[tip: locking/futex] futex: Implement FUTEX2_MPOL

["tip-bot2 for Peter Zijlstra" <tip-bot2@linutronix.de>]

The following commit has been merged into the locking/futex branch of tip:

Commit-ID:     c042c505210dc3453f378df432c10fff3d471bc5
Gitweb:        https://git.kernel.org/tip/c042c505210dc3453f378df432c10fff3d471bc5
Author:        Peter Zijlstra <peterz@infradead.org>
AuthorDate:    Wed, 16 Apr 2025 18:29:17 +02:00
Committer:     Peter Zijlstra <peterz@infradead.org>
CommitterDate: Sat, 03 May 2025 12:02:09 +02:00

futex: Implement FUTEX2_MPOL

Extend the futex2 interface to be aware of mempolicy.

When FUTEX2_MPOL is specified and there is a MPOL_PREFERRED or
home_node specified covering the futex address, use that hash-map.

Notably, in this case the futex will go to the global node hashtable,
even if it is a PRIVATE futex.

When FUTEX2_NUMA|FUTEX2_MPOL is specified and the user specified node
value is FUTEX_NO_NODE, the MPOL lookup (as described above) will be
tried first before reverting to setting node to the local node.

[bigeasy: add CONFIG_FUTEX_MPOL, add MPOL to FUTEX2_VALID_MASK, write
the node only to user if FUTEX_NO_NODE was supplied]

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250416162921.513656-18-bigeasy@linutronix.de
---
 include/linux/mmap_lock.h  |   4 +-
 include/uapi/linux/futex.h |   2 +-
 init/Kconfig               |   5 ++-
 kernel/futex/core.c        | 116 +++++++++++++++++++++++++++++++-----
 kernel/futex/futex.h       |   6 +-
 5 files changed, 115 insertions(+), 18 deletions(-)

diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index 4706c67..e0eddfd 100644
--- a/include/linux/mmap_lock.h
+++ b/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);
diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h
index 6b94da4..7e2744e 100644
--- a/include/uapi/linux/futex.h
+++ b/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 */
diff --git a/init/Kconfig b/init/Kconfig
index 4b84da2..b373267 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1704,6 +1704,11 @@ config FUTEX_PRIVATE_HASH
 	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
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 1490e64..19a2c65 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -43,6 +43,8 @@
 #include <linux/slab.h>
 #include <linux/prctl.h>
 #include <linux/rcuref.h>
+#include <linux/mempolicy.h>
+#include <linux/mmap_lock.h>
 
 #include "futex.h"
 #include "../locking/rtmutex_common.h"
@@ -328,6 +330,75 @@ struct futex_hash_bucket *futex_hash(union futex_key *key)
 
 #endif /* CONFIG_FUTEX_PRIVATE_HASH */
 
+#ifdef CONFIG_FUTEX_MPOL
+
+static int __futex_key_to_node(struct mm_struct *mm, unsigned long addr)
+{
+	struct vm_area_struct *vma = vma_lookup(mm, addr);
+	struct mempolicy *mpol;
+	int node = FUTEX_NO_NODE;
+
+	if (!vma)
+		return FUTEX_NO_NODE;
+
+	mpol = vma_policy(vma);
+	if (!mpol)
+		return FUTEX_NO_NODE;
+
+	switch (mpol->mode) {
+	case MPOL_PREFERRED:
+		node = first_node(mpol->nodes);
+		break;
+	case MPOL_PREFERRED_MANY:
+	case MPOL_BIND:
+		if (mpol->home_node != NUMA_NO_NODE)
+			node = mpol->home_node;
+		break;
+	default:
+		break;
+	}
+
+	return node;
+}
+
+static int futex_key_to_node_opt(struct mm_struct *mm, unsigned long addr)
+{
+	int seq, node;
+
+	guard(rcu)();
+
+	if (!mmap_lock_speculate_try_begin(mm, &seq))
+		return -EBUSY;
+
+	node = __futex_key_to_node(mm, addr);
+
+	if (mmap_lock_speculate_retry(mm, seq))
+		return -EAGAIN;
+
+	return node;
+}
+
+static int futex_mpol(struct mm_struct *mm, unsigned long addr)
+{
+	int node;
+
+	node = futex_key_to_node_opt(mm, addr);
+	if (node >= FUTEX_NO_NODE)
+		return node;
+
+	guard(mmap_read_lock)(mm);
+	return __futex_key_to_node(mm, addr);
+}
+
+#else /* !CONFIG_FUTEX_MPOL */
+
+static int futex_mpol(struct mm_struct *mm, unsigned long addr)
+{
+	return FUTEX_NO_NODE;
+}
+
+#endif /* CONFIG_FUTEX_MPOL */
+
 /**
  * __futex_hash - Return the hash bucket
  * @key:	Pointer to the futex key for which the hash is calculated
@@ -342,18 +413,20 @@ struct futex_hash_bucket *futex_hash(union futex_key *key)
 static struct futex_hash_bucket *
 __futex_hash(union futex_key *key, struct futex_private_hash *fph)
 {
-	struct futex_hash_bucket *hb;
+	int node = key->both.node;
 	u32 hash;
-	int node;
 
