From: Matt Evans <matt@ozlabs.org>
To: "Alex Williamson" <alex@shazbot.org>,
"Leon Romanovsky" <leon@kernel.org>,
"Jason Gunthorpe" <jgg@nvidia.com>,
"Alex Mastro" <amastro@fb.com>,
"Christian König" <christian.koenig@amd.com>,
"Bjorn Helgaas" <bhelgaas@google.com>,
"Logan Gunthorpe" <logang@deltatee.com>,
"Kevin Tian" <kevin.tian@intel.com>,
"Pranjal Shrivastava" <praan@google.com>,
"Longfang Liu" <liulongfang@huawei.com>
Cc: "Mahmoud Adam" <mngyadam@amazon.de>,
"David Matlack" <dmatlack@google.com>,
"Björn Töpel" <bjorn@kernel.org>,
"Sumit Semwal" <sumit.semwal@linaro.org>,
"Ankit Agrawal" <ankita@nvidia.com>,
"Alistair Popple" <apopple@nvidia.com>,
"Vivek Kasireddy" <vivek.kasireddy@intel.com>,
linux-kernel@vger.kernel.org, linux-media@vger.kernel.org,
dri-devel@lists.freedesktop.org, linaro-mm-sig@lists.linaro.org,
kvm@vger.kernel.org, linux-pci@vger.kernel.org
Subject: [PATCH v6 7/9] vfio/pci: Clean up BAR zap and revocation
Date: Fri, 11 Sep 2026 22:41:55 +0100 [thread overview]
Message-ID: <20260911214200.33793-8-matt@ozlabs.org> (raw)
In-Reply-To: <20260911214200.33793-1-matt@ozlabs.org>
Previously, vfio_pci_zap_bars() (and the wrapper
vfio_pci_zap_and_down_write_memory_lock()) calls were paired with
calls to vfio_pci_dma_buf_move().
This commit replaces them with a unified new function,
vfio_pci_revoke_bars() containing both the vfio_pci_dma_buf_move() and
the unmap_mapping_range(), making it harder for callers to omit one.
It adds a wrapper, vfio_pci_lock_revoke_bars(), which takes the write
memory_lock before zapping, and adds a new vfio_pci_unrevoke_bars()
for the re-enable path.
As of "vfio/pci: Convert BAR mmap() to use a DMABUF", the zap via
unmap_mapping_range() is no longer performed for vfio-pci since the
DMABUFs used for BAR mappings already zap PTEs when the
vfio_pci_dma_buf_move() occurs.
However, it must be assumed that VFIO drivers which override the .mmap
op could create mappings _not_ backed by DMABUFs. So, the zap is
still performed on revoke if .mmap is overridden, using a new
zap_bars_on_revoke flag. A driver can explicitly opt out; the flag is
cleared by the hisi_acc_vfio_pci driver, since its .mmap just wraps
vfio_pci_core_mmap() and so still uses DMABUFs.
Signed-off-by: Matt Evans <matt@ozlabs.org>
---
.../vfio/pci/hisilicon/hisi_acc_vfio_pci.c | 14 +++-
drivers/vfio/pci/vfio_pci_config.c | 30 +++-----
drivers/vfio/pci/vfio_pci_core.c | 75 +++++++++++++------
drivers/vfio/pci/vfio_pci_priv.h | 3 +-
include/linux/vfio_pci_core.h | 1 +
5 files changed, 82 insertions(+), 41 deletions(-)
diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
index 86362ec424a5..14622556355e 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
@@ -1564,6 +1564,7 @@ static int hisi_acc_vfio_pci_migrn_init_dev(struct vfio_device *core_vdev)
struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(core_vdev);
struct pci_dev *pdev = to_pci_dev(core_vdev->dev);
struct hisi_qm *pf_qm = hisi_acc_get_pf_qm(pdev);
+ int ret;
hisi_acc_vdev->vf_id = pci_iov_vf_id(pdev) + 1;
hisi_acc_vdev->pf_qm = pf_qm;
@@ -1575,7 +1576,18 @@ static int hisi_acc_vfio_pci_migrn_init_dev(struct vfio_device *core_vdev)
core_vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY;
