* [PATCH v4 1/4] driver core: add device_schedule_reprobe()
2026-10-17 8:55 [PATCH v4 0/4] device_schedule_reprobe(): core helper and conversions Daniel Golle
@ 2026-10-17 8:56 ` Daniel Golle
2026-10-17 8:56 ` [PATCH v4 2/4] wifi: iwlwifi: use device_schedule_reprobe() Daniel Golle
` (2 subsequent siblings)
3 siblings, 0 replies; 5+ messages in thread
From: Daniel Golle @ 2026-10-17 8:56 UTC (permalink / raw)
To: Greg Kroah-Hartman, Rafael J. Wysocki, Danilo Krummrich,
Marcel Holtmann, Luiz Augusto von Dentz, Miri Korenblit,
Emmanuel Grumbach, Hans de Goede, driver-core, linux-kernel,
linux-bluetooth, linux-wireless
iwlwifi and hci_h5 re-probe their own device from a work item in module
text that ends with module_put(THIS_MODULE). Once the count drops, a
concurrent rmmod can free the module while the work still runs: the
text of its epilogue and, with lockdep, the work's lock class key. Nor
is the re-probe tied to the binding that scheduled it, which a driver
cannot check from outside device_reprobe().
Add device_schedule_reprobe(), a delayed detach and re-probe run from
built-in work. One request per device is kept in struct device_private
and cancelled by device_unbind_cleanup(), so it ends with the binding
that scheduled it, by an unbind, a removal or a failed probe. The
caller is the bound driver, in a context its ->remove() waits for; no
lock is taken there, so the device lock may be held. Buses that take
the parent lock to bind are refused, as the parent can change before
the work runs.
Assisted-by: LLM
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
---
v4: reworked as patch 3/6 of the mxl862xx devlink flash series, v13 to
v19 [1][2], mostly after Sashiko AI review there: one request per
device, cancelled with the binding, replaces the driver pointer
check and shutdown_done; parent-lock buses are refused, the parent
is not pinned; no lock in the caller's context; freezable work; no
error message of its own; Hans de Goede's tags dropped
[1] https://lore.kernel.org/all/cover.1788783126.git.daniel@makrotopia.org/
[2] https://lore.kernel.org/all/cover.1791035885.git.daniel@makrotopia.org/
v3: use dev_err_probe() for the re-probe error path, so a re-probe
deferred at resume no longer logs a spurious error (Hans de Goede)
v2: pin the parent across the deferred work and re-lock it across
device_attach() on need_parent_lock buses; schedule on system_dfl_wq
rather than the deprecated system_unbound_wq (found reviewing the
mxl862xx v12 posting)
v1: initial RFC
---
drivers/base/base.h | 4 +
drivers/base/dd.c | 171 +++++++++++++++++++++++++++++++++++++++++
include/linux/device.h | 2 +
3 files changed, 177 insertions(+)
diff --git a/drivers/base/base.h b/drivers/base/base.h
index a5b7abc10ff02..3a6883de7cef3 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -106,6 +106,9 @@ struct driver_private {
* @dead: This device is currently either in the process of or has been
* removed from the system. Any asynchronous events scheduled for this
* device should exit without taking any action.
+ * @reprobe: request scheduled with device_schedule_reprobe(), held until
+ * its work has released the driver; cancelled when the binding
+ * that scheduled it ends
*
* Nothing outside of the driver core should ever touch these fields.
