From d635711daa98be86d4c7fd01499c34f566b54ccb Mon Sep 17 00:00:00 2001 From: André Fabian Silva Delgado Date: Fri, 10 Jun 2016 05:30:17 -0300 Subject: Linux-libre 4.6.2-gnu --- arch/powerpc/include/asm/book3s/64/hash-4k.h | 36 +- arch/powerpc/include/asm/book3s/64/hash-64k.h | 57 +- arch/powerpc/include/asm/book3s/64/hash.h | 68 ++- arch/powerpc/include/asm/book3s/64/mmu-hash.h | 616 +++++++++++++++++++++ arch/powerpc/include/asm/book3s/64/pgtable.h | 36 +- arch/powerpc/include/asm/book3s/64/tlbflush-hash.h | 94 ++++ 6 files changed, 811 insertions(+), 96 deletions(-) create mode 100644 arch/powerpc/include/asm/book3s/64/mmu-hash.h create mode 100644 arch/powerpc/include/asm/book3s/64/tlbflush-hash.h (limited to 'arch/powerpc/include/asm/book3s/64') diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index ea0414d66..5f08a0832 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -52,44 +52,14 @@ _PAGE_F_SECOND | _PAGE_F_GIX) /* shift to put page number into pte */ -#define PTE_RPN_SHIFT (18) +#define PTE_RPN_SHIFT (12) +#define PTE_RPN_SIZE (45) /* gives 57-bit real addresses */ #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 849bbec80..0a7956a80 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 */ @@ -20,13 +19,18 @@ #define PMD_SIZE (1UL << PMD_SHIFT) #define PMD_MASK (~(PMD_SIZE-1)) -/* PGDIR_SHIFT determines what a third-level page table entry can map */ -#define PGDIR_SHIFT (PMD_SHIFT + PMD_INDEX_SIZE) +/* 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 fourth-level page table entry can map */ +#define PGDIR_SHIFT (PUD_SHIFT + PUD_INDEX_SIZE) #define PGDIR_SIZE (1UL << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) -#define _PAGE_COMBO 0x00040000 /* this is a combo 4k page */ -#define _PAGE_4K_PFN 0x00080000 /* PFN is for a single 4k page */ +#define _PAGE_COMBO 0x00001000 /* this is a combo 4k page */ +#define _PAGE_4K_PFN 0x00002000 /* PFN is for a single 4k page */ /* * Used to track subpage group valid if _PAGE_COMBO is set * This overloads _PAGE_F_GIX and _PAGE_F_SECOND @@ -39,10 +43,12 @@ /* Shift to put page number into pte. * - * That gives us a max RPN of 34 bits, which means a max of 50 bits - * of addressable physical space, or 46 bits for the special 4k PFNs. + * That gives us a max RPN of 41 bits, which means a max of 57 bits + * of addressable physical space, or 53 bits for the special 4k PFNs. */ -#define PTE_RPN_SHIFT (30) +#define PTE_RPN_SHIFT (16) +#define PTE_RPN_SIZE (41) + /* * we support 16 fragments per PTE page of 64K size. */ @@ -54,13 +60,12 @@ #define PTE_FRAG_SIZE_SHIFT 12 #define PTE_FRAG_SIZE (1UL << PTE_FRAG_SIZE_SHIFT) -/* - * Bits to mask out from a PMD to get to the PTE page - * PMDs point to PTE table fragments which are PTE_FRAG_SIZE aligned. - */ -#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 +/* Bits to mask out from a PMD to get to the PTE page */ +#define PMD_MASKED_BITS 0xc0000000000000ffUL +/* Bits to mask out from a PUD to get to the PMD page */ +#define PUD_MASKED_BITS 0xc0000000000000ffUL +/* Bits to mask out from a PGD to get to the PUD page */ +#define PGD_MASKED_BITS 0xc0000000000000ffUL #ifndef __ASSEMBLY__ @@ -120,7 +125,7 @@ extern bool __rpte_sub_valid(real_pte_t rpte, unsigned long index); (((pte) & _PAGE_COMBO)? MMU_PAGE_4K: MMU_PAGE_64K) #define remap_4k_pfn(vma, addr, pfn, prot) \ - (WARN_ON(((pfn) >= (1UL << (64 - PTE_RPN_SHIFT)))) ? -EINVAL : \ + (WARN_ON(((pfn) >= (1UL << PTE_RPN_SIZE))) ? -EINVAL : \ remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, \ __pgprot(pgprot_val((prot)) | _PAGE_4K_PFN))) @@ -130,11 +135,9 @@ 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 @@ -208,30 +211,30 @@ static inline char *get_hpte_slot_array(pmd_t *pmdp) /* * The linux hugepage PMD now include the pmd entries followed by the address * to the stashed pgtable_t. The stashed pgtable_t contains the hpte bits. - * [ 1 bit secondary | 3 bit hidx | 1 bit valid | 000]. We use one byte per + * [ 000 | 1 bit secondary | 3 bit hidx | 1 bit valid]. We use one byte per * each HPTE entry. With 16MB hugepage and 64K HPTE we need 256 entries and * with 4K HPTE we need 4096 entries. Both will fit in a 4K pgtable_t. * - * The last three bits are intentionally left to zero. This memory location + * The top three bits