[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[xen staging-4.16] xen/sched: fix cpu hotplug



commit 4f3204c2bc66db18c61600dd3e08bf1fd9584a1b
Author:     Juergen Gross <jgross@xxxxxxxx>
AuthorDate: Tue Oct 11 15:00:19 2022 +0200
Commit:     Jan Beulich <jbeulich@xxxxxxxx>
CommitDate: Tue Oct 11 15:00:19 2022 +0200

    xen/sched: fix cpu hotplug
    
    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.
    
    Fix this 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>
    Reviewed-by: Jan Beulich <jbeulich@xxxxxxxx>
    Acked-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
    Tested-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
    master commit: d84473689611eed32fd90b27e614f28af767fa3f
    master date: 2022-09-05 11:42:30 +0100
---
 xen/common/sched/core.c    | 25 +++++++++++++----
 xen/common/sched/cpupool.c | 69 ++++++++++++++++++++++++++++++++++++----------
 xen/common/sched/private.h |  5 ++--
 3 files changed, 77 insertions(+), 22 deletions(-)

diff --git a/xen/common/sched/core.c b/xen/common/sched/core.c
index 2decb1161a..900aab8f66 100644
--- a/xen/common/sched/core.c
+++ b/xen/common/sched/core.c
@@ -3231,7 +3231,7 @@ out:
  * by alloc_cpu_rm_data() is modified only in case the cpu in question is
  * being moved from or to a cpupool.
  */
-struct cpu_rm_data *alloc_cpu_rm_data(unsigned int cpu)
+struct cpu_rm_data *alloc_cpu_rm_data(unsigned int cpu, bool aff_alloc)
 {
     struct cpu_rm_data *data;
     const struct sched_resource *sr;
@@ -3244,6 +3244,17 @@ struct cpu_rm_data *alloc_cpu_rm_data(unsigned int cpu)
     if ( !data )
         goto out;
 
+    if ( aff_alloc )
+    {
+        if ( !alloc_affinity_masks(&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;
@@ -3264,6 +3275,7 @@ struct cpu_rm_data *alloc_cpu_rm_data(unsigned int cpu)
         {
             while ( idx > 0 )
                 sched_res_free(&data->sr[--idx]->rcu);
+            free_affinity_masks(&data->affinity);
             XFREE(data);
             goto out;
         }
@@ -3286,6 +3298,7 @@ void free_cpu_rm_data(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);
+    free_affinity_masks(&mem->affinity);
 
     xfree(mem);
 }
@@ -3296,17 +3309,18 @@ void free_cpu_rm_data(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 free_data = !data;
 
-    data = alloc_cpu_rm_data(cpu);
+    if ( !data )
+        data = alloc_cpu_rm_data(cpu, false);
     if ( !data )
         return -ENOMEM;
 
@@ -3374,7 +3388,8 @@ int schedule_cpu_rm(unsigned int cpu)
     sched_deinit_pdata(data->old_ops, data->ppriv_old, cpu);
 
     rcu_read_unlock(&sched_res_rculock);
-    free_cpu_rm_data(data, cpu);
+    if ( free_data )
+        free_cpu_rm_data(data, cpu);
 
     return 0;
 }
diff --git a/xen/common/sched/cpupool.c b/xen/common/sched/cpupool.c
index 45b6ff9956..b5a948639a 100644
--- a/xen/common/sched/cpupool.c
+++ b/xen/common/sched/cpupool.c
@@ -402,22 +402,28 @@ 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 ( !alloc_affinity_masks(&masks) )
-        return;
+    if ( !masks )
+    {
+        if ( !alloc_affinity_masks(&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);
 
-    free_affinity_masks(&masks);
+    if ( masks == &local_masks )
+        free_affinity_masks(masks);
 }
 
 /*
@@ -451,15 +457,17 @@ 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 )
@@ -482,7 +490,7 @@ 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
@@ -494,7 +502,7 @@ 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;
 }
@@ -558,7 +566,7 @@ static long 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);
@@ -701,7 +709,7 @@ 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;
 
@@ -709,7 +717,7 @@ 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);
@@ -775,7 +783,7 @@ 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);
         }
     }
@@ -993,12 +1001,24 @@ void dump_runq(unsigned char key)
 static int cpu_callback(
     struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
+    static struct cpu_rm_data *mem;
+
     unsigned int cpu = (unsigned long)hcpu;
     int rc = 0;
 
     switch ( action )
     {
     case CPU_DOWN_FAILED:
+        if ( system_state <= SYS_STATE_active )
+        {
+            if ( mem )
+            {
+                free_cpu_rm_data(mem, cpu);
+                mem = NULL;
+            }
+            rc = cpupool_cpu_add(cpu);
+        }
+        break;
     case CPU_ONLINE:
         if ( system_state <= SYS_STATE_active )
             rc = cpupool_cpu_add(cpu);
@@ -1006,12 +1026,31 @@ static int 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 = alloc_cpu_rm_data(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);
+            free_cpu_rm_data(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 e286849a13..0126a4bb9e 100644
--- a/xen/common/sched/private.h
+++ b/xen/common/sched/private.h
@@ -603,6 +603,7 @@ void free_affinity_masks(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;
@@ -617,9 +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);
-struct cpu_rm_data *alloc_cpu_rm_data(unsigned int cpu);
+struct cpu_rm_data *alloc_cpu_rm_data(unsigned int cpu, bool aff_alloc);
 void free_cpu_rm_data(struct cpu_rm_data *mem, unsigned int cpu);
-int schedule_cpu_rm(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);
--
generated by git-patchbot for /home/xen/git/xen.git#staging-4.16



 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.