>
> No, I meant going back to idea of new gfp flag, but adjust the implementation in
> the allocator (different from what you posted in previous version) so that it
> only looks at the flag after it tries to allocate from pcplist and finds out
> it's empty. So, no inventing of new page allocator entry points or checks such
> as the one you wrote above, but adding the new gfp flag in a way that it doesn't
> affect existing fast paths.
>
OK. Now i see. Please have a look below at the patch, so we fully understand
each other. If that is something that is close to your view or not:
<snip>
t a/include/linux/gfp.h b/include/linux/gfp.h
index c603237e006c..7e613560a502 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -39,8 +39,9 @@ struct vm_area_struct;
#define ___GFP_HARDWALL 0x100000u
#define ___GFP_THISNODE 0x200000u
#define ___GFP_ACCOUNT 0x400000u
+#define ___GFP_NO_LOCKS 0x800000u
#ifdef CONFIG_LOCKDEP
-#define ___GFP_NOLOCKDEP 0x800000u
+#define ___GFP_NOLOCKDEP 0x1000000u
#else
#define ___GFP_NOLOCKDEP 0
#endif
@@ -215,16 +216,22 @@ struct vm_area_struct;
* %__GFP_COMP address compound page metadata.
*
* %__GFP_ZERO returns a zeroed page on success.
+ *
+ * %__GFP_NO_LOCKS order-0 allocation without sleepable-locks.
+ * It obtains a page from the per-cpu-list and considered as
+ * lock-less. No other actions are performed, thus it returns
+ * NULL if per-cpu-list is empty.
*/
#define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN)
#define __GFP_COMP ((__force gfp_t)___GFP_COMP)
#define __GFP_ZERO ((__force gfp_t)___GFP_ZERO)
+#define __GFP_NO_LOCKS ((__force gfp_t)___GFP_NO_LOCKS)
/* Disable lockdep for GFP context tracking */
#define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP)
/* Room for N __GFP_FOO bits */
-#define __GFP_BITS_SHIFT (23 + IS_ENABLED(CONFIG_LOCKDEP))
+#define __GFP_BITS_SHIFT (24 + IS_ENABLED(CONFIG_LOCKDEP))
#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
/**
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 67018d367b9f..d99af78237be 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -45,6 +45,7 @@
{(unsigned long)__GFP_RECLAIMABLE, "__GFP_RECLAIMABLE"}, \
{(unsigned long)__GFP_MOVABLE, "__GFP_MOVABLE"}, \
{(unsigned long)__GFP_ACCOUNT, "__GFP_ACCOUNT"}, \
+ {(unsigned long)__GFP_NO_LOCKS, "__GFP_NO_LOCKS"}, \
{(unsigned long)__GFP_WRITE, "__GFP_WRITE"}, \
{(unsigned long)__GFP_RECLAIM, "__GFP_RECLAIM"}, \
{(unsigned long)__GFP_DIRECT_RECLAIM, "__GFP_DIRECT_RECLAIM"},\
diff --git a/mm/internal.h b/mm/internal.h
index 6345b08ce86c..5724fba921f9 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -569,6 +569,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
#define ALLOC_NOFRAGMENT 0x0
#endif
#define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */
+#define ALLOC_NO_LOCKS 0x1000 /* Lock free allocation. */
enum ttu_flags;
struct tlbflush_unmap_batch;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index aff1f84bf268..19cd9794dd45 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2837,6 +2837,9 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
{
int i, alloced = 0;
+ if (alloc_flags & ALLOC_NO_LOCKS)
+ return alloced;
+
spin_lock(&zone->lock);
for (i = 0; i < count; ++i) {
struct page *page = __rmqueue(zone, order, migratetype,
@@ -3805,7 +3808,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
* grow this zone if it contains deferred pages.
*/
if (static_branch_unlikely(&deferred_pages)) {
- if (_deferred_grow_zone(zone, order))
+ if (!(alloc_flags & ALLOC_NO_LOCKS) &&
+ _deferred_grow_zone(zone, order))
goto try_this_zone;
}
#endif
@@ -3850,7 +3854,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
reserve_highatomic_pageblock(page, zone, order);
return page;
- } else {
+ } else if (!(alloc_flags & ALLOC_NO_LOCKS)) {
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/* Try again if zone has deferred pages */
if (static_branch_unlikely(&deferred_pages)) {
@@ -4846,6 +4850,9 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
ac->highest_zoneidx, ac->nodemask);
+ if (gfp_mask & __GFP_NO_LOCKS)
+ *alloc_flags |= ALLOC_NO_LOCKS;
+
return true;
}
@@ -4886,6 +4893,10 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid,
if (likely(page))
goto out;
+ /* Bypass slow path if __GFP_NO_LOCKS. */
+ if ((gfp_mask & __GFP_NO_LOCKS))
+ goto out;
+
/*
* Apply scoped allocation constraints. This is mainly about GFP_NOFS
* resp. GFP_NOIO which has to be inherited for all allocation requests
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index a50dae2c4ae9..fee3221bcf6a 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -656,6 +656,7 @@ static const struct {
{ "__GFP_RECLAIMABLE", "RC" },
{ "__GFP_MOVABLE", "M" },
{ "__GFP_ACCOUNT", "AC" },
+ { "__GFP_NO_LOCKS", "NL" },
{ "__GFP_WRITE", "WR" },
{ "__GFP_RECLAIM", "R" },
{ "__GFP_DIRECT_RECLAIM", "DR" },
<snip>
If not, could you please provide some snips or any pseudo code?
Thanks Vlastimil!
--
Vlad Rezki
