powerpc/eeh: fix recursive pci_lock_rescan_remove locking in EEH event handling (815a8d2f) · Commits · git / linux-net

arch/powerpc/include/asm/eeh.h

+2 −0

Original line number	Diff line number	Diff line
		@@ -289,6 +289,8 @@ void eeh_pe_dev_traverse(struct eeh_pe *root,
		void eeh_pe_restore_bars(struct eeh_pe *pe);
		const char eeh_pe_loc_get(struct eeh_pe pe);
		struct pci_bus eeh_pe_bus_get(struct eeh_pe pe);
		const char eeh_pe_loc_get_bus(struct pci_bus bus);
		struct pci_bus eeh_pe_bus_get_nolock(struct eeh_pe pe);

		void eeh_show_enabled(void);
		int __init eeh_init(struct eeh_ops *ops);

arch/powerpc/kernel/eeh_driver.c

+6 −5

Original line number	Diff line number	Diff line
		@@ -846,7 +846,7 @@ void eeh_handle_normal_event(struct eeh_pe *pe)

		pci_lock_rescan_remove();

		bus = eeh_pe_bus_get(pe);
		bus = eeh_pe_bus_get_nolock(pe);
		if (!bus) {
		pr_err("%s: Cannot find PCI bus for PHB#%x-PE#%x\n",
		__func__, pe->phb->global_number, pe->addr);
		@@ -886,14 +886,15 @@ void eeh_handle_normal_event(struct eeh_pe *pe)
		/* Log the event */
		if (pe->type & EEH_PE_PHB) {
		pr_err("EEH: Recovering PHB#%x, location: %s\n",
		pe->phb->global_number, eeh_pe_loc_get(pe));
		pe->phb->global_number, eeh_pe_loc_get_bus(bus));
		} else {
		struct eeh_pe *phb_pe = eeh_phb_pe_get(pe->phb);

		pr_err("EEH: Recovering PHB#%x-PE#%x\n",
		pe->phb->global_number, pe->addr);
		pr_err("EEH: PE location: %s, PHB location: %s\n",
		eeh_pe_loc_get(pe), eeh_pe_loc_get(phb_pe));
		eeh_pe_loc_get_bus(bus),
		eeh_pe_loc_get_bus(eeh_pe_bus_get_nolock(phb_pe)));
		}

		#ifdef CONFIG_STACKTRACE
		@@ -1098,7 +1099,7 @@ void eeh_handle_normal_event(struct eeh_pe *pe)
		eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true);
		eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);

		bus = eeh_pe_bus_get(pe);
		bus = eeh_pe_bus_get_nolock(pe);
		if (bus)
		pci_hp_remove_devices(bus);
		else
		@@ -1222,7 +1223,7 @@ void eeh_handle_special_event(void)
		(phb_pe->state & EEH_PE_RECOVERING))
		continue;

		bus = eeh_pe_bus_get(phb_pe);
		bus = eeh_pe_bus_get_nolock(phb_pe);
		if (!bus) {
		pr_err("%s: Cannot find PCI bus for "
		"PHB#%x-PE#%x\n",

arch/powerpc/kernel/eeh_pe.c

+70 −4

Original line number	Diff line number	Diff line
		@@ -812,6 +812,24 @@ void eeh_pe_restore_bars(struct eeh_pe *pe)
		const char eeh_pe_loc_get(struct eeh_pe pe)
		{
		struct pci_bus *bus = eeh_pe_bus_get(pe);
		return eeh_pe_loc_get_bus(bus);
		}

		/**
		* eeh_pe_loc_get_bus - Retrieve location code binding to the given PCI bus
		* @bus: PCI bus
		*
		* Retrieve the location code associated with the given PCI bus. If the bus
		* is a root bus, the location code is fetched from the PHB device tree node
		* or root port. Otherwise, the location code is obtained from the device
		* tree node of the upstream bridge of the bus. The function walks up the
		* bus hierarchy if necessary, checking each node for the appropriate
		* location code property ("ibm,io-base-loc-code" for root buses,
		* "ibm,slot-location-code" for others). If no location code is found,
		* returns "N/A".
		*/
		const char eeh_pe_loc_get_bus(struct pci_bus bus)
		{
		struct device_node *dn;
		const char *loc = NULL;

		@@ -838,8 +856,9 @@ const char eeh_pe_loc_get(struct eeh_pe pe)
		}

		/**
		* eeh_pe_bus_get - Retrieve PCI bus according to the given PE
		* _eeh_pe_bus_get - Retrieve PCI bus according to the given PE
		* @pe: EEH PE
		* @do_lock: Is the caller already held the pci_lock_rescan_remove?
		*
		* Retrieve the PCI bus according to the given PE. Basically,
		* there're 3 types of PEs: PHB/Bus/Device. For PHB PE, the
		@@ -847,7 +866,7 @@ const char eeh_pe_loc_get(struct eeh_pe pe)
		* returned for BUS PE. However, we don't have associated PCI
		* bus for DEVICE PE.
		*/
		struct pci_bus eeh_pe_bus_get(struct eeh_pe pe)
		static struct pci_bus _eeh_pe_bus_get(struct eeh_pe pe, bool do_lock)
		{
		struct eeh_dev *edev;
		struct pci_dev *pdev;
		@@ -862,11 +881,58 @@ struct pci_bus eeh_pe_bus_get(struct eeh_pe pe)

		/* Retrieve the parent PCI bus of first (top) PCI device */
		edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, entry);
		if (do_lock)
		pci_lock_rescan_remove();
		pdev = eeh_dev_to_pci_dev(edev);
		if (pdev)
		bus = pdev->bus;
		if (do_lock)
		pci_unlock_rescan_remove();

		return bus;
		}

		/**
		* eeh_pe_bus_get - Retrieve PCI bus associated with the given EEH PE, locking
		* if needed
		* @pe: Pointer to the EEH PE
		*
		* This function is a wrapper around _eeh_pe_bus_get(), which retrieves the PCI
		* bus associated with the provided EEH PE structure. It acquires the PCI
		* rescans lock to ensure safe access to shared data during the retrieval
		* process. This function should be used when the caller requires the PCI bus
		* while holding the rescan/remove lock, typically during operations that modify
		* or inspect PCIe device state in a safe manner.
		*
		* RETURNS:
		* A pointer to the PCI bus associated with the EEH PE, or NULL if none found.
		*/

		struct pci_bus eeh_pe_bus_get(struct eeh_pe pe)
		{
		return _eeh_pe_bus_get(pe, true);
		}

		/**
		* eeh_pe_bus_get_nolock - Retrieve PCI bus associated with the given EEH PE
		* without locking
		* @pe: Pointer to the EEH PE
		*
		* This function is a variant of _eeh_pe_bus_get() that retrieves the PCI bus
		* associated with the specified EEH PE without acquiring the
		* pci_lock_rescan_remove lock. It should only be used when the caller can
		* guarantee safe access to PE structures without the need for that lock,
		* typically in contexts where the lock is already held locking is otherwise
		* managed.
		*
		* RETURNS:
		* pointer to the PCI bus associated with the EEH PE, or NULL if none is found.
		*
		* NOTE:
		* Use this function carefully to avoid race conditions and data corruption.
		*/

		struct pci_bus eeh_pe_bus_get_nolock(struct eeh_pe pe)
		{
		return _eeh_pe_bus_get(pe, false);
		}