sched/numa: Set preferred NUMA node based on number of private faults

Ideally it would be possible to distinguish between NUMA hinting faults that
are private to a task and those that are shared. If treated identically
there is a risk that shared pages bounce between nodes depending on
the order they are referenced by tasks. Ultimately what is desirable is
that task private pages remain local to the task while shared pages are
interleaved between sharing tasks running on different nodes to give good
average performance. This is further complicated by THP as even
applications that partition their data may not be partitioning on a huge
page boundary.

To start with, this patch assumes that multi-threaded or multi-process
applications partition their data and that in general the private accesses
are more important for cpu->memory locality in the general case. Also,
no new infrastructure is required to treat private pages properly but
interleaving for shared pages requires additional infrastructure.

To detect private accesses the pid of the last accessing task is required
but the storage requirements are a high. This patch borrows heavily from
Ingo Molnar's patch "numa, mm, sched: Implement last-CPU+PID hash tracking"
to encode some bits from the last accessing task in the page flags as
well as the node information. Collisions will occur but it is better than
just depending on the node information. Node information is then used to
determine if a page needs to migrate. The PID information is used to detect
private/shared accesses. The preferred NUMA node is selected based on where
the maximum number of approximately private faults were measured. Shared
faults are not taken into consideration for a few reasons.

First, if there are many tasks sharing the page then they'll all move
towards the same node. The node will be compute overloaded and then
scheduled away later only to bounce back again. Alternatively the shared
tasks would just bounce around nodes because the fault information is
effectively noise. Either way accounting for shared faults the same as
private faults can result in lower performance overall.

The second reason is based on a hypothetical workload that has a small
number of very important, heavily accessed private pages but a large shared
array. The shared array would dominate the number of faults and be selected
as a preferred node even though it's the wrong decision.

The third reason is that multiple threads in a process will race each
other to fault the shared page making the fault information unreliable.

Signed-off-by: Mel Gorman <mgorman@suse.de>
[ Fix complication error when !NUMA_BALANCING. ]
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-30-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

8 files changed, 54 insertions, 44 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2a28c2c6c165..0baf0e4d5203 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1282,7 +1282,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *page;
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
 	int page_nid = -1, this_nid = numa_node_id();
-	int target_nid, last_nid = -1;
+	int target_nid, last_nidpid = -1;
 	bool page_locked;
 	bool migrated = false;
 
@@ -1293,7 +1293,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	page = pmd_page(pmd);
 	BUG_ON(is_huge_zero_page(page));
 	page_nid = page_to_nid(page);
-	last_nid = page_nid_last(page);
+	last_nidpid = page_nidpid_last(page);
 	count_vm_numa_event(NUMA_HINT_FAULTS);
 	if (page_nid == this_nid)
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
@@ -1362,7 +1362,7 @@ out:
 		page_unlock_anon_vma_read(anon_vma);
 
 	if (page_nid != -1)
-		task_numa_fault(last_nid, page_nid, HPAGE_PMD_NR, migrated);
+		task_numa_fault(last_nidpid, page_nid, HPAGE_PMD_NR, migrated);
 
 	return 0;
 }
@@ -1682,7 +1682,7 @@ static void __split_huge_page_refcount(struct page *page,
 		page_tail->mapping = page->mapping;
 
 		page_tail->index = page->index + i;
-		page_nid_xchg_last(page_tail, page_nid_last(page));
+		page_nidpid_xchg_last(page_tail, page_nidpid_last(page));
 
 		BUG_ON(!PageAnon(page_tail));
 		BUG_ON(!PageUptodate(page_tail));
diff --git a/mm/memory.c b/mm/memory.c
index 3e3b4b8b6c41..cc7f20691c82 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -69,8 +69,8 @@
 
 #include "internal.h"
 
-#ifdef LAST_NID_NOT_IN_PAGE_FLAGS
-#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_nid.
+#ifdef LAST_NIDPID_NOT_IN_PAGE_FLAGS
+#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_nidpid.
 #endif
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
@@ -3536,7 +3536,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *page = NULL;
 	spinlock_t *ptl;
 	int page_nid = -1;
-	int last_nid;
+	int last_nidpid;
 	int target_nid;
 	bool migrated = false;
 
@@ -3567,7 +3567,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 	BUG_ON(is_zero_pfn(page_to_pfn(page)));
 
-	last_nid = page_nid_last(page);
+	last_nidpid = page_nidpid_last(page);
 	page_nid = page_to_nid(page);
 	target_nid = numa_migrate_prep(page, vma, addr, page_nid);
 	pte_unmap_unlock(ptep, ptl);
@@ -3583,7 +3583,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 out:
 	if (page_nid != -1)
-		task_numa_fault(last_nid, page_nid, 1, migrated);
+		task_numa_fault(last_nidpid, page_nid, 1, migrated);
 	return 0;
 }
 
