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

13 files changed, 511 insertions, 44 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index d67490dc3a2b..3f0cc89c0622 100644
--- a/include/linux/bpf.h
+++ b/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,
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 6bb1a5a7a4ae..c9fa6309c903 100644
--- a/include/linux/gfp.h
+++ b/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)
diff --git a/include/linux/local_lock.h b/include/linux/local_lock.h
index 091dc0b6bdfb..1a0bc35839e3 100644
--- a/include/linux/local_lock.h
+++ b/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))
diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h
index 8dd71fbbb6d2..67bd13d142fa 100644
--- a/include/linux/local_lock_internal.h
+++ b/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 {								\
@@ -118,6 +132,104 @@ 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 */
 
 /*
@@ -125,8 +237,10 @@ do {								\
  * 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 */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 0234f14f2aa6..75e8850cec3a 100644
--- a/include/linux/mm_types.h
+++ b/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;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 9540b41894da..e16939553930 100644
--- a/include/linux/mmzone.h
+++ b/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_);
 
diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c
index 647b709d7d77..0d56cea71602 100644
--- a/kernel/bpf/arena.c
+++ b/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;
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 77062799143e..9794446bc8c6 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -569,7 +569,24 @@ static void bpf_map_release_memcg(struct bpf_map *map)
 }
 #endif
 
-int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid,
+static bool can_alloc_pages(void)
+{
+	return preempt_count() == 0 && !irqs_disabled() &&
+		!IS_ENABLED(CONFIG_PREEMPT_RT);
+}
+
+static struct page *__bpf_alloc_page(int nid)
+{
+	if (!can_alloc_pages())
+		return try_alloc_pages(nid, 0);
+
+	return alloc_pages_node(nid,
+				GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT
+				| __GFP_NOWARN,
+				0);
+}
+
+int bpf_map_alloc_pages(const struct bpf_map *map, int nid,
 			unsigned long nr_pages, struct page **pages)
 {
 	unsigned long i, j;
@@ -582,14 +599,14 @@ int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid,
 	old_memcg = set_active_memcg(memcg);
 #endif
 	for (i = 0; i < nr_pages; i++) {
-		pg = alloc_pages_node(nid, gfp | __GFP_ACCOUNT, 0);
+		pg = __bpf_alloc_page(nid);
 
 		if (pg) {
 			pages[i] = pg;
 			continue;
 		}
 		for (j = 0; j < i; j++)
-			__free_page(pages[j]);
+			free_pages_nolock(pages[j], 0);
 		ret = -ENOMEM;
 		break;
 	}
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index 245d5b416699..73d7b50924ef 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -591,7 +591,8 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
 	depot_stack_handle_t handle = 0;
 	struct page *page = NULL;
 	void *prealloc = NULL;
-	bool can_alloc = depot_flags & STACK_DEPOT_FLAG_CAN_ALLOC;
+	bool allow_spin = gfpflags_allow_spinning(alloc_flags);
+	bool can_alloc = (depot_flags & STACK_DEPOT_FLAG_CAN_ALLOC) && allow_spin;
 	unsigned long flags;
 	u32 hash;
 
@@ -630,7 +631,7 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
 			prealloc = page_address(page);
 	}
 
-	if (in_nmi()) {
+	if (in_nmi() || !allow_spin) {
 		/* We can never allocate in NMI context. */
 		WARN_ON_ONCE(can_alloc);
 		/* Best effort; bail if we fail to take the lock. */
@@ -671,7 +672,10 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
 exit:
 	if (prealloc) {
 		/* Stack depot didn't use this memory, free it. */
-		free_pages((unsigned long)prealloc, DEPOT_POOL_ORDER);
+		if (!allow_spin)
+			free_pages_nolock(virt_to_page(prealloc), DEPOT_POOL_ORDER);
+		else
+			free_pages((unsigned long)prealloc, DEPOT_POOL_ORDER);
 	}
 	if (found)
 		handle = found->handle.handle;
diff --git a/mm/internal.h b/mm/internal.h
index 7eb27ab83ed7..8d1bada7323a 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1198,6 +1198,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
 #define ALLOC_NOFRAGMENT	  0x0
 #endif
 #define ALLOC_HIGHATOMIC	0x200 /* Allows access to MIGRATE_HIGHATOMIC */
+#define ALLOC_TRYLOCK		0x400 /* Only use spin_trylock in allocation path */
 #define ALLOC_KSWAPD		0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */
 
