[PATCH 4.9 19/39] kaiser: vmstat show NR_KAISERTABLE as nr_overhead

[Greg Kroah-Hartman]

4.9-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Hugh Dickins <hughd@xxxxxxxxxx>


The kaiser update made an interesting choice, never to free any shadow
page tables.  Contention on global spinlock was worrying, particularly
with it held across page table scans when freeing.  Something had to be
done: I was going to add refcounting; but simply never to free them is
an appealing choice, minimizing contention without complicating the code
(the more a page table is found already, the less the spinlock is used).

But leaking pages in this way is also a worry: can we get away with it?
At the very least, we need a count to show how bad it actually gets:
in principle, one might end up wasting about 1/256 of memory that way
(1/512 for when direct-mapped pages have to be user-mapped, plus 1/512
for when they are user-mapped from the vmalloc area on another occasion
(but we don't have vmalloc'ed stacks, so only large ldts are vmalloc'ed).

Add per-cpu stat NR_KAISERTABLE: including 256 at startup for the
shared pgd entries, and 1 for each intermediate page table added
thereafter for user-mapping - but leave out the 1 per mm, for its
shadow pgd, because that distracts from the monotonic increase.
Shown in /proc/vmstat as nr_overhead (0 if kaiser not enabled).

In practice, it doesn't look so bad so far: more like 1/12000 after
nine hours of gtests below; and movable pageblock segregation should
tend to cluster the kaiser tables into a subset of the address space
(if not, they will be bad for compaction too).  But production may
tell a different story: keep an eye on this number, and bring back
lighter freeing if it gets out of control (maybe a shrinker).

["nr_overhead" should of course say "nr_kaisertable", if it needs
to stay; but for the moment we are being coy, preferring that when
Joe Blow notices a new line in his /proc/vmstat, he does not get
too curious about what this "kaiser" stuff might be.]

Signed-off-by: Hugh Dickins <hughd@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 arch/x86/mm/kaiser.c   |   16 +++++++++++-----
 include/linux/mmzone.h |    3 ++-
 mm/vmstat.c            |    1 +
 3 files changed, 14 insertions(+), 6 deletions(-)

--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -121,9 +121,11 @@ static pte_t *kaiser_pagetable_walk(unsi
 		if (!new_pmd_page)
 			return NULL;
 		spin_lock(&shadow_table_allocation_lock);
-		if (pud_none(*pud))
+		if (pud_none(*pud)) {
 			set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page)));
-		else
+			__inc_zone_page_state(virt_to_page((void *)
+						new_pmd_page), NR_KAISERTABLE);
+		} else
 			free_page(new_pmd_page);
 		spin_unlock(&shadow_table_allocation_lock);
 	}
@@ -139,9 +141,11 @@ static pte_t *kaiser_pagetable_walk(unsi
 		if (!new_pte_page)
 			return NULL;
 		spin_lock(&shadow_table_allocation_lock);
-		if (pmd_none(*pmd))
+		if (pmd_none(*pmd)) {
 			set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page)));
-		else
+			__inc_zone_page_state(virt_to_page((void *)
+						new_pte_page), NR_KAISERTABLE);
+		} else
 			free_page(new_pte_page);
 		spin_unlock(&shadow_table_allocation_lock);
 	}
@@ -205,11 +209,13 @@ static void __init kaiser_init_all_pgds(
 	pgd = native_get_shadow_pgd(pgd_offset_k((unsigned long )0));
 	for (i = PTRS_PER_PGD / 2; i < PTRS_PER_PGD; i++) {
 		pgd_t new_pgd;
-		pud_t *pud = pud_alloc_one(&init_mm, PAGE_OFFSET + i * PGDIR_SIZE);
+		pud_t *pud = pud_alloc_one(&init_mm,
+					   PAGE_OFFSET + i * PGDIR_SIZE);
 		if (!pud) {
 			WARN_ON(1);
 			break;
 		}
+		inc_zone_page_state(virt_to_page(pud), NR_KAISERTABLE);
 		new_pgd = __pgd(_KERNPG_TABLE |__pa(pud));
 		/*
 		 * Make sure not to stomp on some other pgd entry.
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -124,8 +124,9 @@ enum zone_stat_item {
 	NR_SLAB_UNRECLAIMABLE,
 	NR_PAGETABLE,		/* used for pagetables */
 	NR_KERNEL_STACK_KB,	/* measured in KiB */
-	/* Second 128 byte cacheline */
+	NR_KAISERTABLE,
 	NR_BOUNCE,
+	/* Second 128 byte cacheline */
 #if IS_ENABLED(CONFIG_ZSMALLOC)
 	NR_ZSPAGES,		/* allocated in zsmalloc */
 #endif
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -932,6 +932,7 @@ const char * const vmstat_text[] = {
 	"nr_slab_unreclaimable",
 	"nr_page_table_pages",
 	"nr_kernel_stack",
+	"nr_overhead",
 	"nr_bounce",
 #if IS_ENABLED(CONFIG_ZSMALLOC)
 	"nr_zspages",