linux-kernel - [PATCH 2/2] fork: group allocation of per-cpu counters for mm struct

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Mon, 21 Aug 2023 22:28:29 +0200
From:   Mateusz Guzik <mjguzik@...il.com>
To:     linux-kernel@...r.kernel.org
Cc:     dennis@...nel.org, tj@...nel.org, cl@...ux.com,
        akpm@...ux-foundation.org, shakeelb@...gle.com, linux-mm@...ck.org,
        Mateusz Guzik <mjguzik@...il.com>
Subject: [PATCH 2/2] fork: group allocation of per-cpu counters for mm struct

A trivial execve scalability test which tries to be very friendly
(statically linked binaries, all separate) is predominantly bottlenecked
by back-to-back per-cpu counter allocations which serialize on global
locks.

Ease the pain by allocating and freeing them in one go.

Bench can be found here:
http://apollo.backplane.com/DFlyMisc/doexec.c

$ cc -static -O2 -o static-doexec doexec.c
$ ./static-doexec $(nproc)

Even at a very modest scale of 26 cores (ops/s):
before:	133543.63
after:	186061.81 (+39%)

While with the patch these allocations remain a significant problem,
the primary bottleneck shifts to:

    __pv_queued_spin_lock_slowpath+1
    _raw_spin_lock_irqsave+57
    folio_lruvec_lock_irqsave+91
    release_pages+590
    tlb_batch_pages_flush+61
    tlb_finish_mmu+101
    exit_mmap+327
    __mmput+61
    begin_new_exec+1245
    load_elf_binary+712
    bprm_execve+644
    do_execveat_common.isra.0+429
    __x64_sys_execve+50
    do_syscall_64+46
    entry_SYSCALL_64_after_hwframe+110

Signed-off-by: Mateusz Guzik <mjguzik@...il.com>
---
 kernel/fork.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index d2e12b6d2b18..86ff78e001c1 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -909,8 +909,6 @@ static void cleanup_lazy_tlbs(struct mm_struct *mm)
  */
 void __mmdrop(struct mm_struct *mm)
 {
-	int i;
-
 	BUG_ON(mm == &init_mm);
 	WARN_ON_ONCE(mm == current->mm);
 
@@ -925,9 +923,8 @@ void __mmdrop(struct mm_struct *mm)
 	put_user_ns(mm->user_ns);
 	mm_pasid_drop(mm);
 	mm_destroy_cid(mm);
+	percpu_counter_destroy_many(mm->rss_stat, NR_MM_COUNTERS);
 
-	for (i = 0; i < NR_MM_COUNTERS; i++)
-		percpu_counter_destroy(&mm->rss_stat[i]);
 	free_mm(mm);
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
@@ -1252,7 +1249,6 @@ static void mm_init_uprobes_state(struct mm_struct *mm)
 static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	struct user_namespace *user_ns)
 {
-	int i;
 
 	mt_init_flags(&mm->mm_mt, MM_MT_FLAGS);
 	mt_set_external_lock(&mm->mm_mt, &mm->mmap_lock);
@@ -1301,17 +1297,14 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	if (mm_alloc_cid(mm))
 		goto fail_cid;
 
-	for (i = 0; i < NR_MM_COUNTERS; i++)
-		if (percpu_counter_init(&mm->rss_stat[i], 0, GFP_KERNEL_ACCOUNT))
-			goto fail_pcpu;
+	if (percpu_counter_init_many(mm->rss_stat, 0, GFP_KERNEL_ACCOUNT, NR_MM_COUNTERS))
+		goto fail_pcpu;
 
 	mm->user_ns = get_user_ns(user_ns);
 	lru_gen_init_mm(mm);
 	return mm;
 
 fail_pcpu:
-	while (i > 0)
-		percpu_counter_destroy(&mm->rss_stat[--i]);
 	mm_destroy_cid(mm);
 fail_cid:
 	destroy_context(mm);
-- 
2.39.2