 /* Flags that allow allocations below the min watermark. */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a037ec92881d..83c2df73e4b6 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1739,7 +1739,7 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
 }
 
 struct memcg_stock_pcp {
-	local_lock_t stock_lock;
+	localtry_lock_t stock_lock;
 	struct mem_cgroup *cached; /* this never be root cgroup */
 	unsigned int nr_pages;
 
@@ -1754,7 +1754,7 @@ struct memcg_stock_pcp {
 #define FLUSHING_CACHED_CHARGE	0
 };
 static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock) = {
-	.stock_lock = INIT_LOCAL_LOCK(stock_lock),
+	.stock_lock = INIT_LOCALTRY_LOCK(stock_lock),
 };
 static DEFINE_MUTEX(percpu_charge_mutex);
 
@@ -1766,6 +1766,7 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
  * consume_stock: Try to consume stocked charge on this cpu.
  * @memcg: memcg to consume from.
  * @nr_pages: how many pages to charge.
+ * @gfp_mask: allocation mask.
  *
  * The charges will only happen if @memcg matches the current cpu's memcg
  * stock, and at least @nr_pages are available in that stock.  Failure to
@@ -1773,7 +1774,8 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
  *
  * returns true if successful, false otherwise.
  */
-static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
+static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages,
+			  gfp_t gfp_mask)
 {
 	struct memcg_stock_pcp *stock;
 	unsigned int stock_pages;
@@ -1783,7 +1785,11 @@ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 	if (nr_pages > MEMCG_CHARGE_BATCH)
 		return ret;
 
-	local_lock_irqsave(&memcg_stock.stock_lock, flags);
+	if (!localtry_trylock_irqsave(&memcg_stock.stock_lock, flags)) {
+		if (!gfpflags_allow_spinning(gfp_mask))
+			return ret;
+		localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
+	}
 
 	stock = this_cpu_ptr(&memcg_stock);
 	stock_pages = READ_ONCE(stock->nr_pages);
@@ -1792,7 +1798,7 @@ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 		ret = true;
 	}
 
-	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 
 	return ret;
 }
@@ -1831,14 +1837,14 @@ static void drain_local_stock(struct work_struct *dummy)
 	 * drain_stock races is that we always operate on local CPU stock
 	 * here with IRQ disabled
 	 */
-	local_lock_irqsave(&memcg_stock.stock_lock, flags);
+	localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
 	old = drain_obj_stock(stock);
 	drain_stock(stock);
 	clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
 
-	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 	obj_cgroup_put(old);
 }
 
@@ -1868,9 +1874,20 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
 	unsigned long flags;
 
-	local_lock_irqsave(&memcg_stock.stock_lock, flags);
+	if (!localtry_trylock_irqsave(&memcg_stock.stock_lock, flags)) {
+		/*
+		 * In case of unlikely failure to lock percpu stock_lock
+		 * uncharge memcg directly.
+		 */
+		if (mem_cgroup_is_root(memcg))
+			return;
+		page_counter_uncharge(&memcg->memory, nr_pages);
+		if (do_memsw_account())
+			page_counter_uncharge(&memcg->memsw, nr_pages);
+		return;
+	}
 	__refill_stock(memcg, nr_pages);
-	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 }
 
 /*
@@ -1927,9 +1944,9 @@ static int memcg_hotplug_cpu_dead(unsigned int cpu)
 	stock = &per_cpu(memcg_stock, cpu);
 
 	/* drain_obj_stock requires stock_lock */
-	local_lock_irqsave(&memcg_stock.stock_lock, flags);
+	localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
 	old = drain_obj_stock(stock);
-	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 
 	drain_stock(stock);
 	obj_cgroup_put(old);
@@ -2222,9 +2239,13 @@ int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	unsigned long pflags;
 
 retry:
-	if (consume_stock(memcg, nr_pages))
+	if (consume_stock(memcg, nr_pages, gfp_mask))
 		return 0;
 