-	hb = __futex_hash_private(key, fph);
-	if (hb)
-		return hb;
+	if (node == FUTEX_NO_NODE) {
+		struct futex_hash_bucket *hb;
+
+		hb = __futex_hash_private(key, fph);
+		if (hb)
+			return hb;
+	}
 
 	hash = jhash2((u32 *)key,
 		      offsetof(typeof(*key), both.offset) / sizeof(u32),
 		      key->both.offset);
-	node = key->both.node;
 
 	if (node == FUTEX_NO_NODE) {
 		/*
@@ -480,6 +553,7 @@ int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key,
 	struct folio *folio;
 	struct address_space *mapping;
 	int node, err, size, ro = 0;
+	bool node_updated = false;
 	bool fshared;
 
 	fshared = flags & FLAGS_SHARED;
@@ -501,27 +575,37 @@ int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key,
 	if (unlikely(should_fail_futex(fshared)))
 		return -EFAULT;
 
+	node = FUTEX_NO_NODE;
+
 	if (flags & FLAGS_NUMA) {
 		u32 __user *naddr = (void *)uaddr + size / 2;
 
 		if (futex_get_value(&node, naddr))
 			return -EFAULT;
 
-		if (node == FUTEX_NO_NODE) {
-			node = numa_node_id();
-			if (futex_put_value(node, naddr))
-				return -EFAULT;
-
-		} else if (node >= MAX_NUMNODES || !node_possible(node)) {
+		if (node != FUTEX_NO_NODE &&
+		    (node >= MAX_NUMNODES || !node_possible(node)))
 			return -EINVAL;
-		}
+	}
 
-		key->both.node = node;
+	if (node == FUTEX_NO_NODE && (flags & FLAGS_MPOL)) {
+		node = futex_mpol(mm, address);
+		node_updated = true;
+	}
 
-	} else {
-		key->both.node = FUTEX_NO_NODE;
+	if (flags & FLAGS_NUMA) {
+		u32 __user *naddr = (void *)uaddr + size / 2;
+
+		if (node == FUTEX_NO_NODE) {
+			node = numa_node_id();
+			node_updated = true;
+		}
+		if (node_updated && futex_put_value(node, naddr))
+			return -EFAULT;
 	}
 
+	key->both.node = node;
+
 	/*
 	 * PROCESS_PRIVATE futexes are fast.
 	 * As the mm cannot disappear under us and the 'key' only needs
diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h
index acc7953..069fc2a 100644
--- a/kernel/futex/futex.h
+++ b/kernel/futex/futex.h
@@ -39,6 +39,7 @@
 #define FLAGS_HAS_TIMEOUT	0x0040
 #define FLAGS_NUMA		0x0080
 #define FLAGS_STRICT		0x0100
+#define FLAGS_MPOL		0x0200
 
 /* FUTEX_ to FLAGS_ */
 static inline unsigned int futex_to_flags(unsigned int op)
@@ -54,7 +55,7 @@ static inline unsigned int futex_to_flags(unsigned int op)
 	return flags;
 }
 
-#define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_NUMA | FUTEX2_PRIVATE)
+#define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_NUMA | FUTEX2_MPOL | FUTEX2_PRIVATE)
 
 /* FUTEX2_ to FLAGS_ */
 static inline unsigned int futex2_to_flags(unsigned int flags2)
@@ -67,6 +68,9 @@ static inline unsigned int futex2_to_flags(unsigned int flags2)
 	if (flags2 & FUTEX2_NUMA)
 		flags |= FLAGS_NUMA;
 
+	if (flags2 & FUTEX2_MPOL)
+		flags |= FLAGS_MPOL;
+
 	return flags;
 }