[RFC PATCH 1/2] mm/slub: perform free consistency checks before call_rcu

[RFC PATCH 1/2] mm/slub: perform free consistency checks before call_rcu

[Vlastimil Babka]

For SLAB_TYPESAFE_BY_RCU caches we use call_rcu to perform empty slab
freeing. The rcu callback rcu_free_slab() calls __free_slab() that
currently includes checking the slab consistency for caches with
SLAB_CONSISTENCY_CHECKS flags. This check needs the slab->objects field
to be intact.

Because in the next patch we want to allow rcu_head in struct slab to
become larger in debug configurations and thus potentially overwrite
more fields through a union than slab_list, we want to limit the fields
used in rcu_free_slab().  Thus move the consistency checks to
free_slab() before call_rcu(). This can be done safely even for
SLAB_TYPESAFE_BY_RCU caches where accesses to the objects can still
occur after freeing them.

As a result, only the slab->slab_cache field has to be physically
separate from rcu_head for the freeing callback to work. We also save
some cycles in the rcu callback for caches with consistency checks
enabled.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/slub.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 862dbd9af4f5..d86be1b0d09f 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2036,14 +2036,6 @@ static void __free_slab(struct kmem_cache *s, struct slab *slab)
 	int order = folio_order(folio);
 	int pages = 1 << order;
 
-	if (kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS)) {
-		void *p;
-
-		slab_pad_check(s, slab);
-		for_each_object(p, s, slab_address(slab), slab->objects)
-			check_object(s, slab, p, SLUB_RED_INACTIVE);
-	}
-
 	__slab_clear_pfmemalloc(slab);
 	__folio_clear_slab(folio);
 	folio->mapping = NULL;
@@ -2062,9 +2054,17 @@ static void rcu_free_slab(struct rcu_head *h)
 
 static void free_slab(struct kmem_cache *s, struct slab *slab)
 {
-	if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU)) {
+	if (kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS)) {
+		void *p;
+
+		slab_pad_check(s, slab);
+		for_each_object(p, s, slab_address(slab), slab->objects)
+			check_object(s, slab, p, SLUB_RED_INACTIVE);
+	}
+
+	if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU))
 		call_rcu(&slab->rcu_head, rcu_free_slab);
-	} else
+	else
 		__free_slab(s, slab);
 }
 
-- 
2.37.2

[RFC PATCH 2/2] mm/sl[au]b: rearrange struct slab fields to allow larger rcu_head

[Vlastimil Babka]

Joel reports [1] that increasing the rcu_head size for debugging
purposes used to work before struct slab was split from struct page, but
now runs into the various SLAB_MATCH() sanity checks of the layout.

This is because the rcu_head in struct page is in union with large
sub-structures and has space to grow without exceeding their size, while
in struct slab (for SLAB and SLUB) it's in union only with a list_head.

On closer inspection (and after the previous patch) we can put all
fields except slab_cache to a union with rcu_head, as slab_cache is
sufficient for the rcu freeing callbacks to work and the rest can be
overwritten by rcu_head without causing issues.

This is only somewhat complicated by the need to keep SLUB's
freelist+counters aligned for cmpxchg_double. As a result the fields
need to be reordered so that slab_cache is first (after page flags) and
the union with rcu_head follows. For consistency, do that for SLAB as
well, although not necessary there.

As a result, the rcu_head field in struct page and struct slab is no
longer at the same offset, but that doesn't matter as there is no
casting that would rely on that in the slab freeing callbacks, so we can
just drop the respective SLAB_MATCH() check.

Also we need to update the SLAB_MATCH() for compound_head to reflect the
new ordering.

While at it, also add a static_assert to check the alignment needed for
cmpxchg_double so mistakes are found sooner than a runtime GPF.

