|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [PATCH v2 3/3] xen/sched: fix cpu hotplug
Cpu cpu unplugging is calling schedule_cpu_rm() via stop_machine_run()
with interrupts disabled, thus any memory allocation or freeing must
be avoided.
Since commit 5047cd1d5dea ("xen/common: Use enhanced
ASSERT_ALLOC_CONTEXT in xmalloc()") this restriction is being enforced
via an assertion, which will now fail.
Before that commit cpu unplugging in normal configurations was working
just by chance as only the cpu performing schedule_cpu_rm() was doing
active work. With core scheduling enabled, however, failures could
result from memory allocations not being properly propagated to other
cpus' TLBs.
Fix this mess by allocating needed memory before entering
stop_machine_run() and freeing any memory only after having finished
stop_machine_run().
Fixes: 1ec410112cdd ("xen/sched: support differing granularity in
schedule_cpu_[add/rm]()")
Reported-by: Gao Ruifeng <ruifeng.gao@xxxxxxxxx>
Signed-off-by: Juergen Gross <jgross@xxxxxxxx>
---
V2:
- move affinity mask allocation into schedule_cpu_rm_alloc() (Jan Beulich)
---
xen/common/sched/core.c | 27 +++++++++++----
xen/common/sched/cpupool.c | 68 +++++++++++++++++++++++++++++---------
xen/common/sched/private.h | 5 ++-
3 files changed, 78 insertions(+), 22 deletions(-)
diff --git a/xen/common/sched/core.c b/xen/common/sched/core.c
index d0b6513b6f..ec09c8e5a9 100644
--- a/xen/common/sched/core.c
+++ b/xen/common/sched/core.c
@@ -3237,7 +3237,7 @@ out:
return ret;
}
-static struct cpu_rm_data *schedule_cpu_rm_alloc(unsigned int cpu)
+struct cpu_rm_data *schedule_cpu_rm_alloc(unsigned int cpu, bool aff_alloc)
{
struct cpu_rm_data *data;
const struct sched_resource *sr;
@@ -3250,6 +3250,17 @@ static struct cpu_rm_data
*schedule_cpu_rm_alloc(unsigned int cpu)
if ( !data )
goto out;
+ if ( aff_alloc )
+ {
+ if ( !update_node_aff_alloc(&data->affinity) )
+ {
+ XFREE(data);
+ goto out;
+ }
+ }
+ else
+ memset(&data->affinity, 0, sizeof(data->affinity));
+
data->old_ops = sr->scheduler;
data->vpriv_old = idle_vcpu[cpu]->sched_unit->priv;
data->ppriv_old = sr->sched_priv;
@@ -3270,6 +3281,7 @@ static struct cpu_rm_data *schedule_cpu_rm_alloc(unsigned
int cpu)
{
while ( idx > 0 )
sched_res_free(&data->sr[--idx]->rcu);
+ update_node_aff_free(&data->affinity);
XFREE(data);
goto out;
}
@@ -3288,10 +3300,11 @@ static struct cpu_rm_data
*schedule_cpu_rm_alloc(unsigned int cpu)
return data;
}
-static void schedule_cpu_rm_free(struct cpu_rm_data *mem, unsigned int cpu)
+void schedule_cpu_rm_free(struct cpu_rm_data *mem, unsigned int cpu)
{
sched_free_udata(mem->old_ops, mem->vpriv_old);
sched_free_pdata(mem->old_ops, mem->ppriv_old, cpu);
+ update_node_aff_free(&mem->affinity);
xfree(mem);
}
@@ -3302,17 +3315,18 @@ static void schedule_cpu_rm_free(struct cpu_rm_data
*mem, unsigned int cpu)
* The cpu is already marked as "free" and not valid any longer for its
* cpupool.