are intentionally left as zero. This memory location * are also used as normal page PTE pointers. So if we have any pointers * left around while we collapse a hugepage, we need to make sure * _PAGE_PRESENT bit of that is zero when we look at them */ static inline unsigned int hpte_valid(unsigned char *hpte_slot_array, int index) { - return (hpte_slot_array[index] >> 3) & 0x1; + return hpte_slot_array[index] & 0x1; } static inline unsigned int hpte_hash_index(unsigned char *hpte_slot_array, int index) { - return hpte_slot_array[index] >> 4; + return hpte_slot_array[index] >> 1; } static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array, unsigned int index, unsigned int hidx) { - hpte_slot_array[index] = hidx << 4 | 0x1 << 3; + hpte_slot_array[index] = (hidx << 1) | 0x1; } /* diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index 8d1c8162f..d0ee6fcef 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -4,8 +4,7 @@ /* * Common bits between 4K and 64K pages in a linux-style PTE. - * These match the bits in the (hardware-defined) PowerPC PTE as closely - * as possible. Additional bits may be defined in pgtable-hash64-*.h + * Additional bits may be defined in pgtable-hash64-*.h * * Note: We only support user read/write permissions. Supervisor always * have full read/write to pages above PAGE_OFFSET (pages below that @@ -14,32 +13,35 @@ * We could create separate kernel read-only if we used the 3 PP bits * combinations that newer processors provide but we currently don't. */ -#define _PAGE_PTE 0x00001 -#define _PAGE_PRESENT 0x00002 /* software: pte contains a translation */ -#define _PAGE_BIT_SWAP_TYPE 2 -#define _PAGE_USER 0x00004 /* matches one of the PP bits */ -#define _PAGE_EXEC 0x00008 /* No execute on POWER4 and newer (we invert) */ -#define _PAGE_GUARDED 0x00010 -/* We can derive Memory coherence from _PAGE_NO_CACHE */ +#define _PAGE_BIT_SWAP_TYPE 0 + +#define _PAGE_EXEC 0x00001 /* execute permission */ +#define _PAGE_RW 0x00002 /* read & write access allowed */ +#define _PAGE_READ 0x00004 /* read access allowed */ +#define _PAGE_USER 0x00008 /* page may be accessed by userspace */ +#define _PAGE_GUARDED 0x00010 /* G: guarded (side-effect) page */ +/* M (memory coherence) is always set in the HPTE, so we don't need it here */ #define _PAGE_COHERENT 0x0 #define _PAGE_NO_CACHE 0x00020 /* I: cache inhibit */ #define _PAGE_WRITETHRU 0x00040 /* W: cache write-through */ #define _PAGE_DIRTY 0x00080 /* C: page changed */ #define _PAGE_ACCESSED 0x00100 /* R: page referenced */ -#define _PAGE_RW 0x00200 /* software: user write access allowed */ -#define _PAGE_HASHPTE 0x00400 /* software: pte has an associated HPTE */ +#define _PAGE_SPECIAL 0x00400 /* software: special page */ #define _PAGE_BUSY 0x00800 /* software: PTE & hash are busy */ -#define _PAGE_F_GIX 0x07000 /* full page: hidx bits */ -#define _PAGE_F_GIX_SHIFT 12 -#define _PAGE_F_SECOND 0x08000 /* Whether to use secondary hash or not */ -#define _PAGE_SPECIAL 0x10000 /* software: special page */ #ifdef CONFIG_MEM_SOFT_DIRTY -#define _PAGE_SOFT_DIRTY 0x20000 /* software: software dirty tracking */ +#define _PAGE_SOFT_DIRTY 0x200 /* software: software dirty tracking */ #else -#define _PAGE_SOFT_DIRTY 0x00000 +#define _PAGE_SOFT_DIRTY 0x000 #endif +#define _PAGE_F_GIX_SHIFT 57 +#define _PAGE_F_GIX (7ul << 57) /* HPTE index within HPTEG */ +#define _PAGE_F_SECOND (1ul << 60) /* HPTE is in 2ndary HPTEG */ +#define _PAGE_HASHPTE (1ul << 61) /* PTE has associated HPTE */ +#define _PAGE_PTE (1ul << 62) /* distinguishes PTEs from pointers */ +#define _PAGE_PRESENT (1ul << 63) /* pte contains a translation */ + /* * We need to differentiate between explicit huge page and THP huge * page, since THP huge page also need to track real subpage details @@ -132,7 +134,7 @@ * The mask convered by the RPN must be a ULL on 32-bit platforms with * 64-bit PTEs */ -#define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) +#define PTE_RPN_MASK (((1UL << PTE_RPN_SIZE) - 1) << PTE_RPN_SHIFT) /* * _PAGE_CHG_MASK masks of bits that are to be preserved across * pgprot changes @@ -223,15 +225,17 @@ #define PUD_BAD_BITS (PMD_TABLE_SIZE-1) #ifndef __ASSEMBLY__ -#define pmd_bad(pmd) (!is_kernel_addr(pmd_val(pmd)) \ - || (pmd_val(pmd) & PMD_BAD_BITS)) -#define