*/
@@ -119,6 +122,7 @@ struct device_private {
const struct device_driver *async_driver;
char *deferred_probe_reason;
struct device *device;
+ struct device_reprobe *reprobe;
u8 dead:1;
};
#define to_device_private_parent(obj) \
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index f6525a7ee8c54..1ec740f0e4816 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -590,6 +590,40 @@ static ssize_t state_synced_show(struct device *dev,
}
static DEVICE_ATTR_RW(state_synced);
+struct device_reprobe {
+ struct delayed_work work;
+ struct device *dev;
+};
+
+/* Ties the slot in struct device_private to the queueing of its work. */
+static DEFINE_SPINLOCK(device_reprobe_lock);
+
+static void device_reprobe_free(struct device_reprobe *rp)
+{
+ put_device(rp->dev);
+ kfree(rp);
+}
+
+/*
+ * The slot holds a request from its scheduling until its work has released
+ * the driver. A pending work is freed here; a running one finds the slot no
+ * longer its own and frees itself.
+ */
+static void device_reprobe_cancel(struct device *dev)
+{
+ struct device_reprobe *rp;
+ bool pending = false;
+
+ spin_lock(&device_reprobe_lock);
+ rp = dev->p->reprobe;
+ WRITE_ONCE(dev->p->reprobe, NULL);
+ if (rp)
+ pending = cancel_delayed_work(&rp->work);
+ spin_unlock(&device_reprobe_lock);
+ if (pending)
+ device_reprobe_free(rp);
+}
+
static void device_unbind_cleanup(struct device *dev)
{
if (dev->driver->p_cb.post_unbind_rust)
@@ -599,6 +633,7 @@ static void device_unbind_cleanup(struct device *dev)
kfree(dev->dma_range_map);
dev->dma_range_map = NULL;
device_set_driver(dev, NULL);
+ device_reprobe_cancel(dev);
dev_set_drvdata(dev, NULL);
dev_pm_domain_detach(dev, dev->power.detach_power_off);
if (dev->pm_domain && dev->pm_domain->dismiss)
@@ -1436,3 +1471,139 @@ void driver_detach(const struct device_driver *drv)
put_device(dev);
}
}
+
+/* Retry interval while probing is blocked; the caller's delay may be 0. */
+#define DEVICE_REPROBE_BLOCKED_RETRY HZ
+
+static void device_reprobe_work_fn(struct work_struct *work)
+{
+ struct device_reprobe *rp = container_of(work, struct device_reprobe,
+ work.work);
+ struct device *dev = rp->dev;
+ bool rearm;
+ int ret;
+
+ device_lock(dev);
+ /* The slot still holding rp means the binding that scheduled it does. */
+ if (dev->p->dead || READ_ONCE(dev->p->reprobe) != rp) {
+ device_unlock(dev);
+ goto out;
+ }
+ /* A stale read means one more retry or a probe that defers itself. */
+ if (data_race(defer_all_probes)) {
+ device_unlock(dev);
+ spin_lock(&device_reprobe_lock);
+ rearm = dev->p->reprobe == rp &&
+ (system_state < SYSTEM_HALT ||
+ system_state == SYSTEM_SUSPEND) &&
+ queue_delayed_work(system_freezable_wq, &rp->work,
+ DEVICE_REPROBE_BLOCKED_RETRY);
+ spin_unlock(&device_reprobe_lock);
+ if (rearm)
+ return;
+ goto out;
+ }
+ /* Releasing the driver clears the slot, which was this request. */
+ __device_release_driver(dev, NULL);
+ device_unlock(dev);
+
+ /* A failed probe is logged by the probe path, as for a first probe. */
+ ret = device_attach(dev);
+ dev_dbg(dev, "re-probe: device_attach() returned %d\n", ret);
+out:
+ spin_lock(&device_reprobe_lock);
+ if (dev->p->reprobe == rp)
+ WRITE_ONCE(dev->p->reprobe, NULL);
+ spin_unlock(&device_reprobe_lock);
+ device_reprobe_free(rp);
+}
+
+/**
+ * device_schedule_reprobe - schedule a deferred detach and re-probe
+ * @dev: device to detach and re-probe
+ * @delay_ms: delay in milliseconds before the re-probe runs
+ *
+ * Schedule a detach and re-probe of @dev after @delay_ms milliseconds,
+ * from built-in driver-core work rather than a driver-owned work item,
+ * so the bound driver may call it without pinning its own module.
