arm64: SMP support

This patch adds SMP initialisation and spinlocks implementation for
AArch64. The spinlock support uses the new load-acquire/store-release
instructions to avoid explicit barriers. The architecture also specifies
that an event is automatically generated when clearing the exclusive
monitor state to wake up processors in WFE, so there is no need for an
explicit DSB/SEV instruction sequence. The SEVL instruction is used to
set the exclusive monitor locally as there is no conditional WFE and a
branch is more expensive.

For the SMP booting protocol, see Documentation/arm64/booting.txt.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Tony Lindgren <tony@atomide.com>
Acked-by: Nicolas Pitre <nico@linaro.org>
Acked-by: Olof Johansson <olof@lixom.net>
Acked-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>

4 files changed, 314 insertions, 0 deletions

diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h
index c6c9514..5075463 100644
--- a/arch/arm64/include/asm/hardirq.h
+++ b/arch/arm64/include/asm/hardirq.h
@@ -20,8 +20,13 @@
 #include <linux/threads.h>
 #include <asm/irq.h>
 
+#define NR_IPI	4
+
 typedef struct {
 	unsigned int __softirq_pending;
+#ifdef CONFIG_SMP
+	unsigned int ipi_irqs[NR_IPI];
+#endif
 } ____cacheline_aligned irq_cpustat_t;
 
