Merge tag 'bpf_try_alloc_pages' of git://git.kernel.org/pub/scm/linux…

…/kernel/git/bpf/bpf-next

Pull bpf try_alloc_pages() support from Alexei Starovoitov:
 "The pull includes work from Sebastian, Vlastimil and myself with a lot
  of help from Michal and Shakeel.

  This is a first step towards making kmalloc reentrant to get rid of
  slab wrappers: bpf_mem_alloc, kretprobe's objpool, etc. These patches
  make page allocator safe from any context.

  Vlastimil kicked off this effort at LSFMM 2024:

    https://lwn.net/Articles/974138/

  and we continued at LSFMM 2025:

    https://lore.kernel.org/all/CAADnVQKfkGxudNUkcPJgwe3nTZ=xohnRshx9kLZBTmR_E1DFEg@mail.gmail.com/

  Why:

  SLAB wrappers bind memory to a particular subsystem making it
  unavailable to the rest of the kernel. Some BPF maps in production
  consume Gbytes of preallocated memory. Top 5 in Meta: 1.5G, 1.2G,
  1.1G, 300M, 200M. Once we have kmalloc that works in any context BPF
  map preallocation won't be necessary.

  How:

  Synchronous kmalloc/page alloc stack has multiple stages going from
  fast to slow: cmpxchg16 -> slab_alloc -> new_slab -> alloc_pages ->
  rmqueue_pcplist -> __rmqueue, where rmqueue_pcplist was already
  relying on trylock.

  This set changes rmqueue_bulk/rmqueue_buddy to attempt a trylock and
  return ENOMEM if alloc_flags & ALLOC_TRYLOCK. It then wraps this
  functionality into try_alloc_pages() helper. We make sure that the
  logic is sane in PREEMPT_RT.

  End result: try_alloc_pages()/free_pages_nolock() are safe to call
  from any context.

  try_kmalloc() for any context with similar trylock approach will
  follow. It will use try_alloc_pages() when slab needs a new page.
  Though such try_kmalloc/page_alloc() is an opportunistic allocator,
  this design ensures that the probability of successful allocation of
  small objects (up to one page in size) is high.

  Even before we have try_kmalloc(), we already use try_alloc_pages() in
  BPF arena implementation and it's going to be used more extensively in
  BPF"

* tag 'bpf_try_alloc_pages' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next:
  mm: Fix the flipped condition in gfpflags_allow_spinning()
  bpf: Use try_alloc_pages() to allocate pages for bpf needs.
  mm, bpf: Use memcg in try_alloc_pages().
  memcg: Use trylock to access memcg stock_lock.
  mm, bpf: Introduce free_pages_nolock()
  mm, bpf: Introduce try_alloc_pages() for opportunistic page allocation
  locking/local_lock: Introduce localtry_lock_t

include/linux/bpf.h

@@ -2385,7 +2385,7 @@ int  generic_map_delete_batch(struct bpf_map *map,
 struct bpf_map *bpf_map_get_curr_or_next(u32 *id);
 struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id);
 
-int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid,
+int bpf_map_alloc_pages(const struct bpf_map *map, int nid,
 			unsigned long nr_pages, struct page **page_array);
 #ifdef CONFIG_MEMCG
 void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags,

include/linux/gfp.h

@@ -39,6 +39,25 @@ static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
 	return !!(gfp_flags & __GFP_DIRECT_RECLAIM);
 }
 
+static inline bool gfpflags_allow_spinning(const gfp_t gfp_flags)
+{
+	/*
+	 * !__GFP_DIRECT_RECLAIM -> direct claim is not allowed.
+	 * !__GFP_KSWAPD_RECLAIM -> it's not safe to wake up kswapd.
+	 * All GFP_* flags including GFP_NOWAIT use one or both flags.
+	 * try_alloc_pages() is the only API that doesn't specify either flag.
+	 *
+	 * This is stronger than GFP_NOWAIT or GFP_ATOMIC because
+	 * those are guaranteed to never block on a sleeping lock.
+	 * Here we are enforcing that the allocation doesn't ever spin
+	 * on any locks (i.e. only trylocks). There is no high level
+	 * GFP_$FOO flag for this use in try_alloc_pages() as the
+	 * regular page allocator doesn't fully support this
+	 * allocation mode.
+	 */
+	return !!(gfp_flags & __GFP_RECLAIM);
+}
+
 #ifdef CONFIG_HIGHMEM
 #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM
 #else
@@ -335,6 +354,9 @@ static inline struct page *alloc_page_vma_noprof(gfp_t gfp,
 }
 #define alloc_page_vma(...)			alloc_hooks(alloc_page_vma_noprof(__VA_ARGS__))
 
