[PATCH V2 19/20] accel/amdxdna: Implement runtime suspend and resume support

From: David Zhang

Date: Tue Oct 06 2026 - 00:24:03 EST


Add runtime suspend/resume for AIE4 driver.

Wake and acquire an RPM reference across amdxdna_sriov_configure() so
that SR-IOV management commands execute with the device active.

Update amdxdna_pm.c to implement amdxdna_pm_runtime_suspend() and
amdxdna_pm_runtime_resume().

Wrap .driver.pm with pm_ptr() to allow the dev_pm_ops structure and
its callbacks to be discarded as dead code when CONFIG_PM is disabled.

Detect passthrough VFs by comparing the VF driver with the PF driver,
since drv->owner is NULL for built-in drivers.

Signed-off-by: David Zhang <yidong.zhang@xxxxxxx>
---
drivers/accel/amdxdna/aie2_pci.c | 2 ++
drivers/accel/amdxdna/aie4_pci.c | 31 +++++++++++++++++++
drivers/accel/amdxdna/aie4_pci.h | 8 +++++
drivers/accel/amdxdna/aie4_sriov.c | 41 +++++++++++++++++++++++++
drivers/accel/amdxdna/amdxdna_pci_drv.c | 17 +++++++---
drivers/accel/amdxdna/amdxdna_pci_drv.h | 2 ++
drivers/accel/amdxdna/amdxdna_pm.c | 34 ++++++++++++++++++++
drivers/accel/amdxdna/amdxdna_pm.h | 4 ++-
8 files changed, 134 insertions(+), 5 deletions(-)

diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c
index bee3d973e6bc..d8b1aa3e0bef 100644
--- a/drivers/accel/amdxdna/aie2_pci.c
+++ b/drivers/accel/amdxdna/aie2_pci.c
@@ -1207,6 +1207,8 @@ const struct amdxdna_dev_ops aie2_ops = {
.fini = aie2_fini,
.resume = aie2_hw_resume,
.suspend = aie2_hw_suspend,
+ .runtime_resume = aie2_hw_resume,
+ .runtime_suspend = aie2_hw_suspend,
.get_aie_info = aie2_get_info,
.set_aie_state = aie2_set_state,
.hwctx_init = aie2_hwctx_init,
diff --git a/drivers/accel/amdxdna/aie4_pci.c b/drivers/accel/amdxdna/aie4_pci.c
index f7fa55c82baa..c395052eb6fd 100644
--- a/drivers/accel/amdxdna/aie4_pci.c
+++ b/drivers/accel/amdxdna/aie4_pci.c
@@ -1162,6 +1162,17 @@ static int aie4_pf_suspend(struct amdxdna_dev *xdna)
return 0;
}

+static int aie4_pf_runtime_suspend(struct amdxdna_dev *xdna)
+{
+ int ret;
+
+ ret = aie4_vfs_alive(xdna);
+ if (ret)
+ return ret;
+
+ return aie4_pf_suspend(xdna);
+}
+
static int aie4_pf_resume(struct amdxdna_dev *xdna)
{
struct amdxdna_dev_hdl *ndev = xdna->dev_handle;
@@ -1214,6 +1225,20 @@ static int aie4_vf_suspend(struct amdxdna_dev *xdna)
return 0;
}

+static int aie4_vf_runtime_suspend(struct amdxdna_dev *xdna)
+{
+ struct amdxdna_dev_hdl *ndev = xdna->dev_handle;
+ struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev);
+
+ drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock));
+ aie4_hwctx_suspend_all(ndev, false);
+ aie4_vf_hw_stop(ndev);
+ pci_disable_device(pdev);
+
+ XDNA_DBG(xdna, "vf runtime suspend done");
+ return 0;
+}
+
static int aie4_vf_resume(struct amdxdna_dev *xdna)
{
struct amdxdna_dev_hdl *ndev = xdna->dev_handle;
@@ -1314,6 +1339,8 @@ const struct amdxdna_dev_ops aie4_pf_ops = {
.sriov_configure = aie4_sriov_configure,
.resume = aie4_pf_resume,
.suspend = aie4_pf_suspend,
+ .runtime_resume = aie4_pf_resume,
+ .runtime_suspend = aie4_pf_runtime_suspend,
};

const struct amdxdna_dev_ops aie4_vf_ops = {
@@ -1330,6 +1357,8 @@ const struct amdxdna_dev_ops aie4_vf_ops = {
.set_aie_state = aie4_set_state,
.resume = aie4_vf_resume,
.suspend = aie4_vf_suspend,
+ .runtime_resume = aie4_vf_resume,
+ .runtime_suspend = aie4_vf_runtime_suspend,
};