*/
-int schedule_cpu_rm(unsigned int cpu)
+int schedule_cpu_rm(unsigned int cpu, struct cpu_rm_data *data)
{
struct sched_resource *sr;
- struct cpu_rm_data *data;
struct sched_unit *unit;
spinlock_t *old_lock;
unsigned long flags;
int idx = 0;
unsigned int cpu_iter;
+ bool freemem = !data;
- data = schedule_cpu_rm_alloc(cpu);
+ if ( !data )
+ data = schedule_cpu_rm_alloc(cpu, false);
if ( !data )
return -ENOMEM;
@@ -3380,7 +3394,8 @@ int schedule_cpu_rm(unsigned int cpu)
sched_deinit_pdata(data->old_ops, data->ppriv_old, cpu);
rcu_read_unlock(&sched_res_rculock);
- schedule_cpu_rm_free(data, cpu);
+ if ( freemem )
+ schedule_cpu_rm_free(data, cpu);
return 0;
}
diff --git a/xen/common/sched/cpupool.c b/xen/common/sched/cpupool.c
index 58e082eb4c..2506861e4f 100644
--- a/xen/common/sched/cpupool.c
+++ b/xen/common/sched/cpupool.c
@@ -411,22 +411,28 @@ int cpupool_move_domain(struct domain *d, struct cpupool
*c)
}
/* Update affinities of all domains in a cpupool. */
-static void cpupool_update_node_affinity(const struct cpupool *c)
+static void cpupool_update_node_affinity(const struct cpupool *c,
+ struct affinity_masks *masks)
{
- struct affinity_masks masks;
+ struct affinity_masks local_masks;
struct domain *d;
- if ( !update_node_aff_alloc(&masks) )
- return;
+ if ( !masks )
+ {
+ if ( !update_node_aff_alloc(&local_masks) )
+ return;
+ masks = &local_masks;
+ }
rcu_read_lock(&domlist_read_lock);
for_each_domain_in_cpupool(d, c)
- domain_update_node_aff(d, &masks);
+ domain_update_node_aff(d, masks);
rcu_read_unlock(&domlist_read_lock);
- update_node_aff_free(&masks);
+ if ( masks == &local_masks )
+ update_node_aff_free(masks);
}
/*
@@ -460,15 +466,17 @@ static int cpupool_assign_cpu_locked(struct cpupool *c,
unsigned int cpu)
rcu_read_unlock(&sched_res_rculock);
- cpupool_update_node_affinity(c);
+ cpupool_update_node_affinity(c, NULL);
return 0;
}
-static int cpupool_unassign_cpu_finish(struct cpupool *c)
+static int cpupool_unassign_cpu_finish(struct cpupool *c,
+ struct cpu_rm_data *mem)
{
int cpu = cpupool_moving_cpu;
const cpumask_t *cpus;
+ struct affinity_masks *masks = mem ? &mem->affinity : NULL;
int ret;
if ( c != cpupool_cpu_moving )
@@ -491,7 +499,7 @@ static int cpupool_unassign_cpu_finish(struct cpupool *c)
*/
if ( !ret )
{
- ret = schedule_cpu_rm(cpu);
+ ret = schedule_cpu_rm(cpu, mem);
if ( ret )
cpumask_andnot(&cpupool_free_cpus, &cpupool_free_cpus, cpus);
else
@@ -503,7 +511,7 @@ static int cpupool_unassign_cpu_finish(struct cpupool *c)
}
rcu_read_unlock(&sched_res_rculock);
- cpupool_update_node_affinity(c);
+ cpupool_update_node_affinity(c, masks);
return ret;
}
@@ -567,7 +575,7 @@ static long cf_check cpupool_unassign_cpu_helper(void *info)
cpupool_cpu_moving->cpupool_id, cpupool_moving_cpu);
spin_lock(&cpupool_lock);
- ret = cpupool_unassign_cpu_finish(c);
+ ret = cpupool_unassign_cpu_finish(c, NULL);
spin_unlock(&cpupool_lock);
debugtrace_printk("cpupool_unassign_cpu ret=%ld\n", ret);
@@ -714,7 +722,7 @@ static int cpupool_cpu_add(unsigned int cpu)
* This function is called in stop_machine context, so we can be sure no
* non-idle vcpu is active on the system.
