diff options
Diffstat (limited to 'arch/powerpc/include/asm/book3s/64')
21 files changed, 4757 insertions, 0 deletions
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h new file mode 100644 index 000000000..b6ac4f86c --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -0,0 +1,172 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_HASH_4K_H +#define _ASM_POWERPC_BOOK3S_64_HASH_4K_H + +#define H_PTE_INDEX_SIZE 9 // size: 8B << 9 = 4KB, maps: 2^9 x 4KB = 2MB +#define H_PMD_INDEX_SIZE 7 // size: 8B << 7 = 1KB, maps: 2^7 x 2MB = 256MB +#define H_PUD_INDEX_SIZE 9 // size: 8B << 9 = 4KB, maps: 2^9 x 256MB = 128GB +#define H_PGD_INDEX_SIZE 9 // size: 8B << 9 = 4KB, maps: 2^9 x 128GB = 64TB + +/* + * Each context is 512TB. But on 4k we restrict our max TASK size to 64TB + * Hence also limit max EA bits to 64TB. + */ +#define MAX_EA_BITS_PER_CONTEXT 46 + + +/* + * Our page table limit us to 64TB. For 64TB physical memory, we only need 64GB + * of vmemmap space. To better support sparse memory layout, we use 61TB + * linear map range, 1TB of vmalloc, 1TB of I/O and 1TB of vmememmap. + */ +#define REGION_SHIFT (40) +#define H_KERN_MAP_SIZE (ASM_CONST(1) << REGION_SHIFT) + +/* + * Limits the linear mapping range + */ +#define H_MAX_PHYSMEM_BITS 46 + +/* + * Define the address range of the kernel non-linear virtual area (61TB) + */ +#define H_KERN_VIRT_START ASM_CONST(0xc0003d0000000000) + +#ifndef __ASSEMBLY__ +#define H_PTE_TABLE_SIZE (sizeof(pte_t) << H_PTE_INDEX_SIZE) +#define H_PMD_TABLE_SIZE (sizeof(pmd_t) << H_PMD_INDEX_SIZE) +#define H_PUD_TABLE_SIZE (sizeof(pud_t) << H_PUD_INDEX_SIZE) +#define H_PGD_TABLE_SIZE (sizeof(pgd_t) << H_PGD_INDEX_SIZE) + +#define H_PAGE_F_GIX_SHIFT _PAGE_PA_MAX +#define H_PAGE_F_SECOND _RPAGE_PKEY_BIT0 /* HPTE is in 2ndary HPTEG */ +#define H_PAGE_F_GIX (_RPAGE_RPN43 | _RPAGE_RPN42 | _RPAGE_RPN41) +#define H_PAGE_BUSY _RPAGE_RSV1 +#define H_PAGE_HASHPTE _RPAGE_PKEY_BIT4 + +/* PTE flags to conserve for HPTE identification */ +#define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_HASHPTE | \ + H_PAGE_F_SECOND | H_PAGE_F_GIX) +/* + * Not supported by 4k linux page size + */ +#define H_PAGE_4K_PFN 0x0 +#define H_PAGE_THP_HUGE 0x0 +#define H_PAGE_COMBO 0x0 + +/* 8 bytes per each pte entry */ +#define H_PTE_FRAG_SIZE_SHIFT (H_PTE_INDEX_SIZE + 3) +#define H_PTE_FRAG_NR (PAGE_SIZE >> H_PTE_FRAG_SIZE_SHIFT) +#define H_PMD_FRAG_SIZE_SHIFT (H_PMD_INDEX_SIZE + 3) +#define H_PMD_FRAG_NR (PAGE_SIZE >> H_PMD_FRAG_SIZE_SHIFT) + +/* memory key bits, only 8 keys supported */ +#define H_PTE_PKEY_BIT4 0 +#define H_PTE_PKEY_BIT3 0 +#define H_PTE_PKEY_BIT2 _RPAGE_PKEY_BIT3 +#define H_PTE_PKEY_BIT1 _RPAGE_PKEY_BIT2 +#define H_PTE_PKEY_BIT0 _RPAGE_PKEY_BIT1 + + +/* + * 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)) + +#ifdef CONFIG_HUGETLB_PAGE +static inline int hash__hugepd_ok(hugepd_t hpd) +{ + unsigned long hpdval = hpd_val(hpd); + /* + * if it is not a pte and have hugepd shift mask + * set, then it is a hugepd directory pointer + */ + if (!(hpdval & _PAGE_PTE) && (hpdval & _PAGE_PRESENT) && + ((hpdval & HUGEPD_SHIFT_MASK) != 0)) + return true; + return false; +} +#endif + +/* + * 4K PTE format is different from 64K PTE format. Saving the hash_slot is just + * a matter of returning the PTE bits that need to be modified. On 64K PTE, + * things are a little more involved and hence needs many more parameters to + * accomplish the same. However we want to abstract this out from the caller by + * keeping the prototype consistent across the two formats. + */ +static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte, + unsigned int subpg_index, unsigned long hidx, + int offset) +{ + return (hidx << H_PAGE_F_GIX_SHIFT) & + (H_PAGE_F_SECOND | H_PAGE_F_GIX); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + +static inline char *get_hpte_slot_array(pmd_t *pmdp) +{ + BUG(); + return NULL; +} + +static inline unsigned int hpte_valid(unsigned char *hpte_slot_array, int index) +{ + BUG(); + return 0; +} + +static inline unsigned int hpte_hash_index(unsigned char *hpte_slot_array, + int index) +{ + BUG(); + return 0; +} + +static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array, + unsigned int index, unsigned int hidx) +{ + BUG(); +} + +static inline int hash__pmd_trans_huge(pmd_t pmd) +{ + return 0; +} + +static inline int hash__pmd_same(pmd_t pmd_a, pmd_t pmd_b) +{ + BUG(); + return 0; +} + +static inline pmd_t hash__pmd_mkhuge(pmd_t pmd) +{ + BUG(); + return pmd; +} + +extern unsigned long hash__pmd_hugepage_update(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp, + unsigned long clr, unsigned long set); +extern pmd_t hash__pmdp_collapse_flush(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); +extern void hash__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable); +extern pgtable_t hash__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); +extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp); +extern int hash__has_transparent_hugepage(void); +#endif + +static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd) +{ + BUG(); + return pmd; +} + +#endif /* !__ASSEMBLY__ */ + +#endif /* _ASM_POWERPC_BOOK3S_64_HASH_4K_H */ diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h new file mode 100644 index 000000000..338e62fbe --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -0,0 +1,296 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_HASH_64K_H +#define _ASM_POWERPC_BOOK3S_64_HASH_64K_H + +#define H_PTE_INDEX_SIZE 8 // size: 8B << 8 = 2KB, maps 2^8 x 64KB = 16MB +#define H_PMD_INDEX_SIZE 10 // size: 8B << 10 = 8KB, maps 2^10 x 16MB = 16GB +#define H_PUD_INDEX_SIZE 10 // size: 8B << 10 = 8KB, maps 2^10 x 16GB = 16TB +#define H_PGD_INDEX_SIZE 8 // size: 8B << 8 = 2KB, maps 2^8 x 16TB = 4PB + +/* + * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS + * if we increase SECTIONS_WIDTH we will not store node details in page->flags and + * page_to_nid does a page->section->node lookup + * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce + * memory requirements with large number of sections. + * 51 bits is the max physical real address on POWER9 + */ +#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) +#define H_MAX_PHYSMEM_BITS 51 +#else +#define H_MAX_PHYSMEM_BITS 46 +#endif + +/* + * Each context is 512TB size. SLB miss for first context/default context + * is handled in the hotpath. + */ +#define MAX_EA_BITS_PER_CONTEXT 49 +#define REGION_SHIFT MAX_EA_BITS_PER_CONTEXT + +/* + * We use one context for each MAP area. + */ +#define H_KERN_MAP_SIZE (1UL << MAX_EA_BITS_PER_CONTEXT) + +/* + * Define the address range of the kernel non-linear virtual area + * 2PB + */ +#define H_KERN_VIRT_START ASM_CONST(0xc008000000000000) + +/* + * 64k aligned address free up few of the lower bits of RPN for us + * We steal that here. For more deatils look at pte_pfn/pfn_pte() + */ +#define H_PAGE_COMBO _RPAGE_RPN0 /* this is a combo 4k page */ +#define H_PAGE_4K_PFN _RPAGE_RPN1 /* PFN is for a single 4k page */ +#define H_PAGE_BUSY _RPAGE_RSV1 /* software: PTE & hash are busy */ +#define H_PAGE_HASHPTE _RPAGE_RPN43 /* PTE has associated HPTE */ + +/* memory key bits. */ +#define H_PTE_PKEY_BIT4 _RPAGE_PKEY_BIT4 +#define H_PTE_PKEY_BIT3 _RPAGE_PKEY_BIT3 +#define H_PTE_PKEY_BIT2 _RPAGE_PKEY_BIT2 +#define H_PTE_PKEY_BIT1 _RPAGE_PKEY_BIT1 +#define H_PTE_PKEY_BIT0 _RPAGE_PKEY_BIT0 + +/* + * We need to differentiate between explicit huge page and THP huge + * page, since THP huge page also need to track real subpage details + */ +#define H_PAGE_THP_HUGE H_PAGE_4K_PFN + +/* PTE flags to conserve for HPTE identification */ +#define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_HASHPTE | H_PAGE_COMBO) +/* + * We use a 2K PTE page fragment and another 2K for storing + * real_pte_t hash index + * 8 bytes per each pte entry and another 8 bytes for storing + * slot details. + */ +#define H_PTE_FRAG_SIZE_SHIFT (H_PTE_INDEX_SIZE + 3 + 1) +#define H_PTE_FRAG_NR (PAGE_SIZE >> H_PTE_FRAG_SIZE_SHIFT) + +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE) +#define H_PMD_FRAG_SIZE_SHIFT (H_PMD_INDEX_SIZE + 3 + 1) +#else +#define H_PMD_FRAG_SIZE_SHIFT (H_PMD_INDEX_SIZE + 3) +#endif +#define H_PMD_FRAG_NR (PAGE_SIZE >> H_PMD_FRAG_SIZE_SHIFT) + +#ifndef __ASSEMBLY__ +#include <asm/errno.h> + +/* + * With 64K pages on hash table, we have a special PTE format that + * uses a second "half" of the page table to encode sub-page information + * in order to deal with 64K made of 4K HW pages. Thus we override the + * generic accessors and iterators here + */ +#define __real_pte __real_pte +static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep, int offset) +{ + real_pte_t rpte; + unsigned long *hidxp; + + rpte.pte = pte; + + /* + * Ensure that we do not read the hidx before we read the PTE. Because + * the writer side is expected to finish writing the hidx first followed + * by the PTE, by using smp_wmb(). pte_set_hash_slot() ensures that. + */ + smp_rmb(); + + hidxp = (unsigned long *)(ptep + offset); + rpte.hidx = *hidxp; + return rpte; +} + +/* + * shift the hidx representation by one-modulo-0xf; i.e hidx 0 is respresented + * as 1, 1 as 2,... , and 0xf as 0. This convention lets us represent a + * invalid hidx 0xf with a 0x0 bit value. PTEs are anyway zero'd when + * allocated. We dont have to zero them gain; thus save on the initialization. + */ +#define HIDX_UNSHIFT_BY_ONE(x) ((x + 0xfUL) & 0xfUL) /* shift backward by one */ +#define HIDX_SHIFT_BY_ONE(x) ((x + 0x1UL) & 0xfUL) /* shift forward by one */ +#define HIDX_BITS(x, index) (x << (index << 2)) +#define BITS_TO_HIDX(x, index) ((x >> (index << 2)) & 0xfUL) +#define INVALID_RPTE_HIDX 0x0UL + +static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index) +{ + return HIDX_UNSHIFT_BY_ONE(BITS_TO_HIDX(rpte.hidx, index)); +} + +/* + * Commit the hidx and return PTE bits that needs to be modified. The caller is + * expected to modify the PTE bits accordingly and commit the PTE to memory. + */ +static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte, + unsigned int subpg_index, + unsigned long hidx, int offset) +{ + unsigned long *hidxp = (unsigned long *)(ptep + offset); + + rpte.hidx &= ~HIDX_BITS(0xfUL, subpg_index); + *hidxp = rpte.hidx | HIDX_BITS(HIDX_SHIFT_BY_ONE(hidx), subpg_index); + + /* + * Anyone reading PTE must ensure hidx bits are read after reading the + * PTE by using the read-side barrier smp_rmb(). __real_pte() can be + * used for that. + */ + smp_wmb(); + + /* No PTE bits to be modified, return 0x0UL */ + return 0x0UL; +} + +#define __rpte_to_pte(r) ((r).pte) +extern bool __rpte_sub_valid(real_pte_t rpte, unsigned long index); +/* + * Trick: we set __end to va + 64k, which happens works for + * a 16M page as well as we want only one iteration + */ +#define pte_iterate_hashed_subpages(rpte, psize, vpn, index, shift) \ + do { \ + unsigned long __end = vpn + (1UL << (PAGE_SHIFT - VPN_SHIFT)); \ + unsigned __split = (psize == MMU_PAGE_4K || \ + psize == MMU_PAGE_64K_AP); \ + shift = mmu_psize_defs[psize].shift; \ + for (index = 0; vpn < __end; index++, \ + vpn += (1L << (shift - VPN_SHIFT))) { \ + if (!__split || __rpte_sub_valid(rpte, index)) + +#define pte_iterate_hashed_end() } } while(0) + +#define pte_pagesize_index(mm, addr, pte) \ + (((pte) & H_PAGE_COMBO)? MMU_PAGE_4K: MMU_PAGE_64K) + +extern int remap_pfn_range(struct vm_area_struct *, unsigned long addr, + unsigned long pfn, unsigned long size, pgprot_t); +static inline int hash__remap_4k_pfn(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t prot) +{ + if (pfn > (PTE_RPN_MASK >> PAGE_SHIFT)) { + WARN(1, "remap_4k_pfn called with wrong pfn value\n"); + return -EINVAL; + } + return remap_pfn_range(vma, addr, pfn, PAGE_SIZE, + __pgprot(pgprot_val(prot) | H_PAGE_4K_PFN)); +} + +#define H_PTE_TABLE_SIZE PTE_FRAG_SIZE +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined (CONFIG_HUGETLB_PAGE) +#define H_PMD_TABLE_SIZE ((sizeof(pmd_t) << PMD_INDEX_SIZE) + \ + (sizeof(unsigned long) << PMD_INDEX_SIZE)) +#else +#define H_PMD_TABLE_SIZE (sizeof(pmd_t) << PMD_INDEX_SIZE) +#endif +#ifdef CONFIG_HUGETLB_PAGE +#define H_PUD_TABLE_SIZE ((sizeof(pud_t) << PUD_INDEX_SIZE) + \ + (sizeof(unsigned long) << PUD_INDEX_SIZE)) +#else +#define H_PUD_TABLE_SIZE (sizeof(pud_t) << PUD_INDEX_SIZE) +#endif +#define H_PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE) + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline char *get_hpte_slot_array(pmd_t *pmdp) +{ + /* + * The hpte hindex is stored in the pgtable whose address is in the + * second half of the PMD + * + * Order this load with the test for pmd_trans_huge in the caller + */ + smp_rmb(); + return *(char **)(pmdp + PTRS_PER_PMD); + + +} +/* + * 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. + * [ 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 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] & 0x1; +} + +static inline unsigned int hpte_hash_index(unsigned char *hpte_slot_array, + int index) +{ + 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 << 1) | 0x1; +} + +/* + * + * For core kernel code by design pmd_trans_huge is never run on any hugetlbfs + * page. The hugetlbfs page table walking and mangling paths are totally + * separated form the core VM paths and they're differentiated by + * VM_HUGETLB being set on vm_flags well before any pmd_trans_huge could run. + * + * pmd_trans_huge() is defined as false at build time if + * CONFIG_TRANSPARENT_HUGEPAGE=n to optimize away code blocks at build + * time in such case. + * + * For ppc64 we need to differntiate from explicit hugepages from THP, because + * for THP we also track the subpage details at the pmd level. We don't do + * that for explicit huge pages. + * + */ +static inline int hash__pmd_trans_huge(pmd_t pmd) +{ + return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP)) == + (_PAGE_PTE | H_PAGE_THP_HUGE)); +} + +static inline int hash__pmd_same(pmd_t pmd_a, pmd_t pmd_b) +{ + return (((pmd_raw(pmd_a) ^ pmd_raw(pmd_b)) & ~cpu_to_be64(_PAGE_HPTEFLAGS)) == 0); +} + +static inline pmd_t hash__pmd_mkhuge(pmd_t pmd) +{ + return __pmd(pmd_val(pmd) | (_PAGE_PTE | H_PAGE_THP_HUGE)); +} + +extern unsigned long hash__pmd_hugepage_update(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp, + unsigned long clr, unsigned long set); +extern pmd_t hash__pmdp_collapse_flush(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); +extern void hash__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable); +extern pgtable_t hash__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); +extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp); +extern int hash__has_transparent_hugepage(void); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd) +{ + return __pmd(pmd_val(pmd) | (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP)); +} + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_POWERPC_BOOK3S_64_HASH_64K_H */ diff --git a/arch/powerpc/include/asm/book3s/64/hash-pkey.h b/arch/powerpc/include/asm/book3s/64/hash-pkey.h new file mode 100644 index 000000000..795010897 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/hash-pkey.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_HASH_PKEY_H +#define _ASM_POWERPC_BOOK3S_64_HASH_PKEY_H + +static inline u64 hash__vmflag_to_pte_pkey_bits(u64 vm_flags) +{ + return (((vm_flags & VM_PKEY_BIT0) ? H_PTE_PKEY_BIT0 : 0x0UL) | + ((vm_flags & VM_PKEY_BIT1) ? H_PTE_PKEY_BIT1 : 0x0UL) | + ((vm_flags & VM_PKEY_BIT2) ? H_PTE_PKEY_BIT2 : 0x0UL) | + ((vm_flags & VM_PKEY_BIT3) ? H_PTE_PKEY_BIT3 : 0x0UL) | + ((vm_flags & VM_PKEY_BIT4) ? H_PTE_PKEY_BIT4 : 0x0UL)); +} + +static inline u64 pte_to_hpte_pkey_bits(u64 pteflags) +{ + return (((pteflags & H_PTE_PKEY_BIT4) ? HPTE_R_KEY_BIT4 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT3) ? HPTE_R_KEY_BIT3 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT2) ? HPTE_R_KEY_BIT2 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT1) ? HPTE_R_KEY_BIT1 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT0) ? HPTE_R_KEY_BIT0 : 0x0UL)); +} + +static inline u16 hash__pte_to_pkey_bits(u64 pteflags) +{ + return (((pteflags & H_PTE_PKEY_BIT4) ? 