lkml.org 
[lkml]   [2019]   [Jul]   [23]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH v12 1/2] mm: page_alloc: introduce memblock_next_valid_pfn() (again) for arm64
Date
From: Jia He <hejianet@gmail.com>

Commit b92df1de5d28 ("mm: page_alloc: skip over regions of invalid pfns
where possible") optimized the loop in memmap_init_zone(). But it causes
possible panic on x86 due to specific memory mapping on x86_64 which will
skip valid pfns as well, so Daniel Vacek reverted it later.

But as suggested by Daniel Vacek, it is fine to using memblock to skip
gaps and finding next valid frame with CONFIG_HAVE_ARCH_PFN_VALID.

Daniel said:
"On arm and arm64, memblock is used by default. But generic version of
pfn_valid() is based on mem sections and memblock_next_valid_pfn() does
not always return the next valid one but skips more resulting in some
valid frames to be skipped (as if they were invalid). And that's why
kernel was eventually crashing on some !arm machines."

Introduce a new config option CONFIG_HAVE_MEMBLOCK_PFN_VALID and only
selected for arm64, using the new config option to guard the
memblock_next_valid_pfn().

This was tested on a HiSilicon Kunpeng920 based ARM64 server, the speedup
is pretty impressive for bootmem_init() at boot:

with 384G memory,
before: 13310ms
after: 1415ms

with 1T memory,
before: 20s
after: 2s

Suggested-by: Daniel Vacek <neelx@redhat.com>
Signed-off-by: Jia He <hejianet@gmail.com>
Signed-off-by: Hanjun Guo <guohanjun@huawei.com>
---
arch/arm64/Kconfig | 1 +
include/linux/mmzone.h | 9 +++++++++
mm/Kconfig | 3 +++
mm/memblock.c | 31 +++++++++++++++++++++++++++++++
mm/page_alloc.c | 4 +++-
5 files changed, 47 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 697ea0510729..058eb26579be 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -893,6 +893,7 @@ config ARCH_FLATMEM_ENABLE

config HAVE_ARCH_PFN_VALID
def_bool y
+ select HAVE_MEMBLOCK_PFN_VALID

config HW_PERF_EVENTS
def_bool y
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 70394cabaf4e..24cb6bdb1759 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1325,6 +1325,10 @@ static inline int pfn_present(unsigned long pfn)
#endif

#define early_pfn_valid(pfn) pfn_valid(pfn)
+#ifdef CONFIG_HAVE_MEMBLOCK_PFN_VALID
+extern unsigned long memblock_next_valid_pfn(unsigned long pfn);
+#define next_valid_pfn(pfn) memblock_next_valid_pfn(pfn)
+#endif
void sparse_init(void);
#else
#define sparse_init() do {} while (0)
@@ -1347,6 +1351,11 @@ struct mminit_pfnnid_cache {
#define early_pfn_valid(pfn) (1)
#endif

+/* fallback to default definitions */
+#ifndef next_valid_pfn
+#define next_valid_pfn(pfn) (pfn + 1)
+#endif
+
void memory_present(int nid, unsigned long start, unsigned long end);

/*
diff --git a/mm/Kconfig b/mm/Kconfig
index f0c76ba47695..c578374b6413 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -132,6 +132,9 @@ config HAVE_MEMBLOCK_NODE_MAP
config HAVE_MEMBLOCK_PHYS_MAP
bool

+config HAVE_MEMBLOCK_PFN_VALID
+ bool
+
config HAVE_GENERIC_GUP
bool

diff --git a/mm/memblock.c b/mm/memblock.c
index 7d4f61ae666a..d57ba51bb9cd 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1251,6 +1251,37 @@ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size,
return 0;
}
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+
+#ifdef CONFIG_HAVE_MEMBLOCK_PFN_VALID
+unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn)
+{
+ struct memblock_type *type = &memblock.memory;
+ unsigned int right = type->cnt;
+ unsigned int mid, left = 0;
+ phys_addr_t addr = PFN_PHYS(++pfn);
+
+ do {
+ mid = (right + left) / 2;
+
+ if (addr < type->regions[mid].base)
+ right = mid;
+ else if (addr >= (type->regions[mid].base +
+ type->regions[mid].size))
+ left = mid + 1;
+ else {
+ /* addr is within the region, so pfn is valid */
+ return pfn;
+ }
+ } while (left < right);
+
+ if (right == type->cnt)
+ return -1UL;
+ else
+ return PHYS_PFN(type->regions[right].base);
+}
+EXPORT_SYMBOL(memblock_next_valid_pfn);
+#endif /* CONFIG_HAVE_MEMBLOCK_PFN_VALID */
+
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/**
* __next_mem_pfn_range_in_zone - iterator for for_each_*_range_in_zone()
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d66bc8abe0af..70933c40380a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5811,8 +5811,10 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
* function. They do not exist on hotplugged memory.
*/
if (context == MEMMAP_EARLY) {
- if (!early_pfn_valid(pfn))
+ if (!early_pfn_valid(pfn)) {
+ pfn = next_valid_pfn(pfn) - 1;
continue;
+ }
if (!early_pfn_in_nid(pfn, nid))
continue;
if (overlap_memmap_init(zone, &pfn))
--
2.19.1
\
 
 \ /
  Last update: 2019-07-23 07:55    [W:0.101 / U:0.984 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site