mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Pranjal Shrivastava <praan@google.com>
To: Joerg Roedel <joro@8bytes.org>, Will Deacon <will@kernel.org>,
	 Robin Murphy <robin.murphy@arm.com>,
	Jason Gunthorpe <jgg@ziepe.ca>, Kevin Tian <kevin.tian@intel.com>,
	 Alex Williamson <alex@shazbot.org>,
	David Matlack <dmatlack@google.com>,
	Jonathan Corbet <corbet@lwn.net>,
	 Shuah Khan <skhan@linuxfoundation.org>,
	Randy Dunlap <rdunlap@infradead.org>
Cc: Mostafa Saleh <smostafa@google.com>,
	Daniel Mentz <danielmentz@google.com>,
	 Samiullah Khawaja <skhawaja@google.com>,
	iommu@lists.linux.dev, kvm@vger.kernel.org,
	 linux-kselftest@vger.kernel.org, linux-doc@vger.kernel.org,
	 Logan Odell <loganodell@google.com>,
	linux-fsdevel@vger.kernel.org,  linux-kernel@vger.kernel.org,
	Pranjal Shrivastava <praan@google.com>
Subject: [RFC PATCH 4/7] vfio/type1: Expose IO page table usage via fdinfo
Date: Thu,  1 Oct 2026 22:45:28 +0000	[thread overview]
Message-ID: <20261001224531.765278-5-praan@google.com> (raw)
In-Reply-To: <20261001224531.765278-1-praan@google.com>

From: Logan Odell <loganodell@google.com>

Collect the IO page table usage statistics from each IOMMU domain
attached to a legacy VFIO container and expose that data to userspace via
the new iommu-nr-pages field in fdinfo.

Introduce and implement the get_nr_pages callback for vfio-iommu-type1,
that iterates over all attached domains and aggregates their nr_pages
counters.

Only domains whose page table is implemented by the generic_pt library
account their page table memory. If any domain attached to the container
does not, get_nr_pages() returns -EOPNOTSUPP and the field is omitted
instead of reporting a partial count.

Document the new field in Documentation/filesystems/proc.rst.

Signed-off-by: Logan Odell <loganodell@google.com>
Signed-off-by: Pranjal Shrivastava <praan@google.com>
---
 Documentation/filesystems/proc.rst | 17 +++++++++++++++++
 drivers/vfio/container.c           | 21 +++++++++++++++++++++
 drivers/vfio/vfio.h                |  2 ++
 drivers/vfio/vfio_iommu_type1.c    | 21 +++++++++++++++++++++
 4 files changed, 61 insertions(+)

diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index c102b62023cd..2d06c9930fcf 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -2200,6 +2200,23 @@ VFIO Device files
 where 'vfio-device-syspath' is the sysfs path corresponding to the VFIO device
 file.
 
+VFIO Container files
+~~~~~~~~~~~~~~~~~~~~
+
+::
+
+	pos:	0
+	flags:	02000002
+	mnt_id:	17
+	ino:	1103
+	iommu-nr-pages:	11
+
+where 'iommu-nr-pages' is the number of pages of memory used by the IO page
+tables of all IOMMU domains attached to the container. It is omitted when no
+IOMMU backend is set, or when any attached domain does not account its IO page
+table memory. Currently only domains using the generic_pt page table library
+account their IO page table memory.
+
 3.9	/proc/<pid>/map_files - Information about memory mapped files
 ---------------------------------------------------------------------
 This directory contains symbolic links which represent memory mapped files
diff --git a/drivers/vfio/container.c b/drivers/vfio/container.c
index 003281dbf8bc..2cb6c5373626 100644
--- a/drivers/vfio/container.c
+++ b/drivers/vfio/container.c
@@ -7,6 +7,7 @@
 #include <linux/file.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
+#include <linux/seq_file.h>
 #include <linux/capability.h>
 #include <linux/iommu.h>
 #include <linux/miscdevice.h>
@@ -384,12 +385,32 @@ static int vfio_fops_release(struct inode *inode, struct file *filep)
 	return 0;
 }
 