[1] https://lore.kernel.org/all/85afd876-d8bb-0804-b2c5-48ed3055e702@joelfernandes.org/

Reported-by: Joel Fernandes <joel@joelfernandes.org>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/slab.h | 54 ++++++++++++++++++++++++++++++++----------------------
 1 file changed, 32 insertions(+), 22 deletions(-)

diff --git a/mm/slab.h b/mm/slab.h
index 4ec82bec15ec..2c248864ea91 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -11,37 +11,43 @@ struct slab {
 
 #if defined(CONFIG_SLAB)
 
+	struct kmem_cache *slab_cache;
 	union {
-		struct list_head slab_list;
+		struct {
+			struct list_head slab_list;
+			void *freelist;	/* array of free object indexes */
+			void *s_mem;	/* first object */
+		};
 		struct rcu_head rcu_head;
 	};
-	struct kmem_cache *slab_cache;
-	void *freelist;	/* array of free object indexes */
-	void *s_mem;	/* first object */
 	unsigned int active;
 
 #elif defined(CONFIG_SLUB)
 
-	union {
-		struct list_head slab_list;
-		struct rcu_head rcu_head;
-#ifdef CONFIG_SLUB_CPU_PARTIAL
-		struct {
-			struct slab *next;
-			int slabs;	/* Nr of slabs left */
-		};
-#endif
-	};
 	struct kmem_cache *slab_cache;
-	/* Double-word boundary */
-	void *freelist;		/* first free object */
 	union {
-		unsigned long counters;
 		struct {
-			unsigned inuse:16;
-			unsigned objects:15;
-			unsigned frozen:1;
+			union {
+				struct list_head slab_list;
+#ifdef CONFIG_SLUB_CPU_PARTIAL
+				struct {
+					struct slab *next;
+					int slabs;	/* Nr of slabs left */
+				};
+#endif
+			};
+			/* Double-word boundary */
+			void *freelist;		/* first free object */
+			union {
+				unsigned long counters;
+				struct {
+					unsigned inuse:16;
+					unsigned objects:15;
+					unsigned frozen:1;
+				};
+			};
 		};
+		struct rcu_head rcu_head;
 	};
 	unsigned int __unused;
 
@@ -66,9 +72,10 @@ struct slab {
 #define SLAB_MATCH(pg, sl)						\
 	static_assert(offsetof(struct page, pg) == offsetof(struct slab, sl))
 SLAB_MATCH(flags, __page_flags);
-SLAB_MATCH(compound_head, slab_list);	/* Ensure bit 0 is clear */
 #ifndef CONFIG_SLOB
-SLAB_MATCH(rcu_head, rcu_head);
+SLAB_MATCH(compound_head, slab_cache);	/* Ensure bit 0 is clear */
+#else
+SLAB_MATCH(compound_head, slab_list);	/* Ensure bit 0 is clear */
 #endif
 SLAB_MATCH(_refcount, __page_refcount);
 #ifdef CONFIG_MEMCG
@@ -76,6 +83,9 @@ SLAB_MATCH(memcg_data, memcg_data);
 #endif
 #undef SLAB_MATCH
 static_assert(sizeof(struct slab) <= sizeof(struct page));
+#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && defined(CONFIG_SLUB)
+static_assert(IS_ALIGNED(offsetof(struct slab, freelist), 16));
+#endif
 
 /**
  * folio_slab - Converts from folio to slab.
-- 
2.37.2

Re: [RFC PATCH 2/2] mm/sl[au]b: rearrange struct slab fields to allow larger rcu_head

[Hyeonggon Yoo]