core_vdev->mig_ops = &hisi_acc_vfio_pci_migrn_state_ops;
- return vfio_pci_core_init_dev(core_vdev);
+ ret = vfio_pci_core_init_dev(core_vdev);
+ if (ret)
+ return ret;
+ /*
+ * hisi_acc_vfio_pci_mmap() calls down to
+ * vfio_pci_core_mmap(), so BAR mappings are still
+ * DMABUF-backed. They don't require a zap on revoke, so opt
+ * out:
+ */
+ hisi_acc_vdev->core_device.zap_bars_on_revoke = false;
+
+ return 0;
}
static const struct vfio_device_ops hisi_acc_vfio_pci_migrn_ops = {
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index a10ed733f0e3..bc6ccb2e135c 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -590,12 +590,10 @@ static int vfio_basic_config_write(struct vfio_pci_core_device *vdev, int pos,
virt_mem = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_MEMORY);
new_mem = !!(new_cmd & PCI_COMMAND_MEMORY);
- if (!new_mem) {
- vfio_pci_zap_and_down_write_memory_lock(vdev);
- vfio_pci_dma_buf_move(vdev, true);
- } else {
+ if (!new_mem)
+ vfio_pci_lock_revoke_bars(vdev);
+ else
down_write(&vdev->memory_lock);
- }
/*
* If the user is writing mem/io enable (new_mem/io) and we
@@ -631,7 +629,7 @@ static int vfio_basic_config_write(struct vfio_pci_core_device *vdev, int pos,
*virt_cmd |= cpu_to_le16(new_cmd & mask);
if (__vfio_pci_memory_enabled(vdev))
- vfio_pci_dma_buf_move(vdev, false);
+ vfio_pci_unrevoke_bars(vdev);
up_write(&vdev->memory_lock);
}
@@ -712,16 +710,14 @@ static int __init init_pci_cap_basic_perm(struct perm_bits *perm)
static void vfio_lock_and_set_power_state(struct vfio_pci_core_device *vdev,
pci_power_t state)
{
- if (state >= PCI_D3hot) {
- vfio_pci_zap_and_down_write_memory_lock(vdev);
- vfio_pci_dma_buf_move(vdev, true);
- } else {
+ if (state >= PCI_D3hot)
+ vfio_pci_lock_revoke_bars(vdev);
+ else
down_write(&vdev->memory_lock);
- }
vfio_pci_set_power_state(vdev, state);
if (__vfio_pci_memory_enabled(vdev))
- vfio_pci_dma_buf_move(vdev, false);
+ vfio_pci_unrevoke_bars(vdev);
up_write(&vdev->memory_lock);
}
@@ -908,11 +904,10 @@ static int vfio_exp_config_write(struct vfio_pci_core_device *vdev, int pos,
&cap);
if (!ret && (cap & PCI_EXP_DEVCAP_FLR)) {
- vfio_pci_zap_and_down_write_memory_lock(vdev);
- vfio_pci_dma_buf_move(vdev, true);
+ vfio_pci_lock_revoke_bars(vdev);
pci_try_reset_function(vdev->pdev);
if (__vfio_pci_memory_enabled(vdev))
- vfio_pci_dma_buf_move(vdev, false);
+ vfio_pci_unrevoke_bars(vdev);
up_write(&vdev->memory_lock);
}
}
@@ -993,11 +988,10 @@ static int vfio_af_config_write(struct vfio_pci_core_device *vdev, int pos,
&cap);
if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP)) {
- vfio_pci_zap_and_down_write_memory_lock(vdev);
- vfio_pci_dma_buf_move(vdev, true);
+ vfio_pci_lock_revoke_bars(vdev);
pci_try_reset_function(vdev->pdev);
if (__vfio_pci_memory_enabled(vdev))
- vfio_pci_dma_buf_move(vdev, false);
+ vfio_pci_unrevoke_bars(vdev);
up_write(&vdev->memory_lock);
}
}
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 8dd69948e0b7..760a816e6de0 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -375,8 +375,7 @@ static int vfio_pci_runtime_pm_entry(struct vfio_pci_core_device *vdev,
* The vdev power related flags are protected with 'memory_lock'
* semaphore.
