Merge branch 'x86-spinlocks-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 spinlock changes from Ingo Molnar:
 "The biggest change here are paravirtualized ticket spinlocks (PV
  spinlocks), which bring a nice speedup on various benchmarks.

  The KVM host side will come to you via the KVM tree"

* 'x86-spinlocks-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/kvm/guest: Fix sparse warning: "symbol 'klock_waiting' was not declared as static"
  kvm: Paravirtual ticketlocks support for linux guests running on KVM hypervisor
  kvm guest: Add configuration support to enable debug information for KVM Guests
  kvm uapi: Add KICK_CPU and PV_UNHALT definition to uapi
  xen, pvticketlock: Allow interrupts to be enabled while blocking
  x86, ticketlock: Add slowpath logic
  jump_label: Split jumplabel ratelimit
  x86, pvticketlock: When paravirtualizing ticket locks, increment by 2
  x86, pvticketlock: Use callee-save for lock_spinning
  xen, pvticketlocks: Add xen_nopvspin parameter to disable xen pv ticketlocks
  xen, pvticketlock: Xen implementation for PV ticket locks
  xen: Defer spinlock setup until boot CPU setup
  x86, ticketlock: Collapse a layer of functions
  x86, ticketlock: Don't inline _spin_unlock when using paravirt spinlocks
  x86, spinlock: Replace pv spinlocks with pv ticketlocks

1 files changed, 128 insertions, 259 deletions

diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index cf3caee356b3..0438b9324a72 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -17,45 +17,44 @@
 #include "xen-ops.h"
 #include "debugfs.h"
 
-#ifdef CONFIG_XEN_DEBUG_FS
-static struct xen_spinlock_stats
-{
-        u64 taken;
-        u32 taken_slow;
-        u32 taken_slow_nested;
-        u32 taken_slow_pickup;
-        u32 taken_slow_spurious;
-        u32 taken_slow_irqenable;
+enum xen_contention_stat {
+        TAKEN_SLOW,
+        TAKEN_SLOW_PICKUP,
+        TAKEN_SLOW_SPURIOUS,
+        RELEASED_SLOW,
+        RELEASED_SLOW_KICKED,
+        NR_CONTENTION_STATS
+};
 
-        u64 released;
-        u32 released_slow;
-        u32 released_slow_kicked;
 
+#ifdef CONFIG_XEN_DEBUG_FS
 #define HISTO_BUCKETS   30
-        u32 histo_spin_total[HISTO_BUCKETS+1];
-        u32 histo_spin_spinning[HISTO_BUCKETS+1];
+static struct xen_spinlock_stats
+{
+        u32 contention_stats[NR_CONTENTION_STATS];
         u32 histo_spin_blocked[HISTO_BUCKETS+1];
-
-        u64 time_total;
-        u64 time_spinning;
         u64 time_blocked;
 } spinlock_stats;
 
 static u8 zero_stats;
 
-static unsigned lock_timeout = 1 << 10;
-#define TIMEOUT lock_timeout
-
 static inline void check_zero(void)
 {
-        if (unlikely(zero_stats)) {
-                memset(&spinlock_stats, 0, sizeof(spinlock_stats));
-                zero_stats = 0;
+        u8 ret;
+        u8 old = ACCESS_ONCE(zero_stats);
+        if (unlikely(old)) {
+                ret = cmpxchg(&zero_stats, old, 0);
+                /* This ensures only one fellow resets the stat */
+                if (ret == old)
+                        memset(&spinlock_stats, 0, sizeof(spinlock_stats));
         }
 }
 
-#define ADD_STATS(elem, val)                    \
-        do { check_zero(); spinlock_stats.elem += (val); } while(0)
+static inline void add_stats(enum xen_contention_stat var, u32 val)
+{
+        check_zero();
+        spinlock_stats.contention_stats[var] += val;
+}
 
 static inline u64 spin_time_start(void)
 {
@@ -74,22 +73,6 @@ static void __spin_time_accum(u64 delta, u32 *array)
                 array[HISTO_BUCKETS]++;
 }
 