On Fri, Aug 26, 2022 at 11:09:12AM +0200, Vlastimil Babka wrote:
> Joel reports [1] that increasing the rcu_head size for debugging
> purposes used to work before struct slab was split from struct page, but
> now runs into the various SLAB_MATCH() sanity checks of the layout.
> 
> This is because the rcu_head in struct page is in union with large
> sub-structures and has space to grow without exceeding their size, while
> in struct slab (for SLAB and SLUB) it's in union only with a list_head.
> 
> On closer inspection (and after the previous patch) we can put all
> fields except slab_cache to a union with rcu_head, as slab_cache is
> sufficient for the rcu freeing callbacks to work and the rest can be
> overwritten by rcu_head without causing issues.
> 
> This is only somewhat complicated by the need to keep SLUB's
> freelist+counters aligned for cmpxchg_double. As a result the fields
> need to be reordered so that slab_cache is first (after page flags) and
> the union with rcu_head follows. For consistency, do that for SLAB as
> well, although not necessary there.
> 
> As a result, the rcu_head field in struct page and struct slab is no
> longer at the same offset, but that doesn't matter as there is no
> casting that would rely on that in the slab freeing callbacks, so we can
> just drop the respective SLAB_MATCH() check.
> 
> Also we need to update the SLAB_MATCH() for compound_head to reflect the
> new ordering.
> 
> While at it, also add a static_assert to check the alignment needed for
> cmpxchg_double so mistakes are found sooner than a runtime GPF.
> 
> [1] https://lore.kernel.org/all/85afd876-d8bb-0804-b2c5-48ed3055e702@joelfernandes.org/
> 
> Reported-by: Joel Fernandes <joel@joelfernandes.org>
> Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
> ---
>  mm/slab.h | 54 ++++++++++++++++++++++++++++++++----------------------
>  1 file changed, 32 insertions(+), 22 deletions(-)
> 
> diff --git a/mm/slab.h b/mm/slab.h
> index 4ec82bec15ec..2c248864ea91 100644
> --- a/mm/slab.h
> +++ b/mm/slab.h
> @@ -11,37 +11,43 @@ struct slab {
>  
>  #if defined(CONFIG_SLAB)
>  
> +	struct kmem_cache *slab_cache;
>  	union {
> -		struct list_head slab_list;
> +		struct {
> +			struct list_head slab_list;
> +			void *freelist;	/* array of free object indexes */
> +			void *s_mem;	/* first object */
> +		};
>  		struct rcu_head rcu_head;
>  	};
> -	struct kmem_cache *slab_cache;
> -	void *freelist;	/* array of free object indexes */
> -	void *s_mem;	/* first object */
>  	unsigned int active;
>  
>  #elif defined(CONFIG_SLUB)
>  
> -	union {
> -		struct list_head slab_list;
> -		struct rcu_head rcu_head;
> -#ifdef CONFIG_SLUB_CPU_PARTIAL
> -		struct {
> -			struct slab *next;
> -			int slabs;	/* Nr of slabs left */
> -		};
> -#endif
> -	};
>  	struct kmem_cache *slab_cache;
> -	/* Double-word boundary */
> -	void *freelist;		/* first free object */
>  	union {
> -		unsigned long counters;
>  		struct {
> -			unsigned inuse:16;
> -			unsigned objects:15;
> -			unsigned frozen:1;
> +			union {
> +				struct list_head slab_list;
> +#ifdef CONFIG_SLUB_CPU_PARTIAL
> +				struct {
> +					struct slab *next;
> +					int slabs;	/* Nr of slabs left */
> +				};
> +#endif
> +			};
> +			/* Double-word boundary */
> +			void *freelist;		/* first free object */
> +			union {
> +				unsigned long counters;
> +				struct {
> +					unsigned inuse:16;
> +					unsigned objects:15;
> +					unsigned frozen:1;
> +				};
> +			};
>  		};
> +		struct rcu_head rcu_head;
>  	};
>  	unsigned int __unused;
>  
> @@ -66,9 +72,10 @@ struct slab {
>  #define SLAB_MATCH(pg, sl)						\
>  	static_assert(offsetof(struct page, pg) == offsetof(struct slab, sl))
>  SLAB_MATCH(flags, __page_flags);
> -SLAB_MATCH(compound_head, slab_list);	/* Ensure bit 0 is clear */
>  #ifndef CONFIG_SLOB
> -SLAB_MATCH(rcu_head, rcu_head);
> +SLAB_MATCH(compound_head, slab_cache);	/* Ensure bit 0 is clear */
> +#else
> +SLAB_MATCH(compound_head, slab_list);	/* Ensure bit 0 is clear */
>  #endif
>  SLAB_MATCH(_refcount, __page_refcount);
>  #ifdef CONFIG_MEMCG
> @@ -76,6 +83,9 @@ SLAB_MATCH(memcg_data, memcg_data);
>  #endif
>  #undef SLAB_MATCH
>  static_assert(sizeof(struct slab) <= sizeof(struct page));
> +#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && defined(CONFIG_SLUB)
> +static_assert(IS_ALIGNED(offsetof(struct slab, freelist), 16));
> +#endif
>  
>  /**
>   * folio_slab - Converts from folio to slab.
> -- 
> 2.37.2
> 

Looks sane to me.