@@ -3598,7 +3598,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long offset;
 	spinlock_t *ptl;
 	bool numa = false;
-	int last_nid;
+	int last_nidpid;
 
 	spin_lock(&mm->page_table_lock);
 	pmd = *pmdp;
@@ -3643,7 +3643,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (unlikely(!page))
 			continue;
 
-		last_nid = page_nid_last(page);
+		last_nidpid = page_nidpid_last(page);
 		page_nid = page_to_nid(page);
 		target_nid = numa_migrate_prep(page, vma, addr, page_nid);
 		pte_unmap_unlock(pte, ptl);
@@ -3656,7 +3656,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		}
 
 		if (page_nid != -1)
-			task_numa_fault(last_nid, page_nid, 1, migrated);
+			task_numa_fault(last_nidpid, page_nid, 1, migrated);
 
 		pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	}
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 04729647f359..aff1f1ed3dc5 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2348,9 +2348,11 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 
 	/* Migrate the page towards the node whose CPU is referencing it */
 	if (pol->flags & MPOL_F_MORON) {
-		int last_nid;
+		int last_nidpid;
+		int this_nidpid;
 
 		polnid = numa_node_id();
+		this_nidpid = nid_pid_to_nidpid(polnid, current->pid);
 
 		/*
 		 * Multi-stage node selection is used in conjunction
@@ -2373,8 +2375,8 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 		 * it less likely we act on an unlikely task<->page
 		 * relation.
 		 */
-		last_nid = page_nid_xchg_last(page, polnid);
-		if (last_nid != polnid)
+		last_nidpid = page_nidpid_xchg_last(page, this_nidpid);
+		if (!nidpid_pid_unset(last_nidpid) && nidpid_to_nid(last_nidpid) != polnid)
 			goto out;
 	}
 
diff --git a/mm/migrate.c b/mm/migrate.c
index fcba2f46bb80..025d1e3d2ad2 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1498,7 +1498,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
 					  __GFP_NOWARN) &
 					 ~GFP_IOFS, 0);
 	if (newpage)
-		page_nid_xchg_last(newpage, page_nid_last(page));
+		page_nidpid_xchg_last(newpage, page_nidpid_last(page));
 
 	return newpage;
 }
@@ -1675,7 +1675,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	if (!new_page)
 		goto out_fail;
 
-	page_nid_xchg_last(new_page, page_nid_last(page));
+	page_nidpid_xchg_last(new_page, page_nidpid_last(page));
 
 	isolated = numamigrate_isolate_page(pgdat, page);
 	if (!isolated) {
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 633c08863fd8..467de579784b 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -71,26 +71,26 @@ void __init mminit_verify_pageflags_layout(void)
 	unsigned long or_mask, add_mask;
 
 	shift = 8 * sizeof(unsigned long);
-	width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH - LAST_NID_SHIFT;
+	width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH - LAST_NIDPID_SHIFT;
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_widths",
-		"Section %d Node %d Zone %d Lastnid %d Flags %d\n",
+		"Section %d Node %d Zone %d Lastnidpid %d Flags %d\n",
 		SECTIONS_WIDTH,
 		NODES_WIDTH,
 		ZONES_WIDTH,
-		LAST_NID_WIDTH,
+		LAST_NIDPID_WIDTH,
 		NR_PAGEFLAGS);
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_shifts",
-		"Section %d Node %d Zone %d Lastnid %d\n",
+		"Section %d Node %d Zone %d Lastnidpid %d\n",
 		SECTIONS_SHIFT,
 		NODES_SHIFT,
 		ZONES_SHIFT,
-		LAST_NID_SHIFT);
+		LAST_NIDPID_SHIFT);
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_pgshifts",
-		"Section %lu Node %lu Zone %lu Lastnid %lu\n",
+		"Section %lu Node %lu Zone %lu Lastnidpid %lu\n",
 		(unsigned long)SECTIONS_PGSHIFT,
 		(unsigned long)NODES_PGSHIFT,
 		(unsigned long)ZONES_PGSHIFT,
-		(unsigned long)LAST_NID_PGSHIFT);
+		(unsigned long)LAST_NIDPID_PGSHIFT);
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodezoneid",
 		"Node/Zone ID: %lu -> %lu\n",
 		(unsigned long)(ZONEID_PGOFF + ZONEID_SHIFT),
@@ -102,9 +102,9 @@ void __init mminit_verify_pageflags_layout(void)
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
 		"Node not in page flags");
 #endif
-#ifdef LAST_NID_NOT_IN_PAGE_FLAGS
+#ifdef LAST_NIDPID_NOT_IN_PAGE_FLAGS
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
-		"Last nid not in page flags");
+		"Last nidpid not in page flags");
 #endif
 
 	if (SECTIONS_WIDTH) {
diff --git a/mm/mmzone.c b/mm/mmzone.c
index 2ac0afbd68f3..25bb477deb26 100644
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -97,20 +97,20 @@ void lruvec_init(struct lruvec *lruvec)
 		INIT_LIST_HEAD(&lruvec->lists[lru]);
 }
 
