd.com>,
	Will Deacon <will@kernel.org>, Alexey Kardashevskiy <aik@amd.com>,
	Alejandro Jimenez <alejandro.j.jimenez@oracle.com>,
	James Gowans <jgowans@amazon.com>,
	"Michael Roth" <michael.roth@amd.com>,
	Pasha Tatashin <pasha.tatashin@soleen.com>,
	<patches@lists.linux.dev>
Subject: Re: [PATCH v5 01/15] genpt: Generic Page Table base API
Date: Thu, 18 Sep 2025 12:43:13 -0700	[thread overview]
Message-ID: <aMxg0bulOYF8HBJo@Asurada-Nvidia> (raw)
In-Reply-To: <20250918144943.GP1391379@nvidia.com>

On Thu, Sep 18, 2025 at 11:49:43AM -0300, Jason Gunthorpe wrote:
> On Thu, Sep 18, 2025 at 12:14:27AM -0700, Nicolin Chen wrote:
> > > > Then, the "entry" sounds like a physical (v.s. "logical") table
> > > > entry, e.g. a PTE that we usually say?
> > > 
> > > I choose entry because it is related to PTE and in most cases you want
> > > to work on the entries. The replication of entry to item is somewhat
> > > hidden.
> > > 
> > > From a HW perspective the TLB should be loading entries.
> > 
> > In that case, "entry" should be a single "physical" element v.s.
> > "logical", right? Because that's what HW/TLB physically loads.
> 
> I would say HW/TLB loads logical entries when it supports
> contiguity. It read a single table item and expand it to the larger
> TLB "entry".

Oh, I got wrong. Thanks for elaborating.

"item" is a PTE and "entry" is a group of items/PTEs that set the
CONTIG bit. TLB loads all those items/PTEs and combines them into
a single TLB "entry".

It seems difficult to define which one is physical or logical, as
both "item" and "entry" physically exist in page table and in TLB
respectively.

Nicolin

  reply	other threads:[~2025-09-18 19:43 UTC|newest]