+ *
+ * At most one request exists per device, from its scheduling until its
+ * work has released the driver, and the request identifies the binding
+ * that scheduled it. It is cancelled when that binding ends, whether by
+ * an unbind, by the deletion of @dev or by a failed probe, so neither an
+ * unbind followed by a rebind nor a module reload within the delay gets a
+ * re-probe it did not ask for; its reference on @dev is dropped with it,
+ * or once a work already running has finished. A request that fires
+ * while probing is blocked for a system suspend or a hibernation restore
+ * re-arms itself every second and runs once the system has resumed; one
+ * that fires while probing is blocked for a halt, power-off or restart is
+ * dropped. A failed re-probe leaves @dev unbound, as a failed initial
+ * probe would, and is logged by the probe path like one.
+ *
+ * This is device_reprobe() deferred, and shares its limitations; the
+ * release path of __device_release_driver() is untouched. The detach and
+ * the re-attach are not one locked operation, so an administrative unbind
+ * arriving between them may be undone. If @dev has managed consumers,
+ * detaching it unbinds them as any driver release does, so a re-probe a
+ * concurrent device_shutdown() overtakes may run ->remove() after
+ * ->shutdown(). None of this is specific to this helper.
+ *
+ * Buses that take the parent lock to bind (only usb_bus_type) are refused
+ * with -EINVAL: the parent would have to be recorded before either lock
+ * is held, where device_move() can replace it.
+ *
+ * Context: May sleep (allocates with %GFP_KERNEL). Must be called by the
+ * driver bound to @dev, from a process context its ->remove() waits for,
+ * so that the binding outlives the call; @dev's own device lock may be
+ * held. A request from ->probe() runs once the probe has returned and is
+ * cancelled if the probe fails.
+ *
+ * Returns: 0 on success, -EINVAL if @dev is not a registered device
+ * bound to a driver or sits on a bus which takes the parent lock to
+ * bind, -EBUSY if a re-probe of @dev is pending or has not yet released
+ * the driver, -ENOMEM on allocation failure.
+ */
+int device_schedule_reprobe(struct device *dev, unsigned int delay_ms)
+{
+ const struct device_driver *drv;
+ struct device_reprobe *rp;
+ int ret = 0;
+
+ drv = READ_ONCE(dev->driver);
+ /*
+ * A bus taking the parent lock would need @dev's parent pinned until
+ * the work runs, which device_move() can invalidate.
+ */
+ if (!drv || !dev->bus || dev->bus->need_parent_lock || !dev->p ||
+ !device_is_registered(dev))
+ return -EINVAL;
+
+ rp = kzalloc_obj(*rp);
+ if (!rp)
+ return -ENOMEM;
+
+ rp->dev = get_device(dev);
+ INIT_DELAYED_WORK(&rp->work, device_reprobe_work_fn);
+
+ /*
+ * A release that got here first has cleared the driver before
+ * cancelling, so a request published after its cancel is refused
+ * here; one published before is cancelled by it.
