Re: [RFC PATCH V1 03/33] powerpc/mm: Switch book3s 64 with 64K page size to 4 level page table
Balbir Singhwrites: > On 12/01/16 18:15, Aneesh Kumar K.V wrote: >> This is needed so that we can support both hash and radix page table >> using single kernel. Radix kernel uses a 4 level table. >> . > diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h > b/arch/powerpc/include/asm/book3s/64/hash-64k.h >> index 849bbec80f7b..5c9392b71a6b 100644 >> --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h >> +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h >> @@ -1,15 +1,14 @@ >> #ifndef _ASM_POWERPC_BOOK3S_64_HASH_64K_H >> #define _ASM_POWERPC_BOOK3S_64_HASH_64K_H >> >> -#include >> - >> #define PTE_INDEX_SIZE 8 >> -#define PMD_INDEX_SIZE 10 >> -#define PUD_INDEX_SIZE 0 >> +#define PMD_INDEX_SIZE 5 >> +#define PUD_INDEX_SIZE 5 >> #define PGD_INDEX_SIZE 12 > > > 10 splits to 5 and 5 for PMD/PUD? Does this impact huge page? Nope. We have huge page at top level and pmd level. (16G and 16M) > >> >> #define PTRS_PER_PTE(1 << PTE_INDEX_SIZE) >> #define PTRS_PER_PMD(1 << PMD_INDEX_SIZE) >> +#define PTRS_PER_PUD(1 << PUD_INDEX_SIZE) >> #define PTRS_PER_PGD(1 << PGD_INDEX_SIZE) >> >> /* With 4k base page size, hugepage PTEs go at the PMD level */ >> @@ -20,8 +19,13 @@ >> #define PMD_SIZE(1UL << PMD_SHIFT) >> #define PMD_MASK(~(PMD_SIZE-1)) >> >> +/* PUD_SHIFT determines what a third-level page table entry can map */ >> +#define PUD_SHIFT (PMD_SHIFT + PMD_INDEX_SIZE) >> +#define PUD_SIZE(1UL << PUD_SHIFT) >> +#define PUD_MASK(~(PUD_SIZE-1)) >> + >> /* PGDIR_SHIFT determines what a third-level page table entry can map */ >> -#define PGDIR_SHIFT (PMD_SHIFT + PMD_INDEX_SIZE) >> +#define PGDIR_SHIFT (PUD_SHIFT + PUD_INDEX_SIZE) >> #define PGDIR_SIZE (1UL << PGDIR_SHIFT) >> #define PGDIR_MASK (~(PGDIR_SIZE-1)) >> >> @@ -61,6 +65,8 @@ >> #define PMD_MASKED_BITS (PTE_FRAG_SIZE - 1) >> /* Bits to mask out from a PGD/PUD to get to the PMD page */ >> #define PUD_MASKED_BITS 0x1ff >> +/* FIXME!! check this */ > > Shouldn't PUD_MASKED_BITS be 0x1f? > >> +#define PGD_MASKED_BITS 0 >> > 0? > The MASKED_BITS need to be cleaned up hence the FIXME!! Linux page table are aligned differently and I didn't want to cleanup that in this series. IMHO using #defines like above instead of deriving it from the pmd table align value is wrong. Will get to that later. >> #ifndef __ASSEMBLY__ >> >> @@ -130,11 +136,9 @@ extern bool __rpte_sub_valid(real_pte_t rpte, unsigned >> long index); >> #else >> #define PMD_TABLE_SIZE (sizeof(pmd_t) << PMD_INDEX_SIZE) >> #endif >> +#define PUD_TABLE_SIZE (sizeof(pud_t) << PUD_INDEX_SIZE) >> #define PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE) >> >> -#define pgd_pte(pgd)(pud_pte(((pud_t){ pgd }))) >> -#define pte_pgd(pte)((pgd_t)pte_pud(pte)) >> - >> #ifdef CONFIG_HUGETLB_PAGE -aneesh ___ Linuxppc-dev mailing list Linuxppc-dev@lists.ozlabs.org https://lists.ozlabs.org/listinfo/linuxppc-dev
Re: [RFC PATCH V1 03/33] powerpc/mm: Switch book3s 64 with 64K page size to 4 level page table
