From 061d19f279f9bebbdb1ee48bef8c25e03de32ae2 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Mon, 24 Jun 2013 15:30:09 -0400 Subject: powerpc: Delete __cpuinit usage from all users The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. This removes all the powerpc uses of the __cpuinit macros. There are no __CPUINIT users in assembly files in powerpc. [1] https://lkml.org/lkml/2013/5/20/589 Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Josh Boyer Cc: Matt Porter Cc: Kumar Gala Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Paul Gortmaker Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/mm/numa.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'arch/powerpc/mm/numa.c') diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 88c0425dc0a8..c792cd95e792 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -516,7 +516,7 @@ static int of_drconf_to_nid_single(struct of_drconf_cell *drmem, * Figure out to which domain a cpu belongs and stick it there. * Return the id of the domain used. */ -static int __cpuinit numa_setup_cpu(unsigned long lcpu) +static int numa_setup_cpu(unsigned long lcpu) { int nid = 0; struct device_node *cpu = of_get_cpu_node(lcpu, NULL); @@ -538,8 +538,7 @@ out: return nid; } -static int __cpuinit cpu_numa_callback(struct notifier_block *nfb, - unsigned long action, +static int cpu_numa_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned long lcpu = (unsigned long)hcpu; @@ -919,7 +918,7 @@ static void __init *careful_zallocation(int nid, unsigned long size, return ret; } -static struct notifier_block __cpuinitdata ppc64_numa_nb = { +static struct notifier_block ppc64_numa_nb = { .notifier_call = cpu_numa_callback, .priority = 1 /* Must run before sched domains notifier. */ }; -- cgit v1.2.3 From dd023217e17e72b46fb4d49c7734c426938c3dba Mon Sep 17 00:00:00 2001 From: Nathan Fontenot Date: Mon, 24 Jun 2013 22:08:05 -0500 Subject: powerpc/numa: Do not update sysfs cpu registration from invalid context The topology update code that updates the cpu node registration in sysfs should not be called while in stop_machine(). The register/unregister calls take a lock and may sleep. This patch moves these calls outside of the call to stop_machine(). Signed-off-by: Nathan Fontenot CC: Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/mm/numa.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/mm/numa.c') diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index c792cd95e792..08397217e8ac 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1432,11 +1432,9 @@ static int update_cpu_topology(void *data) if (cpu != update->cpu) continue; - unregister_cpu_under_node(update->cpu, update->old_nid); unmap_cpu_from_node(update->cpu); map_cpu_to_node(update->cpu, update->new_nid); vdso_getcpu_init(); - register_cpu_under_node(update->cpu, update->new_nid); } return 0; @@ -1484,6 +1482,9 @@ int arch_update_cpu_topology(void) stop_machine(update_cpu_topology, &updates[0], &updated_cpus); for (ud = &updates[0]; ud; ud = ud->next) { + unregister_cpu_under_node(ud->cpu, ud->old_nid); + register_cpu_under_node(ud->cpu, ud->new_nid); + dev = get_cpu_device(ud->cpu); if (dev) kobject_uevent(&dev->kobj, KOBJ_CHANGE); -- cgit v1.2.3 From 3be7db6ab45b21345386d1a466da133b19cde5e4 Mon Sep 17 00:00:00 2001 From: Robert Jennings Date: Wed, 24 Jul 2013 20:13:21 -0500 Subject: powerpc: VPHN topology change updates all siblings When an associativity level change is found for one thread, the siblings threads need to be updated as well. This is done today for PRRN in stage_topology_update() but is missing for VPHN in update_cpu_associativity_changes_mask(). This patch will correctly update all thread siblings during a topology change. Without this patch a topology update can result in a CPU in init_sched_groups_power() getting