0x10 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT3) ? 0x8 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT2) ? 0x4 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT1) ? 0x2 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT0) ? 0x1 : 0x0UL)); +} + +#endif diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h new file mode 100644 index 000000000..73ad038ed --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -0,0 +1,260 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_HASH_H +#define _ASM_POWERPC_BOOK3S_64_HASH_H +#ifdef __KERNEL__ + +#include <asm/asm-const.h> + +/* + * Common bits between 4K and 64K pages in a linux-style PTE. + * Additional bits may be defined in pgtable-hash64-*.h + * + */ +#define H_PTE_NONE_MASK _PAGE_HPTEFLAGS + +#ifdef CONFIG_PPC_64K_PAGES +#include <asm/book3s/64/hash-64k.h> +#else +#include <asm/book3s/64/hash-4k.h> +#endif + +/* Bits to set in a PMD/PUD/PGD entry valid bit*/ +#define HASH_PMD_VAL_BITS (0x8000000000000000UL) +#define HASH_PUD_VAL_BITS (0x8000000000000000UL) +#define HASH_PGD_VAL_BITS (0x8000000000000000UL) + +/* + * Size of EA range mapped by our pagetables. + */ +#define H_PGTABLE_EADDR_SIZE (H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE + \ + H_PUD_INDEX_SIZE + H_PGD_INDEX_SIZE + PAGE_SHIFT) +#define H_PGTABLE_RANGE (ASM_CONST(1) << H_PGTABLE_EADDR_SIZE) +/* + * Top 2 bits are ignored in page table walk. + */ +#define EA_MASK (~(0xcUL << 60)) + +/* + * We store the slot details in the second half of page table. + * Increase the pud level table so that hugetlb ptes can be stored + * at pud level. + */ +#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_PPC_64K_PAGES) +#define H_PUD_CACHE_INDEX (H_PUD_INDEX_SIZE + 1) +#else +#define H_PUD_CACHE_INDEX (H_PUD_INDEX_SIZE) +#endif + +/* + * +------------------------------+ + * | | + * | | + * | | + * +------------------------------+ Kernel virtual map end (0xc00e000000000000) + * | | + * | | + * | 512TB/16TB of vmemmap | + * | | + * | | + * +------------------------------+ Kernel vmemmap start + * | | + * | 512TB/16TB of IO map | + * | | + * +------------------------------+ Kernel IO map start + * | | + * | 512TB/16TB of vmap | + * | | + * +------------------------------+ Kernel virt start (0xc008000000000000) + * | | + * | | + * | | + * +------------------------------+ Kernel linear (0xc.....) + */ + +#define H_VMALLOC_START H_KERN_VIRT_START +#define H_VMALLOC_SIZE H_KERN_MAP_SIZE +#define H_VMALLOC_END (H_VMALLOC_START + H_VMALLOC_SIZE) + +#define H_KERN_IO_START H_VMALLOC_END +#define H_KERN_IO_SIZE H_KERN_MAP_SIZE +#define H_KERN_IO_END (H_KERN_IO_START + H_KERN_IO_SIZE) + +#define H_VMEMMAP_START H_KERN_IO_END +#define H_VMEMMAP_SIZE H_KERN_MAP_SIZE +#define H_VMEMMAP_END (H_VMEMMAP_START + H_VMEMMAP_SIZE) + +#define NON_LINEAR_REGION_ID(ea) ((((unsigned long)ea - H_KERN_VIRT_START) >> REGION_SHIFT) + 2) + +/* + * Region IDs + */ +#define USER_REGION_ID 0 +#define LINEAR_MAP_REGION_ID 1 +#define VMALLOC_REGION_ID NON_LINEAR_REGION_ID(H_VMALLOC_START) +#define IO_REGION_ID NON_LINEAR_REGION_ID(H_KERN_IO_START) +#define VMEMMAP_REGION_ID NON_LINEAR_REGION_ID(H_VMEMMAP_START) +#define INVALID_REGION_ID (VMEMMAP_REGION_ID + 1) + +/* + * Defines the address of the vmemap area, in its own region on + * hash table CPUs. + */ +#ifdef CONFIG_PPC_MM_SLICES +#define HAVE_ARCH_UNMAPPED_AREA +#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN +#endif /* CONFIG_PPC_MM_SLICES */ + +/* PTEIDX nibble */ +#define _PTEIDX_SECONDARY 0x8 +#define _PTEIDX_GROUP_IX 0x7 + +#define H_PMD_BAD_BITS (PTE_TABLE_SIZE-1) +#define H_PUD_BAD_BITS (PMD_TABLE_SIZE-1) + +#ifndef __ASSEMBLY__ +static inline int get_region_id(unsigned long ea) +{ + int region_id; + int id = (ea >> 60UL); + + if (id == 0) + return USER_REGION_ID; + + if (id != (PAGE_OFFSET >> 60)) + return INVALID_REGION_ID; + + if (ea < H_KERN_VIRT_START) + return LINEAR_MAP_REGION_ID; + + BUILD_BUG_ON(NON_LINEAR_REGION_ID(H_VMALLOC_START) != 2); + + region_id = NON_LINEAR_REGION_ID(ea); + return region_id; +} + +#define hash__pmd_bad(pmd) (pmd_val(pmd) & H_PMD_BAD_BITS) +#define hash__pud_bad(pud) (pud_val(pud) & H_PUD_BAD_BITS) +static inline int hash__p4d_bad(p4d_t p4d) +{ + return (p4d_val(p4d) == 0); +} +#ifdef CONFIG_STRICT_KERNEL_RWX +extern void hash__mark_rodata_ro(void); +extern void hash__mark_initmem_nx(void); +#endif + +extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, unsigned long pte, int huge); +extern unsigned long htab_convert_pte_flags(unsigned long pteflags); +/* Atomic PTE updates */ +static inline unsigned long hash__pte_update(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, unsigned long clr, + unsigned long set, + int huge) +{ + __be64 old_be, tmp_be; + unsigned long old; + + __asm__ __volatile__( + "1: ldarx %0,0,%3 # pte_update\n\ + and. %1,%0,%6\n\ + bne- 1b \n\ + andc %1,%0,%4 \n\ + or %1,%1,%7\n\ + stdcx. %1,0,%3 \n\ + bne- 1b" + : "=&r" (old_be), "=&r" (tmp_be), "=m" (*ptep) + : "r" (ptep), "r" (cpu_to_be64(clr)), "m" (*ptep), + "r" (cpu_to_be64(H_PAGE_BUSY)), "r" (cpu_to_be64(set)) + : "cc" ); + /* huge pages use the old page table lock */ + if (!huge) + assert_pte_locked(mm, addr); + + old = be64_to_cpu(old_be); + if (old & H_PAGE_HASHPTE) + hpte_need_flush(mm, addr, ptep, old, huge); + + return old; +} + +/* Set the dirty and/or accessed bits atomically in a linux PTE, this + * function doesn't need to flush the hash entry + */ +static inline void hash__ptep_set_access_flags(pte_t *ptep, pte_t entry) +{ + __be64 old, tmp, val, mask; + + mask = cpu_to_be64(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_READ | _PAGE_WRITE | + _PAGE_EXEC | _PAGE_SOFT_DIRTY); + + val = pte_raw(entry) & mask; + + __asm__ __volatile__( + "1: ldarx %0,0,%4\n\ + and. %1,%0,%6\n\ + bne- 1b \n\ + or %0,%3,%0\n\ + stdcx. %0,0,%4\n\ + bne- 1b" + :"=&r" (old), "=&r" (tmp), "=m" (*ptep) + :"r" (val), "r" (ptep), "m" (*ptep), "r" (cpu_to_be64(H_PAGE_BUSY)) + :"cc"); +} + +static inline int hash__pte_same(pte_t pte_a, pte_t pte_b) +{ + return (((pte_raw(pte_a) ^ pte_raw(pte_b)) & ~cpu_to_be64(_PAGE_HPTEFLAGS)) == 0); +} + +static inline int hash__pte_none(pte_t pte) +{ + return (pte_val(pte) & ~H_PTE_NONE_MASK) == 0; +} + +unsigned long pte_get_hash_gslot(unsigned long vpn, unsigned long shift, + int ssize, real_pte_t rpte, unsigned int subpg_index); + +/* This low level function performs the actual PTE insertion + * Setting the PTE depends on the MMU type and other factors. It's + * an horrible mess that I'm not going to try to clean up now but + * I'm keeping it in one place rather than spread around + */ +static inline void hash__set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, int percpu) +{ + /* + * Anything else just stores the PTE normally. That covers all 64-bit + * cases, and 32-bit non-hash with 32-bit PTEs. + */ + *ptep = pte; +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, unsigned long old_pmd); +#else +static inline void hpte_do_hugepage_flush(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp, + unsigned long old_pmd) +{ + WARN(1, "%s called with THP disabled\n", __func__); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + + +int hash__map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot); +extern int __meminit hash__vmemmap_create_mapping(unsigned long start, + unsigned long page_size, + unsigned long phys); +extern void hash__vmemmap_remove_mapping(unsigned long start, + unsigned long page_size); + +int hash__create_section_mapping(unsigned long start, unsigned long end, + int nid, pgprot_t prot); +int hash__remove_section_mapping(unsigned long start, unsigned long end); + +#endif /* !__ASSEMBLY__ */ +#endif /* __KERNEL__ */ +#endif /* _ASM_POWERPC_BOOK3S_64_HASH_H */ diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h new file mode 100644 index 000000000..12e150e61 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h @@ -0,0 +1,136 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_HUGETLB_H +#define _ASM_POWERPC_BOOK3S_64_HUGETLB_H +/* + * For radix we want generic code to handle hugetlb. But then if we want + * both hash and radix to be enabled together we need to workaround the + * limitations. + */ +void radix__flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr); +void radix__local_flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr); +extern unsigned long +radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); + +extern void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t pte); + +static inline int hstate_get_psize(struct hstate *hstate) +{ + unsigned long shift; + + shift = huge_page_shift(hstate); + if (shift == mmu_psize_defs[MMU_PAGE_2M].shift) + return MMU_PAGE_2M; + else if (shift == mmu_psize_defs[MMU_PAGE_1G].shift) + return MMU_PAGE_1G; + else if (shift == mmu_psize_defs[MMU_PAGE_16M].shift) + return MMU_PAGE_16M; + else if (shift == mmu_psize_defs[MMU_PAGE_16G].shift) + return MMU_PAGE_16G; + else { + WARN(1, "Wrong huge page shift\n"); + return mmu_virtual_psize; + } +} + +#define __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED +static inline bool gigantic_page_runtime_supported(void) +{ + /* + * We used gigantic page reservation with hypervisor assist in some case. + * We cannot use runtime allocation of gigantic pages in those platforms + * This is hash translation mode LPARs. + */ + if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled()) + return false; + + return true; +} + +/* hugepd entry valid bit */ +#define HUGEPD_VAL_BITS (0x8000000000000000UL) + +#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start +extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); + +#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit +extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t new_pte); +/* + * This should work for other subarchs too. But right now we use the + * new format only for 64bit book3s + */ +static inline pte_t *hugepd_page(hugepd_t hpd) +{ + BUG_ON(!hugepd_ok(hpd)); + /* + * We have only four bits to encode, MMU page size + */ + BUILD_BUG_ON((MMU_PAGE_COUNT - 1) > 0xf); + return __va(hpd_val(hpd) & HUGEPD_ADDR_MASK); +} + +static inline unsigned int hugepd_mmu_psize(hugepd_t hpd) +{ + return (hpd_val(hpd) & HUGEPD_SHIFT_MASK) >> 2; +} + +static inline unsigned int hugepd_shift(hugepd_t hpd) +{ + return mmu_psize_to_shift(hugepd_mmu_psize(hpd)); +} +static inline void flush_hugetlb_page(struct vm_area_struct *vma, + unsigned long vmaddr) +{ + if (radix_enabled()) + return radix__flush_hugetlb_page(vma, vmaddr); +} + +static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr, + unsigned int pdshift) +{ + unsigned long idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(hpd); + + return hugepd_page(hpd) + idx; +} + +static inline void hugepd_populate(hugepd_t *hpdp, pte_t *new, unsigned int pshift) +{ + *hpdp = __hugepd(__pa(new) | HUGEPD_VAL_BITS | (shift_to_mmu_psize(pshift) << 2)); +} + +void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr); + +static inline int check_and_get_huge_psize(int shift) +{ + int mmu_psize; + + if (shift > SLICE_HIGH_SHIFT) + return -EINVAL; + + mmu_psize = shift_to_mmu_psize(shift); + + /* + * We need to make sure that for different page sizes reported by + * firmware we only add hugetlb support for page sizes that can be + * supported by linux page table layout. + * For now we have + * Radix: 2M and 1G + * Hash: 16M and 16G + */ + if (radix_enabled()) { + if (mmu_psize != MMU_PAGE_2M && mmu_psize != MMU_PAGE_1G) + return -EINVAL; + } else { + if (mmu_psize != MMU_PAGE_16M && mmu_psize != MMU_PAGE_16G) + return -EINVAL; + } + return mmu_psize; +} + +#endif diff --git a/arch/powerpc/include/asm/book3s/64/kexec.h b/arch/powerpc/include/asm/book3s/64/kexec.h new file mode 100644 index 000000000..6b5c3a248 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/kexec.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_POWERPC_BOOK3S_64_KEXEC_H_ +#define _ASM_POWERPC_BOOK3S_64_KEXEC_H_ + + +#define reset_sprs reset_sprs +static inline void reset_sprs(void) +{ + if (cpu_has_feature(CPU_FTR_ARCH_206)) { + mtspr(SPRN_AMR, 0); + mtspr(SPRN_UAMOR, 0); + } + + if (cpu_has_feature(CPU_FTR_ARCH_207S)) { + mtspr(SPRN_IAMR, 0); + } + + /* Do we need isync()? We are going via a kexec reset */ + isync(); +} + +#endif diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h new file mode 100644 index 000000000..a39e2d193 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h @@ -0,0 +1,205 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H +#define _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H + +#include <linux/const.h> +#include <asm/reg.h> + +#define AMR_KUAP_BLOCK_READ UL(0x4000000000000000) +#define AMR_KUAP_BLOCK_WRITE UL(0x8000000000000000) +#define AMR_KUAP_BLOCKED (AMR_KUAP_BLOCK_READ | AMR_KUAP_BLOCK_WRITE) +#define AMR_KUAP_SHIFT 62 + +#ifdef __ASSEMBLY__ + +.macro kuap_restore_amr gpr1, gpr2 +#ifdef CONFIG_PPC_KUAP + BEGIN_MMU_FTR_SECTION_NESTED(67) + mfspr \gpr1, SPRN_AMR + ld \gpr2, STACK_REGS_KUAP(r1) + cmpd \gpr1, \gpr2 + beq 998f + isync + mtspr SPRN_AMR, \gpr2 + /* No isync required, see kuap_restore_amr() */ +998: + END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_RADIX_KUAP, 67) +#endif +.endm + +#ifdef CONFIG_PPC_KUAP +.macro kuap_check_amr gpr1, gpr2 +#ifdef CONFIG_PPC_KUAP_DEBUG + BEGIN_MMU_FTR_SECTION_NESTED(67) + mfspr \gpr1, SPRN_AMR + li \gpr2, (AMR_KUAP_BLOCKED >> AMR_KUAP_SHIFT) + sldi \gpr2, \gpr2, AMR_KUAP_SHIFT +999: tdne \gpr1, \gpr2 + EMIT_BUG_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE) + END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_RADIX_KUAP, 67) +#endif +.endm +#endif + +.macro kuap_save_amr_and_lock gpr1, gpr2, use_cr, msr_pr_cr +#ifdef CONFIG_PPC_KUAP + BEGIN_MMU_FTR_SECTION_NESTED(67) + .ifnb \msr_pr_cr + bne \msr_pr_cr, 99f + .endif + mfspr \gpr1, SPRN_AMR + std \gpr1, STACK_REGS_KUAP(r1) + li \gpr2, (AMR_KUAP_BLOCKED >> AMR_KUAP_SHIFT) + sldi \gpr2, \gpr2, AMR_KUAP_SHIFT + cmpd \use_cr, \gpr1, \gpr2 + beq \use_cr, 99f + // We don't isync here because we very recently entered via rfid + mtspr SPRN_AMR, \gpr2 + isync +99: + END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_RADIX_KUAP, 67) +#endif +.endm + +#else /* !__ASSEMBLY__ */ + +#include <linux/jump_label.h> + +DECLARE_STATIC_KEY_FALSE(uaccess_flush_key); + +#ifdef CONFIG_PPC_KUAP + +#include <asm/mmu.h> +#include <asm/ptrace.h> + +static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr) +{ + if (mmu_has_feature(MMU_FTR_RADIX_KUAP) && unlikely(regs->kuap != amr)) { + isync(); + mtspr(SPRN_AMR, regs->kuap); + /* + * No isync required here because we are about to RFI back to + * previous context before any user accesses would be made, + * which is a CSI. + */ + } +} + +static inline unsigned long kuap_get_and_check_amr(void) +{ + if (mmu_has_feature(MMU_FTR_RADIX_KUAP)) { + unsigned long amr = mfspr(SPRN_AMR); + if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG)) /* kuap_check_amr() */ + WARN_ON_ONCE(amr != AMR_KUAP_BLOCKED); + return amr; + } + return 0; +} + +static inline void kuap_check_amr(void) +{ + if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG) && mmu_has_feature(MMU_FTR_RADIX_KUAP)) + WARN_ON_ONCE(mfspr(SPRN_AMR) != AMR_KUAP_BLOCKED); +} + +/* + * We support individually allowing read or write, but we don't support nesting + * because that would require an expensive read/modify write of the AMR. + */ + +static inline unsigned long get_kuap(void) +{ + /* + * We return AMR_KUAP_BLOCKED when we don't support KUAP because + * prevent_user_access_return needs to return AMR_KUAP_BLOCKED to + * cause restore_user_access to do a flush. + * + * This has no effect in terms of actually blocking things on hash, + * so it doesn't break anything. + */ + if (!early_mmu_has_feature(MMU_FTR_RADIX_KUAP)) + return AMR_KUAP_BLOCKED; + + return mfspr(SPRN_AMR); +} + +static inline void set_kuap(unsigned long value) +{ + if (!early_mmu_has_feature(MMU_FTR_RADIX_KUAP)) + return; + + /* + * ISA v3.0B says we need a CSI (Context Synchronising Instruction) both + * before and after the move to AMR. See table 6 on page 1134. + */ + isync(); + mtspr(SPRN_AMR, value); + isync(); +} + +static inline bool +bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) +{ + return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) && + (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)), + "Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read"); +} +#else /* CONFIG_PPC_KUAP */ +static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr) { } + +static inline unsigned long kuap_get_and_check_amr(void) +{ + return 0UL; +} + +static inline unsigned long get_kuap(void) +{ + return AMR_KUAP_BLOCKED; +} + +static inline void set_kuap(unsigned long value) { } +#endif /* !CONFIG_PPC_KUAP */ + +static __always_inline void allow_user_access(void __user *to, const void __user *from, + unsigned long size, unsigned long dir) +{ + // This is written so we can resolve to a single case at build time + BUILD_BUG_ON(!