kernel: optimise seqlock

Add branch annotations for seqlock read fastpath, and introduce
__read_seqcount_begin and __read_seqcount_end functions, that can avoid the
smp_rmb() if used carefully. These will be used by store-free path walking
algorithm performance is critical and seqlocks are in use.

Signed-off-by: Nick Piggin <npiggin@kernel.dk>

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 632205c..e98cd2e 100644 (file)
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -107,7 +107,7 @@ static __always_inline int read_seqretry(const seqlock_t *sl, unsigned start)
 {
        smp_rmb();
 
-       return (sl->sequence != start);
+       return unlikely(sl->sequence != start);
 }
 
 
@@ -125,14 +125,25 @@ typedef struct seqcount {
 #define SEQCNT_ZERO { 0 }
 #define seqcount_init(x)       do { *(x) = (seqcount_t) SEQCNT_ZERO; } while (0)
 
-/* Start of read using pointer to a sequence counter only.  */
-static inline unsigned read_seqcount_begin(const seqcount_t *s)
+/**
+ * __read_seqcount_begin - begin a seq-read critical section (without barrier)
+ * @s: pointer to seqcount_t
+ * Returns: count to be passed to read_seqcount_retry
+ *
+ * __read_seqcount_begin is like read_seqcount_begin, but has no smp_rmb()
+ * barrier. Callers should ensure that smp_rmb() or equivalent ordering is
+ * provided before actually loading any of the variables that are to be
+ * protected in this critical section.
+ *
+ * Use carefully, only in critical code, and comment how the barrier is
+ * provided.
+ */
+static inline unsigned __read_seqcount_begin(const seqcount_t *s)
 {
        unsigned ret;
 
 repeat:
        ret = s->sequence;
-       smp_rmb();
        if (unlikely(ret & 1)) {
                cpu_relax();
                goto repeat;
@@ -140,14 +151,56 @@ repeat:
        return ret;
 }
 
-/*
- * Test if reader processed invalid data because sequence number has changed.
+/**
+ * read_seqcount_begin - begin a seq-read critical section
+ * @s: pointer to seqcount_t
+ * Returns: count to be passed to read_seqcount_retry
+ *
+ * read_seqcount_begin opens a read critical section of the given seqcount.
+ * Validity of the critical section is tested by checking read_seqcount_retry
+ * function.
+ */
+static inline unsigned read_seqcount_begin(const seqcount_t *s)
+{
+       unsigned ret = __read_seqcount_begin(s);
+       smp_rmb();
+       return ret;
+}
+
+/**
+ * __read_seqcount_retry - end a seq-read critical section (without barrier)
+ * @s: pointer to seqcount_t
+ * @start: count, from read_seqcount_begin
+ * Returns: 1 if retry is required, else 0
+ *
+ * __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb()
+ * barrier. Callers should ensure that smp_rmb() or equivalent ordering is
+ * provided before actually loading any of the variables that are to be
+ * protected in this critical section.
+ *
+ * Use carefully, only in critical code, and comment how the barrier is
+ * provided.
+ */
+static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start)
+{
+       return unlikely(s->sequence != start);
+}
+
+/**
+ * read_seqcount_retry - end a seq-read critical section
+ * @s: pointer to seqcount_t
+ * @start: count, from read_seqcount_begin
+ * Returns: 1 if retry is required, else 0
+ *
+ * read_seqcount_retry closes a read critical section of the given seqcount.
+ * If the critical section was invalid, it must be ignored (and typically
+ * retried).
  */
 static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
 {
        smp_rmb();
 
-       return s->sequence != start;
+       return __read_seqcount_retry(s, start);
 }
 
 
@@ -167,6 +220,19 @@ static inline void write_seqcount_end(seqcount_t *s)
        s->sequence++;
 }
 
+/**
+ * write_seqcount_barrier - invalidate in-progress read-side seq operations
+ * @s: pointer to seqcount_t
+ *
+ * After write_seqcount_barrier, no read-side seq operations will complete
+ * successfully and see data older than this.
+ */
+static inline void write_seqcount_barrier(seqcount_t *s)
+{
+       smp_wmb();
+       s->sequence+=2;
+}
+
 /*
  * Possible sw/hw IRQ protected versions of the interfaces.
  */