mm/tracing: add 'accounted' entry into output of allocation tracepoints

Slab caches marked with SLAB_ACCOUNT force accounting for every
allocation from this cache even if __GFP_ACCOUNT flag is not passed.
Unfortunately, at the moment this flag is not visible in ftrace output,
and this makes it difficult to analyze the accounted allocations.

This patch adds boolean "accounted" entry into trace output,
and set it to 'true' for calls used __GFP_ACCOUNT flag and
for allocations from caches marked with SLAB_ACCOUNT.
Set it to 'false' if accounting is disabled in configs.

Signed-off-by: Vasily Averin <vvs@openvz.org>
Acked-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Acked-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Link: https://lore.kernel.org/r/c418ed25-65fe-f623-fbf8-1676528859ed@openvz.org
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>

include/trace/events/kmem.h

@@ -13,11 +13,12 @@ DECLARE_EVENT_CLASS(kmem_alloc,
 
 	TP_PROTO(unsigned long call_site,
 		 const void *ptr,
+		 struct kmem_cache *s,
 		 size_t bytes_req,
 		 size_t bytes_alloc,
 		 gfp_t gfp_flags),
 
-	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags),
+	TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,	call_site	)
@@ -25,6 +26,7 @@ DECLARE_EVENT_CLASS(kmem_alloc,
 		__field(	size_t,		bytes_req	)
 		__field(	size_t,		bytes_alloc	)
 		__field(	unsigned long,	gfp_flags	)
+		__field(	bool,		accounted	)
 	),
 
 	TP_fast_assign(
@@ -33,42 +35,47 @@ DECLARE_EVENT_CLASS(kmem_alloc,
 		__entry->bytes_req	= bytes_req;
 		__entry->bytes_alloc	= bytes_alloc;
 		__entry->gfp_flags	= (__force unsigned long)gfp_flags;
+		__entry->accounted	= IS_ENABLED(CONFIG_MEMCG_KMEM) ?
+					  ((gfp_flags & __GFP_ACCOUNT) ||
+					  (s && s->flags & SLAB_ACCOUNT)) : false;
 	),
 
-	TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s",
+	TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s accounted=%s",
 		(void *)__entry->call_site,
 		__entry->ptr,
 		__entry->bytes_req,
 		__entry->bytes_alloc,
-		show_gfp_flags(__entry->gfp_flags))
+		show_gfp_flags(__entry->gfp_flags),
+		__entry->accounted ? "true" : "false")
 );
 
 DEFINE_EVENT(kmem_alloc, kmalloc,
 
-	TP_PROTO(unsigned long call_site, const void *ptr,
+	TP_PROTO(unsigned long call_site, const void *ptr, struct kmem_cache *s,
 		 size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags),
 
-	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags)
+	TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags)
 );
 
 DEFINE_EVENT(kmem_alloc, kmem_cache_alloc,
 
-	TP_PROTO(unsigned long call_site, const void *ptr,
+	TP_PROTO(unsigned long call_site, const void *ptr, struct kmem_cache *s,
 		 size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags),
 
-	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags)
+	TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags)
 );
 
 DECLARE_EVENT_CLASS(kmem_alloc_node,
 
 	TP_PROTO(unsigned long call_site,
 		 const void *ptr,
+		 struct kmem_cache *s,
 		 size_t bytes_req,
 		 size_t bytes_alloc,
 		 gfp_t gfp_flags,
 		 int node),
 
-	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node),
+	TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags, node),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,	call_site	)
@@ -77,6 +84,7 @@ DECLARE_EVENT_CLASS(kmem_alloc_node,
 		__field(	size_t,		bytes_alloc	)
 		__field(	unsigned long,	gfp_flags	)
 		__field(	int,		node		)
+		__field(	bool,		accounted	)
 	),
 
 	TP_fast_assign(
@@ -86,33 +94,37 @@ DECLARE_EVENT_CLASS(kmem_alloc_node,
 		__entry->bytes_alloc	= bytes_alloc;
 		__entry->gfp_flags	= (__force unsigned long)gfp_flags;
 		__entry->node		= node;
+		__entry->accounted	= IS_ENABLED(CONFIG_MEMCG_KMEM) ?
+					  ((gfp_flags & __GFP_ACCOUNT) ||
+					  (s && s->flags & SLAB_ACCOUNT)) : false;
 	),
 
-	TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d",
+	TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s",
 		(void *)__entry->call_site,
 		__entry->ptr,
 		__entry->bytes_req,
 		__entry->bytes_alloc,
 		show_gfp_flags(__entry->gfp_flags),
-		__entry->node)
+		__entry->node,
+		__entry->accounted ? "true" : "false")
 );
 