__builtin_constant_p(dir)); + if (dir == KUAP_READ) + set_kuap(AMR_KUAP_BLOCK_WRITE); + else if (dir == KUAP_WRITE) + set_kuap(AMR_KUAP_BLOCK_READ); + else if (dir == KUAP_READ_WRITE) + set_kuap(0); + else + BUILD_BUG(); +} + +static inline void prevent_user_access(void __user *to, const void __user *from, + unsigned long size, unsigned long dir) +{ + set_kuap(AMR_KUAP_BLOCKED); + if (static_branch_unlikely(&uaccess_flush_key)) + do_uaccess_flush(); +} + +static inline unsigned long prevent_user_access_return(void) +{ + unsigned long flags = get_kuap(); + + set_kuap(AMR_KUAP_BLOCKED); + if (static_branch_unlikely(&uaccess_flush_key)) + do_uaccess_flush(); + + return flags; +} + +static inline void restore_user_access(unsigned long flags) +{ + set_kuap(flags); + if (static_branch_unlikely(&uaccess_flush_key) && flags == AMR_KUAP_BLOCKED) + do_uaccess_flush(); +} +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H */ 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..683a9c7d1 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -0,0 +1,847 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_POWERPC_BOOK3S_64_MMU_HASH_H_ +#define _ASM_POWERPC_BOOK3S_64_MMU_HASH_H_ +/* + * PowerPC64 memory management structures + * + * Dave Engebretsen & Mike Corrigan <{engebret|mikejc}@us.ibm.com> + * PPC64 rework. + */ + +#include <asm/page.h> +#include <asm/bug.h> +#include <asm/asm-const.h> + +/* + * 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 <asm/book3s/64/pgtable.h> +#include <asm/bug.h> +#include <asm/task_size_64.h> +#include <asm/cpu_has_feature.h> + +/* + * SLB + */ + +#define SLB_NUM_BOLTED 2 +#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_256M SLB_VSID_SHIFT +#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_COMMON_BITS ASM_CONST(0x000fffffffffffff) +#define HPTE_V_AVPN ASM_CONST(0x3fffffffffffff80) +#define HPTE_V_AVPN_3_0 ASM_CONST(0x000fffffffffff80) +#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) + +/* + * ISA 3.0 has a different HPTE format. + */ +#define HPTE_R_3_0_SSIZE_SHIFT 58 +#define HPTE_R_3_0_SSIZE_MASK (3ull << HPTE_R_3_0_SSIZE_SHIFT) +#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_KEY_BIT4 ASM_CONST(0x2000000000000000) +#define HPTE_R_KEY_BIT3 ASM_CONST(0x1000000000000000) +#define HPTE_R_RPN_SHIFT 12 +#define HPTE_R_RPN ASM_CONST(0x0ffffffffffff000) +#define HPTE_R_RPN_3_0 ASM_CONST(0x01fffffffffff000) +#define HPTE_R_PP ASM_CONST(0x0000000000000003) +#define HPTE_R_PPP ASM_CONST(0x8000000000000003) +#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_R_KEY_BIT2 ASM_CONST(0x0000000000000800) +#define HPTE_R_KEY_BIT1 ASM_CONST(0x0000000000000400) +#define HPTE_R_KEY_BIT0 ASM_CONST(0x0000000000000200) +#define HPTE_R_KEY (HPTE_R_KEY_LO | HPTE_R_KEY_HI) + +#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 */ +#define POWER9_TLB_SETS_RADIX 128 /* # sets in POWER9 TLB Radix mode */ + +#ifndef __ASSEMBLY__ + +struct mmu_hash_ops { + void (*hpte_invalidate)(unsigned long slot, + unsigned long vpn, + int bpsize, int apsize, + int ssize, int local); + long (*hpte_updatepp)(unsigned long slot, + unsigned long newpp, + unsigned long vpn, + int bpsize, int apsize, + int ssize, unsigned long flags); + void (*hpte_updateboltedpp)(unsigned long newpp, + unsigned long ea, + int psize, int ssize); + long (*hpte_insert)(unsigned long hpte_group, + unsigned long vpn, + unsigned long prpn, + unsigned long rflags, + unsigned long vflags, + int psize, int apsize, + int ssize); + long (*hpte_remove)(unsigned long hpte_group); + int (*hpte_removebolted)(unsigned long ea, + int psize, int ssize); + void (*flush_hash_range)(unsigned long number, int local); + void (*hugepage_invalidate)(unsigned long vsid, + unsigned long addr, + unsigned char *hpte_slot_array, + int psize, int ssize, int local); + int (*resize_hpt)(unsigned long shift); + /* + * Special for kexec. + * To be called in real mode with interrupts disabled. No locks are + * taken as such, concurrent access on pre POWER5 hardware could result + * in a deadlock. + * The linear mapping is destroyed as well. + */ + void (*hpte_clear_all)(void); +}; +extern struct mmu_hash_ops mmu_hash_ops; + +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; + + +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(); +} + +static inline unsigned int ap_to_shift(unsigned long ap) +{ + int psize; + + for (psize = 0; psize < MMU_PAGE_COUNT; psize++) { + if (mmu_psize_defs[psize].ap == ap) + return mmu_psize_defs[psize].shift; + } + + return -1; +} + +static inline unsigned long get_sllp_encoding(int psize) +{ + unsigned long sllp; + + sllp = ((mmu_psize_defs[psize].sllp & SLB_VSID_L) >> 6) | + ((mmu_psize_defs[psize].sllp & SLB_VSID_LP) >> 4); + return sllp; +} + +#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; +} + +/* + * This array is indexed by the LP field of the HPTE second dword. + * Since this field may contain some RPN bits, some entries are + * replicated so that we get the same value irrespective of RPN. + * The top 4 bits are the page size index (MMU_PAGE_*) for the + * actual page size, the bottom 4 bits are the base page size. + */ +extern u8 hpte_page_sizes[1 << LP_BITS]; + +static inline unsigned long __hpte_page_size(unsigned long h, unsigned long l, + bool is_base_size) +{ + unsigned int i, lp; + + if (!(h & HPTE_V_LARGE)) + return 1ul << 12; + + /* Look at the 8 bit LP value */ + lp = (l >> LP_SHIFT) & ((1 << LP_BITS) - 1); + i = hpte_page_sizes[lp]; + if (!i) + return 0; + if (!is_base_size) + i >>= 4; + return 1ul << mmu_psize_defs[i & 0xf].shift; +} + +static inline unsigned long hpte_page_size(unsigned long h, unsigned long l) +{ + return __hpte_page_size(h, l, 0); +} + +static inline unsigned long hpte_base_page_size(unsigned long h, unsigned long l) +{ + return __hpte_page_size(h, l, 1); +} + +/* + * The current system page and segment sizes + */ +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; +} + +/* + * ISA v3.0 defines a new HPTE format, which differs from the old + * format in having smaller AVPN and ARPN fields, and the B field + * in the second dword instead of the first. + */ +static inline unsigned long hpte_old_to_new_v(unsigned long v) +{ + /* trim AVPN, drop B */ + return v & HPTE_V_COMMON_BITS; +} + +static inline unsigned long hpte_old_to_new_r(unsigned long v, unsigned long r) +{ + /* move B field from 1st to 2nd dword, trim ARPN */ + return (r & ~HPTE_R_3_0_SSIZE_MASK) | + (((v) >> HPTE_V_SSIZE_SHIFT) << HPTE_R_3_0_SSIZE_SHIFT); +} + +static inline unsigned long hpte_new_to_old_v(unsigned long v, unsigned long r) +{ + /* insert B field */ + return (v & HPTE_V_COMMON_BITS) | + ((r & HPTE_R_3_0_SSIZE_MASK) << + (HPTE_V_SSIZE_SHIFT - HPTE_R_3_0_SSIZE_SHIFT)); +} + +static inline unsigned long hpte_new_to_old_r(unsigned long r) +{ + /* clear out B field */ + return r & ~HPTE_R_3_0_SSIZE_MASK; +} + +static inline unsigned long hpte_get_old_v(struct hash_pte *hptep) +{ + unsigned long hpte_v; + + hpte_v = be64_to_cpu(hptep->v); + if (cpu_has_feature(CPU_FTR_ARCH_300)) + hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r)); + return hpte_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) +{ + unsigned long 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 pseries_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 hash__setup_new_exec(void); + +#ifdef CONFIG_PPC_PSERIES +void hpte_init_pseries(void); +#else +static inline void hpte_init_pseries(void) { } +#endif + +extern void hpte_init_native(void); + +struct slb_entry { + u64 esid; + u64 vsid; +}; + +extern void slb_initialize(void); +void slb_flush_and_restore_bolted(void); +void slb_flush_all_realmode(void); +void __slb_restore_bolted_realmode(void); +void slb_restore_bolted_realmode(void); +void slb_save_contents(struct slb_entry *slb_ptr); +void slb_dump_contents(struct slb_entry *slb_ptr); + +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 MAX_USER_CONTEXT. + * more details in get_user_context + * + * For kernel space get_kernel_context + * + * 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 use VSID 0 to indicate an invalid VSID. The means we can't use context id + * 0, because a context id of 0 and an EA of 0 gives a proto-VSID of 0, which + * will produce a VSID of 0. + * + * 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. + */ + +/* + * Max Va bits we support as of now is 68 bits. We want 19 bit + * context ID. + * Restrictions: + * GPU has restrictions of not able to access beyond 128TB + * (47 bit effective address). We also cannot do more than 20bit PID. + * For p4 and p5 which can only do 65 bit VA, we restrict our CONTEXT_BITS + * to 16 bits (ie, we can only have 2^16 pids at the same time). + */ +#define VA_BITS 68 +#define CONTEXT_BITS 19 +#define ESID_BITS (VA_BITS - (SID_SHIFT + CONTEXT_BITS)) +#define ESID_BITS_1T (VA_BITS - (SID_SHIFT_1T + CONTEXT_BITS)) + +#define ESID_BITS_MASK ((1 << ESID_BITS) - 1) +#define ESID_BITS_1T_MASK ((1 << ESID_BITS_1T) - 1) + +/* + * Now certain config support MAX_PHYSMEM more than 512TB. Hence we will need + * to use more than one context for linear mapping the kernel. + * For vmalloc and memmap, we use just one context with 512TB. With 64 byte + * struct page size, we need ony 32 TB in memmap for 2PB (51 bits (MAX_PHYSMEM_BITS)). + */ +#if (H_MAX_PHYSMEM_BITS > MAX_EA_BITS_PER_CONTEXT) +#define MAX_KERNEL_CTX_CNT (1UL << (H_MAX_PHYSMEM_BITS - MAX_EA_BITS_PER_CONTEXT)) +#else +#define MAX_KERNEL_CTX_CNT 1 +#endif + +#define MAX_VMALLOC_CTX_CNT 1 +#define MAX_IO_CTX_CNT 1 +#define MAX_VMEMMAP_CTX_CNT 1 + +/* + * 256MB segment + * The proto-VSID space has 2^(CONTEX_BITS + ESID_BITS) - 1 segments + * available for user + kernel mapping. VSID 0 is reserved as invalid, contexts + * 1-4 are used for kernel mapping. Each segment contains 2^28 bytes. Each + * context maps 2^49 bytes (512TB). + * + * 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. + * + */ +#define MAX_USER_CONTEXT ((ASM_CONST(1) << CONTEXT_BITS) - 2) + +// The + 2 accounts for INVALID_REGION and 1 more to avoid overlap with kernel +#define MIN_USER_CONTEXT (MAX_KERNEL_CTX_CNT + MAX_VMALLOC_CTX_CNT + \ + MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT + 2) + +/* + * For platforms that support on 65bit VA we limit the context bits + */ +#define MAX_USER_CONTEXT_65BIT_VA ((ASM_CONST(1) << (65 - (SID_SHIFT + ESID_BITS))) - 2) + +/* + * This should be computed such that protovosid * vsid_mulitplier + * doesn't overflow 64 bits. The vsid_mutliplier should also be + * co-prime to vsid_modulus. We also need to make sure that number + * of bits in multiplied result (dividend) is less than twice the number of + * protovsid bits for our modulus optmization to work. + * + * The below table shows the current values used. + * |-------+------------+----------------------+------------+-------------------| + * | | Prime Bits | proto VSID_BITS_65VA | Total Bits | 2* prot VSID_BITS | + * |-------+------------+----------------------+------------+-------------------| + * | 1T | 24 | 25 | 49 | 50 | + * |-------+------------+----------------------+------------+-------------------| + * | 256MB | 24 | 37 | 61 | 74 | + * |-------+------------+----------------------+------------+-------------------| + * + * |-------+------------+----------------------+------------+--------------------| + * | | Prime Bits | proto VSID_BITS_68VA | Total Bits | 2* proto VSID_BITS | + * |-------+------------+----------------------+------------+--------------------| + * | 1T | 24 | 28 | 52 | 56 | + * |-------+------------+----------------------+------------+--------------------| + * | 256MB | 24 | 40 | 64 | 80 | + * |-------+------------+----------------------+------------+--------------------| + * + */ +#define VSID_MULTIPLIER_256M ASM_CONST(12538073) /* 24-bit prime */ +#define VSID_BITS_256M (VA_BITS - SID_SHIFT) +#define VSID_BITS_65_256M (65 - SID_SHIFT) +/* + * Modular multiplicative inverse of VSID_MULTIPLIER under modulo VSID_MODULUS + */ +#define VSID_MULINV_256M ASM_CONST(665548017062) + +#define VSID_MULTIPLIER_1T ASM_CONST(12538073) /* 24-bit prime */ +#define VSID_BITS_1T (VA_BITS - SID_SHIFT_1T) +#define VSID_BITS_65_1T (65 - SID_SHIFT_1T) +#define VSID_MULINV_1T ASM_CONST(209034062) + +/* 1TB VSID reserved for VRMA */ +#define VRMA_VSID 0x1ffffffUL +#define USER_VSID_RANGE (1UL << (ESID_BITS + SID_SHIFT)) + +/* 4 bits per slice and we have one slice per 1TB */ +#define SLICE_ARRAY_SIZE (H_PGTABLE_RANGE >> 41) +#define LOW_SLICE_ARRAY_SZ (BITS_PER_LONG / BITS_PER_BYTE) +#define TASK_SLICE_ARRAY_SZ(x) ((x)->hash_context->slb_addr_limit >> 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); +#else +static inline void subpage_prot_free(struct mm_struct *mm) {} +#endif /* CONFIG_PPC_SUBPAGE_PROT */ + +/* + * One bit per slice. We have lower slices which cover 256MB segments + * upto 4G range. That gets us 16 low slices. For the rest we track slices + * in 1TB size. + */ +struct slice_mask { + u64 low_slices; + DECLARE_BITMAP(high_slices, SLICE_NUM_HIGH); +}; + +struct hash_mm_context { + u16 user_psize; /* page size index */ + + /* SLB page size encodings*/ + unsigned char low_slices_psize[LOW_SLICE_ARRAY_SZ]; + unsigned char high_slices_psize[SLICE_ARRAY_SIZE]; + unsigned long slb_addr_limit; +#ifdef CONFIG_PPC_64K_PAGES + struct slice_mask mask_64k; +#endif + struct slice_mask mask_4k; +#ifdef CONFIG_HUGETLB_PAGE + struct slice_mask mask_16m; + struct slice_mask mask_16g; +#endif + +#ifdef CONFIG_PPC_SUBPAGE_PROT + struct subpage_prot_table *spt; +#endif /* CONFIG_PPC_SUBPAGE_PROT */ +}; + +#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)) + +/* simplified form avoiding mod operation */ +#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; \ + }) + +#else /* 1 */ +static inline unsigned long vsid_scramble(unsigned long protovsid, + unsigned long vsid_multiplier, int vsid_bits) +{ + unsigned long vsid; + unsigned long vsid_modulus = ((1UL << vsid_bits) - 1); + /* + * We have same multipler for both 256 and 1T segements now + */ + vsid = protovsid * vsid_multiplier; + vsid = (vsid >> vsid_bits) + (vsid & vsid_modulus); + return (vsid + ((vsid + 1) >> vsid_bits)) & vsid_modulus; +} + +#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) +{ + unsigned long va_bits = VA_BITS; + unsigned long vsid_bits; + unsigned long protovsid; + + /* + * Bad address. We return VSID 0 for that + */ + if ((ea & EA_MASK) >= H_PGTABLE_RANGE) + return 0; + + if (!mmu_has_feature(MMU_FTR_68_BIT_VA)) + va_bits = 65; + + if (ssize == MMU_SEGSIZE_256M) { + vsid_bits = va_bits - SID_SHIFT; + protovsid = (context << ESID_BITS) | + ((ea >> SID_SHIFT) & ESID_BITS_MASK); + return vsid_scramble(protovsid, VSID_MULTIPLIER_256M, vsid_bits); + } + /* 1T segment */ + vsid_bits = va_bits - SID_SHIFT_1T; + protovsid = (context << ESID_BITS_1T) | + ((ea >> SID_SHIFT_1T) & ESID_BITS_1T_MASK); + return vsid_scramble(protovsid, VSID_MULTIPLIER_1T, vsid_bits); +} + +/* + * For