public inbox for kvm@vger.kernel.org
 help / color / mirror / Atom feed
From: Matt Evans <mattev@meta.com>
To: Alex Williamson <alex@shazbot.org>,
	Kevin Tian <kevin.tian@intel.com>, Jason Gunthorpe <jgg@ziepe.ca>,
	Ankit Agrawal <ankita@nvidia.com>,
	Alistair Popple <apopple@nvidia.com>,
	Leon Romanovsky <leon@kernel.org>, Kees Cook <kees@kernel.org>,
	Shameer Kolothum <skolothumtho@nvidia.com>,
	Yishai Hadas <yishaih@nvidia.com>
Cc: Alexey Kardashevskiy <aik@ozlabs.ru>,
	Eric Auger <eric.auger@redhat.com>, Peter Xu <peterx@redhat.com>,
	Vivek Kasireddy <vivek.kasireddy@intel.com>,
	Zhi Wang <zhiw@nvidia.com>, <kvm@vger.kernel.org>,
	<linux-kernel@vger.kernel.org>, <virtualization@lists.linux.dev>
Subject: [PATCH v2 1/3] vfio/pci: Set up bar resources and maps in vfio_pci_core_enable()
Date: Thu, 23 Apr 2026 11:25:07 -0700	[thread overview]
Message-ID: <20260423182517.2286030-2-mattev@meta.com> (raw)
In-Reply-To: <20260423182517.2286030-1-mattev@meta.com>

Previously BAR resource requests and the corresponding pci_iomap()
were performed on-demand and without synchronisation, which was racy.
Rather than add synchronisation, it's simplest to address this by
doing both activities from vfio_pci_core_enable().

The resource allocation and/or pci_iomap() can still fail; their
status is tracked and existing calls to vfio_pci_core_setup_barmap()
will fail in the same way as before.  This keeps the point of failure
as observed by userspace the same, i.e. failures to request/map unused
BARs are benign.

Fixes: 7f5764e179c6 ("vfio: use vfio_pci_core_setup_barmap to map bar in mmap")
Fixes: 0d77ed3589ac0 ("vfio/pci: Pull BAR mapping setup from read-write path")
Signed-off-by: Matt Evans <mattev@meta.com>
---
 drivers/vfio/pci/vfio_pci_core.c | 61 +++++++++++++++++++++++++++-----
 drivers/vfio/pci/vfio_pci_rdwr.c | 29 ++++++---------
 include/linux/vfio_pci_core.h    |  1 +
 3 files changed, 64 insertions(+), 27 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 3f8d093aacf8..c59c61861d81 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -482,6 +482,55 @@ static int vfio_pci_core_runtime_resume(struct device *dev)
 }
 #endif /* CONFIG_PM */
 
+static void __vfio_pci_core_unmap_bars(struct vfio_pci_core_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	int i;
+
+	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
+		int bar = i + PCI_STD_RESOURCES;
+
+		if (vdev->barmap[bar])
+			pci_iounmap(pdev, vdev->barmap[bar]);
+		if (vdev->have_bar_resource[bar])
+			pci_release_selected_regions(pdev, 1 << bar);
+		vdev->barmap[bar] = NULL;
+		vdev->have_bar_resource[bar] = false;
+	}
+}
+
+static void __vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	int i;
+
+	/*
+	 * Eager-request BAR resources, and iomap; soft failures are
+	 * allowed, and consumers must check before use.
+	 */
+	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
+		int ret;
+		int bar = i + PCI_STD_RESOURCES;
+		void __iomem *io;
+
+		if (pci_resource_len(pdev, i) == 0)
+			continue;
+
+		ret = pci_request_selected_regions(pdev, 1 << bar, "vfio");
+		if (ret) {
+			pci_warn(vdev->pdev, "Failed to reserve region %d\n", bar);
+			continue;
+		}
+		vdev->have_bar_resource[bar] = true;
+
+		io = pci_iomap(pdev, bar, 0);
+		if (io)
+			vdev->barmap[bar] = io;
+		else
+			pci_warn(vdev->pdev, "Failed to iomap region %d\n", bar);
+	}
+}
+
 /*
  * The pci-driver core runtime PM routines always save the device state
  * before going into suspended state. If the device is going into low power
@@ -568,6 +617,7 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev)
 	if (!vfio_vga_disabled() && vfio_pci_is_vga(pdev))
 		vdev->has_vga = true;
 
