[PATCH 53/60] xen/sched: remove cpu from pool0 before removing it

From: Juergen Gross <jgross@suse.com>
To: xen-devel@lists.xenproject.org
Cc: Juergen Gross <jgross@suse.com>, Tim Deegan <tim@xen.org>,
	Stefano Stabellini <sstabellini@kernel.org>, Wei Liu <wl@xen.org>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	George Dunlap <George.Dunlap@eu.citrix.com>,
	Andrew Cooper <andrew.cooper3@citrix.com>,
	Ian Jackson <ian.jackson@eu.citrix.com>,
	Dario Faggioli <dfaggioli@suse.com>,
	Julien Grall <julien.grall@arm.com>,
	Jan Beulich <jbeulich@suse.com>
Subject: [PATCH 53/60] xen/sched: remove cpu from pool0 before removing it
Date: Tue, 28 May 2019 12:33:06 +0200	[thread overview]
Message-ID: <20190528103313.1343-54-jgross@suse.com> (raw)
In-Reply-To: <20190528103313.1343-1-jgross@suse.com>

Today a cpu which is removed from the system is taken directly from
Pool0 to the offline state. This will conflict with core scheduling,
so remove it from Pool0 first. Additionally accept removing a free cpu
instead of requiring it to be in Pool0.

For the resume failed case we need to call the scheduler code for that
situation after the cpupool handling, so move the scheduler code into
a function and call it from cpupool_cpu_remove_forced() and remove the
CPU_RESUME_FAILED case from cpu_schedule_callback().

Note that we are calling now schedule_cpu_switch() in stop_machine
context so we need to switch from spinlock_irq to spinlock_irqsave.

Signed-off-by: Juergen Gross <jgross@suse.com>
---
V1: new patch
---
 xen/common/cpupool.c       | 177 +++++++++++++++++++++++++++------------------
 xen/common/schedule.c      |  29 +++++---
 xen/include/xen/sched-if.h |   2 +
 3 files changed, 128 insertions(+), 80 deletions(-)

diff --git a/xen/common/cpupool.c b/xen/common/cpupool.c
index 2a3e144700..ab4a2be4fc 100644
--- a/xen/common/cpupool.c
+++ b/xen/common/cpupool.c
@@ -292,22 +292,14 @@ static int cpupool_assign_cpu_locked(struct cpupool *c, unsigned int cpu)
     return 0;
 }
 
-static long cpupool_unassign_cpu_helper(void *info)
+static int cpupool_unassign_cpu_epilogue(struct cpupool *c)
 {
     int cpu = cpupool_moving_cpu;
-    struct cpupool *c = info;
     struct domain *d;
-    long ret;
-
-    cpupool_dprintk("cpupool_unassign_cpu(pool=%d,cpu=%d)\n",
-                    cpupool_cpu_moving->cpupool_id, cpu);
+    int ret;
 
-    spin_lock(&cpupool_lock);
     if ( c != cpupool_cpu_moving )
-    {
-        ret = -EADDRNOTAVAIL;
-        goto out;
-    }
+        return -EADDRNOTAVAIL;
 
     /*
      * We need this for scanning the domain list, both in
@@ -342,39 +334,19 @@ static long cpupool_unassign_cpu_helper(void *info)
         domain_update_node_affinity(d);
     }
     rcu_read_unlock(&domlist_read_lock);
-out:
-    spin_unlock(&cpupool_lock);
-    cpupool_dprintk("cpupool_unassign_cpu ret=%ld\n", ret);
+
     return ret;
 }
 
-/*
- * unassign a specific cpu from a cpupool
- * we must be sure not to run on the cpu to be unassigned! to achieve this
- * the main functionality is performed via continue_hypercall_on_cpu on a
- * specific cpu.
- * if the cpu to be removed is the last one of the cpupool no active domain
- * must be bound to the cpupool. dying domains are moved to cpupool0 as they
- * might be zombies.
- * possible failures:
- * - last cpu and still active domains in cpupool
- * - cpu just being unplugged
- */
-static int cpupool_unassign_cpu(struct cpupool *c, unsigned int cpu)
+static int cpupool_unassign_cpu_prologue(struct cpupool *c, unsigned int cpu)
 {
-    int work_cpu;
     int ret;
     struct domain *d;
 