+	if (!gfpflags_allow_spinning(gfp_mask))
+		/* Avoid the refill and flush of the older stock */
+		batch = nr_pages;
+
 	if (!do_memsw_account() ||
 	    page_counter_try_charge(&memcg->memsw, batch, &counter)) {
 		if (page_counter_try_charge(&memcg->memory, batch, &counter))
@@ -2708,7 +2729,7 @@ static void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
 	unsigned long flags;
 	int *bytes;
 
-	local_lock_irqsave(&memcg_stock.stock_lock, flags);
+	localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
 	stock = this_cpu_ptr(&memcg_stock);
 
 	/*
@@ -2761,7 +2782,7 @@ static void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
 	if (nr)
 		__mod_objcg_mlstate(objcg, pgdat, idx, nr);
 
-	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 	obj_cgroup_put(old);
 }
 
@@ -2771,7 +2792,7 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
 	unsigned long flags;
 	bool ret = false;
 
-	local_lock_irqsave(&memcg_stock.stock_lock, flags);
+	localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
 	if (objcg == READ_ONCE(stock->cached_objcg) && stock->nr_bytes >= nr_bytes) {
@@ -2779,7 +2800,7 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
 		ret = true;
 	}
 
-	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 
 	return ret;
 }
@@ -2871,7 +2892,7 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
 	unsigned long flags;
 	unsigned int nr_pages = 0;
 
-	local_lock_irqsave(&memcg_stock.stock_lock, flags);
+	localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
 	if (READ_ONCE(stock->cached_objcg) != objcg) { /* reset if necessary */
@@ -2889,7 +2910,7 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
 		stock->nr_bytes &= (PAGE_SIZE - 1);
 	}
 
-	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 	obj_cgroup_put(old);
 
 	if (nr_pages)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 542d25f77be8..e3ea5bf5c459 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -88,6 +88,9 @@ typedef int __bitwise fpi_t;
  */
 #define FPI_TO_TAIL		((__force fpi_t)BIT(1))
 
+/* Free the page without taking locks. Rely on trylock only. */
+#define FPI_TRYLOCK		((__force fpi_t)BIT(2))
+
 /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
 static DEFINE_MUTEX(pcp_batch_high_lock);
 #define MIN_PERCPU_PAGELIST_HIGH_FRACTION (8)
@@ -1249,13 +1252,44 @@ static void split_large_buddy(struct zone *zone, struct page *page,
 	} while (1);
 }
 
+static void add_page_to_zone_llist(struct zone *zone, struct page *page,
+				   unsigned int order)
+{
+	/* Remember the order */
+	page->order = order;
+	/* Add the page to the free list */
+	llist_add(&page->pcp_llist, &zone->trylock_free_pages);
+}
+
 static void free_one_page(struct zone *zone, struct page *page,
 			  unsigned long pfn, unsigned int order,
 			  fpi_t fpi_flags)
 {
+	struct llist_head *llhead;
 	unsigned long flags;
 
-	spin_lock_irqsave(&zone->lock, flags);
+	if (!spin_trylock_irqsave(&zone->lock, flags)) {
+		if (unlikely(fpi_flags & FPI_TRYLOCK)) {
+			add_page_to_zone_llist(zone, page, order);
+			return;
+		}
+		spin_lock_irqsave(&zone->lock, flags);
+	}
+
+	/* The lock succeeded. Process deferred pages. */
+	llhead = &zone->trylock_free_pages;
+	if (unlikely(!llist_empty(llhead) && !(fpi_flags & FPI_TRYLOCK))) {
+		struct llist_node *llnode;
+		struct page *p, *tmp;
+
+		llnode = llist_del_all(llhead);
+		llist_for_each_entry_safe(p, tmp, llnode, pcp_llist) {
+			unsigned int p_order = p->order;
+
+			split_large_buddy(zone, p, page_to_pfn(p), p_order, fpi_flags);
+			__count_vm_events(PGFREE, 1 << p_order);
+		}
+	}
 	split_large_buddy(zone, page, pfn, order, fpi_flags);
 	spin_unlock_irqrestore(&zone->lock, flags);
 
@@ -2307,7 +2341,11 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 	unsigned long flags;
 	int i;
 