pmd_page_vaddr(pmd) (pmd_val(pmd) & ~PMD_MASKED_BITS) +#define pmd_bad(pmd) (pmd_val(pmd) & PMD_BAD_BITS) +#define pmd_page_vaddr(pmd) __va(pmd_val(pmd) & ~PMD_MASKED_BITS) + +#define pud_bad(pud) (pud_val(pud) & PUD_BAD_BITS) +#define pud_page_vaddr(pud) __va(pud_val(pud) & ~PUD_MASKED_BITS) -#define pud_bad(pud) (!is_kernel_addr(pud_val(pud)) \ - || (pud_val(pud) & PUD_BAD_BITS)) -#define pud_page_vaddr(pud) (pud_val(pud) & ~PUD_MASKED_BITS) +/* Pointers in the page table tree are physical addresses */ +#define __pgtable_ptr_val(ptr) __pa(ptr) #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)) @@ -360,8 +364,18 @@ 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) +static inline unsigned long pgd_page_vaddr(pgd_t pgd) +{ + return (unsigned long)__va(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);} @@ -402,7 +416,7 @@ static inline int pte_protnone(pte_t pte) static inline int pte_present(pte_t pte) { - return pte_val(pte) & _PAGE_PRESENT; + return !!(pte_val(pte) & _PAGE_PRESENT); } /* Conversion functions: convert a page and protection to a page entry, @@ -413,13 +427,13 @@ static inline int pte_present(pte_t pte) */ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) { - return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) | + return __pte((((pte_basic_t)(pfn) << PTE_RPN_SHIFT) & PTE_RPN_MASK) | pgprot_val(pgprot)); } static inline unsigned long pte_pfn(pte_t pte) { - return pte_val(pte) >> PTE_RPN_SHIFT; + return (pte_val(pte) & PTE_RPN_MASK) >> PTE_RPN_SHIFT; } /* Generic modifiers for PTE bits */ diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h new file mode 100644 index 000000000..0cea4807e --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -0,0 +1,616 @@ +#ifndef _ASM_POWERPC_MMU_HASH64_H_ +#define _ASM_POWERPC_MMU_HASH64_H_ +/* + * PowerPC64 memory management structures + * + * Dave Engebretsen & Mike Corrigan <{engebret|mikejc}@us.ibm.com> + * PPC64 rework. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include +#include + +/* + * This is necessary to get the definition of PGTABLE_RANGE which we + * need for various slices related matters. Note that this isn't the + * complete pgtable.h but only a portion of it. + */ +#include +#include +#include + +/* + * SLB + */ + +#define SLB_NUM_BOLTED 3 +#define SLB_CACHE_ENTRIES 8 +#define SLB_MIN_SIZE 32 + +/* Bits in the SLB ESID word */ +#define SLB_ESID_V ASM_CONST(0x0000000008000000) /* valid */ + +/* Bits in the SLB VSID word */ +#define SLB_VSID_SHIFT 12 +#define SLB_VSID_SHIFT_1T 24 +#define SLB_VSID_SSIZE_SHIFT 62 +#define SLB_VSID_B ASM_CONST(0xc000000000000000) +#define SLB_VSID_B_256M ASM_CONST(0x0000000000000000) +#define SLB_VSID_B_1T ASM_CONST(0x4000000000000000) +#define SLB_VSID_KS ASM_CONST(0x0000000000000800) +#define SLB_VSID_KP ASM_CONST(0x0000000000000400) +#define SLB_VSID_N ASM_CONST(0x0000000000000200) /* no-execute */ +#define SLB_VSID_L ASM_CONST(0x0000000000000100) +#define SLB_VSID_C ASM_CONST(0x0000000000000080) /* class */ +#define SLB_VSID_LP ASM_CONST(0x0000000000000030) +#define SLB_VSID_LP_00 ASM_CONST(0x0000000000000000) +#define SLB_VSID_LP_01 ASM_CONST(0x0000000000000010) +#define SLB_VSID_LP_10 ASM_CONST(0x0000000000000020) +#define SLB_VSID_LP_11 ASM_CONST(0x0000000000000030) +#define SLB_VSID_LLP (SLB_VSID_L|SLB_VSID_LP) + +#define SLB_VSID_KERNEL (SLB_VSID_KP) +#define SLB_VSID_USER (SLB_VSID_KP|SLB_VSID_KS|SLB_VSID_C) + +#define SLBIE_C (0x08000000) +#define SLBIE_SSIZE_SHIFT 25 + +/* + * Hash table + */ + +#define HPTES_PER_GROUP 8 + +#define HPTE_V_SSIZE_SHIFT 62 +#define HPTE_V_AVPN_SHIFT 7 +#define HPTE_V_AVPN ASM_CONST(0x3fffffffffffff80) +#define HPTE_V_AVPN_VAL(x) (((x) & HPTE_V_AVPN) >> HPTE_V_AVPN_SHIFT) +#define HPTE_V_COMPARE(x,y) (!