-    cpupool_dprintk("cpupool_unassign_cpu(pool=%d,cpu=%d)\n",
-                    c->cpupool_id, cpu);
-
     spin_lock(&cpupool_lock);
     ret = -EADDRNOTAVAIL;
     if ( (cpupool_moving_cpu != -1) && (cpu != cpupool_moving_cpu) )
         goto out;
-    if ( cpumask_test_cpu(cpu, &cpupool_locked_cpus) )
-        goto out;
 
     ret = 0;
     if ( !cpumask_test_cpu(cpu, c->cpu_valid) && (cpu != cpupool_moving_cpu) )
@@ -386,7 +358,7 @@ static int cpupool_unassign_cpu(struct cpupool *c, unsigned int cpu)
         rcu_read_lock(&domlist_read_lock);
         for_each_domain_in_cpupool(d, c)
         {
-            if ( !d->is_dying )
+            if ( !d->is_dying && system_state == SYS_STATE_active )
             {
                 ret = -EBUSY;
                 break;
@@ -404,8 +376,58 @@ static int cpupool_unassign_cpu(struct cpupool *c, unsigned int cpu)
     cpupool_cpu_moving = c;
     cpumask_clear_cpu(cpu, c->cpu_valid);
     cpumask_and(c->res_valid, c->cpu_valid, sched_res_mask);
+
+out:
     spin_unlock(&cpupool_lock);
 
+    return ret;
+}
+
+static long cpupool_unassign_cpu_helper(void *info)
+{
+    struct cpupool *c = info;
+    long ret;
+
+    cpupool_dprintk("cpupool_unassign_cpu(pool=%d,cpu=%d)\n",
+                    cpupool_cpu_moving->cpupool_id, cpu);
+    spin_lock(&cpupool_lock);
+
+    ret = cpupool_unassign_cpu_epilogue(c);
+
+    spin_unlock(&cpupool_lock);
+    cpupool_dprintk("cpupool_unassign_cpu ret=%ld\n", ret);
+
+    return ret;
+}
+
+/*
+ * unassign a specific cpu from a cpupool
+ * we must be sure not to run on the cpu to be unassigned! to achieve this
+ * the main functionality is performed via continue_hypercall_on_cpu on a
+ * specific cpu.
+ * if the cpu to be removed is the last one of the cpupool no active domain
+ * must be bound to the cpupool. dying domains are moved to cpupool0 as they
+ * might be zombies.
+ * possible failures:
+ * - last cpu and still active domains in cpupool
+ * - cpu just being unplugged
+ */
+static int cpupool_unassign_cpu(struct cpupool *c, unsigned int cpu)
+{
+    int work_cpu;
+    int ret;
+
+    cpupool_dprintk("cpupool_unassign_cpu(pool=%d,cpu=%d)\n",
+                    c->cpupool_id, cpu);
+
+    ret = cpupool_unassign_cpu_prologue(c, cpu);
+    if ( ret )
+    {
+        cpupool_dprintk("cpupool_unassign_cpu(pool=%d,cpu=%d) ret %d\n",
+                        c->cpupool_id, cpu, ret);
+        return ret;
+    }
+
     work_cpu = smp_processor_id();
     if ( work_cpu == cpu )
     {
@@ -414,12 +436,6 @@ static int cpupool_unassign_cpu(struct cpupool *c, unsigned int cpu)
             work_cpu = cpumask_next(cpu, cpupool0->cpu_valid);
     }
     return continue_hypercall_on_cpu(work_cpu, cpupool_unassign_cpu_helper, c);
-
-out:
-    spin_unlock(&cpupool_lock);
-    cpupool_dprintk("cpupool_unassign_cpu(pool=%d,cpu=%d) ret %d\n",
-                    c->cpupool_id, cpu, ret);
-    return ret;
 }
 
 /*
@@ -503,31 +519,54 @@ static int cpupool_cpu_add(unsigned int cpu)
 }
 
 /*
- * Called to remove a CPU from a pool. The CPU is locked, to forbid removing
- * it from pool0. In fact, if we want to hot-unplug a CPU, it must belong to
- * pool0, or we fail.
+ * This function is called in stop_machine context, so we can be sure no
+ * non-idle vcpu is active on the system.
  */
-static int cpupool_cpu_remove(unsigned int cpu)
+static void cpupool_cpu_remove(unsigned int cpu)
 {
-    int ret = -ENODEV;
+    int ret;
 
