rdmsr_on_cpu, wrmsr_on_cpu

There was OpenVZ specific bug rendering some cpufreq drivers unusable on SMP.
In short, when cpufreq code thinks it confined itself to needed cpu by means
of set_cpus_allowed() to execute rdmsr, some "virtual cpu" feature can migrate
process to anywhere.  This triggers bugons and does wrong things in general.

This got fixed by introducing rdmsr_on_cpu and wrmsr_on_cpu executing rdmsr
and wrmsr on given physical cpu by means of smp_call_function_single().

Dave Jones mentioned cpufreq might be not only user of rdmsr_on_cpu() and
wrmsr_on_cpu(), so I'm putting them into arch/{i386,x86_64}/lib/ .

Signed-off-by: Alexey Dobriyan <adobriyan@openvz.org>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Dave Jones <davej@redhat.com>

6 files changed, 79 insertions, 1 deletions

diff --git a/arch/i386/lib/Makefile b/arch/i386/lib/Makefile
index d86a548b8d54..0d41223472c2 100644
--- a/arch/i386/lib/Makefile
+++ b/arch/i386/lib/Makefile
@@ -7,3 +7,5 @@ lib-y = checksum.o delay.o usercopy.o getuser.o putuser.o memcpy.o strstr.o \
 	bitops.o semaphore.o
 
 lib-$(CONFIG_X86_USE_3DNOW) += mmx.o
+
+obj-y = msr-on-cpu.o
diff --git a/arch/i386/lib/msr-on-cpu.c b/arch/i386/lib/msr-on-cpu.c
new file mode 100644
index 000000000000..2092ea15ba85
--- /dev/null
+++ b/arch/i386/lib/msr-on-cpu.c
@@ -0,0 +1,70 @@
+#include <linux/module.h>
+#include <linux/preempt.h>
+#include <linux/smp.h>
+#include <asm/msr.h>
+
+#ifdef CONFIG_SMP
+struct msr_info {
+	u32 msr_no;
+	u32 l, h;
+};
+
+static void __rdmsr_on_cpu(void *info)
+{
+	struct msr_info *rv = info;
+
+	rdmsr(rv->msr_no, rv->l, rv->h);
+}
+
+void rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
+{
+	preempt_disable();
+	if (smp_processor_id() == cpu)
+		rdmsr(msr_no, *l, *h);
+	else {
+		struct msr_info rv;
+
+		rv.msr_no = msr_no;
+		smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 0, 1);
+		*l = rv.l;
+		*h = rv.h;
+	}
+	preempt_enable();
+}
+
+static void __wrmsr_on_cpu(void *info)
+{
+	struct msr_info *rv = info;
+
+	wrmsr(rv->msr_no, rv->l, rv->h);
+}
+
+void wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+{
+	preempt_disable();
+	if (smp_processor_id() == cpu)
+		wrmsr(msr_no, l, h);
+	else {
+		struct msr_info rv;
+
+		rv.msr_no = msr_no;
+		rv.l = l;
+		rv.h = h;
+		smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 0, 1);
+	}
+	preempt_enable();
+}
+#else
+void rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
+{
+	rdmsr(msr_no, *l, *h);
+}
+
+void wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+{
+	wrmsr(msr_no, l, h);
+}
+#endif
+
+EXPORT_SYMBOL(rdmsr_on_cpu);
+EXPORT_SYMBOL(wrmsr_on_cpu);
diff --git a/arch/x86_64/lib/Makefile b/arch/x86_64/lib/Makefile
index b78d4170fce2..0a43f07b0290 100644
--- a/arch/x86_64/lib/Makefile
+++ b/arch/x86_64/lib/Makefile
@@ -4,7 +4,7 @@
 
 CFLAGS_csum-partial.o := -funroll-loops
 
-obj-y := io.o iomap_copy.o
+obj-y := io.o iomap_copy.o msr-on-cpu.o
 
 lib-y := csum-partial.o csum-copy.o csum-wrappers.o delay.o \
 	usercopy.o getuser.o putuser.o  \
diff --git a/arch/x86_64/lib/msr-on-cpu.c b/arch/x86_64/lib/msr-on-cpu.c
new file mode 100644
index 000000000000..47e0ec47c376
--- /dev/null
+++ b/arch/x86_64/lib/msr-on-cpu.c
@@ -0,0 +1 @@
+#include "../../i386/lib/msr-on-cpu.c"
diff --git a/include/asm-i386/msr.h b/include/asm-i386/msr.h
index 609a3899475c..3516a1fb38e0 100644
--- a/include/asm-i386/msr.h
+++ b/include/asm-i386/msr.h
@@ -83,6 +83,9 @@ static inline void wrmsrl (unsigned long msr, unsigned long long val)
 			  : "c" (counter))
 #endif	/* !CONFIG_PARAVIRT */
 
+void rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
+void wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
+
 /* symbolic names for some interesting MSRs */
 /* Intel defined MSRs. */
 #define MSR_IA32_P5_MC_ADDR		0
diff --git a/include/asm-x86_64/msr.h b/include/asm-x86_64/msr.h
index 3227bc93d69b..995a2b5fb26b 100644
--- a/include/asm-x86_64/msr.h
+++ b/include/asm-x86_64/msr.h
@@ -160,6 +160,8 @@ static inline unsigned int cpuid_edx(unsigned int op)
 #define MSR_IA32_UCODE_WRITE		0x79
 #define MSR_IA32_UCODE_REV		0x8b
 
+void rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
+void wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
 
 #endif