(((x) ^ (y)) & 0xffffffffffffff80UL)) +#define HPTE_V_BOLTED ASM_CONST(0x0000000000000010) +#define HPTE_V_LOCK ASM_CONST(0x0000000000000008) +#define HPTE_V_LARGE ASM_CONST(0x0000000000000004) +#define HPTE_V_SECONDARY ASM_CONST(0x0000000000000002) +#define HPTE_V_VALID ASM_CONST(0x0000000000000001) + +#define HPTE_R_PP0 ASM_CONST(0x8000000000000000) +#define HPTE_R_TS ASM_CONST(0x4000000000000000) +#define HPTE_R_KEY_HI ASM_CONST(0x3000000000000000) +#define HPTE_R_RPN_SHIFT 12 +#define HPTE_R_RPN ASM_CONST(0x0ffffffffffff000) +#define HPTE_R_PP ASM_CONST(0x0000000000000003) +#define HPTE_R_N ASM_CONST(0x0000000000000004) +#define HPTE_R_G ASM_CONST(0x0000000000000008) +#define HPTE_R_M ASM_CONST(0x0000000000000010) +#define HPTE_R_I ASM_CONST(0x0000000000000020) +#define HPTE_R_W ASM_CONST(0x0000000000000040) +#define HPTE_R_WIMG ASM_CONST(0x0000000000000078) +#define HPTE_R_C ASM_CONST(0x0000000000000080) +#define HPTE_R_R ASM_CONST(0x0000000000000100) +#define HPTE_R_KEY_LO ASM_CONST(0x0000000000000e00) + +#define HPTE_V_1TB_SEG ASM_CONST(0x4000000000000000) +#define HPTE_V_VRMA_MASK ASM_CONST(0x4001ffffff000000) + +/* Values for PP (assumes Ks=0, Kp=1) */ +#define PP_RWXX 0 /* Supervisor read/write, User none */ +#define PP_RWRX 1 /* Supervisor read/write, User read */ +#define PP_RWRW 2 /* Supervisor read/write, User read/write */ +#define PP_RXRX 3 /* Supervisor read, User read */ +#define PP_RXXX (HPTE_R_PP0 | 2) /* Supervisor read, user none */ + +/* Fields for tlbiel instruction in architecture 2.06 */ +#define TLBIEL_INVAL_SEL_MASK 0xc00 /* invalidation selector */ +#define TLBIEL_INVAL_PAGE 0x000 /* invalidate a single page */ +#define TLBIEL_INVAL_SET_LPID 0x800 /* invalidate a set for current LPID */ +#define TLBIEL_INVAL_SET 0xc00 /* invalidate a set for all LPIDs */ +#define TLBIEL_INVAL_SET_MASK 0xfff000 /* set number to inval. */ +#define TLBIEL_INVAL_SET_SHIFT 12 + +#define POWER7_TLB_SETS 128 /* # sets in POWER7 TLB */ +#define POWER8_TLB_SETS 512 /* # sets in POWER8 TLB */ +#define POWER9_TLB_SETS_HASH 256 /* # sets in POWER9 TLB Hash mode */ + +#ifndef __ASSEMBLY__ + +struct hash_pte { + __be64 v; + __be64 r; +}; + +extern struct hash_pte *htab_address; +extern unsigned long htab_size_bytes; +extern unsigned long htab_hash_mask; + +/* + * Page size definition + * + * shift : is the "PAGE_SHIFT" value for that page size + * sllp : is a bit mask with the value of SLB L || LP to be or'ed + * directly to a slbmte "vsid" value + * penc : is the HPTE encoding mask for the "LP" field: + * + */ +struct mmu_psize_def +{ + unsigned int shift; /* number of bits */ + int penc[MMU_PAGE_COUNT]; /* HPTE encoding */ + unsigned int tlbiel; /* tlbiel supported for that page size */ + unsigned long avpnm; /* bits to mask out in AVPN in the HPTE */ + unsigned long sllp; /* SLB L||LP (exact mask to use in slbmte) */ +}; +extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; + +static inline int shift_to_mmu_psize(unsigned int shift) +{ + int psize; + + for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) + if (mmu_psize_defs[psize].shift == shift) + return psize; + return -1; +} + +static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize) +{ + if (mmu_psize_defs[mmu_psize].shift) + return mmu_psize_defs[mmu_psize].shift; + BUG(); +} + +#endif /* __ASSEMBLY__ */ + +/* + * Segment sizes. + * These are the values used by hardware in the B field of + * SLB entries and the first dword of MMU hashtable entries. + * The B field is 2 bits; the values 2 and 3 are unused and reserved. + */ +#define MMU_SEGSIZE_256M 0 +#define MMU_SEGSIZE_1T 1 + +/* + * encode page number shift. + * in order to fit the 78 bit va in a 64 bit variable we shift the va by + * 12 bits. This enable us to address upto 76 bit va. + * For hpt hash from a va we can ignore the page size bits of va and for + * hpte encoding we ignore up to 23 bits of va. So ignoring lower 12 bits ensure + * we work in all cases including 4k page size. + */ +#define VPN_SHIFT 12 + +/* + * HPTE Large Page (LP) details + */ +#define LP_SHIFT 12 +#define LP_BITS 8 +#define LP_MASK(i) ((0xFF >> (i)) << LP_SHIFT) + +#ifndef __ASSEMBLY__ + +static inline int slb_vsid_shift(int ssize) +{ + if (ssize == MMU_SEGSIZE_256M) + return SLB_VSID_SHIFT; + return SLB_VSID_SHIFT_1T; +} + +static inline int segment_shift(int ssize) +{ + if (ssize == MMU_SEGSIZE_256M) + return SID_SHIFT; + return SID_SHIFT_1T; +} + +/* + * The current system page and segment sizes + */ +extern int mmu_linear_psize; +extern int mmu_virtual_psize; +extern int mmu_vmalloc_psize; +extern int mmu_vmemmap_psize; +extern int mmu_io_psize; +extern int mmu_kernel_ssize; +extern int mmu_highuser_ssize; +extern u16 mmu_slb_size; +extern unsigned long tce_alloc_start, tce_alloc_end; + +/* + * If