On 12/01/16 18:15, Aneesh Kumar K.V wrote: > This is needed so that we can support both hash and radix page table > using single kernel. Radix kernel uses a 4 level table. > > Signed-off-by: Aneesh Kumar K.V> --- > arch/powerpc/Kconfig | 1 + > arch/powerpc/include/asm/book3s/64/hash-4k.h | 33 > +-- > arch/powerpc/include/asm/book3s/64/hash-64k.h | 20 +--- > arch/powerpc/include/asm/book3s/64/hash.h | 8 +++ > arch/powerpc/include/asm/book3s/64/pgtable.h | 25 +++- > arch/powerpc/include/asm/pgalloc-64.h | 24 --- > arch/powerpc/include/asm/pgtable-types.h | 13 +++ > arch/powerpc/mm/init_64.c | 21 - > 8 files changed, 90 insertions(+), 55 deletions(-) > > diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig > index 378f1127ca98..618afea4c9fc 100644 > --- a/arch/powerpc/Kconfig > +++ b/arch/powerpc/Kconfig > @@ -303,6 +303,7 @@ config ZONE_DMA32 > config PGTABLE_LEVELS > int > default 2 if !PPC64 > + default 4 if PPC_BOOK3S_64 > default 3 if PPC_64K_PAGES > default 4 > > diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h > b/arch/powerpc/include/asm/book3s/64/hash-4k.h > index ea0414d6659e..c78f5928001b 100644 > --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h > +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h > @@ -57,39 +57,8 @@ > #define _PAGE_4K_PFN 0 > #ifndef __ASSEMBLY__ > /* > - * 4-level page tables related bits > + * On all 4K setups, remap_4k_pfn() equates to remap_pfn_range() > */ > - > -#define pgd_none(pgd)(!pgd_val(pgd)) > -#define pgd_bad(pgd) (pgd_val(pgd) == 0) > -#define pgd_present(pgd) (pgd_val(pgd) != 0) > -#define pgd_page_vaddr(pgd) (pgd_val(pgd) & ~PGD_MASKED_BITS) > - > -static inline void pgd_clear(pgd_t *pgdp) > -{ > - *pgdp = __pgd(0); > -} > - > -static inline pte_t pgd_pte(pgd_t pgd) > -{ > - return __pte(pgd_val(pgd)); > -} > - > -static inline pgd_t pte_pgd(pte_t pte) > -{ > - return __pgd(pte_val(pte)); > -} > -extern struct page *pgd_page(pgd_t pgd); > - > -#define pud_offset(pgdp, addr) \ > - (((pud_t *) pgd_page_vaddr(*(pgdp))) + \ > -(((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))) > - > -#define pud_ERROR(e) \ > - pr_err("%s:%d: bad pud %08lx.\n", __FILE__, __LINE__, pud_val(e)) > - > -/* > - * On all 4K setups, remap_4k_pfn() equates to remap_pfn_range() */ > #define remap_4k_pfn(vma, addr, pfn, prot) \ > remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, (prot)) > > diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h > b/arch/powerpc/include/asm/book3s/64/hash-64k.h > index 849bbec80f7b..5c9392b71a6b 100644 > --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h > +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h > @@ -1,15 +1,14 @@ > #ifndef _ASM_POWERPC_BOOK3S_64_HASH_64K_H > #define _ASM_POWERPC_BOOK3S_64_HASH_64K_H > > -#include > - > #define PTE_INDEX_SIZE 8 > -#define PMD_INDEX_SIZE 10 > -#define PUD_INDEX_SIZE 0 > +#define PMD_INDEX_SIZE 5 > +#define PUD_INDEX_SIZE 5 > #define PGD_INDEX_SIZE 12 10 splits to 5 and 5 for PMD/PUD? Does this impact huge page? > > #define PTRS_PER_PTE (1 << PTE_INDEX_SIZE) > #define PTRS_PER_PMD (1 << PMD_INDEX_SIZE) > +#define PTRS_PER_PUD (1 << PUD_INDEX_SIZE) > #define PTRS_PER_PGD (1 << PGD_INDEX_SIZE) > > /* With 4k base page size, hugepage PTEs go at the PMD level */ > @@ -20,8 +19,13 @@ > #define PMD_SIZE (1UL << PMD_SHIFT) > #define PMD_MASK (~(PMD_SIZE-1)) > > +/* PUD_SHIFT determines what a third-level page table entry can map */ > +#define PUD_SHIFT(PMD_SHIFT + PMD_INDEX_SIZE) > +#define PUD_SIZE (1UL << PUD_SHIFT) > +#define PUD_MASK (~(PUD_SIZE-1)) > + > /* PGDIR_SHIFT determines