-	spin_lock_irqsave(&zone->lock, flags);
+	if (!spin_trylock_irqsave(&zone->lock, flags)) {
+		if (unlikely(alloc_flags & ALLOC_TRYLOCK))
+			return 0;
+		spin_lock_irqsave(&zone->lock, flags);
+	}
 	for (i = 0; i < count; ++i) {
 		struct page *page = __rmqueue(zone, order, migratetype,
 								alloc_flags);
@@ -2595,7 +2633,7 @@ static int nr_pcp_high(struct per_cpu_pages *pcp, struct zone *zone,
 
 static void free_frozen_page_commit(struct zone *zone,
 		struct per_cpu_pages *pcp, struct page *page, int migratetype,
-		unsigned int order)
+		unsigned int order, fpi_t fpi_flags)
 {
 	int high, batch;
 	int pindex;
@@ -2630,6 +2668,14 @@ static void free_frozen_page_commit(struct zone *zone,
 	}
 	if (pcp->free_count < (batch << CONFIG_PCP_BATCH_SCALE_MAX))
 		pcp->free_count += (1 << order);
+
+	if (unlikely(fpi_flags & FPI_TRYLOCK)) {
+		/*
+		 * Do not attempt to take a zone lock. Let pcp->count get
+		 * over high mark temporarily.
+		 */
+		return;
+	}
 	high = nr_pcp_high(pcp, zone, batch, free_high);
 	if (pcp->count >= high) {
 		free_pcppages_bulk(zone, nr_pcp_free(pcp, batch, high, free_high),
@@ -2644,7 +2690,8 @@ static void free_frozen_page_commit(struct zone *zone,
 /*
  * Free a pcp page
  */
-void free_frozen_pages(struct page *page, unsigned int order)
+static void __free_frozen_pages(struct page *page, unsigned int order,
+				fpi_t fpi_flags)
 {
 	unsigned long __maybe_unused UP_flags;
 	struct per_cpu_pages *pcp;
@@ -2653,7 +2700,7 @@ void free_frozen_pages(struct page *page, unsigned int order)
 	int migratetype;
 
 	if (!pcp_allowed_order(order)) {
-		__free_pages_ok(page, order, FPI_NONE);
+		__free_pages_ok(page, order, fpi_flags);
 		return;
 	}
 
@@ -2671,23 +2718,33 @@ void free_frozen_pages(struct page *page, unsigned int order)
 	migratetype = get_pfnblock_migratetype(page, pfn);
 	if (unlikely(migratetype >= MIGRATE_PCPTYPES)) {
 		if (unlikely(is_migrate_isolate(migratetype))) {
-			free_one_page(zone, page, pfn, order, FPI_NONE);
+			free_one_page(zone, page, pfn, order, fpi_flags);
 			return;
 		}
 		migratetype = MIGRATE_MOVABLE;
 	}
 
+	if (unlikely((fpi_flags & FPI_TRYLOCK) && IS_ENABLED(CONFIG_PREEMPT_RT)
+		     && (in_nmi() || in_hardirq()))) {
+		add_page_to_zone_llist(zone, page, order);
+		return;
+	}
 	pcp_trylock_prepare(UP_flags);
 	pcp = pcp_spin_trylock(zone->per_cpu_pageset);
 	if (pcp) {
-		free_frozen_page_commit(zone, pcp, page, migratetype, order);
+		free_frozen_page_commit(zone, pcp, page, migratetype, order, fpi_flags);
 		pcp_spin_unlock(pcp);
 	} else {
-		free_one_page(zone, page, pfn, order, FPI_NONE);
+		free_one_page(zone, page, pfn, order, fpi_flags);
 	}
 	pcp_trylock_finish(UP_flags);
 }
 
