Revert "Revert "mm, thp: consolidate THP gfp handling into alloc_huge…

…page_direct_gfpmask""

Patch series "reapply: relax __GFP_THISNODE for MADV_HUGEPAGE mappings".

The fixes for what was originally reported as "pathological THP
behavior" we rightfully reverted to be sure not to introduced
regressions at end of a merge window after a severe regression report
from the kernel bot.  We can safely re-apply them now that we had time
to analyze the problem.

The mm process worked fine, because the good fixes were eventually
committed upstream without excessive delay.

The regression reported by the kernel bot however forced us to revert
the good fixes to be sure not to introduce regressions and to give us
the time to analyze the issue further.  The silver lining is that this
extra time allowed to think more at this issue and also plan for a
future direction to improve things further in terms of THP NUMA
locality.

This patch (of 2):

This reverts commit 356ff8a ("Revert "mm, thp: consolidate THP
gfp handling into alloc_hugepage_direct_gfpmask").  So it reapplies
89c83fb ("mm, thp: consolidate THP gfp handling into
alloc_hugepage_direct_gfpmask").

Consolidation of the THP allocation flags at the same place was meant to
be a clean up to easier handle otherwise scattered code which is
imposing a maintenance burden.  There were no real problems observed
with the gfp mask consolidation but the reversion was rushed through
without a larger consensus regardless.

This patch brings the consolidation back because this should make the
long term maintainability easier as well as it should allow future
changes to be less error prone.

[[email protected]: changelog additions]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Andrea Arcangeli <[email protected]>
Acked-by: Michal Hocko <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: Zi Yan <[email protected]>
Cc: Stefan Priebe - Profihost AG <[email protected]>
Cc: "Kirill A. Shutemov" <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

include/linux/gfp.h

@@ -510,22 +510,18 @@ alloc_pages(gfp_t gfp_mask, unsigned int order)
 }
 extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
 			struct vm_area_struct *vma, unsigned long addr,
-			int node, bool hugepage);
-#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
-	alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true)
+			int node);
 #else
 #define alloc_pages(gfp_mask, order) \
 		alloc_pages_node(numa_node_id(), gfp_mask, order)
-#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\
-	alloc_pages(gfp_mask, order)
-#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
+#define alloc_pages_vma(gfp_mask, order, vma, addr, node)\
 	alloc_pages(gfp_mask, order)
 #endif
 #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
 #define alloc_page_vma(gfp_mask, vma, addr)			\
-	alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false)
+	alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id())
 #define alloc_page_vma_node(gfp_mask, vma, addr, node)		\
-	alloc_pages_vma(gfp_mask, 0, vma, addr, node, false)
+	alloc_pages_vma(gfp_mask, 0, vma, addr, node)
 
 extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
 extern unsigned long get_zeroed_page(gfp_t gfp_mask);

mm/huge_memory.c

@@ -644,30 +644,30 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
  *	    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);
+	const gfp_t gfp_mask = GFP_TRANSHUGE_LIGHT | __GFP_THISNODE;
 
 	/* Always do synchronous compaction */
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
-		return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);
+		return GFP_TRANSHUGE | __GFP_THISNODE |
+		       (vma_madvised ? 0 : __GFP_NORETRY);
 
 	/* Kick kcompactd and fail quickly */
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
-		return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;
+		return gfp_mask | __GFP_KSWAPD_RECLAIM;
 
 	/* Synchronous compaction if madvised, otherwise kick kcompactd */
 	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);
+		return gfp_mask | (vma_madvised ? __GFP_DIRECT_RECLAIM :
+						  __GFP_KSWAPD_RECLAIM);
 
 	/* Only do synchronous compaction if madvised */
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
-		return GFP_TRANSHUGE_LIGHT |
-		       (vma_madvised ? __GFP_DIRECT_RECLAIM : 0);
+		return gfp_mask | (vma_madvised ? __GFP_DIRECT_RECLAIM : 0);
 
-	return GFP_TRANSHUGE_LIGHT;
+	return gfp_mask;
 }
 
 /* Caller must hold page table lock. */
@@ -739,8 +739,8 @@ 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;
@@ -1347,8 +1347,9 @@ 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;
 

mm/mempolicy.c

@@ -1180,8 +1180,8 @@ static struct page *new_page(struct page *page, unsigned long start)
 	} else if (PageTransHuge(page)) {
 		struct page *thp;
 
-		thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address,
-					 HPAGE_PMD_ORDER);
+		thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma,
+				address, numa_node_id());
 		if (!thp)
 			return NULL;
 		prep_transhuge_page(thp);
@@ -2083,7 +2083,6 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
  * 	@vma:  Pointer to VMA or NULL if not available.
  *	@addr: Virtual Address of the allocation. Must be inside the VMA.
  *	@node: Which node to prefer for allocation (modulo policy).
- *	@hugepage: for hugepages try only the preferred node if possible
  *
  * 	This function allocates a page from the kernel page pool and applies
  *	a NUMA policy associated with the VMA or the current process.
@@ -2094,7 +2093,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
  */
 struct page *
 alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
-		unsigned long addr, int node, bool hugepage)
+		unsigned long addr, int node)
 {
 	struct mempolicy *pol;
 	struct page *page;
@@ -2112,31 +2111,6 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 		goto out;
 	}
 
-	if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) {
-		int hpage_node = node;
-
-		/*
-		 * For hugepage allocation and non-interleave policy which
-		 * allows the current node (or other explicitly preferred
-		 * node) we only try to allocate from the current/preferred
-		 * node and don't fall back to other nodes, as the cost of
-		 * remote accesses would likely offset THP benefits.
-		 *
-		 * If the policy is interleave, or does not allow the current
-		 * node in its nodemask, we allocate the standard way.
-		 */
-		if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL))
-			hpage_node = pol->v.preferred_node;
-
-		nmask = policy_nodemask(gfp, pol);
-		if (!nmask || node_isset(hpage_node, *nmask)) {
-			mpol_cond_put(pol);
-			page = __alloc_pages_node(hpage_node,
-						gfp | __GFP_THISNODE, order);
-			goto out;
-		}
-	}
-
 	nmask = policy_nodemask(gfp, pol);
 	preferred_nid = policy_node(gfp, pol, node);
 	page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask);

mm/shmem.c

@@ -1466,7 +1466,7 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp,
 
 	shmem_pseudo_vma_init(&pvma, info, hindex);
 	page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN,
-			HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true);
+			HPAGE_PMD_ORDER, &pvma, 0, numa_node_id());
 	shmem_pseudo_vma_destroy(&pvma);
 	if (page)
 		prep_transhuge_page(page);