what a third-level page table entry can map */ > -#define PGDIR_SHIFT (PMD_SHIFT + PMD_INDEX_SIZE) > +#define PGDIR_SHIFT (PUD_SHIFT + PUD_INDEX_SIZE) > #define PGDIR_SIZE (1UL << PGDIR_SHIFT) > #define PGDIR_MASK (~(PGDIR_SIZE-1)) > > @@ -61,6 +65,8 @@ > #define PMD_MASKED_BITS (PTE_FRAG_SIZE - 1) > /* Bits to mask out from a PGD/PUD to get to the PMD page */ > #define PUD_MASKED_BITS 0x1ff > +/* FIXME!! check this */ Shouldn't PUD_MASKED_BITS be 0x1f? > +#define PGD_MASKED_BITS 0 > 0? > #ifndef __ASSEMBLY__ > > @@ -130,11 +136,9 @@ extern bool __rpte_sub_valid(real_pte_t rpte, unsigned > long index); > #else > #define PMD_TABLE_SIZE (sizeof(pmd_t) << PMD_INDEX_SIZE) > #endif > +#define PUD_TABLE_SIZE (sizeof(pud_t) << PUD_INDEX_SIZE) > #define PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE) > > -#define pgd_pte(pgd) (pud_pte(((pud_t){ pgd }))) > -#define pte_pgd(pte) ((pgd_t)pte_pud(pte)) > - > #ifdef CONFIG_HUGETLB_PAGE > /* > * We have PGD_INDEX_SIZ = 12 and
Re: [RFC PATCH V1 03/33] powerpc/mm: Switch book3s 64 with 64K page size to 4 level page table
On Tue, 12 Jan 2016 12:45:38 +0530 "Aneesh Kumar K.V"wrote: > This is needed so that we can support both hash and radix page table > using single kernel. Radix kernel uses a 4 level table. > > Signed-off-by: Aneesh Kumar K.V > --- > arch/powerpc/Kconfig | 1 + > arch/powerpc/include/asm/book3s/64/hash-4k.h | 33 > +-- > arch/powerpc/include/asm/book3s/64/hash-64k.h | 20 +--- > arch/powerpc/include/asm/book3s/64/hash.h | 8 +++ > arch/powerpc/include/asm/book3s/64/pgtable.h | 25 > +++- arch/powerpc/include/asm/pgalloc-64.h | > 24 --- arch/powerpc/include/asm/pgtable-types.h > | 13 +++ arch/powerpc/mm/init_64.c | 21 > - 8 files changed, 90 insertions(+), 55 deletions(-) > > diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig > index 378f1127ca98..618afea4c9fc 100644 > --- a/arch/powerpc/Kconfig > +++ b/arch/powerpc/Kconfig > @@ -303,6 +303,7 @@ config ZONE_DMA32 snip > - > #define PTE_INDEX_SIZE 8 > -#define PMD_INDEX_SIZE 10 > -#define PUD_INDEX_SIZE 0 > +#define PMD_INDEX_SIZE 5 > +#define PUD_INDEX_SIZE 5 > #define PGD_INDEX_SIZE 12 > OK, so PMD index split from 10 to 5 and 5 to PMD/PUD? What is the plan for huge pages, I saw you mentioned it was a TODO > #define PTRS_PER_PTE (1 << PTE_INDEX_SIZE) > #define PTRS_PER_PMD (1 << PMD_INDEX_SIZE) > +#define PTRS_PER_PUD (1 << PUD_INDEX_SIZE) > #define PTRS_PER_PGD (1 << PGD_INDEX_SIZE) > > /* With 4k base page size, hugepage PTEs go at the PMD level */ > @@ -20,8 +19,13 @@ > #define PMD_SIZE (1UL << PMD_SHIFT) > #define PMD_MASK (~(PMD_SIZE-1)) > > +/* PUD_SHIFT determines what a third-level page table entry can map > */ +#define PUD_SHIFT (PMD_SHIFT + PMD_INDEX_SIZE) > +#define PUD_SIZE (1UL << PUD_SHIFT) > +#define PUD_MASK (~(PUD_SIZE-1)) > + > /* PGDIR_SHIFT determines what a third-level page table entry can > map */ -#define PGDIR_SHIFT (PMD_SHIFT + PMD_INDEX_SIZE) > +#define PGDIR_SHIFT (PUD_SHIFT + PUD_INDEX_SIZE) > #define PGDIR_SIZE (1UL << PGDIR_SHIFT) > #define PGDIR_MASK (~(PGDIR_SIZE-1)) > > @@ -61,6 +65,8 @@ > #define PMD_MASKED_BITS (PTE_FRAG_SIZE - 1) > /* Bits to mask out from a PGD/PUD to get to the PMD page */ The comment looks like it applied to PMD and not PUD. > #define PUD_MASKED_BITS 0x1ff Given that PUD is now 5 bits, this should