Merge tag 'for-linus' of git://github.com/openrisc/linux

Pull OpenRISC updates from Stafford Horne:
 "The OpenRISC work is a bit more interesting this time, adding SMP
  support and a few general cleanups.

  Small Things:

   - Move OpenRISC docs into Documentation and clean them up

   - Document previously undocumented devicetree bindings

   - Update the or1ksim dts to use stdout-path

  OpenRISC SMP support details:

   - First the "use shadow registers" and "define CPU_BIG_ENDIAN as
     true" get the architecture ready for SMP.

   - The "add 1 and 2 byte cmpxchg support" and "use qspinlocks and
     qrwlocks" add the SMP locking infrastructure as needed. Using the
     qspinlocks and qrwlocks as suggested by Peter Z while reviewing the
     original spinlocks implementation.

   - The "support for ompic" adds a new irqchip device which is used for
     IPI communication to support SMP.

   - The "initial SMP support" adds smp.c and makes changes to all of
     the necessary data-structures to be per-cpu.

  The remaining patches are bug fixes and debug helpers which I wanted
  to keep separate from the "initial SMP support" in order to allow them
  to be reviewed on their own. This includes:

   - add cacheflush support to fix icache aliasing

   - fix initial preempt state for secondary cpu tasks

   - sleep instead of spin on secondary wait

   - support framepointers and STACKTRACE_SUPPORT

   - enable LOCKDEP_SUPPORT and irqflags tracing

   - timer sync: Add tick timer sync logic

   - fix possible deadlock in timer sync, pointed out by mips guys

  Note: the irqchip patch was reviewed with Marc and we agreed to push
  it together with these patches"

* tag 'for-linus' of git://github.com/openrisc/linux:
  openrisc: fix possible deadlock scenario during timer sync
  openrisc: pass endianness info to sparse
  openrisc: add tick timer multi-core sync logic
  openrisc: enable LOCKDEP_SUPPORT and irqflags tracing
  openrisc: support framepointers and STACKTRACE_SUPPORT
  openrisc: add simple_smp dts and defconfig for simulators
  openrisc: add cacheflush support to fix icache aliasing
  openrisc: sleep instead of spin on secondary wait
  openrisc: fix initial preempt state for secondary cpu tasks
  openrisc: initial SMP support
  irqchip: add initial support for ompic
  dt-bindings: add openrisc to vendor prefixes list
  openrisc: use qspinlocks and qrwlocks
  openrisc: add 1 and 2 byte cmpxchg support
  openrisc: use shadow registers to save regs on exception
  dt-bindings: openrisc: Add OpenRISC platform SoC
  Documentation: openrisc: Updates to README
  Documentation: Move OpenRISC docs out of arch/
  MAINTAINERS: Add OpenRISC pic maintainer
  openrisc: dts: or1ksim: Add stdout-path

1 files changed, 120 insertions, 0 deletions

diff --git a/arch/openrisc/kernel/sync-timer.c b/arch/openrisc/kernel/sync-timer.c
new file mode 100644
index 000000000000..ed8d835caca1
--- /dev/null
+++ b/arch/openrisc/kernel/sync-timer.c
@@ -0,0 +1,120 @@
+/*
+ * OR1K timer synchronisation
+ *
+ * Based on work from MIPS implementation.
+ *
+ * All CPUs will have their count registers synchronised to the CPU0 next time
+ * value. This can cause a small timewarp for CPU0. All other CPU's should
+ * not have done anything significant (but they may have had interrupts
+ * enabled briefly - prom_smp_finish() should not be responsible for enabling
+ * interrupts...)
+ */
+
+#include <linux/kernel.h>
+#include <linux/irqflags.h>
+#include <linux/cpumask.h>
+
+#include <asm/time.h>
+#include <asm/timex.h>
+#include <linux/atomic.h>
+#include <asm/barrier.h>
+
+#include <asm/spr.h>
+
+static unsigned int initcount;
+static atomic_t count_count_start = ATOMIC_INIT(0);
+static atomic_t count_count_stop = ATOMIC_INIT(0);
+
+#define COUNTON 100
+#define NR_LOOPS 3
+
+void synchronise_count_master(int cpu)
+{
+	int i;
+	unsigned long flags;
+
+	pr_info("Synchronize counters for CPU %u: ", cpu);
+
+	local_irq_save(flags);
+
+	/*
+	 * We loop a few times to get a primed instruction cache,
+	 * then the last pass is more or less synchronised and
+	 * the master and slaves each set their cycle counters to a known
+	 * value all at once. This reduces the chance of having random offsets
+	 * between the processors, and guarantees that the maximum
+	 * delay between the cycle counters is never bigger than
+	 * the latency of information-passing (cachelines) between
+	 * two CPUs.
+	 */
+
+	for (i = 0; i < NR_LOOPS; i++) {
+		/* slaves loop on '!= 2' */
+		while (atomic_read(&count_count_start) != 1)
+			mb();
+		atomic_set(&count_count_stop, 0);
+		smp_wmb();
+
+		/* Let the slave writes its count register */
+		atomic_inc(&count_count_start);
+
+		/* Count will be initialised to current timer */
+		if (i == 1)
+			initcount = get_cycles();
+
+		/*
+		 * Everyone initialises count in the last loop:
+		 */
+		if (i == NR_LOOPS-1)
+			openrisc_timer_set(initcount);
+
+		/*
+		 * Wait for slave to leave the synchronization point:
+		 */
+		while (atomic_read(&count_count_stop) != 1)
+			mb();
+		atomic_set(&count_count_start, 0);
+		smp_wmb();
+		atomic_inc(&count_count_stop);
+	}
+	/* Arrange for an interrupt in a short while */
+	openrisc_timer_set_next(COUNTON);
+
+	local_irq_restore(flags);
+
+	/*
+	 * i386 code reported the skew here, but the
+	 * count registers were almost certainly out of sync
+	 * so no point in alarming people
+	 */
+	pr_cont("done.\n");
+}
+
+void synchronise_count_slave(int cpu)
+{
+	int i;
+
+	/*
+	 * Not every cpu is online at the time this gets called,
+	 * so we first wait for the master to say everyone is ready
+	 */
+
+	for (i = 0; i < NR_LOOPS; i++) {
+		atomic_inc(&count_count_start);
+		while (atomic_read(&count_count_start) != 2)
+			mb();
+
+		/*
+		 * Everyone initialises count in the last loop:
+		 */
+		if (i == NR_LOOPS-1)
+			openrisc_timer_set(initcount);
+
+		atomic_inc(&count_count_stop);
+		while (atomic_read(&count_count_stop) != 2)
+			mb();
+	}
+	/* Arrange for an interrupt in a short while */
+	openrisc_timer_set_next(COUNTON);
+}
+#undef NR_LOOPS