+struct page *try_alloc_pages_noprof(int nid, unsigned int order);
+#define try_alloc_pages(...)			alloc_hooks(try_alloc_pages_noprof(__VA_ARGS__))
+
 extern unsigned long get_free_pages_noprof(gfp_t gfp_mask, unsigned int order);
 #define __get_free_pages(...)			alloc_hooks(get_free_pages_noprof(__VA_ARGS__))
 
@@ -357,6 +379,7 @@ __meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mas
 	__get_free_pages((gfp_mask) | GFP_DMA, (order))
 
 extern void __free_pages(struct page *page, unsigned int order);
+extern void free_pages_nolock(struct page *page, unsigned int order);
 extern void free_pages(unsigned long addr, unsigned int order);
 
 #define __free_page(page) __free_pages((page), 0)

include/linux/local_lock.h

@@ -51,6 +51,76 @@
 #define local_unlock_irqrestore(lock, flags)			\
 	__local_unlock_irqrestore(lock, flags)
 
+/**
+ * localtry_lock_init - Runtime initialize a lock instance
+ */
+#define localtry_lock_init(lock)		__localtry_lock_init(lock)
+
+/**
+ * localtry_lock - Acquire a per CPU local lock
+ * @lock:	The lock variable
+ */
+#define localtry_lock(lock)		__localtry_lock(lock)
+
+/**
+ * localtry_lock_irq - Acquire a per CPU local lock and disable interrupts
+ * @lock:	The lock variable
+ */
+#define localtry_lock_irq(lock)		__localtry_lock_irq(lock)
+
+/**
+ * localtry_lock_irqsave - Acquire a per CPU local lock, save and disable
+ *			 interrupts
+ * @lock:	The lock variable
+ * @flags:	Storage for interrupt flags
+ */
+#define localtry_lock_irqsave(lock, flags)				\
+	__localtry_lock_irqsave(lock, flags)
+
+/**
+ * localtry_trylock - Try to acquire a per CPU local lock.
+ * @lock:	The lock variable
+ *
+ * The function can be used in any context such as NMI or HARDIRQ. Due to
+ * locking constrains it will _always_ fail to acquire the lock in NMI or
+ * HARDIRQ context on PREEMPT_RT.
+ */
+#define localtry_trylock(lock)		__localtry_trylock(lock)
+
+/**
+ * localtry_trylock_irqsave - Try to acquire a per CPU local lock, save and disable
+ *			      interrupts if acquired
+ * @lock:	The lock variable
+ * @flags:	Storage for interrupt flags
+ *
+ * The function can be used in any context such as NMI or HARDIRQ. Due to
+ * locking constrains it will _always_ fail to acquire the lock in NMI or
+ * HARDIRQ context on PREEMPT_RT.
+ */
+#define localtry_trylock_irqsave(lock, flags)				\
+	__localtry_trylock_irqsave(lock, flags)
+
+/**
+ * local_unlock - Release a per CPU local lock
+ * @lock:	The lock variable
+ */
+#define localtry_unlock(lock)		__localtry_unlock(lock)
+
+/**
+ * local_unlock_irq - Release a per CPU local lock and enable interrupts
+ * @lock:	The lock variable
+ */
+#define localtry_unlock_irq(lock)		__localtry_unlock_irq(lock)
+
+/**
+ * localtry_unlock_irqrestore - Release a per CPU local lock and restore
+ *			      interrupt flags
+ * @lock:	The lock variable
+ * @flags:      Interrupt flags to restore
+ */
+#define localtry_unlock_irqrestore(lock, flags)			\
+	__localtry_unlock_irqrestore(lock, flags)
+
 DEFINE_GUARD(local_lock, local_lock_t __percpu*,
 	     local_lock(_T),
 	     local_unlock(_T))

include/linux/local_lock_internal.h

@@ -15,6 +15,11 @@ typedef struct {
 #endif
 } local_lock_t;
 
+typedef struct {
+	local_lock_t	llock;
+	unsigned int	acquired;
+} localtry_lock_t;
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define LOCAL_LOCK_DEBUG_INIT(lockname)		\
 	.dep_map = {					\
@@ -31,6 +36,13 @@ static inline void local_lock_acquire(local_lock_t *l)
 	l->owner = current;
 }
 
