1 files changed, 124 insertions, 4 deletions

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 5f68d0a39..e0582106e 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -35,6 +35,7 @@
 #include <linux/spinlock.h>
 #include <linux/preempt.h>
 #include <linux/lockdep.h>
+#include <linux/compiler.h>
 #include <asm/processor.h>
 
 /*
@@ -233,9 +234,128 @@ static inline void raw_write_seqcount_end(seqcount_t *s)
 	s->sequence++;
 }
 
-/*
+/**
+ * raw_write_seqcount_barrier - do a seq write barrier
+ * @s: pointer to seqcount_t
+ *
+ * This can be used to provide an ordering guarantee instead of the
+ * usual consistency guarantee. It is one wmb cheaper, because we can
+ * collapse the two back-to-back wmb()s.
+ *
+ *      seqcount_t seq;
+ *      bool X = true, Y = false;
+ *
+ *      void read(void)
+ *      {
+ *              bool x, y;
+ *
+ *              do {
+ *                      int s = read_seqcount_begin(&seq);
+ *
+ *                      x = X; y = Y;
+ *
+ *              } while (read_seqcount_retry(&seq, s));
+ *
+ *              BUG_ON(!x && !y);
+ *      }
+ *
+ *      void write(void)
+ *      {
+ *              Y = true;
+ *
+ *              raw_write_seqcount_barrier(seq);
+ *
+ *              X = false;
+ *      }
+ */
+static inline void raw_write_seqcount_barrier(seqcount_t *s)
+{
+	s->sequence++;
+	smp_wmb();
+	s->sequence++;
+}
+
+static inline int raw_read_seqcount_latch(seqcount_t *s)
+{
+	return lockless_dereference(s->sequence);
+}
+
+/**
  * raw_write_seqcount_latch - redirect readers to even/odd copy
  * @s: pointer to seqcount_t
+ *
+ * The latch technique is a multiversion concurrency control method that allows
+ * queries during non-atomic modifications. If you can guarantee queries never
+ * interrupt the modification -- e.g. the concurrency is strictly between CPUs
+ * -- you most likely do not need this.
+ *
+ * Where the traditional RCU/lockless data structures rely on atomic
+ * modifications to ensure queries observe either the old or the new state the
+ * latch allows the same for non-atomic updates. The trade-off is doubling the
+ * cost of storage; we have to maintain two copies of the entire data
+ * structure.
+ *
+ * Very simply put: we first modify one copy and then the other. This ensures
+ * there is always one copy in a stable state, ready to give us an answer.
+ *
+ * The basic form is a data structure like:
+ *
+ * struct latch_struct {
+ *	seqcount_t		seq;
+ *	struct data_struct	data[2];
+ * };
+ *
+ * Where a modification, which is assumed to be externally serialized, does the
+ * following:
+ *
+ * void latch_modify(struct latch_struct *latch, ...)
+ * {
+ *	smp_wmb();	<- Ensure that the last data[1] update is visible
+ *	latch->seq++;
+ *	smp_wmb();	<- Ensure that the seqcount update is visible
+ *
+ *	modify(latch->data[0], ...);
+ *
+ *	smp_wmb();	<- Ensure that the data[0] update is visible
+ *	latch->seq++;
+ *	smp_wmb();	<- Ensure that the seqcount update is visible
+ *
+ *	modify(latch->data[1], ...);
+ * }
+ *
+ * The query will have a form like:
+ *
+ * struct entry *latch_query(struct latch_struct *latch, ...)
+ * {
+ *	struct entry *entry;
+ *	unsigned seq, idx;
+ *
+ *	do {
+ *		seq = lockless_dereference(latch->seq);
+ *
+ *		idx = seq & 0x01;
+ *		entry = data_query(latch->data[idx], ...);
+ *
+ *		smp_rmb();
+ *	} while (seq != latch->seq);
+ *
+ *	return entry;
+ * }
+ *
+ * So during the modification, queries are first redirected to data[1]. Then we
+ * modify data[0]. When that is complete, we redirect queries back to data[0]
+ * and we can modify data[1].
+ *
+ * NOTE: The non-requirement for atomic modifications does _NOT_ include
+ *       the publishing of new entries in the case where data is a dynamic
+ *       data structure.
+ *
+ *       An iteration might start in data[0] and get suspended long enough
+ *       to miss an entire modification sequence, once it resumes it might
+ *       observe the new entry.
+ *
+ * NOTE: When data is a dynamic data structure; one should use regular RCU
+ *       patterns to manage the lifetimes of the objects within.
  */
 static inline void raw_write_seqcount_latch(seqcount_t *s)
 {
@@ -266,13 +386,13 @@ static inline void write_seqcount_end(seqcount_t *s)
 }
 
 /**
- * write_seqcount_barrier - invalidate in-progress read-side seq operations
+ * write_seqcount_invalidate - invalidate in-progress read-side seq operations
  * @s: pointer to seqcount_t
  *
- * After write_seqcount_barrier, no read-side seq operations will complete
+ * After write_seqcount_invalidate, no read-side seq operations will complete
  * successfully and see data older than this.
  */
-static inline void write_seqcount_barrier(seqcount_t *s)
+static inline void write_seqcount_invalidate(seqcount_t *s)
 {
 	smp_wmb();
 	s->sequence+=2;