*/
- vfio_pci_zap_and_down_write_memory_lock(vdev);
- vfio_pci_dma_buf_move(vdev, true);
+ vfio_pci_lock_revoke_bars(vdev);
if (vdev->pm_runtime_engaged) {
up_write(&vdev->memory_lock);
@@ -462,7 +461,7 @@ static void vfio_pci_runtime_pm_exit(struct vfio_pci_core_device *vdev)
down_write(&vdev->memory_lock);
__vfio_pci_runtime_pm_exit(vdev);
if (__vfio_pci_memory_enabled(vdev))
- vfio_pci_dma_buf_move(vdev, false);
+ vfio_pci_unrevoke_bars(vdev);
up_write(&vdev->memory_lock);
}
@@ -531,7 +530,7 @@ static int vfio_pci_core_runtime_resume(struct device *dev)
vdev->pm_wake_eventfd_ctx = NULL;
__vfio_pci_runtime_pm_exit(vdev);
if (__vfio_pci_memory_enabled(vdev))
- vfio_pci_dma_buf_move(vdev, false);
+ vfio_pci_unrevoke_bars(vdev);
eventfd_signal(ctx);
eventfd_ctx_put(ctx);
}
@@ -1319,6 +1318,8 @@ static int vfio_pci_ioctl_set_irqs(struct vfio_pci_core_device *vdev,
return ret;
}
+static void vfio_pci_revoke_bars(struct vfio_pci_core_device *vdev);
+
static int vfio_pci_ioctl_reset(struct vfio_pci_core_device *vdev,
void __user *arg)
{
@@ -1327,7 +1328,7 @@ static int vfio_pci_ioctl_reset(struct vfio_pci_core_device *vdev,
if (!vdev->reset_works)
return -EINVAL;
- vfio_pci_zap_and_down_write_memory_lock(vdev);
+ down_write(&vdev->memory_lock);
/*
* This function can be invoked while the power state is non-D0. If
@@ -1337,13 +1338,18 @@ static int vfio_pci_ioctl_reset(struct vfio_pci_core_device *vdev,
* have NoSoftRst-, the reset function can cause the PCI config space
* reset without restoring the original state (saved locally in
* 'vdev->pm_save').
+ *
+ * The zap is done after making the device accessible in D0,
+ * because a DMABUF importer could access the device as part
+ * of its revocation cleanup.
*/
vfio_pci_set_power_state(vdev, PCI_D0);
- vfio_pci_dma_buf_move(vdev, true);
+ vfio_pci_revoke_bars(vdev);
+
ret = pci_try_reset_function(vdev->pdev);
if (__vfio_pci_memory_enabled(vdev))
- vfio_pci_dma_buf_move(vdev, false);
+ vfio_pci_unrevoke_bars(vdev);
up_write(&vdev->memory_lock);
return ret;
@@ -1711,20 +1717,37 @@ ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *bu
}
EXPORT_SYMBOL_GPL(vfio_pci_core_write);
-static void vfio_pci_zap_bars(struct vfio_pci_core_device *vdev)
+static void vfio_pci_revoke_bars(struct vfio_pci_core_device *vdev)
{
- struct vfio_device *core_vdev = &vdev->vdev;
- loff_t start = VFIO_PCI_INDEX_TO_OFFSET(VFIO_PCI_BAR0_REGION_INDEX);
- loff_t end = VFIO_PCI_INDEX_TO_OFFSET(VFIO_PCI_ROM_REGION_INDEX);
- loff_t len = end - start;
+ lockdep_assert_held_write(&vdev->memory_lock);
+ vfio_pci_dma_buf_move(vdev, true);
- unmap_mapping_range(core_vdev->inode->i_mapping, start, len, true);
+ /*
+ * If a driver could possibly create BAR mappings in the
+ * vdev's address_space, do an additional zap on revoke. See
+ * vfio_pci_core_init_dev().
+ */
+ if (vdev->zap_bars_on_revoke) {
+ struct vfio_device *core_vdev = &vdev->vdev;
+ loff_t start = VFIO_PCI_INDEX_TO_OFFSET(VFIO_PCI_BAR0_REGION_INDEX);
+ loff_t end = VFIO_PCI_INDEX_TO_OFFSET(VFIO_PCI_ROM_REGION_INDEX);
+ loff_t len = end - start;
+
+ unmap_mapping_range(core_vdev->inode->i_mapping,
+ start, len, true);
+ }
}
-void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device *vdev)
+void vfio_pci_lock_revoke_bars(struct vfio_pci_core_device *vdev)
{
down_write(&vdev->memory_lock);
- vfio_pci_zap_bars(vdev);
+ vfio_pci_revoke_bars(vdev);
+}
+
+void vfio_pci_unrevoke_bars(struct vfio_pci_core_device *vdev)
+{
+ lockdep_assert_held_write(&vdev->memory_lock);
+ vfio_pci_dma_buf_move(vdev, false);
}
u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_core_device *vdev)
@@ -2222,6 +2245,16 @@ int vfio_pci_core_init_dev(struct vfio_device *core_vdev)
init_rwsem(&vdev->dmabuf_lock);
xa_init(&vdev->ctx);
+ /*
+ * If a driver overrides .mmap, it has to be assumed that it
+ * might not use the DMABUF-backed core mmap; this flag
+ * enables a zap at revoke time. A driver can opt out by
+ * clearing this flag at init, if their .mmap override calls
+ * down to vfio_pci_core_mmap().
