[Xen-devel] [PATCH v2 48/48] xen/sched: add scheduling granularity enum

[Juergen Gross <jgross@suse.com>]

Add a scheduling granularity enum ("cpu", "core", "socket") for
specification of the scheduling granularity. Initially it is set to
"cpu", this can be modified by the new boot parameter (x86 only)
"sched-gran".

According to the selected granularity sched_granularity is set after
all cpus are online.

A test is added for all sched resources holding the same number of
cpus. Fall back to core- or cpu-scheduling in that case.

Signed-off-by: Juergen Gross <jgross@suse.com>
---
RFC V2:
- fixed freeing of sched_res when merging cpus
- rename parameter to "sched-gran" (Jan Beulich)
- rename parameter option from "thread" to "cpu" (Jan Beulich)

V1:
- rename scheduler_smp_init() to scheduler_gran_init(), let it be called
  by cpupool_init()
- avoid using literal cpu number 0 in scheduler_percpu_init() (Jan Beulich)
- style correction (Jan Beulich)
- fallback to smaller granularity instead of panic in case of
  unbalanced cpu configuration

V2:
- style changes (Jan Beulich)
- introduce CONFIG_HAS_SCHED_GRANULARITY (Jan Beulich)
---
 xen/arch/x86/Kconfig       |  1 +
 xen/common/Kconfig         |  3 ++
 xen/common/cpupool.c       |  2 ++
 xen/common/schedule.c      | 78 ++++++++++++++++++++++++++++++++++++++++++++++
 xen/include/xen/sched-if.h |  1 +
 5 files changed, 85 insertions(+)

diff --git a/xen/arch/x86/Kconfig b/xen/arch/x86/Kconfig
index 288dc6c042..3f88adae97 100644
--- a/xen/arch/x86/Kconfig
+++ b/xen/arch/x86/Kconfig
@@ -22,6 +22,7 @@ config X86
 	select HAS_PASSTHROUGH
 	select HAS_PCI
 	select HAS_PDX
+	select HAS_SCHED_GRANULARITY
 	select HAS_UBSAN
 	select HAS_VPCI if !PV_SHIM_EXCLUSIVE && HVM
 	select NEEDS_LIBELF
diff --git a/xen/common/Kconfig b/xen/common/Kconfig
index 16829f6274..e9247871a8 100644
--- a/xen/common/Kconfig
+++ b/xen/common/Kconfig
@@ -63,6 +63,9 @@ config HAS_GDBSX
 config HAS_IOPORTS
 	bool
 
+config HAS_SCHED_GRANULARITY
+	bool
+
 config NEEDS_LIBELF
 	bool
 
diff --git a/xen/common/cpupool.c b/xen/common/cpupool.c
index 6917488210..d12269d5a3 100644
--- a/xen/common/cpupool.c
+++ b/xen/common/cpupool.c
@@ -870,6 +870,8 @@ static int __init cpupool_init(void)
     unsigned int cpu;
     int err;
 
+    scheduler_gran_init();
+
     cpupool0 = cpupool_create(0, 0, &err);
     BUG_ON(cpupool0 == NULL);
     cpupool_put(cpupool0);
diff --git a/xen/common/schedule.c b/xen/common/schedule.c
index 181adb00b2..bd596ba1dc 100644
--- a/xen/common/schedule.c
+++ b/xen/common/schedule.c
@@ -34,6 +34,7 @@
 #include <xen/cpu.h>
 #include <xen/preempt.h>
 #include <xen/event.h>
+#include <xen/warning.h>
 #include <public/sched.h>
 #include <xsm/xsm.h>
 #include <xen/err.h>
@@ -61,6 +62,23 @@ unsigned int __read_mostly sched_granularity = 1;
 bool __read_mostly sched_disable_smt_switching;
 cpumask_var_t sched_res_mask;
 
+#ifdef CONFIG_HAS_SCHED_GRANULARITY
+static int __init sched_select_granularity(const char *str)
+{
+    if ( strcmp("cpu", str) == 0 )
+        opt_sched_granularity = SCHED_GRAN_cpu;
+    else if ( strcmp("core", str) == 0 )
+        opt_sched_granularity = SCHED_GRAN_core;
+    else if ( strcmp("socket", str) == 0 )
+        opt_sched_granularity = SCHED_GRAN_socket;
+    else
+        return -EINVAL;
+
+    return 0;
+}
+custom_param("sched-gran", sched_select_granularity);
+#endif
+
 /* Common lock for free cpus. */
 static DEFINE_SPINLOCK(sched_free_cpu_lock);
 
@@ -2606,6 +2624,66 @@ void scheduler_enable(void)
     scheduler_active = true;
 }
 
+static unsigned int __init sched_check_granularity(void)
+{
+    unsigned int cpu;
+    unsigned int siblings, gran = 0;
+
+    if ( opt_sched_granularity == SCHED_GRAN_cpu )
+        return 1;
+
+    for_each_online_cpu ( cpu )
+    {
+        siblings = cpumask_weight(sched_get_opt_cpumask(opt_sched_granularity,
+                                                        cpu));
+        if ( gran == 0 )
+            gran = siblings;
+        else if ( gran != siblings )
+            return 0;
+    }
+
+    sched_disable_smt_switching = true;
+
+    return gran;
+}
+
+/* Setup data for selected scheduler granularity. */
+void __init scheduler_gran_init(void)
+{
+    unsigned int gran = 0;
+    const char *fallback = NULL;
+
+    while ( gran == 0 )
+    {
+        gran = sched_check_granularity();
+
+        if ( gran == 0 )
+        {
+            switch ( opt_sched_granularity )
+            {
+            case SCHED_GRAN_core:
+                opt_sched_granularity = SCHED_GRAN_cpu;
+                fallback = "Asymmetric cpu configuration.\n"
+                           "Falling back to sched-gran=cpu.\n";
+                break;
+            case SCHED_GRAN_socket:
+                opt_sched_granularity = SCHED_GRAN_core;
+                fallback = "Asymmetric cpu configuration.\n"
+                           "Falling back to sched-gran=core.\n";
+                break;
+            default:
+                ASSERT_UNREACHABLE();
+                break;
+            }
+        }
+    }
+
+    if ( fallback )
+        warning_add(fallback);
+
+    sched_granularity = gran;
+}
+
 /* Initialise the data structures. */
 void __init scheduler_init(void)
 {
diff --git a/xen/include/xen/sched-if.h b/xen/include/xen/sched-if.h
index c152547a94..ace08d609c 100644
--- a/xen/include/xen/sched-if.h
+++ b/xen/include/xen/sched-if.h
@@ -625,5 +625,6 @@ affinity_balance_cpumask(const struct sched_unit *unit, int step,
 
 void sched_rm_cpu(unsigned int cpu);
 const cpumask_t *sched_get_opt_cpumask(enum sched_gran opt, unsigned int cpu);
+void scheduler_gran_init(void);
 
 #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