Re: [PATCH 8/9] qspinlock: Generic paravirt support

[Peter Zijlstra <peterz@infradead.org>]

On Thu, Mar 19, 2015 at 11:12:42AM +0100, Peter Zijlstra wrote:
> So I was now thinking of hashing the lock pointer; let me go and quickly
> put something together.

A little something like so; ideally we'd allocate the hashtable since
NR_CPUS is kinda bloated, but it shows the idea I think.

And while this has loops in (the rehashing thing) their fwd progress
does not depend on other CPUs.

And I suspect that for the typical lock contention scenarios its
unlikely we ever really get into long rehashing chains.

---
 include/linux/lfsr.h                |   49 ++++++++++++
 kernel/locking/qspinlock_paravirt.h |  143 ++++++++++++++++++++++++++++++++----
 2 files changed, 178 insertions(+), 14 deletions(-)

--- /dev/null
+++ b/include/linux/lfsr.h
@@ -0,0 +1,49 @@
+#ifndef _LINUX_LFSR_H
+#define _LINUX_LFSR_H
+
+/*
+ * Simple Binary Galois Linear Feedback Shift Register
+ *
+ * http://en.wikipedia.org/wiki/Linear_feedback_shift_register
+ *
+ */
+
+extern void __lfsr_needs_more_taps(void);
+
+static __always_inline u32 lfsr_taps(int bits)
+{
+	if (bits ==  1) return 0x0001;
+	if (bits ==  2) return 0x0001;
+	if (bits ==  3) return 0x0003;
+	if (bits ==  4) return 0x0009;
+	if (bits ==  5) return 0x0012;
+	if (bits ==  6) return 0x0021;
+	if (bits ==  7) return 0x0041;
+	if (bits ==  8) return 0x008E;
+	if (bits ==  9) return 0x0108;
+	if (bits == 10) return 0x0204;
+	if (bits == 11) return 0x0402;
+	if (bits == 12) return 0x0829;
+	if (bits == 13) return 0x100D;
+	if (bits == 14) return 0x2015;
+
+	/*
+	 * For more taps see:
+	 *   http://users.ece.cmu.edu/~koopman/lfsr/index.html
+	 */
+	__lfsr_needs_more_taps();
+
+	return 0;
+}
+
+static inline u32 lfsr(u32 val, int bits)
+{
+	u32 bit = val & 1;
+
+	val >>= 1;
+	if (bit)
+		val ^= lfsr_taps(bits);
+	return val;
+}
+
+#endif /* _LINUX_LFSR_H */
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -2,6 +2,9 @@
 #error "do not include this file"
 #endif
 
+#include <linux/hash.h>
+#include <linux/lfsr.h>
+
 /*
  * Implement paravirt qspinlocks; the general idea is to halt the vcpus instead
  * of spinning them.
@@ -107,7 +110,120 @@ static void pv_kick_node(struct mcs_spin
 		pv_kick(pn->cpu);
 }
 