For slab part:
Acked-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>

-- 
Thanks,
Hyeonggon

Re: [RFC PATCH 2/2] mm/sl[au]b: rearrange struct slab fields to allow larger rcu_head

[Vlastimil Babka]

On 8/26/22 11:09, Vlastimil Babka wrote:
> Joel reports [1] that increasing the rcu_head size for debugging
> purposes used to work before struct slab was split from struct page, but
> now runs into the various SLAB_MATCH() sanity checks of the layout.
> 
> This is because the rcu_head in struct page is in union with large
> sub-structures and has space to grow without exceeding their size, while
> in struct slab (for SLAB and SLUB) it's in union only with a list_head.
> 
> On closer inspection (and after the previous patch) we can put all
> fields except slab_cache to a union with rcu_head, as slab_cache is
> sufficient for the rcu freeing callbacks to work and the rest can be
> overwritten by rcu_head without causing issues.
> 
> This is only somewhat complicated by the need to keep SLUB's
> freelist+counters aligned for cmpxchg_double. As a result the fields
> need to be reordered so that slab_cache is first (after page flags) and
> the union with rcu_head follows. For consistency, do that for SLAB as
> well, although not necessary there.
> 
> As a result, the rcu_head field in struct page and struct slab is no
> longer at the same offset, but that doesn't matter as there is no
> casting that would rely on that in the slab freeing callbacks, so we can
> just drop the respective SLAB_MATCH() check.
> 
> Also we need to update the SLAB_MATCH() for compound_head to reflect the
> new ordering.
> 
> While at it, also add a static_assert to check the alignment needed for
> cmpxchg_double so mistakes are found sooner than a runtime GPF.
> 
> [1] https://lore.kernel.org/all/85afd876-d8bb-0804-b2c5-48ed3055e702@joelfernandes.org/
> 
> Reported-by: Joel Fernandes <joel@joelfernandes.org>
> Signed-off-by: Vlastimil Babka <vbabka@suse.cz>

Both patches now pushed to slab.git for-6.1/fit_rcu_head and for-next

> ---
>  mm/slab.h | 54 ++++++++++++++++++++++++++++++++----------------------
>  1 file changed, 32 insertions(+), 22 deletions(-)
> 
> diff --git a/mm/slab.h b/mm/slab.h
> index 4ec82bec15ec..2c248864ea91 100644
> --- a/mm/slab.h
> +++ b/mm/slab.h
> @@ -11,37 +11,43 @@ struct slab {
>  
>  #if defined(CONFIG_SLAB)
>  
> +	struct kmem_cache *slab_cache;
>  	union {
> -		struct list_head slab_list;
> +		struct {
> +			struct list_head slab_list;
> +			void *freelist;	/* array of free object indexes */
> +			void *s_mem;	/* first object */
> +		};
>  		struct rcu_head rcu_head;
>  	};
> -	struct kmem_cache *slab_cache;
> -	void *freelist;	/* array of free object indexes */
> -	void *s_mem;	/* first object */
>  	unsigned int active;
>  
>  #elif defined(CONFIG_SLUB)
>  
> -	union {
> -		struct list_head slab_list;
> -		struct rcu_head rcu_head;
> -#ifdef CONFIG_SLUB_CPU_PARTIAL
> -		struct {
> -			struct slab *next;
> -			int slabs;	/* Nr of slabs left */
> -		};
> -#endif
> -	};
>  	struct kmem_cache *slab_cache;
> -	/* Double-word boundary */
> -	void *freelist;		/* first free object */
>  	union {
> -		unsigned long counters;
>  		struct {
> -			unsigned inuse:16;
> -			unsigned objects:15;
> -			unsigned frozen:1;
> +			union {
> +				struct list_head slab_list;
> +#ifdef CONFIG_SLUB_CPU_PARTIAL
> +				struct {
> +					struct slab *next;
> +					int slabs;	/* Nr of slabs left */
> +				};
> +#endif
> +			};
> +			/* Double-word boundary */
> +			void *freelist;		/* first free object */
> +			union {
> +				unsigned long counters;
> +				struct {
> +					unsigned inuse:16;
> +					unsigned objects:15;
> +					unsigned frozen:1;
> +				};
> +			};
>  		};
> +		struct rcu_head rcu_head;
>  	};
>  	unsigned int __unused;
>  
> @@ -66,9 +72,10 @@ struct slab {
>  #define SLAB_MATCH(pg, sl)						\
>  	static_assert(offsetof(struct page, pg) == offsetof(struct slab, sl))
>  SLAB_MATCH(flags, __page_flags);
> -SLAB_MATCH(compound_head, slab_list);	/* Ensure bit 0 is clear */
>  #ifndef CONFIG_SLOB
> -SLAB_MATCH(rcu_head, rcu_head);
> +SLAB_MATCH(compound_head, slab_cache);	/* Ensure bit 0 is clear */
> +#else
> +SLAB_MATCH(compound_head, slab_list);	/* Ensure bit 0 is clear */
>  #endif
>  SLAB_MATCH(_refcount, __page_refcount);
>  #ifdef CONFIG_MEMCG
> @@ -76,6 +83,9 @@ SLAB_MATCH(memcg_data, memcg_data);
>  #endif
>  #undef SLAB_MATCH
>  static_assert(sizeof(struct slab) <= sizeof(struct page));
> +#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && defined(CONFIG_SLUB)
> +static_assert(IS_ALIGNED(offsetof(struct slab, freelist), 16));
> +#endif
>  
>  /**
>   * folio_slab - Converts from folio to slab.

