Merge tag 'slab-for-6.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab

Pull slab fixes from Vlastimil Babka:

 - The "common kmalloc v4" series [1] by Hyeonggon Yoo.

   While the plan after LPC is to try again if it's possible to get rid
   of SLOB and SLAB (and if any critical aspect of those is not possible
   to achieve with SLUB today, modify it accordingly), it will take a
   while even in case there are no objections.

   Meanwhile this is a nice cleanup and some parts (e.g. to the
   tracepoints) will be useful even if we end up with a single slab
   implementation in the future:

      - Improves the mm/slab_common.c wrappers to allow deleting
        duplicated code between SLAB and SLUB.

      - Large kmalloc() allocations in SLAB are passed to page allocator
        like in SLUB, reducing number of kmalloc caches.

      - Removes the {kmem_cache_alloc,kmalloc}_node variants of
        tracepoints, node id parameter added to non-_node variants.

 - Addition of kmalloc_size_roundup()

   The first two patches from a series by Kees Cook [2] that introduce
   kmalloc_size_roundup(). This will allow merging of per-subsystem
   patches using the new function and ultimately stop (ab)using ksize()
   in a way that causes ongoing trouble for debugging functionality and
   static checkers.

 - Wasted kmalloc() memory tracking in debugfs alloc_traces

   A patch from Feng Tang that enhances the existing debugfs
   alloc_traces file for kmalloc caches with information about how much
   space is wasted by allocations that needs less space than the
   particular kmalloc cache provides.

 - My series [3] to fix validation races for caches with enabled
   debugging:

      - By decoupling the debug cache operation more from non-debug
        fastpaths, extra locking simplifications were possible and thus
        done afterwards.

      - Additional cleanup of PREEMPT_RT specific code on top, by Thomas
        Gleixner.

      - A late fix for slab page leaks caused by the series, by Feng
        Tang.

 - Smaller fixes and cleanups:

      - Unneeded variable removals, by ye xingchen

      - A cleanup removing a BUG_ON() in create_unique_id(), by Chao Yu

Link: https://lore.kernel.org/all/20220817101826.236819-1-42.hyeyoo@gmail.com/ [1]
Link: https://lore.kernel.org/all/20220923202822.2667581-1-keescook@chromium.org/ [2]
Link: https://lore.kernel.org/all/20220823170400.26546-1-vbabka@suse.cz/ [3]

* tag 'slab-for-6.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab: (30 commits)
  mm/slub: fix a slab missed to be freed problem
  slab: Introduce kmalloc_size_roundup()
  slab: Remove __malloc attribute from realloc functions
  mm/slub: clean up create_unique_id()
  mm/slub: enable debugging memory wasting of kmalloc
  slub: Make PREEMPT_RT support less convoluted
  mm/slub: simplify __cmpxchg_double_slab() and slab_[un]lock()
  mm/slub: convert object_map_lock to non-raw spinlock
  mm/slub: remove slab_lock() usage for debug operations
  mm/slub: restrict sysfs validation to debug caches and make it safe
  mm/sl[au]b: check if large object is valid in __ksize()
  mm/slab_common: move declaration of __ksize() to mm/slab.h
  mm/slab_common: drop kmem_alloc & avoid dereferencing fields when not using
  mm/slab_common: unify NUMA and UMA version of tracepoints
  mm/sl[au]b: cleanup kmem_cache_alloc[_node]_trace()
  mm/sl[au]b: generalize kmalloc subsystem
  mm/slub: move free_debug_processing() further
  mm/sl[au]b: introduce common alloc/free functions without tracepoint
  mm/slab: kmalloc: pass requests larger than order-1 page to page allocator
  mm/slab_common: cleanup kmalloc_large()
  ...

1 files changed, 19 insertions, 55 deletions

diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index 4cb51ace600d..243073cfc29d 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -9,16 +9,15 @@
 #include <linux/tracepoint.h>
 #include <trace/events/mmflags.h>
 
-DECLARE_EVENT_CLASS(kmem_alloc,
+TRACE_EVENT(kmem_cache_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),
+		 gfp_t gfp_flags,
+		 int node),
 
-	TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags),
+	TP_ARGS(call_site, ptr, s, gfp_flags, node),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,	call_site	)
@@ -26,56 +25,42 @@ DECLARE_EVENT_CLASS(kmem_alloc,
 		__field(	size_t,		bytes_req	)
 		__field(	size_t,		bytes_alloc	)
 		__field(	unsigned long,	gfp_flags	)
+		__field(	int,		node		)
 		__field(	bool,		accounted	)
 	),
 
 	TP_fast_assign(
 		__entry->call_site	= call_site;
 		__entry->ptr		= ptr;
-		__entry->bytes_req	= bytes_req;
-		__entry->bytes_alloc	= bytes_alloc;
+		__entry->bytes_req	= s->object_size;
+		__entry->bytes_alloc	= s->size;
 		__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;
+					  (s->flags & SLAB_ACCOUNT)) : false;
 	),
 
-	TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s accounted=%s",
+	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->accounted ? "true" : "false")
 );
 
-DEFINE_EVENT(kmem_alloc, kmalloc,
-
-	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, s, bytes_req, bytes_alloc, gfp_flags)
-);
-
-DEFINE_EVENT(kmem_alloc, kmem_cache_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, s, bytes_req, bytes_alloc, gfp_flags)
-);
-
-DECLARE_EVENT_CLASS(kmem_alloc_node,
+TRACE_EVENT(kmalloc,
 
 	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, s, bytes_req, bytes_alloc, gfp_flags, node),
+	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,	call_site	)
@@ -84,7 +69,6 @@ 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(
@@ -94,9 +78,6 @@ 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 accounted=%s",
@@ -106,25 +87,8 @@ DECLARE_EVENT_CLASS(kmem_alloc_node,
 		__entry->bytes_alloc,
 		show_gfp_flags(__entry->gfp_flags),
 		__entry->node,
-		__entry->accounted ? "true" : "false")
-);
-
-DEFINE_EVENT(kmem_alloc_node, kmalloc_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, 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,
-		 struct kmem_cache *s, size_t bytes_req, size_t bytes_alloc,
-		 gfp_t gfp_flags, int node),
-
-	TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags, node)
+		(IS_ENABLED(CONFIG_MEMCG_KMEM) &&
+		 (__entry->gfp_flags & (__force unsigned long)__GFP_ACCOUNT)) ? "true" : "false")
 );
 
 TRACE_EVENT(kfree,
@@ -149,20 +113,20 @@ TRACE_EVENT(kfree,
 
 TRACE_EVENT(kmem_cache_free,
 
-	TP_PROTO(unsigned long call_site, const void *ptr, const char *name),
+	TP_PROTO(unsigned long call_site, const void *ptr, const struct kmem_cache *s),
 
-	TP_ARGS(call_site, ptr, name),
+	TP_ARGS(call_site, ptr, s),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,	call_site	)
 		__field(	const void *,	ptr		)
-		__string(	name,	name	)
+		__string(	name,		s->name		)
 	),
 
 	TP_fast_assign(
 		__entry->call_site	= call_site;
 		__entry->ptr		= ptr;
-		__assign_str(name, name);
+		__assign_str(name, s->name);
 	),
 
 	TP_printk("call_site=%pS ptr=%p name=%s",