locking/pvqspinlock: Implement simple paravirt support for the qspinlock

Provide a separate (second) version of the spin_lock_slowpath for
paravirt along with a special unlock path.

The second slowpath is generated by adding a few pv hooks to the
normal slowpath, but where those will compile away for the native
case, they expand into special wait/wake code for the pv version.

The actual MCS queue can use extra storage in the mcs_nodes[] array to
keep track of state and therefore uses directed wakeups.

The head contender has no such storage directly visible to the
unlocker.  So the unlocker searches a hash table with open addressing
using a simple binary Galois linear feedback shift register.

Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Daniel J Blueman <daniel@numascale.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Douglas Hatch <doug.hatch@hp.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paolo Bonzini <paolo.bonzini@gmail.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1429901803-29771-9-git-send-email-Waiman.Long@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 67 insertions, 1 deletions

diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index fd31a474145d..38c49202d532 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -18,6 +18,9 @@
  * Authors: Waiman Long <waiman.long@hp.com>
  *          Peter Zijlstra <peterz@infradead.org>
  */
+
+#ifndef _GEN_PV_LOCK_SLOWPATH
+
 #include <linux/smp.h>
 #include <linux/bug.h>
 #include <linux/cpumask.h>
@@ -65,13 +68,21 @@
 
 #include "mcs_spinlock.h"
 
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+#define MAX_NODES       8
+#else
+#define MAX_NODES       4
+#endif
+
 /*
  * Per-CPU queue node structures; we can never have more than 4 nested
  * contexts: task, softirq, hardirq, nmi.
  *
  * Exactly fits one 64-byte cacheline on a 64-bit architecture.
+ *
+ * PV doubles the storage and uses the second cacheline for PV state.
  */
-static DEFINE_PER_CPU_ALIGNED(struct mcs_spinlock, mcs_nodes[4]);
+static DEFINE_PER_CPU_ALIGNED(struct mcs_spinlock, mcs_nodes[MAX_NODES]);
 
 /*
  * We must be able to distinguish between no-tail and the tail at 0:0,
@@ -220,6 +231,32 @@ static __always_inline void set_locked(struct qspinlock *lock)
         WRITE_ONCE(l->locked, _Q_LOCKED_VAL);
 }
 
+
+/*
+ * Generate the native code for queued_spin_unlock_slowpath(); provide NOPs for
+ * all the PV callbacks.
+ */
+
+static __always_inline void __pv_init_node(struct mcs_spinlock *node) { }
+static __always_inline void __pv_wait_node(struct mcs_spinlock *node) { }
+static __always_inline void __pv_kick_node(struct mcs_spinlock *node) { }
+
+static __always_inline void __pv_wait_head(struct qspinlock *lock,
+                                           struct mcs_spinlock *node) { }
+
+#define pv_enabled()            false
+
+#define pv_init_node            __pv_init_node
+#define pv_wait_node            __pv_wait_node
+#define pv_kick_node            __pv_kick_node
+#define pv_wait_head            __pv_wait_head
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+#define queued_spin_lock_slowpath       native_queued_spin_lock_slowpath
+#endif
+
+#endif /* _GEN_PV_LOCK_SLOWPATH */
+
 /**
  * queued_spin_lock_slowpath - acquire the queued spinlock
  * @lock: Pointer to queued spinlock structure
@@ -249,6 +286,9 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 
         BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS));
 
+        if (pv_enabled())
+                goto queue;
+
         if (virt_queued_spin_lock(lock))
                 return;
 
@@ -325,6 +365,7 @@ queue:
         node += idx;
         node->locked = 0;
         node->next = NULL;
+        pv_init_node(node);
 
         /*
          * We touched a (possibly) cold cacheline in the per-cpu queue node;
@@ -350,6 +391,7 @@ queue:
                 prev = decode_tail(old);
                 WRITE_ONCE(prev->next, node);
 
+                pv_wait_node(node);
                 arch_mcs_spin_lock_contended(&node->locked);
         }
 
@@ -365,6 +407,7 @@ queue:
          * does not imply a full barrier.
          *
          */
+        pv_wait_head(lock, node);
         while ((val = smp_load_acquire(&lock->val.counter)) & _Q_LOCKED_PENDING_MASK)
                 cpu_relax();
 
@@ -397,6 +440,7 @@ queue:
                 cpu_relax();
 
         arch_mcs_spin_unlock_contended(&next->locked);
+        pv_kick_node(next);
 
 release:
         /*
@@ -405,3 +449,25 @@ release:
         this_cpu_dec(mcs_nodes[0].count);
 }
 EXPORT_SYMBOL(queued_spin_lock_slowpath);
+
+/*
+ * Generate the paravirt code for queued_spin_unlock_slowpath().
+ */
+#if !defined(_GEN_PV_LOCK_SLOWPATH) && defined(CONFIG_PARAVIRT_SPINLOCKS)
+#define _GEN_PV_LOCK_SLOWPATH
+
+#undef  pv_enabled
+#define pv_enabled()    true
+
+#undef pv_init_node
+#undef pv_wait_node
+#undef pv_kick_node
+#undef pv_wait_head
+
+#undef  queued_spin_lock_slowpath
+#define queued_spin_lock_slowpath       __pv_queued_spin_lock_slowpath
+
+#include "qspinlock_paravirt.h"
+#include "qspinlock.c"
+
+#endif