lkml.org 
[lkml]   [2018]   [Mar]   [30]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH v4 2/5] arm: arm64: page_alloc: reduce unnecessary binary search in memblock_next_valid_pfn()
Date
Commit b92df1de5d28 ("mm: page_alloc: skip over regions of invalid pfns
where possible") optimized the loop in memmap_init_zone(). But there is
still some room for improvement. E.g. if pfn and pfn+1 are in the same
memblock region, we can simply pfn++ instead of doing the binary search
in memblock_next_valid_pfn.

Signed-off-by: Jia He <jia.he@hxt-semitech.com>
---
arch/arm/include/asm/page.h | 1 +
arch/arm/mm/init.c | 31 ++++++++++++++++++++++++-------
arch/arm64/include/asm/page.h | 1 +
arch/arm64/mm/init.c | 31 ++++++++++++++++++++++++-------
mm/page_alloc.c | 5 +++--
5 files changed, 53 insertions(+), 16 deletions(-)

diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index 4355f0e..7a0404f 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -157,6 +157,7 @@ extern void copy_page(void *to, const void *from);
typedef struct page *pgtable_t;

#ifdef CONFIG_HAVE_ARCH_PFN_VALID
+extern int early_region_idx;
extern int pfn_valid(unsigned long);
#endif

diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 0fb85ca..7779804 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -193,6 +193,8 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max_low,
}

#ifdef CONFIG_HAVE_ARCH_PFN_VALID
+int early_region_idx __meminitdata = -1;
+
int pfn_valid(unsigned long pfn)
{
return memblock_is_map_memory(__pfn_to_phys(pfn));
@@ -200,31 +202,46 @@ int pfn_valid(unsigned long pfn)
EXPORT_SYMBOL(pfn_valid);

/* HAVE_MEMBLOCK is always enabled on arm */
-unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn)
+unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn,
+ int *last_idx)
{
struct memblock_type *type = &memblock.memory;
+ struct memblock_region *regions = type->regions;
unsigned int right = type->cnt;
unsigned int mid, left = 0;
+ unsigned long start_pfn, end_pfn;
phys_addr_t addr = PFN_PHYS(++pfn);

+ /* fast path, return pfn+1 if next pfn is in the same region */
+ if (*last_idx != -1) {
+ start_pfn = PFN_DOWN(regions[*last_idx].base);
+ end_pfn = PFN_DOWN(regions[*last_idx].base +
+ regions[*last_idx].size);
+
+ if (pfn >= start_pfn && pfn < end_pfn)
+ return pfn;
+ }
+
+ /* slow path, do the binary searching */
do {
mid = (right + left) / 2;

- if (addr < type->regions[mid].base)
+ if (addr < regions[mid].base)
right = mid;
- else if (addr >= (type->regions[mid].base +
- type->regions[mid].size))
+ else if (addr >= (regions[mid].base + regions[mid].size))
left = mid + 1;
else {
- /* addr is within the region, so pfn is valid */
+ *last_idx = mid;
return pfn;
}
} while (left < right);

if (right == type->cnt)
return -1UL;
- else
- return PHYS_PFN(type->regions[right].base);
+
+ *last_idx = right;
+
+ return PHYS_PFN(regions[*last_idx].base);
}
EXPORT_SYMBOL(memblock_next_valid_pfn);
#endif /*CONFIG_HAVE_ARCH_PFN_VALID*/
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 60d02c8..84b503a 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -38,6 +38,7 @@ extern void clear_page(void *to);
typedef struct page *pgtable_t;

#ifdef CONFIG_HAVE_ARCH_PFN_VALID
+extern int early_region_idx;
extern int pfn_valid(unsigned long);
#endif

diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 13e43ff..cd9b473 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -285,6 +285,8 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
#endif /* CONFIG_NUMA */

#ifdef CONFIG_HAVE_ARCH_PFN_VALID
+int early_region_idx __meminitdata = -1;
+
int pfn_valid(unsigned long pfn)
{
return memblock_is_map_memory(pfn << PAGE_SHIFT);
@@ -292,31 +294,46 @@ int pfn_valid(unsigned long pfn)
EXPORT_SYMBOL(pfn_valid);

/* HAVE_MEMBLOCK is always enabled on arm64 */
-unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn)
+unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn,
+ int *last_idx)
{
struct memblock_type *type = &memblock.memory;
+ struct memblock_region *regions = type->regions;
unsigned int right = type->cnt;
unsigned int mid, left = 0;
+ unsigned long start_pfn, end_pfn;
phys_addr_t addr = PFN_PHYS(++pfn);

+ /* fast path, return pfn+1 if next pfn is in the same region */
+ if (*last_idx != -1) {
+ start_pfn = PFN_DOWN(regions[*last_idx].base);
+ end_pfn = PFN_DOWN(regions[*last_idx].base +
+ regions[*last_idx].size);
+
+ if (pfn >= start_pfn && pfn < end_pfn)
+ return pfn;
+ }
+
+ /* slow path, do the binary searching */
do {
mid = (right + left) / 2;

- if (addr < type->regions[mid].base)
+ if (addr < regions[mid].base)
right = mid;
- else if (addr >= (type->regions[mid].base +
- type->regions[mid].size))
+ else if (addr >= (regions[mid].base + regions[mid].size))
left = mid + 1;
else {
- /* addr is within the region, so pfn is valid */
+ *last_idx = mid;
return pfn;
}
} while (left < right);

if (right == type->cnt)
return -1UL;
- else
- return PHYS_PFN(type->regions[right].base);
+
+ *last_idx = right;
+
+ return PHYS_PFN(regions[*last_idx].base);
}
EXPORT_SYMBOL(memblock_next_valid_pfn);
#endif /*CONFIG_HAVE_ARCH_PFN_VALID*/
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8a92df7..f99b513 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5453,8 +5453,9 @@ void __ref build_all_zonelists(pg_data_t *pgdat)
* done. Non-atomic initialization, single-pass.
*/
#if (defined CONFIG_HAVE_MEMBLOCK) && (defined CONFIG_HAVE_ARCH_PFN_VALID)
-extern unsigned long memblock_next_valid_pfn(unsigned long pfn);
-#define skip_to_last_invalid_pfn(pfn) (memblock_next_valid_pfn(pfn) - 1)
+extern unsigned long memblock_next_valid_pfn(unsigned long pfn, int *last_idx);
+#define skip_to_last_invalid_pfn(pfn) \
+ (memblock_next_valid_pfn(pfn, &early_region_idx) - 1)
#endif

#ifndef skip_to_last_invalid_pfn
--
2.7.4
\
 
 \ /
  Last update: 2018-03-30 10:19    [W:0.151 / U:0.168 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site