-static inline void spin_time_accum_spinning(u64 start)
-{
-        u32 delta = xen_clocksource_read() - start;
-
-        __spin_time_accum(delta, spinlock_stats.histo_spin_spinning);
-        spinlock_stats.time_spinning += delta;
-}
-
-static inline void spin_time_accum_total(u64 start)
-{
-        u32 delta = xen_clocksource_read() - start;
-
-        __spin_time_accum(delta, spinlock_stats.histo_spin_total);
-        spinlock_stats.time_total += delta;
-}
-
 static inline void spin_time_accum_blocked(u64 start)
 {
         u32 delta = xen_clocksource_read() - start;
@@ -99,19 +82,15 @@ static inline void spin_time_accum_blocked(u64 start)
 }
 #else  /* !CONFIG_XEN_DEBUG_FS */
 #define TIMEOUT                 (1 << 10)
-#define ADD_STATS(elem, val)    do { (void)(val); } while(0)
+static inline void add_stats(enum xen_contention_stat var, u32 val)
+{
+}
 
 static inline u64 spin_time_start(void)
 {
         return 0;
 }
 
-static inline void spin_time_accum_total(u64 start)
-{
-}
-static inline void spin_time_accum_spinning(u64 start)
-{
-}
 static inline void spin_time_accum_blocked(u64 start)
 {
 }
@@ -134,227 +113,123 @@ typedef u16 xen_spinners_t;
         asm(LOCK_PREFIX " decw %0" : "+m" ((xl)->spinners) : : "memory");
 #endif
 
-struct xen_spinlock {
-        unsigned char lock;             /* 0 -> free; 1 -> locked */
-        xen_spinners_t spinners;        /* count of waiting cpus */
+struct xen_lock_waiting {
+        struct arch_spinlock *lock;
+        __ticket_t want;
 };
 
-static int xen_spin_is_locked(struct arch_spinlock *lock)
-{
-        struct xen_spinlock *xl = (struct xen_spinlock *)lock;
-
-        return xl->lock != 0;
-}
-
-static int xen_spin_is_contended(struct arch_spinlock *lock)
-{
-        struct xen_spinlock *xl = (struct xen_spinlock *)lock;
-
-        /* Not strictly true; this is only the count of contended
-           lock-takers entering the slow path. */
-        return xl->spinners != 0;
-}
-
-static int xen_spin_trylock(struct arch_spinlock *lock)
-{
-        struct xen_spinlock *xl = (struct xen_spinlock *)lock;
-        u8 old = 1;
-
-        asm("xchgb %b0,%1"
-            : "+q" (old), "+m" (xl->lock) : : "memory");
-
-        return old == 0;
-}
-
-static DEFINE_PER_CPU(char *, irq_name);
 static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
-static DEFINE_PER_CPU(struct xen_spinlock *, lock_spinners);
-
-/*
- * Mark a cpu as interested in a lock.  Returns the CPU's previous
- * lock of interest, in case we got preempted by an interrupt.
- */
-static inline struct xen_spinlock *spinning_lock(struct xen_spinlock *xl)
-{
-        struct xen_spinlock *prev;
-
-        prev = __this_cpu_read(lock_spinners);
-        __this_cpu_write(lock_spinners, xl);
-
-        wmb();                  /* set lock of interest before count */
-
-        inc_spinners(xl);
-
-        return prev;
-}
-
-/*
- * Mark a cpu as no longer interested in a lock.  Restores previous
- * lock of interest (NULL for none).
- */
-static inline void unspinning_lock(struct xen_spinlock *xl, struct xen_spinlock *prev)
-{
-        dec_spinners(xl);
-        wmb();                  /* decrement count before restoring lock */
-        __this_cpu_write(lock_spinners, prev);
-}
+static DEFINE_PER_CPU(char *, irq_name);
+static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting);
+static cpumask_t waiting_cpus;
 
