| Message ID | 1522636236-12625-3-git-send-email-hejianet@gmail.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On 2 April 2018 at 04:30, Jia He <hejianet@gmail.com> wrote: > 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 | 28 ++++++++++++++++++++++------ > arch/arm64/include/asm/page.h | 1 + > arch/arm64/mm/init.c | 28 ++++++++++++++++++++++------ > 4 files changed, 46 insertions(+), 12 deletions(-) > Could we put this in a shared file somewhere? This is the second patch where you put make identical changes to ARM and arm64. > diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h > index 489875c..f38909c 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); > extern unsigned long memblock_next_valid_pfn(unsigned long pfn); > #define skip_to_last_invalid_pfn(pfn) (memblock_next_valid_pfn(pfn) - 1) > diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c > index 0fb85ca..06ed190 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)); > @@ -203,28 +205,42 @@ EXPORT_SYMBOL(pfn_valid); > unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn) > { > 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 (early_region_idx != -1) { > + start_pfn = PFN_DOWN(regions[early_region_idx].base); > + end_pfn = PFN_DOWN(regions[early_region_idx].base + > + regions[early_region_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 */ > + early_region_idx = mid; > return pfn; > } > } while (left < right); > > if (right == type->cnt) > return -1UL; > - else > - return PHYS_PFN(type->regions[right].base); > + > + early_region_idx = right; > + > + return PHYS_PFN(regions[early_region_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 e57d3f2..f0d8c8e5 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); > extern unsigned long memblock_next_valid_pfn(unsigned long pfn); > #define skip_to_last_invalid_pfn(pfn) (memblock_next_valid_pfn(pfn) - 1) > diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c > index 13e43ff..342e4e2 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); > @@ -295,28 +297,42 @@ EXPORT_SYMBOL(pfn_valid); > unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn) > { > 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 (early_region_idx != -1) { > + start_pfn = PFN_DOWN(regions[early_region_idx].base); > + end_pfn = PFN_DOWN(regions[early_region_idx].base + > + regions[early_region_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 */ > + early_region_idx = mid; > return pfn; > } > } while (left < right); > > if (right == type->cnt) > return -1UL; > - else > - return PHYS_PFN(type->regions[right].base); > + > + early_region_idx = right; > + > + return PHYS_PFN(regions[early_region_idx].base); > } > EXPORT_SYMBOL(memblock_next_valid_pfn); > #endif /*CONFIG_HAVE_ARCH_PFN_VALID*/ > -- > 2.7.4 >
On Mon, Apr 2, 2018 at 4:30 AM, Jia He <hejianet@gmail.com> wrote: > 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 | 28 ++++++++++++++++++++++------ > arch/arm64/include/asm/page.h | 1 + > arch/arm64/mm/init.c | 28 ++++++++++++++++++++++------ > 4 files changed, 46 insertions(+), 12 deletions(-) > > diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h > index 489875c..f38909c 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; I believe this is not needed anymore. > extern int pfn_valid(unsigned long); > extern unsigned long memblock_next_valid_pfn(unsigned long pfn); > #define skip_to_last_invalid_pfn(pfn) (memblock_next_valid_pfn(pfn) - 1) > diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c > index 0fb85ca..06ed190 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; static? > + > int pfn_valid(unsigned long pfn) > { > return memblock_is_map_memory(__pfn_to_phys(pfn)); > @@ -203,28 +205,42 @@ EXPORT_SYMBOL(pfn_valid); > unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn) > { > 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 (early_region_idx != -1) { > + start_pfn = PFN_DOWN(regions[early_region_idx].base); > + end_pfn = PFN_DOWN(regions[early_region_idx].base + > + regions[early_region_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 */ > + early_region_idx = mid; > return