+ */
+ spin_lock(&device_reprobe_lock);
+ if (dev->p->reprobe)
+ ret = -EBUSY;
+ else if (READ_ONCE(dev->driver) != drv)
+ ret = -EINVAL;
+ else
+ WRITE_ONCE(dev->p->reprobe, rp);
+ if (!ret)
+ queue_delayed_work(system_freezable_wq, &rp->work,
+ msecs_to_jiffies(delay_ms));
+ spin_unlock(&device_reprobe_lock);
+ if (ret)
+ device_reprobe_free(rp);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(device_schedule_reprobe);
diff --git a/include/linux/device.h b/include/linux/device.h
index aee79fd6b32b4..7a99169505772 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1314,6 +1314,8 @@ int __must_check device_attach(struct device *dev);
int __must_check driver_attach(const struct device_driver *drv);
void device_initial_probe(struct device *dev);
int __must_check device_reprobe(struct device *dev);
+int __must_check device_schedule_reprobe(struct device *dev,
+ unsigned int delay_ms);
bool device_is_bound(struct device *dev);
--
2.56.0
^ permalink raw reply related [flat|nested] 5+ messages in thread* [PATCH v4 2/4] wifi: iwlwifi: use device_schedule_reprobe()
2026-10-17 8:55 [PATCH v4 0/4] device_schedule_reprobe(): core helper and conversions Daniel Golle
2026-10-17 8:56 ` [PATCH v4 1/4] driver core: add device_schedule_reprobe() Daniel Golle
@ 2026-10-17 8:56 ` Daniel Golle
2026-10-17 8:56 ` [PATCH v4 3/4] Bluetooth: hci_h5: " Daniel Golle
2026-10-17 8:57 ` [PATCH v4 4/4] Bluetooth: btintel_pcie: use device_schedule_reprobe() after reset Daniel Golle
3 siblings, 0 replies; 5+ messages in thread
From: Daniel Golle @ 2026-10-17 8:56 UTC (permalink / raw)
To: Greg Kroah-Hartman, Rafael J. Wysocki, Danilo Krummrich,
Marcel Holtmann, Luiz Augusto von Dentz, Miri Korenblit,
Emmanuel Grumbach, Hans de Goede, driver-core, linux-kernel,
linux-bluetooth, linux-wireless
iwl_trans_schedule_reprobe() runs device_reprobe() from a work item in
module text that ends with module_put(THIS_MODULE), so a concurrent
rmmod can free the module while the work still runs, and a stale
re-probe can undo an unbind. With the work held just past module_put()
by a test-only delay, rmmod ends in a lockdep oops on the work's lock
class, freed with the module. Use device_schedule_reprobe(); both
callers run in iwl_trans_restart_wk(), which ->remove() cancels
synchronously.
A pending re-probe no longer pins the module: rmmod succeeds and
cancels it.
Fixes: ac1ed4163b5a ("iwlwifi: mvm: reprobe device on firmware error during restart")
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
---
v4: commit message updated for the reworked helper; add Fixes:
v3: no changes
v2: no changes
v1: initial RFC
.../net/wireless/intel/iwlwifi/iwl-trans.c | 40 +------------------
1 file changed, 2 insertions(+), 38 deletions(-)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
index 73aae11250421..5ae734cb90272 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
@@ -78,47 +78,11 @@ void iwl_trans_free_restart_list(void)
}
}
-struct iwl_trans_reprobe {
- struct device *dev;
- struct delayed_work work;
-};
-
-static void iwl_trans_reprobe_wk(struct work_struct *wk)
-{
- struct iwl_trans_reprobe *reprobe;
-
- reprobe = container_of(wk, typeof(*reprobe), work.work);
-
- if (device_reprobe(reprobe->dev))
- dev_err(reprobe->dev, "reprobe failed!\n");
- put_device(reprobe->dev);
- kfree(reprobe);
- module_put(THIS_MODULE);
-}
-
static void iwl_trans_schedule_reprobe(struct iwl_trans *trans,
unsigned int delay_ms)
{
- struct iwl_trans_reprobe *reprobe;
-
- /*
- * get a module reference to avoid doing this while unloading
- * anyway and to avoid scheduling a work with code that's
- * being removed.
