summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2011-05-20 00:50:07 +0400
committerLinus Torvalds <torvalds@linux-foundation.org>2011-05-20 00:50:07 +0400
commit75d65a425c0163d3ec476ddc12b51087217a070c (patch)
tree73fa02941dba62ff65fadc42eb03484428707cc5
parent61c4f2c81c61f73549928dfd9f3e8f26aa36a8cf (diff)
downloadlinux-75d65a425c0163d3ec476ddc12b51087217a070c.tar.xz
hlist: remove software prefetching in hlist iterators
They not only increase the code footprint, they actually make things slower rather than faster. On internationally acclaimed benchmarks ("make -j16" on an already fully built kernel source tree) the hlist prefetching slows down the build by up to 1%. (Almost all of it comes from hlist_for_each_entry_rcu() as used by avc_has_perm_noaudit(), which is very hot due to all the pathname lookups to see if there is anything to do). The cause seems to be two-fold: - on at least some Intel cores, prefetch(NULL) ends up with some microarchitectural stall due to the TLB miss that it incurs. The hlist case triggers this very commonly, since the NULL pointer is the last entry in the list. - the prefetch appears to cause more D$ activity, probably because it prefetches hash list entries that are never actually used (because we ended the search early due to a hit). Regardless, the numbers clearly say that the implicit prefetching is simply a bad idea. If some _particular_ user of the hlist iterators wants to prefetch the next list entry, they can do so themselves explicitly, rather than depend on all list iterators doing so implicitly. Acked-by: Ingo Molnar <mingo@elte.hu> Acked-by: David S. Miller <davem@davemloft.net> Cc: linux-arch@vger.kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--include/linux/list.h9
-rw-r--r--include/linux/rculist.h10
2 files changed, 9 insertions, 10 deletions
diff --git a/include/linux/list.h b/include/linux/list.h
index 3a54266a1e85..9ac11148e037 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -664,8 +664,7 @@ static inline void hlist_move_list(struct hlist_head *old,
#define hlist_entry(ptr, type, member) container_of(ptr,type,member)
#define hlist_for_each(pos, head) \
- for (pos = (head)->first; pos && ({ prefetch(pos->next); 1; }); \
- pos = pos->next)
+ for (pos = (head)->first; pos ; pos = pos->next)
#define hlist_for_each_safe(pos, n, head) \
for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \
@@ -680,7 +679,7 @@ static inline void hlist_move_list(struct hlist_head *old,
*/
#define hlist_for_each_entry(tpos, pos, head, member) \
for (pos = (head)->first; \
- pos && ({ prefetch(pos->next); 1;}) && \
+ pos && \
({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
pos = pos->next)
@@ -692,7 +691,7 @@ static inline void hlist_move_list(struct hlist_head *old,
*/
#define hlist_for_each_entry_continue(tpos, pos, member) \
for (pos = (pos)->next; \
- pos && ({ prefetch(pos->next); 1;}) && \
+ pos && \
({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
pos = pos->next)
@@ -703,7 +702,7 @@ static inline void hlist_move_list(struct hlist_head *old,
* @member: the name of the hlist_node within the struct.
*/
#define hlist_for_each_entry_from(tpos, pos, member) \
- for (; pos && ({ prefetch(pos->next); 1;}) && \
+ for (; pos && \
({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
pos = pos->next)
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 2dea94fc4402..900a97a44769 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -427,7 +427,7 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev,
#define __hlist_for_each_rcu(pos, head) \
for (pos = rcu_dereference(hlist_first_rcu(head)); \
- pos && ({ prefetch(pos->next); 1; }); \
+ pos; \
pos = rcu_dereference(hlist_next_rcu(pos)))
/**
@@ -443,7 +443,7 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev,
*/
#define hlist_for_each_entry_rcu(tpos, pos, head, member) \
for (pos = rcu_dereference_raw(hlist_first_rcu(head)); \
- pos && ({ prefetch(pos->next); 1; }) && \
+ pos && \
({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \
pos = rcu_dereference_raw(hlist_next_rcu(pos)))
@@ -460,7 +460,7 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev,
*/
#define hlist_for_each_entry_rcu_bh(tpos, pos, head, member) \
for (pos = rcu_dereference_bh((head)->first); \
- pos && ({ prefetch(pos->next); 1; }) && \
+ pos && \
({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \
pos = rcu_dereference_bh(pos->next))
@@ -472,7 +472,7 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev,
*/
#define hlist_for_each_entry_continue_rcu(tpos, pos, member) \
for (pos = rcu_dereference((pos)->next); \
- pos && ({ prefetch(pos->next); 1; }) && \
+ pos && \
({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \
pos = rcu_dereference(pos->next))
@@ -484,7 +484,7 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev,
*/
#define hlist_for_each_entry_continue_rcu_bh(tpos, pos, member) \
for (pos = rcu_dereference_bh((pos)->next); \
- pos && ({ prefetch(pos->next); 1; }) && \
+ pos && \
({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \
pos = rcu_dereference_bh(pos->next))