kernel space, we use context ids as + * below. Range is 512TB per context. + * + * 0x00001 - [ 0xc000000000000000 - 0xc001ffffffffffff] + * 0x00002 - [ 0xc002000000000000 - 0xc003ffffffffffff] + * 0x00003 - [ 0xc004000000000000 - 0xc005ffffffffffff] + * 0x00004 - [ 0xc006000000000000 - 0xc007ffffffffffff] + * + * vmap, IO, vmemap + * + * 0x00005 - [ 0xc008000000000000 - 0xc009ffffffffffff] + * 0x00006 - [ 0xc00a000000000000 - 0xc00bffffffffffff] + * 0x00007 - [ 0xc00c000000000000 - 0xc00dffffffffffff] + * + */ +static inline unsigned long get_kernel_context(unsigned long ea) +{ + unsigned long region_id = get_region_id(ea); + unsigned long ctx; + /* + * Depending on Kernel config, kernel region can have one context + * or more. + */ + if (region_id == LINEAR_MAP_REGION_ID) { + /* + * We already verified ea to be not beyond the addr limit. + */ + ctx = 1 + ((ea & EA_MASK) >> MAX_EA_BITS_PER_CONTEXT); + } else + ctx = region_id + MAX_KERNEL_CTX_CNT - 1; + return ctx; +} + +/* + * This is only valid for addresses >= PAGE_OFFSET + */ +static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize) +{ + unsigned long context; + + if (!is_kernel_addr(ea)) + return 0; + + context = get_kernel_context(ea); + return get_vsid(context, ea, ssize); +} + +unsigned htab_shift_for_mem_size(unsigned long mem_size); + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_POWERPC_BOOK3S_64_MMU_HASH_H_ */ diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h new file mode 100644 index 000000000..750918451 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -0,0 +1,278 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_MMU_H_ +#define _ASM_POWERPC_BOOK3S_64_MMU_H_ + +#include <asm/page.h> + +#ifndef __ASSEMBLY__ +/* + * 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 */ + union { + unsigned long sllp; /* SLB L||LP (exact mask to use in slbmte) */ + unsigned long ap; /* Ap encoding used by PowerISA 3.0 */ + }; +}; +extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; +#endif /* __ASSEMBLY__ */ + +/* 64-bit classic hash table MMU */ +#include <asm/book3s/64/mmu-hash.h> + +#ifndef __ASSEMBLY__ +/* + * ISA 3.0 partition and process table entry format + */ +struct prtb_entry { + __be64 prtb0; + __be64 prtb1; +}; +extern struct prtb_entry *process_tb; + +struct patb_entry { + __be64 patb0; + __be64 patb1; +}; +extern struct patb_entry *partition_tb; + +/* Bits in patb0 field */ +#define PATB_HR (1UL << 63) +#define RPDB_MASK 0x0fffffffffffff00UL +#define RPDB_SHIFT (1UL << 8) +#define RTS1_SHIFT 61 /* top 2 bits of radix tree size */ +#define RTS1_MASK (3UL << RTS1_SHIFT) +#define RTS2_SHIFT 5 /* bottom 3 bits of radix tree size */ +#define RTS2_MASK (7UL << RTS2_SHIFT) +#define RPDS_MASK 0x1f /* root page dir. size field */ + +/* Bits in patb1 field */ +#define PATB_GR (1UL << 63) /* guest uses radix; must match HR */ +#define PRTS_MASK 0x1f /* process table size field */ +#define PRTB_MASK 0x0ffffffffffff000UL + +/* Number of supported PID bits */ +extern unsigned int mmu_pid_bits; + +/* Base PID to allocate from */ +extern unsigned int mmu_base_pid; + +/* + * memory block size used with radix translation. + */ +extern unsigned long __ro_after_init radix_mem_block_size; + +#define PRTB_SIZE_SHIFT (mmu_pid_bits + 4) +#define PRTB_ENTRIES (1ul << mmu_pid_bits) + +/* + * Power9 currently only support 64K partition table size. + */ +#define PATB_SIZE_SHIFT 16 + +typedef unsigned long mm_context_id_t; +struct spinlock; + +/* Maximum possible number of NPUs in a system. */ +#define NV_MAX_NPUS 8 + +typedef struct { + union { + /* + * We use id as the PIDR content for radix. On hash we can use + * more than one id. The extended ids are used when we start + * having address above 512TB. We allocate one extended id + * for each 512TB. The new id is then used with the 49 bit + * EA to build a new VA. We always use ESID_BITS_1T_MASK bits + * from EA and new context ids to build the new VAs. + */ + mm_context_id_t id; + mm_context_id_t extended_id[TASK_SIZE_USER64/TASK_CONTEXT_SIZE]; + }; + + /* Number of bits in the mm_cpumask */ + atomic_t active_cpus; + + /* Number of users of the external (Nest) MMU */ + atomic_t copros; + + /* Number of user space windows opened in process mm_context */ + atomic_t vas_windows; + + struct hash_mm_context *hash_context; + + unsigned long vdso_base; + /* + * pagetable fragment support + */ + void *pte_frag; + void *pmd_frag; +#ifdef CONFIG_SPAPR_TCE_IOMMU + struct list_head iommu_group_mem_list; +#endif + +#ifdef CONFIG_PPC_MEM_KEYS + /* + * Each bit represents one protection key. + * bit set -> key allocated + * bit unset -> key available for allocation + */ + u32 pkey_allocation_map; + s16 execute_only_pkey; /* key holding execute-only protection */ +#endif +} mm_context_t; + +static inline u16 mm_ctx_user_psize(mm_context_t *ctx) +{ + return ctx->hash_context->user_psize; +} + +static inline void mm_ctx_set_user_psize(mm_context_t *ctx, u16 user_psize) +{ + ctx->hash_context->user_psize = user_psize; +} + +static inline unsigned char *mm_ctx_low_slices(mm_context_t *ctx) +{ + return ctx->hash_context->low_slices_psize; +} + +static inline unsigned char *mm_ctx_high_slices(mm_context_t *ctx) +{ + return ctx->hash_context->high_slices_psize; +} + +static inline unsigned long mm_ctx_slb_addr_limit(mm_context_t *ctx) +{ + return ctx->hash_context->slb_addr_limit; +} + +static inline void mm_ctx_set_slb_addr_limit(mm_context_t *ctx, unsigned long limit) +{ + ctx->hash_context->slb_addr_limit = limit; +} + +static inline struct slice_mask *slice_mask_for_size(mm_context_t *ctx, int psize) +{ +#ifdef CONFIG_PPC_64K_PAGES + if (psize == MMU_PAGE_64K) + return &ctx->hash_context->mask_64k; +#endif +#ifdef CONFIG_HUGETLB_PAGE + if (psize == MMU_PAGE_16M) + return &ctx->hash_context->mask_16m; + if (psize == MMU_PAGE_16G) + return &ctx->hash_context->mask_16g; +#endif + BUG_ON(psize != MMU_PAGE_4K); + + return &ctx->hash_context->mask_4k; +} + +#ifdef CONFIG_PPC_SUBPAGE_PROT +static inline struct subpage_prot_table *mm_ctx_subpage_prot(mm_context_t *ctx) +{ + return ctx->hash_context->spt; +} +#endif + +/* + * 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; + +/* MMU initialization */ +void mmu_early_init_devtree(void); +void hash__early_init_devtree(void); +void radix__early_init_devtree(void); +#ifdef CONFIG_PPC_MEM_KEYS +void pkey_early_init_devtree(void); +#else +static inline void pkey_early_init_devtree(void) {} +#endif + +extern void hash__early_init_mmu(void); +extern void radix__early_init_mmu(void); +static inline void __init early_init_mmu(void) +{ + if (radix_enabled()) + return radix__early_init_mmu(); + return hash__early_init_mmu(); +} +extern void hash__early_init_mmu_secondary(void); +extern void radix__early_init_mmu_secondary(void); +static inline void early_init_mmu_secondary(void) +{ + if (radix_enabled()) + return radix__early_init_mmu_secondary(); + return hash__early_init_mmu_secondary(); +} + +extern void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base, + phys_addr_t first_memblock_size); +static inline void setup_initial_memory_limit(phys_addr_t first_memblock_base, + phys_addr_t first_memblock_size) +{ + /* + * Hash has more strict restrictions. At this point we don't + * know which translations we will pick. Hence go with hash + * restrictions. + */ + return hash__setup_initial_memory_limit(first_memblock_base, + first_memblock_size); +} + +#ifdef CONFIG_PPC_PSERIES +extern void radix_init_pseries(void); +#else +static inline void radix_init_pseries(void) { }; +#endif + +#ifdef CONFIG_HOTPLUG_CPU +#define arch_clear_mm_cpumask_cpu(cpu, mm) \ + do { \ + if (cpumask_test_cpu(cpu, mm_cpumask(mm))) { \ + atomic_dec(&(mm)->context.active_cpus); \ + cpumask_clear_cpu(cpu, mm_cpumask(mm)); \ + } \ + } while (0) + +void cleanup_cpu_mmu_context(void); +#endif + +static inline int get_user_context(mm_context_t *ctx, unsigned long ea) +{ + int index = ea >> MAX_EA_BITS_PER_CONTEXT; + + if (likely(index < ARRAY_SIZE(ctx->extended_id))) + return ctx->extended_id[index]; + + /* should never happen */ + WARN_ON(1); + return 0; +} + +static inline unsigned long get_user_vsid(mm_context_t *ctx, + unsigned long ea, int ssize) +{ + unsigned long context = get_user_context(ctx, ea); + + return get_vsid(context, ea, ssize); +} + +#endif /* __ASSEMBLY__ */ +#endif /* _ASM_POWERPC_BOOK3S_64_MMU_H_ */ diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h new file mode 100644 index 000000000..e1af0b394 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -0,0 +1,181 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_POWERPC_BOOK3S_64_PGALLOC_H +#define _ASM_POWERPC_BOOK3S_64_PGALLOC_H +/* + */ + +#include <linux/slab.h> +#include <linux/cpumask.h> +#include <linux/kmemleak.h> +#include <linux/percpu.h> + +struct vmemmap_backing { + struct vmemmap_backing *list; + unsigned long phys; + unsigned long virt_addr; +}; +extern struct vmemmap_backing *vmemmap_list; + +extern pmd_t *pmd_fragment_alloc(struct mm_struct *, unsigned long); +extern void pmd_fragment_free(unsigned long *); +extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift); +extern void __tlb_remove_table(void *_table); +void pte_frag_destroy(void *pte_frag); + +static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm) +{ +#ifdef CONFIG_PPC_64K_PAGES + return (pgd_t *)__get_free_page(pgtable_gfp_flags(mm, PGALLOC_GFP)); +#else + struct page *page; + page = alloc_pages(pgtable_gfp_flags(mm, PGALLOC_GFP | __GFP_RETRY_MAYFAIL), + 4); + if (!page) + return NULL; + return (pgd_t *) page_address(page); +#endif +} + +static inline void radix__pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ +#ifdef CONFIG_PPC_64K_PAGES + free_page((unsigned long)pgd); +#else + free_pages((unsigned long)pgd, 4); +#endif +} + +static inline pgd_t *pgd_alloc(struct mm_struct *mm) +{ + pgd_t *pgd; + + if (radix_enabled()) + return radix__pgd_alloc(mm); + + pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), + pgtable_gfp_flags(mm, GFP_KERNEL)); + if (unlikely(!pgd)) + return pgd; + + /* + * Don't scan the PGD for pointers, it contains references to PUDs but + * those references are not full pointers and so can't be recognised by + * kmemleak. + */ + kmemleak_no_scan(pgd); + + /* + * With hugetlb, we don't clear the second half of the page table. + * If we share the same slab cache with the pmd or pud level table, + * we need to make sure we zero out the full table on alloc. + * With 4K we don't store slot in the second half. Hence we don't + * need to do this for 4k. + */ +#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_PPC_64K_PAGES) && \ + (H_PGD_INDEX_SIZE == H_PUD_CACHE_INDEX) + memset(pgd, 0, PGD_TABLE_SIZE); +#endif + return pgd; +} + +static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ + if (radix_enabled()) + return radix__pgd_free(mm, pgd); + kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd); +} + +static inline void p4d_populate(struct mm_struct *mm, p4d_t *pgd, pud_t *pud) +{ + *pgd = __p4d(__pgtable_ptr_val(pud) | PGD_VAL_BITS); +} + +static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) +{ + pud_t *pud; + + pud = kmem_cache_alloc(PGT_CACHE(PUD_CACHE_INDEX), + pgtable_gfp_flags(mm, GFP_KERNEL)); + /* + * Tell kmemleak to ignore the PUD, that means don't scan it for + * pointers and don't consider it a leak. PUDs are typically only + * referred to by their PGD, but kmemleak is not able to recognise those + * as pointers, leading to false leak reports. + */ + kmemleak_ignore(pud); + + return pud; +} + +static inline void __pud_free(pud_t *pud) +{ + struct page *page = virt_to_page(pud); + + /* + * Early pud pages allocated via memblock allocator + * can't be directly freed to slab + */ + if (PageReserved(page)) + free_reserved_page(page); + else + kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), pud); +} + +static inline void pud_free(struct mm_struct *mm, pud_t *pud) +{ + return __pud_free(pud); +} + +static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) +{ + *pud = __pud(__pgtable_ptr_val(pmd) | PUD_VAL_BITS); +} + +static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, + unsigned long address) +{ + pgtable_free_tlb(tlb, pud, PUD_INDEX); +} + +static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) +{ + return pmd_fragment_alloc(mm, addr); +} + +static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) +{ + pmd_fragment_free((unsigned long *)pmd); +} + +static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, + unsigned long address) +{ + return pgtable_free_tlb(tlb, pmd, PMD_INDEX); +} + +static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, + pte_t *pte) +{ + *pmd = __pmd(__pgtable_ptr_val(pte) | PMD_VAL_BITS); +} + +static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, + pgtable_t pte_page) +{ + *pmd = __pmd(__pgtable_ptr_val(pte_page) | PMD_VAL_BITS); +} + +static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, + unsigned long address) +{ + pgtable_free_tlb(tlb, table, PTE_INDEX); +} + +extern atomic_long_t direct_pages_count[MMU_PAGE_COUNT]; +static inline void update_page_count(int psize, long count) +{ + if (IS_ENABLED(CONFIG_PROC_FS)) + atomic_long_add(count, &direct_pages_count[psize]); +} + +#endif /* _ASM_POWERPC_BOOK3S_64_PGALLOC_H */ diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h new file mode 100644 index 000000000..4e697bc2f --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_4K_H +#define _ASM_POWERPC_BOOK3S_64_PGTABLE_4K_H +/* + * hash 4k can't share hugetlb and also doesn't support THP + */ +#ifndef __ASSEMBLY__ +#ifdef CONFIG_HUGETLB_PAGE +static inline int pmd_huge(pmd_t pmd) +{ + /* + * leaf pte for huge page + */ + if (radix_enabled()) + return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); + return 0; +} + +static inline int pud_huge(pud_t pud) +{ + /* + * leaf pte for huge page + */ + if (radix_enabled()) + return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); + return 0; +} + +static inline int pgd_huge(pgd_t pgd) +{ + /* + * leaf pte for huge page + */ + if (radix_enabled()) + return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PTE)); + return 0; +} +#define pgd_huge pgd_huge +/* + * With radix , we have hugepage ptes in the pud and pmd entries. We don't + * need to setup hugepage directory for them. Our pte and page directory format + * enable us to have this enabled. + */ +static inline int hugepd_ok(hugepd_t hpd) +{ + if (radix_enabled()) + return 0; + return hash__hugepd_ok(hpd); +} +#define is_hugepd(hpd) (hugepd_ok(hpd)) + +/* + * 16M and 16G huge page directory tables are allocated from slab cache + * + */ +#define H_16M_CACHE_INDEX (PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE - 24) +#define H_16G_CACHE_INDEX \ + (PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE + H_PUD_INDEX_SIZE - 34) + +static inline int get_hugepd_cache_index(int index) +{ + switch (index) { + case H_16M_CACHE_INDEX: + return HTLB_16M_INDEX; + case H_16G_CACHE_INDEX: + return HTLB_16G_INDEX; + default: + BUG(); + } + /* should not reach */ +} + +#endif /* CONFIG_HUGETLB_PAGE */ + +#endif /* __ASSEMBLY__ */ + +#endif /*_ASM_POWERPC_BOOK3S_64_PGTABLE_4K_H */ diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h new file mode 100644 index 000000000..34d101889 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_64K_H +#define _ASM_POWERPC_BOOK3S_64_PGTABLE_64K_H + +#ifndef __ASSEMBLY__ +#ifdef CONFIG_HUGETLB_PAGE +/* + * We have PGD_INDEX_SIZ = 12 and PTE_INDEX_SIZE = 8, so that we can have + * 16GB hugepage pte in PGD and 16MB hugepage pte at PMD; + * + * Defined in such a way that we can optimize away code block at build time + * if CONFIG_HUGETLB_PAGE=n. + * + * returns true for pmd migration entries, THP, devmap, hugetlb + * But compile time dependent on CONFIG_HUGETLB_PAGE + */ +static inline int pmd_huge(pmd_t pmd) +{ + /* + * leaf pte for huge page + */ + return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); +} + +static inline int pud_huge(pud_t pud) +{ + /* + * leaf pte for huge page + */ + return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); +} + +static inline int pgd_huge(pgd_t pgd) +{ + /* + * leaf pte for huge page + */ + return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PTE)); +} +#define pgd_huge pgd_huge + +/* + * With 64k page size, we have hugepage ptes in the pgd and pmd entries. We don't + * need to setup hugepage directory for them. Our pte and page directory format + * enable us to have this enabled. + */ +static inline int hugepd_ok(hugepd_t hpd) +{ + return 0; +} + +#define is_hugepd(pdep) 0 + +/* + * This should never get called + */ +static inline int get_hugepd_cache_index(int index) +{ + BUG(); +} + +#endif /* CONFIG_HUGETLB_PAGE */ + +static inline int remap_4k_pfn(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t prot) +{ + if (radix_enabled()) + BUG(); + return hash__remap_4k_pfn(vma, addr, pfn, prot); +} +#endif /* __ASSEMBLY__ */ +#endif /*_ASM_POWERPC_BOOK3S_64_PGTABLE_64K_H */ diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h new file mode 100644 index 000000000..2b4af824b --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -0,0 +1,1402 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ +#define _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ + +#include <asm-generic/pgtable-nop4d.h> + +#ifndef __ASSEMBLY__ +#include <linux/mmdebug.h> +#include <linux/bug.h> +#include <linux/sizes.h> +#endif + +/* + * Common bits between hash and Radix page table + */ +#define _PAGE_BIT_SWAP_TYPE 0 + +#define _PAGE_EXEC 0x00001 /* execute permission */ +#define _PAGE_WRITE 0x00002 /* write access allowed */ +#define _PAGE_READ 0x00004 /* read access allowed */ +#define _PAGE_RW (_PAGE_READ | _PAGE_WRITE) +#define _PAGE_RWX (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC) +#define _PAGE_PRIVILEGED 0x00008 /* kernel access only */ +#define _PAGE_SAO 0x00010 /* Strong access order */ +#define _PAGE_NON_IDEMPOTENT 0x00020 /* non idempotent memory */ +#define _PAGE_TOLERANT 0x00030 /* tolerant memory, cache inhibited */ +#define _PAGE_DIRTY 0x00080 /* C: page changed */ +#define _PAGE_ACCESSED 0x00100 /* R: page referenced */ +/* + * Software bits + */ +#define _RPAGE_SW0 0x2000000000000000UL +#define _RPAGE_SW1 0x00800 +#define _RPAGE_SW2 0x00400 +#define _RPAGE_SW3 0x00200 +#define _RPAGE_RSV1 0x00040UL + +#define _RPAGE_PKEY_BIT4 0x1000000000000000UL +#define _RPAGE_PKEY_BIT3 0x0800000000000000UL +#define _RPAGE_PKEY_BIT2 0x0400000000000000UL +#define _RPAGE_PKEY_BIT1 0x0200000000000000UL +#define _RPAGE_PKEY_BIT0 0x0100000000000000UL + +#define _PAGE_PTE 0x4000000000000000UL /* distinguishes PTEs from pointers */ +#define _PAGE_PRESENT 0x8000000000000000UL /* pte contains a translation */ +/* + * We need to mark a pmd pte invalid while splitting. We can do that by clearing + * the _PAGE_PRESENT bit. But then that will be taken as a swap pte. In order to + * differentiate between two use a SW field when invalidating. + * + * We do that temporary invalidate for regular pte entry in ptep_set_access_flags + * + * This is used only when _PAGE_PRESENT is cleared. + */ +#define _PAGE_INVALID _RPAGE_SW0 + +/* + * Top and bottom bits of RPN which can be used by hash + * translation mode, because we expect them to be zero + * otherwise. + */ +#define _RPAGE_RPN0 0x01000 +#define _RPAGE_RPN1 0x02000 +#define _RPAGE_RPN43 0x0080000000000000UL +#define _RPAGE_RPN42 0x0040000000000000UL +#define _RPAGE_RPN41 0x0020000000000000UL + +/* Max physical address bit as per radix table */ +#define _RPAGE_PA_MAX 56 + +/* + * Max physical address bit we will use for now. + * + * This is mostly a hardware limitation and for now Power9 has + * a 51 bit limit. + * + * This is different from the number of physical bit required to address + * the last byte of memory. That is defined by MAX_PHYSMEM_BITS. + * MAX_PHYSMEM_BITS is a linux limitation imposed by the maximum + * number of sections we can support (SECTIONS_SHIFT). + * + * This is different from Radix page table limitation above and + * should always be less than that. The limit is done such that + * we can overload the bits between _RPAGE_PA_MAX and _PAGE_PA_MAX + * for hash linux page table specific bits. + * + * In order to be compatible with future hardware generations we keep + * some offsets and limit this for now to 53 + */ +#define _PAGE_PA_MAX 53 + +#define _PAGE_SOFT_DIRTY _RPAGE_SW3 /* software: software dirty tracking */ +#define _PAGE_SPECIAL _RPAGE_SW2 /* software: special page */ +#define _PAGE_DEVMAP _RPAGE_SW1 /* software: ZONE_DEVICE page */ + +/* + * Drivers request for cache inhibited pte mapping using _PAGE_NO_CACHE + * Instead of fixing all of them, add an alternate define which + * maps CI pte mapping. + */ +#define _PAGE_NO_CACHE _PAGE_TOLERANT +/* + * We support _RPAGE_PA_MAX bit real address in pte. On the linux side + * we are limited by _PAGE_PA_MAX. Clear everything above _PAGE_PA_MAX + * and every thing below PAGE_SHIFT; + */ +#define PTE_RPN_MASK (((1UL << _PAGE_PA_MAX) - 1) & (PAGE_MASK)) +/* + * set of bits not changed in pmd_modify. Even though we have hash specific bits + * in here, on radix we expect them to be zero. + */ +#define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \ + _PAGE_ACCESSED | H_PAGE_THP_HUGE | _PAGE_PTE | \ + _PAGE_SOFT_DIRTY | _PAGE_DEVMAP) +/* + * user access blocked by key + */ +#define _PAGE_KERNEL_RW (_PAGE_PRIVILEGED | _PAGE_RW | _PAGE_DIRTY) +#define _PAGE_KERNEL_RO (_PAGE_PRIVILEGED | _PAGE_READ) +#define _PAGE_KERNEL_RWX (_PAGE_PRIVILEGED | _PAGE_DIRTY | \ + _PAGE_RW | _PAGE_EXEC) +/* + * _PAGE_CHG_MASK masks of bits that are to be preserved across + * pgprot changes + */ +#define _PAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \ + _PAGE_ACCESSED | _PAGE_SPECIAL | _PAGE_PTE | \ + _PAGE_SOFT_DIRTY | _PAGE_DEVMAP) + +/* + * We define 2 sets of base prot bits, one for basic pages (ie, + * cacheable kernel and user pages) and one for non cacheable + * pages. We always set _PAGE_COHERENT when SMP is enabled or + * the processor might need it for DMA coherency. + */ +#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED) +#define _PAGE_BASE (_PAGE_BASE_NC) + +/* Permission masks used to generate the __P and __S table, + * + * Note:__pgprot is defined in arch/powerpc/include/asm/page.h + * + * Write permissions imply read permissions for now (we could make write-only + * pages on BookE but we don't bother for now). Execute permission control is + * possible on platforms that define _PAGE_EXEC + */ +#define PAGE_NONE __pgprot(_PAGE_BASE | _PAGE_PRIVILEGED) +#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_RW) +#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_RW | _PAGE_EXEC) +#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_READ) +#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC) +#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_READ) +#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC) + +/* Permission masks used for kernel mappings */ +#define PAGE_KERNEL __pgprot(_PAGE_BASE | _PAGE_KERNEL_RW) +#define PAGE_KERNEL_NC __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \ + _PAGE_TOLERANT) +#define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \ + _PAGE_NON_IDEMPOTENT) +#define PAGE_KERNEL_X __pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX) +#define PAGE_KERNEL_RO __pgprot(_PAGE_BASE | _PAGE_KERNEL_RO) +#define PAGE_KERNEL_ROX __pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX) + +/* + * Protection used for kernel text. We want the debuggers to be able to + * set breakpoints anywhere, so don't write protect the kernel text + * on platforms where such control is possible. + */ +#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) || \ + defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE) +#define PAGE_KERNEL_TEXT PAGE_KERNEL_X +#else +#define PAGE_KERNEL_TEXT PAGE_KERNEL_ROX +#endif + +/* Make modules code happy. We don't set RO yet */ +#define PAGE_KERNEL_EXEC PAGE_KERNEL_X +#define PAGE_AGP (PAGE_KERNEL_NC) + +#ifndef __ASSEMBLY__ +/* + * page table defines + */ +extern unsigned long __pte_index_size; +extern unsigned long __pmd_index_size; +extern unsigned long __pud_index_size; +extern unsigned long __pgd_index_size; +extern unsigned long __pud_cache_index; +#define PTE_INDEX_SIZE __pte_index_size +#define PMD_INDEX_SIZE __pmd_index_size +#define PUD_INDEX_SIZE __pud_index_size +#define PGD_INDEX_SIZE __pgd_index_size +/* pmd table use page table fragments */ +#define PMD_CACHE_INDEX 0 +#define PUD_CACHE_INDEX __pud_cache_index +/* + * Because of use of pte fragments and THP, size of page table + * are not always derived out of index size above. + */ +extern unsigned long __pte_table_size; +extern unsigned long __pmd_table_size; +extern unsigned long __pud_table_size; +extern unsigned long __pgd_table_size; +#define PTE_TABLE_SIZE __pte_table_size +#define PMD_TABLE_SIZE __pmd_table_size +#define PUD_TABLE_SIZE __pud_table_size +#define PGD_TABLE_SIZE __pgd_table_size + +extern unsigned long __pmd_val_bits; +extern unsigned long __pud_val_bits; +extern unsigned long __pgd_val_bits; +#define PMD_VAL_BITS __pmd_val_bits +#define PUD_VAL_BITS __pud_val_bits +#define PGD_VAL_BITS __pgd_val_bits + +extern unsigned long __pte_frag_nr; +#define PTE_FRAG_NR __pte_frag_nr +extern unsigned long __pte_frag_size_shift; +#define PTE_FRAG_SIZE_SHIFT __pte_frag_size_shift +#define PTE_FRAG_SIZE (1UL << PTE_FRAG_SIZE_SHIFT) + +extern unsigned long __pmd_frag_nr; +#define PMD_FRAG_NR __pmd_frag_nr +extern unsigned long __pmd_frag_size_shift; +#define PMD_FRAG_SIZE_SHIFT __pmd_frag_size_shift +#define PMD_FRAG_SIZE (1UL << PMD_FRAG_SIZE_SHIFT) + +#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) + +/* PMD_SHIFT determines what a second-level page table entry can map */ +#define PMD_SHIFT (PAGE_SHIFT + PTE_INDEX_SIZE) +#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 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)) + +/* 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 P4D_MASKED_BITS 0xc0000000000000ffUL + +/* + * Used as an indicator for rcu callback functions + */ +enum pgtable_index { + PTE_INDEX = 0, + PMD_INDEX, + PUD_INDEX, + PGD_INDEX, + /* + * Below are used with 4k page size and hugetlb + */ + HTLB_16M_INDEX, + HTLB_16G_INDEX, +}; + +extern unsigned long __vmalloc_start; +extern unsigned long __vmalloc_end; +#define VMALLOC_START __vmalloc_start +#define VMALLOC_END __vmalloc_end + +static inline unsigned int ioremap_max_order(void) +{ + if (radix_enabled()) + return PUD_SHIFT; + return 7 + PAGE_SHIFT; /* default from linux/vmalloc.h */ +} +#define IOREMAP_MAX_ORDER ioremap_max_order() + +extern unsigned long __kernel_virt_start; +extern unsigned long __kernel_io_start; +extern unsigned long __kernel_io_end; +#define KERN_VIRT_START __kernel_virt_start +#define KERN_IO_START __kernel_io_start +#define KERN_IO_END __kernel_io_end + +extern struct page *vmemmap; +extern unsigned long pci_io_base; +#endif /* __ASSEMBLY__ */ + +#include <asm/book3s/64/hash.h> +#include <asm/book3s/64/radix.h> + +#if H_MAX_PHYSMEM_BITS > R_MAX_PHYSMEM_BITS +#define MAX_PHYSMEM_BITS H_MAX_PHYSMEM_BITS +#else +#define MAX_PHYSMEM_BITS R_MAX_PHYSMEM_BITS +#endif + + +#ifdef CONFIG_PPC_64K_PAGES +#include <asm/book3s/64/pgtable-64k.h> +#else +#include <asm/book3s/64/pgtable-4k.h> +#endif + +#include <asm/barrier.h> +/* + * IO space itself carved into the PIO region (ISA and PHB IO space) and + * the ioremap space + * + * ISA_IO_BASE = KERN_IO_START, 64K reserved area + * PHB_IO_BASE = ISA_IO_BASE + 64K to ISA_IO_BASE + 2G, PHB IO spaces + * IOREMAP_BASE = ISA_IO_BASE + 2G to VMALLOC_START + PGTABLE_RANGE + */ +#define FULL_IO_SIZE 0x80000000ul +#define ISA_IO_BASE (KERN_IO_START) +#define ISA_IO_END (KERN_IO_START + 0x10000ul) +#define PHB_IO_BASE (ISA_IO_END) +#define PHB_IO_END (KERN_IO_START + FULL_IO_SIZE) +#define IOREMAP_BASE (PHB_IO_END) +#define IOREMAP_START (ioremap_bot) +#define IOREMAP_END (KERN_IO_END - FIXADDR_SIZE) +#define FIXADDR_SIZE SZ_32M + +/* Advertise special mapping type for AGP */ +#define HAVE_PAGE_AGP + +#ifndef __ASSEMBLY__ + +/* + * This is the default implementation of various PTE accessors, it's + * used in all cases except Book3S with 64K pages where we have a + * concept of sub-pages + */ +#ifndef __real_pte + +#define __real_pte(e, p, o) ((real_pte_t){(e)}) +#define __rpte_to_pte(r) ((r).pte) +#define __rpte_to_hidx(r,index) (pte_val(__rpte_to_pte(r)) >> H_PAGE_F_GIX_SHIFT) + +#define pte_iterate_hashed_subpages(rpte, psize, va, index, shift) \ + do { \ + index = 0; \ + shift = mmu_psize_defs[psize].shift; \ + +#define pte_iterate_hashed_end() } while(0) + +/* + * We expect this to be called only for user addresses or kernel virtual + * addresses other than the linear mapping. + */ +#define pte_pagesize_index(mm, addr, pte) MMU_PAGE_4K + +#endif /* __real_pte */ + +static inline unsigned long pte_update(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, unsigned long clr, + unsigned long set, int huge) +{ + if (radix_enabled()) + return radix__pte_update(mm, addr, ptep, clr, set, huge); + return hash__pte_update(mm, addr, ptep, clr, set, huge); +} +/* + * For hash even if we have _PAGE_ACCESSED = 0, we do a pte_update. + * We currently remove entries from the hashtable regardless of whether + * the entry was young or dirty. + * + * We should be more intelligent about this but for the moment we override + * these functions and force a tlb flush unconditionally + * For radix: H_PAGE_HASHPTE should be zero. Hence we can use the same + * function for both hash and radix. + */ +static inline int __ptep_test_and_clear_young(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + unsigned long old; + + if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0) + return 0; + old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0); + return (old & _PAGE_ACCESSED) != 0; +} + +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG +#define ptep_test_and_clear_young(__vma, __addr, __ptep) \ +({ \ + int __r; \ + __r = __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep); \ + __r; \ +}) + +static inline int __pte_write(pte_t pte) +{ + return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE)); +} + +#ifdef CONFIG_NUMA_BALANCING +#define pte_savedwrite pte_savedwrite +static inline bool pte_savedwrite(pte_t pte) +{ + /* + * Saved write ptes are prot none ptes that doesn't have + * privileged bit sit. We mark prot none as one which has + * present and pviliged bit set and RWX cleared. To mark + * protnone which used to have _PAGE_WRITE set we clear + * the privileged bit. + */ + return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED)); +} +#else +#define pte_savedwrite pte_savedwrite +static inline bool pte_savedwrite(pte_t pte) +{ + return false; +} +#endif + +static inline int pte_write(pte_t pte) +{ + return __pte_write(pte) || pte_savedwrite(pte); +} + +static inline int pte_read(pte_t pte) +{ + return !!(pte_raw(pte) & cpu_to_be64(_PAGE_READ)); +} + +#define __HAVE_ARCH_PTEP_SET_WRPROTECT +static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + if (__pte_write(*ptep)) + pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0); + else if (unlikely(pte_savedwrite(*ptep))) + pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 0); +} + +#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT +static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + /* + * We should not find protnone for hugetlb, but this complete the + * interface. + */ + if (__pte_write(*ptep)) + pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1); + else if (unlikely(pte_savedwrite(*ptep))) + pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 1); +} + +#define __HAVE_ARCH_PTEP_GET_AND_CLEAR +static inline pte_t ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0); + return __pte(old); +} + +#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL +static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, int full) +{ + if (full && radix_enabled()) { + /* + * We know that this is a full mm pte clear and + * hence can be sure there is no parallel set_pte. + */ + return radix__ptep_get_and_clear_full(mm, addr, ptep, full); + } + return ptep_get_and_clear(mm, addr, ptep); +} + + +static inline void pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t * ptep) +{ + pte_update(mm, addr, ptep, ~0UL, 0, 0); +} + +static inline int pte_dirty(pte_t pte) +{ + return !!