+	 __vfio_pci_core_map_bars(vdev);
 
 	return 0;
 
@@ -591,7 +641,7 @@ void vfio_pci_core_disable(struct vfio_pci_core_device *vdev)
 	struct pci_dev *pdev = vdev->pdev;
 	struct vfio_pci_dummy_resource *dummy_res, *tmp;
 	struct vfio_pci_ioeventfd *ioeventfd, *ioeventfd_tmp;
-	int i, bar;
+	int i;
 
 	/* For needs_reset */
 	lockdep_assert_held(&vdev->vdev.dev_set->lock);
@@ -646,14 +696,7 @@ void vfio_pci_core_disable(struct vfio_pci_core_device *vdev)
 
 	vfio_config_free(vdev);
 
-	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
-		bar = i + PCI_STD_RESOURCES;
-		if (!vdev->barmap[bar])
-			continue;
-		pci_iounmap(pdev, vdev->barmap[bar]);
-		pci_release_selected_regions(pdev, 1 << bar);
-		vdev->barmap[bar] = NULL;
-	}
+	__vfio_pci_core_unmap_bars(vdev);
 
 	list_for_each_entry_safe(dummy_res, tmp,
 				 &vdev->dummy_resources_list, res_next) {
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index 4251ee03e146..bf7152316db4 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -200,25 +200,18 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_do_io_rw);
 
 int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar)
 {
-	struct pci_dev *pdev = vdev->pdev;
-	int ret;
-	void __iomem *io;
-
-	if (vdev->barmap[bar])
-		return 0;
-
-	ret = pci_request_selected_regions(pdev, 1 << bar, "vfio");
-	if (ret)
-		return ret;
-
-	io = pci_iomap(pdev, bar, 0);
-	if (!io) {
-		pci_release_selected_regions(pdev, 1 << bar);
+	/*
+	 * The barmap is now always set up in vfio_pci_core_enable().
+	 * Some legacy callers use this function to ensure the BAR
+	 * resources are requested, and others to ensure the
+	 * pci_iomap() was done, so check here:
+	 */
+	if (bar < 0 || bar >= PCI_STD_NUM_BARS)
+		return -EINVAL;
+	if (vdev->barmap[bar] == 0)
 		return -ENOMEM;
-	}
-
-	vdev->barmap[bar] = io;
-
+	if (!vdev->bar_has_rsrc[bar])
+		return -EBUSY;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(vfio_pci_core_setup_barmap);
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index 2ebba746c18f..1f508b067d82 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -101,6 +101,7 @@ struct vfio_pci_core_device {
 	const struct vfio_pci_device_ops *pci_ops;
 	void __iomem		*barmap[PCI_STD_NUM_BARS];
 	bool			bar_mmap_supported[PCI_STD_NUM_BARS];
+	bool			have_bar_resource[PCI_STD_NUM_BARS];
 	u8			*pci_config_map;
 	u8			*vconfig;
 	struct perm_bits	*msi_perm;
-- 
2.47.3


  reply	other threads:[~2026-04-23 18:25 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-04-23 18:25 [PATCH v2 0/3] vfio/pci: Request resources and map BARs at enable time Matt Evans
2026-04-23 18:25 ` Matt Evans [this message]
2026-04-23 21:30   ` [PATCH v2 1/3] vfio/pci: Set up bar resources and maps in vfio_pci_core_enable() Alex Williamson
2026-04-23 18:25 ` [PATCH v2 2/3] vfio/pci: Replace vfio_pci_core_setup_barmap() with checks for resource/map Matt Evans
2026-04-23 21:30   ` Alex Williamson
2026-04-23 18:25 ` [PATCH v2 3/3] vfio/pci: Check BAR resources before exporting a DMABUF Matt Evans

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=20260423182517.2286030-2-mattev@meta.com \
    --to=mattev@meta.com \
    --cc=aik@ozlabs.ru \
    --cc=alex@shazbot.org \
    --cc=ankita@nvidia.com \
    --cc=apopple@nvidia.com \
    --cc=eric.auger@redhat.com \
    --cc=jgg@ziepe.ca \
    --cc=kees@kernel.org \
    --cc=kevin.tian@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=leon@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peterx@redhat.com \
    --cc=skolothumtho@nvidia.com \
    --cc=virtualization@lists.linux.dev \
    --cc=vivek.kasireddy@intel.com \
    --cc=yishaih@nvidia.com \
    --cc=zhiw@nvidia.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