-static DEFINE_PER_CPU(struct qspinlock *, __pv_lock_wait);
+/*
+ * Hash table using open addressing with an LFSR probe sequence.
+ *
+ * Since we should not be holding locks from NMI context (very rare indeed) the
+ * max load factor is 0.75, which is around the point where open addressing
+ * breaks down.
+ *
+ * Instead of probing just the immediate bucket we probe all buckets in the
+ * same cacheline.
+ *
+ * http://en.wikipedia.org/wiki/Hash_table#Open_addressing
+ *
+ */
+
+#define HB_RESERVED	((struct qspinlock *)1)
+
+struct pv_hash_bucket {
+	struct qspinlock *lock;
+	int cpu;
+};
+
+/*
+ * XXX dynamic allocate using nr_cpu_ids instead...
+ */
+#define PV_LOCK_HASH_BITS	(2 + NR_CPUS_BITS)
+
+#if PV_LOCK_HASH_BITS < 6
+#undef PV_LOCK_HASH_BITS
+#define PB_LOCK_HASH_BITS	6
+#endif
+
+#define PV_LOCK_HASH_SIZE	(1 << PV_LOCK_HASH_BITS)
+
+static struct pv_hash_bucket __pv_lock_hash[PV_LOCK_HASH_SIZE] ____cacheline_aligned;
+
+#define PV_HB_PER_LINE		(SMP_CACHE_BYTES / sizeof(struct pv_hash_bucket))
+
+static inline u32 hash_align(u32 hash)
+{
+	return hash & ~(PV_HB_PER_LINE - 1);
+}
+
+static struct qspinlock **pv_hash(struct qspinlock *lock)
+{
+	u32 hash = hash_ptr(lock, PV_LOCK_HASH_BITS);
+	struct pv_hash_bucket *hb, *end;
+
+	if (!hash)
+		hash = 1;
+
+	hb = &__pv_lock_hash[hash_align(hash)];
+	for (;;) {
+		for (end = hb + PV_HB_PER_LINE; hb < end; hb++) {
+			if (cmpxchg(&hb->lock, NULL, HB_RESERVED)) {
+				WRITE_ONCE(hb->cpu, smp_processor_id());
+				/*
+				 * Since we must read lock first and cpu
+				 * second, we must write cpu first and lock
+				 * second, therefore use HB_RESERVE to mark an
+				 * entry in use before writing the values.
+				 *
+				 * This can cause hb_hash_find() to not find a
+				 * cpu even though _Q_SLOW_VAL, this is not a
+				 * problem since we re-check l->locked before
+				 * going to sleep and the unlock will have
+				 * cleared l->locked already.
+				 */
+				smp_wmb(); /* matches rmb from pv_hash_find */
+				WRITE_ONCE(hb->lock, lock);
+				goto done;
+			}
+		}
+
+		hash = lfsr(hash, PV_LOCK_HASH_BITS);
+		hb = &__pv_lock_hash[hash_align(hash)];
+	}
+
+done:
+	return &hb->lock;
+}
+
+static int pv_hash_find(struct qspinlock *lock)
+{
+	u64 hash = hash_ptr(lock, PV_LOCK_HASH_BITS);
+	struct pv_hash_bucket *hb, *end;
+	int cpu = -1;
+
+	if (!hash)
+		hash = 1;
+
+	hb = &__pv_lock_hash[hash_align(hash)];
+	for (;;) {
+		for (end = hb + PV_HB_PER_LINE; hb < end; hb++) {
+			struct qspinlock *l = READ_ONCE(hb->lock);
+
+			/*
+			 * If we hit an unused bucket, there is no match.
+			 */
+			if (!l)
+				goto done;
+
+			if (l == lock) {
+				smp_rmb(); /* matches wmb from pv_hash() */
+				cpu = READ_ONCE(hb->cpu);
+				goto done;
+			}
+		}
+
+		hash = lfsr(hash, PV_LOCK_HASH_BITS);
+		hb = &__pv_lock_hash[hash_align(hash)];
+	}
+done:
+	return cpu;
+}
 
 /*
  * Wait for l->locked to become clear; halt the vcpu after a short spin.
@@ -116,6 +232,7 @@ static DEFINE_PER_CPU(struct qspinlock *
 static void pv_wait_head(struct qspinlock *lock)
 {
 	struct __qspinlock *l = (void *)lock;
+	struct qspinlock **lp = NULL;
 	int loop;
 
 	for (;;) {
@@ -126,13 +243,13 @@ static void pv_wait_head(struct qspinloc
 			cpu_relax();
 		}
 
-		this_cpu_write(__pv_lock_wait, lock);
+		lp = pv_hash(lock);
 		/*
-		 * __pv_lock_wait must be set before setting _Q_SLOW_VAL
+		 * lp  must be set before setting _Q_SLOW_VAL
 		 *
-		 * [S] __pv_lock_wait = lock    [RmW] l = l->locked = 0
+		 * [S] lp = lock                [RmW] l = l->locked = 0
 		 *     MB                             MB
-		 * [S] l->locked = _Q_SLOW_VAL  [L]   __pv_lock_wait
+		 * [S] l->locked = _Q_SLOW_VAL  [L]   lp
 		 *
 		 * Matches the xchg() in pv_queue_spin_unlock().
 		 */
@@ -142,7 +259,8 @@ static void pv_wait_head(struct qspinloc
 		pv_wait(&l->locked, _Q_SLOW_VAL);
 	}
 done:
-	this_cpu_write(__pv_lock_wait, NULL);
+	if (lp)
+		WRITE_ONCE(*lp, NULL);
 
 	/*
 	 * Lock is unlocked now; the caller will acquire it without waiting.
@@ -165,13 +283,10 @@ void __pv_queue_spin_unlock(struct qspin
 
 	/*
 	 * At this point the memory pointed at by lock can be freed/reused,
-	 * however we can still use the pointer value to search in our cpu
-	 * array.
-	 *
-	 * XXX: get rid of this loop
+	 * however we can still use the pointer value to search in our hash
+	 * table.
 	 */
-	for_each_possible_cpu(cpu) {
-		if (per_cpu(__pv_lock_wait, cpu) == lock)
-			pv_kick(cpu);
-	}
+	cpu = pv_hash_find(lock);
+	if (cpu >= 0)
+		pv_kick(cpu);
 }