-static noinline int xen_spin_lock_slow(struct arch_spinlock *lock, bool irq_enable)
+static void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
 {
-        struct xen_spinlock *xl = (struct xen_spinlock *)lock;
-        struct xen_spinlock *prev;
         int irq = __this_cpu_read(lock_kicker_irq);
-        int ret;
+        struct xen_lock_waiting *w = &__get_cpu_var(lock_waiting);
+        int cpu = smp_processor_id();
         u64 start;
+        unsigned long flags;
 
         /* If kicker interrupts not initialized yet, just spin */
         if (irq == -1)
-                return 0;
+                return;
 
         start = spin_time_start();
 
-        /* announce we're spinning */
-        prev = spinning_lock(xl);
+        /*
+         * Make sure an interrupt handler can't upset things in a
+         * partially setup state.
+         */
+        local_irq_save(flags);
+        /*
+         * We don't really care if we're overwriting some other
+         * (lock,want) pair, as that would mean that we're currently
+         * in an interrupt context, and the outer context had
+         * interrupts enabled.  That has already kicked the VCPU out
+         * of xen_poll_irq(), so it will just return spuriously and
+         * retry with newly setup (lock,want).
+         *
+         * The ordering protocol on this is that the "lock" pointer
+         * may only be set non-NULL if the "want" ticket is correct.
+         * If we're updating "want", we must first clear "lock".
+         */
+        w->lock = NULL;
+        smp_wmb();
+        w->want = want;
+        smp_wmb();
+        w->lock = lock;
 
-        ADD_STATS(taken_slow, 1);
-        ADD_STATS(taken_slow_nested, prev != NULL);
+        /* This uses set_bit, which atomic and therefore a barrier */
+        cpumask_set_cpu(cpu, &waiting_cpus);
+        add_stats(TAKEN_SLOW, 1);
 
-        do {
-                unsigned long flags;
+        /* clear pending */
+        xen_clear_irq_pending(irq);
 
-                /* clear pending */
-                xen_clear_irq_pending(irq);
+        /* Only check lock once pending cleared */
+        barrier();
 
-                /* check again make sure it didn't become free while
-                   we weren't looking  */
-                ret = xen_spin_trylock(lock);
-                if (ret) {
-                        ADD_STATS(taken_slow_pickup, 1);
+        /*
+         * Mark entry to slowpath before doing the pickup test to make
+         * sure we don't deadlock with an unlocker.
+         */
+        __ticket_enter_slowpath(lock);
 
-                        /*
-                         * If we interrupted another spinlock while it
-                         * was blocking, make sure it doesn't block
-                         * without rechecking the lock.
-                         */
-                        if (prev != NULL)
-                                xen_set_irq_pending(irq);
-                        goto out;
-                }
+        /*
+         * check again make sure it didn't become free while
+         * we weren't looking
+         */
+        if (ACCESS_ONCE(lock->tickets.head) == want) {
+                add_stats(TAKEN_SLOW_PICKUP, 1);
+                goto out;
+        }
 
-                flags = arch_local_save_flags();
-                if (irq_enable) {
-                        ADD_STATS(taken_slow_irqenable, 1);
-                        raw_local_irq_enable();
-                }
+        /* Allow interrupts while blocked */
+        local_irq_restore(flags);
 
-                /*
-                 * Block until irq becomes pending.  If we're
-                 * interrupted at this point (after the trylock but
-                 * before entering the block), then the nested lock
-                 * handler guarantees that the irq will be left
-                 * pending if there's any chance the lock became free;
-                 * xen_poll_irq() returns immediately if the irq is
-                 * pending.
-                 */
-                xen_poll_irq(irq);
+        /*
+         * If an interrupt happens here, it will leave the wakeup irq
+         * pending, which will cause xen_poll_irq() to return
+         * immediately.
+         */
 
-                raw_local_irq_restore(flags);
+        /* Block until irq becomes pending (or perhaps a spurious wakeup) */
+        xen_poll_irq(irq);
+        add_stats(TAKEN_SLOW_SPURIOUS, !xen_test_irq_pending(irq));
 