be 0x1f? > +/* FIXME!! check this */ > +#define PGD_MASKED_BITS 0 > PGD_MASKED_BITS is 0? Shouldn't it be 0xfe > #ifndef __ASSEMBLY__ > > @@ -130,11 +136,9 @@ extern bool __rpte_sub_valid(real_pte_t rpte, > unsigned long index); #else > #define PMD_TABLE_SIZE (sizeof(pmd_t) << PMD_INDEX_SIZE) > #endif > +#define PUD_TABLE_SIZE (sizeof(pud_t) << PUD_INDEX_SIZE) > #define PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE) > > -#define pgd_pte(pgd) (pud_pte(((pud_t){ pgd }))) > -#define pte_pgd(pte) ((pgd_t)pte_pud(pte)) > - > #ifdef CONFIG_HUGETLB_PAGE > /* > * We have PGD_INDEX_SIZ = 12 and PTE_INDEX_SIZE = 8, so that we can > have diff --git a/arch/powerpc/include/asm/book3s/64/hash.h > b/arch/powerpc/include/asm/book3s/64/hash.h index > f46974d0134a..9ff1e056acef 100644 --- > a/arch/powerpc/include/asm/book3s/64/hash.h +++ > b/arch/powerpc/include/asm/book3s/64/hash.h @@ -226,6 +226,7 @@ > #define pud_page_vaddr(pud) (pud_val(pud) & ~PUD_MASKED_BITS) > > #define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & > (PTRS_PER_PGD - 1)) +#define pud_index(address) (((address) >> > (PUD_SHIFT)) & (PTRS_PER_PUD - 1)) #define pmd_index(address) > (((address) >> (PMD_SHIFT)) & (PTRS_PER_PMD - 1)) #define > pte_index(address) (((address) >> (PAGE_SHIFT)) & (PTRS_PER_PTE - 1)) > @@ -354,8 +355,15 @@ static inline void __ptep_set_access_flags(pte_t > *ptep, pte_t entry) :"cc"); > } > > +static inline int pgd_bad(pgd_t pgd) > +{ > + return (pgd_val(pgd) == 0); > +} > + > #define __HAVE_ARCH_PTE_SAME > #define pte_same(A,B)(((pte_val(A) ^ pte_val(B)) & > ~_PAGE_HPTEFLAGS) == 0) +#define pgd_page_vaddr(pgd) > (pgd_val(pgd) & ~PGD_MASKED_BITS) + > > /* Generic accessors to PTE bits */ > static inline int pte_write(pte_t pte) > { return !!(pte_val(pte) & _PAGE_RW);} diff --git > a/arch/powerpc/include/asm/book3s/64/pgtable.h > b/arch/powerpc/include/asm/book3s/64/pgtable.h index > e7162dba987e..8f639401c7ba 100644 --- > a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ > b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -111,6 +111,26 @@ > static inline void pgd_set(pgd_t *pgdp, unsigned long val) *pgdp = > __pgd(val); } > +static inline void pgd_clear(pgd_t *pgdp) > +{ > + *pgdp = __pgd(0); > +} > + > +#define pgd_none(pgd)(!pgd_val(pgd)) > +#define pgd_present(pgd) (!pgd_none(pgd)) > + > +static inline
[RFC PATCH V1 03/33] powerpc/mm: Switch book3s 64 with 64K page size to 4 level page table
This is needed so that we can support both hash and radix page table using single kernel. Radix kernel uses a 4 level table. Signed-off-by: Aneesh Kumar K.V--- arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/book3s/64/hash-4k.h | 33 +-- arch/powerpc/include/asm/book3s/64/hash-64k.h | 20 +--- arch/powerpc/include/asm/book3s/64/hash.h | 8 +++ arch/powerpc/include/asm/book3s/64/pgtable.h | 25 +++- arch/powerpc/include/asm/pgalloc-64.h | 24 --- arch/powerpc/include/asm/pgtable-types.h | 13 +++ arch/powerpc/mm/init_64.c | 21 - 8 files changed, 90 insertions(+), 55 deletions(-) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 378f1127ca98..618afea4c9fc 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -303,6 +303,7 @@ config ZONE_DMA32 config PGTABLE_LEVELS int default 2 if !PPC64 + default 4 if PPC_BOOK3S_64 default 3 if PPC_64K_PAGES default 4 diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index ea0414d6659e..c78f5928001b 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -57,39 +57,8 @@ #define _PAGE_4K_PFN 0 #ifndef __ASSEMBLY__ /* - * 4-level page tables related bits + * On all 4K setups, remap_4k_pfn() equates to remap_pfn_range() */ - -#define pgd_none(pgd) (!pgd_val(pgd)) -#define pgd_bad(pgd) (pgd_val(pgd) == 0) -#define pgd_present(pgd) (pgd_val(pgd) != 0) -#define pgd_page_vaddr(pgd)(pgd_val(pgd) & ~PGD_MASKED_BITS) - -static inline void pgd_clear(pgd_t *pgdp) -{ - *pgdp = __pgd(0); -} - -static inline pte_t pgd_pte(pgd_t pgd) -{ - return __pte(pgd_val(pgd)); -} - -static inline pgd_t pte_pgd(pte_t pte) -{ - return __pgd(pte_val(pte)); -} -extern struct page *pgd_page(pgd_t pgd); - -#define pud_offset(pgdp, addr) \ - (((pud_t *) pgd_page_vaddr(*(pgdp))) + \ -(((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))) - -#define pud_ERROR(e) \ - pr_err("%s:%d: bad pud %08lx.\n", __FILE__, __LINE__, pud_val(e)) - -/* - * On all 4K setups, remap_4k_pfn() equates to remap_pfn_range() */ #define remap_4k_pfn(vma, addr, pfn, prot) \ remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, (prot)) diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index 849bbec80f7b..5c9392b71a6b 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -1,15 +1,14 @@ #ifndef _ASM_POWERPC_BOOK3S_64_HASH_64K_H #define _ASM_POWERPC_BOOK3S_64_HASH_64K_H -#include - #define PTE_INDEX_SIZE 8 -#define PMD_INDEX_SIZE 10 -#define PUD_INDEX_SIZE 0 +#define PMD_INDEX_SIZE 5 +#define PUD_INDEX_SIZE 5 #define PGD_INDEX_SIZE 12 #define PTRS_PER_PTE (1 << PTE_INDEX_SIZE) #define PTRS_PER_PMD (1 << PMD_INDEX_SIZE) +#define PTRS_PER_PUD (1 << PUD_INDEX_SIZE) #define PTRS_PER_PGD (1 << PGD_INDEX_SIZE) /* With 4k base page size, hugepage PTEs go at the PMD level */ @@ -20,8 +19,13 @@ #define PMD_SIZE (1UL << PMD_SHIFT) #define PMD_MASK (~(PMD_SIZE-1)) +/* PUD_SHIFT determines what a third-level page table entry can map */ +#define PUD_SHIFT (PMD_SHIFT + PMD_INDEX_SIZE) +#define PUD_SIZE (1UL << PUD_SHIFT) +#define PUD_MASK (~(PUD_SIZE-1)) + /* PGDIR_SHIFT determines what a third-level page table entry can map */ -#define PGDIR_SHIFT(PMD_SHIFT + PMD_INDEX_SIZE) +#define PGDIR_SHIFT(PUD_SHIFT + PUD_INDEX_SIZE) #define PGDIR_SIZE (1UL << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) @@ -61,6 +65,8 @@ #define PMD_MASKED_BITS(PTE_FRAG_SIZE - 1) /* Bits to mask out from a PGD/PUD to get to the PMD page */ #define PUD_MASKED_BITS0x1ff +/* FIXME!! check this */ +#define PGD_MASKED_BITS0 #ifndef __ASSEMBLY__ @@ -130,11 +136,9 @@ extern bool __rpte_sub_valid(real_pte_t rpte, unsigned long index); #else #define PMD_TABLE_SIZE (sizeof(pmd_t) << PMD_INDEX_SIZE) #endif +#define PUD_TABLE_SIZE (sizeof(pud_t) << PUD_INDEX_SIZE) #define PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE) -#define pgd_pte(pgd) (pud_pte(((pud_t){ pgd }))) -#define pte_pgd(pte) ((pgd_t)pte_pud(pte)) - #ifdef CONFIG_HUGETLB_PAGE /* * We have PGD_INDEX_SIZ = 12 and PTE_INDEX_SIZE = 8, so that we can have diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index f46974d0134a..9ff1e056acef 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -226,6 +226,7 @@ #define pud_page_vaddr(pud)(pud_val(pud) & ~PUD_MASKED_BITS) #define pgd_index(address) (((address)