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 v5 3/3] vfio/pci: Replace vfio_pci_core_setup_barmap() with vfio_pci_core_get_iomap()
Date: Mon, 11 May 2026 07:58:25 -0700 [thread overview]
Message-ID: <20260511145829.2993601-4-mattev@meta.com> (raw)
In-Reply-To: <20260511145829.2993601-1-mattev@meta.com>
Since "vfio/pci: Set up barmap in vfio_pci_core_enable()", the
resource request and iomap for the BARs was performed early, and
vfio_pci_core_setup_barmap() just checks those actions succeeded.
Move this logic to a new helper that checks success and returns the
iomap address, replacing the various bare vdev->barmap[] lookups.
This maintains the error behaviour of the previous on-demand
vfio_pci_core_setup_barmap() scheme.
Signed-off-by: Matt Evans <mattev@meta.com>
---
drivers/vfio/pci/nvgrace-gpu/main.c | 20 ++++++++++++-------
drivers/vfio/pci/vfio_pci_core.c | 11 +++++------
drivers/vfio/pci/vfio_pci_dmabuf.c | 2 +-
drivers/vfio/pci/vfio_pci_rdwr.c | 30 ++++++++---------------------
drivers/vfio/pci/virtio/legacy_io.c | 13 ++++++-------
include/linux/vfio_pci_core.h | 20 ++++++++++++++++++-
6 files changed, 52 insertions(+), 44 deletions(-)
diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c
index fa056b69f899..15e2f03c6cd4 100644
--- a/drivers/vfio/pci/nvgrace-gpu/main.c
+++ b/drivers/vfio/pci/nvgrace-gpu/main.c
@@ -61,6 +61,7 @@ struct nvgrace_gpu_pci_core_device {
struct mem_region resmem;
/* Lock to control device memory kernel mapping */
struct mutex remap_lock;
+ void __iomem *bar0_base;
bool has_mig_hw_bug;
/* GPU has just been reset */
bool reset_done;
@@ -171,6 +172,7 @@ static int nvgrace_gpu_open_device(struct vfio_device *core_vdev)
struct nvgrace_gpu_pci_core_device *nvdev =
container_of(core_vdev, struct nvgrace_gpu_pci_core_device,
core_device.vdev);
+ void __iomem *io;
int ret;
ret = vfio_pci_core_enable(vdev);
@@ -184,14 +186,14 @@ static int nvgrace_gpu_open_device(struct vfio_device *core_vdev)
/*
* GPU readiness is checked by reading the BAR0 registers.
- *
- * ioremap BAR0 to ensure that the BAR0 mapping is present before
- * register reads on first fault before establishing any GPU
- * memory mapping.
+ * The BAR map was just set up by vfio_pci_core_enable(), so
+ * bail early if that wasn't successful:
*/
- ret = vfio_pci_core_setup_barmap(vdev, 0);
- if (ret)
+ io = vfio_pci_core_get_iomap(vdev, 0);
+ if (IS_ERR(io)) {
+ ret = PTR_ERR(io);
goto error_exit;
+ }
if (nvdev->resmem.memlength) {
ret = nvgrace_gpu_vfio_pci_register_pfn_range(core_vdev, &nvdev->resmem);
@@ -204,6 +206,8 @@ static int nvgrace_gpu_open_device(struct vfio_device *core_vdev)
goto register_mem_failed;
vfio_pci_core_finish_enable(vdev);
+ nvdev->bar0_base = io;
+
return 0;
register_mem_failed:
@@ -220,6 +224,8 @@ static void nvgrace_gpu_close_device(struct vfio_device *core_vdev)
container_of(core_vdev, struct nvgrace_gpu_pci_core_device,
core_device.vdev);
+ nvdev->bar0_base = NULL;
+
if (nvdev->resmem.memlength)
unregister_pfn_address_space(&nvdev->resmem.pfn_address_space);
@@ -275,7 +281,7 @@ nvgrace_gpu_check_device_ready(struct nvgrace_gpu_pci_core_device *nvdev)
if (!__vfio_pci_memory_enabled(vdev))
return -EIO;
- ret = nvgrace_gpu_wait_device_ready(vdev->barmap[0]);
+ ret = nvgrace_gpu_wait_device_ready(nvdev->bar0_base);
if (ret)
return ret;
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 0e4fc17d360f..b1b7fc5183a7 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1762,7 +1762,7 @@ int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma
struct pci_dev *pdev = vdev->pdev;
unsigned int index;
u64 phys_len, req_len, pgoff, req_start;
- int ret;
+ void __iomem *bar_io;
index = vma->vm_pgoff >> (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT);
@@ -1796,12 +1796,11 @@ int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma
return -EINVAL;
/*
- * Even though we don't make use of the barmap for the mmap,
- * we need to request the region and the barmap tracks that.
