ARM: SMP: remove per_cpu based spinlock in do_IPI()

The spinlock used in the do_IPI function is declared in per_cpu section,
and it does not have the cache snooping which can cause the spinlock
failure.

This fix is based on the main kernel tree:
 - ARM: SMP: avoid using bitmasks and locks for IPIs, use hardware
   instead
   commit 24480d980e9063b3ebd0dfdf2f396c305956c356

 - ARM: SMP: remove IRQ-disabling for smp_cross_call()
   commit 0df7095205cbf6ea1cdfe6254e0d6a3b823caa3b

BUG 798775

Change-Id: I6e03027cb3f586803a260e216c71fc2fd74d09f2
Reviewed-on: http://git-master/r/23779
Reviewed-by: Xin Xie <xxie@nvidia.com>
Tested-by: Xin Xie <xxie@nvidia.com>
Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>

4 files changed, 32 insertions, 79 deletions

diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 3d05190797cb..da7e7ca53cc1 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -38,7 +38,7 @@ extern void show_ipi_list(struct seq_file *p);
 /*
  * Called from assembly code, this handles an IPI.
  */
-asmlinkage void do_IPI(struct pt_regs *regs);
+asmlinkage void do_IPI(int ipinr, struct pt_regs *regs);
 
 /*
  * Setup the set of possible CPUs (via set_cpu_possible)
@@ -53,7 +53,7 @@ extern void smp_store_cpu_info(unsigned int cpuid);
 /*
  * Raise an IPI cross call on CPUs in callmap.
  */
-extern void smp_cross_call(const struct cpumask *mask);
+extern void smp_cross_call(const struct cpumask *mask, int ipi);
 
 /*
  * Boot a secondary CPU, and assign it the specified idle task.
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 44cb9db8dd50..0db42186a769 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -47,7 +47,7 @@
 	 * preserved from get_irqnr_and_base above
 	 */
 	test_for_ipi r0, r6, r5, lr
-	movne	r0, sp
+	movne	r1, sp
 	adrne	lr, BSYM(1b)
 	bne	do_IPI
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 40dc74f2b27f..7c5ddb111897 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -47,20 +47,15 @@ struct secondary_data secondary_data;
 
 /*
  * structures for inter-processor calls
- * - A collection of single bit ipi messages.
  */
 struct ipi_data {
-	spinlock_t lock;
 	unsigned long ipi_count;
-	unsigned long bits;
 };
 
-static DEFINE_PER_CPU(struct ipi_data, ipi_data) = {
-	.lock	= SPIN_LOCK_UNLOCKED,
-};
+static DEFINE_PER_CPU(struct ipi_data, ipi_data);
 
 enum ipi_msg_type {
-	IPI_TIMER,
+	IPI_TIMER = 2,
 	IPI_RESCHEDULE,
 	IPI_CALL_FUNC,
 	IPI_CALL_FUNC_SINGLE,
@@ -341,25 +336,10 @@ void __init smp_prepare_boot_cpu(void)
 
 static void send_ipi_message(const struct cpumask *mask, enum ipi_msg_type msg)
 {
-	unsigned long flags;
-	unsigned int cpu;
-
-	local_irq_save(flags);
-
-	for_each_cpu(cpu, mask) {
-		struct ipi_data *ipi = &per_cpu(ipi_data, cpu);
-
-		spin_lock(&ipi->lock);
-		ipi->bits |= 1 << msg;
-		spin_unlock(&ipi->lock);
-	}
-
 	/*
 	 * Call the platform specific cross-CPU call function.
 	 */
-	smp_cross_call(mask);
-
-	local_irq_restore(flags);
+	smp_cross_call(mask, msg);
 }
 
 void arch_send_call_function_ipi_mask(const struct cpumask *mask)
@@ -490,14 +470,8 @@ static void ipi_cpu_stop(unsigned int cpu)
 
 /*
  * Main handler for inter-processor interrupts
- *
- * For ARM, the ipimask now only identifies a single
- * category of IPI (Bit 1 IPIs have been replaced by a
- * different mechanism):
- *
- *  Bit 0 - Inter-processor function call
  */
-asmlinkage void __exception do_IPI(struct pt_regs *regs)
+asmlinkage void __exception do_IPI(int ipinr, struct pt_regs *regs)
 {
 	unsigned int cpu = smp_processor_id();
 	struct ipi_data *ipi = &per_cpu(ipi_data, cpu);
@@ -505,56 +479,35 @@ asmlinkage void __exception do_IPI(struct pt_regs *regs)
 
 	ipi->ipi_count++;
 
-	for (;;) {
-		unsigned long msgs;
-
-		spin_lock(&ipi->lock);
-		msgs = ipi->bits;
-		ipi->bits = 0;
-		spin_unlock(&ipi->lock);
-
-		if (!msgs)
-			break;
-
-		do {
-			unsigned nextmsg;
-
-			nextmsg = msgs & -msgs;
-			msgs &= ~nextmsg;
-			nextmsg = ffz(~nextmsg);
-
-			switch (nextmsg) {
-			case IPI_TIMER:
-				ipi_timer();
-				break;
+	switch (ipinr) {
+	case IPI_TIMER:
+		ipi_timer();
+		break;
 
-			case IPI_RESCHEDULE:
-				/*
-				 * nothing more to do - eveything is
-				 * done on the interrupt return path
-				 */
-				break;
+	case IPI_RESCHEDULE:
+		/*
+		 * nothing more to do - eveything is
+		 * done on the interrupt return path
+		 */
+		break;
 
-			case IPI_CALL_FUNC:
-				generic_smp_call_function_interrupt();
-				break;
+	case IPI_CALL_FUNC:
+		generic_smp_call_function_interrupt();
+		break;
 
-			case IPI_CALL_FUNC_SINGLE:
-				generic_smp_call_function_single_interrupt();
-				break;
+	case IPI_CALL_FUNC_SINGLE:
+		generic_smp_call_function_single_interrupt();
+		break;
 
-			case IPI_CPU_STOP:
-				ipi_cpu_stop(cpu);
-				break;
+	case IPI_CPU_STOP:
+		ipi_cpu_stop(cpu);
+		break;
 
-			default:
-				printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
-				       cpu, nextmsg);
-				break;
-			}
-		} while (msgs);
+	default:
+		printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
+				cpu, ipinr);
+		break;
 	}
-
 	set_irq_regs(old_regs);
 }
 
diff --git a/arch/arm/mach-tegra/include/mach/smp.h b/arch/arm/mach-tegra/include/mach/smp.h
index cd6a3fc567f1..97b460134a5e 100644
--- a/arch/arm/mach-tegra/include/mach/smp.h
+++ b/arch/arm/mach-tegra/include/mach/smp.h
@@ -15,10 +15,10 @@
 /*
  * We use IRQ1 as the IPI
  */
-static inline void smp_cross_call(const struct cpumask *mask)
+static inline void smp_cross_call(const struct cpumask *mask, int ipi)
 {
 	dsb();
-	gic_raise_softirq(mask, 1);
+	gic_raise_softirq(mask, ipi);
 }
 
 /*