-#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_NID_NOT_IN_PAGE_FLAGS)
-int page_nid_xchg_last(struct page *page, int nid)
+#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_NIDPID_NOT_IN_PAGE_FLAGS)
+int page_nidpid_xchg_last(struct page *page, int nidpid)
 {
 	unsigned long old_flags, flags;
-	int last_nid;
+	int last_nidpid;
 
 	do {
 		old_flags = flags = page->flags;
-		last_nid = page_nid_last(page);
+		last_nidpid = page_nidpid_last(page);
 
-		flags &= ~(LAST_NID_MASK << LAST_NID_PGSHIFT);
-		flags |= (nid & LAST_NID_MASK) << LAST_NID_PGSHIFT;
+		flags &= ~(LAST_NIDPID_MASK << LAST_NIDPID_PGSHIFT);
+		flags |= (nidpid & LAST_NIDPID_MASK) << LAST_NIDPID_PGSHIFT;
 	} while (unlikely(cmpxchg(&page->flags, old_flags, flags) != old_flags));
 
-	return last_nid;
+	return last_nidpid;
 }
 #endif
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 41e02923fcd9..f0b087d1069c 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -37,14 +37,15 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 
 static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
-		int dirty_accountable, int prot_numa, bool *ret_all_same_node)
+		int dirty_accountable, int prot_numa, bool *ret_all_same_nidpid)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pte_t *pte, oldpte;
 	spinlock_t *ptl;
 	unsigned long pages = 0;
-	bool all_same_node = true;
+	bool all_same_nidpid = true;
 	int last_nid = -1;
+	int last_pid = -1;
 
 	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
 	arch_enter_lazy_mmu_mode();
@@ -63,11 +64,18 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 
 				page = vm_normal_page(vma, addr, oldpte);
 				if (page) {
-					int this_nid = page_to_nid(page);
+					int nidpid = page_nidpid_last(page);
+					int this_nid = nidpid_to_nid(nidpid);
+					int this_pid = nidpid_to_pid(nidpid);
+
 					if (last_nid == -1)
 						last_nid = this_nid;
-					if (last_nid != this_nid)
-						all_same_node = false;
+					if (last_pid == -1)
+						last_pid = this_pid;
+					if (last_nid != this_nid ||
+					    last_pid != this_pid) {
+						all_same_nidpid = false;
+					}
 
 					if (!pte_numa(oldpte)) {
 						ptent = pte_mknuma(ptent);
@@ -107,7 +115,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
 
-	*ret_all_same_node = all_same_node;
+	*ret_all_same_nidpid = all_same_nidpid;
 	return pages;
 }
 
@@ -134,7 +142,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 	pmd_t *pmd;
 	unsigned long next;
 	unsigned long pages = 0;
-	bool all_same_node;
+	bool all_same_nidpid;
 
 	pmd = pmd_offset(pud, addr);
 	do {
@@ -158,7 +166,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
 		pages += change_pte_range(vma, pmd, addr, next, newprot,
-				 dirty_accountable, prot_numa, &all_same_node);
+				 dirty_accountable, prot_numa, &all_same_nidpid);
 
 		/*
 		 * If we are changing protections for NUMA hinting faults then
@@ -166,7 +174,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		 * node. This allows a regular PMD to be handled as one fault
 		 * and effectively batches the taking of the PTL
 		 */
-		if (prot_numa && all_same_node)
+		if (prot_numa && all_same_nidpid)
 			change_pmd_protnuma(vma->vm_mm, addr, pmd);
 	} while (pmd++, addr = next, addr != end);
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index dd886fac451a..89bedd0e4cad 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -626,7 +626,7 @@ static inline int free_pages_check(struct page *page)
 		bad_page(page);
 		return 1;
 	}
-	page_nid_reset_last(page);
+	page_nidpid_reset_last(page);
 	if (page->flags & PAGE_FLAGS_CHECK_AT_PREP)
 		page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 	return 0;
@@ -4015,7 +4015,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		mminit_verify_page_links(page, zone, nid, pfn);
 		init_page_count(page);
 		page_mapcount_reset(page);
-		page_nid_reset_last(page);
+		page_nidpid_reset_last(page);
 		SetPageReserved(page);
 		/*
 		 * Mark the block movable so that blocks are reserved for