+ * Ensure the BAR resource region is reserved for use.
*/
- ret = vfio_pci_core_setup_barmap(vdev, index);
- if (ret)
- return ret;
+ bar_io = vfio_pci_core_get_iomap(vdev, index);
+ if (IS_ERR(bar_io))
+ return PTR_ERR(bar_io);
vma->vm_private_data = vdev;
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c b/drivers/vfio/pci/vfio_pci_dmabuf.c
index 69a5c2d511e6..46cd44b22c9c 100644
--- a/drivers/vfio/pci/vfio_pci_dmabuf.c
+++ b/drivers/vfio/pci/vfio_pci_dmabuf.c
@@ -248,7 +248,7 @@ int vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags,
* else. Check that PCI resources have been claimed for it.
*/
if (get_dma_buf.region_index >= VFIO_PCI_ROM_REGION_INDEX ||
- vfio_pci_core_setup_barmap(vdev, get_dma_buf.region_index))
+ IS_ERR(vfio_pci_core_get_iomap(vdev, get_dma_buf.region_index)))
return -ENODEV;
dma_ranges = memdup_array_user(&arg->dma_ranges, get_dma_buf.nr_ranges,
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index 3bfbb879a005..7f14dd46de17 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -198,19 +198,6 @@ ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
}
EXPORT_SYMBOL_GPL(vfio_pci_core_do_io_rw);
-/*
- * The barmap is set up in vfio_pci_core_enable(). Callers use this
- * function to check that the BAR resources are requested or that the
- * pci_iomap() was done.
- */
-int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar)
-{
- if (IS_ERR(vdev->barmap[bar]))
- return PTR_ERR(vdev->barmap[bar]);
- return 0;
-}
-EXPORT_SYMBOL_GPL(vfio_pci_core_setup_barmap);
-
ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
size_t count, loff_t *ppos, bool iswrite)
{
@@ -262,13 +249,11 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
*/
max_width = VFIO_PCI_IO_WIDTH_4;
} else {
- int ret = vfio_pci_core_setup_barmap(vdev, bar);
- if (ret) {
- done = ret;
+ io = vfio_pci_core_get_iomap(vdev, bar);
+ if (IS_ERR(io)) {
+ done = PTR_ERR(io);
goto out;
}
-
- io = vdev->barmap[bar];
}
if (bar == vdev->msix_bar) {
@@ -423,6 +408,7 @@ int vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset,
loff_t pos = offset & VFIO_PCI_OFFSET_MASK;
int ret, bar = VFIO_PCI_OFFSET_TO_INDEX(offset);
struct vfio_pci_ioeventfd *ioeventfd;
+ void __iomem *io;
/* Only support ioeventfds into BARs */
if (bar > VFIO_PCI_BAR5_REGION_INDEX)
@@ -440,9 +426,9 @@ int vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset,
if (count == 8)
return -EINVAL;
- ret = vfio_pci_core_setup_barmap(vdev, bar);
- if (ret)
- return ret;
+ io = vfio_pci_core_get_iomap(vdev, bar);
+ if (IS_ERR(io))
+ return PTR_ERR(io);
mutex_lock(&vdev->ioeventfds_lock);
@@ -479,7 +465,7 @@ int vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset,
}
ioeventfd->vdev = vdev;
- ioeventfd->addr = vdev->barmap[bar] + pos;
+ ioeventfd->addr = io + pos;
ioeventfd->data = data;
ioeventfd->pos = pos;
ioeventfd->bar = bar;
diff --git a/drivers/vfio/pci/virtio/legacy_io.c b/drivers/vfio/pci/virtio/legacy_io.c
index 1ed349a55629..c868b2177310 100644
--- a/drivers/vfio/pci/virtio/legacy_io.c
+++ b/drivers/vfio/pci/virtio/legacy_io.c
@@ -299,19 +299,18 @@ int virtiovf_pci_ioctl_get_region_info(struct vfio_device *core_vdev,
static int virtiovf_set_notify_addr(struct virtiovf_pci_core_device *virtvdev)
{
struct vfio_pci_core_device *core_device = &virtvdev->core_device;
- int ret;
+ void __iomem *io;
/*
* Setup the BAR where the 'notify' exists to be used by vfio as well
* This will let us mmap it only once and use it when needed.