the processor supports 64k normal pages but not 64k cache + * inhibited pages, we have to be prepared to switch processes + * to use 4k pages when they create cache-inhibited mappings. + * If this is the case, mmu_ci_restrictions will be set to 1. + */ +extern int mmu_ci_restrictions; + +/* + * This computes the AVPN and B fields of the first dword of a HPTE, + * for use when we want to match an existing PTE. The bottom 7 bits + * of the returned value are zero. + */ +static inline unsigned long hpte_encode_avpn(unsigned long vpn, int psize, + int ssize) +{ + unsigned long v; + /* + * The AVA field omits the low-order 23 bits of the 78 bits VA. + * These bits are not needed in the PTE, because the + * low-order b of these bits are part of the byte offset + * into the virtual page and, if b < 23, the high-order + * 23-b of these bits are always used in selecting the + * PTEGs to be searched + */ + v = (vpn >> (23 - VPN_SHIFT)) & ~(mmu_psize_defs[psize].avpnm); + v <<= HPTE_V_AVPN_SHIFT; + v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT; + return v; +} + +/* + * This function sets the AVPN and L fields of the HPTE appropriately + * using the base page size and actual page size. + */ +static inline unsigned long hpte_encode_v(unsigned long vpn, int base_psize, + int actual_psize, int ssize) +{ + unsigned long v; + v = hpte_encode_avpn(vpn, base_psize, ssize); + if (actual_psize != MMU_PAGE_4K) + v |= HPTE_V_LARGE; + return v; +} + +/* + * This function sets the ARPN, and LP fields of the HPTE appropriately + * for the page size. We assume the pa is already "clean" that is properly + * aligned for the requested page size + */ +static inline unsigned long hpte_encode_r(unsigned long pa, int base_psize, + int actual_psize) +{ + /* A 4K page needs no special encoding */ + if (actual_psize == MMU_PAGE_4K) + return pa & HPTE_R_RPN; + else { + unsigned int penc = mmu_psize_defs[base_psize].penc[actual_psize]; + unsigned int shift = mmu_psize_defs[actual_psize].shift; + return (pa & ~((1ul << shift) - 1)) | (penc << LP_SHIFT); + } +} + +/* + * Build a VPN_SHIFT bit shifted va given VSID, EA and segment size. + */ +static inline unsigned long hpt_vpn(unsigned long ea, + unsigned long vsid, int ssize) +{ + unsigned long mask; + int s_shift = segment_shift(ssize); + + mask = (1ul << (s_shift - VPN_SHIFT)) - 1; + return (vsid << (s_shift - VPN_SHIFT)) | ((ea >> VPN_SHIFT) & mask); +} + +/* + * This hashes a virtual address + */ +static inline unsigned long hpt_hash(unsigned long vpn, + unsigned int shift, int ssize) +{ + int mask; + unsigned long hash, vsid; + + /* VPN_SHIFT can be atmost 12 */ + if (ssize == MMU_SEGSIZE_256M) { + mask = (1ul << (SID_SHIFT - VPN_SHIFT)) - 1; + hash = (vpn >> (SID_SHIFT - VPN_SHIFT)) ^ + ((vpn & mask) >> (shift - VPN_SHIFT)); + } else { + mask = (1ul << (SID_SHIFT_1T - VPN_SHIFT)) - 1; + vsid = vpn >> (SID_SHIFT_1T - VPN_SHIFT); + hash = vsid ^ (vsid << 25) ^ + ((vpn & mask) >> (shift - VPN_SHIFT)) ; + } + return hash & 0x7fffffffffUL; +} + +#define HPTE_LOCAL_UPDATE 0x1 +#define HPTE_NOHPTE_UPDATE 0x2 + +extern int __hash_page_4K(unsigned long ea, unsigned long access, + unsigned long vsid, pte_t *ptep, unsigned long trap, + unsigned long flags, int ssize, int subpage_prot); +extern int __hash_page_64K(unsigned long ea, unsigned long access, + unsigned long vsid, pte_t *ptep, unsigned long trap, + unsigned long flags, int ssize); +struct mm_struct; +unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap); +extern int hash_page_mm(struct mm_struct *mm, unsigned long ea, + unsigned long access, unsigned long trap, + unsigned long flags); +extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap, + unsigned long dsisr); +int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, + pte_t *ptep, unsigned long trap, unsigned long flags, + int ssize, unsigned int shift, unsigned int mmu_psize); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern int __hash_page_thp(unsigned long ea, unsigned long access, + unsigned long vsid, pmd_t *pmdp, unsigned long trap, + unsigned long flags, int ssize, unsigned int psize); +#else +static inline int __hash_page_thp(unsigned long ea, unsigned long access, + unsigned long vsid, pmd_t *pmdp, + unsigned long trap, unsigned long