mm, mempolicy: don't check cpuset seqlock where it doesn't matter

Two wrappers of __alloc_pages_nodemask() are checking
task->mems_allowed_seq themselves to retry allocation that has raced
with a cpuset update.

This has been shown to be ineffective in preventing premature OOM's
which can happen in __alloc_pages_slowpath() long before it returns back
to the wrappers to detect the race at that level.

Previous patches have made __alloc_pages_slowpath() more robust, so we
can now simply remove the seqlock checking in the wrappers to prevent
further wrong impression that it can actually help.

Link: http://lkml.kernel.org/r/20170517081140.30654-7-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Dimitri Sivanich <sivanich@sgi.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 047181452040c6430ffb051da9094fdc24847230..7d8e56214ac099ad7c0a1eb8201d344a008428f1 100644 (file)
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1898,12 +1898,9 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
        struct mempolicy *pol;
        struct page *page;
        int preferred_nid;
-       unsigned int cpuset_mems_cookie;
        nodemask_t *nmask;
 
-retry_cpuset:
        pol = get_vma_policy(vma, addr);
-       cpuset_mems_cookie = read_mems_allowed_begin();
 
        if (pol->mode == MPOL_INTERLEAVE) {
                unsigned nid;
@@ -1945,8 +1942,6 @@ retry_cpuset:
        page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask);
        mpol_cond_put(pol);
 out:
-       if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
-               goto retry_cpuset;
        return page;
 }
 
@@ -1964,23 +1959,15 @@ out:
  *     Allocate a page from the kernel page pool.  When not in
  *     interrupt context and apply the current process NUMA policy.
  *     Returns NULL when no page can be allocated.
- *
- *     Don't call cpuset_update_task_memory_state() unless
- *     1) it's ok to take cpuset_sem (can WAIT), and
- *     2) allocating for current task (not interrupt).
  */
 struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 {
        struct mempolicy *pol = &default_policy;
        struct page *page;
-       unsigned int cpuset_mems_cookie;
 
        if (!in_interrupt() && !(gfp & __GFP_THISNODE))
                pol = get_task_policy(current);
 
-retry_cpuset:
-       cpuset_mems_cookie = read_mems_allowed_begin();
-
        /*
         * No reference counting needed for current->mempolicy
         * nor system default_policy
@@ -1992,9 +1979,6 @@ retry_cpuset:
                                policy_node(gfp, pol, numa_node_id()),
                                policy_nodemask(gfp, pol));
 
-       if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
-               goto retry_cpuset;
-
        return page;
 }
 EXPORT_SYMBOL(alloc_pages_current);