 #include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
new file mode 100644
index 0000000..7e34295
--- /dev/null
+++ b/arch/arm64/include/asm/smp.h
@@ -0,0 +1,69 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_SMP_H
+#define __ASM_SMP_H
+
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/thread_info.h>
+
+#ifndef CONFIG_SMP
+# error "<asm/smp.h> included in non-SMP build"
+#endif
+
+#define raw_smp_processor_id() (current_thread_info()->cpu)
+
+struct seq_file;
+
+/*
+ * generate IPI list text
+ */
+extern void show_ipi_list(struct seq_file *p, int prec);
+
+/*
+ * Called from C code, this handles an IPI.
+ */
+extern void handle_IPI(int ipinr, struct pt_regs *regs);
+
+/*
+ * Setup the set of possible CPUs (via set_cpu_possible)
+ */
+extern void smp_init_cpus(void);
+
+/*
+ * Provide a function to raise an IPI cross call on CPUs in callmap.
+ */
+extern void set_smp_cross_call(void (*)(const struct cpumask *, unsigned int));
+
+/*
+ * Called from the secondary holding pen, this is the secondary CPU entry point.
+ */
+asmlinkage void secondary_start_kernel(void);
+
+/*
+ * Initial data for bringing up a secondary CPU.
+ */
+struct secondary_data {
+	void *stack;
+};
+extern struct secondary_data secondary_data;
+extern void secondary_holding_pen(void);
+extern volatile unsigned long secondary_holding_pen_release;
+
+extern void arch_send_call_function_single_ipi(int cpu);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
+
+#endif /* ifndef __ASM_SMP_H */
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
new file mode 100644
index 0000000..41112fe
--- /dev/null
+++ b/arch/arm64/include/asm/spinlock.h
@@ -0,0 +1,202 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_SPINLOCK_H
+#define __ASM_SPINLOCK_H
+
+#include <asm/spinlock_types.h>
+#include <asm/processor.h>
+
+/*
+ * Spinlock implementation.
+ *
+ * The old value is read exclusively and the new one, if unlocked, is written
+ * exclusively. In case of failure, the loop is restarted.
+ *
+ * The memory barriers are implicit with the load-acquire and store-release
+ * instructions.
+ *
+ * Unlocked value: 0
+ * Locked value: 1
+ */
+
+#define arch_spin_is_locked(x)		((x)->lock != 0)
+#define arch_spin_unlock_wait(lock) \
+	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
+
+#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
+
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+	unsigned int tmp;
+
+	asm volatile(
+	"	sevl\n"
+	"1:	wfe\n"
+	"2:	ldaxr	%w0, [%1]\n"
+	"	cbnz	%w0, 1b\n"
+	"	stxr	%w0, %w2, [%1]\n"
+	"	cbnz	%w0, 2b\n"
+	: "=&r" (tmp)
+	: "r" (&lock->lock), "r" (1)
+	: "memory");
+}
+
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
+{
+	unsigned int tmp;
+
+	asm volatile(
+	"	ldaxr	%w0, [%1]\n"
+	"	cbnz	%w0, 1f\n"
+	"	stxr	%w0, %w2, [%1]\n"
+	"1:\n"
+	: "=&r" (tmp)
+	: "r" (&lock->lock), "r" (1)
+	: "memory");
+
+	return !tmp;
+}
+
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+	asm volatile(
+	"	stlr	%w1, [%0]\n"
+	: : "r" (&lock->lock), "r" (0) : "memory");
+}
+
+/*
+ * Write lock implementation.
+ *
+ * Write locks set bit 31. Unlocking, is done by writing 0 since the lock is
+ * exclusively held.
+ *
+ * The memory barriers are implicit with the load-acquire and store-release
+ * instructions.
+ */
+
+static inline void arch_write_lock(arch_rwlock_t *rw)
+{
+	unsigned int tmp;
+
+	asm volatile(
+	"	sevl\n"
+	"1:	wfe\n"
+	"2:	ldaxr	%w0, [%1]\n"
+	"	cbnz	%w0, 1b\n"
+	"	stxr	%w0, %w2, [%1]\n"
+	"	cbnz	%w0, 2b\n"
+	: "=&r" (tmp)
+	: "r" (&rw->lock), "r" (0x80000000)
+	: "memory");
+}
+
+static inline int arch_write_trylock(arch_rwlock_t *rw)
+{
+	unsigned int tmp;
+
+	asm volatile(
+	"	ldaxr	%w0, [%1]\n"
+	"	cbnz	%w0, 1f\n"
+	"	stxr	%w0, %w2, [%1]\n"
+	"1:\n"
+	: "=&r" (tmp)
+	: "r" (&rw->lock), "r" (0x80000000)
+	: "memory");
+
+	return !tmp;
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *rw)
+{
+	asm volatile(
+	"	stlr	%w1, [%0]\n"
+	: : "r" (&rw->lock), "r" (0) : "memory");
+}
+
+/* write_can_lock - would write_trylock() succeed? */
+#define arch_write_can_lock(x)		((x)->lock == 0)
+
+/*
+ * Read lock implementation.
+ *
+ * It exclusively loads the lock value, increments it and stores the new value
+ * back if positive and the CPU still exclusively owns the location. If the
+ * value is negative, the lock is already held.
+ *
+ * During unlocking there may be multiple active read locks but no write lock.
+ *
+ * The memory barriers are implicit with the load-acquire and store-release
+ * instructions.
+ */
+static inline void arch_read_lock(arch_rwlock_t *rw)
+{
+	unsigned int tmp, tmp2;
+
+	asm volatile(
+	"	sevl\n"
+	"1:	wfe\n"
+	"2:	ldaxr	%w0, [%2]\n"
+	"	add	%w0, %w0, #1\n"
+	"	tbnz	%w0, #31, 1b\n"
+	"	stxr	%w1, %w0, [%2]\n"
+	"	cbnz	%w1, 2b\n"
+	: "=&r" (tmp), "=&r" (tmp2)
+	: "r" (&rw->lock)
+	: "memory");
+}
+
+static inline void arch_read_unlock(arch_rwlock_t *rw)
+{
+	unsigned int tmp, tmp2;
+
+	asm volatile(
+	"1:	ldxr	%w0, [%2]\n"
+	"	sub	%w0, %w0, #1\n"
+	"	stlxr	%w1, %w0, [%2]\n"
+	"	cbnz	%w1, 1b\n"
+	: "=&r" (tmp), "=&r" (tmp2)
+	: "r" (&rw->lock)
+	: "memory");
+}
+
+static inline int arch_read_trylock(arch_rwlock_t *rw)
+{
+	unsigned int tmp, tmp2 = 1;
+
+	asm volatile(
+	"	ldaxr	%w0, [%2]\n"
+	"	add	%w0, %w0, #1\n"
+	"	tbnz	%w0, #31, 1f\n"
+	"	stxr	%w1, %w0, [%2]\n"
+	"1:\n"
+	: "=&r" (tmp), "+r" (tmp2)
+	: "r" (&rw->lock)
+	: "memory");
+
+	return !tmp2;
+}
+
+/* read_can_lock - would read_trylock() succeed? */
+#define arch_read_can_lock(x)		((x)->lock < 0x80000000)
+
+#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
+#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
+
+#define arch_spin_relax(lock)	cpu_relax()
+#define arch_read_relax(lock)	cpu_relax()
+#define arch_write_relax(lock)	cpu_relax()
+
+#endif /* __ASM_SPINLOCK_H */
diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h
new file mode 100644
index 0000000..9a49434
--- /dev/null
+++ b/arch/arm64/include/asm/spinlock_types.h
@@ -0,0 +1,38 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_SPINLOCK_TYPES_H
+#define __ASM_SPINLOCK_TYPES_H
+
+#if !defined(__LINUX_SPINLOCK_TYPES_H) && !defined(__ASM_SPINLOCK_H)
+# error "please don't include this file directly"
+#endif
+
+/* We only require natural alignment for exclusive accesses. */
+#define __lock_aligned
+
+typedef struct {
+	volatile unsigned int lock;
+} arch_spinlock_t;
+
+#define __ARCH_SPIN_LOCK_UNLOCKED	{ 0 }
+
+typedef struct {
+	volatile unsigned int lock;
+} arch_rwlock_t;
+
+#define __ARCH_RW_LOCK_UNLOCKED		{ 0 }
+
+#endif