On Wed 23-07-14 15:50:09, David Rientjes wrote:
> The page allocator relies on __GFP_WAIT to determine if ALLOC_CPUSET
> should be set in allocflags. ALLOC_CPUSET controls if a page allocation
> should be restricted only to the set of allowed cpuset mems.
>
> Transparent hugepages clears __GFP_WAIT when defrag is disabled to prevent
> the fault path from using memory compaction or direct reclaim. Thus, it
> is unfairly able to allocate outside of its cpuset mems restriction as a
> side-effect.
>
> This patch ensures that ALLOC_CPUSET is only cleared when the gfp mask is
> truly GFP_ATOMIC by verifying it is also not a thp allocation.
>
> Reported-by: Alex Thorlton <athorlton@xxxxxxx>
> Cc: stable@xxxxxxxxxxxxxxx
> Signed-off-by: David Rientjes <rientjes@xxxxxxxxxx>
This is an abuse of __GFP_NO_KSWAPD but it also looks like a new gfp
flag would need to be added to do it in other way. No other users seem to
clear GFP_WAIT while using __GFP_NO_KSWAPD AFAICS so this should really
affect only THP allocations.
Reviewed-by: Michal Hocko <mhocko@xxxxxxx>
> ---
> mm/page_alloc.c | 16 ++++++++--------
> 1 file changed, 8 insertions(+), 8 deletions(-)
>
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -2447,7 +2447,7 @@ static inline int
> gfp_to_alloc_flags(gfp_t gfp_mask)
> {
> int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
> - const gfp_t wait = gfp_mask & __GFP_WAIT;
> + const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD));
>
> /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
> BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
> @@ -2456,20 +2456,20 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
> * The caller may dip into page reserves a bit more if the caller
> * cannot run direct reclaim, or if the caller has realtime scheduling
> * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will
> - * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
> + * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH).
> */
> alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH);
>
> - if (!wait) {
> + if (atomic) {
> /*
> - * Not worth trying to allocate harder for
> - * __GFP_NOMEMALLOC even if it can't schedule.
> + * Not worth trying to allocate harder for __GFP_NOMEMALLOC even
> + * if it can't schedule.
> */
> - if (!(gfp_mask & __GFP_NOMEMALLOC))
> + if (!(gfp_mask & __GFP_NOMEMALLOC))
> alloc_flags |= ALLOC_HARDER;
> /*
> - * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
> - * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
> + * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the
> + * comment for __cpuset_node_allowed_softwall().
> */
> alloc_flags &= ~ALLOC_CPUSET;
> } else if (unlikely(rt_task(current)) && !in_interrupt())
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@xxxxxxxxx. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>
--
Michal Hocko
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>