[PATCH] i386 adds smp_call_function_single

[PATCH] i386 adds smp_call_function_single

[Stephane Eranian]

Hello,

Continiung the series of small patches necessary for the perfmon subsystem, here
is a patch that adds support for the smp_call_function_single() function for i386.
It exists for almost all other architectures but i386. The perfmon subsystem
needs it in one case to free some state on a designated remote CPU.

Changelog:
	- adds smp_call_function_single() to i386 tree. This function
	  is used to invoked a procedure on a designated remote CPU.

<signed-off-by>: eranian@hpl.hp.com

diff --git a/arch/i386/kernel/smp.c b/arch/i386/kernel/smp.c
--- a/arch/i386/kernel/smp.c
+++ b/arch/i386/kernel/smp.c
@@ -634,3 +634,69 @@ fastcall void smp_call_function_interrup
 	}
 }
 
+/*
+ * this function sends a 'generic call function' IPI to one other CPU
+ * in the system.
+ *
+ * cpu is a standard Linux logical CPU number.
+ */
+static void
+__smp_call_function_single(int cpu, void (*func) (void *info), void *info,
+				int nonatomic, int wait)
+{
+	struct call_data_struct data;
+	int cpus = 1;
+  
+	data.func = func;
+	data.info = info;
+	atomic_set(&data.started, 0);
+	data.wait = wait;
+	if (wait)
+		atomic_set(&data.finished, 0);
+
+	call_data = &data;
+	wmb();
+	/* Send a message to all other CPUs and wait for them to respond */
+	send_IPI_mask(cpumask_of_cpu(cpu), CALL_FUNCTION_VECTOR);
+
+	/* Wait for response */
+	while (atomic_read(&data.started) != cpus)
+		cpu_relax();
+
+	if (!wait)
+		return;
+
+	while (atomic_read(&data.finished) != cpus)
+		cpu_relax();
+}
+
+/*
+ * smp_call_function_single - Run a function on another CPU
+ * @func: The function to run. This must be fast and non-blocking.
+ * @info: An arbitrary pointer to pass to the function.
+ * @nonatomic: Currently unused.
+ * @wait: If true, wait until function has completed on other CPUs.
+ *
+ * Retrurns 0 on success, else a negative status code.
+ *
+ * Does not return until the remote CPU is nearly ready to execute <func>
+ * or is or has executed.
+ */
+
+int smp_call_function_single (int cpu, void (*func) (void *info), void *info,
+	int nonatomic, int wait)
+{
+	/* prevent preemption and reschedule on another processor */
+	int me = get_cpu();
+	if (cpu == me) {
+		WARN_ON(1);
+		put_cpu();
+		return -EBUSY;
+	}
+	spin_lock_bh(&call_lock);
+	__smp_call_function_single(cpu, func, info, nonatomic, wait);
+	spin_unlock_bh(&call_lock);
+	put_cpu();
+	return 0;
+}
+EXPORT_SYMBOL(smp_call_function_single);

Re: [PATCH] i386 adds smp_call_function_single

[Dave Jones]

On Tue, Jul 11, 2006 at 06:24:22AM -0700, Stephane Eranian wrote:
 > Hello,
 > 
 > Continiung the series of small patches necessary for the perfmon subsystem, here
 > is a patch that adds support for the smp_call_function_single() function for i386.
 > It exists for almost all other architectures but i386. The perfmon subsystem
 > needs it in one case to free some state on a designated remote CPU.
 > 
 > Changelog:
 > 	- adds smp_call_function_single() to i386 tree. This function
 > 	  is used to invoked a procedure on a designated remote CPU.

The naming seems a little strange to me.  Something like
run_on_cpu() would be clearer.  Less keystrokes too :)

		Dave

-- 
http://www.codemonkey.org.uk

Re: [PATCH] i386 adds smp_call_function_single

[Stephane Eranian]

Dave,

On Tue, Jul 11, 2006 at 01:52:39PM -0400, Dave Jones wrote:
> On Tue, Jul 11, 2006 at 06:24:22AM -0700, Stephane Eranian wrote:
>  > Hello,
>  > 
>  > Continiung the series of small patches necessary for the perfmon subsystem, here
>  > is a patch that adds support for the smp_call_function_single() function for i386.
>  > It exists for almost all other architectures but i386. The perfmon subsystem
>  > needs it in one case to free some state on a designated remote CPU.
>  > 
>  > Changelog:
>  > 	- adds smp_call_function_single() to i386 tree. This function
>  > 	  is used to invoked a procedure on a designated remote CPU.
> 
> The naming seems a little strange to me.  Something like
> run_on_cpu() would be clearer.  Less keystrokes too :)
> 

I agree with you that the name is a bit long but I did not invent it.
The same function name is used for this functionality on IA-64 and X86-64.

--
-Stephane

Re: [PATCH] i386 adds smp_call_function_single

[Keith Owens]

Stephane Eranian (on Tue, 11 Jul 2006 06:24:22 -0700) wrote:
>+static void
>+__smp_call_function_single(int cpu, void (*func) (void *info), void *info,
>+				int nonatomic, int wait)
>...
>+	wmb();
>+	/* Send a message to all other CPUs and wait for them to respond */
>+	send_IPI_mask(cpumask_of_cpu(cpu), CALL_FUNCTION_VECTOR);

Nit pick.  The comment is wrong, one cpu, not all cpus.