From: Shameer Kolothum <skolothumtho@nvidia.com>
To: <kvm@vger.kernel.org>, <linux-pci@vger.kernel.org>,
<linux-kernel@vger.kernel.org>
Cc: <alex@shazbot.org>, <jgg@ziepe.ca>, <kevin.tian@intel.com>,
<kbusch@meta.com>, <michal.winiarski@intel.com>,
<satyanarayana.k.v.p@intel.com>, <sonangp@nvidia.com>,
<ankita@nvidia.com>, <nathanc@nvidia.com>, <mochs@nvidia.com>,
<skolothumtho@nvidia.com>
Subject: [RFC PATCH v2 07/16] vfio/pci: Gate function reset and runtime power management
Date: Tue, 29 Sep 2026 18:32:56 +0100 [thread overview]
Message-ID: <20260929173305.204856-8-skolothumtho@nvidia.com> (raw)
In-Reply-To: <20260929173305.204856-1-skolothumtho@nvidia.com>
Reject function reset and low-power entry or exit while device access is
blocked. Hold access_srcu across reset and runtime power-management
updates so recovery waits for admitted operations to finish.
Perform the reset ioctl's D0 transition before taking SRCU, preserving
VFIO's pm_save handling. Keep memory_lock held across D0 preparation and
reset so a concurrent guest D3 write cannot intervene. Check the blocked
state before D0 and check SRCU admission afterward. A rejected reset does
not queue a deferred D0 request.
The reset uses pci_try_reset_function(), which returns -EAGAIN if AER
holds device_lock.
Assisted-by: LLM
Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com>
---
Note: D0 remains outside SRCU, but this series introduces a recovery
locking dependency involving memory_lock and pci_bus_sem through ASPM.
This remains unresolved. See the cover letter's "Locking and open
questions" section.
---
drivers/vfio/pci/vfio_pci_priv.h | 3 +++
drivers/vfio/pci/vfio_pci_config.c | 4 ++--
drivers/vfio/pci/vfio_pci_core.c | 32 ++++++++++++++++++++++++++++--
3 files changed, 35 insertions(+), 4 deletions(-)
diff --git a/drivers/vfio/pci/vfio_pci_priv.h b/drivers/vfio/pci/vfio_pci_priv.h
index 623e73f379cc..f757e5407ce4 100644
--- a/drivers/vfio/pci/vfio_pci_priv.h
+++ b/drivers/vfio/pci/vfio_pci_priv.h
@@ -41,6 +41,9 @@ ssize_t vfio_pci_config_rw_single(struct vfio_pci_core_device *vdev,
char __user *buf, size_t count, loff_t *ppos,
bool iswrite);
+int vfio_lock_and_set_power_state(struct vfio_pci_core_device *vdev,
+ pci_power_t state);
+
ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
size_t count, loff_t *ppos, bool iswrite);
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index e9480b573381..f3366df4af68 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -720,8 +720,8 @@ static int __init init_pci_cap_basic_perm(struct perm_bits *perm)
* It takes all the required locks to protect the access of power related
* variables and then invokes vfio_pci_set_power_state().
*/
-static int vfio_lock_and_set_power_state(struct vfio_pci_core_device *vdev,
- pci_power_t state)
+int 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);
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 91c92e8f3daa..38551bdedc89 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -372,6 +372,12 @@ int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev, pci_power_t stat
static int vfio_pci_runtime_pm_entry(struct vfio_pci_core_device *vdev,
struct eventfd_ctx *efdctx)
{
+ int idx;
+
+ idx = vfio_pci_core_access_begin(vdev);
+ if (idx < 0)
+ return idx;
+
/*
* The vdev power related flags are protected with 'memory_lock'
* semaphore.
@@ -381,6 +387,7 @@ static int vfio_pci_runtime_pm_entry(struct vfio_pci_core_device *vdev,
if (vdev->pm_runtime_engaged) {
up_write(&vdev->memory_lock);
+ vfio_pci_core_access_end(vdev, idx);
return -EINVAL;
}
@@ -388,6 +395,7 @@ static int vfio_pci_runtime_pm_entry(struct vfio_pci_core_device *vdev,
vdev->pm_wake_eventfd_ctx = efdctx;
pm_runtime_put_noidle(&vdev->pdev->dev);
up_write(&vdev->memory_lock);
+ vfio_pci_core_access_end(vdev, idx);
return 0;
}
@@ -470,7 +478,7 @@ static void vfio_pci_runtime_pm_exit(struct vfio_pci_core_device *vdev)
static int vfio_pci_core_pm_exit(struct vfio_pci_core_device *vdev, u32 flags,
void __user *arg, size_t argsz)
{
- int ret;
+ int ret, idx;
ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_SET, 0);
if (ret != 1)
@@ -483,7 +491,11 @@ static int vfio_pci_core_pm_exit(struct vfio_pci_core_device *vdev, u32 flags,
* already signaled the eventfd and exited low power mode itself.