const struct amdxdna_dev_ops aie4_classic_ops = {
@@ -1346,4 +1375,6 @@ const struct amdxdna_dev_ops aie4_classic_ops = {
.set_aie_state = aie4_set_state,
.resume = aie4_classic_resume,
.suspend = aie4_classic_suspend,
+ .runtime_resume = aie4_classic_resume,
+ .runtime_suspend = aie4_classic_suspend,
};
diff --git a/drivers/accel/amdxdna/aie4_pci.h b/drivers/accel/amdxdna/aie4_pci.h
index 011d2f4f0b68..a03c39457ab8 100644
--- a/drivers/accel/amdxdna/aie4_pci.h
+++ b/drivers/accel/amdxdna/aie4_pci.h
@@ -180,16 +180,24 @@ void aie4_free_notification(struct cert_comp *comp);
int aie4_create_vfs(struct amdxdna_dev_hdl *ndev, int num_vfs);
int aie4_sriov_configure(struct amdxdna_dev *xdna, int num_vfs);
int aie4_sriov_stop(struct amdxdna_dev_hdl *ndev);
+int aie4_vfs_alive(struct amdxdna_dev *xdna);
#else
static inline int aie4_create_vfs(struct amdxdna_dev_hdl *ndev, int num_vfs)
{
return 0;
}
+
#define aie4_sriov_configure NULL
+
static inline int aie4_sriov_stop(struct amdxdna_dev_hdl *ndev)
{
return 0;
}
+
+static inline int aie4_vfs_alive(struct amdxdna_dev *xdna)
+{
+ return 0;
+}
#endif

extern const struct amdxdna_dev_ops aie4_pf_ops;
diff --git a/drivers/accel/amdxdna/aie4_sriov.c b/drivers/accel/amdxdna/aie4_sriov.c
index 3cad0526087d..c89bb033bb16 100644
--- a/drivers/accel/amdxdna/aie4_sriov.c
+++ b/drivers/accel/amdxdna/aie4_sriov.c
@@ -6,6 +6,7 @@
#include <drm/amdxdna_accel.h>
#include <drm/drm_print.h>
#include <linux/pci.h>
+#include <linux/pm_runtime.h>

#include "aie.h"
#include "aie4_msg_priv.h"
@@ -119,6 +120,46 @@ static int aie4_link_vf(struct amdxdna_dev *xdna, struct pci_dev *pdev_vf)
return 0;
}

+/* Check if a VF is actively running workloads or in passthrough. */
+static int aie4_check_vf_alive(struct amdxdna_dev *xdna, struct pci_dev *pdev_vf)
+{
+ struct device *pf_dev = xdna->ddev.dev;
+ struct device_driver *drv;
+ bool busy = false;
+
+ if (!device_trylock(&pdev_vf->dev)) {
+ XDNA_WARN(xdna, "VF:%s is busy (locked)", pci_name(pdev_vf));
+ return -EBUSY;
+ }
+
+ drv = pdev_vf->dev.driver;
+ if (!drv) {
+ device_unlock(&pdev_vf->dev);
+ return 0;
+ }
+
+ /* VF bound to a driver other than the PF's (amdxdna) is passthrough. */
+ if (drv != pf_dev->driver) {
+ XDNA_WARN(xdna, "VF:%s is in passthrough", pci_name(pdev_vf));
+ busy = true;
+ } else if (!pm_runtime_suspended(&pdev_vf->dev)) {
+ XDNA_WARN(xdna, "VF:%s is busy", pci_name(pdev_vf));
+ busy = true;
+ }
+
+ device_unlock(&pdev_vf->dev);
+ return busy ? -EBUSY : 0;
+}
+
+int aie4_vfs_alive(struct amdxdna_dev *xdna)
+{
+ if (pci_vfs_assigned(to_pci_dev(xdna->ddev.dev))) {
+ XDNA_WARN(xdna, "VF devices are being used in VMs, cannot suspend");
+ return -EBUSY;
+ }
+ return aie4_for_each_vfs(xdna, aie4_check_vf_alive);
+}
+
static int aie4_link_vfs(struct amdxdna_dev *xdna)
{
return aie4_for_each_vfs(xdna, aie4_link_vf);
diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c
index 8faf651fb534..57985ebee0ac 100644
--- a/drivers/accel/amdxdna/amdxdna_pci_drv.c
+++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c
@@ -469,18 +469,27 @@ static void amdxdna_remove(struct pci_dev *pdev)

static const struct dev_pm_ops amdxdna_pm_ops = {
SYSTEM_SLEEP_PM_OPS(amdxdna_pm_suspend, amdxdna_pm_resume)
- RUNTIME_PM_OPS(amdxdna_pm_suspend, amdxdna_pm_resume, NULL)
+ RUNTIME_PM_OPS(amdxdna_pm_runtime_suspend, amdxdna_pm_runtime_resume, NULL)
};

static int amdxdna_sriov_configure(struct pci_dev *pdev, int num_vfs)
{
struct amdxdna_dev *xdna = pci_get_drvdata(pdev);
+ int ret;

guard(mutex)(&xdna->dev_lock);
+
+ ret = amdxdna_pm_resume_get_locked(xdna);
+ if (ret)
+ return ret;
+
if (xdna->dev_info->ops->sriov_configure)
- return xdna->dev_info->ops->sriov_configure(xdna, num_vfs);
+ ret = xdna->dev_info->ops->sriov_configure(xdna, num_vfs);
+ else
+ ret = -EOPNOTSUPP;

