Re: [PATCH v4 1/4] mm/slub: enable debugging memory wasting of kmalloc
From: Feng Tang
Date: Mon Sep 05 2022 - 04:39:01 EST
On Mon, Sep 05, 2022 at 03:33:14PM +0800, Vlastimil Babka wrote:
> On 9/5/22 09:06, Feng Tang wrote:
> > On Mon, Sep 05, 2022 at 02:29:51PM +0800, Vlastimil Babka wrote:
> >>
> >> How about get_partial() instantiates an on-stack structure that contains
> >> gfpflags, ret_slab, orig_size and passes pointer to that to all the nested
> >> functions.
> >>
> >> Would be similar to "struct alloc_context" in page allocation.
> >> Something like "struct partial_context pc"?
> >
> > Yep! This would make the parameters passing much tidier. Will try
> > this way.
> >
> > More aggressively is to also embed the 'kmem_cache' parameter into
> > it, but this may make the code look ambiguous.
>
> That one is used a lot everywhere, so it would be tedious to dereference it
> from a struct, and also might be a bit better code if it's in a register.
Got it. Following is the incremental patch for 1/4, which uses the
'partial_context' to pass parameters. And actually the 4/4 patch will
benefit more from this refactoring, as the object initialization doesn't
need to be separated and has race issue.
Thanks,
Feng
---
diff --git a/mm/slub.c b/mm/slub.c
index 82e7bd3a3966..7497fb6ca8e2 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -194,6 +194,12 @@ DEFINE_STATIC_KEY_FALSE(slub_debug_enabled);
#endif
#endif /* CONFIG_SLUB_DEBUG */
+struct partial_context {
+ struct slab **slab;
+ gfp_t flags;
+ int orig_size;
+};
+
static inline bool kmem_cache_debug(struct kmem_cache *s)
{
return kmem_cache_debug_flags(s, SLAB_DEBUG_FLAGS);
@@ -1333,7 +1339,7 @@ static inline int alloc_consistency_checks(struct kmem_cache *s,
}
static noinline int alloc_debug_processing(struct kmem_cache *s,
- struct slab *slab, void *object)
+ struct slab *slab, void *object, int orig_size)
{
if (s->flags & SLAB_CONSISTENCY_CHECKS) {
if (!alloc_consistency_checks(s, slab, object))
@@ -1342,6 +1348,7 @@ static noinline int alloc_debug_processing(struct kmem_cache *s,
/* Success. Perform special debug activities for allocs */
trace(s, slab, object, 1);
+ set_orig_size(s, object, orig_size);
init_object(s, object, SLUB_RED_ACTIVE);
return 1;
@@ -1610,7 +1617,7 @@ static inline
void setup_slab_debug(struct kmem_cache *s, struct slab *slab, void *addr) {}
static inline int alloc_debug_processing(struct kmem_cache *s,
- struct slab *slab, void *object) { return 0; }
+ struct slab *slab, void *object, int orig_size) { return 0; }
static inline void set_orig_size(struct kmem_cache *s,
void *object, unsigned int orig_size) {}
@@ -2042,7 +2049,7 @@ static inline void remove_partial(struct kmem_cache_node *n,
* it to full list if it was the last free object.
*/
static void *alloc_single_from_partial(struct kmem_cache *s,
- struct kmem_cache_node *n, struct slab *slab)
+ struct kmem_cache_node *n, struct slab *slab, int orig_size)
{
void *object;
@@ -2052,7 +2059,7 @@ static void *alloc_single_from_partial(struct kmem_cache *s,
slab->freelist = get_freepointer(s, object);
slab->inuse++;
- if (!alloc_debug_processing(s, slab, object)) {
+ if (!alloc_debug_processing(s, slab, object, orig_size)) {
remove_partial(n, slab);
return NULL;
}
@@ -2071,7 +2078,7 @@ static void *alloc_single_from_partial(struct kmem_cache *s,
* and put the slab to the partial (or full) list.
*/
static void *alloc_single_from_new_slab(struct kmem_cache *s,
- struct slab *slab)
+ struct slab *slab, int orig_size)
{
int nid = slab_nid(slab);
struct kmem_cache_node *n = get_node(s, nid);
@@ -2083,7 +2090,7 @@ static void *alloc_single_from_new_slab(struct kmem_cache *s,
slab->freelist = get_freepointer(s, object);
slab->inuse = 1;
- if (!alloc_debug_processing(s, slab, object))
+ if (!alloc_debug_processing(s, slab, object, orig_size))
/*
* It's not really expected that this would fail on a
* freshly allocated slab, but a concurrent memory
@@ -2161,7 +2168,7 @@ static inline bool pfmemalloc_match(struct slab *slab, gfp_t gfpflags);
* Try to allocate a partial slab from a specific node.