 DEFINE_EVENT(kmem_alloc_node, kmalloc_node,
 
 	TP_PROTO(unsigned long call_site, const void *ptr,
-		 size_t bytes_req, size_t bytes_alloc,
+		 struct kmem_cache *s, size_t bytes_req, size_t bytes_alloc,
 		 gfp_t gfp_flags, int node),
 
-	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node)
+	TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags, node)
 );
 
 DEFINE_EVENT(kmem_alloc_node, kmem_cache_alloc_node,
 
 	TP_PROTO(unsigned long call_site, const void *ptr,
-		 size_t bytes_req, size_t bytes_alloc,
+		 struct kmem_cache *s, size_t bytes_req, size_t bytes_alloc,
 		 gfp_t gfp_flags, int node),
 
-	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node)
+	TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags, node)
 );
 
 TRACE_EVENT(kfree,

mm/slab.c

@@ -3478,7 +3478,7 @@ void *__kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru,
 {
 	void *ret = slab_alloc(cachep, lru, flags, cachep->object_size, _RET_IP_);
 
-	trace_kmem_cache_alloc(_RET_IP_, ret,
+	trace_kmem_cache_alloc(_RET_IP_, ret, cachep,
 			       cachep->object_size, cachep->size, flags);
 
 	return ret;
@@ -3567,7 +3567,7 @@ kmem_cache_alloc_trace(struct kmem_cache *cachep, gfp_t flags, size_t size)
 	ret = slab_alloc(cachep, NULL, flags, size, _RET_IP_);
 
 	ret = kasan_kmalloc(cachep, ret, size, flags);
-	trace_kmalloc(_RET_IP_, ret,
+	trace_kmalloc(_RET_IP_, ret, cachep,
 		      size, cachep->size, flags);
 	return ret;
 }
@@ -3592,7 +3592,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 {
 	void *ret = slab_alloc_node(cachep, flags, nodeid, cachep->object_size, _RET_IP_);
 
-	trace_kmem_cache_alloc_node(_RET_IP_, ret,
+	trace_kmem_cache_alloc_node(_RET_IP_, ret, cachep,
 				    cachep->object_size, cachep->size,
 				    flags, nodeid);
 
@@ -3611,7 +3611,7 @@ void *kmem_cache_alloc_node_trace(struct kmem_cache *cachep,
 	ret = slab_alloc_node(cachep, flags, nodeid, size, _RET_IP_);
 
 	ret = kasan_kmalloc(cachep, ret, size, flags);
-	trace_kmalloc_node(_RET_IP_, ret,
+	trace_kmalloc_node(_RET_IP_, ret, cachep,
 			   size, cachep->size,
 			   flags, nodeid);
 	return ret;
@@ -3694,7 +3694,7 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
 	ret = slab_alloc(cachep, NULL, flags, size, caller);
 
 	ret = kasan_kmalloc(cachep, ret, size, flags);
-	trace_kmalloc(caller, ret,
+	trace_kmalloc(caller, ret, cachep,
 		      size, cachep->size, flags);
 
 	return ret;

mm/slab_common.c

@@ -26,13 +26,12 @@
 #include <linux/memcontrol.h>
 #include <linux/stackdepot.h>
 
+#include "internal.h"
+#include "slab.h"
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/kmem.h>
 
-#include "internal.h"
-
-#include "slab.h"
-
 enum slab_state slab_state;
 LIST_HEAD(slab_caches);
 DEFINE_MUTEX(slab_mutex);
@@ -959,7 +958,7 @@ EXPORT_SYMBOL(kmalloc_order);
 void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order)
 {
 	void *ret = kmalloc_order(size, flags, order);
-	trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << order, flags);
+	trace_kmalloc(_RET_IP_, ret, NULL, size, PAGE_SIZE << order, flags);
 	return ret;
 }
 EXPORT_SYMBOL(kmalloc_order_trace);

mm/slob.c

@@ -507,7 +507,7 @@ __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
 		*m = size;
 		ret = (void *)m + minalign;
 
-		trace_kmalloc_node(caller, ret,
+		trace_kmalloc_node(caller, ret, NULL,
 				   size, size + minalign, gfp, node);
 	} else {
 		unsigned int order = get_order(size);
@@ -516,7 +516,7 @@ __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
 			gfp |= __GFP_COMP;
 		ret = slob_new_pages(gfp, order, node);
 
-		trace_kmalloc_node(caller, ret,
+		trace_kmalloc_node(caller, ret, NULL,
 				   size, PAGE_SIZE << order, gfp, node);
 	}
 
