diff options
Diffstat (limited to 'arch/powerpc/include/asm/book3s/64')
| -rw-r--r-- | arch/powerpc/include/asm/book3s/64/hash-4k.h | 23 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/book3s/64/hash-64k.h | 21 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/book3s/64/hash.h | 95 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/book3s/64/hugetlb.h | 77 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/book3s/64/kup-radix.h | 108 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/book3s/64/mmu-hash.h | 70 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/book3s/64/mmu.h | 104 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/book3s/64/pgalloc.h | 52 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/book3s/64/pgtable.h | 12 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/book3s/64/radix-4k.h | 9 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/book3s/64/radix-64k.h | 8 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/book3s/64/radix.h | 40 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/book3s/64/slice.h | 13 |
13 files changed, 435 insertions, 197 deletions
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index cf5ba5254299..8fd8599c9395 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -2,10 +2,10 @@ #ifndef _ASM_POWERPC_BOOK3S_64_HASH_4K_H #define _ASM_POWERPC_BOOK3S_64_HASH_4K_H -#define H_PTE_INDEX_SIZE 9 -#define H_PMD_INDEX_SIZE 7 -#define H_PUD_INDEX_SIZE 9 -#define H_PGD_INDEX_SIZE 9 +#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 @@ -13,6 +13,21 @@ */ #define MAX_EA_BITS_PER_CONTEXT 46 +#define REGION_SHIFT (MAX_EA_BITS_PER_CONTEXT - 2) + +/* + * Our page table limit us to 64TB. Hence for the kernel mapping, + * each MAP area is limited to 16 TB. + * The four map areas are: linear mapping, vmap, IO and vmemmap + */ +#define H_KERN_MAP_SIZE (ASM_CONST(1) << REGION_SHIFT) + +/* + * Define the address range of the kernel non-linear virtual area + * 16TB + */ +#define H_KERN_VIRT_START ASM_CONST(0xc000100000000000) + #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) diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index f82ee8a3b561..d1d9177d9ebd 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -2,16 +2,29 @@ #ifndef _ASM_POWERPC_BOOK3S_64_HASH_64K_H #define _ASM_POWERPC_BOOK3S_64_HASH_64K_H -#define H_PTE_INDEX_SIZE 8 -#define H_PMD_INDEX_SIZE 10 -#define H_PUD_INDEX_SIZE 10 -#define H_PGD_INDEX_SIZE 8 +#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 + /* * 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 diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index 54b7af6cd27f..1d1183048cfd 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -29,6 +29,10 @@ #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. @@ -42,59 +46,63 @@ #endif /* - * Define the address range of the kernel non-linear virtual area. In contrast - * to the linear mapping, this is managed using the kernel page tables and then - * inserted into the hash page table to actually take effect, similarly to user - * mappings. + * +------------------------------+ + * | | + * | | + * | | + * +------------------------------+ 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_KERN_VIRT_START ASM_CONST(0xD000000000000000) -/* - * Allow virtual mapping of one context size. - * 512TB for 64K page size - * 64TB for 4K page size - */ -#define H_KERN_VIRT_SIZE (1UL << MAX_EA_BITS_PER_CONTEXT) +#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) -/* - * 8TB IO mapping size - */ -#define H_KERN_IO_SIZE ASM_CONST(0x80000000000) /* 8T */ +#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) -/* - * The vmalloc space starts at the beginning of the kernel non-linear virtual - * region, and occupies 504T (64K) or 56T (4K) - */ -#define H_VMALLOC_START H_KERN_VIRT_START -#define H_VMALLOC_SIZE (H_KERN_VIRT_SIZE - H_KERN_IO_SIZE) -#define H_VMALLOC_END (H_VMALLOC_START + H_VMALLOC_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 H_KERN_IO_START H_VMALLOC_END +#define NON_LINEAR_REGION_ID(ea) ((((unsigned long)ea - H_KERN_VIRT_START) >> REGION_SHIFT) + 2) /* * Region IDs */ -#define REGION_SHIFT 60UL -#define REGION_MASK (0xfUL << REGION_SHIFT) -#define REGION_ID(ea) (((unsigned long)(ea)) >> REGION_SHIFT) - -#define VMALLOC_REGION_ID (REGION_ID(H_VMALLOC_START)) -#define KERNEL_REGION_ID (REGION_ID(PAGE_OFFSET)) -#define VMEMMAP_REGION_ID (0xfUL) /* Server only */ -#define USER_REGION_ID (0UL) +#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) /* * Defines the address of the vmemap area, in its own region on * hash table CPUs. */ -#define H_VMEMMAP_BASE (VMEMMAP_REGION_ID << REGION_SHIFT) - #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 @@ -103,6 +111,25 @@ #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 (ea < H_KERN_VIRT_START) + return LINEAR_MAP_REGION_ID; + + VM_BUG_ON(id != 0xc); + BUILD_BUG_ON(NON_LINEAR_REGION_ID(H_VMALLOC_START) != 2); + + region_id = NON_LINEAR_REGION_ID(ea); + VM_BUG_ON(region_id > VMEMMAP_REGION_ID); + 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__pgd_bad(pgd_t pgd) diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h index ec2a55a553c7..12e150e615b7 100644 --- a/arch/powerpc/include/asm/book3s/64/hugetlb.h +++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h @@ -36,8 +36,8 @@ static inline int hstate_get_psize(struct hstate *hstate) } } -#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE -static inline bool gigantic_page_supported(void) +#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. @@ -49,7 +49,6 @@ static inline bool gigantic_page_supported(void) return true; } -#endif /* hugepd entry valid bit */ #define HUGEPD_VAL_BITS (0x8000000000000000UL) @@ -62,4 +61,76 @@ extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, 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/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h new file mode 100644 index 000000000000..f254de956d6a --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h @@ -0,0 +1,108 @@ +/* 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> + +#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 gpr +#ifdef CONFIG_PPC_KUAP + BEGIN_MMU_FTR_SECTION_NESTED(67) + ld \gpr, STACK_REGS_KUAP(r1) + mtspr SPRN_AMR, \gpr + END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_RADIX_KUAP, 67) +#endif +.endm + +.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 + +.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__ */ + +#ifdef CONFIG_PPC_KUAP + +#include <asm/reg.h> + +/* + * 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 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 void allow_user_access(void __user *to, const void __user *from, + unsigned long size) +{ + // This is written so we can resolve to a single case at build time + if (__builtin_constant_p(to) && to == NULL) + set_kuap(AMR_KUAP_BLOCK_WRITE); + else if (__builtin_constant_p(from) && from == NULL) + set_kuap(AMR_KUAP_BLOCK_READ); + else + set_kuap(0); +} + +static inline void prevent_user_access(void __user *to, const void __user *from, + unsigned long size) +{ + set_kuap(AMR_KUAP_BLOCKED); +} + +static inline bool bad_kuap_fault(struct pt_regs *regs, 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"); +} +#endif /* CONFIG_PPC_KUAP */ + +#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 index a28a28079edb..1e4705516a54 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -588,7 +588,8 @@ extern void slb_set_size(u16 size); #endif #define MAX_VMALLOC_CTX_CNT 1 -#define MAX_MEMMAP_CTX_CNT 1 +#define MAX_IO_CTX_CNT 1 +#define MAX_VMEMMAP_CTX_CNT 1 /* * 256MB segment @@ -601,13 +602,10 @@ extern void slb_set_size(u16 size); * would give a protovsid of 0x1fffffffff. That will result in a VSID 0 * because of the modulo operation in vsid scramble. * - * We add one extra context to MIN_USER_CONTEXT so that we can map kernel - * context easily. The +1 is to map the unused 0xe region mapping. */ #define MAX_USER_CONTEXT ((ASM_CONST(1) << CONTEXT_BITS) - 2) #define MIN_USER_CONTEXT (MAX_KERNEL_CTX_CNT + MAX_VMALLOC_CTX_CNT + \ - MAX_MEMMAP_CTX_CNT + 2) - + MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT) /* * For platforms that support on 65bit VA we limit the context bits */ @@ -657,8 +655,8 @@ extern void slb_set_size(u16 size); /* 4 bits per slice and we have one slice per 1TB */ #define SLICE_ARRAY_SIZE (H_PGTABLE_RANGE >> 41) -#define TASK_SLICE_ARRAY_SZ(x) ((x)->context.slb_addr_limit >> 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 @@ -687,12 +685,41 @@ struct subpage_prot_table { #define SBP_L3_SHIFT (SBP_L2_SHIFT + SBP_L2_BITS) extern void subpage_prot_free(struct mm_struct *mm); -extern void subpage_prot_init_new_context(struct mm_struct *mm); #else static inline void subpage_prot_free(struct mm_struct *mm) {} -static inline void subpage_prot_init_new_context(struct mm_struct *mm) { } #endif /* CONFIG_PPC_SUBPAGE_PROT */ +/* + * 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 @@ -747,7 +774,7 @@ static inline unsigned long get_vsid(unsigned long context, unsigned long ea, /* * Bad address. We return VSID 0 for that */ - if ((ea & ~REGION_MASK) >= H_PGTABLE_RANGE) + if ((ea & EA_MASK) >= H_PGTABLE_RANGE) return 0; if (!mmu_has_feature(MMU_FTR_68_BIT_VA)) @@ -774,28 +801,29 @@ static inline unsigned long get_vsid(unsigned long context, unsigned long ea, * 0x00002 - [ 0xc002000000000000 - 0xc003ffffffffffff] * 0x00003 - [ 0xc004000000000000 - 0xc005ffffffffffff] * 0x00004 - [ 0xc006000000000000 - 0xc007ffffffffffff] - - * 0x00005 - [ 0xd000000000000000 - 0xd001ffffffffffff ] - * 0x00006 - Not used - Can map 0xe000000000000000 range. - * 0x00007 - [ 0xf000000000000000 - 0xf001ffffffffffff ] * - * So we can compute the context from the region (top nibble) by - * subtracting 11, or 0xc - 1. + * 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 = REGION_ID(ea); + unsigned long region_id = get_region_id(ea); unsigned long ctx; /* - * For linear mapping we do support multiple context + * Depending on Kernel config, kernel region can have one context + * or more. */ - if (region_id == KERNEL_REGION_ID) { + if (region_id == LINEAR_MAP_REGION_ID) { /* * We already verified ea to be not beyond the addr limit. */ - ctx = 1 + ((ea & ~REGION_MASK) >> MAX_EA_BITS_PER_CONTEXT); + ctx = 1 + ((ea & EA_MASK) >> MAX_EA_BITS_PER_CONTEXT); } else - ctx = (region_id - 0xc) + MAX_KERNEL_CTX_CNT; + ctx = region_id + MAX_KERNEL_CTX_CNT - 1; return ctx; } diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index 1ceee000c18d..74d24201fc4f 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -25,15 +25,22 @@ struct mmu_psize_def { }; }; extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; +#endif /* __ASSEMBLY__ */ /* - * For BOOK3s 64 with 4k and 64K linux page size - * we want to use pointers, because the page table - * actually store pfn + * 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 */ -typedef pte_t *pgtable_t; - -#endif /* __ASSEMBLY__ */ +#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) && \ + defined(CONFIG_PPC_64K_PAGES) +#define MAX_PHYSMEM_BITS 51 +#else +#define MAX_PHYSMEM_BITS 46 +#endif /* 64-bit classic hash table MMU */ #include <asm/book3s/64/mmu-hash.h> @@ -89,16 +96,6 @@ struct spinlock; /* Maximum possible number of NPUs in a system. */ #define NV_MAX_NPUS 8 -/* - * 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); -}; - typedef struct { union { /* @@ -112,7 +109,6 @@ typedef struct { mm_context_id_t id; mm_context_id_t extended_id[TASK_SIZE_USER64/TASK_CONTEXT_SIZE]; }; - u16 user_psize; /* page size index */ /* Number of bits in the mm_cpumask */ atomic_t active_cpus; @@ -122,27 +118,9 @@ typedef struct { /* NPU NMMU context */ struct npu_context *npu_context; + struct hash_mm_context *hash_context; -#ifdef CONFIG_PPC_MM_SLICES - /* SLB page size encodings*/ - unsigned char low_slices_psize[BITS_PER_LONG / BITS_PER_BYTE]; - 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 -#else - u16 sllp; /* SLB page size encoding */ -#endif unsigned long vdso_base; -#ifdef CONFIG_PPC_SUBPAGE_PROT - struct subpage_prot_table spt; -#endif /* CONFIG_PPC_SUBPAGE_PROT */ /* * pagetable fragment