PCI/ASPM: Fix deadlock when enabling ASPM

A last minute revert in 6.7-final introduced a potential deadlock when
enabling ASPM during probe of Qualcomm PCIe controllers as reported by
lockdep:

  ============================================
  WARNING: possible recursive locking detected
  6.7.0 #40 Not tainted
  --------------------------------------------
  kworker/u16:5/90 is trying to acquire lock:
  ffffacfa78ced000 (pci_bus_sem){++++}-{3:3}, at: pcie_aspm_pm_state_change+0x58/0xdc

              but task is already holding lock:
  ffffacfa78ced000 (pci_bus_sem){++++}-{3:3}, at: pci_walk_bus+0x34/0xbc

              other info that might help us debug this:
   Possible unsafe locking scenario:

         CPU0
         ----
    lock(pci_bus_sem);
    lock(pci_bus_sem);

               *** DEADLOCK ***

  Call trace:
   print_deadlock_bug+0x25c/0x348
   __lock_acquire+0x10a4/0x2064
   lock_acquire+0x1e8/0x318
   down_read+0x60/0x184
   pcie_aspm_pm_state_change+0x58/0xdc
   pci_set_full_power_state+0xa8/0x114
   pci_set_power_state+0xc4/0x120
   qcom_pcie_enable_aspm+0x1c/0x3c [pcie_qcom]
   pci_walk_bus+0x64/0xbc
   qcom_pcie_host_post_init_2_7_0+0x28/0x34 [pcie_qcom]

The deadlock can easily be reproduced on machines like the Lenovo ThinkPad
X13s by adding a delay to increase the race window during asynchronous
probe where another thread can take a write lock.

Add a new pci_set_power_state_locked() and associated helper functions that
can be called with the PCI bus semaphore held to avoid taking the read lock
twice.

Link: https://lore.kernel.org/r/ZZu0qx2cmn7IwTyQ@hovoldconsulting.com
Link: https://lore.kernel.org/r/20240130100243.11011-1-johan+linaro@kernel.org
Fixes: f93e71aea6c6 ("Revert "PCI/ASPM: Remove pcie_aspm_pm_state_change()"")
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: <stable@vger.kernel.org>	# 6.7

1 files changed, 32 insertions, 17 deletions

diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 9c2137dae429..826b5016a101 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -386,21 +386,8 @@ void pci_bus_add_devices(const struct pci_bus *bus)
 }
 EXPORT_SYMBOL(pci_bus_add_devices);
 
-/** pci_walk_bus - walk devices on/under bus, calling callback.
- *  @top      bus whose devices should be walked
- *  @cb       callback to be called for each device found
- *  @userdata arbitrary pointer to be passed to callback.
- *
- *  Walk the given bus, including any bridged devices
- *  on buses under this bus.  Call the provided callback
- *  on each device found.
- *
- *  We check the return of @cb each time. If it returns anything
- *  other than 0, we break out.
- *
- */
-void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
-		  void *userdata)
+static void __pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
+			   void *userdata, bool locked)
 {
 	struct pci_dev *dev;
 	struct pci_bus *bus;
@@ -408,7 +395,8 @@ void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
 	int retval;
 
 	bus = top;
-	down_read(&pci_bus_sem);
+	if (!locked)
+		down_read(&pci_bus_sem);
 	next = top->devices.next;
 	for (;;) {
 		if (next == &bus->devices) {
@@ -431,10 +419,37 @@ void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
 		if (retval)
 			break;
 	}
-	up_read(&pci_bus_sem);
+	if (!locked)
+		up_read(&pci_bus_sem);
+}
+
+/**
+ *  pci_walk_bus - walk devices on/under bus, calling callback.
+ *  @top: bus whose devices should be walked
+ *  @cb: callback to be called for each device found
+ *  @userdata: arbitrary pointer to be passed to callback
+ *
+ *  Walk the given bus, including any bridged devices
+ *  on buses under this bus.  Call the provided callback
+ *  on each device found.
+ *
+ *  We check the return of @cb each time. If it returns anything
+ *  other than 0, we break out.
+ */
+void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata)
+{
+	__pci_walk_bus(top, cb, userdata, false);
 }
 EXPORT_SYMBOL_GPL(pci_walk_bus);
 
+void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata)
+{
+	lockdep_assert_held(&pci_bus_sem);
+
+	__pci_walk_bus(top, cb, userdata, true);
+}
+EXPORT_SYMBOL_GPL(pci_walk_bus_locked);
+
 struct pci_bus *pci_bus_get(struct pci_bus *bus)
 {
 	if (bus)