mm/mm_init: deferred_init_memmap: use a job per zone

deferred_init_memmap() loops over free memory ranges and creates a
padata_mt_job for every free range that intersects with the zone being
initialized.

padata_do_multithreaded() then splits every such range to several chunks
and runs a thread that initializes struct pages in that chunk using
deferred_init_memmap_chunk(). The number of threads is limited by amount of
the CPUs on the node (or 1 for memoryless nodes).

Looping through free memory ranges is then repeated in
deferred_init_memmap_chunk() first to find the first range that should be
initialized and then to traverse the ranges until the end of the chunk is
reached.

Remove the loop over free memory regions in deferred_init_memmap() and pass
the entire zone to padata_do_multithreaded() so that it will be divided to
several chunks by the parallelization code.

Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Wei Yang <richard.weiyang@gmail.com>
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>

diff --git a/mm/mm_init.c b/mm/mm_init.c
index e73f313dc375ae095a593f7a326ce9ef64e4ced3..57b256ea9e6c47f9b0b5fc309da4ee5988f11d75 100644 (file)
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -2179,12 +2179,10 @@ static int __init deferred_init_memmap(void *data)
 {
        pg_data_t *pgdat = data;
        const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
-       unsigned long spfn = 0, epfn = 0;
-       unsigned long first_init_pfn, flags;
+       int max_threads = deferred_page_init_max_threads(cpumask);
+       unsigned long first_init_pfn, last_pfn, flags;
        unsigned long start = jiffies;
        struct zone *zone;
-       int max_threads;
-       u64 i = 0;
 
        /* Bind memory initialisation thread to a local node if possible */
        if (!cpumask_empty(cpumask))
@@ -2212,24 +2210,20 @@ static int __init deferred_init_memmap(void *data)
 
        /* Only the highest zone is deferred */
        zone = pgdat->node_zones + pgdat->nr_zones - 1;
-
-       max_threads = deferred_page_init_max_threads(cpumask);
-
-       while (deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, first_init_pfn)) {
-               first_init_pfn = ALIGN(epfn, PAGES_PER_SECTION);
-               struct padata_mt_job job = {
-                       .thread_fn   = deferred_init_memmap_job,
-                       .fn_arg      = zone,
-                       .start       = spfn,
-                       .size        = first_init_pfn - spfn,
-                       .align       = PAGES_PER_SECTION,
-                       .min_chunk   = PAGES_PER_SECTION,
-                       .max_threads = max_threads,
-                       .numa_aware  = false,
-               };
-
-               padata_do_multithreaded(&job);
-       }
+       last_pfn = SECTION_ALIGN_UP(zone_end_pfn(zone));
+
+       struct padata_mt_job job = {
+               .thread_fn   = deferred_init_memmap_job,
+               .fn_arg      = zone,
+               .start       = first_init_pfn,
+               .size        = last_pfn - first_init_pfn,
+               .align       = PAGES_PER_SECTION,
+               .min_chunk   = PAGES_PER_SECTION,
+               .max_threads = max_threads,
+               .numa_aware  = false,
+       };
+
+       padata_do_multithreaded(&job);
 
        /* Sanity check that the next zone really is unpopulated */
        WARN_ON(pgdat->nr_zones < MAX_NR_ZONES && populated_zone(++zone));