Thread overview: 66+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-09-03 17:46 [PATCH v5 00/15] Consolidate iommu page table implementations (AMD) Jason Gunthorpe
2025-09-03 17:46 ` [PATCH v5 01/15] genpt: Generic Page Table base API Jason Gunthorpe
2025-09-10  3:40   ` Nicolin Chen
2025-09-15 15:51     ` Jason Gunthorpe
2025-09-18  7:14       ` Nicolin Chen
2025-09-18 14:49         ` Jason Gunthorpe
2025-09-18 19:43           ` Nicolin Chen [this message]
2025-09-18  6:49   ` Tian, Kevin
2025-09-18 18:06     ` Jason Gunthorpe
2025-09-19  8:11       ` Tian, Kevin
2025-09-19 14:31         ` Jason Gunthorpe
2025-09-24  9:20           ` Tian, Kevin
2025-09-22 14:45   ` [External] : " ALOK TIWARI
2025-09-22 17:05     ` Jason Gunthorpe
2025-09-03 17:46 ` [PATCH v5 02/15] genpt: Add Documentation/ files Jason Gunthorpe
2025-09-11  4:23   ` Nicolin Chen
2025-09-15 15:42     ` Jason Gunthorpe
2025-09-18  6:55   ` Tian, Kevin
2025-09-19 14:42     ` Jason Gunthorpe
2025-09-24  9:21       ` Tian, Kevin
2025-09-03 17:46 ` [PATCH v5 03/15] iommupt: Add the basic structure of the iommu implementation Jason Gunthorpe
2025-09-11  5:38   ` Nicolin Chen
2025-09-15 15:36     ` Jason Gunthorpe
2025-09-18  6:58   ` Tian, Kevin
2025-09-19 15:26     ` Jason Gunthorpe
2025-09-24  9:22       ` Tian, Kevin
2025-09-03 17:46 ` [PATCH v5 04/15] iommupt: Add the AMD IOMMU v1 page table format Jason Gunthorpe
2025-09-18  7:05   ` Tian, Kevin
2025-09-19 18:19     ` Jason Gunthorpe
2025-09-24  9:23       ` Tian, Kevin
2025-10-07 12:28     ` Jason Gunthorpe
2025-10-08  9:43   ` Vasant Hegde
2025-10-08 13:08     ` Jason Gunthorpe
2025-10-09 11:44       ` Vasant Hegde
2025-09-03 17:46 ` [PATCH v5 05/15] iommupt: Add iova_to_phys op Jason Gunthorpe
2025-09-18  7:08   ` Tian, Kevin
2025-09-19 18:35     ` Jason Gunthorpe
2025-09-03 17:46 ` [PATCH v5 06/15] iommupt: Add unmap_pages op Jason Gunthorpe
2025-09-24  9:28   ` Tian, Kevin
2025-09-24 12:23     ` Jason Gunthorpe
2025-09-26  7:23       ` Tian, Kevin
2025-09-03 17:46 ` [PATCH v5 07/15] iommupt: Add map_pages op Jason Gunthorpe
2025-09-26  7:47   ` Tian, Kevin
2025-09-29 16:44     ` Jason Gunthorpe
2025-10-07 12:08   ` Vasant Hegde
2025-10-07 13:11     ` Jason Gunthorpe
2025-10-08  9:52       ` Vasant Hegde
2025-09-03 17:46 ` [PATCH v5 08/15] iommupt: Add read_and_clear_dirty op Jason Gunthorpe
2025-09-26  7:48   ` Tian, Kevin
2025-09-03 17:46 ` [PATCH v5 09/15] iommupt: Add a kunit test for Generic Page Table Jason Gunthorpe
2025-09-03 17:46 ` [PATCH v5 10/15] iommupt: Add a mock pagetable format for iommufd selftest to use Jason Gunthorpe
2025-09-26  7:50   ` Tian, Kevin
2025-09-03 17:46 ` [PATCH v5 11/15] iommufd: Change the selftest to use iommupt instead of xarray Jason Gunthorpe
2025-09-03 17:46 ` [PATCH v5 12/15] iommupt: Add the x86 64 bit page table format Jason Gunthorpe
2025-09-26  7:57   ` Tian, Kevin
2025-09-29 16:17     ` Jason Gunthorpe
2025-10-08 10:05   ` Vasant Hegde
2025-10-08 13:03     ` Jason Gunthorpe
2025-10-09 11:43       ` Vasant Hegde
2025-09-03 17:46 ` [PATCH v5 13/15] iommu/amd: Use the generic iommu page table Jason Gunthorpe
2025-09-25 12:07   ` Ankit Soni
2025-09-25 12:32     ` Jason Gunthorpe
2025-09-25 12:39       ` Ankit Soni
2025-10-08  9:47   ` Vasant Hegde
2025-09-03 17:46 ` [PATCH v5 14/15] iommu/amd: Remove AMD io_pgtable support Jason Gunthorpe
2025-09-03 17:46 ` [PATCH v5 15/15] iommupt: Add a kunit test for the IOMMU implementation Jason Gunthorpe

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=aMxg0bulOYF8HBJo@Asurada-Nvidia \
    --to=nicolinc@nvidia.com \
    --cc=aik@amd.com \
    --cc=alejandro.j.jimenez@oracle.com \
    --cc=corbet@lwn.net \
    --cc=iommu@lists.linux.dev \
    --cc=jgg@nvidia.com \
    --cc=jgowans@amazon.com \
    --cc=joro@8bytes.org \
    --cc=justinstitt@google.com \
    --cc=kevin.tian@intel.com \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=llvm@lists.linux.dev \
    --cc=michael.roth@amd.com \
    --cc=morbo@google.com \
    --cc=nathan@kernel.org \
    --cc=nick.desaulniers+lkml@gmail.com \
    --cc=ojeda@kernel.org \
    --cc=pasha.tatashin@soleen.com \
    --cc=patches@lists.linux.dev \
    --cc=robin.murphy@arm.com \
    --cc=shuah@kernel.org \
    --cc=suravee.suthikulpanit@amd.com \
    --cc=will@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 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).