(pte_raw(pte) & cpu_to_be64(_PAGE_DIRTY)); +} + +static inline int pte_young(pte_t pte) +{ + return !!(pte_raw(pte) & cpu_to_be64(_PAGE_ACCESSED)); +} + +static inline int pte_special(pte_t pte) +{ + return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SPECIAL)); +} + +static inline bool pte_exec(pte_t pte) +{ + return !!(pte_raw(pte) & cpu_to_be64(_PAGE_EXEC)); +} + + +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY +static inline bool pte_soft_dirty(pte_t pte) +{ + return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SOFT_DIRTY)); +} + +static inline pte_t pte_mksoft_dirty(pte_t pte) +{ + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SOFT_DIRTY)); +} + +static inline pte_t pte_clear_soft_dirty(pte_t pte) +{ + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_SOFT_DIRTY)); +} +#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ + +#ifdef CONFIG_NUMA_BALANCING +static inline int pte_protnone(pte_t pte) +{ + return (pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE | _PAGE_RWX)) == + cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE); +} + +#define pte_mk_savedwrite pte_mk_savedwrite +static inline pte_t pte_mk_savedwrite(pte_t pte) +{ + /* + * Used by Autonuma subsystem to preserve the write bit + * while marking the pte PROT_NONE. Only allow this + * on PROT_NONE pte + */ + VM_BUG_ON((pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_RWX | _PAGE_PRIVILEGED)) != + cpu_to_be64(_PAGE_PRESENT | _PAGE_PRIVILEGED)); + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_PRIVILEGED)); +} + +#define pte_clear_savedwrite pte_clear_savedwrite +static inline pte_t pte_clear_savedwrite(pte_t pte) +{ + /* + * Used by KSM subsystem to make a protnone pte readonly. + */ + VM_BUG_ON(!pte_protnone(pte)); + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PRIVILEGED)); +} +#else +#define pte_clear_savedwrite pte_clear_savedwrite +static inline pte_t pte_clear_savedwrite(pte_t pte) +{ + VM_WARN_ON(1); + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_WRITE)); +} +#endif /* CONFIG_NUMA_BALANCING */ + +static inline bool pte_hw_valid(pte_t pte) +{ + return (pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE)) == + cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE); +} + +static inline int pte_present(pte_t pte) +{ + /* + * A pte is considerent present if _PAGE_PRESENT is set. + * We also need to consider the pte present which is marked + * invalid during ptep_set_access_flags. Hence we look for _PAGE_INVALID + * if we find _PAGE_PRESENT cleared. + */ + + if (pte_hw_valid(pte)) + return true; + return (pte_raw(pte) & cpu_to_be64(_PAGE_INVALID | _PAGE_PTE)) == + cpu_to_be64(_PAGE_INVALID | _PAGE_PTE); +} + +#ifdef CONFIG_PPC_MEM_KEYS +extern bool arch_pte_access_permitted(u64 pte, bool write, bool execute); +#else +static inline bool arch_pte_access_permitted(u64 pte, bool write, bool execute) +{ + return true; +} +#endif /* CONFIG_PPC_MEM_KEYS */ + +static inline bool pte_user(pte_t pte) +{ + return !(pte_raw(pte) & cpu_to_be64(_PAGE_PRIVILEGED)); +} + +#define pte_access_permitted pte_access_permitted +static inline bool pte_access_permitted(pte_t pte, bool write) +{ + /* + * _PAGE_READ is needed for any access and will be + * cleared for PROT_NONE + */ + if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte)) + return false; + + if (write && !pte_write(pte)) + return false; + + return arch_pte_access_permitted(pte_val(pte), write, 0); +} + +/* + * Conversion functions: convert a page and protection to a page entry, + * and a page entry and page directory to the page they refer to. + * + * Even if PTEs can be unsigned long long, a PFN is always an unsigned + * long for now. + */ +static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) +{ + VM_BUG_ON(pfn >> (64 - PAGE_SHIFT)); + VM_BUG_ON((pfn << PAGE_SHIFT) & ~PTE_RPN_MASK); + + return __pte(((pte_basic_t)pfn << PAGE_SHIFT) | pgprot_val(pgprot) | _PAGE_PTE); +} + +static inline unsigned long pte_pfn(pte_t pte) +{ + return (pte_val(pte) & PTE_RPN_MASK) >> PAGE_SHIFT; +} + +/* Generic modifiers for PTE bits */ +static inline pte_t pte_wrprotect(pte_t pte) +{ + if (unlikely(pte_savedwrite(pte))) + return pte_clear_savedwrite(pte); + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_WRITE)); +} + +static inline pte_t pte_exprotect(pte_t pte) +{ + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_EXEC)); +} + +static inline pte_t pte_mkclean(pte_t pte) +{ + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_DIRTY)); +} + +static inline pte_t pte_mkold(pte_t pte) +{ + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_ACCESSED)); +} + +static inline pte_t pte_mkexec(pte_t pte) +{ + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_EXEC)); +} + +static inline pte_t pte_mkwrite(pte_t pte) +{ + /* + * write implies read, hence set both + */ + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_RW)); +} + +static inline pte_t pte_mkdirty(pte_t pte) +{ + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_DIRTY | _PAGE_SOFT_DIRTY)); +} + +static inline pte_t pte_mkyoung(pte_t pte) +{ + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_ACCESSED)); +} + +static inline pte_t pte_mkspecial(pte_t pte) +{ + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SPECIAL)); +} + +static inline pte_t pte_mkhuge(pte_t pte) +{ + return pte; +} + +static inline pte_t pte_mkdevmap(pte_t pte) +{ + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SPECIAL | _PAGE_DEVMAP)); +} + +static inline pte_t pte_mkprivileged(pte_t pte) +{ + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PRIVILEGED)); +} + +static inline pte_t pte_mkuser(pte_t pte) +{ + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_PRIVILEGED)); +} + +/* + * This is potentially called with a pmd as the argument, in which case it's not + * safe to check _PAGE_DEVMAP unless we also confirm that _PAGE_PTE is set. + * That's because the bit we use for _PAGE_DEVMAP is not reserved for software + * use in page directory entries (ie. non-ptes). + */ +static inline int pte_devmap(pte_t pte) +{ + u64 mask = cpu_to_be64(_PAGE_DEVMAP | _PAGE_PTE); + + return (pte_raw(pte) & mask) == mask; +} + +static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) +{ + /* FIXME!! check whether this need to be a conditional */ + return __pte_raw((pte_raw(pte) & cpu_to_be64(_PAGE_CHG_MASK)) | + cpu_to_be64(pgprot_val(newprot))); +} + +/* Encode and de-code a swap entry */ +#define MAX_SWAPFILES_CHECK() do { \ + BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS); \ + /* \ + * Don't have overlapping bits with _PAGE_HPTEFLAGS \ + * We filter HPTEFLAGS on set_pte. \ + */ \ + BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \ + BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_SOFT_DIRTY); \ + } while (0) + +#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_MASK) >> PAGE_SHIFT) +#define __swp_entry(type, offset) ((swp_entry_t) { \ + ((type) << _PAGE_BIT_SWAP_TYPE) \ + | (((offset) << PAGE_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 + * matching pte in linux page table. + * Clear bits not found in swap entries here. + */ +#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) & ~_PAGE_PTE }) +#define __swp_entry_to_pte(x) __pte((x).val | _PAGE_PTE) +#define __pmd_to_swp_entry(pmd) (__pte_to_swp_entry(pmd_pte(pmd))) +#define __swp_entry_to_pmd(x) (pte_pmd(__swp_entry_to_pte(x))) + +#ifdef CONFIG_MEM_SOFT_DIRTY +#define _PAGE_SWP_SOFT_DIRTY (1UL << (SWP_TYPE_BITS + _PAGE_BIT_SWAP_TYPE)) +#else +#define _PAGE_SWP_SOFT_DIRTY 0UL +#endif /* CONFIG_MEM_SOFT_DIRTY */ + +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY +static inline pte_t pte_swp_mksoft_dirty(pte_t pte) +{ + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SWP_SOFT_DIRTY)); +} + +static inline bool pte_swp_soft_dirty(pte_t pte) +{ + return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SWP_SOFT_DIRTY)); +} + +static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) +{ + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_SWP_SOFT_DIRTY)); +} +#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ + +static inline bool check_pte_access(unsigned long access, unsigned long ptev) +{ + /* + * This check for _PAGE_RWX and _PAGE_PRESENT bits + */ + if (access & ~ptev) + return false; + /* + * This check for access to privilege space + */ + if ((access & _PAGE_PRIVILEGED) != (ptev & _PAGE_PRIVILEGED)) + return false; + + return true; +} +/* + * Generic functions with hash/radix callbacks + */ + +static inline void __ptep_set_access_flags(struct vm_area_struct *vma, + pte_t *ptep, pte_t entry, + unsigned long address, + int psize) +{ + if (radix_enabled()) + return radix__ptep_set_access_flags(vma, ptep, entry, + address, psize); + return hash__ptep_set_access_flags(ptep, entry); +} + +#define __HAVE_ARCH_PTE_SAME +static inline int pte_same(pte_t pte_a, pte_t pte_b) +{ + if (radix_enabled()) + return radix__pte_same(pte_a, pte_b); + return hash__pte_same(pte_a, pte_b); +} + +static inline int pte_none(pte_t pte) +{ + if (radix_enabled()) + return radix__pte_none(pte); + return hash__pte_none(pte); +} + +static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, int percpu) +{ + + VM_WARN_ON(!(pte_raw(pte) & cpu_to_be64(_PAGE_PTE))); + /* + * Keep the _PAGE_PTE added till we are sure we handle _PAGE_PTE + * in all the callers. + */ + pte = __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PTE)); + + if (radix_enabled()) + return radix__set_pte_at(mm, addr, ptep, pte, percpu); + return hash__set_pte_at(mm, addr, ptep, pte, percpu); +} + +#define _PAGE_CACHE_CTL (_PAGE_SAO | _PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT) + +#define pgprot_noncached pgprot_noncached +static inline pgprot_t pgprot_noncached(pgprot_t prot) +{ + return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | + _PAGE_NON_IDEMPOTENT); +} + +#define pgprot_noncached_wc pgprot_noncached_wc +static inline pgprot_t pgprot_noncached_wc(pgprot_t prot) +{ + return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | + _PAGE_TOLERANT); +} + +#define pgprot_cached pgprot_cached +static inline pgprot_t pgprot_cached(pgprot_t prot) +{ + return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL)); +} + +#define pgprot_writecombine pgprot_writecombine +static inline pgprot_t pgprot_writecombine(pgprot_t prot) +{ + return pgprot_noncached_wc(prot); +} +/* + * check a pte mapping have cache inhibited property + */ +static inline bool pte_ci(pte_t pte) +{ + __be64 pte_v = pte_raw(pte); + + if (((pte_v & cpu_to_be64(_PAGE_CACHE_CTL)) == cpu_to_be64(_PAGE_TOLERANT)) || + ((pte_v & cpu_to_be64(_PAGE_CACHE_CTL)) == cpu_to_be64(_PAGE_NON_IDEMPOTENT))) + return true; + return false; +} + +static inline void pmd_clear(pmd_t *pmdp) +{ + if (IS_ENABLED(CONFIG_DEBUG_VM) && !radix_enabled()) { + /* + * Don't use this if we can possibly have a hash page table + * entry mapping this. + */ + WARN_ON((pmd_val(*pmdp) & (H_PAGE_HASHPTE | _PAGE_PTE)) == (H_PAGE_HASHPTE | _PAGE_PTE)); + } + *pmdp = __pmd(0); +} + +static inline int pmd_none(pmd_t pmd) +{ + return !pmd_raw(pmd); +} + +static inline int pmd_present(pmd_t pmd) +{ + /* + * A pmd is considerent present if _PAGE_PRESENT is set. + * We also need to consider the pmd present which is marked + * invalid during a split. Hence we look for _PAGE_INVALID + * if we find _PAGE_PRESENT cleared. + */ + if (pmd_raw(pmd) & cpu_to_be64(_PAGE_PRESENT | _PAGE_INVALID)) + return true; + + return false; +} + +static inline int pmd_is_serializing(pmd_t pmd) +{ + /* + * If the pmd is undergoing a split, the _PAGE_PRESENT bit is clear + * and _PAGE_INVALID is set (see pmd_present, pmdp_invalidate). + * + * This condition may also occur when flushing a pmd while flushing + * it (see ptep_modify_prot_start), so callers must ensure this + * case is fine as well. + */ + if ((pmd_raw(pmd) & cpu_to_be64(_PAGE_PRESENT | _PAGE_INVALID)) == + cpu_to_be64(_PAGE_INVALID)) + return true; + + return false; +} + +static inline int pmd_bad(pmd_t pmd) +{ + if (radix_enabled()) + return radix__pmd_bad(pmd); + return hash__pmd_bad(pmd); +} + +static inline void pud_clear(pud_t *pudp) +{ + if (IS_ENABLED(CONFIG_DEBUG_VM) && !radix_enabled()) { + /* + * Don't use this if we can possibly have a hash page table + * entry mapping this. + */ + WARN_ON((pud_val(*pudp) & (H_PAGE_HASHPTE | _PAGE_PTE)) == (H_PAGE_HASHPTE | _PAGE_PTE)); + } + *pudp = __pud(0); +} + +static inline int pud_none(pud_t pud) +{ + return !pud_raw(pud); +} + +static inline int pud_present(pud_t pud) +{ + return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PRESENT)); +} + +extern struct page *pud_page(pud_t pud); +extern struct page *pmd_page(pmd_t pmd); +static inline pte_t pud_pte(pud_t pud) +{ + return __pte_raw(pud_raw(pud)); +} + +static inline pud_t pte_pud(pte_t pte) +{ + return __pud_raw(pte_raw(pte)); +} +#define pud_write(pud) pte_write(pud_pte(pud)) + +static inline int pud_bad(pud_t pud) +{ + if (radix_enabled()) + return radix__pud_bad(pud); + return hash__pud_bad(pud); +} + +#define pud_access_permitted pud_access_permitted +static inline bool pud_access_permitted(pud_t pud, bool write) +{ + return pte_access_permitted(pud_pte(pud), write); +} + +#define __p4d_raw(x) ((p4d_t) { __pgd_raw(x) }) +static inline __be64 p4d_raw(p4d_t x) +{ + return pgd_raw(x.pgd); +} + +#define p4d_write(p4d) pte_write(p4d_pte(p4d)) + +static inline void p4d_clear(p4d_t *p4dp) +{ + *p4dp = __p4d(0); +} + +static inline int p4d_none(p4d_t p4d) +{ + return !p4d_raw(p4d); +} + +static inline int p4d_present(p4d_t p4d) +{ + return !!