From: Dan Williams dan.j.williams@intel.com
[ Upstream commit a4e772898f8bf2e7e1cf661a12c60a5612c4afab ]
One of the true positives that the cfg_access_lock lockdep effort identified is this sequence:
WARNING: CPU: 14 PID: 1 at drivers/pci/pci.c:4886 pci_bridge_secondary_bus_reset+0x5d/0x70 RIP: 0010:pci_bridge_secondary_bus_reset+0x5d/0x70 Call Trace: <TASK> ? __warn+0x8c/0x190 ? pci_bridge_secondary_bus_reset+0x5d/0x70 ? report_bug+0x1f8/0x200 ? handle_bug+0x3c/0x70 ? exc_invalid_op+0x18/0x70 ? asm_exc_invalid_op+0x1a/0x20 ? pci_bridge_secondary_bus_reset+0x5d/0x70 pci_reset_bus+0x1d8/0x270 vmd_probe+0x778/0xa10 pci_device_probe+0x95/0x120
Where pci_reset_bus() users are triggering unlocked secondary bus resets. Ironically pci_bus_reset(), several calls down from pci_reset_bus(), uses pci_bus_lock() before issuing the reset which locks everything *but* the bridge itself.
For the same motivation as adding:
bridge = pci_upstream_bridge(dev); if (bridge) pci_dev_lock(bridge);
to pci_reset_function() for the "bus" and "cxl_bus" reset cases, add pci_dev_lock() for @bus->self to pci_bus_lock().
Link: https://lore.kernel.org/r/171711747501.1628941.15217746952476635316.stgit@dw... Reported-by: Imre Deak imre.deak@intel.com Closes: http://lore.kernel.org/r/6657833b3b5ae_14984b29437@dwillia2-xfh.jf.intel.com... Signed-off-by: Dan Williams dan.j.williams@intel.com Signed-off-by: Keith Busch kbusch@kernel.org [bhelgaas: squash in recursive locking deadlock fix from Keith Busch: https://lore.kernel.org/r/20240711193650.701834-1-kbusch@meta.com] Signed-off-by: Bjorn Helgaas bhelgaas@google.com Tested-by: Hans de Goede hdegoede@redhat.com Tested-by: Kalle Valo kvalo@kernel.org Reviewed-by: Dave Jiang dave.jiang@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pci/pci.c | 35 +++++++++++++++++++++-------------- 1 file changed, 21 insertions(+), 14 deletions(-)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 67216f4ea2151..84c1300afb951 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -5491,10 +5491,12 @@ static void pci_bus_lock(struct pci_bus *bus) { struct pci_dev *dev;
+ pci_dev_lock(bus->self); list_for_each_entry(dev, &bus->devices, bus_list) { - pci_dev_lock(dev); if (dev->subordinate) pci_bus_lock(dev->subordinate); + else + pci_dev_lock(dev); } }
@@ -5506,8 +5508,10 @@ static void pci_bus_unlock(struct pci_bus *bus) list_for_each_entry(dev, &bus->devices, bus_list) { if (dev->subordinate) pci_bus_unlock(dev->subordinate); - pci_dev_unlock(dev); + else + pci_dev_unlock(dev); } + pci_dev_unlock(bus->self); }
/* Return 1 on successful lock, 0 on contention */ @@ -5515,15 +5519,15 @@ static int pci_bus_trylock(struct pci_bus *bus) { struct pci_dev *dev;
+ if (!pci_dev_trylock(bus->self)) + return 0; + list_for_each_entry(dev, &bus->devices, bus_list) { - if (!pci_dev_trylock(dev)) - goto unlock; if (dev->subordinate) { - if (!pci_bus_trylock(dev->subordinate)) { - pci_dev_unlock(dev); + if (!pci_bus_trylock(dev->subordinate)) goto unlock; - } - } + } else if (!pci_dev_trylock(dev)) + goto unlock; } return 1;
@@ -5531,8 +5535,10 @@ static int pci_bus_trylock(struct pci_bus *bus) list_for_each_entry_continue_reverse(dev, &bus->devices, bus_list) { if (dev->subordinate) pci_bus_unlock(dev->subordinate); - pci_dev_unlock(dev); + else + pci_dev_unlock(dev); } + pci_dev_unlock(bus->self); return 0; }
@@ -5564,9 +5570,10 @@ static void pci_slot_lock(struct pci_slot *slot) list_for_each_entry(dev, &slot->bus->devices, bus_list) { if (!dev->slot || dev->slot != slot) continue; - pci_dev_lock(dev); if (dev->subordinate) pci_bus_lock(dev->subordinate); + else + pci_dev_lock(dev); } }
@@ -5592,14 +5599,13 @@ static int pci_slot_trylock(struct pci_slot *slot) list_for_each_entry(dev, &slot->bus->devices, bus_list) { if (!dev->slot || dev->slot != slot) continue; - if (!pci_dev_trylock(dev)) - goto unlock; if (dev->subordinate) { if (!pci_bus_trylock(dev->subordinate)) { pci_dev_unlock(dev); goto unlock; } - } + } else if (!pci_dev_trylock(dev)) + goto unlock; } return 1;
@@ -5610,7 +5616,8 @@ static int pci_slot_trylock(struct pci_slot *slot) continue; if (dev->subordinate) pci_bus_unlock(dev->subordinate); - pci_dev_unlock(dev); + else + pci_dev_unlock(dev); } return 0; }