+void free_frozen_pages(struct page *page, unsigned int order)
+{
+	__free_frozen_pages(page, order, FPI_NONE);
+}
+
 /*
  * Free a batch of folios
  */
@@ -2776,7 +2833,7 @@ void free_unref_folios(struct folio_batch *folios)
 
 		trace_mm_page_free_batched(&folio->page);
 		free_frozen_page_commit(zone, pcp, &folio->page, migratetype,
-				order);
+					order, FPI_NONE);
 	}
 
 	if (pcp) {
@@ -2907,7 +2964,11 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone,
 
 	do {
 		page = NULL;
-		spin_lock_irqsave(&zone->lock, flags);
+		if (!spin_trylock_irqsave(&zone->lock, flags)) {
+			if (unlikely(alloc_flags & ALLOC_TRYLOCK))
+				return NULL;
+			spin_lock_irqsave(&zone->lock, flags);
+		}
 		if (alloc_flags & ALLOC_HIGHATOMIC)
 			page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
 		if (!page) {
@@ -4512,7 +4573,12 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
 
 	might_alloc(gfp_mask);
 
-	if (should_fail_alloc_page(gfp_mask, order))
+	/*
+	 * Don't invoke should_fail logic, since it may call
+	 * get_random_u32() and printk() which need to spin_lock.
+	 */
+	if (!(*alloc_flags & ALLOC_TRYLOCK) &&
+	    should_fail_alloc_page(gfp_mask, order))
 		return false;
 
 	*alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, *alloc_flags);
@@ -4810,9 +4876,10 @@ unsigned long get_zeroed_page_noprof(gfp_t gfp_mask)
 EXPORT_SYMBOL(get_zeroed_page_noprof);
 
 /**
- * __free_pages - Free pages allocated with alloc_pages().
+ * ___free_pages - Free pages allocated with alloc_pages().
  * @page: The page pointer returned from alloc_pages().
  * @order: The order of the allocation.
+ * @fpi_flags: Free Page Internal flags.
  *
  * This function can free multi-page allocations that are not compound
  * pages.  It does not check that the @order passed in matches that of
@@ -4829,22 +4896,37 @@ EXPORT_SYMBOL(get_zeroed_page_noprof);
  * Context: May be called in interrupt context or while holding a normal
  * spinlock, but not in NMI context or while holding a raw spinlock.
  */
-void __free_pages(struct page *page, unsigned int order)
+static void ___free_pages(struct page *page, unsigned int order,
+			  fpi_t fpi_flags)
 {
 	/* get PageHead before we drop reference */
 	int head = PageHead(page);
 	struct alloc_tag *tag = pgalloc_tag_get(page);
 
 	if (put_page_testzero(page))
-		free_frozen_pages(page, order);
+		__free_frozen_pages(page, order, fpi_flags);
 	else if (!head) {
 		pgalloc_tag_sub_pages(tag, (1 << order) - 1);
 		while (order-- > 0)
-			free_frozen_pages(page + (1 << order), order);
+			__free_frozen_pages(page + (1 << order), order,
+					    fpi_flags);
 	}
 }
+void __free_pages(struct page *page, unsigned int order)
+{
+	___free_pages(page, order, FPI_NONE);
+}
 EXPORT_SYMBOL(__free_pages);
 
+/*
+ * Can be called while holding raw_spin_lock or from IRQ and NMI for any
+ * page type (not only those that came from try_alloc_pages)
+ */
+void free_pages_nolock(struct page *page, unsigned int order)
+{
+	___free_pages(page, order, FPI_TRYLOCK);
+}
+
 void free_pages(unsigned long addr, unsigned int order)
 {
 	if (addr != 0) {
@@ -7081,3 +7163,94 @@ static bool __free_unaccepted(struct page *page)
 }
 