*/
- ret = vfio_pci_core_setup_barmap(core_device,
- virtvdev->notify_bar);
- if (ret)
- return ret;
+ io = vfio_pci_core_get_iomap(core_device,
+ virtvdev->notify_bar);
+ if (IS_ERR(io))
+ return PTR_ERR(io);
- virtvdev->notify_addr = core_device->barmap[virtvdev->notify_bar] +
- virtvdev->notify_offset;
+ virtvdev->notify_addr = io + virtvdev->notify_offset;
return 0;
}
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index 89165b769e5c..7accd0eac457 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -188,7 +188,6 @@ int vfio_pci_core_match_token_uuid(struct vfio_device *core_vdev,
int vfio_pci_core_enable(struct vfio_pci_core_device *vdev);
void vfio_pci_core_disable(struct vfio_pci_core_device *vdev);
void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev);
-int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar);
pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev,
pci_channel_state_t state);
ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
@@ -234,6 +233,25 @@ static inline bool is_aligned_for_order(struct vm_area_struct *vma,
!IS_ALIGNED(pfn, 1 << order)));
}
+/*
+ * Returns a BAR's iomap base or an ERR_PTR() if, for example, the
+ * BAR isn't valid, its resource wasn't acquired, or its iomap
+ * failed. This shall only be used after vfio_pci_core_enable()
+ * has set up the BAR maps and before vfio_pci_core_disable()
+ * tears them down.
+ */
+static inline void __iomem __must_check *
+vfio_pci_core_get_iomap(struct vfio_pci_core_device *vdev, unsigned int bar)
+{
+ if (WARN_ON_ONCE(bar >= PCI_STD_NUM_BARS))
+ return ERR_PTR(-EINVAL);
+
+ if (WARN_ON_ONCE(!vdev->barmap[bar]))
+ return ERR_PTR(-ENODEV);
+
+ return vdev->barmap[bar];
+}
+
int vfio_pci_dma_buf_iommufd_map(struct dma_buf_attachment *attachment,
struct phys_vec *phys);
--
2.47.3
next prev parent reply other threads:[~2026-05-11 14:59 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-11 14:58 [PATCH v5 0/3] vfio/pci: Request resources and map BARs at enable time Matt Evans
2026-05-11 14:58 ` [PATCH v5 1/3] vfio/pci: Set up BAR resources and maps in vfio_pci_core_enable() Matt Evans
2026-05-11 14:58 ` [PATCH v5 2/3] vfio/pci: Check BAR resources before exporting a DMABUF Matt Evans
2026-05-11 14:58 ` Matt Evans [this message]
2026-05-20 21:11 ` [PATCH v5 3/3] vfio/pci: Replace vfio_pci_core_setup_barmap() with vfio_pci_core_get_iomap() Alex Williamson
2026-05-14 16:38 ` [PATCH v5 0/3] vfio/pci: Request resources and map BARs at enable time Alex Williamson
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=20260511145829.2993601-4-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 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.