Merge branch 'locking/futex' into locking/core, to pick up pending futex changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

Author: Ingo Molnar

include/linux/futex.h

@@ -4,11 +4,11 @@
 
 #include <linux/sched.h>
 #include <linux/ktime.h>
+#include <linux/mm_types.h>
 
 #include <uapi/linux/futex.h>
 
 struct inode;
-struct mm_struct;
 struct task_struct;
 
 /*
@@ -34,6 +34,7 @@ union futex_key {
 		u64 i_seq;
 		unsigned long pgoff;
 		unsigned int offset;
+		/* unsigned int node; */
 	} shared;
 	struct {
 		union {
@@ -42,11 +43,13 @@ union futex_key {
 		};
 		unsigned long address;
 		unsigned int offset;
+		/* unsigned int node; */
 	} private;
 	struct {
 		u64 ptr;
 		unsigned long word;
 		unsigned int offset;
+		unsigned int node;	/* NOT hashed! */
 	} both;
 };
 
@@ -77,7 +80,25 @@ void futex_exec_release(struct task_struct *tsk);
 
 long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 	      u32 __user *uaddr2, u32 val2, u32 val3);
-#else
+int futex_hash_prctl(unsigned long arg2, unsigned long arg3, unsigned long arg4);
+
+#ifdef CONFIG_FUTEX_PRIVATE_HASH
+int futex_hash_allocate_default(void);
+void futex_hash_free(struct mm_struct *mm);
+
+static inline void futex_mm_init(struct mm_struct *mm)
+{
+	RCU_INIT_POINTER(mm->futex_phash, NULL);
+	mutex_init(&mm->futex_hash_lock);
+}
+
+#else /* !CONFIG_FUTEX_PRIVATE_HASH */
+static inline int futex_hash_allocate_default(void) { return 0; }
+static inline void futex_hash_free(struct mm_struct *mm) { }
+static inline void futex_mm_init(struct mm_struct *mm) { }
+#endif /* CONFIG_FUTEX_PRIVATE_HASH */
+
+#else /* !CONFIG_FUTEX */
 static inline void futex_init_task(struct task_struct *tsk) { }
 static inline void futex_exit_recursive(struct task_struct *tsk) { }
 static inline void futex_exit_release(struct task_struct *tsk) { }
@@ -88,6 +109,17 @@ static inline long do_futex(u32 __user *uaddr, int op, u32 val,
 {
 	return -EINVAL;
 }
+static inline int futex_hash_prctl(unsigned long arg2, unsigned long arg3, unsigned long arg4)
+{
+	return -EINVAL;
+}
+static inline int futex_hash_allocate_default(void)
+{
+	return 0;
+}
+static inline void futex_hash_free(struct mm_struct *mm) { }
+static inline void futex_mm_init(struct mm_struct *mm) { }
+
 #endif
 
 #endif

include/linux/mm_types.h

@@ -31,6 +31,7 @@
 #define INIT_PASID	0
 
 struct address_space;
+struct futex_private_hash;
 struct mem_cgroup;
 
 /*
@@ -1031,7 +1032,11 @@ struct mm_struct {
 		 */
 		seqcount_t mm_lock_seq;
 #endif
-
+#ifdef CONFIG_FUTEX_PRIVATE_HASH
+		struct mutex			futex_hash_lock;
+		struct futex_private_hash	__rcu *futex_phash;
+		struct futex_private_hash	*futex_phash_new;
+#endif
 
 		unsigned long hiwater_rss; /* High-watermark of RSS usage */
 		unsigned long hiwater_vm;  /* High-water virtual memory usage */

include/linux/mmap_lock.h

@@ -7,6 +7,7 @@
 #include <linux/rwsem.h>
 #include <linux/tracepoint-defs.h>
 #include <linux/types.h>
+#include <linux/cleanup.h>
 
 #define MMAP_LOCK_INITIALIZER(name) \
 	.mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock),
@@ -211,6 +212,9 @@ static inline void mmap_read_unlock(struct mm_struct *mm)
 	up_read(&mm->mmap_lock);
 }
 
+DEFINE_GUARD(mmap_read_lock, struct mm_struct *,
+	     mmap_read_lock(_T), mmap_read_unlock(_T))
+
 static inline void mmap_read_unlock_non_owner(struct mm_struct *mm)
 {
 	__mmap_lock_trace_released(mm, false);

include/linux/rcuref.h

@@ -30,7 +30,11 @@ static inline void rcuref_init(rcuref_t *ref, unsigned int cnt)
  * rcuref_read - Read the number of held reference counts of a rcuref
  * @ref:	Pointer to the reference count
  *
- * Return: The number of held references (0 ... N)
+ * Return: The number of held references (0 ... N). The value 0 does not
+ * indicate that it is safe to schedule the object, protected by this reference
+ * counter, for deconstruction.
+ * If you want to know if the reference counter has been marked DEAD (as
+ * signaled by rcuref_put()) please use rcuread_is_dead().
  */
 static inline unsigned int rcuref_read(rcuref_t *ref)
 {
@@ -40,6 +44,22 @@ static inline unsigned int rcuref_read(rcuref_t *ref)
 	return c >= RCUREF_RELEASED ? 0 : c + 1;
 }
 