-                ADD_STATS(taken_slow_spurious, !xen_test_irq_pending(irq));
-        } while (!xen_test_irq_pending(irq)); /* check for spurious wakeups */
+        local_irq_save(flags);
 
         kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
-
 out:
-        unspinning_lock(xl, prev);
-        spin_time_accum_blocked(start);
-
-        return ret;
-}
-
-static inline void __xen_spin_lock(struct arch_spinlock *lock, bool irq_enable)
-{
-        struct xen_spinlock *xl = (struct xen_spinlock *)lock;
-        unsigned timeout;
-        u8 oldval;
-        u64 start_spin;
-
-        ADD_STATS(taken, 1);
-
-        start_spin = spin_time_start();
-
-        do {
-                u64 start_spin_fast = spin_time_start();
-
-                timeout = TIMEOUT;
-
-                asm("1: xchgb %1,%0\n"
-                    "   testb %1,%1\n"
-                    "   jz 3f\n"
-                    "2: rep;nop\n"
-                    "   cmpb $0,%0\n"
-                    "   je 1b\n"
-                    "   dec %2\n"
-                    "   jnz 2b\n"
-                    "3:\n"
-                    : "+m" (xl->lock), "=q" (oldval), "+r" (timeout)
-                    : "1" (1)
-                    : "memory");
+        cpumask_clear_cpu(cpu, &waiting_cpus);
+        w->lock = NULL;
 
-                spin_time_accum_spinning(start_spin_fast);
+        local_irq_restore(flags);
 
-        } while (unlikely(oldval != 0 &&
-                          (TIMEOUT == ~0 || !xen_spin_lock_slow(lock, irq_enable))));
-
-        spin_time_accum_total(start_spin);
-}
-
-static void xen_spin_lock(struct arch_spinlock *lock)
-{
-        __xen_spin_lock(lock, false);
-}
-
-static void xen_spin_lock_flags(struct arch_spinlock *lock, unsigned long flags)
-{
-        __xen_spin_lock(lock, !raw_irqs_disabled_flags(flags));
+        spin_time_accum_blocked(start);
 }
+PV_CALLEE_SAVE_REGS_THUNK(xen_lock_spinning);
 
-static noinline void xen_spin_unlock_slow(struct xen_spinlock *xl)
+static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next)
 {
         int cpu;
 
-        ADD_STATS(released_slow, 1);
+        add_stats(RELEASED_SLOW, 1);
+
+        for_each_cpu(cpu, &waiting_cpus) {
+                const struct xen_lock_waiting *w = &per_cpu(lock_waiting, cpu);
 
-        for_each_online_cpu(cpu) {
-                /* XXX should mix up next cpu selection */
-                if (per_cpu(lock_spinners, cpu) == xl) {
-                        ADD_STATS(released_slow_kicked, 1);
+                /* Make sure we read lock before want */
+                if (ACCESS_ONCE(w->lock) == lock &&
+                    ACCESS_ONCE(w->want) == next) {
+                        add_stats(RELEASED_SLOW_KICKED, 1);
                         xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
+                        break;
                 }
         }
 }
 
-static void xen_spin_unlock(struct arch_spinlock *lock)
-{
-        struct xen_spinlock *xl = (struct xen_spinlock *)lock;
-
-        ADD_STATS(released, 1);
-
-        smp_wmb();              /* make sure no writes get moved after unlock */
-        xl->lock = 0;           /* release lock */
-
-        /*
-         * Make sure unlock happens before checking for waiting
-         * spinners.  We need a strong barrier to enforce the
-         * write-read ordering to different memory locations, as the
-         * CPU makes no implied guarantees about their ordering.
-         */
-        mb();
-
-        if (unlikely(xl->spinners))
-                xen_spin_unlock_slow(xl);
-}
-
 static irqreturn_t dummy_handler(int irq, void *dev_id)
 {
         BUG();
@@ -408,6 +283,8 @@ void xen_uninit_lock_cpu(int cpu)
         per_cpu(irq_name, cpu) = NULL;
 }
 