flags, + int ssize, unsigned int psize) +{ + BUG(); + return -1; +} +#endif +extern void hash_failure_debug(unsigned long ea, unsigned long access, + unsigned long vsid, unsigned long trap, + int ssize, int psize, int lpsize, + unsigned long pte); +extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend, + unsigned long pstart, unsigned long prot, + int psize, int ssize); +int htab_remove_mapping(unsigned long vstart, unsigned long vend, + int psize, int ssize); +extern void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages); +extern void demote_segment_4k(struct mm_struct *mm, unsigned long addr); + +extern void hpte_init_native(void); +extern void hpte_init_lpar(void); +extern void hpte_init_beat(void); +extern void hpte_init_beat_v3(void); + +extern void slb_initialize(void); +extern void slb_flush_and_rebolt(void); + +extern void slb_vmalloc_update(void); +extern void slb_set_size(u16 size); +#endif /* __ASSEMBLY__ */ + +/* + * VSID allocation (256MB segment) + * + * We first generate a 37-bit "proto-VSID". Proto-VSIDs are generated + * from mmu context id and effective segment id of the address. + * + * For user processes max context id is limited to ((1ul << 19) - 5) + * for kernel space, we use the top 4 context ids to map address as below + * NOTE: each context only support 64TB now. + * 0x7fffc - [ 0xc000000000000000 - 0xc0003fffffffffff ] + * 0x7fffd - [ 0xd000000000000000 - 0xd0003fffffffffff ] + * 0x7fffe - [ 0xe000000000000000 - 0xe0003fffffffffff ] + * 0x7ffff - [ 0xf000000000000000 - 0xf0003fffffffffff ] + * + * The proto-VSIDs are then scrambled into real VSIDs with the + * multiplicative hash: + * + * VSID = (proto-VSID * VSID_MULTIPLIER) % VSID_MODULUS + * + * VSID_MULTIPLIER is prime, so in particular it is + * co-prime to VSID_MODULUS, making this a 1:1 scrambling function. + * Because the modulus is 2^n-1 we can compute it efficiently without + * a divide or extra multiply (see below). The scramble function gives + * robust scattering in the hash table (at least based on some initial + * results). + * + * We also consider VSID 0 special. We use VSID 0 for slb entries mapping + * bad address. This enables us to consolidate bad address handling in + * hash_page. + * + * We also need to avoid the last segment of the last context, because that + * would give a protovsid of 0x1fffffffff. That will result in a VSID 0 + * because of the modulo operation in vsid scramble. But the vmemmap + * (which is what uses region 0xf) will never be close to 64TB in size + * (it's 56 bytes per page of system memory). + */ + +#define CONTEXT_BITS 19 +#define ESID_BITS 18 +#define ESID_BITS_1T 6 + +/* + * 256MB segment + * The proto-VSID space has 2^(CONTEX_BITS + ESID_BITS) - 1 segments + * available for user + kernel mapping. The top 4 contexts are used for + * kernel mapping. Each segment contains 2^28 bytes. Each + * context maps 2^46 bytes (64TB) so we can support 2^19-1 contexts + * (19 == 37 + 28 - 46). + */ +#define MAX_USER_CONTEXT ((ASM_CONST(1) << CONTEXT_BITS) - 5) + +/* + * This should be computed such that protovosid * vsid_mulitplier + * doesn't overflow 64 bits. It should also be co-prime to vsid_modulus + */ +#define VSID_MULTIPLIER_256M ASM_CONST(12538073) /* 24-bit prime */ +#define VSID_BITS_256M (CONTEXT_BITS + ESID_BITS) +#define VSID_MODULUS_256M ((1UL<= \ + * 2^36-1, then r3+1 has the 2^36 bit set. So, if r3+1 has \ + * the bit clear, r3 already has the answer we want, if it \ + * doesn't, the answer is the low 36 bits of r3+1. So in all \ + * cases the answer is the low 36 bits of (r3 + ((r3+1) >> 36))*/\ + addi rx,rt,1; \ + srdi rx,rx,VSID_BITS_##size; /* extract 2^VSID_BITS bit */ \ + add rt,rt,rx + +/* 4 bits per slice and we have one slice per 1TB */ +#define SLICE_ARRAY_SIZE (PGTABLE_RANGE >> 41) + +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_PPC_SUBPAGE_PROT +/* + * For the sub-page protection option, we extend the PGD with one of + * these. Basically we have a 3-level tree, with the top level being + * the protptrs array. To optimize speed and memory consumption when + * only addresses < 4GB are being protected, pointers to the first + * four pages of sub-page protection words are stored in the low_prot + * array. + * Each page of sub-page