|author||Nick Piggin <email@example.com>||2008-05-14 06:35:11 +0200|
|committer||Linus Torvalds <firstname.lastname@example.org>||2008-05-14 10:05:18 -0700|
read_barrier_depends arch fixlets
read_barrie_depends has always been a noop (not a compiler barrier) on all architectures except SMP alpha. This brings UP alpha and frv into line with all other architectures, and fixes incorrect documentation. Signed-off-by: Nick Piggin <email@example.com> Acked-by: Paul E. McKenney <firstname.lastname@example.org> Signed-off-by: Linus Torvalds <email@example.com>
Diffstat (limited to 'Documentation/memory-barriers.txt')
1 files changed, 11 insertions, 1 deletions
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index e5a819a4f0c..f5b7127f54a 100644
@@ -994,7 +994,17 @@ The Linux kernel has eight basic CPU memory barriers:
DATA DEPENDENCY read_barrier_depends() smp_read_barrier_depends()
-All CPU memory barriers unconditionally imply compiler barriers.
+All memory barriers except the data dependency barriers imply a compiler
+barrier. Data dependencies do not impose any additional compiler ordering.
+Aside: In the case of data dependencies, the compiler would be expected to
+issue the loads in the correct order (eg. `a[b]` would have to load the value
+of b before loading a[b]), however there is no guarantee in the C specification
+that the compiler may not speculate the value of b (eg. is equal to 1) and load
+a before b (eg. tmp = a; if (b != 1) tmp = a[b]; ). There is also the
+problem of a compiler reloading b after having loaded a[b], thus having a newer
+copy of b than a[b]. A consensus has not yet been reached about these problems,
+however the ACCESS_ONCE macro is a good place to start looking.
SMP memory barriers are reduced to compiler barriers on uniprocessor compiled
systems because it is assumed that a CPU will appear to be self-consistent,