- */
- if (!try_module_get(THIS_MODULE)) {
- IWL_ERR(trans, "Module is being unloaded - abort\n");
- return;
- }
-
- reprobe = kzalloc_obj(*reprobe);
- if (!reprobe) {
- module_put(THIS_MODULE);
- return;
- }
- reprobe->dev = get_device(trans->dev);
- INIT_DELAYED_WORK(&reprobe->work, iwl_trans_reprobe_wk);
- schedule_delayed_work(&reprobe->work, msecs_to_jiffies(delay_ms));
+ if (device_schedule_reprobe(trans->dev, delay_ms))
+ IWL_ERR(trans, "Could not schedule reprobe\n");
}
#define IWL_TRANS_RESET_OK_TIME 7 /* seconds */
--
2.56.0
^ permalink raw reply related [flat|nested] 5+ messages in thread* [PATCH v4 3/4] Bluetooth: hci_h5: use device_schedule_reprobe()
2026-10-17 8:55 [PATCH v4 0/4] device_schedule_reprobe(): core helper and conversions Daniel Golle
2026-10-17 8:56 ` [PATCH v4 1/4] driver core: add device_schedule_reprobe() Daniel Golle
2026-10-17 8:56 ` [PATCH v4 2/4] wifi: iwlwifi: use device_schedule_reprobe() Daniel Golle
@ 2026-10-17 8:56 ` Daniel Golle
2026-10-17 8:57 ` [PATCH v4 4/4] Bluetooth: btintel_pcie: use device_schedule_reprobe() after reset Daniel Golle
3 siblings, 0 replies; 5+ messages in thread
From: Daniel Golle @ 2026-10-17 8:56 UTC (permalink / raw)
To: Greg Kroah-Hartman, Rafael J. Wysocki, Danilo Krummrich,
Marcel Holtmann, Luiz Augusto von Dentz, Miri Korenblit,
Emmanuel Grumbach, Hans de Goede, driver-core, linux-kernel,
linux-bluetooth, linux-wireless
h5_btrtl_resume() runs device_reprobe() from a work item in module text
that ends with module_put(THIS_MODULE), so a concurrent rmmod can free
the module while the work still runs, and a stale re-probe can undo an
unbind. Use device_schedule_reprobe(), which may be called from the
resume callback with the device lock held.
The re-probe now runs once tasks are thawed, after the resume has
unblocked probing.
Fixes: 8589086f4efd ("Bluetooth: hci_h5: Turn off RTL8723BS on suspend, reprobe on resume")
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Tested-by: Hans de Goede <johannes.goede@oss.qualcomm.com>
Reviewed-by: Hans de Goede <johannes.goede@oss.qualcomm.com>
---
v4: commit message updated for the reworked helper; add Fixes:; code
unchanged, so Hans de Goede's tags, given with the v3 helper, stay
v3: picked up Hans de Goede's Tested-by/Reviewed-by
v2: also correct the stale device_reprobe() reference in the
h5_btrtl_open() comment
v1: initial RFC
drivers/bluetooth/hci_h5.c | 43 ++++++--------------------------------
1 file changed, 6 insertions(+), 37 deletions(-)
diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index 37f4d9327e724..fb819d769dd52 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -989,7 +989,7 @@ static int h5_btrtl_setup(struct h5 *h5)
static void h5_btrtl_open(struct h5 *h5)
{
/*
- * Since h5_btrtl_resume() does a device_reprobe() the suspend handling
+ * Since h5_btrtl_resume() schedules a device re-probe the suspend handling
* done by the hci_suspend_notifier is not necessary; it actually causes
* delays and a bunch of errors to get logged, so disable it.
