rcu: add rcu library

This includes a (mangled) copy of the liburcu code.  The main changes
are: 1) removing dependencies on many other header files in liburcu; 2)
removing for simplicity the tentative busy waiting in synchronize_rcu,
which has limited performance effects; 3) replacing futexes in
synchronize_rcu with QemuEvents for Win32 portability.  The API is
the same as liburcu, so it should be possible in the future to require
liburcu on POSIX systems for example and use our copy only on Windows.

Among the various versions available I chose urcu-mb, which is the
least invasive implementation even though it does not have the
fastest rcu_read_{lock,unlock} implementation.  The urcu flavor can
be changed later, after benchmarking.

Reviewed-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 61 insertions, 0 deletions

diff --git a/include/qemu/atomic.h b/include/qemu/atomic.h
index 93c2ae2..98e05ca 100644
--- a/include/qemu/atomic.h
+++ b/include/qemu/atomic.h
@@ -129,6 +129,67 @@
 #define atomic_set(ptr, i)     ((*(__typeof__(*ptr) volatile*) (ptr)) = (i))
 #endif
 
+/**
+ * atomic_rcu_read - reads a RCU-protected pointer to a local variable
+ * into a RCU read-side critical section. The pointer can later be safely
+ * dereferenced within the critical section.
+ *
+ * This ensures that the pointer copy is invariant thorough the whole critical
+ * section.
+ *
+ * Inserts memory barriers on architectures that require them (currently only
+ * Alpha) and documents which pointers are protected by RCU.
+ *
+ * Unless the __ATOMIC_CONSUME memory order is available, atomic_rcu_read also
+ * includes a compiler barrier to ensure that value-speculative optimizations
+ * (e.g. VSS: Value Speculation Scheduling) does not perform the data read
+ * before the pointer read by speculating the value of the pointer.  On new
+ * enough compilers, atomic_load takes care of such concern about
+ * dependency-breaking optimizations.
+ *
+ * Should match atomic_rcu_set(), atomic_xchg(), atomic_cmpxchg().
+ */
+#ifndef atomic_rcu_read
+#ifdef __ATOMIC_CONSUME
+#define atomic_rcu_read(ptr)    ({                \
+    typeof(*ptr) _val;                            \
+     __atomic_load(ptr, &_val, __ATOMIC_CONSUME); \
+    _val;                                         \
+})
+#else
+#define atomic_rcu_read(ptr)    ({                \
+    typeof(*ptr) _val = atomic_read(ptr);         \
+    smp_read_barrier_depends();                   \
+    _val;                                         \
+})
+#endif
+#endif
+
+/**
+ * atomic_rcu_set - assigns (publicizes) a pointer to a new data structure
+ * meant to be read by RCU read-side critical sections.
+ *
+ * Documents which pointers will be dereferenced by RCU read-side critical
+ * sections and adds the required memory barriers on architectures requiring
+ * them. It also makes sure the compiler does not reorder code initializing the
+ * data structure before its publication.
+ *
+ * Should match atomic_rcu_read().
+ */
+#ifndef atomic_rcu_set
+#ifdef __ATOMIC_RELEASE
+#define atomic_rcu_set(ptr, i)  do {              \
+    typeof(*ptr) _val = (i);                      \
+    __atomic_store(ptr, &_val, __ATOMIC_RELEASE); \
+} while(0)
+#else
+#define atomic_rcu_set(ptr, i)  do {              \
+    smp_wmb();                                    \
+    atomic_set(ptr, i);                           \
+} while (0)
+#endif
+#endif
+
 /* These have the same semantics as Java volatile variables.
  * See http://gee.cs.oswego.edu/dl/jmm/cookbook.html:
  * "1. Issue a StoreStore barrier (wmb) before each volatile store."