*/
-static void cpupool_cpu_remove(unsigned int cpu)
+static void cpupool_cpu_remove(unsigned int cpu, struct cpu_rm_data *mem)
{
int ret;
@@ -722,7 +730,7 @@ static void cpupool_cpu_remove(unsigned int cpu)
if ( !cpumask_test_cpu(cpu, &cpupool_free_cpus) )
{
- ret = cpupool_unassign_cpu_finish(cpupool0);
+ ret = cpupool_unassign_cpu_finish(cpupool0, mem);
BUG_ON(ret);
}
cpumask_clear_cpu(cpu, &cpupool_free_cpus);
@@ -788,7 +796,7 @@ static void cpupool_cpu_remove_forced(unsigned int cpu)
{
ret = cpupool_unassign_cpu_start(c, master_cpu);
BUG_ON(ret);
- ret = cpupool_unassign_cpu_finish(c);
+ ret = cpupool_unassign_cpu_finish(c, NULL);
BUG_ON(ret);
}
}
@@ -1008,10 +1016,21 @@ static int cf_check cpu_callback(
{
unsigned int cpu = (unsigned long)hcpu;
int rc = 0;
+ static struct cpu_rm_data *mem;
switch ( action )
{
case CPU_DOWN_FAILED:
+ if ( system_state <= SYS_STATE_active )
+ {
+ if ( mem )
+ {
+ schedule_cpu_rm_free(mem, cpu);
+ mem = NULL;
+ }
+ rc = cpupool_cpu_add(cpu);
+ }
+ break;
case CPU_ONLINE:
if ( system_state <= SYS_STATE_active )
rc = cpupool_cpu_add(cpu);
@@ -1019,12 +1038,31 @@ static int cf_check cpu_callback(
case CPU_DOWN_PREPARE:
/* Suspend/Resume don't change assignments of cpus to cpupools. */
if ( system_state <= SYS_STATE_active )
+ {
rc = cpupool_cpu_remove_prologue(cpu);
+ if ( !rc )
+ {
+ ASSERT(!mem);
+ mem = schedule_cpu_rm_alloc(cpu, true);
+ rc = mem ? 0 : -ENOMEM;
+ }
+ }
break;
case CPU_DYING:
/* Suspend/Resume don't change assignments of cpus to cpupools. */
if ( system_state <= SYS_STATE_active )
- cpupool_cpu_remove(cpu);
+ {
+ ASSERT(mem);
+ cpupool_cpu_remove(cpu, mem);
+ }
+ break;
+ case CPU_DEAD:
+ if ( system_state <= SYS_STATE_active )
+ {
+ ASSERT(mem);
+ schedule_cpu_rm_free(mem, cpu);
+ mem = NULL;
+ }
break;
case CPU_RESUME_FAILED:
cpupool_cpu_remove_forced(cpu);
diff --git a/xen/common/sched/private.h b/xen/common/sched/private.h
index 601d639699..cc7a6cb571 100644
--- a/xen/common/sched/private.h
+++ b/xen/common/sched/private.h
@@ -603,6 +603,7 @@ void update_node_aff_free(struct affinity_masks *affinity);
/* Memory allocation related data for schedule_cpu_rm(). */
struct cpu_rm_data {
+ struct affinity_masks affinity;
const struct scheduler *old_ops;
void *ppriv_old;
void *vpriv_old;
@@ -617,7 +618,9 @@ struct scheduler *scheduler_alloc(unsigned int sched_id);
void scheduler_free(struct scheduler *sched);
int cpu_disable_scheduler(unsigned int cpu);
int schedule_cpu_add(unsigned int cpu, struct cpupool *c);
-int schedule_cpu_rm(unsigned int cpu);
+struct cpu_rm_data *schedule_cpu_rm_alloc(unsigned int cpu, bool aff_alloc);
+void schedule_cpu_rm_free(struct cpu_rm_data *mem, unsigned int cpu);
+int schedule_cpu_rm(unsigned int cpu, struct cpu_rm_data *mem);
int sched_move_domain(struct domain *d, struct cpupool *c);
struct cpupool *cpupool_get_by_id(unsigned int poolid);
void cpupool_put(struct cpupool *pool);
--
2.35.3
|
 |
Lists.xenproject.org is hosted with RackSpace, monitoring our |