*/
@@ -1048,46 +1048,15 @@ static int h5_btrtl_suspend(struct h5 *h5)
return 0;
}
-struct h5_btrtl_reprobe {
- struct device *dev;
- struct work_struct work;
-};
-
-static void h5_btrtl_reprobe_worker(struct work_struct *work)
-{
- struct h5_btrtl_reprobe *reprobe =
- container_of(work, struct h5_btrtl_reprobe, work);
- int ret;
-
- ret = device_reprobe(reprobe->dev);
- if (ret && ret != -EPROBE_DEFER)
- dev_err(reprobe->dev, "Reprobe error %d\n", ret);
-
- put_device(reprobe->dev);
- kfree(reprobe);
- module_put(THIS_MODULE);
-}
-
static int h5_btrtl_resume(struct h5 *h5)
{
- if (test_bit(H5_WAKEUP_DISABLE, &h5->flags)) {
- struct h5_btrtl_reprobe *reprobe;
-
- reprobe = kzalloc_obj(*reprobe);
- if (!reprobe)
- return -ENOMEM;
-
- __module_get(THIS_MODULE);
+ if (test_bit(H5_WAKEUP_DISABLE, &h5->flags))
+ return device_schedule_reprobe(&h5->hu->serdev->dev, 0);
- INIT_WORK(&reprobe->work, h5_btrtl_reprobe_worker);
- reprobe->dev = get_device(&h5->hu->serdev->dev);
- queue_work(system_long_wq, &reprobe->work);
- } else {
- gpiod_set_value_cansleep(h5->device_wake_gpio, 1);
+ gpiod_set_value_cansleep(h5->device_wake_gpio, 1);
- if (test_bit(H5_HW_FLOW_CONTROL, &h5->flags))
- serdev_device_set_flow_control(h5->hu->serdev, true);
- }
+ if (test_bit(H5_HW_FLOW_CONTROL, &h5->flags))
+ serdev_device_set_flow_control(h5->hu->serdev, true);
return 0;
}
--
2.56.0
^ permalink raw reply related [flat|nested] 5+ messages in thread* [PATCH v4 4/4] Bluetooth: btintel_pcie: use device_schedule_reprobe() after reset
2026-10-17 8:55 [PATCH v4 0/4] device_schedule_reprobe(): core helper and conversions Daniel Golle
` (2 preceding siblings ...)
2026-10-17 8:56 ` [PATCH v4 3/4] Bluetooth: hci_h5: " Daniel Golle
@ 2026-10-17 8:57 ` Daniel Golle
3 siblings, 0 replies; 5+ messages in thread
From: Daniel Golle @ 2026-10-17 8:57 UTC (permalink / raw)
To: Greg Kroah-Hartman, Rafael J. Wysocki, Danilo Krummrich,
Marcel Holtmann, Luiz Augusto von Dentz, Miri Korenblit,
Emmanuel Grumbach, Hans de Goede, driver-core, linux-kernel,
linux-bluetooth, linux-wireless
The reset work re-probes its own device with device_reprobe() after an
FLR or a PLDR, so .remove() runs inside it. That needs the
current_work() check in .remove(), and 'data' must not be touched
after the call.
Schedule the re-probe with device_schedule_reprobe(). .remove() then
runs from the driver core's work, the current_work() check goes, and
disable_work_sync(&data->reset_work) waits for the reset work before
'data' is freed. Until the deferred detach 'data' stays alive but idle:
RECOVERY_IN_PROGRESS fails send_frame and coalesces further resets,
interrupts are masked, and the dump and rfkill workers stay disabled.
If scheduling fails in the FLR path, the reset work re-enables them as
on any FLR failure. The PLDR re-probe of the Wi-Fi sibling, a
different device, is unchanged.
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
---
v4: rebased onto bluetooth-next for its hardware rfkill work; commit
message updated for the reworked helper
v3: rebased onto bluetooth-next, whose btintel_pcie has four dump
workers (coredump/hwexp/fwtrigger/mbox) rather than the single one
the mainline snapshot v2 targeted
v2: reconciled to the current tree and adapted the commit message
v1: initial RFC
drivers/bluetooth/btintel_pcie.c | 47 ++++++++++++++++----------------
1 file changed, 23 insertions(+), 24 deletions(-)
diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index df95d16a163c8..9f65eb0ceb0b2 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -4093,7 +4093,7 @@ static void btintel_pcie_perform_pldr(struct btintel_pcie_data *data)
* BT needs pci_save_state()/pci_restore_state() because the BT driver
* is still partially attached when the _PRR runs (it hasn't been unbound yet).
