cpufreq: use smp_call_function_[single|many]() in acpi-cpufreq.c

Atttempting to rid us of the problematic work_on_cpu().  Just use
smp_call_fuction_single() here.

This repairs a 10% sysbench(oltp)+mysql regression which Mike reported,
due to

  commit 6b44003e5ca66a3fffeb5bc90f40ada2c4340896
  Author: Andrew Morton <akpm@linux-foundation.org>
  Date:   Thu Apr 9 09:50:37 2009 -0600

      work_on_cpu(): rewrite it to create a kernel thread on demand

It seems that the kernel calls these acpi-cpufreq functions at a quite
high frequency.

Valdis Kletnieks also reports that this causes 70-90 forks per second on
his hardware.

Cc: Valdis.Kletnieks@vt.edu
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Zhao Yakui <yakui.zhao@intel.com>
Acked-by: Dave Jones <davej@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Mike Galbraith <efault@gmx.de>
Cc: "Zhang, Yanmin" <yanmin_zhang@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Ingo Molnar <mingo@elte.hu>
[ Made it use smp_call_function_many() instead of looping over cpu's
  with smp_call_function_single()    - Linus ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 9d3af38..3e3cd3d 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -153,7 +153,8 @@
 	u32 val;
 };
 
-static long do_drv_read(void *_cmd)
+/* Called via smp_call_function_single(), on the target CPU */
+static void do_drv_read(void *_cmd)
 {
 	struct drv_cmd *cmd = _cmd;
 	u32 h;
@@ -170,10 +171,10 @@
 	default:
 		break;
 	}
-	return 0;
 }
 
-static long do_drv_write(void *_cmd)
+/* Called via smp_call_function_many(), on the target CPUs */
+static void do_drv_write(void *_cmd)
 {
 	struct drv_cmd *cmd = _cmd;
 	u32 lo, hi;
@@ -192,23 +193,18 @@
 	default:
 		break;
 	}
-	return 0;
 }
 
 static void drv_read(struct drv_cmd *cmd)
 {
 	cmd->val = 0;
 
-	work_on_cpu(cpumask_any(cmd->mask), do_drv_read, cmd);
+	smp_call_function_single(cpumask_any(cmd->mask), do_drv_read, cmd, 1);
 }
 
 static void drv_write(struct drv_cmd *cmd)
 {
-	unsigned int i;
-
-	for_each_cpu(i, cmd->mask) {
-		work_on_cpu(i, do_drv_write, cmd);
-	}
+	smp_call_function_many(cmd->mask, do_drv_write, cmd, 1);
 }
 
 static u32 get_cur_val(const struct cpumask *mask)
@@ -252,15 +248,13 @@
 	} aperf, mperf;
 };
 
-
-static long read_measured_perf_ctrs(void *_cur)
+/* Called via smp_call_function_single(), on the target CPU */
+static void read_measured_perf_ctrs(void *_cur)
 {
 	struct perf_pair *cur = _cur;
 
 	rdmsr(MSR_IA32_APERF, cur->aperf.split.lo, cur->aperf.split.hi);
 	rdmsr(MSR_IA32_MPERF, cur->mperf.split.lo, cur->mperf.split.hi);
-
-	return 0;
 }
 
 /*
@@ -283,7 +277,7 @@
 	unsigned int perf_percent;
 	unsigned int retval;
 
-	if (!work_on_cpu(cpu, read_measured_perf_ctrs, &readin))
+	if (smp_call_function_single(cpu, read_measured_perf_ctrs, &cur, 1))
 		return 0;
 
 	cur.aperf.whole = readin.aperf.whole -