-    spin_lock(&cpupool_lock);
+    ASSERT(is_idle_vcpu(current));
 
-    if ( cpumask_test_cpu(cpu, cpupool0->cpu_valid) )
+    if ( !cpumask_test_cpu(cpu, &cpupool_free_cpus) )
     {
-        /*
-         * If we are not suspending, we are hot-unplugging cpu, and that is
-         * allowed only for CPUs in pool0.
-         */
-        cpumask_clear_cpu(cpu, cpupool0->cpu_valid);
-        cpumask_and(cpupool0->res_valid, cpupool0->cpu_valid, sched_res_mask);
-        ret = 0;
+        ret = cpupool_unassign_cpu_epilogue(cpupool0);
+        BUG_ON(ret);
     }
+}
 
-    if ( !ret )
+/*
+ * Called before a CPU is being removed from the system.
+ * Removing a CPU is allowed for free CPUs or CPUs in Pool-0 (those are moved
+ * to free cpus actually before removing them).
+ * The CPU is locked, to forbid adding it again to another cpupool.
+ */
+static int cpupool_cpu_remove_prologue(unsigned int cpu)
+{
+    int ret = 0;
+
+    spin_lock(&cpupool_lock);
+
+    if ( cpumask_test_cpu(cpu, &cpupool_locked_cpus) )
+        ret = -EBUSY;
+    else
         cpumask_set_cpu(cpu, &cpupool_locked_cpus);
+
     spin_unlock(&cpupool_lock);
 
+    if ( ret )
+        return  ret;
+
+    if ( cpumask_test_cpu(cpu, cpupool0->cpu_valid) )
+    {
+        /* Cpupool0 is populated only after all cpus are up. */
+        ASSERT(system_state == SYS_STATE_active);
+
+        ret = cpupool_unassign_cpu_prologue(cpupool0, cpu);
+    }
+    else if ( !cpumask_test_cpu(cpu, &cpupool_free_cpus) )
+        ret = -ENODEV;
+
     return ret;
 }
 
@@ -535,13 +574,13 @@ static int cpupool_cpu_remove(unsigned int cpu)
  * Called during resume for all cpus which didn't come up again. The cpu must
  * be removed from the cpupool it is assigned to. In case a cpupool will be
  * left without cpu we move all domains of that cpupool to cpupool0.
+ * As we are called with all domains still frozen there is no need to take the
+ * cpupool lock here.
  */
 static void cpupool_cpu_remove_forced(unsigned int cpu)
 {
     struct cpupool **c;
-    struct domain *d;
-
-    spin_lock(&cpupool_lock);
+    int ret;
 
     if ( cpumask_test_cpu(cpu, &cpupool_free_cpus) )
         cpumask_clear_cpu(cpu, &cpupool_free_cpus);
@@ -551,19 +590,13 @@ static void cpupool_cpu_remove_forced(unsigned int cpu)
         {
             if ( cpumask_test_cpu(cpu, (*c)->cpu_valid) )
             {
-                cpumask_clear_cpu(cpu, (*c)->cpu_valid);
-                if ( cpumask_weight((*c)->cpu_valid) == 0 )
-                {
-                    if ( *c == cpupool0 )
-                        panic("No cpu left in cpupool0\n");
-                    for_each_domain_in_cpupool(d, *c)
-                        cpupool_move_domain_locked(d, cpupool0);
-                }
+                ret = cpupool_unassign_cpu(*c, cpu);
+                BUG_ON(ret);
             }
         }
     }
 
