[PATCH v5 1/3] lib/stackdepot: Add a refcount field in stack_record

From: Oscar Salvador
Date: Tue May 16 2023 - 10:04:05 EST


We want to filter out page_owner output and print only those
stacks that have been repeated beyond a certain threshold.
This gives us the chance to get rid of a lot of noise.
In order to do that, we need to keep track of how many repeated stacks
(for allocation) do we have, so we add a new refcount_t field
in the stack_record struct.

Note that this might increase the size of the struct for some
architectures.
E.g: x86_64 is not affected due to alignment, but x86 32bits might.

The alternative would be to have some kind of struct like this:

struct track_stacks {
struct stack_record *stack;
struct track_stacks *next;
refcount_t stack_count;

But ithat would imply to perform more allocations and glue everything
together, which would make the code more complex, so I think that
going with a new field in the struct stack_record is good enough.

Note that on __set_page_owner_handle(), page_owner->handle is set,
and on __reset_page_owner(), page_owner->free_handle is set.

We are interested in page_owner->handle, so when __set_page_owner()
gets called, we derive the stack_record struct from page_owner->handle,
and we increment its refcount_t field; and when __reset_page_owner()
gets called, we derive its stack_record from page_owner->handle()
and we decrement its refcount_t field.

Signed-off-by: Oscar Salvador <osalvador@xxxxxxx>
---
include/linux/stackdepot.h | 2 ++
lib/stackdepot.c | 53 +++++++++++++++++++++++++++++++-------
mm/page_owner.c | 6 +++++
3 files changed, 51 insertions(+), 10 deletions(-)

diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h
index e58306783d8e..6ba4fcdb0c5f 100644
--- a/include/linux/stackdepot.h
+++ b/include/linux/stackdepot.h
@@ -94,6 +94,8 @@ static inline int stack_depot_early_init(void) { return 0; }
depot_stack_handle_t __stack_depot_save(unsigned long *entries,
unsigned int nr_entries,
gfp_t gfp_flags, bool can_alloc);
+void stack_depot_inc_count(depot_stack_handle_t handle);
+void stack_depot_dec_count(depot_stack_handle_t handle);

/**
* stack_depot_save - Save a stack trace to stack depot
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index 2f5aa851834e..bc4a9cd25834 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -60,6 +60,7 @@ struct stack_record {
u32 hash; /* Hash in the hash table */
u32 size; /* Number of stored frames */
union handle_parts handle;
+ refcount_t count; /* Number of the same repeated stacks */
unsigned long entries[]; /* Variable-sized array of frames */
};

@@ -305,6 +306,7 @@ depot_alloc_stack(unsigned long *entries, int size, u32 hash, void **prealloc)
stack->handle.offset = pool_offset >> DEPOT_STACK_ALIGN;
stack->handle.valid = 1;
stack->handle.extra = 0;
+ refcount_set(&stack->count, 1);
memcpy(stack->entries, entries, flex_array_size(stack, entries, size));
pool_offset += required_size;
/*
@@ -457,8 +459,7 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries,
}
EXPORT_SYMBOL_GPL(stack_depot_save);

-unsigned int stack_depot_fetch(depot_stack_handle_t handle,
- unsigned long **entries)
+static struct stack_record *stack_depot_getstack(depot_stack_handle_t handle)
{
union handle_parts parts = { .handle = handle };
/*
@@ -470,6 +471,26 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle,
size_t offset = parts.offset << DEPOT_STACK_ALIGN;
struct stack_record *stack;

+ if (!handle)
+ return NULL;
+
+ if (parts.pool_index > pool_index_cached) {
+ WARN(1, "pool index %d out of bounds (%d) for stack id %08x\n",
+ parts.pool_index, pool_index_cached, handle);
+ return NULL;
+ }
+ pool = stack_pools[parts.pool_index];
+ if (!pool)
+ return NULL;
+ stack = pool + offset;
+ return stack;
+}
+
+unsigned int stack_depot_fetch(depot_stack_handle_t handle,
+ unsigned long **entries)
+{
+ struct stack_record *stack;
+
*entries = NULL;
/*
* Let KMSAN know *entries is initialized. This shall prevent false
@@ -480,21 +501,33 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle,
if (!handle)
return 0;

- if (parts.pool_index > pool_index_cached) {
- WARN(1, "pool index %d out of bounds (%d) for stack id %08x\n",
- parts.pool_index, pool_index_cached, handle);
- return 0;
- }
- pool = stack_pools[parts.pool_index];
- if (!pool)
+ stack = stack_depot_getstack(handle);
+ if (!stack)
return 0;
- stack = pool + offset;

*entries = stack->entries;
return stack->size;
}
EXPORT_SYMBOL_GPL(stack_depot_fetch);

+void stack_depot_inc_count(depot_stack_handle_t handle)
+{
+ struct stack_record *stack = NULL;
+
+ stack = stack_depot_getstack(handle);
+ if (stack)
+ refcount_inc(&stack->count);
+}
+
+void stack_depot_dec_count(depot_stack_handle_t handle)
+{
+ struct stack_record *stack = NULL;
+
+ stack = stack_depot_getstack(handle);
+ if (stack)
+ refcount_dec(&stack->count);
+}
+
void stack_depot_print(depot_stack_handle_t stack)
{
unsigned long *entries;
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 31169b3e7f06..2d5d07013e4e 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -139,6 +139,7 @@ void __reset_page_owner(struct page *page, unsigned short order)
int i;
struct page_ext *page_ext;
depot_stack_handle_t handle;
+ depot_stack_handle_t alloc_handle;
struct page_owner *page_owner;
u64 free_ts_nsec = local_clock();

@@ -146,6 +147,9 @@ void __reset_page_owner(struct page *page, unsigned short order)
if (unlikely(!page_ext))
return;

+ page_owner = get_page_owner(page_ext);
+ alloc_handle = page_owner->handle;
+
handle = save_stack(GFP_NOWAIT | __GFP_NOWARN);
for (i = 0; i < (1 << order); i++) {
__clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);
@@ -155,6 +159,7 @@ void __reset_page_owner(struct page *page, unsigned short order)
page_ext = page_ext_next(page_ext);
}
page_ext_put(page_ext);
+ stack_depot_dec_count(alloc_handle);
}

static inline void __set_page_owner_handle(struct page_ext *page_ext,
@@ -196,6 +201,7 @@ noinline void __set_page_owner(struct page *page, unsigned short order,
return;
__set_page_owner_handle(page_ext, handle, order, gfp_mask);
page_ext_put(page_ext);
+ stack_depot_inc_count(handle);
}

void __set_page_owner_migrate_reason(struct page *page, int reason)
--
2.35.3