Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 3e401f7a authored by Thiago Jung Bauermann's avatar Thiago Jung Bauermann Committed by Thomas Gleixner
Browse files

powerpc: Only obtain cpu_hotplug_lock if called by rtasd 



Calling arch_update_cpu_topology from a CPU hotplug state machine callback
hits a deadlock because the function tries to get a read lock on
cpu_hotplug_lock while the state machine still holds a write lock on it.

Since all callers of arch_update_cpu_topology except rtasd already hold
cpu_hotplug_lock, this patch changes the function to use
stop_machine_cpuslocked and creates a separate function for rtasd which
still tries to obtain the lock.

Michael Bringmann investigated the bug and provided a detailed analysis
of the deadlock on this previous RFC for an alternate solution:

Signed-off-by: default avatarThiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
Signed-off-by: default avatarThomas Gleixner <tglx@linutronix.de>
Acked-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
Cc: John Allen <jallen@linux.vnet.ibm.com>
Cc: Michael Bringmann <mwb@linux.vnet.ibm.com>
Cc: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Cc: linuxppc-dev@lists.ozlabs.org
Link: http://lkml.kernel.org/r/1497996510-4032-1-git-send-email-bauerman@linux.vnet.ibm.com
Link: https://patchwork.ozlabs.org/patch/771293/
parent 1b3b2250

arch/powerpc/include/asm/topology.h

+6 −0
Original line number Diff line number Diff line
@@ -43,6 +43,7 @@ extern void __init dump_numa_cpu_topology(void); 


extern int sysfs_add_device_to_node(struct device *dev, int nid);

extern void sysfs_remove_device_from_node(struct device *dev, int nid);

extern int numa_update_cpu_topology(bool cpus_locked);



#else
@@ -57,6 +58,11 @@ static inline void sysfs_remove_device_from_node(struct device *dev, 
						int nid)

{

}



static inline int numa_update_cpu_topology(bool cpus_locked)

{

	return 0;

}

#endif /* CONFIG_NUMA */



#if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)

arch/powerpc/kernel/rtasd.c

+1 −1
Original line number Diff line number Diff line
@@ -283,7 +283,7 @@ static void prrn_work_fn(struct work_struct *work) 
	 * the RTAS event.

	 */

	pseries_devicetree_update(-prrn_update_scope);

	arch_update_cpu_topology();

	numa_update_cpu_topology(false);

}



static DECLARE_WORK(prrn_work, prrn_work_fn);

arch/powerpc/mm/numa.c

+19 −3
Original line number Diff line number Diff line
@@ -1311,8 +1311,10 @@ static int update_lookup_table(void *data) 
/*

 * Update the node maps and sysfs entries for each cpu whose home node

 * has changed. Returns 1 when the topology has changed, and 0 otherwise.

 *

 * cpus_locked says whether we already hold cpu_hotplug_lock.

 */

int arch_update_cpu_topology(void)

int numa_update_cpu_topology(bool cpus_locked)

{

	unsigned int cpu, sibling, changed = 0;

	struct topology_update_data *updates, *ud;
@@ -1400,6 +1402,10 @@ int arch_update_cpu_topology(void) 
	if (!cpumask_weight(&updated_cpus))

		goto out;



	if (cpus_locked)

		stop_machine_cpuslocked(update_cpu_topology, &updates[0],

					&updated_cpus);

	else

		stop_machine(update_cpu_topology, &updates[0], &updated_cpus);



	/*
@@ -1407,6 +1413,10 @@ int arch_update_cpu_topology(void) 
	 * offline CPUs. It is best to perform this update from the stop-

	 * machine context.

	 */

	if (cpus_locked)

		stop_machine_cpuslocked(update_lookup_table, &updates[0],

					cpumask_of(raw_smp_processor_id()));

	else

		stop_machine(update_lookup_table, &updates[0],

			     cpumask_of(raw_smp_processor_id()));
@@ -1426,6 +1436,12 @@ int arch_update_cpu_topology(void) 
	return changed;

}



int arch_update_cpu_topology(void)

{

	lockdep_assert_cpus_held();

	return numa_update_cpu_topology(true);

}



static void topology_work_fn(struct work_struct *work)

{

	rebuild_sched_domains();