@@ -616,12 +616,12 @@ static void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
 
 	if (c->size < PAGE_SIZE) {
 		b = slob_alloc(c->size, flags, c->align, node, 0);
-		trace_kmem_cache_alloc_node(_RET_IP_, b, c->object_size,
+		trace_kmem_cache_alloc_node(_RET_IP_, b, NULL, c->object_size,
 					    SLOB_UNITS(c->size) * SLOB_UNIT,
 					    flags, node);
 	} else {
 		b = slob_new_pages(flags, get_order(c->size), node);
-		trace_kmem_cache_alloc_node(_RET_IP_, b, c->object_size,
+		trace_kmem_cache_alloc_node(_RET_IP_, b, NULL, c->object_size,
 					    PAGE_SIZE << get_order(c->size),
 					    flags, node);
 	}

mm/slub.c

@@ -3257,7 +3257,7 @@ void *__kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru,
 {
 	void *ret = slab_alloc(s, lru, gfpflags, _RET_IP_, s->object_size);
 
-	trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size,
+	trace_kmem_cache_alloc(_RET_IP_, ret, s, s->object_size,
 				s->size, gfpflags);
 
 	return ret;
@@ -3280,7 +3280,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_lru);
 void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size)
 {
 	void *ret = slab_alloc(s, NULL, gfpflags, _RET_IP_, size);
-	trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags);
+	trace_kmalloc(_RET_IP_, ret, s, size, s->size, gfpflags);
 	ret = kasan_kmalloc(s, ret, size, gfpflags);
 	return ret;
 }
@@ -3292,7 +3292,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
 {
 	void *ret = slab_alloc_node(s, NULL, gfpflags, node, _RET_IP_, s->object_size);
 
-	trace_kmem_cache_alloc_node(_RET_IP_, ret,
+	trace_kmem_cache_alloc_node(_RET_IP_, ret, s,
 				    s->object_size, s->size, gfpflags, node);
 
 	return ret;
@@ -3306,7 +3306,7 @@ void *kmem_cache_alloc_node_trace(struct kmem_cache *s,
 {
 	void *ret = slab_alloc_node(s, NULL, gfpflags, node, _RET_IP_, size);
 
-	trace_kmalloc_node(_RET_IP_, ret,
+	trace_kmalloc_node(_RET_IP_, ret, s,
 			   size, s->size, gfpflags, node);
 
 	ret = kasan_kmalloc(s, ret, size, gfpflags);
@@ -4441,7 +4441,7 @@ void *__kmalloc(size_t size, gfp_t flags)
 
 	ret = slab_alloc(s, NULL, flags, _RET_IP_, size);
 
-	trace_kmalloc(_RET_IP_, ret, size, s->size, flags);
+	trace_kmalloc(_RET_IP_, ret, s, size, s->size, flags);
 
 	ret = kasan_kmalloc(s, ret, size, flags);
 
@@ -4475,7 +4475,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node)
 	if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) {
 		ret = kmalloc_large_node(size, flags, node);
 
-		trace_kmalloc_node(_RET_IP_, ret,
+		trace_kmalloc_node(_RET_IP_, ret, NULL,
 				   size, PAGE_SIZE << get_order(size),
 				   flags, node);
 
@@ -4489,7 +4489,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node)
 
 	ret = slab_alloc_node(s, NULL, flags, node, _RET_IP_, size);
 
-	trace_kmalloc_node(_RET_IP_, ret, size, s->size, flags, node);
+	trace_kmalloc_node(_RET_IP_, ret, s, size, s->size, flags, node);
 
 	ret = kasan_kmalloc(s, ret, size, flags);
 
@@ -4946,7 +4946,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
 	ret = slab_alloc(s, NULL, gfpflags, caller, size);
 
 	/* Honor the call site pointer we received. */
-	trace_kmalloc(caller, ret, size, s->size, gfpflags);
+	trace_kmalloc(caller, ret, s, size, s->size, gfpflags);
 
 	return ret;
 }
@@ -4962,7 +4962,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 	if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) {
 		ret = kmalloc_large_node(size, gfpflags, node);
 
-		trace_kmalloc_node(caller, ret,
+		trace_kmalloc_node(caller, ret, NULL,
 				   size, PAGE_SIZE << get_order(size),
 				   gfpflags, node);
 
@@ -4977,7 +4977,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 	ret = slab_alloc_node(s, NULL, gfpflags, node, caller, size);
 
 	/* Honor the call site pointer we received. */
-	trace_kmalloc_node(caller, ret, size, s->size, gfpflags, node);
+	trace_kmalloc_node(caller, ret, s, size, s->size, gfpflags, node);
 
 	return ret;
 }