-    spin_unlock(&cpupool_lock);
+    sched_rm_cpu(cpu);
 }
 
 /*
@@ -631,7 +664,8 @@ int cpupool_do_sysctl(struct xen_sysctl_cpupool_op *op)
         if ( cpu >= nr_cpu_ids )
             goto addcpu_out;
         ret = -ENODEV;
-        if ( !cpumask_test_cpu(cpu, &cpupool_free_cpus) )
+        if ( !cpumask_test_cpu(cpu, &cpupool_free_cpus) ||
+             cpumask_test_cpu(cpu, &cpupool_locked_cpus) )
             goto addcpu_out;
         c = cpupool_find_by_id(op->cpupool_id);
         ret = -ENOENT;
@@ -759,7 +793,12 @@ 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(cpu);
+            rc = cpupool_cpu_remove_prologue(cpu);
+        break;
+    case CPU_DYING:
+        /* Suspend/Resume don't change assignments of cpus to cpupools. */
+        if ( system_state <= SYS_STATE_active )
+            cpupool_cpu_remove(cpu);
         break;
     case CPU_RESUME_FAILED:
         cpupool_cpu_remove_forced(cpu);
diff --git a/xen/common/schedule.c b/xen/common/schedule.c
index 44364ff4d2..7a5ab4b1b6 100644
--- a/xen/common/schedule.c
+++ b/xen/common/schedule.c
@@ -2235,12 +2235,24 @@ void scheduler_percpu_init(unsigned int cpu)
         sched_init_pdata(sched, sd->sched_priv, cpu);
 }
 
+void sched_rm_cpu(unsigned int cpu)
+{
+    int rc;
+    struct sched_resource *sd = get_sched_res(cpu);
+    struct scheduler *sched = sd->scheduler;
+
+    rcu_read_lock(&domlist_read_lock);
+    rc = cpu_disable_scheduler(cpu);
+    BUG_ON(rc);
+    rcu_read_unlock(&domlist_read_lock);
+    sched_deinit_pdata(sched, sd->sched_priv, cpu);
+    cpu_schedule_down(cpu);
+}
+
 static int cpu_schedule_callback(
     struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
     unsigned int cpu = (unsigned long)hcpu;
-    struct sched_resource *sd = get_sched_res(cpu);
-    struct scheduler *sched = sd->scheduler;
     int rc = 0;
 
     /*
@@ -2286,16 +2298,10 @@ static int cpu_schedule_callback(
         rc = cpu_disable_scheduler_check(cpu);
         rcu_read_unlock(&domlist_read_lock);
         break;
-    case CPU_RESUME_FAILED:
     case CPU_DEAD:
         if ( system_state == SYS_STATE_suspend )
             break;
-        rcu_read_lock(&domlist_read_lock);
-        rc = cpu_disable_scheduler(cpu);
-        BUG_ON(rc);
-        rcu_read_unlock(&domlist_read_lock);
-        sched_deinit_pdata(sched, sd->sched_priv, cpu);
-        cpu_schedule_down(cpu);
+        sched_rm_cpu(cpu);
         break;
     case CPU_UP_CANCELED:
         if ( system_state != SYS_STATE_resume )
@@ -2421,6 +2427,7 @@ int schedule_cpu_switch(unsigned int cpu, struct cpupool *c)
     struct sched_resource *sd = get_sched_res(cpu);
     struct cpupool *old_pool = sd->cpupool;
     spinlock_t *old_lock, *new_lock;
+    unsigned long flags;
 
     /*
      * pCPUs only move from a valid cpupool to free (i.e., out of any pool),
@@ -2476,7 +2483,7 @@ int schedule_cpu_switch(unsigned int cpu, struct cpupool *c)
      * that the lock itself changed, and retry acquiring the new one (which
      * will be the correct, remapped one, at that point).
      */
-    old_lock = pcpu_schedule_lock_irq(cpu);
+    old_lock = pcpu_schedule_lock_irqsave(cpu, &flags);
 
     vpriv_old = idle->sched_unit->priv;
     ppriv_old = sd->sched_priv;
@@ -2494,7 +2501,7 @@ int schedule_cpu_switch(unsigned int cpu, struct cpupool *c)
     sd->schedule_lock = c ? new_lock : &sched_free_cpu_lock;
 
     /* _Not_ pcpu_schedule_unlock(): schedule_lock may have changed! */
-    spin_unlock_irq(old_lock);
+    spin_unlock_irqrestore(old_lock, flags);
 
     sched_do_tick_resume(new_ops, cpu);
 
diff --git a/xen/include/xen/sched-if.h b/xen/include/xen/sched-if.h
index a0f11d0c15..e04d249dfd 100644
--- a/xen/include/xen/sched-if.h
+++ b/xen/include/xen/sched-if.h
@@ -609,4 +609,6 @@ affinity_balance_cpumask(const struct sched_unit *unit, int step,
         cpumask_copy(mask, unit->cpu_hard_affinity);
 }
 
+void sched_rm_cpu(unsigned int cpu);
+
 #endif /* __XEN_SCHED_IF_H__ */
-- 
2.16.4


_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
