/proc/meminfo: add percpu populated pages count

Currently, percpu memory only exposes allocation and utilization
information via debugfs. This more or less is only really useful for
understanding the fragmentation and allocation information at a per-chunk
level with a few global counters. This is also gated behind a config.
BPF and cgroup, for example, have seen an increase in use causing
increased use of percpu memory. Let's make it easier for someone to
identify how much memory is being used.

This patch adds the "Percpu" stat to meminfo to more easily look up how
much percpu memory is in use. This number includes the cost for all
allocated backing pages and not just insight at the per a unit, per chunk
level. Metadata is excluded. I think excluding metadata is fair because
the backing memory scales with the numbere of cpus and can quickly
outweigh the metadata. It also makes this calculation light.

Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Dennis Zhou <[e-mail]>
Acked-by: Tejun Heo <[e-mail]>
Acked-by: Roman Gushchin <[e-mail]>
Reviewed-by: Andrew Morton <[e-mail]>
Acked-by: David Rientjes <[e-mail]>
Acked-by: Vlastimil Babka <[e-mail]>
Cc: Johannes Weiner <[e-mail]>
Cc: Christoph Lameter <[e-mail]>
Cc: Alexey Dobriyan <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

Documentation/filesystems/proc.txt

···
 VmallocTotal:   112216 kB
 VmallocUsed:       428 kB
 VmallocChunk:   111088 kB
+Percpu:          62080 kB
 HardwareCorrupted:   0 kB
 AnonHugePages:   49152 kB
 ShmemHugePages:      0 kB
···
 VmallocTotal: total size of vmalloc memory area
  VmallocUsed: amount of vmalloc area which is used
 VmallocChunk: largest contiguous block of vmalloc area which is free
+      Percpu: Memory allocated to the percpu allocator used to back percpu
+              allocations. This stat excludes the cost of metadata.
 
 ..............................................................................
 

fs/proc/meminfo.c

···
 #include <linux/mman.h>
 #include <linux/mmzone.h>
 #include <linux/proc_fs.h>
+#include <linux/percpu.h>
 #include <linux/quicklist.h>
 #include <linux/seq_file.h>
 #include <linux/swap.h>
···
 		   (unsigned long)VMALLOC_TOTAL >> 10);
 	show_val_kb(m, "VmallocUsed:    ", 0ul);
 	show_val_kb(m, "VmallocChunk:   ", 0ul);
+	show_val_kb(m, "Percpu:         ", pcpu_nr_pages());
 
 #ifdef CONFIG_MEMORY_FAILURE
 	seq_printf(m, "HardwareCorrupted: %5lu kB\n",

include/linux/percpu.h

···
 	(typeof(type) __percpu *)__alloc_percpu(sizeof(type),		\
 						__alignof__(type))
 
+extern unsigned long pcpu_nr_pages(void);
+
 #endif /* __LINUX_PERCPU_H */

mm/percpu.c

···
 int pcpu_nr_empty_pop_pages;
 
 /*
+ * The number of populated pages in use by the allocator, protected by
+ * pcpu_lock.  This number is kept per a unit per chunk (i.e. when a page gets
+ * allocated/deallocated, it is allocated/deallocated in all units of a chunk
+ * and increments/decrements this count by 1).
+ */
+static unsigned long pcpu_nr_populated;
+
+/*
  * Balance work is used to populate or destroy chunks asynchronously.  We
  * try to keep the number of populated free pages between
  * PCPU_EMPTY_POP_PAGES_LOW and HIGH for atomic allocations and at most one
···
 
 	bitmap_set(chunk->populated, page_start, nr);
 	chunk->nr_populated += nr;
+	pcpu_nr_populated += nr;
 
 	if (!for_alloc) {
 		chunk->nr_empty_pop_pages += nr;
···
 	chunk->nr_populated -= nr;
 	chunk->nr_empty_pop_pages -= nr;
 	pcpu_nr_empty_pop_pages -= nr;
+	pcpu_nr_populated -= nr;
 }
 
 /*
···
 	pcpu_nr_empty_pop_pages = pcpu_first_chunk->nr_empty_pop_pages;
 	pcpu_chunk_relocate(pcpu_first_chunk, -1);
 
+	/* include all regions of the first chunk */
+	pcpu_nr_populated += PFN_DOWN(size_sum);
+
 	pcpu_stats_chunk_alloc();
 	trace_percpu_create_chunk(base_addr);
 
···
 }
 
 #endif	/* CONFIG_SMP */
+
+/*
+ * pcpu_nr_pages - calculate total number of populated backing pages
+ *
+ * This reflects the number of pages populated to back chunks.  Metadata is
+ * excluded in the number exposed in meminfo as the number of backing pages
+ * scales with the number of cpus and can quickly outweigh the memory used for
+ * metadata.  It also keeps this calculation nice and simple.
+ *
+ * RETURNS:
+ * Total number of populated backing pages in use by the allocator.
+ */
+unsigned long pcpu_nr_pages(void)
+{
+	return pcpu_nr_populated * pcpu_nr_units;
+}
 
 /*
  * Percpu allocator is initialized early during boot when neither slab or