sched: make implementing .alloc_pdata optional

The .alloc_pdata scheduler hook must, before this change,
be implemented by all schedulers --even those ones that
don't need to allocate anything.

Make it possible to just use the SCHED_OP(), like for
the other hooks, by using ERR_PTR() and IS_ERR() for
error reporting. This:
 - makes NULL a variant of success;
 - allows for errors other than ENOMEM to be properly
   communicated (if ever necessary).

This, in turn, means that schedulers not needing to
allocate any per-pCPU data, can avoid implementing the
hook. In fact, the artificial implementation of
.alloc_pdata in the ARINC653 is removed (and, while there,
nuke .free_pdata too, as it is equally useless).

Signed-off-by: Dario Faggioli <dario.faggioli@citrix.com>
Reviewed-by: Meng Xu <mengxu@cis.upenn.edu>
Reviewed-by: Juergen Gross <jgross@suse.com>
Acked-by: George Dunlap <george.dunlap@citrix.com>

diff --git a/xen/common/sched_arinc653.c b/xen/common/sched_arinc653.c
index 8a11a2f6b83c28e86dbecccab8e98c066082d3f9..b79fcdf7f6c528f596ad125be6409ec72cce15c0 100644 (file)
--- a/xen/common/sched_arinc653.c
+++ b/xen/common/sched_arinc653.c
@@ -455,34 +455,6 @@ a653sched_free_vdata(const struct scheduler *ops, void *priv)
     update_schedule_vcpus(ops);
 }
 
-/**
- * This function allocates scheduler-specific data for a physical CPU
- *
- * We do not actually make use of any per-CPU data but the hypervisor expects
- * a non-NULL return value
- *
- * @param ops       Pointer to this instance of the scheduler structure
- *
- * @return          Pointer to the allocated data
- */
-static void *
-a653sched_alloc_pdata(const struct scheduler *ops, int cpu)
-{
-    /* return a non-NULL value to keep schedule.c happy */
-    return SCHED_PRIV(ops);
-}
-
-/**
- * This function frees scheduler-specific data for a physical CPU
- *
- * @param ops       Pointer to this instance of the scheduler structure
- */
-static void
-a653sched_free_pdata(const struct scheduler *ops, void *pcpu, int cpu)
-{
-    /* nop */
-}
-
 /**
  * This function allocates scheduler-specific data for a domain
  *
@@ -737,9 +709,6 @@ static const struct scheduler sched_arinc653_def = {
     .free_vdata     = a653sched_free_vdata,
     .alloc_vdata    = a653sched_alloc_vdata,
 
-    .free_pdata     = a653sched_free_pdata,
-    .alloc_pdata    = a653sched_alloc_pdata,
-
     .free_domdata   = a653sched_free_domdata,
     .alloc_domdata  = a653sched_alloc_domdata,
 

diff --git a/xen/common/sched_credit.c b/xen/common/sched_credit.c
index 4c4927fac439e15b6c161e58583ef1d528594334..63a4a638f5427a260d774088fef70de8ef48e093 100644 (file)
--- a/xen/common/sched_credit.c
+++ b/xen/common/sched_credit.c
@@ -23,6 +23,7 @@
 #include <xen/errno.h>
 #include <xen/keyhandler.h>
 #include <xen/trace.h>
+#include <xen/err.h>
 
 
 /*
@@ -532,12 +533,12 @@ csched_alloc_pdata(const struct scheduler *ops, int cpu)
     /* Allocate per-PCPU info */
     spc = xzalloc(struct csched_pcpu);
     if ( spc == NULL )
-        return NULL;
+        return ERR_PTR(-ENOMEM);
 
     if ( !alloc_cpumask_var(&spc->balance_mask) )
     {
         xfree(spc);
-        return NULL;
+        return ERR_PTR(-ENOMEM);
     }
 
     spin_lock_irqsave(&prv->lock, flags);

diff --git a/xen/common/sched_credit2.c b/xen/common/sched_credit2.c
index b8c8e40fc94e6d2ae3d6c99f59ef4046f9fe68b1..e97d8be07465b2e2441c1334181aeb2cdcb03cc5 100644 (file)
--- a/xen/common/sched_credit2.c
+++ b/xen/common/sched_credit2.c
@@ -2047,7 +2047,7 @@ csched2_alloc_pdata(const struct scheduler *ops, int cpu)
         printk("%s: cpu %d not online yet, deferring initializatgion\n",
                __func__, cpu);
 
-    return (void *)1;
+    return NULL;
 }
 
 static void

diff --git a/xen/common/sched_rt.c b/xen/common/sched_rt.c
index 321b0a5f9c5463cd62137d30d1bcce5d8f885fc9..aece318da8348203af3437abb66248a0a1812ea8 100644 (file)
--- a/xen/common/sched_rt.c
+++ b/xen/common/sched_rt.c
@@ -29,6 +29,7 @@
 #include <xen/cpu.h>
 #include <xen/keyhandler.h>
 #include <xen/trace.h>
+#include <xen/err.h>
 #include <xen/guest_access.h>
 