Re: [RFC PATCH 1/2] mm/slub: perform free consistency checks before call_rcu

[Hyeonggon Yoo]

On Fri, Aug 26, 2022 at 11:09:11AM +0200, Vlastimil Babka wrote:
> For SLAB_TYPESAFE_BY_RCU caches we use call_rcu to perform empty slab
> freeing. The rcu callback rcu_free_slab() calls __free_slab() that
> currently includes checking the slab consistency for caches with
> SLAB_CONSISTENCY_CHECKS flags. This check needs the slab->objects field
> to be intact.
> 
> Because in the next patch we want to allow rcu_head in struct slab to
> become larger in debug configurations and thus potentially overwrite
> more fields through a union than slab_list, we want to limit the fields
> used in rcu_free_slab().  Thus move the consistency checks to
> free_slab() before call_rcu(). This can be done safely even for
> SLAB_TYPESAFE_BY_RCU caches where accesses to the objects can still
> occur after freeing them.
> 
> As a result, only the slab->slab_cache field has to be physically
> separate from rcu_head for the freeing callback to work. We also save
> some cycles in the rcu callback for caches with consistency checks
> enabled.
> 
> Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
> ---
>  mm/slub.c | 20 ++++++++++----------
>  1 file changed, 10 insertions(+), 10 deletions(-)
> 
> diff --git a/mm/slub.c b/mm/slub.c
> index 862dbd9af4f5..d86be1b0d09f 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -2036,14 +2036,6 @@ static void __free_slab(struct kmem_cache *s, struct slab *slab)
>  	int order = folio_order(folio);
>  	int pages = 1 << order;
>  
> -	if (kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS)) {
> -		void *p;
> -
> -		slab_pad_check(s, slab);
> -		for_each_object(p, s, slab_address(slab), slab->objects)
> -			check_object(s, slab, p, SLUB_RED_INACTIVE);
> -	}
> -
>  	__slab_clear_pfmemalloc(slab);
>  	__folio_clear_slab(folio);
>  	folio->mapping = NULL;
> @@ -2062,9 +2054,17 @@ static void rcu_free_slab(struct rcu_head *h)
>  
>  static void free_slab(struct kmem_cache *s, struct slab *slab)
>  {
> -	if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU)) {
> +	if (kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS)) {
> +		void *p;
> +
> +		slab_pad_check(s, slab);
> +		for_each_object(p, s, slab_address(slab), slab->objects)
> +			check_object(s, slab, p, SLUB_RED_INACTIVE);
> +	}
> +
> +	if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU))
>  		call_rcu(&slab->rcu_head, rcu_free_slab);
> -	} else
> +	else
>  		__free_slab(s, slab);
>  }

So this allows corrupting 'counters' with patch 2.

The code looks still safe to me as we do only
redzone checking for SLAB_TYPESAFE_RCU caches.

Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>

> -- 
> 2.37.2
> 

-- 
Thanks,
Hyeonggon