From 80367ad01d93ac781b0e1df246edaf006928002f Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 16 Apr 2025 18:29:12 +0200 Subject: futex: Add basic infrastructure for local task local hash The futex hash is system wide and shared by all tasks. Each slot is hashed based on futex address and the VMA of the thread. Due to randomized VMAs (and memory allocations) the same logical lock (pointer) can end up in a different hash bucket on each invocation of the application. This in turn means that different applications may share a hash bucket on the first invocation but not on the second and it is not always clear which applications will be involved. This can result in high latency's to acquire the futex_hash_bucket::lock especially if the lock owner is limited to a CPU and can not be effectively PI boosted. Introduce basic infrastructure for process local hash which is shared by all threads of process. This hash will only be used for a PROCESS_PRIVATE FUTEX operation. The hashmap can be allocated via: prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_SET_SLOTS, num); A `num' of 0 means that the global hash is used instead of a private hash. Other values for `num' specify the number of slots for the hash and the number must be power of two, starting with two. The prctl() returns zero on success. This function can only be used before a thread is created. The current status for the private hash can be queried via: num = prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_GET_SLOTS); which return the current number of slots. The value 0 means that the global hash is used. Values greater than 0 indicate the number of slots that are used. A negative number indicates an error. For optimisation, for the private hash jhash2() uses only two arguments the address and the offset. This omits the VMA which is always the same. [peterz: Use 0 for global hash. A bit shuffling and renaming. ] Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20250416162921.513656-13-bigeasy@linutronix.de --- include/uapi/linux/prctl.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 15c18ef4eb11..3b93fb906e3c 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -364,4 +364,9 @@ 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 PR_FUTEX_HASH_GET_SLOTS 2 + #endif /* _LINUX_PRCTL_H */ -- cgit v1.2.3 From 63e8595c060a1fef421e3eecfc05ad882dafb8ac Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 16 Apr 2025 18:29:15 +0200 Subject: futex: Allow to make the private hash immutable My initial testing showed that: perf bench futex hash reported less operations/sec with private hash. After using the same amount of buckets in the private hash as used by the global hash then the operations/sec were about the same. This changed once the private hash became resizable. This feature added an RCU section and reference counting via atomic inc+dec operation into the hot path. The reference counting can be avoided if the private hash is made immutable. Extend PR_FUTEX_HASH_SET_SLOTS by a fourth argument which denotes if the private should be made immutable. Once set (to true) the a further resize is not allowed (same if set to global hash). Add PR_FUTEX_HASH_GET_IMMUTABLE which returns true if the hash can not be changed. Update "perf bench" suite. For comparison, results of "perf bench futex hash -s": - Xeon CPU E5-2650, 2 NUMA nodes, total 32 CPUs: - Before the introducing task local hash shared Averaged 1.487.148 operations/sec (+- 0,53%), total secs = 10 private Averaged 2.192.405 operations/sec (+- 0,07%), total secs = 10 - With the series shared Averaged 1.326.342 operations/sec (+- 0,41%), total secs = 10 -b128 Averaged 141.394 operations/sec (+- 1,15%), total secs = 10 -Ib128 Averaged 851.490 operations/sec (+- 0,67%), total secs = 10 -b8192 Averaged 131.321 operations/sec (+- 2,13%), total secs = 10 -Ib8192 Averaged 1.923.077 operations/sec (+- 0,61%), total secs = 10 128 is the default allocation of hash buckets. 8192 was the previous amount of allocated hash buckets. - Xeon(R) CPU E7-8890 v3, 4 NUMA nodes, total 144 CPUs: - Before the introducing task local hash shared Averaged 1.810.936 operations/sec (+- 0,26%), total secs = 20 private Averaged 2.505.801 operations/sec (+- 0,05%), total secs = 20 - With the series shared Averaged 1.589.002 operations/sec (+- 0,25%), total secs = 20 -b1024 Averaged 42.410 operations/sec (+- 0,20%), total secs = 20 -Ib1024 Averaged 740.638 operations/sec (+- 1,51%), total secs = 20 -b65536 Averaged 48.811 operations/sec (+- 1,35%), total secs = 20 -Ib65536 Averaged 1.963.165 operations/sec (+- 0,18%), total secs = 20 1024 is the default allocation of hash buckets. 65536 was the previous amount of allocated hash buckets. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Acked-by: Shrikanth Hegde Link: https://lore.kernel.org/r/20250416162921.513656-16-bigeasy@linutronix.de --- include/uapi/linux/prctl.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 3b93fb906e3c..43dec6eed559 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -367,6 +367,8 @@ struct prctl_mm_map { /* 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 */ -- cgit v1.2.3 From cec199c5e39bde7191a08087cc3d002ccfab31ff Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Apr 2025 18:29:16 +0200 Subject: 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) Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20250416162921.513656-17-bigeasy@linutronix.de --- include/uapi/linux/futex.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h index d2ee625ea189..6b94da467e70 100644 --- a/include/uapi/linux/futex.h +++ b/include/uapi/linux/futex.h @@ -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 */ -- cgit v1.2.3 From c042c505210dc3453f378df432c10fff3d471bc5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Apr 2025 18:29:17 +0200 Subject: 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) Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20250416162921.513656-18-bigeasy@linutronix.de --- include/uapi/linux/futex.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h index 6b94da467e70..7e2744ec8933 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 */ -- cgit v1.2.3