[patch 2/2] mm, thp: track fallbacks due to failed memcg charges separately

[David Rientjes <rientjes@xxxxxxxxxx>]

The thp_fault_fallback stat in /proc/vmstat is incremented if either the
hugepage allocation fails through the page allocator or the hugepage
charge fails through mem cgroup.

This patch leaves this field untouched but adds a new field,
thp_fault_fallback_charge, which is incremented only when the mem cgroup
charge fails.

This distinguishes between faults that want to be backed by hugepages but
fail due to fragmentation (or low memory conditions) and those that fail
due to mem cgroup limits.  That can be used to determine the impact of
fragmentation on the system by excluding faults that failed due to memcg
usage.

Signed-off-by: David Rientjes <rientjes@xxxxxxxxxx>
---
 v2:
  - supported for shmem faults as well per Kirill
  - fixed worked in documentation and commit description per Mike

 Documentation/admin-guide/mm/transhuge.rst | 5 +++++
 include/linux/vm_event_item.h              | 1 +
 mm/huge_memory.c                           | 2 ++
 mm/shmem.c                                 | 4 +++-
 mm/vmstat.c                                | 1 +
 5 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
--- a/Documentation/admin-guide/mm/transhuge.rst
+++ b/Documentation/admin-guide/mm/transhuge.rst
@@ -310,6 +310,11 @@ thp_fault_fallback
 	is incremented if a page fault fails to allocate
 	a huge page and instead falls back to using small pages.
 
+thp_fault_fallback_charge
+	is incremented if a page fault fails to charge a huge page and
+	instead falls back to using small pages even though the
+	allocation was successful.
+
 thp_collapse_alloc_failed
 	is incremented if khugepaged found a range
 	of pages that should be collapsed into one huge page but failed
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -73,6 +73,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 		THP_FAULT_ALLOC,
 		THP_FAULT_FALLBACK,
+		THP_FAULT_FALLBACK_CHARGE,
 		THP_COLLAPSE_ALLOC,
 		THP_COLLAPSE_ALLOC_FAILED,
 		THP_FILE_ALLOC,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -597,6 +597,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg, true)) {
 		put_page(page);
 		count_vm_event(THP_FAULT_FALLBACK);
+		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
 		return VM_FAULT_FALLBACK;
 	}
 
@@ -1406,6 +1407,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
 			put_page(page);
 		ret |= VM_FAULT_FALLBACK;
 		count_vm_event(THP_FAULT_FALLBACK);
+		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
 		goto out;
 	}
 
diff --git a/mm/shmem.c b/mm/shmem.c
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1872,8 +1872,10 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 	error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg,
 					    PageTransHuge(page));
 	if (error) {
-		if (vmf && PageTransHuge(page))
+		if (vmf && PageTransHuge(page)) {
 			count_vm_event(THP_FAULT_FALLBACK);
+			count_vm_event(THP_FAULT_FALLBACK_CHARGE);
+		}
 		goto unacct;
 	}
 	error = shmem_add_to_page_cache(page, mapping, hindex,
diff --git a/mm/vmstat.c b/mm/vmstat.c
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1254,6 +1254,7 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	"thp_fault_alloc",
 	"thp_fault_fallback",
+	"thp_fault_fallback_charge",
 	"thp_collapse_alloc",
 	"thp_collapse_alloc_failed",
 	"thp_file_alloc",