Re: [PATCH v12 00/21] futex: Add support task local hash maps, FUTEX2_NUMA and FUTEX2_MPOL

[Sebastian Andrzej Siewior <bigeasy@linutronix.de>]

On 2025-04-16 18:29:00 [+0200], To linux-kernel@vger.kernel.org wrote:
> v11…v12: https://lore.kernel.org/all/20250407155742.968816-1-bigeasy@linutronix.de

A diff excluding the tools/testing/ changes:

diff --git a/include/linux/futex.h b/include/linux/futex.h
index 96c7229856d97..eccc99751bd94 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -109,7 +109,7 @@ 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)
+static inline int futex_hash_prctl(unsigned long arg2, unsigned long arg3, unsigned long arg4)
 {
 	return -EINVAL;
 }
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 44bb9eeb0a9c1..ee1d7182ce0c0 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -551,6 +551,7 @@ 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;
@@ -575,24 +576,29 @@ int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key,
 	node = FUTEX_NO_NODE;
 
 	if (flags & FLAGS_NUMA) {
-		u32 __user *naddr = uaddr + size / 2;
+		u32 __user *naddr = (void *)uaddr + size / 2;
 
 		if (futex_get_value(&node, naddr))
 			return -EFAULT;
 
-		if (node >= MAX_NUMNODES || !node_possible(node))
+		if (node != FUTEX_NO_NODE &&
+		    (node >= MAX_NUMNODES || !node_possible(node)))
 			return -EINVAL;
 	}
 
-	if (node == FUTEX_NO_NODE && (flags & FLAGS_MPOL))
+	if (node == FUTEX_NO_NODE && (flags & FLAGS_MPOL)) {
 		node = futex_mpol(mm, address);
+		node_updated = true;
+	}
 
 	if (flags & FLAGS_NUMA) {
-		u32 __user *naddr = uaddr + size / 2;
+		u32 __user *naddr = (void *)uaddr + size / 2;
 
-		if (node == FUTEX_NO_NODE)
+		if (node == FUTEX_NO_NODE) {
 			node = numa_node_id();
-		if (futex_put_value(node, naddr))
+			node_updated = true;
+		}
+		if (node_updated && futex_put_value(node, naddr))
 			return -EFAULT;
 	}
 
@@ -1573,6 +1579,8 @@ static int futex_hash_allocate(unsigned int hash_slots, unsigned int immutable,
 
 	if (hash_slots && (hash_slots == 1 || !is_power_of_2(hash_slots)))
 		return -EINVAL;
+	if (immutable > 2)
+		return -EINVAL;
 
 	/*
 	 * Once we've disabled the global hash there is no way back.
@@ -1586,7 +1594,7 @@ static int futex_hash_allocate(unsigned int hash_slots, unsigned int immutable,
 		}
 	}
 
-	fph = kvzalloc(struct_size(fph, queues, hash_slots), GFP_KERNEL_ACCOUNT);
+	fph = kvzalloc(struct_size(fph, queues, hash_slots), GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
 	if (!fph)
 		return -ENOMEM;
 
diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h
index 004e4dbee4f93..069fc2a83080d 100644
--- a/kernel/futex/futex.h
+++ b/kernel/futex/futex.h
@@ -55,7 +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)
diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c
index 356e52c17d3c5..dacb2330f1fbc 100644
--- a/kernel/futex/pi.c
+++ b/kernel/futex/pi.c
@@ -993,6 +993,16 @@ int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int tryl
 			goto no_block;
 		}
 
+		/*
+		 * Caution; releasing @hb in-scope. The hb->lock is still locked
+		 * while the reference is dropped. The reference can not be dropped
+		 * after the unlock because if a user initiated resize is in progress
+		 * then we might need to wake him. This can not be done after the
+		 * rt_mutex_pre_schedule() invocation. The hb will remain valid because
+		 * the thread, performing resize, will block on hb->lock during
+		 * the requeue.
+		 */
+		futex_hash_put(no_free_ptr(hb));
 		/*
 		 * Must be done before we enqueue the waiter, here is unfortunately
 		 * under the hb lock, but that *should* work because it does nothing.
@@ -1016,10 +1026,6 @@ int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int tryl
 		 */
 		raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock);
 		spin_unlock(q.lock_ptr);
-		/*
-		 * Caution; releasing @hb in-scope.
-		 */
-		futex_hash_put(no_free_ptr(hb));
 		/*
 		 * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter
 		 * such that futex_unlock_pi() is guaranteed to observe the waiter when
diff --git a/tools/perf/bench/futex.c b/tools/perf/bench/futex.c
index bed3b6e46d109..02ae6c52ba881 100644
--- a/tools/perf/bench/futex.c
+++ b/tools/perf/bench/futex.c
@@ -31,20 +31,25 @@ void futex_print_nbuckets(struct bench_futex_parameters *params)
 	if (params->nbuckets >= 0) {
 		if (ret != params->nbuckets) {
 			if (ret < 0) {
-				printf("Can't query number of buckets: %d/%m\n", ret);
+				printf("Can't query number of buckets: %m\n");
 				err(EXIT_FAILURE, "prctl(PR_FUTEX_HASH)");
 			}
 			printf("Requested number of hash buckets does not currently used.\n");
 			printf("Requested: %d in usage: %d\n", params->nbuckets, ret);
 			err(EXIT_FAILURE, "prctl(PR_FUTEX_HASH)");
 		}
-		ret = prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_GET_IMMUTABLE);
-		if (params->nbuckets == 0)
+		if (params->nbuckets == 0) {
 			ret = asprintf(&futex_hash_mode, "Futex hashing: global hash");
-		else
+		} else {
+			ret = prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_GET_IMMUTABLE);
+			if (ret < 0) {
+				printf("Can't check if the hash is immutable: %m\n");
+				err(EXIT_FAILURE, "prctl(PR_FUTEX_HASH)");
+			}
 			ret = asprintf(&futex_hash_mode, "Futex hashing: %d hash buckets %s",
 				       params->nbuckets,
 				       ret == 1 ? "(immutable)" : "");
+		}
 	} else {
 		if (ret <= 0) {
 			ret = asprintf(&futex_hash_mode, "Futex hashing: global hash");


Sebastian