(p4d_raw(p4d) & cpu_to_be64(_PAGE_PRESENT)); +} + +static inline pte_t p4d_pte(p4d_t p4d) +{ + return __pte_raw(p4d_raw(p4d)); +} + +static inline p4d_t pte_p4d(pte_t pte) +{ + return __p4d_raw(pte_raw(pte)); +} + +static inline int p4d_bad(p4d_t p4d) +{ + if (radix_enabled()) + return radix__p4d_bad(p4d); + return hash__p4d_bad(p4d); +} + +#define p4d_access_permitted p4d_access_permitted +static inline bool p4d_access_permitted(p4d_t p4d, bool write) +{ + return pte_access_permitted(p4d_pte(p4d), write); +} + +extern struct page *p4d_page(p4d_t p4d); + +/* Pointers in the page table tree are physical addresses */ +#define __pgtable_ptr_val(ptr) __pa(ptr) + +static inline pud_t *p4d_pgtable(p4d_t p4d) +{ + return (pud_t *)__va(p4d_val(p4d) & ~P4D_MASKED_BITS); +} + +static inline pmd_t *pud_pgtable(pud_t pud) +{ + return (pmd_t *)__va(pud_val(pud) & ~PUD_MASKED_BITS); +} + +#define pte_ERROR(e) \ + 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)) + +static inline int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot) +{ + if (radix_enabled()) { +#if defined(CONFIG_PPC_RADIX_MMU) && defined(DEBUG_VM) + unsigned long page_size = 1 << mmu_psize_defs[mmu_io_psize].shift; + WARN((page_size != PAGE_SIZE), "I/O page size != PAGE_SIZE"); +#endif + return radix__map_kernel_page(ea, pa, prot, PAGE_SIZE); + } + return hash__map_kernel_page(ea, pa, prot); +} + +void unmap_kernel_page(unsigned long va); + +static inline int __meminit vmemmap_create_mapping(unsigned long start, + unsigned long page_size, + unsigned long phys) +{ + if (radix_enabled()) + return radix__vmemmap_create_mapping(start, page_size, phys); + return hash__vmemmap_create_mapping(start, page_size, phys); +} + +#ifdef CONFIG_MEMORY_HOTPLUG +static inline void vmemmap_remove_mapping(unsigned long start, + unsigned long page_size) +{ + if (radix_enabled()) + return radix__vmemmap_remove_mapping(start, page_size); + return hash__vmemmap_remove_mapping(start, page_size); +} +#endif + +static inline pte_t pmd_pte(pmd_t pmd) +{ + return __pte_raw(pmd_raw(pmd)); +} + +static inline pmd_t pte_pmd(pte_t pte) +{ + return __pmd_raw(pte_raw(pte)); +} + +static inline pte_t *pmdp_ptep(pmd_t *pmd) +{ + return (pte_t *)pmd; +} +#define pmd_pfn(pmd) pte_pfn(pmd_pte(pmd)) +#define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) +#define pmd_young(pmd) pte_young(pmd_pte(pmd)) +#define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) +#define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) +#define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) +#define pmd_mkclean(pmd) pte_pmd(pte_mkclean(pmd_pte(pmd))) +#define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) +#define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd))) +#define pmd_mk_savedwrite(pmd) pte_pmd(pte_mk_savedwrite(pmd_pte(pmd))) +#define pmd_clear_savedwrite(pmd) pte_pmd(pte_clear_savedwrite(pmd_pte(pmd))) + +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY +#define pmd_soft_dirty(pmd) pte_soft_dirty(pmd_pte(pmd)) +#define pmd_mksoft_dirty(pmd) pte_pmd(pte_mksoft_dirty(pmd_pte(pmd))) +#define pmd_clear_soft_dirty(pmd) pte_pmd(pte_clear_soft_dirty(pmd_pte(pmd))) + +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION +#define pmd_swp_mksoft_dirty(pmd) pte_pmd(pte_swp_mksoft_dirty(pmd_pte(pmd))) +#define pmd_swp_soft_dirty(pmd) pte_swp_soft_dirty(pmd_pte(pmd)) +#define pmd_swp_clear_soft_dirty(pmd) pte_pmd(pte_swp_clear_soft_dirty(pmd_pte(pmd))) +#endif +#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ + +#ifdef CONFIG_NUMA_BALANCING +static inline int pmd_protnone(pmd_t pmd) +{ + return pte_protnone(pmd_pte(pmd)); +} +#endif /* CONFIG_NUMA_BALANCING */ + +#define pmd_write(pmd) pte_write(pmd_pte(pmd)) +#define __pmd_write(pmd) __pte_write(pmd_pte(pmd)) +#define pmd_savedwrite(pmd) pte_savedwrite(pmd_pte(pmd)) + +#define pmd_access_permitted pmd_access_permitted +static inline bool pmd_access_permitted(pmd_t pmd, bool write) +{ + /* + * pmdp_invalidate sets this combination (which is not caught by + * !pte_present() check in pte_access_permitted), to prevent + * lock-free lookups, as part of the serialize_against_pte_lookup() + * synchronisation. + * + * This also catches the case where the PTE's hardware PRESENT bit is + * cleared while TLB is flushed, which is suboptimal but should not + * be frequent. + */ + if (pmd_is_serializing(pmd)) + return false; + + return pte_access_permitted(pmd_pte(pmd), write); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot); +extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot); +extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot); +extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmd); +static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmd) +{ +} + +extern int hash__has_transparent_hugepage(void); +static inline int has_transparent_hugepage(void) +{ + if (radix_enabled()) + return radix__has_transparent_hugepage(); + return hash__has_transparent_hugepage(); +} +#define has_transparent_hugepage has_transparent_hugepage + +static inline unsigned long +pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, + unsigned long clr, unsigned long set) +{ + if (radix_enabled()) + return radix__pmd_hugepage_update(mm, addr, pmdp, clr, set); + return hash__pmd_hugepage_update(mm, addr, pmdp, clr, set); +} + +/* + * returns true for pmd migration entries, THP, devmap, hugetlb + * But compile time dependent on THP config + */ +static inline int pmd_large(pmd_t pmd) +{ + return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); +} + +/* + * For radix we should always find H_PAGE_HASHPTE zero. Hence + * the below will work for radix too + */ +static inline int __pmdp_test_and_clear_young(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp) +{ + unsigned long old; + + if ((pmd_raw(*pmdp) & cpu_to_be64(_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0) + return 0; + old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0); + return ((old & _PAGE_ACCESSED) != 0); +} + +#define __HAVE_ARCH_PMDP_SET_WRPROTECT +static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + if (__pmd_write((*pmdp))) + pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0); + else if (unlikely(pmd_savedwrite(*pmdp))) + pmd_hugepage_update(mm, addr, pmdp, 0, _PAGE_PRIVILEGED); +} + +/* + * Only returns true for a THP. False for pmd migration entry. + * We also need to return true when we come across a pte that + * in between a thp split. While splitting THP, we mark the pmd + * invalid (pmdp_invalidate()) before we set it with pte page + * address. A pmd_trans_huge() check against a pmd entry during that time + * should return true. + * We should not call this on a hugetlb entry. We should check for HugeTLB + * entry using vma->vm_flags + * The page table walk rule is explained in Documentation/vm/transhuge.rst + */ +static inline int pmd_trans_huge(pmd_t pmd) +{ + if (!pmd_present(pmd)) + return false; + + if (radix_enabled()) + return radix__pmd_trans_huge(pmd); + return hash__pmd_trans_huge(pmd); +} + +#define __HAVE_ARCH_PMD_SAME +static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) +{ + if (radix_enabled()) + return radix__pmd_same(pmd_a, pmd_b); + return hash__pmd_same(pmd_a, pmd_b); +} + +static inline pmd_t pmd_mkhuge(pmd_t pmd) +{ + if (radix_enabled()) + return radix__pmd_mkhuge(pmd); + return hash__pmd_mkhuge(pmd); +} + +#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS +extern int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty); + +#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG +extern int pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); + +#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR +static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp) +{ + if (radix_enabled()) + return radix__pmdp_huge_get_and_clear(mm, addr, pmdp); + return hash__pmdp_huge_get_and_clear(mm, addr, pmdp); +} + +static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) +{ + if (radix_enabled()) + return radix__pmdp_collapse_flush(vma, address, pmdp); + return hash__pmdp_collapse_flush(vma, address, pmdp); +} +#define pmdp_collapse_flush pmdp_collapse_flush + +#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL +pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma, + unsigned long addr, + pmd_t *pmdp, int full); + +#define __HAVE_ARCH_PGTABLE_DEPOSIT +static inline void pgtable_trans_huge_deposit(struct mm_struct *mm, + pmd_t *pmdp, pgtable_t pgtable) +{ + if (radix_enabled()) + return radix__pgtable_trans_huge_deposit(mm, pmdp, pgtable); + return hash__pgtable_trans_huge_deposit(mm, pmdp, pgtable); +} + +#define __HAVE_ARCH_PGTABLE_WITHDRAW +static inline pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, + pmd_t *pmdp) +{ + if (radix_enabled()) + return radix__pgtable_trans_huge_withdraw(mm, pmdp); + return hash__pgtable_trans_huge_withdraw(mm, pmdp); +} + +#define __HAVE_ARCH_PMDP_INVALIDATE +extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp); + +#define pmd_move_must_withdraw pmd_move_must_withdraw +struct spinlock; +extern int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, + struct spinlock *old_pmd_ptl, + struct vm_area_struct *vma); +/* + * Hash translation mode use the deposited table to store hash pte + * slot information. + */ +#define arch_needs_pgtable_deposit arch_needs_pgtable_deposit +static inline bool arch_needs_pgtable_deposit(void) +{ + if (radix_enabled()) + return false; + return true; +} +extern void serialize_against_pte_lookup(struct mm_struct *mm); + + +static inline pmd_t pmd_mkdevmap(pmd_t pmd) +{ + if (radix_enabled()) + return radix__pmd_mkdevmap(pmd); + return hash__pmd_mkdevmap(pmd); +} + +static inline int pmd_devmap(pmd_t pmd) +{ + return pte_devmap(pmd_pte(pmd)); +} + +static inline int pud_devmap(pud_t pud) +{ + return 0; +} + +static inline int pgd_devmap(pgd_t pgd) +{ + return 0; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +static inline int pud_pfn(pud_t pud) +{ + /* + * Currently all calls to pud_pfn() are gated around a pud_devmap() + * check so this should never be used. If it grows another user we + * want to know about it. + */ + BUILD_BUG(); + return 0; +} +#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION +pte_t ptep_modify_prot_start(struct vm_area_struct *, unsigned long, pte_t *); +void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long, + pte_t *, pte_t, pte_t); + +/* + * Returns true for a R -> RW upgrade of pte + */ +static inline bool is_pte_rw_upgrade(unsigned long old_val, unsigned long new_val) +{ + if (!(old_val & _PAGE_READ)) + return false; + + if ((!(old_val & _PAGE_WRITE)) && (new_val & _PAGE_WRITE)) + return true; + + return false; +} + +/* + * Like pmd_huge() and pmd_large(), but works regardless of config options + */ +#define pmd_is_leaf pmd_is_leaf +#define pmd_leaf pmd_is_leaf +static inline bool pmd_is_leaf(pmd_t pmd) +{ + return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); +} + +#define pud_is_leaf pud_is_leaf +#define pud_leaf pud_is_leaf +static inline bool pud_is_leaf(pud_t pud) +{ + return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); +} + +#define p4d_is_leaf p4d_is_leaf +#define p4d_leaf p4d_is_leaf +static inline bool p4d_is_leaf(p4d_t p4d) +{ + return !!(p4d_raw(p4d) & cpu_to_be64(_PAGE_PTE)); +} + +#endif /* __ASSEMBLY__ */ +#endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */ diff --git a/arch/powerpc/include/asm/book3s/64/pkeys.h b/arch/powerpc/include/asm/book3s/64/pkeys.h new file mode 100644 index 000000000..b7d9f4267 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/pkeys.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef _ASM_POWERPC_BOOK3S_64_PKEYS_H +#define _ASM_POWERPC_BOOK3S_64_PKEYS_H + +#include <asm/book3s/64/hash-pkey.h> + +extern u64 __ro_after_init default_uamor; + +static inline u64 vmflag_to_pte_pkey_bits(u64 vm_flags) +{ + if (!mmu_has_feature(MMU_FTR_PKEY)) + return 0x0UL; + + if (radix_enabled()) + BUG(); + return hash__vmflag_to_pte_pkey_bits(vm_flags); +} + +static inline u16 pte_to_pkey_bits(u64 pteflags) +{ + if (radix_enabled()) + BUG(); + return hash__pte_to_pkey_bits(pteflags); +} + +#endif /*_ASM_POWERPC_KEYS_H */ diff --git a/arch/powerpc/include/asm/book3s/64/radix-4k.h b/arch/powerpc/include/asm/book3s/64/radix-4k.h new file mode 100644 index 000000000..035ceecd6 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/radix-4k.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_PGTABLE_RADIX_4K_H +#define _ASM_POWERPC_PGTABLE_RADIX_4K_H + +/* + * For 4K page size supported index is 13/9/9/9 + */ +#define RADIX_PTE_INDEX_SIZE 9 // size: 8B << 9 = 4KB, maps 2^9 x 4K = 2MB +#define RADIX_PMD_INDEX_SIZE 9 // size: 8B << 9 = 4KB, maps 2^9 x 2MB = 1GB +#define RADIX_PUD_INDEX_SIZE 9 // size: 8B << 9 = 4KB, maps 2^9 x 1GB = 512GB +#define RADIX_PGD_INDEX_SIZE 13 // size: 8B << 13 = 64KB, maps 2^13 x 512GB = 4PB + +/* + * One fragment per page + */ +#define RADIX_PTE_FRAG_SIZE_SHIFT (RADIX_PTE_INDEX_SIZE + 3) +#define RADIX_PTE_FRAG_NR (PAGE_SIZE >> RADIX_PTE_FRAG_SIZE_SHIFT) + +#define RADIX_PMD_FRAG_SIZE_SHIFT (RADIX_PMD_INDEX_SIZE + 3) +#define RADIX_PMD_FRAG_NR (PAGE_SIZE >> RADIX_PMD_FRAG_SIZE_SHIFT) + +#endif /* _ASM_POWERPC_PGTABLE_RADIX_4K_H */ diff --git a/arch/powerpc/include/asm/book3s/64/radix-64k.h b/arch/powerpc/include/asm/book3s/64/radix-64k.h new file mode 100644 index 000000000..54e33828b --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/radix-64k.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_PGTABLE_RADIX_64K_H +#define _ASM_POWERPC_PGTABLE_RADIX_64K_H + +/* + * For 64K page size supported index is 13/9/9/5 + */ +#define RADIX_PTE_INDEX_SIZE 5 // size: 8B << 5 = 256B, maps 2^5 x 64K = 2MB +#define RADIX_PMD_INDEX_SIZE 9 // size: 8B << 9 = 4KB, maps 2^9 x 2MB = 1GB +#define RADIX_PUD_INDEX_SIZE 9 // size: 8B << 9 = 4KB, maps 2^9 x 1GB = 512GB +#define RADIX_PGD_INDEX_SIZE 13 // size: 8B << 13 = 64KB, maps 2^13 x 512GB = 4PB + +/* + * We use a 256 byte PTE page fragment in radix + * 8 bytes per each PTE entry. + */ +#define RADIX_PTE_FRAG_SIZE_SHIFT (RADIX_PTE_INDEX_SIZE + 3) +#define RADIX_PTE_FRAG_NR (PAGE_SIZE >> RADIX_PTE_FRAG_SIZE_SHIFT) + +#define RADIX_PMD_FRAG_SIZE_SHIFT (RADIX_PMD_INDEX_SIZE + 3) +#define RADIX_PMD_FRAG_NR (PAGE_SIZE >> RADIX_PMD_FRAG_SIZE_SHIFT) + +#endif /* _ASM_POWERPC_PGTABLE_RADIX_64K_H */ diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h new file mode 100644 index 000000000..59cab558e --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -0,0 +1,320 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_PGTABLE_RADIX_H +#define _ASM_POWERPC_PGTABLE_RADIX_H + +#include <asm/asm-const.h> + +#ifndef __ASSEMBLY__ +#include <asm/cmpxchg.h> +#endif + +#ifdef CONFIG_PPC_64K_PAGES +#include <asm/book3s/64/radix-64k.h> +#else +#include <asm/book3s/64/radix-4k.h> +#endif + +#ifndef __ASSEMBLY__ +#include <asm/book3s/64/tlbflush-radix.h> +#include <asm/cpu_has_feature.h> +#endif + +/* An empty PTE can still have a R or C writeback */ +#define RADIX_PTE_NONE_MASK (_PAGE_DIRTY | _PAGE_ACCESSED) + +/* Bits to set in a RPMD/RPUD/RPGD */ +#define RADIX_PMD_VAL_BITS (0x8000000000000000UL | RADIX_PTE_INDEX_SIZE) +#define RADIX_PUD_VAL_BITS (0x8000000000000000UL | RADIX_PMD_INDEX_SIZE) +#define RADIX_PGD_VAL_BITS (0x8000000000000000UL | RADIX_PUD_INDEX_SIZE) + +/* Don't have anything in the reserved bits and leaf bits */ +#define RADIX_PMD_BAD_BITS 0x60000000000000e0UL +#define RADIX_PUD_BAD_BITS 0x60000000000000e0UL +#define RADIX_P4D_BAD_BITS 0x60000000000000e0UL + +#define RADIX_PMD_SHIFT (PAGE_SHIFT + RADIX_PTE_INDEX_SIZE) +#define RADIX_PUD_SHIFT (RADIX_PMD_SHIFT + RADIX_PMD_INDEX_SIZE) +#define RADIX_PGD_SHIFT (RADIX_PUD_SHIFT + RADIX_PUD_INDEX_SIZE) +/* + * Size of EA range mapped by our pagetables. + */ +#define RADIX_PGTABLE_EADDR_SIZE (RADIX_PTE_INDEX_SIZE + RADIX_PMD_INDEX_SIZE + \ + RADIX_PUD_INDEX_SIZE + RADIX_PGD_INDEX_SIZE + PAGE_SHIFT) +#define RADIX_PGTABLE_RANGE (ASM_CONST(1) << RADIX_PGTABLE_EADDR_SIZE) + +/* + * We support 52 bit address space, Use top bit for kernel + * virtual mapping. Also make sure kernel fit in the top + * quadrant. + * + * +------------------+ + * +------------------+ Kernel virtual map (0xc008000000000000) + * | | + * | | + * | | + * 0b11......+------------------+ Kernel linear map (0xc....) + * | | + * | 2 quadrant | + * | | + * 0b10......+------------------+ + * | | + * | 1 quadrant | + * | | + * 0b01......+------------------+ + * | | + * | 0 quadrant | + * | | + * 0b00......