pfn; > } > } while (left < right); > > if (right == type->cnt) > return -1UL; > - else > - return PHYS_PFN(type->regions[right].base); > + > + early_region_idx = right; > + > + return PHYS_PFN(regions[early_region_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 e57d3f2..f0d8c8e5 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; ditto > extern int pfn_valid(unsigned long); > extern unsigned long memblock_next_valid_pfn(unsigned long pfn); > #define skip_to_last_invalid_pfn(pfn) (memblock_next_valid_pfn(pfn) - 1) > diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c > index 13e43ff..342e4e2 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; ditto --nX > + > int pfn_valid(unsigned long pfn) > { > return memblock_is_map_memory(pfn << PAGE_SHIFT); > @@ -295,28 +297,42 @@ EXPORT_SYMBOL(pfn_valid); > unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn) > { > 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 (early_region_idx != -1) { > + start_pfn = PFN_DOWN(regions[early_region_idx].base); > + end_pfn = PFN_DOWN(regions[early_region_idx].base + > + regions[early_region_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 */ > + early_region_idx = mid; > return pfn; > } > } while (left < right); > > if (right == type->cnt) > return -1UL; > - else > - return PHYS_PFN(type->regions[right].base); > + > + early_region_idx = right; > + > + return PHYS_PFN(regions[early_region_idx].base); > } > EXPORT_SYMBOL(memblock_next_valid_pfn); > #endif /*CONFIG_HAVE_ARCH_PFN_VALID*/ > -- > 2.7.4 >
On Mon, Apr 2, 2018 at 8:57 AM, Ard Biesheuvel <ard.biesheuvel@linaro.org> wrote: > On 2 April 2018 at 04:30, Jia He <hejianet@gmail.com> wrote: >> 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 | 28 ++++++++++++++++++++++------ >> arch/arm64/include/asm/page.h | 1 + >> arch/arm64/mm/init.c | 28 ++++++++++++++++++++++------ >> 4 files changed, 46 insertions(+), 12 deletions(-) >> > > Could we put this in a shared file somewhere? This is the second patch > where you put make identical changes to ARM and arm64. Ard, I was wondering if we can actually have this changed to something like CONFIG_MEMBLOCK_PFN_VALID and shared instead of it being arm specific? Is there a reason it's only usable for arm? The rest is dependent on this, hence I suggested to place it close-by. But generalizing it all would make it a lot cleaner. arch/arm/mm/init.c:196: #ifdef CONFIG_HAVE_ARCH_PFN_VALID int pfn_valid(unsigned long pfn) { return memblock_is_map_memory(__pfn_to_phys(pfn)); } EXPORT_SYMBOL(pfn_valid); #endif arch/arm64/mm/init.c:287: #ifdef CONFIG_HAVE_ARCH_PFN_VALID int pfn_valid(unsigned long pfn) { return memblock_is_map_memory(pfn << PAGE_SHIFT); } EXPORT_SYMBOL(pfn_valid); #endif --nX >> diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h >> index 489875c..f38909c 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); >> extern unsigned long memblock_next_valid_pfn(unsigned long pfn); >> #define skip_to_last_invalid_pfn(pfn) (memblock_next_valid_pfn(pfn) - 1) >> diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c >> index 0fb85ca..06ed190 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)); >> @@ -203,28 +205,42 @@ EXPORT_SYMBOL(pfn_valid); >> unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn) >> { >> 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 (early_region_idx != -1) { >> + start_pfn = PFN_DOWN(regions[early_region_idx].base); >> + end_pfn = PFN_DOWN(regions[early_region_idx].base + >> + regions[early_region_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 */ >> + early_region_idx = mid; >> return pfn; >> } >> } while (left < right); >> >> if (right == type->cnt) >> return -1UL; >> - else >> - return PHYS_PFN(type->regions[right].base); >> + >> + early_region_idx = right; >> + >> + return PHYS_PFN(regions[early_region_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 e57d3f2..f0d8c8e5 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); >> extern unsigned long memblock_next_valid_pfn(unsigned long pfn); >> #define skip_to_last_invalid_pfn(pfn) (memblock_next_valid_pfn(pfn) - 