support */ @@ -163,6 +141,60 @@ typedef struct { #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 */ diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index 138bc2ecc0c4..d45e4449619f 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -19,29 +19,7 @@ struct vmemmap_backing { }; extern struct vmemmap_backing *vmemmap_list; -/* - * Functions that deal with pagetables that could be at any level of - * the table need to be passed an "index_size" so they know how to - * handle allocation. For PTE pages (which are linked to a struct - * page for now, and drawn from the main get_free_pages() pool), the - * allocation size will be (2^index_size * sizeof(pointer)) and - * allocations are drawn from the kmem_cache in PGT_CACHE(index_size). - * - * The maximum index size needs to be big enough to allow any - * pagetable sizes we need, but small enough to fit in the low bits of - * any page table pointer. In other words all pagetables, even tiny - * ones, must be aligned to allow at least enough low 0 bits to - * contain this value. This value is also used as a mask, so it must - * be one less than a power of two. - */ -#define MAX_PGTABLE_INDEX_SIZE 0xf - -extern struct kmem_cache *pgtable_cache[]; -#define PGT_CACHE(shift) pgtable_cache[shift] - -extern pte_t *pte_fragment_alloc(struct mm_struct *, int); extern pmd_t *pmd_fragment_alloc(struct mm_struct *, unsigned long); -extern void pte_fragment_free(unsigned long *, int); extern void pmd_fragment_free(unsigned long *); extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift); #ifdef CONFIG_SMP @@ -81,6 +59,9 @@ static inline pgd_t *pgd_alloc(struct mm_struct *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 @@ -185,31 +166,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, *pmd = __pmd(__pgtable_ptr_val(pte_page) | PMD_VAL_BITS); } -static inline pgtable_t pmd_pgtable(pmd_t pmd) -{ - return (pgtable_t)pmd_page_vaddr(pmd); -} - -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) -{ - return (pte_t *)pte_fragment_alloc(mm, 1); -} - -static inline pgtable_t pte_alloc_one(struct mm_struct *mm) -{ - return (pgtable_t)pte_fragment_alloc(mm, 0); -} - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - pte_fragment_free((unsigned long *)pte, 1); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) -{ - pte_fragment_free((unsigned long *)ptepage, 0); -} - static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) { @@ -221,8 +177,6 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, pgtable_free_tlb(tlb, table, PTE_INDEX); } -#define check_pgt_cache() do { } while (0) - extern atomic_long_t direct_pages_count[MMU_PAGE_COUNT]; static inline void update_page_count(int psize, long count) { diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 581f91be9dd4..7dede2e34b70 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -277,9 +277,11 @@ extern unsigned long __vmalloc_end; extern unsigned long __kernel_virt_start; extern unsigned long __kernel_virt_size; extern unsigned long __kernel_io_start; +extern unsigned long __kernel_io_end; #define KERN_VIRT_START __kernel_virt_start -#define KERN_VIRT_SIZE __kernel_virt_size #define KERN_IO_START __kernel_io_start +#define KERN_IO_END __kernel_io_end + extern struct page *vmemmap; extern unsigned long ioremap_bot; extern unsigned long pci_io_base; @@ -296,8 +298,7 @@ extern unsigned long pci_io_base; #include <asm/barrier.h> /* - * The second half of the kernel virtual space is used for IO mappings, - * it's itself carved into the PIO region (ISA and PHB IO space) and + * 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 @@ -310,7 +311,7 @@ extern unsigned long pci_io_base; #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_END (KERN_VIRT_START + KERN_VIRT_SIZE) +#define IOREMAP_END (KERN_IO_END) /* Advertise special mapping type for AGP */ #define HAVE_PAGE_AGP @@ -992,7 +993,8 @@ extern struct page *pgd_page(pgd_t pgd); (((pte_t *) pmd_page_vaddr(*(dir))) + pte_index(addr)) #define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr)) -#define