*/
static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
- struct slab **ret_slab, gfp_t gfpflags)
+ struct partial_context *pc)
{
struct slab *slab, *slab2;
void *object = NULL;
@@ -2181,11 +2188,11 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
list_for_each_entry_safe(slab, slab2, &n->partial, slab_list) {
void *t;
- if (!pfmemalloc_match(slab, gfpflags))
+ if (!pfmemalloc_match(slab, pc->flags))
continue;
if (kmem_cache_debug(s)) {
- object = alloc_single_from_partial(s, n, slab);
+ object = alloc_single_from_partial(s, n, slab, pc->orig_size);
if (object)
break;
continue;
@@ -2196,7 +2203,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
break;
if (!object) {
- *ret_slab = slab;
+ *pc->slab = slab;
stat(s, ALLOC_FROM_PARTIAL);
object = t;
} else {
@@ -2220,14 +2227,13 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
/*
* Get a slab from somewhere. Search in increasing NUMA distances.
*/
-static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
- struct slab **ret_slab)
+static void *get_any_partial(struct kmem_cache *s, struct partial_context *pc)
{
#ifdef CONFIG_NUMA
struct zonelist *zonelist;
struct zoneref *z;
struct zone *zone;
- enum zone_type highest_zoneidx = gfp_zone(flags);
+ enum zone_type highest_zoneidx = gfp_zone(pc->flags);
void *object;
unsigned int cpuset_mems_cookie;
@@ -2255,15 +2261,15 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
do {
cpuset_mems_cookie = read_mems_allowed_begin();
- zonelist = node_zonelist(mempolicy_slab_node(), flags);
+ zonelist = node_zonelist(mempolicy_slab_node(), pc->flags);
for_each_zone_zonelist(zone, z, zonelist, highest_zoneidx) {
struct kmem_cache_node *n;
n = get_node(s, zone_to_nid(zone));
- if (n && cpuset_zone_allowed(zone, flags) &&
+ if (n && cpuset_zone_allowed(zone, pc->flags) &&
n->nr_partial > s->min_partial) {
- object = get_partial_node(s, n, ret_slab, flags);
+ object = get_partial_node(s, n, pc);
if (object) {
/*
* Don't check read_mems_allowed_retry()
@@ -2284,8 +2290,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
/*
* Get a partial slab, lock it and return it.
*/
-static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
- struct slab **ret_slab)
+static void *get_partial(struct kmem_cache *s, int node, struct partial_context *pc)
{
void *object;
int searchnode = node;
@@ -2293,11 +2298,11 @@ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
if (node == NUMA_NO_NODE)
searchnode = numa_mem_id();
- object = get_partial_node(s, get_node(s, searchnode), ret_slab, flags);
+ object = get_partial_node(s, get_node(s, searchnode), pc);
if (object || node != NUMA_NO_NODE)
return object;
- return get_any_partial(s, flags, ret_slab);
+ return get_any_partial(s, pc);
}
#ifdef CONFIG_PREEMPTION
@@ -3022,6 +3027,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
void *freelist;
struct slab *slab;
unsigned long flags;
+ struct partial_context pc;
stat(s, ALLOC_SLOWPATH);
@@ -3135,7 +3141,10 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
new_objects:
- freelist = get_partial(s, gfpflags, node, &slab);
+ pc.flags = gfpflags;
+ pc.slab = &slab;
+ pc.orig_size = orig_size;
+ freelist = get_partial(s, node, &pc);
if (freelist)
goto check_new_slab;
@@ -3151,14 +3160,13 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
stat(s, ALLOC_SLAB);
if (kmem_cache_debug(s)) {
- freelist = alloc_single_from_new_slab(s, slab);
+ freelist = alloc_single_from_new_slab(s, slab, orig_size);
if (unlikely(!freelist))
goto new_objects;
if (s->flags & SLAB_STORE_USER)
set_track(s, freelist, TRACK_ALLOC, addr);
- set_orig_size(s, freelist, orig_size);
return freelist;
}
@@ -3184,7 +3192,6 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
*/
if (s->flags & SLAB_STORE_USER)
set_track(s, freelist, TRACK_ALLOC, addr);
- set_orig_size(s, freelist, orig_size);
return freelist;
}