summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorPeter Zijlstra <peterz@infradead.org>2025-04-16 18:29:16 +0200
committerPeter Zijlstra <peterz@infradead.org>2025-05-03 12:02:09 +0200
commitcec199c5e39bde7191a08087cc3d002ccfab31ff (patch)
tree762331a79f406043a53d49a423c41ff94f84b797 /kernel
parent63e8595c060a1fef421e3eecfc05ad882dafb8ac (diff)
futex: Implement FUTEX2_NUMA
Extend the futex2 interface to be numa aware. When FUTEX2_NUMA is specified for a futex, the user value is extended to two words (of the same size). The first is the user value we all know, the second one will be the node to place this futex on. struct futex_numa_32 { u32 val; u32 node; }; When node is set to ~0, WAIT will set it to the current node_id such that WAKE knows where to find it. If userspace corrupts the node value between WAIT and WAKE, the futex will not be found and no wakeup will happen. When FUTEX2_NUMA is not set, the node is simply an extension of the hash, such that traditional futexes are still interleaved over the nodes. This is done to avoid having to have a separate !numa hash-table. [bigeasy: ensure to have at least hashsize of 4 in futex_init(), add pr_info() for size and allocation information. Cast the naddr math to void*] 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/20250416162921.513656-17-bigeasy@linutronix.de
Diffstat (limited to 'kernel')
-rw-r--r--kernel/futex/core.c100
-rw-r--r--kernel/futex/futex.h33
2 files changed, 113 insertions, 20 deletions
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 8054fda94719..1490e6492993 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -36,6 +36,8 @@
#include <linux/pagemap.h>
#include <linux/debugfs.h>
#include <linux/plist.h>
+#include <linux/gfp.h>
+#include <linux/vmalloc.h>
#include <linux/memblock.h>
#include <linux/fault-inject.h>
#include <linux/slab.h>
@@ -51,11 +53,14 @@
* reside in the same cacheline.
*/
static struct {
- struct futex_hash_bucket *queues;
unsigned long hashmask;
+ unsigned int hashshift;
+ struct futex_hash_bucket *queues[MAX_NUMNODES];
} __futex_data __read_mostly __aligned(2*sizeof(long));
-#define futex_queues (__futex_data.queues)
-#define futex_hashmask (__futex_data.hashmask)
+
+#define futex_hashmask (__futex_data.hashmask)
+#define futex_hashshift (__futex_data.hashshift)
+#define futex_queues (__futex_data.queues)
struct futex_private_hash {
rcuref_t users;
@@ -339,15 +344,35 @@ __futex_hash(union futex_key *key, struct futex_private_hash *fph)
{
struct futex_hash_bucket *hb;
u32 hash;
+ int node;
hb = __futex_hash_private(key, fph);
if (hb)
return hb;
hash = jhash2((u32 *)key,
- offsetof(typeof(*key), both.offset) / 4,
+ offsetof(typeof(*key), both.offset) / sizeof(u32),
key->both.offset);
- return &futex_queues[hash & futex_hashmask];
+ node = key->both.node;
+
+ if (node == FUTEX_NO_NODE) {
+ /*
+ * In case of !FLAGS_NUMA, use some unused hash bits to pick a
+ * node -- this ensures regular futexes are interleaved across
+ * the nodes and avoids having to allocate multiple
+ * hash-tables.
+ *
+ * NOTE: this isn't perfectly uniform, but it is fast and
+ * handles sparse node masks.
+ */
+ node = (hash >> futex_hashshift) % nr_node_ids;
+ if (!node_possible(node)) {
+ node = find_next_bit_wrap(node_possible_map.bits,
+ nr_node_ids, node);
+ }
+ }
+
+ return &futex_queues[node][hash & futex_hashmask];
}
/**
@@ -454,25 +479,49 @@ int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key,
struct page *page;
struct folio *folio;
struct address_space *mapping;
- int err, ro = 0;
+ int node, err, size, ro = 0;
bool fshared;
fshared = flags & FLAGS_SHARED;
+ size = futex_size(flags);
+ if (flags & FLAGS_NUMA)
+ size *= 2;
/*
* The futex address must be "naturally" aligned.
*/
key->both.offset = address % PAGE_SIZE;
- if (unlikely((address % sizeof(u32)) != 0))
+ if (unlikely((address % size) != 0))
return -EINVAL;
address -= key->both.offset;
- if (unlikely(!access_ok(uaddr, sizeof(u32))))
+ if (unlikely(!access_ok(uaddr, size)))
return -EFAULT;
if (unlikely(should_fail_futex(fshared)))
return -EFAULT;
+ 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)) {
+ return -EINVAL;
+ }
+
+ key->both.node = node;
+
+ } else {
+ key->both.node = FUTEX_NO_NODE;
+ }
+
/*
* PROCESS_PRIVATE futexes are fast.
