mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask

THP allocation mode is quite complex and it depends on the defrag mode.
This complexity is hidden in alloc_hugepage_direct_gfpmask from a large
part currently. The NUMA special casing (namely __GFP_THISNODE) is
however independent and placed in alloc_pages_vma currently. This both
adds an unnecessary branch to all vma based page allocation requests and
it makes the code more complex unnecessarily as well. Not to mention
that e.g. shmem THP used to do the node reclaiming unconditionally
regardless of the defrag mode until recently. This was not only
unexpected behavior but it was also hardly a good default behavior and I
strongly suspect it was just a side effect of the code sharing more than
a deliberate decision which suggests that such a layering is wrong.

Get rid of the thp special casing from alloc_pages_vma and move the
logic to alloc_hugepage_direct_gfpmask. __GFP_THISNODE is applied to the
resulting gfp mask only when the direct reclaim is not requested and
when there is no explicit numa binding to preserve the current logic.

Please note that there's also a slight difference wrt MPOL_BIND now. The
previous code would avoid using __GFP_THISNODE if the local node was
outside of policy_nodemask(). After this patch __GFP_THISNODE is avoided
for all MPOL_BIND policies. So there's a difference that if local node
is actually allowed by the bind policy's nodemask, previously
__GFP_THISNODE would be added, but now it won't be. From the behavior
POV this is still correct because the policy nodemask is used.

Link: http://lkml.kernel.org/r/20180925120326.24392-3-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Stefan Priebe - Profihost AG <s.priebe@profihost.ag>
Cc: Zi Yan <zi.yan@cs.rutgers.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 29 insertions, 9 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 4e4ef8fa479d..55478ab3c83b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -629,21 +629,40 @@ release:
  *	    available
  * never: never stall for any thp allocation
  */
-static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma)
+static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr)
 {
 	const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE);
+	gfp_t this_node = 0;
+
+#ifdef CONFIG_NUMA
+	struct mempolicy *pol;
+	/*
+	 * __GFP_THISNODE is used only when __GFP_DIRECT_RECLAIM is not
+	 * specified, to express a general desire to stay on the current
+	 * node for optimistic allocation attempts. If the defrag mode
+	 * and/or madvise hint requires the direct reclaim then we prefer
+	 * to fallback to other node rather than node reclaim because that
+	 * can lead to excessive reclaim even though there is free memory
+	 * on other nodes. We expect that NUMA preferences are specified
+	 * by memory policies.
+	 */
+	pol = get_vma_policy(vma, addr);
+	if (pol->mode != MPOL_BIND)
+		this_node = __GFP_THISNODE;
+	mpol_cond_put(pol);
+#endif
 
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
 		return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
-		return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;
+		return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM | this_node;
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags))
 		return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
-							     __GFP_KSWAPD_RECLAIM);
+							     __GFP_KSWAPD_RECLAIM | this_node);
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
 		return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
-							     0);
-	return GFP_TRANSHUGE_LIGHT;
+							     this_node);
+	return GFP_TRANSHUGE_LIGHT | this_node;
 }
 
 /* Caller must hold page table lock. */
@@ -715,8 +734,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 			pte_free(vma->vm_mm, pgtable);
 		return ret;
 	}
-	gfp = alloc_hugepage_direct_gfpmask(vma);
-	page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER);
+	gfp = alloc_hugepage_direct_gfpmask(vma, haddr);
+	page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, vma, haddr, numa_node_id());
 	if (unlikely(!page)) {
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
@@ -1286,8 +1305,9 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
 alloc:
 	if (transparent_hugepage_enabled(vma) &&
 	    !transparent_hugepage_debug_cow()) {
-		huge_gfp = alloc_hugepage_direct_gfpmask(vma);
-		new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER);
+		huge_gfp = alloc_hugepage_direct_gfpmask(vma, haddr);
+		new_page = alloc_pages_vma(huge_gfp, HPAGE_PMD_ORDER, vma,
+				haddr, numa_node_id());
 	} else
 		new_page = NULL;