- return -ENOENT;
+ amdxdna_pm_suspend_put(xdna);
+ return ret;
}

static struct pci_driver amdxdna_pci_driver = {
@@ -488,7 +497,7 @@ static struct pci_driver amdxdna_pci_driver = {
.id_table = pci_ids,
.probe = amdxdna_probe,
.remove = amdxdna_remove,
- .driver.pm = &amdxdna_pm_ops,
+ .driver.pm = pm_ptr(&amdxdna_pm_ops),
.sriov_configure = amdxdna_sriov_configure,
};

diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.h b/drivers/accel/amdxdna/amdxdna_pci_drv.h
index fde48ef0ca6c..f669f6a6cc4c 100644
--- a/drivers/accel/amdxdna/amdxdna_pci_drv.h
+++ b/drivers/accel/amdxdna/amdxdna_pci_drv.h
@@ -57,6 +57,8 @@ struct amdxdna_dev_ops {
void (*debugfs_init)(struct amdxdna_dev *xdna);
int (*resume)(struct amdxdna_dev *xdna);
int (*suspend)(struct amdxdna_dev *xdna);
+ int (*runtime_resume)(struct amdxdna_dev *xdna);
+ int (*runtime_suspend)(struct amdxdna_dev *xdna);
int (*sriov_configure)(struct amdxdna_dev *xdna, int num_vfs);
int (*hwctx_init)(struct amdxdna_hwctx *hwctx);
void (*hwctx_stop)(struct amdxdna_hwctx *hwctx);
diff --git a/drivers/accel/amdxdna/amdxdna_pm.c b/drivers/accel/amdxdna/amdxdna_pm.c
index 9c030b7836fb..2b4ce301bb96 100644
--- a/drivers/accel/amdxdna/amdxdna_pm.c
+++ b/drivers/accel/amdxdna/amdxdna_pm.c
@@ -37,11 +37,40 @@ int amdxdna_pm_resume(struct device *dev)
return ret;
}

+int amdxdna_pm_runtime_suspend(struct device *dev)
+{
+ struct amdxdna_dev *xdna = to_xdna_dev(dev_get_drvdata(dev));
+ int ret = -EOPNOTSUPP;
+
+ guard(mutex)(&xdna->dev_lock);
+ if (xdna->dev_info->ops->runtime_suspend)
+ ret = xdna->dev_info->ops->runtime_suspend(xdna);
+
+ XDNA_DBG(xdna, "Runtime suspend done ret %d", ret);
+ return ret;
+}
+
+int amdxdna_pm_runtime_resume(struct device *dev)
+{
+ struct amdxdna_dev *xdna = to_xdna_dev(dev_get_drvdata(dev));
+ int ret = -EOPNOTSUPP;
+
+ guard(mutex)(&xdna->dev_lock);
+ if (xdna->dev_info->ops->runtime_resume)
+ ret = xdna->dev_info->ops->runtime_resume(xdna);
+
+ XDNA_DBG(xdna, "Runtime resume done ret %d", ret);
+ return ret;
+}
+
int amdxdna_pm_resume_get(struct amdxdna_dev *xdna)
{
struct device *dev = xdna->ddev.dev;
int ret;

+ if (!pm_runtime_enabled(dev))
+ return 0;
+
ret = pm_runtime_resume_and_get(dev);
if (ret) {
XDNA_ERR(xdna, "Resume failed: %d", ret);
@@ -55,6 +84,10 @@ void amdxdna_pm_suspend_put(struct amdxdna_dev *xdna)
{
struct device *dev = xdna->ddev.dev;

+ if (!pm_runtime_enabled(dev))
+ return;
+
+ pm_runtime_mark_last_busy(dev);
pm_runtime_put_autosuspend(dev);
}

@@ -66,6 +99,7 @@ void amdxdna_pm_init(struct amdxdna_dev *xdna)
pm_runtime_set_autosuspend_delay(dev, AMDXDNA_AUTOSUSPEND_DELAY);
pm_runtime_use_autosuspend(dev);
pm_runtime_allow(dev);
+ pm_runtime_mark_last_busy(dev);
pm_runtime_put_autosuspend(dev);
}

diff --git a/drivers/accel/amdxdna/amdxdna_pm.h b/drivers/accel/amdxdna/amdxdna_pm.h
index 3d26b973e0e3..26df3d50d8ea 100644
--- a/drivers/accel/amdxdna/amdxdna_pm.h
+++ b/drivers/accel/amdxdna/amdxdna_pm.h
@@ -9,7 +9,9 @@
#include "amdxdna_pci_drv.h"

int amdxdna_pm_suspend(struct device *dev);
-int amdxdna_pm_resume(struct device *dev);
+int amdxdna_pm_resume(struct device *dev);
+int amdxdna_pm_runtime_suspend(struct device *dev);
+int amdxdna_pm_runtime_resume(struct device *dev);
int amdxdna_pm_resume_get(struct amdxdna_dev *xdna);
void amdxdna_pm_suspend_put(struct amdxdna_dev *xdna);
void amdxdna_pm_init(struct amdxdna_dev *xdna);
--
2.34.1