[PATCH] mm/vmalloc: Cache the vmalloc memory info

[Ingo Molnar]

Linus reported that glibc (rather stupidly) reads /proc/meminfo
for every sysinfo() call, which causes the Git build to use
a surprising amount of CPU time, mostly due to the overhead
of get_vmalloc_info() - which walks a long list to do its
statistics.

Modify Linus's jiffies based patch to use generation counters
to cache the vmalloc info: vmap_unlock() increases the generation
counter, and the get_vmalloc_info() reads it and compares it
against a cached generation counter.

Also use a seqlock to make sure we always print a consistent
set of vmalloc statistics.

Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: linux-mm@xxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 mm/vmalloc.c | 59 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 56 insertions(+), 3 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 605138083880..d72b23436906 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -276,7 +276,21 @@ EXPORT_SYMBOL(vmalloc_to_pfn);
 #define VM_LAZY_FREEING	0x02
 #define VM_VM_AREA	0x04
 
-static DEFINE_SPINLOCK(vmap_area_lock);
+static __cacheline_aligned_in_smp DEFINE_SPINLOCK(vmap_area_lock);
+
+#ifdef CONFIG_PROC_FS
+/*
+ * A seqlock and two generation counters for a simple cache of the
+ * vmalloc allocation statistics info printed in /proc/meminfo.
+ *
+ * ( The assumption of the optimization is that it's read frequently, but
+ *   modified infrequently. )
+ */
+static DEFINE_SEQLOCK(vmap_info_lock);
+static u64 vmap_info_gen;
+static u64 vmap_info_cache_gen;
+static struct vmalloc_info vmap_info_cache;
+#endif
 
 static inline void vmap_lock(void)
 {
@@ -285,6 +299,9 @@ static inline void vmap_lock(void)
 
 static inline void vmap_unlock(void)
 {
+#ifdef CONFIG_PROC_FS
+	WRITE_ONCE(vmap_info_gen, vmap_info_gen+1);
+#endif
 	spin_unlock(&vmap_area_lock);
 }
 
@@ -2699,7 +2716,7 @@ static int __init proc_vmalloc_init(void)
 }
 module_init(proc_vmalloc_init);
 
-void get_vmalloc_info(struct vmalloc_info *vmi)
+static void calc_vmalloc_info(struct vmalloc_info *vmi)
 {
 	struct vmap_area *va;
 	unsigned long free_area_size;
@@ -2746,5 +2763,41 @@ void get_vmalloc_info(struct vmalloc_info *vmi)
 out:
 	rcu_read_unlock();
 }
-#endif
 
+/*
+ * Return a consistent snapshot of the current vmalloc allocation
+ * statistics, for /proc/meminfo:
+ */
+void get_vmalloc_info(struct vmalloc_info *vmi)
+{
+	u64 gen = READ_ONCE(vmap_info_gen);
+
+	/*
+	 * If the generation counter of the cache matches that of
+	 * the vmalloc generation counter then return the cache:
+	 */
+	if (READ_ONCE(vmap_info_cache_gen) == gen) {
+		unsigned int seq;
+
+		do {
+			seq = read_seqbegin(&vmap_info_lock);
+			*vmi = vmap_info_cache;
+		} while (read_seqretry(&vmap_info_lock, seq));
+
+		return;
+	}
+
+	calc_vmalloc_info(vmi);
+
+	/*
+	 * If are racing with a new vmalloc() then we might write
+	 * the old generation counter here - and the next call to
+	 * get_vmalloc_info() will fix things up:
+	 */
+	write_seqlock(&vmap_info_lock);
+	vmap_info_cache = *vmi;
+	WRITE_ONCE(vmap_info_cache_gen, gen);
+	write_sequnlock(&vmap_info_lock);
+}
+
+#endif /* CONFIG_PROC_FS */
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/