 #endif /* CONFIG_UNACCEPTED_MEMORY */
+
+/**
+ * try_alloc_pages - opportunistic reentrant allocation from any context
+ * @nid: node to allocate from
+ * @order: allocation order size
+ *
+ * Allocates pages of a given order from the given node. This is safe to
+ * call from any context (from atomic, NMI, and also reentrant
+ * allocator -> tracepoint -> try_alloc_pages_noprof).
+ * Allocation is best effort and to be expected to fail easily so nobody should
+ * rely on the success. Failures are not reported via warn_alloc().
+ * See always fail conditions below.
+ *
+ * Return: allocated page or NULL on failure.
+ */
+struct page *try_alloc_pages_noprof(int nid, unsigned int order)
+{
+	/*
+	 * Do not specify __GFP_DIRECT_RECLAIM, since direct claim is not allowed.
+	 * Do not specify __GFP_KSWAPD_RECLAIM either, since wake up of kswapd
+	 * is not safe in arbitrary context.
+	 *
+	 * These two are the conditions for gfpflags_allow_spinning() being true.
+	 *
+	 * Specify __GFP_NOWARN since failing try_alloc_pages() is not a reason
+	 * to warn. Also warn would trigger printk() which is unsafe from
+	 * various contexts. We cannot use printk_deferred_enter() to mitigate,
+	 * since the running context is unknown.
+	 *
+	 * Specify __GFP_ZERO to make sure that call to kmsan_alloc_page() below
+	 * is safe in any context. Also zeroing the page is mandatory for
+	 * BPF use cases.
+	 *
+	 * Though __GFP_NOMEMALLOC is not checked in the code path below,
+	 * specify it here to highlight that try_alloc_pages()
+	 * doesn't want to deplete reserves.
+	 */
+	gfp_t alloc_gfp = __GFP_NOWARN | __GFP_ZERO | __GFP_NOMEMALLOC
+			| __GFP_ACCOUNT;
+	unsigned int alloc_flags = ALLOC_TRYLOCK;
+	struct alloc_context ac = { };
+	struct page *page;
+
+	/*
+	 * In PREEMPT_RT spin_trylock() will call raw_spin_lock() which is
+	 * unsafe in NMI. If spin_trylock() is called from hard IRQ the current
+	 * task may be waiting for one rt_spin_lock, but rt_spin_trylock() will
+	 * mark the task as the owner of another rt_spin_lock which will
+	 * confuse PI logic, so return immediately if called form hard IRQ or
+	 * NMI.
+	 *
+	 * Note, irqs_disabled() case is ok. This function can be called
+	 * from raw_spin_lock_irqsave region.
+	 */
+	if (IS_ENABLED(CONFIG_PREEMPT_RT) && (in_nmi() || in_hardirq()))
+		return NULL;
+	if (!pcp_allowed_order(order))
+		return NULL;
+
+#ifdef CONFIG_UNACCEPTED_MEMORY
+	/* Bailout, since try_to_accept_memory_one() needs to take a lock */
+	if (has_unaccepted_memory())
+		return NULL;
+#endif
+	/* Bailout, since _deferred_grow_zone() needs to take a lock */
+	if (deferred_pages_enabled())
+		return NULL;
+
+	if (nid == NUMA_NO_NODE)
+		nid = numa_node_id();
+
+	prepare_alloc_pages(alloc_gfp, order, nid, NULL, &ac,
+			    &alloc_gfp, &alloc_flags);
+
+	/*
+	 * Best effort allocation from percpu free list.
+	 * If it's empty attempt to spin_trylock zone->lock.
+	 */
+	page = get_page_from_freelist(alloc_gfp, order, alloc_flags, &ac);
+
+	/* Unlike regular alloc_pages() there is no __alloc_pages_slowpath(). */
+
+	if (memcg_kmem_online() && page &&
+	    unlikely(__memcg_kmem_charge_page(page, alloc_gfp, order) != 0)) {
+		free_pages_nolock(page, order);
+		page = NULL;
+	}
+	trace_mm_page_alloc(page, order, alloc_gfp, ac.migratetype);
+	kmsan_alloc_page(page, order, alloc_gfp);
+	return page;
+}
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 2d6360eaccbb..90e31d0e3ed7 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -294,7 +294,13 @@ void __reset_page_owner(struct page *page, unsigned short order)
 	page_owner = get_page_owner(page_ext);
 	alloc_handle = page_owner->handle;
 
-	handle = save_stack(GFP_NOWAIT | __GFP_NOWARN);
+	/*
+	 * Do not specify GFP_NOWAIT to make gfpflags_allow_spinning() == false
+	 * to prevent issues in stack_depot_save().
+	 * This is similar to try_alloc_pages() gfp flags, but only used
+	 * to signal stack_depot to avoid spin_locks.
+	 */
+	handle = save_stack(__GFP_NOWARN);
 	__update_page_owner_free_handle(page_ext, handle, order, current->pid,
 					current->tgid, free_ts_nsec);
 	page_ext_put(page_ext);