+------------------+ + * + * + * 3rd quadrant expanded: + * +------------------------------+ + * | | + * | | + * | | + * +------------------------------+ Kernel vmemmap end (0xc010000000000000) + * | | + * | 512TB | + * | | + * +------------------------------+ Kernel IO map end/vmemap start + * | | + * | 512TB | + * | | + * +------------------------------+ Kernel vmap end/ IO map start + * | | + * | 512TB | + * | | + * +------------------------------+ Kernel virt start (0xc008000000000000) + * | | + * | | + * | | + * +------------------------------+ Kernel linear (0xc.....) + */ + + +/* + * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS + * if we increase SECTIONS_WIDTH we will not store node details in page->flags and + * page_to_nid does a page->section->node lookup + * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce + * memory requirements with large number of sections. + * 51 bits is the max physical real address on POWER9 + */ + +#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) +#define R_MAX_PHYSMEM_BITS 51 +#else +#define R_MAX_PHYSMEM_BITS 46 +#endif + +#define RADIX_KERN_VIRT_START ASM_CONST(0xc008000000000000) +/* + * 49 = MAX_EA_BITS_PER_CONTEXT (hash specific). To make sure we pick + * the same value as hash. + */ +#define RADIX_KERN_MAP_SIZE (1UL << 49) + +#define RADIX_VMALLOC_START RADIX_KERN_VIRT_START +#define RADIX_VMALLOC_SIZE RADIX_KERN_MAP_SIZE +#define RADIX_VMALLOC_END (RADIX_VMALLOC_START + RADIX_VMALLOC_SIZE) + +#define RADIX_KERN_IO_START RADIX_VMALLOC_END +#define RADIX_KERN_IO_SIZE RADIX_KERN_MAP_SIZE +#define RADIX_KERN_IO_END (RADIX_KERN_IO_START + RADIX_KERN_IO_SIZE) + +#define RADIX_VMEMMAP_START RADIX_KERN_IO_END +#define RADIX_VMEMMAP_SIZE RADIX_KERN_MAP_SIZE +#define RADIX_VMEMMAP_END (RADIX_VMEMMAP_START + RADIX_VMEMMAP_SIZE) + +#ifndef __ASSEMBLY__ +#define RADIX_PTE_TABLE_SIZE (sizeof(pte_t) << RADIX_PTE_INDEX_SIZE) +#define RADIX_PMD_TABLE_SIZE (sizeof(pmd_t) << RADIX_PMD_INDEX_SIZE) +#define RADIX_PUD_TABLE_SIZE (sizeof(pud_t) << RADIX_PUD_INDEX_SIZE) +#define RADIX_PGD_TABLE_SIZE (sizeof(pgd_t) << RADIX_PGD_INDEX_SIZE) + +#ifdef CONFIG_STRICT_KERNEL_RWX +extern void radix__mark_rodata_ro(void); +extern void radix__mark_initmem_nx(void); +#endif + +extern void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, + pte_t entry, unsigned long address, + int psize); + +extern void radix__ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t pte); + +static inline unsigned long __radix_pte_update(pte_t *ptep, unsigned long clr, + unsigned long set) +{ + __be64 old_be, tmp_be; + + __asm__ __volatile__( + "1: ldarx %0,0,%3 # pte_update\n" + " andc %1,%0,%5 \n" + " or %1,%1,%4 \n" + " stdcx. %1,0,%3 \n" + " bne- 1b" + : "=&r" (old_be), "=&r" (tmp_be), "=m" (*ptep) + : "r" (ptep), "r" (cpu_to_be64(set)), "r" (cpu_to_be64(clr)) + : "cc" ); + + return be64_to_cpu(old_be); +} + +static inline unsigned long radix__pte_update(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, unsigned long clr, + unsigned long set, + int huge) +{ + unsigned long old_pte; + + old_pte = __radix_pte_update(ptep, clr, set); + if (!huge) + assert_pte_locked(mm, addr); + + return old_pte; +} + +static inline pte_t radix__ptep_get_and_clear_full(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, int full) +{ + unsigned long old_pte; + + if (full) { + old_pte = pte_val(*ptep); + *ptep = __pte(0); + } else + old_pte = radix__pte_update(mm, addr, ptep, ~0ul, 0, 0); + + return __pte(old_pte); +} + +static inline int radix__pte_same(pte_t pte_a, pte_t pte_b) +{ + return ((pte_raw(pte_a) ^ pte_raw(pte_b)) == 0); +} + +static inline int radix__pte_none(pte_t pte) +{ + return (pte_val(pte) & ~RADIX_PTE_NONE_MASK) == 0; +} + +static inline void radix__set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, int percpu) +{ + *ptep = pte; + + /* + * The architecture suggests a ptesync after setting the pte, which + * orders the store that updates the pte with subsequent page table + * walk accesses which may load the pte. Without this it may be + * possible for a subsequent access to result in spurious fault. + * + * This is not necessary for correctness, because a spurious fault + * is tolerated by the page fault handler, and this store will + * eventually be seen. In testing, there was no noticable increase + * in user faults on POWER9. Avoiding ptesync here is a significant + * win for things like fork. If a future microarchitecture benefits + * from ptesync, it should probably go into update_mmu_cache, rather + * than set_pte_at (which is used to set ptes unrelated to faults). + * + * Spurious faults from the kernel memory are not tolerated, so there + * is a ptesync in flush_cache_vmap, and __map_kernel_page() follows + * the pte update sequence from ISA Book III 6.10 Translation Table + * Update Synchronization Requirements. + */ +} + +static inline int radix__pmd_bad(pmd_t pmd) +{ + return !!(pmd_val(pmd) & RADIX_PMD_BAD_BITS); +} + +static inline int radix__pmd_same(pmd_t pmd_a, pmd_t pmd_b) +{ + return ((pmd_raw(pmd_a) ^ pmd_raw(pmd_b)) == 0); +} + +static inline int radix__pud_bad(pud_t pud) +{ + return !!(pud_val(pud) & RADIX_PUD_BAD_BITS); +} + + +static inline int radix__p4d_bad(p4d_t p4d) +{ + return !!(p4d_val(p4d) & RADIX_P4D_BAD_BITS); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + +static inline int radix__pmd_trans_huge(pmd_t pmd) +{ + return (pmd_val(pmd) & (_PAGE_PTE | _PAGE_DEVMAP)) == _PAGE_PTE; +} + +static inline pmd_t radix__pmd_mkhuge(pmd_t pmd) +{ + return __pmd(pmd_val(pmd) | _PAGE_PTE); +} + +extern unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, unsigned long clr, + unsigned long set); +extern pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); +extern void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable); +extern pgtable_t radix__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); +extern pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp); +static inline int radix__has_transparent_hugepage(void) +{ + /* For radix 2M at PMD level means thp */ + if (mmu_psize_defs[MMU_PAGE_2M].shift == PMD_SHIFT) + return 1; + return 0; +} +#endif + +static inline pmd_t radix__pmd_mkdevmap(pmd_t pmd) +{ + return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP)); +} + +extern int __meminit radix__vmemmap_create_mapping(unsigned long start, + unsigned long page_size, + unsigned long phys); +extern void radix__vmemmap_remove_mapping(unsigned long start, + unsigned long page_size); + +extern int radix__map_kernel_page(unsigned long ea, unsigned long pa, + pgprot_t flags, unsigned int psz); + +static inline unsigned long radix__get_tree_size(void) +{ + unsigned long rts_field; + /* + * We support 52 bits, hence: + * bits 52 - 31 = 21, 0b10101 + * RTS encoding details + * bits 0 - 3 of rts -> bits 6 - 8 unsigned long + * bits 4 - 5 of rts -> bits 62 - 63 of unsigned long + */ + rts_field = (0x5UL << 5); /* 6 - 8 bits */ + rts_field |= (0x2UL << 61); + + return rts_field; +} + +#ifdef CONFIG_MEMORY_HOTPLUG +int radix__create_section_mapping(unsigned long start, unsigned long end, + int nid, pgprot_t prot); +int radix__remove_section_mapping(unsigned long start, unsigned long end); +#endif /* CONFIG_MEMORY_HOTPLUG */ +#endif /* __ASSEMBLY__ */ +#endif diff --git a/arch/powerpc/include/asm/book3s/64/slice.h b/arch/powerpc/include/asm/book3s/64/slice.h new file mode 100644 index 000000000..f0d3194ba --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/slice.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_SLICE_H +#define _ASM_POWERPC_BOOK3S_64_SLICE_H + +#define SLICE_LOW_SHIFT 28 +#define SLICE_LOW_TOP (0x100000000ul) +#define SLICE_NUM_LOW (SLICE_LOW_TOP >> SLICE_LOW_SHIFT) +#define GET_LOW_SLICE_INDEX(addr) ((addr) >> SLICE_LOW_SHIFT) + +#define SLICE_HIGH_SHIFT 40 +#define SLICE_NUM_HIGH (H_PGTABLE_RANGE >> SLICE_HIGH_SHIFT) +#define GET_HIGH_SLICE_INDEX(addr) ((addr) >> SLICE_HIGH_SHIFT) + +#define SLB_ADDR_LIMIT_DEFAULT DEFAULT_MAP_WINDOW_USER64 + +#endif /* _ASM_POWERPC_BOOK3S_64_SLICE_H */ 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..3b9576973 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h @@ -0,0 +1,119 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_TLBFLUSH_HASH_H +#define _ASM_POWERPC_BOOK3S_64_TLBFLUSH_HASH_H + +/* + * TLB flushing for 64-bit hash-MMU CPUs + */ + +#include <linux/percpu.h> +#include <asm/page.h> + +#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; + + if (radix_enabled()) + return; + batch = this_cpu_ptr(&ppc64_tlb_batch); + batch->active = 1; +} + +static inline void arch_leave_lazy_mmu_mode(void) +{ + struct ppc64_tlb_batch *batch; + + if (radix_enabled()) + return; + 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 hash__tlbiel_all(unsigned int action); + +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 hash__local_flush_tlb_mm(struct mm_struct *mm) +{ +} + +static inline void hash__flush_tlb_mm(struct mm_struct *mm) +{ +} + +static inline void hash__local_flush_all_mm(struct mm_struct *mm) +{ + /* + * There's no Page Walk Cache for hash, so what is needed is + * the same as flush_tlb_mm(), which doesn't really make sense + * with hash. So the only thing we could do is flush the + * entire LPID! Punt for now, as it's not being used. + */ + WARN_ON_ONCE(1); +} + +static inline void hash__flush_all_mm(struct mm_struct *mm) +{ + /* + * There's no Page Walk Cache for hash, so what is needed is + * the same as flush_tlb_mm(), which doesn't really make sense + * with hash. So the only thing we could do is flush the + * entire LPID! Punt for now, as it's not being used. + */ + WARN_ON_ONCE(1); +} + +static inline void hash__local_flush_tlb_page(struct vm_area_struct *vma, + unsigned long vmaddr) +{ +} + +static inline void hash__flush_tlb_page(struct vm_area_struct *vma, + unsigned long vmaddr) +{ +} + +static inline void hash__flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ +} + +static inline void hash__flush_tlb_kernel_range(unsigned long start, + unsigned long end) +{ +} + + +struct mmu_gather; +extern void hash__tlb_flush(struct mmu_gather *tlb); +/* Private function for use by PCI IO mapping code */ +extern void __flush_hash_table_range(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 */ diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h new file mode 100644 index 000000000..94439e0ce --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_TLBFLUSH_RADIX_H +#define _ASM_POWERPC_TLBFLUSH_RADIX_H + +#include <asm/hvcall.h> + +struct vm_area_struct; +struct mm_struct; +struct mmu_gather; + +static inline u64 psize_to_rpti_pgsize(unsigned long psize) +{ + if (psize == MMU_PAGE_4K) + return H_RPTI_PAGE_4K; + if (psize == MMU_PAGE_64K) + return H_RPTI_PAGE_64K; + if (psize == MMU_PAGE_2M) + return H_RPTI_PAGE_2M; + if (psize == MMU_PAGE_1G) + return H_RPTI_PAGE_1G; + return H_RPTI_PAGE_ALL; +} + +static inline int mmu_get_ap(int psize) +{ + return mmu_psize_defs[psize].ap; +} + +#ifdef CONFIG_PPC_RADIX_MMU +extern void radix__tlbiel_all(unsigned int action); +extern void radix__flush_tlb_lpid_page(unsigned int lpid, + unsigned long addr, + unsigned long page_size); +extern void radix__flush_pwc_lpid(unsigned int lpid); +extern void radix__flush_all_lpid(unsigned int lpid); +extern void radix__flush_all_lpid_guest(unsigned int lpid); +#else +static inline void radix__tlbiel_all(unsigned int action) { WARN_ON(1); }; +static inline void radix__flush_tlb_lpid_page(unsigned int lpid, + unsigned long addr, + unsigned long page_size) +{ + WARN_ON(1); +} +static inline void radix__flush_pwc_lpid(unsigned int lpid) +{ + WARN_ON(1); +} +static inline void radix__flush_all_lpid(unsigned int lpid) +{ + WARN_ON(1); +} +static inline void radix__flush_all_lpid_guest(unsigned int lpid) +{ + WARN_ON(1); +} +#endif + +extern void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end); +extern void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start, + unsigned long end, int psize); +extern void radix__flush_pmd_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end); +extern void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end); +extern void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end); + +extern void radix__local_flush_tlb_mm(struct mm_struct *mm); +extern void radix__local_flush_all_mm(struct mm_struct *mm); +extern void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); +extern void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, + int psize); +extern void radix__tlb_flush(struct mmu_gather *tlb); +#ifdef CONFIG_SMP +extern void radix__flush_tlb_mm(struct mm_struct *mm); +extern void radix__flush_all_mm(struct mm_struct *mm); +extern void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); +extern void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, + int psize); +#else +#define radix__flush_tlb_mm(mm) radix__local_flush_tlb_mm(mm) +#define radix__flush_all_mm(mm) radix__local_flush_all_mm(mm) +#define radix__flush_tlb_page(vma,addr) radix__local_flush_tlb_page(vma,addr) +#define radix__flush_tlb_page_psize(mm,addr,p) radix__local_flush_tlb_page_psize(mm,addr,p) +#endif +extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr); +extern void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr); +extern void radix__flush_tlb_all(void); + +#endif diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h new file mode 100644 index 000000000..dcb5c3839 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -0,0 +1,158 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_TLBFLUSH_H +#define _ASM_POWERPC_BOOK3S_64_TLBFLUSH_H + +#define MMU_NO_CONTEXT ~0UL + +#include <linux/mm_types.h> +#include <asm/book3s/64/tlbflush-hash.h> +#include <asm/book3s/64/tlbflush-radix.h> + +/* TLB flush actions. Used as argument to tlbiel_all() */ +enum { + TLB_INVAL_SCOPE_GLOBAL = 0, /* invalidate all TLBs */ + TLB_INVAL_SCOPE_LPID = 1, /* invalidate TLBs for current LPID */ +}; + +#ifdef CONFIG_PPC_NATIVE +static inline void tlbiel_all(void) +{ + /* + * This is used for host machine check and bootup. + * + * This uses early_radix_enabled and implementations use + * early_cpu_has_feature etc because that works early in boot + * and this is the machine check path which is not performance + * critical. + */ + if (early_radix_enabled()) + radix__tlbiel_all(TLB_INVAL_SCOPE_GLOBAL); + else + hash__tlbiel_all(TLB_INVAL_SCOPE_GLOBAL); +} +#else +static inline void tlbiel_all(void) { BUG(); }; +#endif + +static inline void tlbiel_all_lpid(bool radix) +{ + /* + * This is used for guest machine check. + */ + if (radix) + radix__tlbiel_all(TLB_INVAL_SCOPE_LPID); + else + hash__tlbiel_all(TLB_INVAL_SCOPE_LPID); +} + + +#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE +static inline void flush_pmd_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + if (radix_enabled()) + return radix__flush_pmd_tlb_range(vma, start, end); + return hash__flush_tlb_range(vma, start, end); +} + +#define __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE +static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma, + unsigned long start, + unsigned long end) +{ + if (radix_enabled()) + return radix__flush_hugetlb_tlb_range(vma, start, end); + return hash__flush_tlb_range(vma, start, end); +} + +static inline void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + if (radix_enabled()) + return radix__flush_tlb_range(vma, start, end); + return hash__flush_tlb_range(vma, start, end); +} + +static inline void flush_tlb_kernel_range(unsigned long start, + unsigned long end) +{ + if (radix_enabled()) + return radix__flush_tlb_kernel_range(start, end); + return hash__flush_tlb_kernel_range(start, end); +} + +static inline void local_flush_tlb_mm(struct mm_struct *mm) +{ + if (radix_enabled()) + return radix__local_flush_tlb_mm(mm); + return hash__local_flush_tlb_mm(mm); +} + +static inline void local_flush_tlb_page(struct vm_area_struct *vma, + unsigned long vmaddr) +{ + if (radix_enabled()) + return radix__local_flush_tlb_page(vma, vmaddr); + return hash__local_flush_tlb_page(vma, vmaddr); +} + +static inline void local_flush_all_mm(struct mm_struct *mm) +{ + if (radix_enabled()) + return radix__local_flush_all_mm(mm); + return hash__local_flush_all_mm(mm); +} + +static inline void tlb_flush(struct mmu_gather *tlb) +{ + if (radix_enabled()) + return radix__tlb_flush(tlb); + return hash__tlb_flush(tlb); +} + +#ifdef CONFIG_SMP +static inline void flush_tlb_mm(struct mm_struct *mm) +{ + if (radix_enabled()) + return radix__flush_tlb_mm(mm); + return hash__flush_tlb_mm(mm); +} + +static inline void flush_tlb_page(struct vm_area_struct *vma, + unsigned long vmaddr) +{ + if (radix_enabled()) + return radix__flush_tlb_page(vma, vmaddr); + return hash__flush_tlb_page(vma, vmaddr); +} + +static inline void flush_all_mm(struct mm_struct *mm) +{ + if (radix_enabled()) + return radix__flush_all_mm(mm); + return hash__flush_all_mm(mm); +} +#else +#define flush_tlb_mm(mm) local_flush_tlb_mm(mm) +#define flush_tlb_page(vma, addr) local_flush_tlb_page(vma, addr) +#define flush_all_mm(mm) local_flush_all_mm(mm) +#endif /* CONFIG_SMP */ + +#define flush_tlb_fix_spurious_fault flush_tlb_fix_spurious_fault +static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma, + unsigned long address) +{ + /* See ptep_set_access_flags comment */ + if (atomic_read(&vma->vm_mm->context.copros) > 0) + flush_tlb_page(vma, address); +} + +extern bool tlbie_capable; +extern bool tlbie_enabled; + +static inline bool cputlb_use_tlbie(void) +{ + return tlbie_enabled; +} + +#endif /* _ASM_POWERPC_BOOK3S_64_TLBFLUSH_H */ |