* As the mm cannot disappear under us and the 'key' only needs
@@ -1642,24 +1691,41 @@ int futex_hash_prctl(unsigned long arg2, unsigned long arg3, unsigned long arg4)
static int __init futex_init(void)
{
unsigned long hashsize, i;
- unsigned int futex_shift;
+ unsigned int order, n;
+ unsigned long size;
#ifdef CONFIG_BASE_SMALL
hashsize = 16;
#else
- hashsize = roundup_pow_of_two(256 * num_possible_cpus());
+ hashsize = 256 * num_possible_cpus();
+ hashsize /= num_possible_nodes();
+ hashsize = max(4, hashsize);
+ hashsize = roundup_pow_of_two(hashsize);
#endif
+ futex_hashshift = ilog2(hashsize);
+ size = sizeof(struct futex_hash_bucket) * hashsize;
+ order = get_order(size);
- futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues),
- hashsize, 0, 0,
- &futex_shift, NULL,
- hashsize, hashsize);
- hashsize = 1UL << futex_shift;
+ for_each_node(n) {
+ struct futex_hash_bucket *table;
- for (i = 0; i < hashsize; i++)
- futex_hash_bucket_init(&futex_queues[i], NULL);
+ if (order > MAX_PAGE_ORDER)
+ table = vmalloc_huge_node(size, GFP_KERNEL, n);
+ else
+ table = alloc_pages_exact_nid(n, size, GFP_KERNEL);
+
+ BUG_ON(!table);
+
+ for (i = 0; i < hashsize; i++)
+ futex_hash_bucket_init(&table[i], NULL);
+
+ futex_queues[n] = table;
+ }
futex_hashmask = hashsize - 1;
+ pr_info("futex hash table entries: %lu (%lu bytes on %d NUMA nodes, total %lu KiB, %s).\n",
+ hashsize, size, num_possible_nodes(), size * num_possible_nodes() / 1024,
+ order > MAX_PAGE_ORDER ? "vmalloc" : "linear");
return 0;
}
core_initcall(futex_init);
diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h
index 899aed5acde1..acc795367889 100644
--- a/kernel/futex/futex.h
+++ b/kernel/futex/futex.h
@@ -54,7 +54,7 @@ static inline unsigned int futex_to_flags(unsigned int op)
return flags;
}
-#define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_PRIVATE)
+#define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_NUMA | FUTEX2_PRIVATE)
/* FUTEX2_ to FLAGS_ */
static inline unsigned int futex2_to_flags(unsigned int flags2)
@@ -87,6 +87,19 @@ static inline bool futex_flags_valid(unsigned int flags)
if ((flags & FLAGS_SIZE_MASK) != FLAGS_SIZE_32)
return false;
+ /*
+ * Must be able to represent both FUTEX_NO_NODE and every valid nodeid
+ * in a futex word.
+ */
+ if (flags & FLAGS_NUMA) {
+ int bits = 8 * futex_size(flags);
+ u64 max = ~0ULL;
+
+ max >>= 64 - bits;
+ if (nr_node_ids >= max)
+ return false;
+ }
+
return true;
}
@@ -282,7 +295,7 @@ static inline int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32
* This looks a bit overkill, but generally just results in a couple
* of instructions.
*/
-static __always_inline int futex_read_inatomic(u32 *dest, u32 __user *from)
+static __always_inline int futex_get_value(u32 *dest, u32 __user *from)
{
u32 val;
@@ -299,12 +312,26 @@ Efault:
return -EFAULT;
}
+static __always_inline int futex_put_value(u32 val, u32 __user *to)
+{
+ if (can_do_masked_user_access())
+ to = masked_user_access_begin(to);
+ else if (!user_read_access_begin(to, sizeof(*to)))
+ return -EFAULT;
+ unsafe_put_user(val, to, Efault);
+ user_read_access_end();
+ return 0;
+Efault:
+ user_read_access_end();
+ return -EFAULT;
+}
+
static inline int futex_get_value_locked(u32 *dest, u32 __user *from)
{
int ret;
pagefault_disable();
- ret = futex_read_inatomic(dest, from);
+ ret = futex_get_value(dest, from);
pagefault_enable();
return ret;