+static inline void local_trylock_acquire(local_lock_t *l)
+{
+	lock_map_acquire_try(&l->dep_map);
+	DEBUG_LOCKS_WARN_ON(l->owner);
+	l->owner = current;
+}
+
 static inline void local_lock_release(local_lock_t *l)
 {
 	DEBUG_LOCKS_WARN_ON(l->owner != current);
@@ -45,11 +57,13 @@ static inline void local_lock_debug_init(local_lock_t *l)
 #else /* CONFIG_DEBUG_LOCK_ALLOC */
 # define LOCAL_LOCK_DEBUG_INIT(lockname)
 static inline void local_lock_acquire(local_lock_t *l) { }
+static inline void local_trylock_acquire(local_lock_t *l) { }
 static inline void local_lock_release(local_lock_t *l) { }
 static inline void local_lock_debug_init(local_lock_t *l) { }
 #endif /* !CONFIG_DEBUG_LOCK_ALLOC */
 
 #define INIT_LOCAL_LOCK(lockname)	{ LOCAL_LOCK_DEBUG_INIT(lockname) }
+#define INIT_LOCALTRY_LOCK(lockname)	{ .llock = { LOCAL_LOCK_DEBUG_INIT(lockname.llock) }}
 
 #define __local_lock_init(lock)					\
 do {								\
@@ -118,15 +132,115 @@ do {								\
 #define __local_unlock_nested_bh(lock)				\
 	local_lock_release(this_cpu_ptr(lock))
 
+/* localtry_lock_t variants */
+
+#define __localtry_lock_init(lock)				\
+do {								\
+	__local_lock_init(&(lock)->llock);			\
+	WRITE_ONCE((lock)->acquired, 0);			\
+} while (0)
+
+#define __localtry_lock(lock)					\
+	do {							\
+		localtry_lock_t *lt;				\
+		preempt_disable();				\
+		lt = this_cpu_ptr(lock);			\
+		local_lock_acquire(&lt->llock);			\
+		WRITE_ONCE(lt->acquired, 1);			\
+	} while (0)
+
+#define __localtry_lock_irq(lock)				\
+	do {							\
+		localtry_lock_t *lt;				\
+		local_irq_disable();				\
+		lt = this_cpu_ptr(lock);			\
+		local_lock_acquire(&lt->llock);			\
+		WRITE_ONCE(lt->acquired, 1);			\
+	} while (0)
+
+#define __localtry_lock_irqsave(lock, flags)			\
+	do {							\
+		localtry_lock_t *lt;				\
+		local_irq_save(flags);				\
+		lt = this_cpu_ptr(lock);			\
+		local_lock_acquire(&lt->llock);			\
+		WRITE_ONCE(lt->acquired, 1);			\
+	} while (0)
+
+#define __localtry_trylock(lock)				\
+	({							\
+		localtry_lock_t *lt;				\
+		bool _ret;					\
+								\
+		preempt_disable();				\
+		lt = this_cpu_ptr(lock);			\
+		if (!READ_ONCE(lt->acquired)) {			\
+			WRITE_ONCE(lt->acquired, 1);		\
+			local_trylock_acquire(&lt->llock);	\
+			_ret = true;				\
+		} else {					\
+			_ret = false;				\
+			preempt_enable();			\
+		}						\
+		_ret;						\
+	})
+
+#define __localtry_trylock_irqsave(lock, flags)			\
+	({							\
+		localtry_lock_t *lt;				\
+		bool _ret;					\
+								\
+		local_irq_save(flags);				\
+		lt = this_cpu_ptr(lock);			\
+		if (!READ_ONCE(lt->acquired)) {			\
+			WRITE_ONCE(lt->acquired, 1);		\
+			local_trylock_acquire(&lt->llock);	\
+			_ret = true;				\
+		} else {					\
+			_ret = false;				\
+			local_irq_restore(flags);		\
+		}						\
+		_ret;						\
+	})
+
+#define __localtry_unlock(lock)					\
+	do {							\
+		localtry_lock_t *lt;				\
+		lt = this_cpu_ptr(lock);			\
+		WRITE_ONCE(lt->acquired, 0);			\
+		local_lock_release(&lt->llock);			\
+		preempt_enable();				\
+	} while (0)
+
+#define __localtry_unlock_irq(lock)				\
+	do {							\
+		localtry_lock_t *lt;				\
+		lt = this_cpu_ptr(lock);			\
+		WRITE_ONCE(lt->acquired, 0);			\
+		local_lock_release(&lt->llock);			\
+		local_irq_enable();				\
+	} while (0)
+
+#define __localtry_unlock_irqrestore(lock, flags)		\
+	do {							\
+		localtry_lock_t *lt;				\
+		lt = this_cpu_ptr(lock);			\
+		WRITE_ONCE(lt->acquired, 0);			\
+		local_lock_release(&lt->llock);			\
+		local_irq_restore(flags);			\
+	} while (0)
+
 #else /* !CONFIG_PREEMPT_RT */
 