protection words protects 1GB (4 bytes + * protects 64k). For the 3-level tree, each page of pointers then + * protects 8TB. + */ +struct subpage_prot_table { + unsigned long maxaddr; /* only addresses < this are protected */ + unsigned int **protptrs[(TASK_SIZE_USER64 >> 43)]; + unsigned int *low_prot[4]; +}; + +#define SBP_L1_BITS (PAGE_SHIFT - 2) +#define SBP_L2_BITS (PAGE_SHIFT - 3) +#define SBP_L1_COUNT (1 << SBP_L1_BITS) +#define SBP_L2_COUNT (1 << SBP_L2_BITS) +#define SBP_L2_SHIFT (PAGE_SHIFT + SBP_L1_BITS) +#define SBP_L3_SHIFT (SBP_L2_SHIFT + SBP_L2_BITS) + +extern void subpage_prot_free(struct mm_struct *mm); +extern void subpage_prot_init_new_context(struct mm_struct *mm); +#else +static inline void subpage_prot_free(struct mm_struct *mm) {} +static inline void subpage_prot_init_new_context(struct mm_struct *mm) { } +#endif /* CONFIG_PPC_SUBPAGE_PROT */ + +typedef unsigned long mm_context_id_t; +struct spinlock; + +typedef struct { + mm_context_id_t id; + u16 user_psize; /* page size index */ + +#ifdef CONFIG_PPC_MM_SLICES + u64 low_slices_psize; /* SLB page size encodings */ + unsigned char high_slices_psize[SLICE_ARRAY_SIZE]; +#else + u16 sllp; /* SLB page size encoding */ +#endif + unsigned long vdso_base; +#ifdef CONFIG_PPC_SUBPAGE_PROT + struct subpage_prot_table spt; +#endif /* CONFIG_PPC_SUBPAGE_PROT */ +#ifdef CONFIG_PPC_ICSWX + struct spinlock *cop_lockp; /* guard acop and cop_pid */ + unsigned long acop; /* mask of enabled coprocessor types */ + unsigned int cop_pid; /* pid value used with coprocessors */ +#endif /* CONFIG_PPC_ICSWX */ +#ifdef CONFIG_PPC_64K_PAGES + /* for 4K PTE fragment support */ + void *pte_frag; +#endif +#ifdef CONFIG_SPAPR_TCE_IOMMU + struct list_head iommu_group_mem_list; +#endif +} mm_context_t; + + +#if 0 +/* + * The code below is equivalent to this function for arguments + * < 2^VSID_BITS, which is all this should ever be called + * with. However gcc is not clever enough to compute the + * modulus (2^n-1) without a second multiply. + */ +#define vsid_scramble(protovsid, size) \ + ((((protovsid) * VSID_MULTIPLIER_##size) % VSID_MODULUS_##size)) + +#else /* 1 */ +#define vsid_scramble(protovsid, size) \ + ({ \ + unsigned long x; \ + x = (protovsid) * VSID_MULTIPLIER_##size; \ + x = (x >> VSID_BITS_##size) + (x & VSID_MODULUS_##size); \ + (x + ((x+1) >> VSID_BITS_##size)) & VSID_MODULUS_##size; \ + }) +#endif /* 1 */ + +/* Returns the segment size indicator for a user address */ +static inline int user_segment_size(unsigned long addr) +{ + /* Use 1T segments if possible for addresses >= 1T */ + if (addr >= (1UL << SID_SHIFT_1T)) + return mmu_highuser_ssize; + return MMU_SEGSIZE_256M; +} + +static inline unsigned long get_vsid(unsigned long context, unsigned long ea, + int ssize) +{ + /* + * Bad address. We return VSID 0 for that + */ + if ((ea & ~REGION_MASK) >= PGTABLE_RANGE) + return 0; + + if (ssize == MMU_SEGSIZE_256M) + return vsid_scramble((context << ESID_BITS) + | (ea >> SID_SHIFT), 256M); + return vsid_scramble((context << ESID_BITS_1T) + | (ea >> SID_SHIFT_1T), 1T); +} + +/* + * This is only valid for addresses >= PAGE_OFFSET + * + * For kernel space, we use the top 4 context ids to map address as below + * 0x7fffc - [ 0xc000000000000000 - 0xc0003fffffffffff ] + * 0x7fffd - [ 0xd000000000000000 - 0xd0003fffffffffff ] + * 0x7fffe - [ 0xe000000000000000 - 0xe0003fffffffffff ] + * 0x7ffff - [ 0xf000000000000000 - 0xf0003fffffffffff ] + */ +static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize) +{ + unsigned long context; + + /* + * kernel take the top 4 context from the available range + */ + context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1; + return get_vsid(context, ea, ssize); +} + +unsigned htab_shift_for_mem_size(unsigned long mem_size); + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_POWERPC_MMU_HASH64_H_ */ diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index ac07a30a7..77d3ce057 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -43,13 +43,8 @@ */ #ifndef __real_pte -#ifdef CONFIG_STRICT_MM_TYPECHECKS #define __real_pte(e,p) ((real_pte_t){(e)}) #define __rpte_to_pte(r) ((r).pte) -#else -#define __real_pte(e,p) (e) -#define __rpte_to_pte(r) (__pte(r)) -#endif #define __rpte_to_hidx(r,index) (pte_val(__rpte_to_pte(r)) >>_PAGE_F_GIX_SHIFT) #define pte_iterate_hashed_subpages(rpte, psize, va, index, shift) \ @@ -111,6 +106,26 @@ 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 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); + /* * Find an entry in a page-table-directory. We combine the address region * (the high order N bits) and the pgd portion of the address. @@ -118,9 +133,10 @@ static inline void pgd_set(pgd_t *pgdp, unsigned long val) #define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address)) +#define pud_offset(pgdp, addr) \ + (((pud_t *) pgd_page_vaddr(*(pgdp))) + pud_index(addr)) #define pmd_offset(pudp,addr) \ (((pmd_t *) pud_page_vaddr(*(pudp))) + pmd_index(addr)) - #define pte_offset_kernel(dir,addr) \ (((pte_t *) pmd_page_vaddr(*(dir))) + pte_index(addr)) @@ -135,6 +151,8 @@ static inline void pgd_set(pgd_t *pgdp, unsigned long val) pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e)) #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e)) +#define pud_ERROR(e) \ + pr_err("%s:%d: bad pud %08lx.\n", __FILE__, __LINE__, pud_val(e)) #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) @@ -154,10 +172,10 @@ static inline void pgd_set(pgd_t *pgdp, unsigned long val) #define SWP_TYPE_BITS 5 #define __swp_type(x) (((x).val >> _PAGE_BIT_SWAP_TYPE) \ & ((1UL << SWP_TYPE_BITS) - 1)) -#define __swp_offset(x) ((x).val >> PTE_RPN_SHIFT) +#define __swp_offset(x) (((x).val & PTE_RPN_MASK) >> PTE_RPN_SHIFT) #define __swp_entry(type, offset) ((swp_entry_t) { \ - ((type) << _PAGE_BIT_SWAP_TYPE) \ - | ((offset) << PTE_RPN_SHIFT) }) + ((type) << _PAGE_BIT_SWAP_TYPE) \ + | (((offset) << PTE_RPN_SHIFT) & PTE_RPN_MASK)}) /* * swp_entry_t must be independent of pte bits. We build a swp_entry_t from * swap type and offset we get from swap and convert that to pte to find a diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h new file mode 100644 index 000000000..1b753f96b --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h @@ -0,0 +1,94 @@ +#ifndef _ASM_POWERPC_BOOK3S_64_TLBFLUSH_HASH_H +#define _ASM_POWERPC_BOOK3S_64_TLBFLUSH_HASH_H + +#define MMU_NO_CONTEXT 0 + +/* + * TLB flushing for 64-bit hash-MMU CPUs + */ + +#include +#include + +#define PPC64_TLB_BATCH_NR 192 + +struct ppc64_tlb_batch { + int active; + unsigned long index; + struct mm_struct *mm; + real_pte_t pte[PPC64_TLB_BATCH_NR]; + unsigned long vpn[PPC64_TLB_BATCH_NR]; + unsigned int psize; + int ssize; +}; +DECLARE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch); + +extern void __flush_tlb_pending(struct ppc64_tlb_batch *batch); + +#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE + +static inline void arch_enter_lazy_mmu_mode(void) +{ + struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch); + + batch->active = 1; +} + +static inline void arch_leave_lazy_mmu_mode(void) +{ + struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch); + + if (batch->index) + __flush_tlb_pending(batch); + batch->active = 0; +} + +#define arch_flush_lazy_mmu_mode() do {} while (0) + + +extern void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, + int ssize, unsigned long flags); +extern void flush_hash_range(unsigned long number, int local); +extern void flush_hash_hugepage(unsigned long vsid, unsigned long addr, + pmd_t *pmdp, unsigned int psize, int ssize, + unsigned long flags); + +static inline void local_flush_tlb_mm(struct mm_struct *mm) +{ +} + +static inline void flush_tlb_mm(struct mm_struct *mm) +{ +} + +static inline void local_flush_tlb_page(struct vm_area_struct *vma, + unsigned long vmaddr) +{ +} + +static inline void flush_tlb_page(struct vm_area_struct *vma, + unsigned long vmaddr) +{ +} + +static inline void flush_tlb_page_nohash(struct vm_area_struct *vma, + unsigned long vmaddr) +{ +} + +static inline void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ +} + +static inline void flush_tlb_kernel_range(unsigned long start, + unsigned long end) +{ +} + +/* Private function for use by PCI IO mapping code */ +extern void __flush_hash_table_range(struct mm_struct *mm, unsigned long start, + unsigned long end); +extern void flush_tlb_pmd_range(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr); +#endif /* _ASM_POWERPC_BOOK3S_64_TLBFLUSH_HASH_H */ -- cgit v1.2.3-54-g00ecf