* The PCI device needs to remain minimally functional so that
- * device_reprobe(&pdev->dev) can work afterward
+ * the deferred re-probe of the BT device can work afterward
*/
ret = btintel_pcie_acpi_reset_method(data);
@@ -4104,14 +4104,16 @@ static void btintel_pcie_perform_pldr(struct btintel_pcie_data *data)
}
if (!ret) {
- if (device_reprobe(&pdev->dev))
- BT_ERR("BT reprobe failed for BDF:%s", pci_name(pdev));
+ if (device_schedule_reprobe(&pdev->dev, 0))
+ BT_ERR("BT reprobe scheduling failed for BDF:%s",
+ pci_name(pdev));
}
}
/*
- * Issue a Function Level Reset and hand teardown/re-init off to the PCI
- * core via device_reprobe(), mirroring the PLDR path's contract.
+ * Issue a Function Level Reset and hand teardown/re-init off to the
+ * driver core via device_schedule_reprobe(), mirroring the PLDR path's
+ * contract.
*
* Caller must hold pci_lock_rescan_remove() and must have already
* disabled interrupts and drained both rx_work and coredump_work.
@@ -4133,14 +4135,12 @@ static int btintel_pcie_perform_flr(struct btintel_pcie_data *data)
return err;
}
- /* device_reprobe() always detaches the driver first (running
- * .remove(), which frees 'data'); any re-probe failure leaves the
- * device unbound but 'data' is already gone, so just log it.
- */
- if (device_reprobe(&pdev->dev))
- BT_ERR("BT reprobe failed for BDF:%s", pci_name(pdev));
+ err = device_schedule_reprobe(&pdev->dev, 0);
+ if (err)
+ BT_ERR("BT reprobe scheduling failed for BDF:%s",
+ pci_name(pdev));
- return 0;
+ return err;
}
static void btintel_pcie_reset_work(struct work_struct *wk)
@@ -4173,11 +4173,15 @@ static void btintel_pcie_reset_work(struct work_struct *wk)
disable_work_sync(&data->mbox_work);
bt_dev_dbg(data->hdev, "Release bluetooth interface");
- /* Both reset paths follow the same contract: on success they
- * destroy 'data' via device_reprobe() (a fresh probe re-INIT_WORKs
- * the dump workers with disable count 0), so enable_work() must
- * NOT be called on the success path. Only the FLR path can fail
- * with 'data' still alive, in which case we balance the
+ /* Both reset paths follow the same contract: on success the
+ * deferred re-probe scheduled with device_schedule_reprobe()
+ * destroys 'data' by re-running .probe() (which re-INIT_WORKs the
+ * dump workers with disable count 0), so enable_work() must NOT be
+ * called on the success path. 'data' stays alive until the deferred
+ * detach runs; in this window new activity is fenced by
+ * BTINTEL_PCIE_RECOVERY_IN_PROGRESS, the masked interrupts and the
+ * disabled dump workers. Only the FLR path can fail with no
+ * re-probe scheduled, in which case we balance the
* disable_work_sync() calls above so a later successful reset is
* not permanently blocked.
*
@@ -4598,13 +4602,8 @@ static void btintel_pcie_remove(struct pci_dev *pdev)
disable_work_sync(&data->fwtrigger_work);
disable_work_sync(&data->mbox_work);
- /* Cancel pending reset work. Skip only when remove() is called from
- * within the reset work itself (PLDR device_reprobe path) to avoid
- * deadlock. current_work() returns the work_struct of the caller if
- * we are in a workqueue context.
- */
- if (current_work() != &data->reset_work)
- disable_work_sync(&data->reset_work);
+ /* reset_work may still be running after scheduling the re-probe. */
+ disable_work_sync(&data->reset_work);
btintel_pcie_mask_hw_rfkill(data);
btintel_pcie_synchronize_irqs(data);
--
2.56.0
^ permalink raw reply related [flat|nested] 5+ messages in thread