+ */
+ if (vdev->vdev.ops->mmap != vfio_pci_core_mmap)
+ vdev->zap_bars_on_revoke = true;
+
return 0;
}
EXPORT_SYMBOL_GPL(vfio_pci_core_init_dev);
@@ -2589,9 +2622,10 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set,
}
/*
- * Take the memory write lock for each device and zap BAR
- * mappings to prevent the user accessing the device while in
- * reset. Locking multiple devices is prone to deadlock,
+ * Take the memory write lock for each device and
+ * zap/revoke BAR mappings to prevent the user (or
+ * peers) accessing the device while in reset.
+ * Locking multiple devices is prone to deadlock,
* runaway and unwind if we hit contention.
*/
if (!down_write_trylock(&vdev->memory_lock)) {
@@ -2599,8 +2633,7 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set,
break;
}
- vfio_pci_dma_buf_move(vdev, true);
- vfio_pci_zap_bars(vdev);
+ vfio_pci_revoke_bars(vdev);
}
if (!list_entry_is_head(vdev,
@@ -2630,7 +2663,7 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set,
list_for_each_entry_from_reverse(vdev, &dev_set->device_list,
vdev.dev_set_list) {
if (vdev->vdev.open_count && __vfio_pci_memory_enabled(vdev))
- vfio_pci_dma_buf_move(vdev, false);
+ vfio_pci_unrevoke_bars(vdev);
up_write(&vdev->memory_lock);
}
diff --git a/drivers/vfio/pci/vfio_pci_priv.h b/drivers/vfio/pci/vfio_pci_priv.h
index c62fbbf1625e..b0e0ac295db4 100644
--- a/drivers/vfio/pci/vfio_pci_priv.h
+++ b/drivers/vfio/pci/vfio_pci_priv.h
@@ -83,7 +83,8 @@ void vfio_config_free(struct vfio_pci_core_device *vdev);
int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev,
pci_power_t state);
-void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device *vdev);
+void vfio_pci_lock_revoke_bars(struct vfio_pci_core_device *vdev);
+void vfio_pci_unrevoke_bars(struct vfio_pci_core_device *vdev);
u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_core_device *vdev);
void vfio_pci_memory_unlock_and_restore(struct vfio_pci_core_device *vdev,
u16 cmd);
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index f99b152edcca..44891fdb7c76 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -129,6 +129,7 @@ struct vfio_pci_core_device {
bool disable_idle_d3:1;
bool nointxmask:1;
bool disable_vga:1;
+ bool zap_bars_on_revoke:1;
/* Flags modified at runtime - dedicated storage unit */
bool needs_reset;
bool pm_intx_masked;
--
2.50.1 (Apple Git-155)
next prev parent reply other threads:[~2026-09-11 21:42 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-11 21:41 [PATCH v6 0/9] vfio/pci: Add mmap() for DMABUFs Matt Evans
2026-09-11 21:41 ` [PATCH v6 1/9] vfio/pci: Remove DMABUF export dependency on vdev->memory_lock Matt Evans
2026-09-11 21:41 ` [PATCH v6 2/9] vfio/pci: Un-revoke DMABUFs in LOW_POWER_ENTRY_WITH_WAKEUP resume Matt Evans
2026-09-11 21:41 ` [PATCH v6 3/9] dma-buf: Export dma_buf_set_name() Matt Evans
2026-09-11 21:41 ` [PATCH v6 4/9] vfio/pci: Add a helper to look up PFNs for DMABUFs Matt Evans
2026-09-11 21:41 ` [PATCH v6 5/9] vfio/pci: Add a helper to create a DMABUF for a BAR-map VMA Matt Evans
2026-09-11 21:41 ` [PATCH v6 6/9] vfio/pci: Convert BAR mmap() to use a DMABUF Matt Evans
2026-09-11 21:41 ` Matt Evans [this message]
2026-09-11 21:41 ` [PATCH v6 8/9] vfio/pci: Support mmap() of a VFIO DMABUF Matt Evans
2026-09-11 21:41 ` [PATCH v6 9/9] vfio/pci: Permanently revoke a DMABUF on request Matt Evans
2026-09-13 16:52 ` Leon Romanovsky
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=20260911214200.33793-8-matt@ozlabs.org \
--to=matt@ozlabs.org \
--cc=alex@shazbot.org \
--cc=amastro@fb.com \
--cc=ankita@nvidia.com \
--cc=apopple@nvidia.com \
--cc=bhelgaas@google.com \
--cc=bjorn@kernel.org \
--cc=christian.koenig@amd.com \
--cc=dmatlack@google.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=jgg@nvidia.com \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=leon@kernel.org \
--cc=linaro-mm-sig@lists.linaro.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-media@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=liulongfang@huawei.com \
--cc=logang@deltatee.com \
--cc=mngyadam@amazon.de \
--cc=praan@google.com \
--cc=sumit.semwal@linaro.org \
--cc=vivek.kasireddy@intel.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.