 /*
  * On PREEMPT_RT local_lock maps to a per CPU spinlock, which protects the
  * critical section while staying preemptible.
  */
 typedef spinlock_t local_lock_t;
+typedef spinlock_t localtry_lock_t;
 
 #define INIT_LOCAL_LOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname))
+#define INIT_LOCALTRY_LOCK(lockname) INIT_LOCAL_LOCK(lockname)
 
 #define __local_lock_init(l)					\
 	do {							\
@@ -169,4 +283,36 @@ do {								\
 	spin_unlock(this_cpu_ptr((lock)));			\
 } while (0)
 
+/* localtry_lock_t variants */
+
+#define __localtry_lock_init(lock)			__local_lock_init(lock)
+#define __localtry_lock(lock)				__local_lock(lock)
+#define __localtry_lock_irq(lock)			__local_lock(lock)
+#define __localtry_lock_irqsave(lock, flags)		__local_lock_irqsave(lock, flags)
+#define __localtry_unlock(lock)				__local_unlock(lock)
+#define __localtry_unlock_irq(lock)			__local_unlock(lock)
+#define __localtry_unlock_irqrestore(lock, flags)	__local_unlock_irqrestore(lock, flags)
+
+#define __localtry_trylock(lock)				\
+	({							\
+		int __locked;					\
+								\
+		if (in_nmi() | in_hardirq()) {			\
+			__locked = 0;				\
+		} else {					\
+			migrate_disable();			\
+			__locked = spin_trylock(this_cpu_ptr((lock)));	\
+			if (!__locked)				\
+				migrate_enable();		\
+		}						\
+		__locked;					\
+	})
+
+#define __localtry_trylock_irqsave(lock, flags)			\
+	({							\
+		typecheck(unsigned long, flags);		\
+		flags = 0;					\
+		__localtry_trylock(lock);			\
+	})
+
 #endif /* CONFIG_PREEMPT_RT */

include/linux/mm_types.h

@@ -99,6 +99,10 @@ struct page {
 				/* Or, free page */
 				struct list_head buddy_list;
 				struct list_head pcp_list;
+				struct {
+					struct llist_node pcp_llist;
+					unsigned int order;
+				};
 			};
 			/* See page-flags.h for PAGE_MAPPING_FLAGS */
 			struct address_space *mapping;

include/linux/mmzone.h

@@ -972,6 +972,9 @@ struct zone {
 	/* Primarily protects free_area */
 	spinlock_t		lock;
 
+	/* Pages to be freed when next trylock succeeds */
+	struct llist_head	trylock_free_pages;
+
 	/* Write-intensive fields used by compaction and vmstats. */
 	CACHELINE_PADDING(_pad2_);
 

kernel/bpf/arena.c

@@ -287,7 +287,7 @@ static vm_fault_t arena_vm_fault(struct vm_fault *vmf)
 		return VM_FAULT_SIGSEGV;
 
 	/* Account into memcg of the process that created bpf_arena */
-	ret = bpf_map_alloc_pages(map, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE, 1, &page);
+	ret = bpf_map_alloc_pages(map, NUMA_NO_NODE, 1, &page);
 	if (ret) {
 		range_tree_set(&arena->rt, vmf->pgoff, 1);
 		return VM_FAULT_SIGSEGV;
@@ -465,8 +465,7 @@ static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt
 	if (ret)
 		goto out_free_pages;
 
-	ret = bpf_map_alloc_pages(&arena->map, GFP_KERNEL | __GFP_ZERO,
-				  node_id, page_cnt, pages);
+	ret = bpf_map_alloc_pages(&arena->map, node_id, page_cnt, pages);
 	if (ret)
 		goto out;