[PATCH v2 09/13] fork: Dynamic Kernel Stack accounting

[David Stevens]

From: Pasha Tatashin <pasha.tatashin@xxxxxxxxxx>

Add an accounting of the amount of stack pages that have been faulted in
and are currently in use.

Example use case:
  $ cat /proc/vmstat | grep stack
  nr_kernel_stack 18684
  nr_dynamic_stacks_faults 156

The above shows that the kernel stacks use total 18684KiB, out of which
156KiB were faulted in.

Given that the pre-allocated stacks are 4KiB, we can determine the total
number of tasks:

tasks = (nr_kernel_stack - nr_dynamic_stacks_faults) / 4 = 4632.

The amount of kernel stack memory without dynamic stack on this machine
would be:

4632 * 16 KiB = 74,112 KiB

Therefore, in this example dynamic stacks save: 55,428 KiB

Signed-off-by: Pasha Tatashin <pasha.tatashin@xxxxxxxxxx>
[Rebased]
Signed-off-by: Linus Walleij <linus.walleij@xxxxxxxxxx>
[add to memcg stats, fix typos]
Signed-off-by: David Stevens <stevensd@xxxxxxxxxx>
---
 include/linux/mmzone.h |  3 +++
 kernel/fork.c          | 12 +++++++++++-
 mm/memcontrol.c        | 10 ++++++++++
 mm/vmstat.c            |  3 +++
 4 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 3e51190a55e4..4458fa7016a1 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -221,6 +221,9 @@ enum node_stat_item {
 	NR_FOLL_PIN_ACQUIRED,	/* via: pin_user_page(), gup flag: FOLL_PIN */
 	NR_FOLL_PIN_RELEASED,	/* pages returned via unpin_user_page() */
 	NR_KERNEL_STACK_KB,	/* measured in KiB */
+#ifdef CONFIG_DYNAMIC_STACK
+	NR_DYNAMIC_STACKS_FAULTS_KB, /* KiB of faulted kernel stack memory */
+#endif
 #if IS_ENABLED(CONFIG_SHADOW_CALL_STACK)
 	NR_KERNEL_SCS_KB,	/* measured in KiB */
 #endif
diff --git a/kernel/fork.c b/kernel/fork.c
index e615ef736dc0..9ac9d23f5f4b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -463,6 +463,8 @@ unsigned long dynamic_stack_accounting(struct task_struct *tsk, bool finalize)
 
 		mod_lruvec_page_state(page, NR_KERNEL_STACK_KB,
 				      PAGE_SIZE / 1024);
+		mod_lruvec_page_state(page, NR_DYNAMIC_STACKS_FAULTS_KB,
+				      PAGE_SIZE / 1024);
 	}
 
 	if (finalize) {
@@ -811,9 +813,17 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
 		nr_accounted = vm_area->nr_pages;
 #endif
 
-		for (i = 0; i < nr_accounted; i++)
+		for (i = 0; i < nr_accounted; i++) {
 			mod_lruvec_page_state(vm_area->pages[i], NR_KERNEL_STACK_KB,
 					      account * (PAGE_SIZE / 1024));
+#ifdef CONFIG_DYNAMIC_STACK
+			if (i >= THREAD_PREALLOC_PAGES) {
+				mod_lruvec_page_state(vm_area->pages[i],
+						      NR_DYNAMIC_STACKS_FAULTS_KB,
+						      account * (PAGE_SIZE / 1024));
+			}
+#endif
+		}
 	} else {
 		void *stack = task_stack_page(tsk);
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 772bac21d155..cd2195a735ab 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -318,6 +318,9 @@ static const unsigned int memcg_node_stat_items[] = {
 	NR_FILE_THPS,
 	NR_ANON_THPS,
 	NR_KERNEL_STACK_KB,
+#ifdef CONFIG_DYNAMIC_STACK
+	NR_DYNAMIC_STACKS_FAULTS_KB,
+#endif
 	NR_PAGETABLE,
 	NR_SECONDARY_PAGETABLE,
 #ifdef CONFIG_SWAP
@@ -1403,6 +1406,10 @@ static const struct memory_stat memory_stats[] = {
 #ifdef CONFIG_NUMA_BALANCING
 	{ "pgpromote_success",		PGPROMOTE_SUCCESS	},
 #endif
+
+#ifdef CONFIG_DYNAMIC_STACK
+	{ "dynamic_stack_faults",	NR_DYNAMIC_STACKS_FAULTS_KB     },
+#endif
 };
 
 /* The actual unit of the state item, not the same as the output unit */
@@ -1415,6 +1422,9 @@ static int memcg_page_state_unit(int item)
 	case NR_SLAB_UNRECLAIMABLE_B:
 		return 1;
 	case NR_KERNEL_STACK_KB:
+#ifdef CONFIG_DYNAMIC_STACK
+	case NR_DYNAMIC_STACKS_FAULTS_KB:
+#endif
 		return SZ_1K;
 	default:
 		return PAGE_SIZE;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 86b14b0f77b5..8fa1c7bcbaea 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1256,6 +1256,9 @@ const char * const vmstat_text[] = {
 	[I(NR_FOLL_PIN_ACQUIRED)]		= "nr_foll_pin_acquired",
 	[I(NR_FOLL_PIN_RELEASED)]		= "nr_foll_pin_released",
 	[I(NR_KERNEL_STACK_KB)]			= "nr_kernel_stack",
+#ifdef CONFIG_DYNAMIC_STACK
+	[I(NR_DYNAMIC_STACKS_FAULTS_KB)]	= "nr_dynamic_stacks_faults",
+#endif
 #if IS_ENABLED(CONFIG_SHADOW_CALL_STACK)
 	[I(NR_KERNEL_SCS_KB)]			= "nr_shadow_call_stack",
 #endif
-- 
2.54.0.rc2.544.gc7ae2d5bb8-goog