From dc2da7b45ffe954a0090f5d0310ed7b0b37d2bd2 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Tue, 29 Dec 2020 15:14:37 -0800 Subject: mm: memmap defer init doesn't work as expected VMware observed a performance regression during memmap init on their platform, and bisected to commit 73a6e474cb376 ("mm: memmap_init: iterate over memblock regions rather that check each PFN") causing it. Before the commit: [0.033176] Normal zone: 1445888 pages used for memmap [0.033176] Normal zone: 89391104 pages, LIFO batch:63 [0.035851] ACPI: PM-Timer IO Port: 0x448 With commit [0.026874] Normal zone: 1445888 pages used for memmap [0.026875] Normal zone: 89391104 pages, LIFO batch:63 [2.028450] ACPI: PM-Timer IO Port: 0x448 The root cause is the current memmap defer init doesn't work as expected. Before, memmap_init_zone() was used to do memmap init of one whole zone, to initialize all low zones of one numa node, but defer memmap init of the last zone in that numa node. However, since commit 73a6e474cb376, function memmap_init() is adapted to iterater over memblock regions inside one zone, then call memmap_init_zone() to do memmap init for each region. E.g, on VMware's system, the memory layout is as below, there are two memory regions in node 2. The current code will mistakenly initialize the whole 1st region [mem 0xab00000000-0xfcffffffff], then do memmap defer to iniatialize only one memmory section on the 2nd region [mem 0x10000000000-0x1033fffffff]. In fact, we only expect to see that there's only one memory section's memmap initialized. That's why more time is costed at the time. [ 0.008842] ACPI: SRAT: Node 0 PXM 0 [mem 0x00000000-0x0009ffff] [ 0.008842] ACPI: SRAT: Node 0 PXM 0 [mem 0x00100000-0xbfffffff] [ 0.008843] ACPI: SRAT: Node 0 PXM 0 [mem 0x100000000-0x55ffffffff] [ 0.008844] ACPI: SRAT: Node 1 PXM 1 [mem 0x5600000000-0xaaffffffff] [ 0.008844] ACPI: SRAT: Node 2 PXM 2 [mem 0xab00000000-0xfcffffffff] [ 0.008845] ACPI: SRAT: Node 2 PXM 2 [mem 0x10000000000-0x1033fffffff] Now, let's add a parameter 'zone_end_pfn' to memmap_init_zone() to pass down the real zone end pfn so that defer_init() can use it to judge whether defer need be taken in zone wide. Link: https://lkml.kernel.org/r/20201223080811.16211-1-bhe@redhat.com Link: https://lkml.kernel.org/r/20201223080811.16211-2-bhe@redhat.com Fixes: commit 73a6e474cb376 ("mm: memmap_init: iterate over memblock regions rather that check each PFN") Signed-off-by: Baoquan He Reported-by: Rahul Gopakumar Reviewed-by: Mike Rapoport Cc: David Hildenbrand Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/mm/init.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 9b5acf8fb092..e76386a3479e 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -536,7 +536,7 @@ virtual_memmap_init(u64 start, u64 end, void *arg) if (map_start < map_end) memmap_init_zone((unsigned long)(map_end - map_start), - args->nid, args->zone, page_to_pfn(map_start), + args->nid, args->zone, page_to_pfn(map_start), page_to_pfn(map_end), MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); return 0; } @@ -546,7 +546,7 @@ memmap_init (unsigned long size, int nid, unsigned long zone, unsigned long start_pfn) { if (!vmem_map) { - memmap_init_zone(size, nid, zone, start_pfn, + memmap_init_zone(size, nid, zone, start_pfn, start_pfn + size, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); } else { struct page *start; -- cgit v1.2.3