[PATCH v3 06/15] mm/slab: add alloc_flags to slab_alloc_context

[Vlastimil Babka (SUSE)]

Add alloc_flags as a new field to the slab_alloc_context helper struct,
so we can pass it to more functions in the slab implementation without
adding another function parameter.

Start checking them via alloc_flags_allow_spinning() in
alloc_single_from_new_slab() (where we can drop the allow_spin
parameter), ___slab_alloc(), get_from_partial_node() and
get_from_any_partial(). This further reduces false-positive
spinning-not-allowed from allocations that are not kmalloc_nolock() but
lack __GFP_RECLAIM flags.

_kmalloc_nolock_noprof() initializes ac.alloc_flags using its flags that
are SLAB_ALLOC_NOLOCK. slab_alloc_node() and __kmem_cache_alloc_bulk()
are not reachable from kmalloc_nolock() and all their callers expect
spinning to be allowed, so they can use SLAB_ALLOC_DEFAULT. This is
temporary as the scope of slab_alloc_context will further move to the
callers, making the alloc_flags usage more obvious.

Also change how trynode_flags are constructed in ___slab_alloc() to
achieve the same "do not upgrade to GFP_NOWAIT" by using masking instead
of checking allow_spin. We need to do that because we now determine
allow_spin from alloc_flags, and would otherwise start to upgrade e.g.
kmalloc() allocations without __GFP_KSWAPD_RECLAIM (that however do
allow spinning) to GFP_NOWAIT, thus including __GFP_KSWAPD_RECLAIM.

During the masking keep also existing __GFP_NOMEMALLOC (pointed out by
Sashiko) and __GFP_ACCOUNT. Previously the hardcoded GFP_NOWAIT would
eliminate them, but it's not a big problem that would need a separate
fix.

Link: https://patch.msgid.link/20260610-slab_alloc_flags-v2-6-7190909db118@xxxxxxxxxx
Reviewed-by: Harry Yoo (Oracle) <harry@xxxxxxxxxx>
Reviewed-by: Hao Li <hao.li@xxxxxxxxx>
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@xxxxxxxxxx>
---
 mm/slub.c | 28 +++++++++++++++-------------
 1 file changed, 15 insertions(+), 13 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 6f6c15d796e1..3a34907b881b 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -217,6 +217,7 @@ static DEFINE_STATIC_KEY_FALSE(strict_numa);
 struct slab_alloc_context {
 	unsigned long caller_addr;
 	size_t orig_size;
+	unsigned int alloc_flags;
 };
 
 /* Structure holding parameters for get_partial_node_bulk() */
@@ -3687,9 +3688,9 @@ static inline void init_slab_obj_iter(struct kmem_cache *s, struct slab *slab,
  * and put the slab to the partial (or full) list.
  */
 static void *alloc_single_from_new_slab(struct kmem_cache *s, struct slab *slab,
-					const struct slab_alloc_context *ac,
-					bool allow_spin)
+					const struct slab_alloc_context *ac)
 {
+	bool allow_spin = alloc_flags_allow_spinning(ac->alloc_flags);
 	struct kmem_cache_node *n;
 	struct slab_obj_iter iter;
 	bool needs_add_partial;
@@ -3835,7 +3836,7 @@ static void *get_from_partial_node(struct kmem_cache *s,
 	if (!n || !n->nr_partial)
 		return NULL;
 
-	if (gfpflags_allow_spinning(gfp_flags))
+	if (alloc_flags_allow_spinning(ac->alloc_flags))
 		spin_lock_irqsave(&n->list_lock, flags);
 	else if (!spin_trylock_irqsave(&n->list_lock, flags))
 		return NULL;
@@ -3891,7 +3892,7 @@ static void *get_from_any_partial(struct kmem_cache *s, gfp_t gfp_flags,
 	struct zone *zone;
 	enum zone_type highest_zoneidx = gfp_zone(gfp_flags);
 	unsigned int cpuset_mems_cookie;
-	bool allow_spin = gfpflags_allow_spinning(gfp_flags);
+	bool allow_spin = alloc_flags_allow_spinning(ac->alloc_flags);
 