 /*
@@ -681,7 +682,7 @@ rt_alloc_pdata(const struct scheduler *ops, int cpu)
     spin_unlock_irqrestore(old_lock, flags);
 
     if ( !alloc_cpumask_var(&_cpumask_scratch[cpu]) )
-        return NULL;
+        return ERR_PTR(-ENOMEM);
 
     if ( prv->repl_timer == NULL )
     {
@@ -689,13 +690,12 @@ rt_alloc_pdata(const struct scheduler *ops, int cpu)
         prv->repl_timer = xzalloc(struct timer);
 
         if ( prv->repl_timer == NULL )
-            return NULL;
+            return ERR_PTR(-ENOMEM);
 
         init_timer(prv->repl_timer, repl_timer_handler, (void *)ops, cpu);
     }
 
-    /* 1 indicates alloc. succeed in schedule.c */
-    return (void *)1;
+    return NULL;
 }
 
 static void

diff --git a/xen/common/schedule.c b/xen/common/schedule.c
index b7dee16afa58a74d681e40ecc204fcb2c2ef369f..19416136574aaa620108218372fbcc69cd6f774f 100644 (file)
--- a/xen/common/schedule.c
+++ b/xen/common/schedule.c
@@ -37,6 +37,7 @@
 #include <xen/event.h>
 #include <public/sched.h>
 #include <xsm/xsm.h>
+#include <xen/err.h>
 
 /* opt_sched: scheduler - default to configured value */
 static char __initdata opt_sched[10] = CONFIG_SCHED_DEFAULT;
@@ -1462,6 +1463,7 @@ static void poll_timer_fn(void *data)
 static int cpu_schedule_up(unsigned int cpu)
 {
     struct schedule_data *sd = &per_cpu(schedule_data, cpu);
+    void *sched_priv;
 
     per_cpu(scheduler, cpu) = &ops;
     spin_lock_init(&sd->_lock);
@@ -1500,9 +1502,16 @@ static int cpu_schedule_up(unsigned int cpu)
     if ( idle_vcpu[cpu] == NULL )
         return -ENOMEM;
 
-    if ( (ops.alloc_pdata != NULL) &&
-         ((sd->sched_priv = ops.alloc_pdata(&ops, cpu)) == NULL) )
-        return -ENOMEM;
+    /*
+     * We don't want to risk calling xfree() on an sd->sched_priv
+     * (e.g., inside free_pdata, from cpu_schedule_down() called
+     * during CPU_UP_CANCELLED) that contains an IS_ERR value.
+     */
+    sched_priv = SCHED_OP(&ops, alloc_pdata, cpu);
+    if ( IS_ERR(sched_priv) )
+        return PTR_ERR(sched_priv);
+
+    sd->sched_priv = sched_priv;
 
     return 0;
 }
@@ -1512,8 +1521,7 @@ static void cpu_schedule_down(unsigned int cpu)
     struct schedule_data *sd = &per_cpu(schedule_data, cpu);
     struct scheduler *sched = per_cpu(scheduler, cpu);
 
-    if ( sd->sched_priv != NULL )
-        SCHED_OP(sched, free_pdata, sd->sched_priv, cpu);
+    SCHED_OP(sched, free_pdata, sd->sched_priv, cpu);
     SCHED_OP(sched, free_vdata, idle_vcpu[cpu]->sched_priv);
 
     idle_vcpu[cpu]->sched_priv = NULL;
@@ -1608,9 +1616,8 @@ void __init scheduler_init(void)
     idle_domain->max_vcpus = nr_cpu_ids;
     if ( alloc_vcpu(idle_domain, 0, 0) == NULL )
         BUG();
-    if ( ops.alloc_pdata &&
-         !(this_cpu(schedule_data).sched_priv = ops.alloc_pdata(&ops, 0)) )
-        BUG();
+    this_cpu(schedule_data).sched_priv = SCHED_OP(&ops, alloc_pdata, 0);
+    BUG_ON(IS_ERR(this_cpu(schedule_data).sched_priv));
     SCHED_OP(&ops, init_pdata, this_cpu(schedule_data).sched_priv, 0);
 }
 
@@ -1653,8 +1660,8 @@ int schedule_cpu_switch(unsigned int cpu, struct cpupool *c)
 
     idle = idle_vcpu[cpu];
     ppriv = SCHED_OP(new_ops, alloc_pdata, cpu);
-    if ( ppriv == NULL )
-        return -ENOMEM;
+    if ( IS_ERR(ppriv) )
+        return PTR_ERR(ppriv);
     SCHED_OP(new_ops, init_pdata, ppriv, cpu);
     vpriv = SCHED_OP(new_ops, alloc_vdata, idle, idle->domain->sched_priv);
     if ( vpriv == NULL )