From 7e8a6304d5419cbf056a59de92939e5eef039c57 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 21 Aug 2018 21:53:58 -0700 Subject: /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/20180807184723.74919-1-dennisszhou@gmail.com Signed-off-by: Dennis Zhou Acked-by: Tejun Heo Acked-by: Roman Gushchin Reviewed-by: Andrew Morton Acked-by: David Rientjes Acked-by: Vlastimil Babka Cc: Johannes Weiner Cc: Christoph Lameter Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/percpu.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'mm') diff --git a/mm/percpu.c b/mm/percpu.c index 0b6480979ac7..a749d4d96e3e 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -169,6 +169,14 @@ static LIST_HEAD(pcpu_map_extend_chunks); */ 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 @@ -1232,6 +1240,7 @@ static void pcpu_chunk_populated(struct pcpu_chunk *chunk, int page_start, bitmap_set(chunk->populated, page_start, nr); chunk->nr_populated += nr; + pcpu_nr_populated += nr; if (!for_alloc) { chunk->nr_empty_pop_pages += nr; @@ -1260,6 +1269,7 @@ static void pcpu_chunk_depopulated(struct pcpu_chunk *chunk, chunk->nr_populated -= nr; chunk->nr_empty_pop_pages -= nr; pcpu_nr_empty_pop_pages -= nr; + pcpu_nr_populated -= nr; } /* @@ -2176,6 +2186,9 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, 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); @@ -2745,6 +2758,22 @@ void __init setup_per_cpu_areas(void) #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 * workqueue is available. Plug async management until everything is up -- cgit v1.2.3