vmalloc: align nr_vmalloc_pages and vmap_lazy_nr

Currently both atomics share one cache-line:

<snip>
...
ffffffff83eab400 b vmap_lazy_nr
ffffffff83eab408 b nr_vmalloc_pages
...
<snip>

those are global variables and they are only 8 bytes apart.  Since they
are modified by different threads this causes a false sharing.  This can
lead to a performance drop due to unnecessary cache invalidations.

After this patch it is aligned to a cache line boundary:

<snip>
...
ffffffff8260a600 d vmap_lazy_nr
ffffffff8260a640 d nr_vmalloc_pages
...
<snip>

Link: https://lkml.kernel.org/r/20250417161216.88318-4-urezki@gmail.com
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Reviewed-by: Baoquan He <bhe@redhat.com>
Reviewed-by: Adrian Huang <ahuang12@lenovo.com>
Tested-by: Adrian Huang <ahuang12@lenovo.com>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: Christop Hellwig <hch@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index dc33ebeb8b1bde8d2dbe58aeb1714b5a8992df1c..3fd802134e4eadf3993fc8d2e773dbf17856be61 100644 (file)
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1008,7 +1008,8 @@ static BLOCKING_NOTIFIER_HEAD(vmap_notify_list);
 static void drain_vmap_area_work(struct work_struct *work);
 static DECLARE_WORK(drain_vmap_work, drain_vmap_area_work);
 
-static atomic_long_t nr_vmalloc_pages;
+static __cacheline_aligned_in_smp atomic_long_t nr_vmalloc_pages;
+static __cacheline_aligned_in_smp atomic_long_t vmap_lazy_nr;
 
 unsigned long vmalloc_nr_pages(void)
 {
@@ -2117,8 +2118,6 @@ static unsigned long lazy_max_pages(void)
        return log * (32UL * 1024 * 1024 / PAGE_SIZE);
 }
 
-static atomic_long_t vmap_lazy_nr = ATOMIC_LONG_INIT(0);
-
 /*
  * Serialize vmap purging.  There is no actual critical section protected
  * by this lock, but we want to avoid concurrent calls for performance