stuck indefinitely in a loop. This loop is built in build_sched_groups(). As a result of the thread moving to a node separate from its siblings the struct sched_group will have its next pointer set to point to itself rather than the sched_group struct of the next thread. This happens because we have a domain without the SD_OVERLAP flag, which is correct, and a topology that doesn't conform with reality (threads on the same core assigned to different numa nodes). When this list is traversed by init_sched_groups_power() it will reach the thread's sched_group structure and loop indefinitely; the cpu will be stuck at this point. The bug was exposed when VPHN was enabled in commit b7abef0 (v3.9). Cc: [v3.9+] Reported-by: Jan Stancek Signed-off-by: Robert Jennings Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/mm/numa.c | 59 +++++++++++++++++++++++++++++++++++++------------- 1 file changed, 44 insertions(+), 15 deletions(-) (limited to 'arch/powerpc/mm/numa.c') diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 08397217e8ac..5850798826cd 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -1318,7 +1319,8 @@ static int update_cpu_associativity_changes_mask(void) } } if (changed) { - cpumask_set_cpu(cpu, changes); + cpumask_or(changes, changes, cpu_sibling_mask(cpu)); + cpu = cpu_last_thread_sibling(cpu); } } @@ -1426,7 +1428,7 @@ static int update_cpu_topology(void *data) if (!data) return -EINVAL; - cpu = get_cpu(); + cpu = smp_processor_id(); for (update = data; update; update = update->next) { if (cpu != update->cpu) @@ -1446,12 +1448,12 @@ static int update_cpu_topology(void *data) */ int arch_update_cpu_topology(void) { - unsigned int cpu, changed = 0; + unsigned int cpu, sibling, changed = 0; struct topology_update_data *updates, *ud; unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0}; cpumask_t updated_cpus; struct device *dev; - int weight, i = 0; + int weight, new_nid, i = 0; weight = cpumask_weight(&cpu_associativity_changes_mask); if (!weight) @@ -1464,19 +1466,46 @@ int arch_update_cpu_topology(void) cpumask_clear(&updated_cpus); for_each_cpu(cpu, &cpu_associativity_changes_mask) { - ud = &updates[i++]; - ud->cpu = cpu; - vphn_get_associativity(cpu, associativity); - ud->new_nid = associativity_to_nid(associativity); - - if (ud->new_nid < 0 || !node_online(ud->new_nid)) - ud->new_nid = first_online_node; + /* + * If siblings aren't flagged for changes, updates list + * will be too short. Skip on this update and set for next + * update. + */ + if (!cpumask_subset(cpu_sibling_mask(cpu), + &cpu_associativity_changes_mask)) { + pr_info("Sibling bits not set for associativity " + "change, cpu%d\n", cpu); + cpumask_or(&cpu_associativity_changes_mask, + &cpu_associativity_changes_mask, + cpu_sibling_mask(cpu)); + cpu = cpu_last_thread_sibling(cpu); + continue; + } - ud->old_nid = numa_cpu_lookup_table[cpu]; - cpumask_set_cpu(cpu, &updated_cpus); + /* Use associativity from first thread for all siblings */ + vphn_get_associativity(cpu, associativity); + new_nid = associativity_to_nid(associativity); + if (new_nid < 0 || !node_online(new_nid)) + new_nid = first_online_node; + + if (new_nid == numa_cpu_lookup_table[cpu]) { + cpumask_andnot(&cpu_associativity_changes_mask, + &cpu_associativity_changes_mask, + cpu_sibling_mask(cpu)); + cpu = cpu_last_thread_sibling(cpu); + continue; + } - if (i < weight) - ud->next = &updates[i]; + for_each_cpu(sibling, cpu_sibling_mask(cpu)) { + ud = &updates[i++]; + ud->cpu = sibling; + ud->new_nid = new_nid; + ud->old_nid = numa_cpu_lookup_table[sibling]; + cpumask_set_cpu(sibling, &updated_cpus); + if (i < weight) + ud->next = &updates[i]; + } + cpu = cpu_last_thread_sibling(cpu); } stop_machine(update_cpu_topology, &updates[0], &updated_cpus); -- cgit v1.2.3