+/**
+ * rcuref_is_dead -	Check if the rcuref has been already marked dead
+ * @ref:		Pointer to the reference count
+ *
+ * Return: True if the object has been marked DEAD. This signals that a previous
+ * invocation of rcuref_put() returned true on this reference counter meaning
+ * the protected object can safely be scheduled for deconstruction.
+ * Otherwise, returns false.
+ */
+static inline bool rcuref_is_dead(rcuref_t *ref)
+{
+	unsigned int c = atomic_read(&ref->refcnt);
+
+	return (c >= RCUREF_RELEASED) && (c < RCUREF_NOREF);
+}
+
 extern __must_check bool rcuref_get_slowpath(rcuref_t *ref);
 
 /**

include/linux/restart_block.h

@@ -26,7 +26,7 @@ struct restart_block {
 	unsigned long arch_data;
 	long (*fn)(struct restart_block *);
 	union {
-		/* For futex_wait and futex_wait_requeue_pi */
+		/* For futex_wait() */
 		struct {
 			u32 __user *uaddr;
 			u32 val;

include/linux/vmalloc.h

@@ -168,8 +168,13 @@ void *__vmalloc_node_noprof(unsigned long size, unsigned long align, gfp_t gfp_m
 		int node, const void *caller) __alloc_size(1);
 #define __vmalloc_node(...)	alloc_hooks(__vmalloc_node_noprof(__VA_ARGS__))
 
-void *vmalloc_huge_noprof(unsigned long size, gfp_t gfp_mask) __alloc_size(1);
-#define vmalloc_huge(...)	alloc_hooks(vmalloc_huge_noprof(__VA_ARGS__))
+void *vmalloc_huge_node_noprof(unsigned long size, gfp_t gfp_mask, int node) __alloc_size(1);
+#define vmalloc_huge_node(...)	alloc_hooks(vmalloc_huge_node_noprof(__VA_ARGS__))
+
+static inline void *vmalloc_huge(unsigned long size, gfp_t gfp_mask)
+{
+	return vmalloc_huge_node(size, gfp_mask, NUMA_NO_NODE);
+}
 
 extern void *__vmalloc_array_noprof(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2);
 #define __vmalloc_array(...)	alloc_hooks(__vmalloc_array_noprof(__VA_ARGS__))

include/uapi/linux/futex.h

@@ -63,7 +63,7 @@
 #define FUTEX2_SIZE_U32		0x02
 #define FUTEX2_SIZE_U64		0x03
 #define FUTEX2_NUMA		0x04
-			/*	0x08 */
+#define FUTEX2_MPOL		0x08
 			/*	0x10 */
 			/*	0x20 */
 			/*	0x40 */
@@ -74,6 +74,13 @@
 /* do not use */
 #define FUTEX_32		FUTEX2_SIZE_U32 /* historical accident :-( */
 
+/*
+ * When FUTEX2_NUMA doubles the futex word, the second word is a node value.
+ * The special value -1 indicates no-node. This is the same value as
+ * NUMA_NO_NODE, except that value is not ABI, this is.
+ */
+#define FUTEX_NO_NODE		(-1)
+
 /*
  * Max numbers of elements in a futex_waitv array
  */

include/uapi/linux/prctl.h

@@ -364,4 +364,11 @@ struct prctl_mm_map {
 # define PR_TIMER_CREATE_RESTORE_IDS_ON		1
 # define PR_TIMER_CREATE_RESTORE_IDS_GET	2
 
+/* FUTEX hash management */
+#define PR_FUTEX_HASH			78
+# define PR_FUTEX_HASH_SET_SLOTS	1
+# define FH_FLAG_IMMUTABLE		(1ULL << 0)
+# define PR_FUTEX_HASH_GET_SLOTS	2
+# define PR_FUTEX_HASH_GET_IMMUTABLE	3
+
 #endif /* _LINUX_PRCTL_H */

init/Kconfig

@@ -1699,6 +1699,16 @@ config FUTEX_PI
 	depends on FUTEX && RT_MUTEXES
 	default y
 
+config FUTEX_PRIVATE_HASH
+	bool
+	depends on FUTEX && !BASE_SMALL && MMU
+	default y
+
+config FUTEX_MPOL
+	bool
+	depends on FUTEX && NUMA
+	default y
+
 config EPOLL
 	bool "Enable eventpoll support" if EXPERT
 	default y

io_uring/futex.c

@@ -273,7 +273,6 @@ int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags)
 	struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);
 	struct io_ring_ctx *ctx = req->ctx;
 	struct io_futex_data *ifd = NULL;
-	struct futex_hash_bucket *hb;
 	int ret;
 
 	if (!iof->futex_mask) {
@@ -295,12 +294,11 @@ int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags)
 	ifd->req = req;
 
 	ret = futex_wait_setup(iof->uaddr, iof->futex_val, iof->futex_flags,
-			       &ifd->q, &hb);
+			       &ifd->q, NULL, NULL);
 	if (!ret) {
 		hlist_add_head(&req->hash_node, &ctx->futex_list);
 		io_ring_submit_unlock(ctx, issue_flags);
 
-		futex_queue(&ifd->q, hb, NULL);
 		return IOU_ISSUE_SKIP_COMPLETE;
 	}