The patch titled Subject: mm/page_alloc.c: fix tick timer stall during deferred page init has been removed from the -mm tree. Its filename was mm-fix-tick-timer-stall-during-deferred-page-init.patch This patch was dropped because an alternative patch was merged ------------------------------------------------------ From: Shile Zhang <shile.zhang@xxxxxxxxxxxxxxxxx> Subject: mm/page_alloc.c: fix tick timer stall during deferred page init When 'CONFIG_DEFERRED_STRUCT_PAGE_INIT' is set, 'pgdatinit' kthread will initialise the deferred pages with local interrupts disabled. It is introduced by commit 3a2d7fa8a3d5 ("mm: disable interrupts while initializing deferred pages"). On machine with NCPUS <= 2, the 'pgdatinit' kthread could be bound to the boot CPU, which could caused the tick timer long time stall, system jiffies not be updated in time. The dmesg shown that: [ 0.197975] node 0 initialised, 32170688 pages in 1ms Obviously, 1ms is unreasonable. Now, fix it by restore in the pending interrupts for every 32*1204 pages (128MB) initialized, give the chance to update the systemd jiffies. The reasonable demsg shown likes: [ 1.069306] node 0 initialised, 32203456 pages in 894ms Link: http://lkml.kernel.org/r/20200311123848.118638-1-shile.zhang@xxxxxxxxxxxxxxxxx Fixes: 3a2d7fa8a3d5 ("mm: disable interrupts while initializing deferred pages") Signed-off-by: Kirill Tkhai <ktkhai@xxxxxxxxxxxxx> Signed-off-by: Shile Zhang <shile.zhang@xxxxxxxxxxxxxxxxx> Co-developed-by: Kirill Tkhai <ktkhai@xxxxxxxxxxxxx> Reviewed-by: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx> Reviewed-by: Daniel Jordan <daniel.m.jordan@xxxxxxxxxx> Acked-by: David Hildenbrand <david@xxxxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxxxxx> Cc: Baoquan He <bhe@xxxxxxxxxx> Cc: Pankaj Gupta <pankaj.gupta.linux@xxxxxxxxx Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/page_alloc.c | 25 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-) --- a/mm/page_alloc.c~mm-fix-tick-timer-stall-during-deferred-page-init +++ a/mm/page_alloc.c @@ -1764,12 +1764,17 @@ deferred_init_maxorder(u64 *i, struct zo return nr_pages; } +/* + * Release the pending interrupts for every TICK_PAGE_COUNT pages. + */ +#define TICK_PAGE_COUNT (32 * 1024) + /* Initialise remaining memory on a node */ 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, nr_pages = 0; + unsigned long spfn = 0, epfn = 0, nr_pages = 0, prev_nr_pages = 0; unsigned long first_init_pfn, flags; unsigned long start = jiffies; struct zone *zone; @@ -1780,6 +1785,7 @@ static int __init deferred_init_memmap(v if (!cpumask_empty(cpumask)) set_cpus_allowed_ptr(current, cpumask); +again: pgdat_resize_lock(pgdat, &flags); first_init_pfn = pgdat->first_deferred_pfn; if (first_init_pfn == ULONG_MAX) { @@ -1791,7 +1797,6 @@ static int __init deferred_init_memmap(v /* Sanity check boundaries */ BUG_ON(pgdat->first_deferred_pfn < pgdat->node_start_pfn); BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat)); - pgdat->first_deferred_pfn = ULONG_MAX; /* Only the highest zone is deferred so find it */ for (zid = 0; zid < MAX_NR_ZONES; zid++) { @@ -1810,9 +1815,23 @@ static int __init deferred_init_memmap(v * that we can avoid introducing any issues with the buddy * allocator. */ - while (spfn < epfn) + while (spfn < epfn) { nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn); + /* + * Release the interrupts for every TICK_PAGE_COUNT pages + * (128MB) to give tick timer the chance to update the + * system jiffies. + */ + if ((nr_pages - prev_nr_pages) > TICK_PAGE_COUNT) { + prev_nr_pages = nr_pages; + pgdat->first_deferred_pfn = spfn; + pgdat_resize_unlock(pgdat, &flags); + goto again; + } + } + zone_empty: + pgdat->first_deferred_pfn = ULONG_MAX; pgdat_resize_unlock(pgdat, &flags); /* Sanity check that the next zone really is unpopulated */ _ Patches currently in -mm which might be from shile.zhang@xxxxxxxxxxxxxxxxx are