+#ifdef CONFIG_PROC_FS
+static void vfio_fops_show_fdinfo(struct seq_file *m, struct file *filep)
+{
+	struct vfio_container *container = filep->private_data;
+	long nr_pages = -EOPNOTSUPP;
+
+	down_read(&container->group_lock);
+	if (container->iommu_driver && container->iommu_driver->ops->get_nr_pages)
+		nr_pages = container->iommu_driver->ops->get_nr_pages(container->iommu_data);
+	up_read(&container->group_lock);
+
+	/* Only report a count that covers every domain in the container */
+	if (nr_pages >= 0)
+		seq_printf(m, "iommu-nr-pages:\t%ld\n", nr_pages);
+}
+#endif
+
 static const struct file_operations vfio_fops = {
 	.owner		= THIS_MODULE,
 	.open		= vfio_fops_open,
 	.release	= vfio_fops_release,
 	.unlocked_ioctl	= vfio_fops_unl_ioctl,
 	.compat_ioctl	= compat_ptr_ioctl,
+#ifdef CONFIG_PROC_FS
+	.show_fdinfo	= vfio_fops_show_fdinfo,
+#endif
 };
 
 struct vfio_container *vfio_container_from_file(struct file *file)
diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h
index 7728bc99b63d..37e8841ad0e9 100644
--- a/drivers/vfio/vfio.h
+++ b/drivers/vfio/vfio.h
@@ -226,6 +226,8 @@ struct vfio_iommu_driver_ops {
 				  void *data, size_t count, bool write);
 	struct iommu_domain *(*group_iommu_domain)(void *iommu_data,
 						   struct iommu_group *group);
+	/* Returns IO page table pages used, or -EOPNOTSUPP if not accounted */
+	long		(*get_nr_pages)(void *iommu_data);
 };
 
 struct vfio_iommu_driver {
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index c8151ba54de3..fc7c1553d574 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -3249,6 +3249,26 @@ vfio_iommu_type1_group_iommu_domain(void *iommu_data,
 	return domain;
 }
 
+static long vfio_iommu_type1_get_nr_pages(void *iommu_data)
+{
+	struct vfio_iommu *iommu = iommu_data;
+	struct vfio_domain *d;
+	long total = 0;
+
+	mutex_lock(&iommu->lock);
+	list_for_each_entry(d, &iommu->domain_list, next) {
+		/* Only generic_pt page tables account their pages */
+		if (!d->domain->is_iommupt) {
+			total = -EOPNOTSUPP;
+			break;
+		}
+		total += atomic_long_read(&d->domain->nr_pages);
+	}
+	mutex_unlock(&iommu->lock);
+
+	return total;
+}
+
 static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = {
 	.name			= "vfio-iommu-type1",
 	.owner			= THIS_MODULE,
@@ -3263,6 +3283,7 @@ static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = {
 	.unregister_device	= vfio_iommu_type1_unregister_device,
 	.dma_rw			= vfio_iommu_type1_dma_rw,
 	.group_iommu_domain	= vfio_iommu_type1_group_iommu_domain,
+	.get_nr_pages		= vfio_iommu_type1_get_nr_pages,
 };
 
 static int __init vfio_iommu_type1_init(void)
-- 
2.56.0.rc1.315.gc6ed9934b7-goog


  parent reply	other threads:[~2026-10-01 22:46 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20261001224531.765278-1-praan@google.com>
2026-10-01 22:45 ` [RFC PATCH 1/7] iommu: Add infrastructure for per-domain IOPT accounting Pranjal Shrivastava
2026-10-01 22:45 ` [RFC PATCH 2/7] iommu: Implement domain-attributed page allocation Pranjal Shrivastava
2026-10-01 22:45 ` [RFC PATCH 3/7] iommupt: Enable per-domain IOPT attribution Pranjal Shrivastava
2026-10-01 22:45 ` Pranjal Shrivastava [this message]
2026-10-01 22:45 ` [RFC PATCH 5/7] iommufd: Expose IO page table usage via fdinfo Pranjal Shrivastava
2026-10-01 22:45 ` [RFC PATCH 6/7] iommufd/selftest: Add observability test for iommu-nr-pages Pranjal Shrivastava
2026-10-01 22:45 ` [RFC PATCH 7/7] vfio/selftests: Add observability test for IO page table usage Pranjal Shrivastava

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=20261001224531.765278-5-praan@google.com \
    --to=praan@google.com \
    --cc=alex@shazbot.org \
    --cc=corbet@lwn.net \
    --cc=danielmentz@google.com \
    --cc=dmatlack@google.com \
    --cc=iommu@lists.linux.dev \
    --cc=jgg@ziepe.ca \
    --cc=joro@8bytes.org \
    --cc=kevin.tian@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=loganodell@google.com \
    --cc=rdunlap@infradead.org \
    --cc=robin.murphy@arm.com \
    --cc=skhan@linuxfoundation.org \
    --cc=skhawaja@google.com \
    --cc=smostafa@google.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

all inboxes | Powered by JetHome®