1) >> diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c >> index 13e43ff..342e4e2 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); >> @@ -295,28 +297,42 @@ EXPORT_SYMBOL(pfn_valid); >> unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn) >> { >> 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 (early_region_idx != -1) { >> + start_pfn = PFN_DOWN(regions[early_region_idx].base); >> + end_pfn = PFN_DOWN(regions[early_region_idx].base + >> + regions[early_region_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 */ >> + early_region_idx = mid; >> return pfn; >> } >> } while (left < right); >> >> if (right == type->cnt) >> return -1UL; >> - else >> - return PHYS_PFN(type->regions[right].base); >> + >> + early_region_idx = right; >> + >> + return PHYS_PFN(regions[early_region_idx].base); >> } >> EXPORT_SYMBOL(memblock_next_valid_pfn); >> #endif /*CONFIG_HAVE_ARCH_PFN_VALID*/ >> -- >> 2.7.4 >>
Hi Jia,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on linus/master]
[also build test WARNING on v4.16 next-20180329]
[cannot apply to arm64/for-next/core]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Jia-He/optimize-memblock_next_valid_pfn-and-early_pfn_valid-on-arm-and-arm64/20180402-131223
config: arm64-allmodconfig (attached as .config)
compiler: aarch64-linux-gnu-gcc (Debian 7.2.0-11) 7.2.0
reproduce:
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
make.cross ARCH=arm64
All warnings (new ones prefixed by >>):
>> WARNING: vmlinux.o(.text+0x39a80): Section mismatch in reference from the function memblock_next_valid_pfn() to the variable .meminit.data:$d
The function memblock_next_valid_pfn() references
the variable __meminitdata $d.
This is often because memblock_next_valid_pfn lacks a __meminitdata
annotation or the annotation of $d is wrong.
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h index 489875c..f38909c 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); extern unsigned long memblock_next_valid_pfn(unsigned long pfn); #define skip_to_last_invalid_pfn(pfn) (memblock_next_valid_pfn(pfn) - 1) diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 0fb85ca..06ed190 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)); @@ -203,28 +205,42 @@ EXPORT_SYMBOL(pfn_valid); unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn) { 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 (early_region_idx != -1) { + start_pfn = PFN_DOWN(regions[early_region_idx].base); + end_pfn = PFN_DOWN(regions[early_region_idx].base + + regions[early_region_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 */ + early_region_idx = mid; return pfn; } } while (left < right); if (right == type->cnt) return -1UL; - else - return PHYS_PFN(type->regions[right].base); + + early_region_idx = right; + + return PHYS_PFN(regions[early_region_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 e57d3f2..f0d8c8e5 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); extern unsigned long memblock_next_valid_pfn(unsigned long pfn); #define skip_to_last_invalid_pfn(pfn) (memblock_next_valid_pfn(pfn) - 1) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 13e43ff..342e4e2 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); @@ -295,28 +297,42 @@ EXPORT_SYMBOL(pfn_valid); unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn) { 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 (early_region_idx != -1) { + start_pfn = PFN_DOWN(regions[early_region_idx].base); + end_pfn = PFN_DOWN(regions[early_region_idx].base + + regions[early_region_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 */ + early_region_idx = mid; return pfn; } } while (left < right); if (right == type->cnt) return -1UL; - else - return PHYS_PFN(type->regions[right].base); + + early_region_idx = right; + + return PHYS_PFN(regions[early_region_idx].base); } EXPORT_SYMBOL(memblock_next_valid_pfn); #endif /*CONFIG_HAVE_ARCH_PFN_VALID*/
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 | 28 ++++++++++++++++++++++------ arch/arm64/include/asm/page.h | 1 + arch/arm64/mm/init.c | 28 ++++++++++++++++++++++------ 4 files changed, 46 insertions(+), 12 deletions(-)