Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/cmarinas/linux-aarch64

Pull ARM64 update from Catalin Marinas:
 "Main features:
   - Ticket-based spinlock implementation and lockless lockref support
   - Big endian support
   - CPU hotplug support, currently for PSCI (Power State Coordination
     Interface) capable firmware
   - Virtual address space extended to 42-bit in the 64K page
     configuration (maximum VA space with 2 levels of page tables)
   - Compat (AArch32) kuser helpers updated to ARMv8 (make use of
     load-acquire/store-release instructions)
   - Code cleanup, defconfig update and minor fixes"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/cmarinas/linux-aarch64: (43 commits)
  ARM64: /proc/interrupts: display IPIs of online CPUs only
  arm64: locks: Remove CONFIG_GENERIC_LOCKBREAK
  arm64: KVM: vgic: byteswap GICv2 access on world switch if BE
  arm64: KVM: initialize HYP mode following the kernel endianness
  arm64: compat: Clear the IT state independent of the 32-bit ARM or Thumb-2 mode
  arm64: Use 42-bit address space with 64K pages
  arm64: module: ensure instruction is little-endian before manipulation
  arm64: defconfig: Enable CONFIG_PREEMPT by default
  arm64: fix access to preempt_count from assembly code
  arm64: move enabling of GIC before CPUs are set online
  arm64: use generic RW_DATA_SECTION macro in linker script
  arm64: Slightly improve the warning on CPU0 enable-method
  ARM64: simplify cpu_read_bootcpu_ops using OF/DT helper
  ARM64: DT: define ARM64 specific arch_match_cpu_phys_id
  arm64: allow ioremap_cache() to use existing RAM mappings
  arm64: update 32-bit kuser helpers to ARMv8
  arm64: perf: fix event number mask
  arm64: kconfig: allow CPU_BIG_ENDIAN to be selected
  arm64: Fix the endianness of arch_spinlock_t
  arm64: big-endian: write CPU holding pen address as LE
  ...

1 files changed, 91 insertions, 6 deletions

diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 7c35fa6..44c2280 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -16,15 +16,39 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/smp.h>
 
 #include <asm/cacheflush.h>
+#include <asm/cpu_ops.h>
+#include <asm/cputype.h>
+#include <asm/smp_plat.h>
+
+extern void secondary_holding_pen(void);
+volatile unsigned long secondary_holding_pen_release = INVALID_HWID;
 
 static phys_addr_t cpu_release_addr[NR_CPUS];
+static DEFINE_RAW_SPINLOCK(boot_lock);
+
+/*
+ * Write secondary_holding_pen_release in a way that is guaranteed to be
+ * visible to all observers, irrespective of whether they're taking part
+ * in coherency or not.  This is necessary for the hotplug code to work
+ * reliably.
+ */
+static void write_pen_release(u64 val)
+{
+	void *start = (void *)&secondary_holding_pen_release;
+	unsigned long size = sizeof(secondary_holding_pen_release);
 
-static int __init smp_spin_table_init_cpu(struct device_node *dn, int cpu)
+	secondary_holding_pen_release = val;
+	__flush_dcache_area(start, size);
+}
+
+
+static int smp_spin_table_cpu_init(struct device_node *dn, unsigned int cpu)
 {
 	/*
 	 * Determine the address from which the CPU is polling.
@@ -40,7 +64,7 @@ static int __init smp_spin_table_init_cpu(struct device_node *dn, int cpu)
 	return 0;
 }
 
-static int __init smp_spin_table_prepare_cpu(int cpu)
+static int smp_spin_table_cpu_prepare(unsigned int cpu)
 {
 	void **release_addr;
 
@@ -48,7 +72,16 @@ static int __init smp_spin_table_prepare_cpu(int cpu)
 		return -ENODEV;
 
 	release_addr = __va(cpu_release_addr[cpu]);
-	release_addr[0] = (void *)__pa(secondary_holding_pen);
+
+	/*
+	 * We write the release address as LE regardless of the native
+	 * endianess of the kernel. Therefore, any boot-loaders that
+	 * read this address need to convert this address to the
+	 * boot-loader's endianess before jumping. This is mandated by
+	 * the boot protocol.
+	 */
+	release_addr[0] = (void *) cpu_to_le64(__pa(secondary_holding_pen));
+
 	__flush_dcache_area(release_addr, sizeof(release_addr[0]));
 
 	/*
@@ -59,8 +92,60 @@ static int __init smp_spin_table_prepare_cpu(int cpu)
 	return 0;
 }
 
-const struct smp_enable_ops smp_spin_table_ops __initconst = {
+static int smp_spin_table_cpu_boot(unsigned int cpu)
+{
+	unsigned long timeout;
+
+	/*
+	 * Set synchronisation state between this boot processor
+	 * and the secondary one
+	 */
+	raw_spin_lock(&boot_lock);
+
+	/*
+	 * Update the pen release flag.
+	 */
+	write_pen_release(cpu_logical_map(cpu));
+
+	/*
+	 * Send an event, causing the secondaries to read pen_release.
+	 */
+	sev();
+
+	timeout = jiffies + (1 * HZ);
+	while (time_before(jiffies, timeout)) {
+		if (secondary_holding_pen_release == INVALID_HWID)
+			break;
+		udelay(10);
+	}
+
+	/*
+	 * Now the secondary core is starting up let it run its
+	 * calibrations, then wait for it to finish
+	 */
+	raw_spin_unlock(&boot_lock);
+
+	return secondary_holding_pen_release != INVALID_HWID ? -ENOSYS : 0;
+}
+
+void smp_spin_table_cpu_postboot(void)
+{
+	/*
+	 * Let the primary processor know we're out of the pen.
+	 */
+	write_pen_release(INVALID_HWID);
+
+	/*
+	 * Synchronise with the boot thread.
+	 */
+	raw_spin_lock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
+}
+
+const struct cpu_operations smp_spin_table_ops = {
 	.name		= "spin-table",
-	.init_cpu 	= smp_spin_table_init_cpu,
-	.prepare_cpu	= smp_spin_table_prepare_cpu,
+	.cpu_init	= smp_spin_table_cpu_init,
+	.cpu_prepare	= smp_spin_table_cpu_prepare,
+	.cpu_boot	= smp_spin_table_cpu_boot,
+	.cpu_postboot	= smp_spin_table_cpu_postboot,
 };