pte_unmap(pte) do { } while(0) + +static inline void pte_unmap(pte_t *pte) { } /* to find an entry in a kernel page-table-directory */ /* This now only contains the vmalloc pages */ diff --git a/arch/powerpc/include/asm/book3s/64/radix-4k.h b/arch/powerpc/include/asm/book3s/64/radix-4k.h index 863c3e8286fb..d5f5ab73dc7f 100644 --- a/arch/powerpc/include/asm/book3s/64/radix-4k.h +++ b/arch/powerpc/include/asm/book3s/64/radix-4k.h @@ -5,10 +5,11 @@ /* * For 4K page size supported index is 13/9/9/9 */ -#define RADIX_PTE_INDEX_SIZE 9 /* 2MB huge page */ -#define RADIX_PMD_INDEX_SIZE 9 /* 1G huge page */ -#define RADIX_PUD_INDEX_SIZE 9 -#define RADIX_PGD_INDEX_SIZE 13 +#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 per page */ diff --git a/arch/powerpc/include/asm/book3s/64/radix-64k.h b/arch/powerpc/include/asm/book3s/64/radix-64k.h index ccb78ca9d0c5..54e33828b0fb 100644 --- a/arch/powerpc/include/asm/book3s/64/radix-64k.h +++ b/arch/powerpc/include/asm/book3s/64/radix-64k.h @@ -5,10 +5,10 @@ /* * For 64K page size supported index is 13/9/9/5 */ -#define RADIX_PTE_INDEX_SIZE 5 /* 2MB huge page */ -#define RADIX_PMD_INDEX_SIZE 9 /* 1G huge page */ -#define RADIX_PUD_INDEX_SIZE 9 -#define RADIX_PGD_INDEX_SIZE 13 +#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 diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 5ab134eeed20..574eca33f893 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -72,19 +72,17 @@ * | | * | | * | | - * +------------------------------+ Kernel IO map end (0xc010000000000000) + * +------------------------------+ Kernel vmemmap end (0xc010000000000000) * | | + * | 512TB | * | | - * | 1/2 of virtual map | + * +------------------------------+ Kernel IO map end/vmemap start * | | + * | 512TB | * | | - * +------------------------------+ Kernel IO map start + * +------------------------------+ Kernel vmap end/ IO map start * | | - * | 1/4 of virtual map | - * | | - * +------------------------------+ Kernel vmemap start - * | | - * | 1/4 of virtual map | + * | 512TB | * | | * +------------------------------+ Kernel virt start (0xc008000000000000) * | | @@ -93,24 +91,24 @@ * +------------------------------+ Kernel linear (0xc.....) */ -#define RADIX_KERN_VIRT_START ASM_CONST(0xc008000000000000) -#define RADIX_KERN_VIRT_SIZE ASM_CONST(0x0008000000000000) - +#define RADIX_KERN_VIRT_START ASM_CONST(0xc008000000000000) /* - * The vmalloc space starts at the beginning of that region, and - * occupies a quarter of it on radix config. - * (we keep a quarter for the virtual memmap) + * 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_VIRT_SIZE >> 2) +#define RADIX_VMALLOC_SIZE RADIX_KERN_MAP_SIZE #define RADIX_VMALLOC_END (RADIX_VMALLOC_START + RADIX_VMALLOC_SIZE) -/* - * Defines the address of the vmemap area, in its own region on - * hash table CPUs. - */ -#define RADIX_VMEMMAP_BASE (RADIX_VMALLOC_END) -#define RADIX_KERN_IO_START (RADIX_KERN_VIRT_START + (RADIX_KERN_VIRT_SIZE >> 1)) +#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) diff --git a/arch/powerpc/include/asm/book3s/64/slice.h b/arch/powerpc/include/asm/book3s/64/slice.h index db0dedab65ee..f0d3194ba41b 100644 --- a/arch/powerpc/include/asm/book3s/64/slice.h +++ b/arch/powerpc/include/asm/book3s/64/slice.h @@ -2,8 +2,6 @@ #ifndef _ASM_POWERPC_BOOK3S_64_SLICE_H #define _ASM_POWERPC_BOOK3S_64_SLICE_H -#ifdef CONFIG_PPC_MM_SLICES - #define SLICE_LOW_SHIFT 28 #define SLICE_LOW_TOP (0x100000000ul) #define SLICE_NUM_LOW (SLICE_LOW_TOP >> SLICE_LOW_SHIFT) @@ -13,15 +11,6 @@ #define SLICE_NUM_HIGH (H_PGTABLE_RANGE >> SLICE_HIGH_SHIFT) #define GET_HIGH_SLICE_INDEX(addr) ((addr) >> SLICE_HIGH_SHIFT) -#else /* CONFIG_PPC_MM_SLICES */ - -#define get_slice_psize(mm, addr) ((mm)->context.user_psize) -#define slice_set_user_psize(mm, psize) \ -do { \ - (mm)->context.user_psize = (psize); \ - (mm)->context.sllp = SLB_VSID_USER | mmu_psize_defs[(psize)].sllp; \ -} while (0) - -#endif /* CONFIG_PPC_MM_SLICES */ +#define SLB_ADDR_LIMIT_DEFAULT DEFAULT_MAP_WINDOW_USER64 #endif /* _ASM_POWERPC_BOOK3S_64_SLICE_H */ |