 	/*
 	 * The defrag ratio allows a configuration of the tradeoffs between
@@ -4449,7 +4450,7 @@ static unsigned int alloc_from_new_slab(struct kmem_cache *s, struct slab *slab,
 static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 			   const struct slab_alloc_context *ac)
 {
-	bool allow_spin = gfpflags_allow_spinning(gfpflags);
+	bool allow_spin = alloc_flags_allow_spinning(ac->alloc_flags);
 	gfp_t trynode_flags;
 	void *object;
 	struct slab *slab;
@@ -4466,18 +4467,15 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	 * 1) try to get a partial slab from target node only by having
 	 *    __GFP_THISNODE in trynode_flags for get_from_partial()
 	 * 2) if 1) failed, try to allocate a new slab from target node with
-	 *    GPF_NOWAIT | __GFP_THISNODE opportunistically
+	 *    (at most) GFP_NOWAIT | __GFP_THISNODE opportunistically
 	 * 3) if 2) failed, retry with original gfpflags which will allow
 	 *    get_from_partial() try partial lists of other nodes before
 	 *    potentially allocating new page from other nodes
 	 */
 	if (unlikely(node != NUMA_NO_NODE && !(gfpflags & __GFP_THISNODE)
 		     && try_thisnode)) {
-		if (unlikely(!allow_spin))
-			/* Do not upgrade gfp to NOWAIT from more restrictive mode */
-			trynode_flags = gfpflags | __GFP_THISNODE;
-		else
-			trynode_flags = GFP_NOWAIT | __GFP_THISNODE;
+		trynode_flags &= GFP_NOWAIT | __GFP_NOMEMALLOC | __GFP_ACCOUNT;
+		trynode_flags |= __GFP_NOWARN | __GFP_THISNODE;
 	}
 
 	object = get_from_partial(s, node, trynode_flags, ac);
@@ -4499,7 +4497,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	stat(s, ALLOC_SLAB);
 
 	if (IS_ENABLED(CONFIG_SLUB_TINY) || kmem_cache_debug(s)) {
-		object = alloc_single_from_new_slab(s, slab, ac, allow_spin);
+		object = alloc_single_from_new_slab(s, slab, ac);
 
 		if (likely(object))
 			goto success;
@@ -4918,6 +4916,7 @@ unsigned int alloc_from_pcs_bulk(struct kmem_cache *s, gfp_t gfp, size_t size,
 static __fastpath_inline void *slab_alloc_node(struct kmem_cache *s, struct list_lru *lru,
 		gfp_t gfpflags, int node, unsigned long addr, size_t orig_size)
 {
+	const unsigned int alloc_flags = SLAB_ALLOC_DEFAULT;
 	void *object;
 
 	s = slab_pre_alloc_hook(s, gfpflags);
@@ -4928,12 +4927,13 @@ static __fastpath_inline void *slab_alloc_node(struct kmem_cache *s, struct list
 	if (unlikely(object))
 		goto out;
 
-	object = alloc_from_pcs(s, gfpflags, SLAB_ALLOC_DEFAULT, node);
+	object = alloc_from_pcs(s, gfpflags, alloc_flags, node);
 
 	if (unlikely(!object)) {
 		const struct slab_alloc_context ac = {
 			.caller_addr = addr,
 			.orig_size = orig_size,
+			.alloc_flags = alloc_flags,
 		};
 		object = __slab_alloc_node(s, gfpflags, node, &ac);
 	}
@@ -5366,6 +5366,7 @@ void *_kmalloc_nolock_noprof(DECL_TOKEN_PARAMS(size, token), gfp_t gfp_flags, in
 	const struct slab_alloc_context ac = {
 		.caller_addr = _RET_IP_,
 		.orig_size = orig_size,
+		.alloc_flags = alloc_flags,
 	};
 
 	VM_WARN_ON_ONCE(gfp_flags & ~(__GFP_ACCOUNT | __GFP_ZERO |
@@ -7254,6 +7255,7 @@ static bool __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags,
 		const struct slab_alloc_context ac = {
 			.caller_addr = _RET_IP_,
 			.orig_size = s->object_size,
+			.alloc_flags = SLAB_ALLOC_DEFAULT,
 		};
 		for (i = 0; i < size; i++) {
 

-- 
2.54.0