* pm_runtime_engaged protects the redundant call here.
*/
+ idx = vfio_pci_core_access_begin(vdev);
+ if (idx < 0)
+ return idx;
vfio_pci_runtime_pm_exit(vdev);
+ vfio_pci_core_access_end(vdev, idx);
return 0;
}
@@ -1387,12 +1399,16 @@ static int vfio_pci_ioctl_set_irqs(struct vfio_pci_core_device *vdev,
static int vfio_pci_ioctl_reset(struct vfio_pci_core_device *vdev,
void __user *arg)
{
- int ret;
+ int ret, idx;
if (!vdev->reset_works)
return -EINVAL;
vfio_pci_zap_and_down_write_memory_lock(vdev);
+ if (vdev->pci_recovery_supported && READ_ONCE(vdev->access_blocked)) {
+ up_write(&vdev->memory_lock);
+ return -EIO;
+ }
/*
* This function can be invoked while the power state is non-D0. If
@@ -1402,15 +1418,27 @@ 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').
+ *
+ * Do the D0 transition outside access_srcu because it can acquire
+ * pci_bus_sem through ASPM. Keep memory_lock held through reset to
+ * prevent a concurrent power-state write from putting the device in D3.
*/
vfio_pci_set_power_state(vdev, PCI_D0);
+ idx = vfio_pci_core_access_begin(vdev);
+ if (idx < 0) {
+ up_write(&vdev->memory_lock);
+ return idx;
+ }
+
vfio_pci_dma_buf_move(vdev, true);
ret = pci_try_reset_function(vdev->pdev);
if (__vfio_pci_memory_enabled(vdev))
vfio_pci_dma_buf_move(vdev, false);
up_write(&vdev->memory_lock);
+ vfio_pci_core_access_end(vdev, idx);
+
return ret;
}
--
2.43.0
next prev parent reply other threads:[~2026-09-29 17:34 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-29 17:32 [RFC PATCH v2 00/16] vfio/pci: Handle PCI error recovery and report state to userspace Shameer Kolothum
2026-09-29 17:32 ` [RFC PATCH v2 01/16] vfio/pci: Add a device access gate Shameer Kolothum
2026-09-29 17:32 ` [RFC PATCH v2 02/16] vfio/pci: Gate config space access Shameer Kolothum
2026-09-29 17:32 ` [RFC PATCH v2 03/16] vfio/pci: Buffer ROM reads before copying to userspace Shameer Kolothum
2026-09-29 17:32 ` [RFC PATCH v2 04/16] vfio/pci: Gate BAR and ROM access Shameer Kolothum
2026-09-29 17:32 ` [RFC PATCH v2 05/16] vfio/pci: Fail BAR faults while access is blocked Shameer Kolothum
2026-09-29 17:32 ` [RFC PATCH v2 06/16] vfio/pci: Gate interrupt configuration Shameer Kolothum
2026-09-29 17:32 ` Shameer Kolothum [this message]
2026-09-29 17:32 ` [RFC PATCH v2 08/16] vfio/pci: Gate device information queries and DMA-BUF export Shameer Kolothum
2026-09-29 17:32 ` [RFC PATCH v2 09/16] vfio/pci: Add PCI error recovery state Shameer Kolothum
2026-09-29 17:32 ` [RFC PATCH v2 10/16] vfio/pci: Quiesce INTx while access is blocked Shameer Kolothum
2026-09-29 17:33 ` [RFC PATCH v2 11/16] vfio/pci: Add INTx recovery start and finish helpers Shameer Kolothum
2026-09-29 17:33 ` [RFC PATCH v2 12/16] vfio/pci: Restore device state from slot_reset() Shameer Kolothum
2026-09-29 17:33 ` [RFC PATCH v2 13/16] vfio/pci: Complete recovery in resume() Shameer Kolothum
2026-09-29 17:33 ` [RFC PATCH v2 14/16] vfio/pci: Block device access during host recovery Shameer Kolothum
2026-09-29 17:33 ` [RFC PATCH v2 15/16] vfio/pci: Add VFIO_DEVICE_FEATURE_PCI_ERROR_RECOVERY Shameer Kolothum
2026-09-29 17:33 ` [RFC PATCH v2 16/16] vfio/pci: Enable host PCI error recovery for vfio-pci Shameer Kolothum
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=20260929173305.204856-8-skolothumtho@nvidia.com \
--to=skolothumtho@nvidia.com \
--cc=alex@shazbot.org \
--cc=ankita@nvidia.com \
--cc=jgg@ziepe.ca \
--cc=kbusch@meta.com \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=michal.winiarski@intel.com \
--cc=mochs@nvidia.com \
--cc=nathanc@nvidia.com \
--cc=satyanarayana.k.v.p@intel.com \
--cc=sonangp@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
all inboxes | Powered by JetHome®