+static bool xen_pvspin __initdata = true;
+
 void __init xen_init_spinlocks(void)
 {
         /*
@@ -417,15 +294,23 @@ void __init xen_init_spinlocks(void)
         if (xen_hvm_domain())
                 return;
 
-        BUILD_BUG_ON(sizeof(struct xen_spinlock) > sizeof(arch_spinlock_t));
+        if (!xen_pvspin) {
+                printk(KERN_DEBUG "xen: PV spinlocks disabled\n");
+                return;
+        }
 
-        pv_lock_ops.spin_is_locked = xen_spin_is_locked;
-        pv_lock_ops.spin_is_contended = xen_spin_is_contended;
-        pv_lock_ops.spin_lock = xen_spin_lock;
-        pv_lock_ops.spin_lock_flags = xen_spin_lock_flags;
-        pv_lock_ops.spin_trylock = xen_spin_trylock;
-        pv_lock_ops.spin_unlock = xen_spin_unlock;
+        static_key_slow_inc(&paravirt_ticketlocks_enabled);
+
+        pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
+        pv_lock_ops.unlock_kick = xen_unlock_kick;
+}
+
+static __init int xen_parse_nopvspin(char *arg)
+{
+        xen_pvspin = false;
+        return 0;
 }
+early_param("xen_nopvspin", xen_parse_nopvspin);
 
 #ifdef CONFIG_XEN_DEBUG_FS
 
@@ -442,37 +327,21 @@ static int __init xen_spinlock_debugfs(void)
 
         debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats);
 
-        debugfs_create_u32("timeout", 0644, d_spin_debug, &lock_timeout);
-
-        debugfs_create_u64("taken", 0444, d_spin_debug, &spinlock_stats.taken);
         debugfs_create_u32("taken_slow", 0444, d_spin_debug,
-                           &spinlock_stats.taken_slow);
-        debugfs_create_u32("taken_slow_nested", 0444, d_spin_debug,
-                           &spinlock_stats.taken_slow_nested);
+                           &spinlock_stats.contention_stats[TAKEN_SLOW]);
         debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug,
-                           &spinlock_stats.taken_slow_pickup);
+                           &spinlock_stats.contention_stats[TAKEN_SLOW_PICKUP]);
         debugfs_create_u32("taken_slow_spurious", 0444, d_spin_debug,
-                           &spinlock_stats.taken_slow_spurious);
-        debugfs_create_u32("taken_slow_irqenable", 0444, d_spin_debug,
-                           &spinlock_stats.taken_slow_irqenable);
+                           &spinlock_stats.contention_stats[TAKEN_SLOW_SPURIOUS]);
 
-        debugfs_create_u64("released", 0444, d_spin_debug, &spinlock_stats.released);
         debugfs_create_u32("released_slow", 0444, d_spin_debug,
-                           &spinlock_stats.released_slow);
+                           &spinlock_stats.contention_stats[RELEASED_SLOW]);
         debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug,
-                           &spinlock_stats.released_slow_kicked);
+                           &spinlock_stats.contention_stats[RELEASED_SLOW_KICKED]);
 
-        debugfs_create_u64("time_spinning", 0444, d_spin_debug,
-                           &spinlock_stats.time_spinning);
         debugfs_create_u64("time_blocked", 0444, d_spin_debug,
                            &spinlock_stats.time_blocked);
-        debugfs_create_u64("time_total", 0444, d_spin_debug,
-                           &spinlock_stats.time_total);
 
-        debugfs_create_u32_array("histo_total", 0444, d_spin_debug,
-                                spinlock_stats.histo_spin_total, HISTO_BUCKETS + 1);
-        debugfs_create_u32_array("histo_spinning", 0444, d_spin_debug,
-                                spinlock_stats.histo_spin_spinning, HISTO_BUCKETS + 1);
         debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug,
                                 spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1);